TECHNIQUES FOR BEHAVIORAL PAIRING IN A CONTACT CENTER SYSTEM

专利摘要:
techniques for behavioral matching in a contact center system are revealed. in a specific modality, the techniques can be performed as a method for behavioral pairing in a contact center system, comprising: determining, by at least one computer processor communicatively coupled to and configured to operate in the contact center system, a plurality of agents available to connect with a contact; determining, at least one computer processor, a plurality of preferred contact-agent pairings among possible pairings between the contact and the plurality of agents; selecting at least one computer processor, one of the plurality of preferred contact-agent pairings according to a probabilistic model; and issue, at least one computer processor, the one selected from the plurality of preferred contact-agent pairings for connection in the contact center system.
公开号:BR112019022538A2
申请号:R112019022538-2
申请日:2018-04-05
公开日:2020-05-12
发明作者:Kan Ittai；Richard Klugerman Michael；Jay Riley Blake
申请人:Afiniti Europe Technologies Limited；
IPC主号:

专利说明:

TECHNIQUES FOR BEHAVIORAL PAIRING IN A CONTACT CENTER SYSTEM
CROSS REFERENCE FOR RELATED ORDERS
[001] This international patent application claims priority for US Patent Application No. 15 / 582,223, filed on April 28, 2017 and claims priority for US Patent Application No. 15 / 691,106, filed on August 30, 2017 2017, which is a continuation of U.S. Patent Application No. 15 / 582,223, filed on April 28, 2017, each of which is incorporated herein by reference in its entirety, as if it were fully established here.
FIELD OF DISSEMINATION
[002] This disclosure generally refers to the pairing of contacts and agents in contact centers and, more particularly, to techniques for behavioral pairing in a contact center system.
FUNDAMENTALS OF DISSEMINATION
[003] A typical contact center algorithmically assigns contacts arriving at the contact center to the agents available to handle those contacts. Sometimes, the contact center may have agents available and waiting to be assigned incoming or outgoing contacts (for example, phone calls, Internet chat sessions, e-mail). At other times, the contact center may have contacts waiting in one or more queues for an agent to be available for assignment.
[004] In some typical contact centers, contacts are assigned to requested agents based on time of arrival, and agents receive contacts sorted based on
Petition 870190140259, of 12/27/2019, p. 7/90
2/59 time that these agents were available. This strategy can be called the first in, first out, FIFO or round-robin strategy. In other typical contact centers, other strategies can be used, such as performance-based routing or a PBR strategy.
[005] In other more advanced contact centers, contacts are paired with agents using a behavioral pairing, or a BP strategy, under which contacts and agents can be deliberately (preferably) paired in a way that allows the assignment of peers contact agents so that when the benefits of all assignments in a BP strategy are totaled, they can exceed those of FIFO and other strategies, such as performance-based routing (PBR) strategies. BP was designed to encourage balanced use (or a degree of utilization bias) of agents in a skill queue while simultaneously improving the overall performance of the contact center beyond what the FIFO or PBR methods will allow. This is a notable achievement, as BP acts on the same calls and agents as the FIFO or PBR methods, uses agents approximately uniformly, as FIFO provides, and further improves the overall performance of the contact center. BP is described, for example, in U.S. Patent No. 9,300,802, which is incorporated herein by reference. Additional information about these and other resources related to the matching or matching modules (sometimes also called SATMAP, routing system, routing mechanism etc.) is described, for example, in the Patent of the
Petition 870190140259, of 12/27/2019, p. 8/90
3/59
USA 8,879,715, which is incorporated by reference here.
[006] A BP strategy can use a one-dimensional order of agents and contact types in conjunction with a diagonal strategy to determine preferred pairings. However, this strategy can restrict or otherwise limit the type and number of variables that a BP strategy could optimize, or the amount by which one or more variables could be optimized, with more degrees of freedom.
[007] In view of the above, it can be understood that there is a need for a system that allows improving the efficiency and performance of the pairing strategies that are designed to choose between several possible pairing, such as a BP strategy.
SUMMARY OF THE DISCLOSURE
[008] Techniques for behavioral matching in a contact center system are disclosed. In a specific modality, the techniques can be performed as a method for behavioral matching in a contact center system, comprising: determining, by at least one computer processor communicatively coupled to and configured to operate in the contact center system, a plurality of agents available to connect with a contact; determining, at least one computer processor, a plurality of preferred contact-agent pairings among possible pairings between the contact and the plurality of agents; selecting at least one computer processor, one of the plurality of preferred contact-agent pairings according to a probabilistic model; and issue at least one processor
Petition 870190140259, of 12/27/2019, p. 9/90
4/59 computer, the one selected from the plurality of preferred contact-agent pairings for connection in the contact center system.
[009] According to other aspects of this specific modality, the probabilistic model can be a network flow model to balance the use of agent, a network flow model to apply a quantity of agent usage slope, a model of network flow to optimize an overall expected value of at least one contact center metric. Additionally, at least one contact center metric can be at least one of revenue generation, customer satisfaction, and average time of operation.
[0010] According to other aspects of this specific modality, the probabilistic model can be a network flow model restricted by agent skills and contact skill needs. Additionally, the network flow model can be adjusted to minimize the imbalance of agent usage, according to the constraints of agent skills and the needs of contact skills.
[0011] In accordance with other aspects of this specific modality, the probabilistic model can incorporate the expected return values based on an analysis of at least one of historical contact-agent outcome data and contact attribute data.
[0012] In another specific modality, the techniques can be performed as a system for behavioral matching in a contact center system comprising at least one computer processor
Petition 870190140259, of 12/27/2019, p. 10/90
5/59 configured to operate on the contact center system, where at least one computer processor is configured to perform the steps in the method discussed above.
[0013] In another specific modality, the techniques can be performed as an article of manufacture for behavioral pairing in a contact center system comprising a medium readable by a non-transitory processor and instructions stored in the medium, where the instructions are configured to be readable from the middle by at least one computer processor configured to operate on the contact center system and thus have at least one computer processor operate to perform the steps in the method discussed above.
[0014] The present disclosure will now be described in more detail with reference to particular modalities thereof, as shown in the attached drawings. Although the present disclosure is described below with reference to particular modalities, it should be understood that the present disclosure is not limited to them. Those skilled in the art who have access to the teachings described herein will recognize additional implementations, modifications and modalities, as well as other fields of use, which are within the scope of the present disclosure, as described here, and in relation to which the present disclosure may be of significant utility.
BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to facilitate a more complete understanding of the present disclosure, reference is now made to the attached drawings, in which similar elements are referenced with similar numbers. These drawings should not be
Petition 870190140259, of 12/27/2019, p. 11/90
6/59 interpreted as limiting this disclosure, but are intended to be illustrative only.
[0016] Figure 1 shows a block diagram of a contact center according to the modalities of the present disclosure.
[0017] THE Figure 2 shows an example of an matrix of return from BP according to modalities gives gift disclosure. [0018] THE Figure 3 represents an example in a matrix
of using naive BP according to the modalities of this disclosure.
[0019] Figure 4A shows an example of a return matrix based on BP skill according to the modalities of the present disclosure.
[0020] Figure 4B shows an example of a BP network flow according to the modalities of the present disclosure.
[0021] Figure 4C shows an example of a BP network flow according to the modalities of the present disclosure.
[0022] Figure 4D shows an example of a BP network flow according to the modalities of the present disclosure.
[0023] Figure 4E shows an example of a BP network flow according to the modalities of the present disclosure.
[0024] Figure 4F shows an example of a BP network flow according to the modalities of the present disclosure.
[0025] Figure 4G shows an example of a BP network flow according to the modalities of the present disclosure.
[0026] Figure 5A represents an example of a return matrix based on BP skill according to the modalities of the present disclosure.
[0027] Figure 5B shows an example of a flow of
Petition 870190140259, of 12/27/2019, p. 12/90
7/59 BP network in accordance with the terms of the present disclosure.
[0028] Figure 5C shows an example of a BP network flow according to the modalities of the present disclosure.
[0029] Figure 5D shows an example of a BP network flow according to the modalities of the present disclosure.
[0030] Figure 5E shows an example of a BP network flow according to the modalities of the present disclosure.
[0031] Figure 5F shows an example of a BP network flow according to the modalities of the present disclosure.
[0032] Figure 5G shows an example of a BP network flow according to the modalities of the present disclosure.
[0033] Figure 5H shows an example of a BP network flow according to the modalities of the present disclosure.
[0034] Figure 51 shows an example of a BP network flow according to the modalities of the present disclosure.
[0035] Figure 6 represents a flowchart of a return matrix method based on BP skill according to the modalities of the present disclosure.
[0036] Figure 7A shows a flow chart of a BP network flow method according to the modalities of the present disclosure.
[0037] Figure 7B shows a flow chart of a BP network flow method according to the modalities of the present disclosure.
[0038] Figure 8 shows a flow chart of a BP network flow method according to the modalities of the present disclosure.
[0039] Figure 9 shows a flow chart of a BP network flow method according to the modalities of the present disclosure.
Petition 870190140259, of 12/27/2019, p. 13/90
8/59
DETAILED DESCRIPTION
[0040] A typical contact center algorithmically assigns contacts arriving at the contact center to the agents available to handle those contacts. Sometimes, the contact center may have agents available and waiting to be assigned incoming or outgoing contacts (for example, phone calls, Internet chat sessions, e-mail). At other times, the contact center may have contacts waiting in one or more queues for an agent to be available for assignment.
[0041] In some typical contact centers, contacts are assigned to requested agents based on time of arrival and agents receive requested contacts based on the time these agents were available. This strategy can be called the first in, first out, FIFO or round-robin strategy. In other typical contact centers, other strategies can be used, such as performance-based routing or a PBR strategy.
[0042] In other more advanced contact centers, contacts are paired with agents using a behavioral combination or a BP strategy, in which contacts and agents can be deliberately (preferably) paired in a way that allows the assignment of contact pairs - subsequent agent so that when the benefits of all BP strategy assignments are totaled, they can exceed those of FIFO and other strategies, such as performance-based routing (PBR) strategies. BP was designed to encourage balanced usage (or a degree of usage bias)
Petition 870190140259, of 12/27/2019, p. 14/90
9/59 of the agents in a skill queue, while simultaneously improving the overall performance of the contact center beyond what the FIFO or PBR methods will allow. This is a notable achievement because BP acts on the same calls and agents as the FIFO or PBR methods, uses agents approximately uniformly, as the FIFO provides, and further improves the overall performance of the contact center. BP is described, for example, in U.S. Patent No. 9,300,802, which is incorporated herein by reference. Additional information about these and other resources related to the matching or matching modules (sometimes also called SATMAP, routing system, routing mechanism, etc.) is described, for example, in U.S. Patent 8,879,715, which is incorporated by reference here.
[0043] A BP strategy can use a one-dimensional order of agents and contact types in conjunction with a diagonal strategy to determine preferred pairs. However, this strategy can restrict or limit the type and number of variables that a BP strategy could optimize or the amount by which one or more variables could be optimized, with more degrees of freedom.
[0044] In view of the above, it can be understood that there is a need for a system that allows improving the efficiency and performance of the pairing strategies that are designed to choose between several possible pairing, such as a BP strategy. Such a system can offer numerous benefits, including, in some modalities, optimization based on comparative advantages at runtime; maintenance of uniform use or
Petition 870190140259, of 12/27/2019, p. 15/90
Approximately uniform 10/59 of agents; consolidation of models between skills into a single coherent model or a smaller number of coherent models; creation of more complex, sophisticated and capable models; etc. As described in detail below, the techniques can be multidimensional (for example, multivariate) in nature, and can use linear programming, quadratic programming or other optimization techniques to determine preferred contact-agent pairings. Examples of these techniques are described, for example, in Cormen et al., Introduction to Algorithms, 3rd ed., 708-68 and 843-897 (Ch. 26. Maximum Flow and Ch. 29 Linear Programming) (2009) and Nocedal and Wright, Numerical Optimization, at 448-96 (2006), which are hereby incorporated by reference in this document.
[0045] Figure 1 shows a block diagram of a contact center system 100 according to the modalities of the present disclosure. The description described here describes network elements, computers and / or components of a system and method for simulating contact center systems that can include one or more modules. As used in this document, the term module can be understood as referring to computing software, firmware, hardware and / or various combinations thereof. The modules, however, should not be interpreted as software that is not implemented in hardware, firmware or written to a processor-readable recordable storage medium (that is, the modules are not software in themselves). Note that the modules are exemplary. The modules can be combined, integrated, separated and / or duplicated to support various applications. In addition, a function described here as being executed in a module
Petition 870190140259, of 12/27/2019, p. 16/90
11/59 can be performed on one or more other modules and / or by one or more other devices, instead of or in addition to the function performed on the specific module. In addition, the modules can be implemented in various devices and / or other local or remote components among themselves. In addition, the modules can be moved from one device and added to another device and / or can be included in both devices.
[0046] As shown in Figure 1, contact center system 100 can include a central switch 110. Central switch 110 can receive incoming contacts (for example, callers) or support outgoing connections for contacts over a network. telecommunications (not shown). Central switch 110 may include contact routing hardware and software to help route contacts between one or more contact centers, or to one or more PBX / ACDs or other queuing or switching components, including other contact center based solutions on the Internet, cloud-based or based on hardware or otherwise agent-contact software networked.
[0047] Central switch 110 may not be necessary, as if there is only one contact center, or if there is only one PBX / ACD routing component, in contact center system 100. If more than one contact center is part of of the contact center system 100, each contact center can include at least one contact center switch (for example, contact center switches 120A and 120B). Contact center switches 120A and 120B can be communicatively coupled to the
Petition 870190140259, of 12/27/2019, p. 17/90
12/59 central switch 110. In the modalities, several routing topologies and network components can be configured to implement the contact center system.
[0048] Each contact center switch for each contact center can be communicatively coupled to a plurality (or grouping) of agents. Each contact center switch can support a number of agents (or seats) to be registered at one time. At any time, a registered agent may be available and waiting to be connected to a contact, or the registered agent may be unavailable for a variety of reasons, such as being connected to another contact, performing certain post-call functions, such as registration information about the call, or take a break.
[0049] In the example in Figure 1, central switch 110 routes the contacts to one of two contact centers via contact center switch 120A and contact center switch 120B, respectively. Each of the 120A and 120B contact center switches is shown with two agents each. Agents 130A and 130B can be registered to the contact center switch 120A, and agents 130C and 130D can be registered to the contact center switch 120B.
[0050] The contact center system 100 can also be coupled communicatively to an integrated service from, for example, a third party supplier. In the example in Figure 1, the BP module 140 can be communicatively coupled to one or more switches in the switching system of the contact center system 100, such as central switch 110, contact center switch 120A or switch
Petition 870190140259, of 12/27/2019, p. 18/90
13/59 120B contact center. In some embodiments, the switches of the contact center system 100 can be communicatively coupled to multiple BP modules. In some embodiments, the BP 140 module can be incorporated within a component of a contact center system (for example, incorporated or otherwise integrated into a switch or a BP switch). The BP 140 module can receive information from a switch (for example, contact center switch 120A) about agents registered to the switch (for example, agents 130A and 130B) and about incoming contacts via another switch (for example , central switch 110) or, in some embodiments, from a network (for example, the Internet or a telecommunications network) (not shown).
[0051] A contact center can include multiple pairing modules (for example, a BP module and a FIFO module) (not shown), and one or more pairing modules can be supplied by one or more different suppliers. In some embodiments, one or more pairing modules can be components of the BP 140 module or one or more switches, such as the central switch 110 or the contact center switches 120A and 120B. In some modalities, a BP module can determine which pairing module can handle pairing for a specific contact. For example, the BP module can switch between enabling pairing via the BP module and enabling pairing with the FIFO module. In other modalities, a pairing module (for example, the BP module) can be configured to emulate other pairing strategies. For example, a BP module, or a BP component
Petition 870190140259, of 12/27/2019, p. 19/90
14/59 integrated with the BP components in the BP module, it can determine whether the BP module can use BP pairing or emulated FIFO pairing for a specific contact. In this case, BP on may refer to times when the BP module is applying the BP pairing strategy, and BP off may refer to other times when the BP module is applying a different pairing strategy (for example , FIFO).
[0052] In some modalities, regardless of whether the pairing strategies are handled by separate modules, or if some pairing strategies are emulated in a single pairing module, the single pairing module can be configured to monitor and store information about pairing done under any or all of the matching strategies. For example, a BP module can observe and record data about FIFO pairings made by a FIFO module, or the BP module can observe and record data about emulated FIFO pairings made by a BP module operating in FIFO emulation mode.
[0053] Figure 2 shows an example of a BP 200 return matrix according to the modalities of the present disclosure. In this simplified and hypothetical computer-generated model of a contact center system, there are three agents (Agents 201, 202 and 203), and three types of contacts (Contact Types 211, 212 and 213). Each cell in the matrix indicates the return, either the expected result or the expected value of a contact-agent interaction between a particular agent and an indicated contact type contact. In real-world contact center systems, there may be
Petition 870190140259, of 12/27/2019, p. 20/90
15/59 dozens of agents, hundreds of agents or more, and there can be dozens of contact types, hundreds of contact types or more.
[0054] In the BP 200 return matrix, the return for an interaction between Agent 201 and a contact of Contact Type 211 is 0.30 or 30%. The other returns for Agent 201 are 0.28 for Contact Type 212 and 0.15 for Contact Type 213. Returns for Agent 202 are 0.30 for Contact Type 211, 0.24 for Contact Type 212 and 0.10 for Contact Type 213. Returns for Agent 203 are 0.25 for Contact Type 211, 0.20 for Contact Type 212 and 0.09 for Contact Type 213 .
[0055] A return can represent the expected value for a variety of different metrics or optimized variables. Examples of optimized variables include conversion rates to sales, customer retention rates, customer satisfaction rates, measurements of average operating time, etc. or combinations of two or more metrics. For example, if the BP 200 return matrix models a hold queue in a contact center system, each return can represent the possibility for an agent to save or retain a customer of a specific contact type, for example, there is 0 , 30 (or 30%) chance that Agent 201 will save a given contact as Contact Type 211.
[0056] In some embodiments, the BP 200 return matrix or other similar computer-generated model of the contact center system can be generated using historical contact-agent interaction data. For example, the BP 200 return matrix can incorporate a rolling window of several weeks, several months, several years, etc. in
Petition 870190140259, of 12/27/2019, p. 21/90
16/59 historical data to predict or otherwise estimate the returns for a given interaction between an agent and a type of contact. As the agent workforce changes, the model can be updated to reflect changes in the agent workforce, including hiring new agents, releasing existing agents, or training existing agents in new skills. Contact types can be generated based on information about expected contacts and existing customers, such as customer relationship management (CRM) data, customer attribute data, third party consumer data, contact center data, etc., which they can include various types of data, such as demographic and psychographic data, and behavioral data, such as past purchases or other historical customer information. The BP 200 return matrix can be updated in real time or periodically, such as hourly, nightly, weekly, etc. to incorporate new contact-agent interaction data as it becomes available.
[0057] Figure 3 represents an example of a matrix of using BP naive 300 according to the modalities of the present disclosure. As for the BP 200 return matrix (Figure 2), this simplified and computer generated hypothetical model of a contact center system, there are three agents (Agents 201, 202 and 203) and there are three types of contact (Contact Types 211, 212 and 213). In real-world contact center systems, there can be dozens of agents, hundreds of agents or more, and there can be dozens of contact types, hundreds of contact types or more.
[0058] Under a BP strategy, agents are
Petition 870190140259, of 12/27/2019, p. 22/90
17/59 preferably paired with contacts of particular contact types, according to the BP models generated by computer. In a Ll environment, the contact queue is empty, and several agents are available, idle, or otherwise ready and waiting to connect to a contact. For example, in a chat context, an agent may have the ability to chat with multiple contacts simultaneously. In these environments, an agent can be ready to connect with one or more additional contacts while multitasking on one or more other channels, such as email and chat simultaneously.
[0059] In some modalities, when a contact arrives in the queue or another component of the contact center system, the BP strategy analyzes information about the contact to determine the type of contact (for example, a contact of Type 211 contact, 212 or 213). The BP strategy determines which agents are available to connect with the contact and selects, recommends or otherwise issues a pairing instruction for the most preferred available agent.
[0060] In an L2 environment, multiple contacts are waiting in line to connect with an agent and none of them are available, free or otherwise ready to connect to a contact. The BP strategy analyzes information about each contact to determine the type of each contact (for example, one or contacts from Contact Types 211, 212 or 213). In some modalities, when an agent becomes available, the BP strategy determines which contacts are available to connect with the agent and selects, recommends or otherwise issues a pairing instruction to the agent.
Petition 870190140259, of 12/27/2019, p. 23/90
18/59 most preferred contact available.
[0061] As shown in the header line of the BP naive 300 usage matrix, each agent has an expected availability or a target use. In this example, the BP strategy is aimed at a balanced use of 1/3 (0.33) for each of the three Agents 201, 202 and 203. Thus, over time, it is expected that each agent will be used equally, or roughly equally. This BP configuration is similar to FIFO, in that both BP and FIFO aim at an impartial or balanced use of the agent.
[0062] This BP configuration is different from performance-based routing (PBR), in that PBR aims at an inclined or unbalanced agent use, intentionally assigning a disproportionate number of contacts to relatively superior performance agents. Other BP configurations may be similar to PBR configurations, in that other BP configurations may also target an inclined agent use. Additional information on these and other resources relating to agent tilt or contact usage (for example, kappa and rho functionality) is described in, for example, U.S. Patent Application Nos. 14 / 956,086 and 14 / 956,074, which are incorporated herein by reference.
[0063] As shown in the header column of the BP naive 300 usage matrix, each type of contact has an expected availability (eg arrival frequency) or a target usage. In this example, Contact Type 211 contacts are expected to reach 50% (0.50) of the time, Contact Type 212 contacts to reach 30%
Petition 870190140259, of 12/27/2019, p. 24/90
19/59 (0.30) of the time, and the Contact Type 212 contacts reach the remaining 20% (0.20) of the time.
[0064] Each cell in the matrix indicates the target use, or expected frequency, of a contact-agent interaction between a particular agent and a contact of the type of contact indicated. In the example of the BP naive 300 usage matrix, agents are expected to be assigned equally to each type of contact according to each frequency of the type of contact. Contact Type 211 contacts are expected to reach the queue 50% of the time, with approximately one third of these contacts assigned to each of Agents 201, 202 and 203. Overall, interactions between contacts and agents between the Contact Type 211 and Agent 201 are expected to occur approximately 16% (0.16) of the time, between Contact Type 211 and Agent 202 approximately 16% of the time, and between Contact Type 211 and Agent 203 approximately 16% of time. Likewise, interactions between Contact Type 212 contacts (30% frequency) and each of 201203 Agents are expected to occur approximately 10% (0.01) of the time each, and interactions between Type of Contact 213 (20% frequency) and each Agent 201-203 occurs, approximately 7% (0.07) of the time.
[0065] The BP naive 300 usage matrix also represents approximately the same distribution of contact-agent interactions that would arise under a FIFO matching strategy, under which each contact agent interaction would be equally likely (normalized to the frequency of each type) contact details). Under BP naive and FIFO, the targeted (and expected) use of each agent is the same:
Petition 870190140259, of 12/27/2019, p. 25/90
20/59 one third of contact-agent interactions with each of the three agents 201-203.
[0066] Together, the BP 200 return matrix (Figure 2) and the BP naive 300 utilization matrix allow to determine an expected general performance of the contact center system, calculating a weighted average return according to the distribution of frequency of each contact-agent interaction shown in the BP naive 300 usage matrix: (0.30 + 0.30 + 0.25) (0.50) (1/3) + (0.28 + 0.24 + 0.20) (0.30) (1/3) + (0.15 + 0.10 + 0.09) (0.20) (1/3) «0.24. Thus, the expected performance of the contact center system under BP naive and FIFO is approximately 0.24 or 24%. If returns represent, for example, retention rates, the overall expected performance would have a savings rate of 24%.
[0067] Figures 4A - 4G show an example of a more sophisticated BP return matrix and network flow. In this simplified hypothetical contact center, agents or types of contact may have different combinations of one or more skills (i.e., skill sets), and network flow optimization techniques based on linear programming can be applied to increase overall performance. contact center, maintaining a balance of use between agents and contacts.
[0068] Figure 4A shows an example of a skill-based return matrix of BP 400A according to the modalities of the present disclosure. The hypothetical contact center system represented in the BP 400A skill-based return matrix is similar to the contact center system represented in the BP 200 return matrix (Figure 2), in that there are three agents (Agents
Petition 870190140259, of 12/27/2019, p. 26/90
21/59
401, 402 and 403) having an expected availability / utilization of approximately one third or 0.33 each, and there are three types of contact (Contact Types 411, 412 and 413) with an expected frequency / utilization of approximately 25% (0, 15 + 0.10), 45% (0.15 + 0.30) and 30% (0.20 + 0.10), respectively.
[0069] However, in the present example, each agent was assigned, trained or otherwise made available to a specific skill (or, in another example, contact center systems, multiple skill sets). Examples of skills include broad skills, such as technical support, billing support, sales, retention, etc .; language skills such as English, Spanish, French, etc .; more restricted skills, such as Level 2 advanced technical support, technical support for Apple iPhone users, technical support for Google Android users, etc .; and any variety of other skills.
[0070] Agent 401 is available for contacts that require at least Skill 421, Agent 402 is available for contacts that require at least Skill 422 and Agent 403 is available for contacts that require at least Skill 423.
[0071] Also in the present example, contacts of each type can arrive, requiring one or more of Skills 421423. For example, a call center caller can interact with an Interactive Voice Response (IVR) system, toga menu by tone, or live operator to determine what skills the specific caller / contact requires for future interaction. Another way to consider a contact type skill is a need
Petition 870190140259, of 12/27/2019, p. 27/90
22/59 contact details, such as buying something from an agent with a sales skill or solving a technical problem with an agent with a technical support skill.
[0072] In the present example, it is expected that 0.15 or 15% of the contacts are of Contact Type 411 and require Skill 421 or Skill 422; it is expected that 0.15 or 15% of the contacts must be Contact Type 412 and require Skill 421 or 422; it is expected that 0.20 or 20% of contacts must be Contact Type 413 and require Skill 421 or 422; 0.10 or 10% of contacts are expected to be Contact Type 411 and require Skill 422 or Skill 423; 0.30 or 30% of contacts are expected to be Contact Type 412 and require Skill 422 or Skill 423; 10 or 10% of contacts are expected to be Contact Type 413 and require Skill 422 or Skill 423.
[0073] In some modalities, agents may need to combine all the skills determined by a specific contact (for example, Spanish language skills and iPhone technical support skills). In some embodiments, some skills may be preferred, but not required (that is, if no agent with the iPhone technical support skill is available immediately or within a threshold amount of time, a contact can be paired with an agent. Android technical support available).
[0074] Each cell in the matrix indicates the return of a contact-agent interaction between a particular agent with a particular skill or particular skill set and a contact with a type and need (skill) or set of needs (set of
Petition 870190140259, of 12/27/2019, p. 28/90
Skills). In the present example, Agent 401, which has Skill 421, can be paired with contacts of any Type of Contact 411, 412 or 413 when they require at least Skill 421 (with returns of 0.30, 0.28 and 0 , 15, respectively). Agent 402, which has Skill 422, can be paired with contacts of any Contact Type 411, 412 or 413 when they require at least Skill 422 (with returns of 0.30, 0.24, 0.10, 0 , 30, 0.24 and 0.10, respectively). Agent 403, which has Skill 423, can be paired with contacts of any Type of Contact 411, 412 or 413 when they require at least Skill 423 (with returns of 0.25, 0.20 and 0.9, respectively ).
[0075] The empty cells represent combinations of contacts and agents that would not be paired under this BP pairing strategy. For example, Agent 401, which has Skill 421, would not be paired with contacts that do not require at least Skill 421. In the present example, the 18 cell return matrix includes 6 empty cells, and the 12 non-empty cells represent 12 possible pairings.
[0076] Figure 4B shows an example of a BP 400B network flow according to the modalities of the present disclosure. The BP 400B network flow shows Agents 401-403 as sources on the left side of the network (or graph) and Contact Types 411-413 for each skill set as consumers on the right side of the network. Each edge in the BP 400B network flow represents a possible pairing between an agent and a contact having a particular type and set of needs (skills).
Petition 870190140259, of 12/27/2019, p. 29/90
24/59
For example, edge 401A represents a contact-agent interaction between Agent 401 and Contact Type 411 contacts that require Skill 421 or Skill 422. Edges 401B, 401C, 402A-F and 403A-C represent other possible contact-agent pairings for their respective types and skills of agents and contacts, as shown.
[0077] Figure 4C shows an example of a BP 400C network flow according to the modalities of the present disclosure. The BP 400C network flow is a network / graph representation of the BP 400A return matrix (Figure 4A). The BP 400C network flow is identical to the BP 400B network flow (Figure 4B), except, for clarity, the identifiers of each edge are not shown and instead shows the return of each edge, for example , 0.30 at edge 401A, 0.28 at edge 401B and 0.15 at edge 401C for Agent 401, and the corresponding returns for each edge for Agents 402 and 403.
[0078] Figure 4D shows an example of a BP 400D network flow according to the modalities of the present disclosure. The BP 400D network flow is identical to the BP 400C network flow (Figure 4C), except for the sake of clarity, the abilities of each Agent 401-403 are not shown and instead shows the relative offers provided by each agent and the demands demanded by each contact type / skill combination. Each agent provides an offer equivalent to the expected availability or target use of each agent (one third each, for a total offer of 1 or 100%). Each type / skill of contact requires an amount of agent offer equivalent to
Petition 870190140259, of 12/27/2019, p. 30/90
25/59 expected frequency or target use of each type / ability of contact (0.15, 0.15, 0.20, 0.10, 0.30, 0.10, respectively, for a total demand of 1 or 100 %). In this example, supply and total demand are normalized or otherwise set to match, and the capacity or bandwidth along each edge is considered to be infinite or unlimited (that is, an edge can describe who can be paired with who, not how much or how many times). In other modalities, there may be an imbalance of supply / demand, or there may be limited quotas or capacities defined for some or all edges.
[0079] Figure 4E shows an example of a BP 400E network flow according to the modalities of the present disclosure. The BP 400E network flow is identical to the BP 400D network flow (Figure 4D), except to facilitate representation, the offers and demands were scaled by a factor of 3000. When doing this, the offer for each agent is shown like 1000 instead of a third, and the total supply is shown to be 3000. Likewise, the relative demands for each type of contact skill / set have been dimensioned and the total 3000 as well. In some embodiments, no scaling occurs. In other modalities, the amount of dimensioning may vary and be greater or less than 3000.
[0080] Figure 4F shows an example of a BP 400F network flow according to the modalities of the present disclosure. The BP 400F network flow is identical to the BP 400E network flow (Figure 4E), except, for clarity, returns along each edge are not shown and, in
Petition 870190140259, of 12/27/2019, p. 31/90
26/59 instead, it shows a solution for the BP 400F network flow. In some embodiments, a maximum flow or max flow algorithm, or another linear programming algorithm, can be applied to the BP 400F network flow to determine one or more solutions to optimize the flow or allocation of offers (sources) to meet demands (consumers), which can balance the use of agents and contacts.
[0081] In some modalities, the objective can also be to maximize the global expected value for the metric or metrics to be optimized. For example, in a sales queue, the metric to optimize may be the conversion rate, and the goal of maximum flow is to maximize the overall expected conversion rate. In environments where multiple maximum flow solutions are available, one technique for selecting a solution may be to select the maximum cost or max cost solution, that is, the solution that results in the highest global returns under maximum flow.
[0082] In this example, Agents 401-403 represent sources, and Contact Types 411-413 with various combinations of skill sets represent consumers. In some contact center environments, such as an L2 (excess contact) environment, the network flow can be reversed, so the contacts waiting in the queue are the sources that provide offers, and the possible agents that can become available are the consumers who supply demands.
[0083] The BP 400F network flow shows an optimal flow solution determined by a BP module or similar component. According to this solution, among which there may be several to choose or randomly select, the
Petition 870190140259, of 12/27/2019, p. 32/90
27/59 edge 401A (from Agent 401 to Contact Type 411 with Skills 421 and 422) has an optimal flow of 0; edge 401B (from Agent 401 to Contact Type 412 with Skills 421 and 422) has an optimal flow of 400; and edge 401C (from Agent 401 to Contact Type 413 with Skills 421 and 422) has an optimum flow of 600. Likewise, the optimum flows for Agent 402A - F edges are 450, 50, 0 , 300, 200 and 0, respectively; and the optimal flows for the 403A - C edges for Agent 403 are 0, 700 and 300, respectively. As explained in detail below, this optimal flow solution describes the relative proportion of contact-agent interactions (or the relative possibilities of selecting specific contact-agent interactions) that will achieve the target use of agents and contacts, while maximizing overall performance expected from the contact center system according to the returns of each agent pair and contact type / skill set.
[0084] Figure 4G shows an example of a BP 400G network flow according to the modalities of the present disclosure. The BP 400G network flow is identical to the BP 400F network flow (Figure 4F), except, for clarity, the edges for which the optimal flow solution was determined to be 0 have been removed. According to a BP strategy, an agent will preferably not be associated with a type of contact for which the optimal flow solution was determined to be 0, despite having complementary skills and a non-zero return.
[0085] In this example, edges 401A, 402C, 402F and 403A have been removed. The remaining edges represent
Petition 870190140259, of 12/27/2019, p. 33/90
28/59 preferred pairings. Thus, in a LI (surplus agent) environment, when a contact arrives, it can preferably be paired with one of the agents for which yours is a preferred pairing available. For example, a Contact Type 411 contact with Skills 421 and 422 can always be paired preferentially with Agent 402, requiring 450 units of Agent 402's total offer (availability). For another example, a Contact Type 412 contact with Skills 421 and 422 it can preferably be paired with Agent 401 part of the time and with Agent 402 part of the time. This contact has a total demand of 450 (based on the expected frequency that this type / contact skill will arrive) and requires 400 Agent 401 offering units and the remaining 50 Agent 402 offering units.
[0086] In some modalities, when this type / skill contact arrives, the BP module or similar component can select Agent 401 or 402 according to the relative demands (400 and 50) made by each agent. For example, a pseudo-random number generator can be used to select Agent 401 or 402 at random, with random selection weighted according to relative demands. Thus, for each contact of this type / skill, there is a 400/450 («89%) chance of selecting Agent 401 as the preferred match and a 50/450 (« 11%) chance of selecting Agent 402 as the match. preferred. Over time, as many contacts of this type / skill have been paired using the BP strategy, approximately 89% of them may have been preferably paired with Agent 401 and the remaining 11% may have been preferably paired with Agent 402. In some modalities , general use
Petition 870190140259, of 12/27/2019, p. 34/90
29/59 target of an agent or target use by type / skill of contact, it can be the bandwidth of the agent to receive a proportional percentage of contacts.
[0087] For this BP 400G network flow with this solution, it is expected that the total supply of all agents will meet the total demand of all contacts. Thus, the target utilization (here, a balanced utilization) of all agents can be achieved, in addition to achieving a higher overall expected performance in the contact center system according to the returns and the relative allocations of agents to contacts over edges with these returns.
[0088] Figures 5A - I show an example of another BP return matrix and network flow. For some agent configurations and contact types with various skill combinations, it is possible that the optimal or maximum flow for a given BP network flow may not completely balance supply and demand. The present example is similar to the example in Figures 4A - 4G, except that this configuration of agents and types of contact initially leads to an unbalanced supply and demand. In this hypothetical and simplified contact center, quadratic programming-based techniques to adjust the target utilization can be applied in conjunction with network flow optimization techniques based on linear programming to increase the performance of the general contact center, while maintaining an optimal use tilted between agents and contacts to accommodate the unbalanced configuration of agents and contact types.
[0089] Figure 5A represents an example of a skill-based return matrix of BP 500A according to
Petition 870190140259, of 12/27/2019, p. 35/90
30/59 with the modalities of this disclosure. The hypothetical contact center system represented in the skill-based return matrix of BP 500A is similar to the contact center system represented in the skill-based return matrix of BP 400A (Figure 4), in that there are three agents ( Agents 501, 502 and 503) having an expected initial availability / use of approximately one third or 0.33 each. There are two types of contact (Contact Types 511 and 512) having an expected frequency / use of approximately 40% (0.30 + 0.10) and 60% (0.30 + 0.30), respectively.
[0090] In the present example, Agent 501 was assigned, trained or otherwise made available for Skills 521 and 522, and Agents 502 and 503 only for Skill 522. For example, if Skill 521 represented a skill in the French language and Skill 522 represented a skill in the German language, Agent 501 could be assigned to contacts requiring either French or German, while Agents 502 and 503 could be assigned only to contacts requiring German and not to contacts requiring French.
[0091] In the present example, it is expected that 0.30 or 30% of the contacts are of Contact Type 511 and require Skill 521; 0.30 or 30% of contacts are expected to be Contact Type 512 and require Skill 521; 0.10 or 10% of contacts are of Contact Type 511 and require Skill 522; and 0.30 or 30% of contacts must be Contact Type 512 and require Skill 522.
[0092] In the present example, Agent 501 can be paired with any contact (with returns of 0.30, 0.28,
Petition 870190140259, of 12/27/2019, p. 36/90
31/59
0.30 and 0.28, as shown in the skill-based return matrix of BP 500A). Agents 502 and 503, which only have Skill 522, can be paired with contacts of Contact Type 511 and 512 when they require at least Skill 522 (with returns of 0.30, 0.24, 0.25 and 0, 20, as shown in the skill-based return matrix of BP 500A). As indicated by the empty cells in the BP 500A skill-based feedback matrix, Agents 502 and 503 would not be paired with contacts requiring only Skill 521. The 12-cell feedback matrix includes 4 empty cells and the 8 non-empty cells represent 8 possible pairings.
[0093] Figure 5B shows an example of a BP 500B network flow according to the modalities of the present disclosure. Similar to the BP 400B network flow (Figure 4B), the BP 500B network flow shows Agents 501-503 as sources on the left side of the network and Contact Types 512 and 5123 for each skill set as consumers on the side right of the network. Each edge in the BP 500B network flow represents a possible match between an agent and a contact with a particular type and set of needs (skills). Edges 501A - D, 502A B and 503A - B represent the possible contactings of the agent for their respective agents and types / skills of contact, as shown.
[0094] Figure 5C shows an example of a BP 500C network flow according to the modalities of the present disclosure. The BP 500C network flow is a network representation of the BP 500A return matrix (Figure 5A). For clarity, the identifiers for each edge are not
Petition 870190140259, of 12/27/2019, p. 37/90
32/59 shown and instead show the return of each edge, for example, 0.30 at edges 501A and 501D and 0.28 at edges 501B and 501C and the corresponding returns for each edge for Agents 502 and 503.
[0095] Figure 5D shows an example of a BP 500D network flow according to the modalities of the present disclosure. The BP 500D network flow shows the relative initial offers provided by each agent and demands demanded by each contact type / skill combination. The total supply of 1 is equal to the total supply of 1.
[0096] Figure 5E shows an example of a BP 500E network flow according to the modalities of the present disclosure. To facilitate representation, the offers and demands were dimensioned by a factor of 3000, and a maximum flow solution for the initial offers is shown for each edge. According to this solution, edge 501A (from Agent 501 for Contact Type 511 with Skill 521) has an optimum flow of 900; edge 501B (from Agent 501 for Contact Type 512 with Skill 521) has an optimum flow of 100; and edges 501C and 501D have optimal flows of 0. Likewise, the optimal flows for Agent 502 are 300 and 700, respectively; and the optimal flows for Agent 503 are 0 and 200, respectively.
[0097] Under this solution, Agent 503 can be substantially underutilized in relation to Agents 501 and 502. While Agents 501 and 502 are optimized for their complete offering of 1000 units each, Agent 503 is expected to use only 200 units, or a fifth of Agent 503's offering. In a contact center environment, Agent 503 can be assigned to fewer contacts and spends more idle time on
Petition 870190140259, of 12/27/2019, p. 38/90
33/59 with respect to Agents 501 and 502, or agents can be assigned to non-preferred contacts, resulting in lower contact center performance than the performance predicted by the maximum flow solution.
[0098] Likewise, according to this solution, contacts of Contact Type 512 that require Skill 521 can be substantially underutilized (or underserved) in relation to other contact type / ability combinations. While the other contact type / skill combinations are optimized for your complete demands of 900, 300 and 900 units, respectively, Contact Type 512 requiring Skill 521 is expected to receive only 100 units, or a ninth of that demand for contact type / ability. In a contact center environment, this underused contact type / skill combination can experience longer wait times compared to other contact type / skill combinations, or contacts can be assigned to non-preferred agents, resulting in performance contact center lower than the performance predicted by the maximum flow solution.
[0099] The solution shown in the BP 500E network flow still balances total supply and demand, but Agent 503 may be selected much less often than its peers, and / or some contacts may need to wait much longer for a preferred agent, and / or the performance of the general contact center may not achieve the overall return expected by the maximum flow solution.
[00100] Figures 5F and 5G show a technique of some modalities for adjusting agent offers
Petition 870190140259, of 12/27/2019, p. 39/90
34/59 relative to improve the balance of agent and contact utilization in a contact center system where the maximum flow solution is unbalanced, as in the BP 500E network flow (Figure 5E).
[00101] Figure 5F shows an example of a BP 500F network flow according to the modalities of the present disclosure. In the BP 500F network flow, agents who share the same skill sets have been collapsed into a single network node. In this example, the Agent
502 and Agent 503 were combined into a single Skill 522 node with a combined total offering of 2000.
[00102] Likewise, contact types that share the same skill sets have been collapsed into single network nodes. In this example, Contact Types 511 and 512 requiring Skill 521 have been combined into a single node for Skill 521 with a combined total demand of 1800, and Contact Types 511 and 512 requiring Skill 522 have been combined into a single Skill 522 node with a combined total demand of 1200.
[00103] Additionally, the edges were collapsed. For example, the four edges emanating from Agents 502 and
503 (edges 502A, 502B, 503A and 503B, as labeled in Figure 5B) were collapsed into a single edge emanating from the super node for agents with Skill 522 to the super node for contact types that require Skill 522.
[00104] At this point, in some modalities, a quadratic programming algorithm or similar technique can be applied to the collapsed network to adjust the relative offers of the agents.
[00105] Figure 5G shows an example of a flow of
Petition 870190140259, of 12/27/2019, p. 40/90
35/59 BP 500G network in accordance with the terms of the present disclosure. The BP 500G network flow shows the agent offer adjusted according to a solution for a quadratic programming algorithm or similar technique. In this example, the offer for the agent's super node for skills 521 and 522 has been adjusted from 1000 in the BP 500F network flow (Figure 5F) to 1800, and the offer for the agent's super node for Skill 522 has been adjusted. from 2000 on the BP 500F to 1200 network flow.
[00106] The total supply may remain the same (for example, 3000 in this example), but the relative supply of agents of various skill sets has been adjusted. In some modalities, the total supply of a single super node can be distributed equally among the agents within the super node. In this example, the 1200 offer units for the Skill 522 agent super node were divided evenly between agents, allocating 600 units for each of Agents 502 and 503.
[00107] Figure 5H shows an example of a BP 500H network flow according to the modalities of the present disclosure. The BP 500H network flow shows a maximum flow solution calculated using the adjusted offers shown in the BP 500G network flow (Figure 5G). Agent 501 has an adjusted offer of 1800, Agent 502 has an adjusted offer of 600 and Agent 503 has an adjusted offer of 600. According to this solution, edge 501A (from Agent 501 for the Contact Type 511 with Skill 521) still has an optimal flow of 900; edge 501B (from Agent 501 to Contact Type 512 with Skill 521) now has an optimum flow of 900; and edges 501C and 501D
Petition 870190140259, of 12/27/2019, p. 41/90
36/59 still have optimal flows of 0. Likewise, the optimal flows for Agent 502 are now 300 and 300 each; and the optimal flows for Agent 503 are now 0 and 600, respectively.
[00108] Figure 51 shows an example of a BP 5001 network flow according to the modalities of the present disclosure. The BP 5001 network flow is identical to the BP 500H network flow, except for the sake of clarity, the edges for which the optimal flow solution has been determined to be 0 have been removed. In this example, edges 501C, 501D and 503A have been removed.
[00109] Using the solution shown in the BP 500H and 5001 network flows, all contact type / ability combinations can now be fully utilized (fully serviced).
[00110] Additionally, the use of general agents can become more balanced. Under the BP 500E network flow (Figure 5E), Agent 503 may have been used by only one fifth as Agents 501 and 502. Thus, Agents 501 and 502 would receive approximately 45% of contacts each, while Agent 503 approximately 10% of the contacts would be assigned only to the rest. Under the BP 500H network flow, Agent 501 can be assigned to approximately 60% of the contacts, and Agents 502 and 503 can be assigned to approximately 20% of each of the remaining contacts. In this example, the busiest agent (Agent 501) would receive only three times as many contacts as the least busy agents (Agents 502 and 503), instead of receiving five times as many contacts.
[00111] Figure 6 represents a flow chart of a
Petition 870190140259, of 12/27/2019, p. 42/90
37/59 BP 600 skill-based return matrix method, according to the modalities of this disclosure. The BP 600 skill-based return matrix method can start at block 610.
[00112] In block 610, historical data of contact agent results can be analyzed. In some modalities, a rolling window of historical data of contact-agent results can be analyzed, such as a window of a week, a month, ninety days or a year. Historical contact agent outcome data can include information about individual interactions between a contact and an agent, including identifiers of which agent communicated with which contact, when the communication occurred, the duration of the communication, and the result of the communication. For example, at a telesales call center, the result can indicate whether a sale has taken place or the dollar value of a sale, if any. In a customer retention queue, the result can indicate whether a customer has been retained (or saved) or the dollar value of any incentive offered to retain the customer. In a customer service queue, the result can indicate whether the customer's needs have been met or whether problems have been resolved or whether a score (for example, Net Promoter Score or NPS) or other customer satisfaction rating representative with contact-agent interaction. After - or in parallel with - analyzing the historical contact agent result data, the BP 600 skill-based return matrix method can proceed to block 620.
[00113] In block 620, the contact attribute data can be analyzed. Contact attribute data can
Petition 870190140259, of 12/27/2019, p. 43/90
38/59 include data stored in one or more customer relationship management (CRM) databases. For example, a wireless telecommunications provider's CRM database may include information about the type of mobile phone a customer uses, the type of contract the customer signed up for, the length of the customer's contract, the price monthly contract of the client, and the time of the client's relationship with the company. For another example, a bank's CRM database may include information about the type and number of accounts held by the customer, the average monthly balance of the customer's accounts and the length of the customer's relationship with the company. In some embodiments, contact attribute data may also include data from third parties stored in one or more databases obtained from third parties. After - or in parallel with - analyzing the contact attribute data, the BP 600 skill-based return matrix method can proceed to block 630.
[00114] In block 630, skill groups can be determined for each agent and each type of contact. Examples of skills include broad skills, such as technical support, billing support, sales, retention, etc .; language skills such as English, Spanish, French, etc .; more restricted skills, such as Level 2 advanced technical support, technical support for Apple iPhone users, technical support for Google Android users, etc .; and any variety of other skills. In some modalities, there may be no distinct skills or only one skill can be identified in all agents or in all types of contact. In these modalities, there may be
Petition 870190140259, of 12/27/2019, p. 44/90
39/59 only a single skill group.
[00115] In some modalities, a certain type of contact may require different skill sets at different times. For example, during a first call to a call center, a contact of one type may have a technical question and require an agent with a technical support skill, but during a second call, the same contact of the same type may have a question. and require an agent with a customer support skill. In these modalities, the same type of contact can be included more than once, according to each type of contact / skill combination. After skill groups have been determined, the BP 600 skill-based return matrix method can proceed to block 640.
[00116] In block 640, a target usage can be determined for each agent, and an expected rate can be determined for each type of contact (or contact type / skill combinations). In some Ll environments, a balanced use of the agent can be targeted, so that each agent is expected to be assigned with an approximately equal number of contacts over time. For example, if a contact center environment has four agents, each agent can have an estimated use of 1/4 (or 25%). As another example, if a contact center environment has n agents, each agent can have a target utilization of 1 / n (or the equivalent percentage of contacts).
[00117] Likewise, the expected rates for each type / skill of contact can be determined based, for example, on the actual rates observed in the historical result data of contact agents analyzed in block 610.
Petition 870190140259, of 12/27/2019, p. 45/90
40/59
After the target utilization and the expected rates have been determined, the skill-based return matrix method of BP 600 can proceed to block 650.
[00118] In block 650, a return matrix with expected returns for each viable contact-agent pairing can be determined. In some modalities, contact-agent pairing may be feasible if an agent and type of contact have at least one skill in common. In other modalities, contact-agent pairing can be feasible if an agent has at least all the skills required by the type of contact. In yet other modalities, other viability heuristics can be used.
[00119] An example of a return matrix is the skill-based return matrix of BP 400A, described in detail above with reference to Figure 4A. The BP 400A skill-based feedback matrix includes a set of agents with associated skills and target uses, a set of contact types (combined with various skill sets) with expected frequencies determined based on historical contact results- agent and / or contact attribute data, and a set of expected returns other than zero for each viable contact-agent pairing. After determining the return matrix, the BP 600 skill-based return matrix method can proceed to block 660.
[00120] In block 660, a model generated by a computer processor according to the return matrix can be generated. For example, a computer processor incorporated or communicatively coupled to the contact center system or a component thereof, such as a module
Petition 870190140259, of 12/27/2019, p. 46/90
41/59 of BP, can issue the return matrix model to be received by another component of the computer processor or contact center system. In some embodiments, the return matrix model can be registered, printed, displayed, transmitted or otherwise stored for other components or human administrators of the contact center system. Upon departure from the return matrix model, the BP 600 skills-based return matrix method may terminate.
[00121] Figure 7A shows a flow chart of a BP 7 00A network flow method according to the modalities of the present disclosure. The BP 700A network flow method can start at block 710.
[00122] In block 710, a BP return matrix can be determined. In some embodiments, the BP return matrix can be determined using the BP 600 return matrix method or similar methods. In other modalities, the BP return matrix can be received from another component or module. After determining the BP return matrix, the BP 7 00A network flow method can proceed to block 720.
[00123] In block 720, a target use can be determined for each agent and expected rates can be determined for each type of contact. In other embodiments, the return matrix determined in block 710 may incorporate or include target uses and / or expected rates, such as a return matrix emitted by the BP 600 return matrix method or BP 400A skill-based return matrix ( Figure 4A). After the target uses and expected rates have been determined, if necessary,
Petition 870190140259, of 12/27/2019, p. 47/90
42/59 the BP 700A network flow method can proceed to block 730.
[00124] In block 730, agent offers and contact type demands can be determined. As described in detail above with reference, for example, to Figures 4D and 4E, each agent can provide an offering equivalent to the expected availability or target use of each agent (for example, in a three agent environment, one third each, for one total offer of 1 or 100%). In addition, each contact type / skill may require an amount of agent supply equivalent to the expected frequency or target use of each contact type / skill, for a total demand of 1 or 100%. Total supply and demand can be normalized or configured to match, and the capacity or bandwidth along each edge can be considered infinite or otherwise unlimited. In other modalities, there may be an imbalance of supply / demand, or there may be limited quotas or capacities defined for some or all edges.
[00125] In some modalities, offers and demands can be dimensioned by some factor, for example, 1000, 3000, etc. In doing so, the bid for each of the three agents can be shown as 1000 instead of a third, and the total bid can be shown as 3000. Likewise, the relative demands for each type of contact skill set can be shown. be scaled. In some embodiments, no scaling occurs. After determining agent offers and contact type demands, the BP 700A network flow method can proceed to the block
Petition 870190140259, of 12/27/2019, p. 48/90
43/59
740.
[00126] In block 740, the preferred contact-agent pairings can be determined. As described in detail above with reference, for example, to Figures 4F and 4G, one or more solutions for the BP network flow can be determined. In some embodiments, a maximum flow or max flow algorithm, or another linear programming algorithm, can be applied to the BP network flow to determine one or more solutions to optimize the flow or allocation of offers (sources) to satisfy demands (consumers). In some embodiments, a max cost algorithm can be applied to select a maximum optimal flow solution.
[00127] In some contact center environments, such as an L2 environment (excess contact), the network flow can be reversed, so that the contacts waiting in the queue are the sources that provide offers, and the possible agents that can become available it is consumers who supply demands.
[00128] The BP network flow can include an optimal flow solution determined by a BP module or similar component. According to this solution, from which there may be several options to choose from, or to be selected at random, some (viable) edges may have an optimal flow of 0, indicating that this viable pairing is not the preferred pairing. In some embodiments, the BP network flow can remove edges that represent possible matches if the match is determined to be not a preferred match.
[00129] Other edges can have an optimum flow
Petition 870190140259, of 12/27/2019, p. 49/90
44/59 different from zero, indicating that this viable pairing is preferred at least part of the time. As explained in detail above, this optimal flow solution describes the relative proportion of contact-agent interactions (or the relative possibility of selecting specific contact-agent interactions) that will achieve the target use of agents and contacts, while maximizing the overall expected performance contact center system according to the returns of each agent pair and contact type / skill set.
[00130] For some solutions of some BP network flows, a single contact type / ability can have several edges flowing from several agents. In these environments, the contact type / ability may have several preferred pairs. Given a choice between multiple agents, the BP network flow indicates the relative proportion or weighting for which one of the various agents can be selected each time a contact of that type / contact skill arrives at the contact center. After determining preferred contact agent pairings, the BP 700A network flow method can proceed to block 750.
[00131] In block 750, a model generated by a computer processor according to the preferred contact-agent pairings can be generated. For example, a computer processor embedded or communicatively coupled to the contact center system or a component therein, such as a BP module, can output the preferred match model to be received by another component of the computer processor or system contact center. In some modalities, the preferred matching model can be
Petition 870190140259, of 12/27/2019, p. 50/90
45/59 registered, printed, displayed, transmitted or otherwise stored to other components or human administrators of the contact center system. After leaving the preferred matching model, the BP 700A network flow method may terminate.
[00132] Figure 7B shows a flow chart of a BP 7 00B network flow method according to the modalities of the present disclosure. The BP 700B network flow is similar to the BP 700A network flow described above with reference to Figure 7A. The BP 700B network flow method can start at block 710. At block 710, a BP return matrix can be determined. After determining the BP return matrix, the BP 700B return matrix method can proceed to block 720. In block 720, a target use can be determined for each agent and the expected rates can be determined for each type of contact. After the target uses and expected rates have been determined, if necessary, the BP 700B network flow method can proceed to block 730. In block 730, agent offer needs and contact type demands can be determined. After determining agent offers and contact type demands, the BP 700B network flow method can proceed to block 735.
[00133] In block 735, agent offers and / or contact demands can be adjusted to balance agent usage, or to improve the balance of agent usage. As described in detail above with reference, for example, to Figures 5F and 5G, agents that share the same skill sets can be collapsed into single network nodes (or super nodes). Of the same
Petition 870190140259, of 12/27/2019, p. 51/90
46/59 way, the types of contacts that share the same skill sets can be collapsed into single network nodes. Additionally, the edges can be collapsed according to their corresponding supernodes. At this point, in some modalities, a quadratic programming algorithm or similar technique can be applied to the collapsed network to adjust the relative offers of the agents and / or the relative demands of the contacts. After adjusting agent offers and / or contact demands to balance agent usage, the BP 700B network flow method can proceed to block 740.
[00134] In block 740, the preferred contact-agent pairings can be determined. After determining the preferred contact-agent pairings, the BP 700A network flow method can proceed to block 750. In block 750, a model generated by the computer processor according to the preferred contact-agent pairings can be generated . After leaving the preferred matching model, the BP 700B network flow method may terminate.
[00135] Figure 8 shows a flow chart of a BP 800 network flow method, according to the modalities of the present disclosure. The BP 800 network flow method can start at block 810.
[00136] In block 810, the available agents can be determined. In a real-world queue for a contact center system, there may be tens, hundreds or thousands of agents or more employees. At any time, a fraction of these employed agents can be registered in the system or work actively in a shift. Additionally, at any time, a fraction of registered agents can
Petition 870190140259, of 12/27/2019, p. 52/90
47/59 be involved in a contact interaction (for example, in a call to a contact center), recording the result of a recent contact interaction, giving time, or otherwise unavailable to be assigned to incoming contacts. The remaining portion of registered agents may be inactive or otherwise available for assignment. After determining the set of available agents, the BP 800 network flow method can proceed to block 820.
[00137] In block 820, a BP model of preferred contact-agent pairings can be determined. In some embodiments, the preferred matching model can be determined using the BP 700A (Figure 7A) or 700B (Figure 7B) network flow method, or similar methods. In other modalities, the preferred matching model can be received from another component or module.
[00138] In some modalities, the preferred matching model may include all agents employed for the contact center queue or queues. In other modalities, the preferred pairing model may include only agents registered in the queue at any given time. In still other modalities, the preferred matching model may include only the agents determined to be available in block 810. For example, with reference to Figure 4B, if Agent 403 is unavailable, some modalities may use a different preferred matching model that omits a node for Agent 403 and includes nodes only for available agents Agent 401 and Agent 402. In other embodiments, the preferred pairing model may include a node for Agent 403, but it can be
Petition 870190140259, of 12/27/2019, p. 53/90
48/59 adapted to avoid generating a non-zero probability of assigning an Agent 403 contact. For example, the flow capacity from Agent 403 for each compatible contact type can be set to zero.
[00139] The preferred matching model can be pre-computed (for example, retrieved from a cache or other storage) or calculated in real time or near real time as agents become available or unavailable, and / or when contacts of various types with varying skill needs arrive at the contact center. After determining the preferred matching model, the BP 800 network flow method can proceed to block 830.
[00140] In block 830, an available contact can be determined. For example, in a Ll environment, multiple agents are available and waiting to be assigned to a contact, and the contact queue is empty. When a contact arrives at the contact center, it can be assigned to one of the available agents without waiting on hold. In some embodiments, the preferred matching model determined in block 820 can be determined for the first time or updated after determining an available contact in block 830. For example, with reference to Figures 4A - 4G, Agents 401-403 can be the three agents out of dozens or more that are available at any given time. At that time, the skill-based return matrix of BP 400A (Figure 4A) can be determined for the three agents available instantly, and the BP 400G network flow (Figure 4G) can be determined for the three agents available instantly based on in the return matrix
Petition 870190140259, of 12/27/2019, p. 54/90
49/59 based on skill of BP 400A. Thus, the preferred matching model can be determined at that time for these three available agents.
[00141] In some modalities, the preferred matching model may be responsible for some or all the expected contact type / skill combinations, for example, in the BP 400G network flow, even if the specific contact to be paired already is known by the BP 800 network flow method because the contact has already been determined in block 830. After the available contact has been determined in block 830 (and the preferred matching model has been generated or updated, in some modalities), the method BP 800 network flow can proceed to block 840.
[00142] In block 840, at least one preferred contact-agent pairing between the available agents and the available contact can be determined. For example, as shown in the BP 400G network flow (Figure 4G), if the available contact is Contact Type 411 and requires Skill 421 or 422, the preferred pairing is for Agent 402. Likewise, if the available contact is Contact Type 412 and require Skill 421 or 422, the preferred pairings are Agent 401 (optimal flow of 400) or Agent 402 (optimal flow of 50). After determining at least one preferred contact-agent pairing, the BP 800 network flow method can proceed to block 850.
[00143] In block 850, one of at least one preferred contact-agent pairing can be selected. In some modalities, the selection can be random, such as using a pseudo-random number generator. The possibility (or
Petition 870190140259, of 12/27/2019, p. 55/90
50/59 probability) of selecting one of at least one preferred contact-agent pairing can be based on the statistical possibilities described by the BP model. For example, as shown in the BP 400G network flow (Figure 4G), if the available contact is Contact Type 412 and requires Skill 421 or 422, the probability of selecting Agent 401 is 400/450 ^ 89% of chance, and the probability of selecting Agent 402 is a 50/450 ^ 11% chance.
[00144] If there is only one preferred agent contact pairing, there may be no need for random selection in some modalities, as the selection can be trivial. For example, as shown in the BP 400G network flow (Figure 4G), if the available contact is Contact Type 411 and requires Skill 421 or 422, the preferred pairing will always be Agent 402 and the probability of selecting Agent 402 is 450/450 = 100% chance. After selecting one of at least one preferred contact-agent pairing, the BP 800 network flow method can proceed to block 860.
[00145] In block 860, the selected pairing can be issued for connection to the contact center system. For example, a computer processor embedded or communicatively coupled to the contact center system or a component in it, such as a BP module, can output the preferred pairing selection (or recommended pairing, or pairing instruction) to be received by another component of the computer processor or the contact center system. In some modalities, the preferred pairing selection can be registered, printed, displayed, transmitted or otherwise stored for others
Petition 870190140259, of 12/27/2019, p. 56/90
51/59 human components or administrators of the contact center system. The receiving component can use the preferred pairing selection to cause the selected agent to be connected to the contact for which a pairing was requested or otherwise determined. After the output of the preferred pairing instruction, the BP 800 network flow method may terminate.
[00146] Figure 9 shows a flow chart of a BP 900 network flow method according to the modalities of the present disclosure. In some embodiments, the BP 900 network flow method is similar to the BP 800 network flow method. While the BP 800 network flow method illustrates a LI (surplus agent) environment, the network flow method BP 900 illustrates an L2 environment (queued contacts). The BP 900 network flow method can start at block 910.
[00147] In block 910, the available contacts can be determined. In a real-world queue for a contact center system, there can be dozens, hundreds, etc. of employed agents. In L2 environments, all registered agents are involved in contact interactions or unavailable. As contacts arrive at the contact center, contacts may be asked to wait in a queue. At any given time, there may be dozens or more contacts waiting. In some modes, the queue can be ordered sequentially by the time of arrival, with the longest contact waiting at the head of the queue. In other embodiments, the queue can be ordered at least in part based on a classification or priority status of individual contacts. For example, a
Petition 870190140259, of 12/27/2019, p. 57/90
52/59 contact designated as high priority can be positioned at or near the head of the queue, in front of other normal priority contacts that are waiting longer. After determining the set of available contacts waiting in the queue, the BP 900 network flow method can proceed to block 920.
[00148] In block 920, a BP model of preferred contact-agent pairings can be determined. In some embodiments, the preferred matching model can be determined using a method similar to the BP 700A (Figure 7A) or 700B (Figure 7B) network flow method, as long as the waiting contacts provide the supply sources, and agents that can become available provide consumers with demand. In other modalities, the preferred matching model can be received from another component or module.
[00149] In some modalities, the preferred matching model may include all types of contact that must reach the queue or queues at the contact center. In other modalities, the preferred matching model may include only the type / skill combinations of contact present and waiting in line at the time the model was requested. For example, consider a contact center system that expects to receive contacts of three types X, Y and Z, but only contacts of types X and Y are currently waiting in line. Some modalities may use a different preferred matching model that omits a node for contact type Z, including nodes only for waiting contacts of types X and Y. In other modalities, the preferred matching model may include a node for type in
Petition 870190140259, of 12/27/2019, p. 58/90
53/59 Z contact, but this model can be adapted to avoid generating a nonzero probability of assigning an agent to a type Z contact. For example, the flow capacity from type Z contact to each compatible agent can be defined like zero.
[00150] The preferred matching model can be pre-computed (for example, retrieved from a cache or other storage) or computed in real time or near real time as agents become available or unavailable, and / or at as contacts of various types with varying skill needs arrive at the contact center. After determining the preferred matching model, the BP 900 network flow method can proceed to block 930.
[00151] In block 930, an available agent can be determined. For example, in an L2 environment, multiple contacts are waiting and available for assignment to an agent, and all agents can be busy. When an agent becomes available, it can be assigned to one of the waiting contacts without remaining inactive. In some embodiments, the preferred matching model determined in block 920 can be determined for the first time or updated after determining an available agent in block 830. For example, there may be three contacts waiting in the queue, each with a skill and types many different. A BP skill-based return matrix can be determined for the three instant hold contacts, and a BP network flow can be determined for the three instant hold contacts based on the BP skill-based return matrix. Thus, the matching model
Petition 870190140259, of 12/27/2019, p. 59/90
54/59 can be determined at that time for these three contacts on hold.
[00152] In some modalities, the preferred matching model may be responsible for some or all potentially available agents, even if the agent to be paired is already known by the BP 900 network flow method, because the agent has already been determined in block 930. After the available agent has been determined in block 930 (and the preferred matching model has been generated or updated, in some modalities), the BP 900 network flow method can proceed to block 940.
[00153] In block 940, at least one preferred contact-agent pairing between the available agent and the available contacts can be determined. After determining at least one preferred contact-agent pairing, the BP 900 network flow method can proceed to block 950.
[00154] In block 950, one of at least one preferred contact-agent pairing can be selected. In some modalities, the selection can be random, such as using a pseudo-random number generator. The possibility (or probability) of selecting data from at least one preferred contact-agent pairing can be based on the statistical possibilities described by the BP model. If there is only one preferred contact-agent pairing, there may be no need for random selection in some modalities, as the selection can be trivial. After selecting one of at least one preferred contact-agent pairing, the BP 900 network flow method can proceed to block 960.
Petition 870190140259, of 12/27/2019, p. 60/90
55/59
[00155] In block 960, the selected pairing can be issued for connection to the contact center system. For example, a computer processor incorporated or communicatively coupled to the contact center system or a component in it, such as a BP module, can issue the preferred pairing selection (or recommended pairing, or pairing instruction) to be received by another component of the computer processor or the contact center system. In some embodiments, the preferred pairing selection can be recorded, printed, displayed, transmitted or otherwise stored to other components or human administrators of the contact center system. The receiving component can use the preferred pairing selection to cause the selected agent to be connected to the contact for which pairing was requested or otherwise determined. After the output of the preferred pairing instruction, the BP 900 network flow method may terminate.
[00156] In some modalities, a network flow model and BP return matrix can be used in L3 environments (that is, multiple agents available and multiple contacts waiting in the queue). In some embodiments, the network flow model can be used for multiple contact pair agent pairings simultaneously. BP matching in L3 environments is described in detail, for example, in U.S. Patent Application No. 15 / 395,469, which is incorporated herein by reference. In other embodiments, a BP network flow model can be used when a contact center system is operating in Ll and / or L2 environments, and a
Petition 870190140259, of 12/27/2019, p. 61/90
56/59 alternative BP pairing when the contact center system is operating in L3 (or LO) environments.
[00157] In the examples described above, the BP network flow model aims at a balanced use of the agent (or as close as possible to the balanced one for a private contact center environment). In other embodiments, a use of an inclined or otherwise unbalanced agent can be targeted (for example, Kappa techniques) and / or an inclined or otherwise unbalanced contact use can be targeted (for example, Rho techniques). Examples of these techniques, including Kappa and Rho techniques, are described in detail in, for example, U.S. Patent Application Nos. 14 / 956,086 and 14 / 956,074 mentioned above, which have been incorporated by reference here.
[00158] In some embodiments, such as those in which a BP module (for example, BP 140 module) is fully incorporated or otherwise integrated with a contact center switch (for example, central switch 110, center switch contact 120A, etc.), the switch can perform BP techniques without separate pairing requests and responses between the switch and a BP module. For example, the switch can determine its own function or cost functions to be applied to each possible match, as needed, and the switch can automatically minimize (or, in some configurations, maximize) the cost function accordingly. The switch can reduce or eliminate the need for skill queues or other hierarchical arrangements for agents or contacts; instead, the switch can operate on one or
Petition 870190140259, of 12/27/2019, p. 62/90
57/59 more groups of virtual agents or sets of agents among a larger set of agents within the contact center system. Some or all aspects of the BP matching methodology can be implemented by the switch as needed, including data collection, data analysis, model generation, network flow optimization, etc.
[00159] In some modalities, such as those that optimize groups of virtual agents, models of agent nodes in network flows can represent sets of agents having one or more combinations of skills / types of agents for agents found anywhere in the system. contact center, regardless of whether the contact center system assigns agents to one or more skill queues. For example, nodes for Agents 401, 402 and 403 in Figures 4B-4G can represent groups of virtual agents instead of individual agents, and a contact assigned to a group of virtual agents can subsequently be assigned to an individual agent within the group virtual agents (for example, random assignment, round-robin assignment, model-based behavioral matching, etc.). In these modalities, BP can be applied to a contact at a higher level within the contact center system (for example, central switch 101 in Figure 1), before a contact is filtered or otherwise assigned to a queue. individual skills and / or group of agents (for example, the center switch
contact 120A or the switch in center of contact 120B on Figure 1).[00160] A application of BP at first of the process can be advantageous, because it avoids scripts and others techniques
Petition 870190140259, of 12/27/2019, p. 63/90
58/59 prescriptives that conventional central switches use to decide which queue / switch / VDN a contact should be assigned to. These scripts and other prescriptive techniques can be inefficient and suboptimal, both in terms of optimizing the performance of the general contact center and achieving the desired target agent usage (eg balanced agent usage, minimal agent usage imbalance, inclination specific use of the curing agent).
[00161] At this point, it should be noted that behavioral pairing in a contact center system in accordance with the present disclosure, as described above, may involve processing input data and generating output data to some extent. This processing of input data and generation of output data can be implemented in hardware or software. For example, specific electronic components can be employed in a behavioral matching module or in similar or related circuits to implement the functions associated with behavioral matching in a contact center system in accordance with the present disclosure, as described above. Alternatively, one or more processors operating according to instructions can implement the functions associated with behavioral pairing in a contact center system in accordance with the present disclosure as described above. If so, it is within the scope of this disclosure that such instructions may be stored on one or more non-transitory processor-readable storage media (for example, a magnetic disk or other storage medium)
Petition 870190140259, of 12/27/2019, p. 64/90
59/59 or transmitted to one or more processors via one or more signals embedded in one or more carrier waves.
[00162] The present disclosure should not be limited in scope by the specific modalities described here. In fact, other various modalities and modifications of this disclosure, in addition to those described in this document, will be evident to those skilled in the art from the previous description and the attached drawings. Thus, such other modalities and modifications must fall within the scope of this disclosure. In addition, although the present disclosure has been described here in the context of at least one specific implementation in at least one specific environment for at least one specific purpose, those skilled in the art will recognize that its usefulness is not limited to this and that the present disclosure may be beneficially implemented in any number of environments for any number of purposes. Therefore, the claims set out below must be interpreted in view of the scope and spirit of the present disclosure, as described herein.

权利要求:
Claims (11)
[1]
1. Method for behavioral matching in a contact center system, characterized by the fact that it comprises:
determine, by at least one computer processor communicatively coupled to and configured to operate in the contact center system, a plurality of agents available for connection to a contact;
determining, at least one computer processor, a plurality of preferred contact-agent pairings among possible pairings between the contact and the plurality of agents;
selecting at least one computer processor, one of the plurality of preferred contact-agent pairings according to a probabilistic model; and issue, at least one computer processor, the one selected from the plurality of preferred contact-agent pairings for connection in the contact center system.
[2]
11/11
2. Method, according to claim 1, characterized by the fact that the probabilistic model is a network flow model for the use of balancing agent.
[3]
3/11 select one of the plurality of preferred contact-agent pairings according to a probabilistic model; and issue the selected one from the plurality of preferred contact-agent pairings for connection in the contact center system.
3. Method, according to claim 1, characterized by the fact that the probabilistic model is a network flow model to apply a quantity of agent usage slope.
[4]
4/11
16. System, according to claim 9, characterized by the fact that the probabilistic model incorporates the expected return values based on an analysis of at least one of the contact result data, historical agent and contact attribute data.
17. Article of manufacture for behavioral matching in a contact center system, characterized by the fact that it comprises:
a medium readable by a non-transitory processor; and instructions stored in the middle;
where the instructions are configured to be readable from the middle by at least one computer processor communicatively coupled to and configured to operate on the contact center system and thus make at least one computer processor operate in order to:
determine a plurality of agents available to connect with a contact;
determining a plurality of preferred contact-agent pairings among possible pairings between the contact and the plurality of agents;
select one of the plurality of preferred contact-agent pairings according to a probabilistic model; and issue the selected one from the plurality of preferred contact-agent pairings for connection in the contact center system.
18. Article of manufacture, according to claim 17, characterized by the fact that the probabilistic model is a network flow model for the use of balancing agent.
19. Article of manufacture, according to claim
Petition 870190109113, of 10/28/2019, p. 21/29
4. Method, according to claim 1, characterized by the fact that the probabilistic model is a network flow model to optimize an overall expected value of at least one contact center metric.
Petition 870190109113, of 10/28/2019, p. 18/29
[5]
5/11
17, characterized by the fact that the probabilistic model is a network flow model to apply a quantity of agent usage slope.
20. Manufacturing article according to claim 17, characterized by the fact that the probabilistic model is a network flow model to optimize an overall expected value of at least one contact center metric.
21. Article of manufacture, according to claim 20, characterized by the fact that at least one contact center metric is at least one of revenue generation, customer satisfaction, and average treatment time.
22. Manufacturing article according to claim 17, characterized by the fact that the probabilistic model is a network flow model restricted by agent skills and contact skill needs.
23. Article of manufacture, according to claim 22, characterized by the fact that the network flow model is adjusted to minimize the imbalance of agent usage according to the restrictions of agent skills and the needs of contact skill .
24. Manufacture article according to claim 17, characterized by the fact that the probabilistic model incorporates the expected return values based on an analysis of at least one of the contact result data, historical agent and contact attribute data .
25. Method for behavioral matching in a contact center system, characterized by the fact that it comprises:
determine at least one computer processor communicatively coupled to and configured to operate on the
Petition 870190109113, of 10/28/2019, p. 22/29
5. Method, according to claim 4, characterized by the fact that at least one contact center metric is at least one of revenue generation, customer satisfaction, and average treatment time.
[6]
6/11 contact center system, a plurality of contacts available for connection with an agent;
determining, at least one computer processor, a plurality of preferred contact-agent pairings among possible pairings between the agent and the plurality of contacts;
selecting at least one computer processor, one of the plurality of preferred contact-agent pairings according to a probabilistic network flow model; and issue, at least one computer processor, the one selected from the plurality of preferred contact-agent pairings for connection in the contact center system.
26. Method, according to claim 25, characterized by the fact that the probabilistic network flow model is a network flow model for the use of balancing agent.
27. Method according to claim 25, characterized by the fact that the probabilistic network flow model is a network flow model for applying an amount of agent usage slope.
28. Method according to claim 25, characterized by the fact that the probabilistic network flow model is a network flow model to optimize an overall expected value of at least one contact center metric.
29. Method, according to claim 28, characterized by the fact that at least one contact center metric is at least one of revenue generation, customer satisfaction, and average treatment time.
Petition 870190109113, of 10/28/2019, p. 23/29
6. Method, according to claim 1, characterized by the fact that the probabilistic model is a network flow model restricted by agent skills and contact skill needs.
[7]
7/11
30. Method, according to claim 25, characterized by the fact that the probabilistic network flow model is a network flow model restricted by agent skills and contact skill needs.
31. Method, according to claim 30, characterized by the fact that the probabilistic network flow model is adjusted to minimize the imbalance of
use in agent according the restrictions of skills in agent and skill needs in contact. 32. Method, of according to claim 25,
characterized by the fact that the probabilistic network flow model incorporates expected return values based on an analysis of at least one of historical agent-contact result data and contact attribute data.
33. System for behavioral matching in a contact center system, characterized by the fact that it comprises:
at least one computer processor communicatively coupled to and configured to operate in the contact center system, where at least one computer processor is further configured to:
determine a plurality of contacts available to connect with an agent;
determining a plurality of preferred contact-agent pairings among possible pairings between the agent and the plurality of contacts;
select one of the plurality of contact pairings Petition 870190109113, of 10/28/2019, p. 24/29
7. Method, according to claim 6, characterized by the fact that the network flow model is adjusted to minimize the imbalance of agent use according to the restrictions of agent skills and contact skill needs.
[8]
8/11 preferred agents according to a probabilistic network flow model; and issue the selected one from the plurality of preferred contact-agent pairings for connection in the contact center system.
34. System according to claim 33, characterized by the fact that the probabilistic network flow model is a network flow model for the use of balancing agent.
35. System according to claim 33, characterized by the fact that the probabilistic network flow model is a network flow model for applying an amount of agent usage slope.
36. System according to claim 33, characterized by the fact that the probabilistic network flow model is a network flow model to optimize an overall expected value of at least one contact center metric.
37. System according to claim 36, characterized by the fact that at least one contact center metric is at least one of revenue generation, customer satisfaction, and average treatment time.
38. System according to claim 33, characterized by the fact that the probabilistic network flow model is a network flow model restricted by agent skills and contact skill needs.
39. System, according to claim 38, characterized by the fact that the probabilistic network flow model is adjusted to minimize the imbalance of
Petition 870190109113, of 10/28/2019, p. 25/29
8. Method, according to claim 1, characterized by the fact that the probabilistic model incorporates the expected return values based on an analysis of at least one of the contact result data, historical agent and contact attribute data.
[9]
9/11 agent utilization according to restrictions on agent skills and contact skill needs.
40. System according to claim 33, characterized by the fact that the probabilistic network flow model incorporates expected return values based on an analysis of at least one of contact-agent outcome data from history and data from contact attribute.
41. Article of manufacture for behavioral matching in a contact center system characterized by the fact that it comprises:
a medium readable by a non-transitory processor; and instructions stored in the middle;
where the instructions are configured to be readable from the middle by at least one computer processor communicatively coupled to and configured to operate on the contact center system and thus make at least one computer processor operate in order to:
determine a plurality of contacts available to connect with an agent;
determining a plurality of preferred contact-agent pairings among possible pairings between the agent and the plurality of contacts;
selecting one of the plurality of preferred contact-agent pairings according to a probabilistic network flow model; and issue the selected one from the plurality of preferred contact-agent pairings for connection in the contact center system.
Petition 870190109113, of 10/28/2019, p. 26/29
9. System for behavioral matching in a contact center system, characterized by the fact that it comprises:
at least one computer processor communicatively coupled to and configured to operate in the contact center system, where at least one computer processor is further configured to:
determine a plurality of agents available to connect with a contact;
determining a plurality of preferred contact-agent pairings among possible pairings between the contact and the plurality of agents;
Petition 870190109113, of 10/28/2019, p. 19/29
[10]
11/10
42. Article of manufacture, according to claim 41, characterized by the fact that the probabilistic network flow model is a network flow model for the use of balancing agent.
43. Article of manufacture, according to claim 41, characterized by the fact that the probabilistic network flow model is a network flow model for applying an amount of agent usage slope.
44. Article of manufacture, according to claim 41, characterized by the fact that the probabilistic network flow model is a network flow model to optimize an overall expected value of at least one contact center metric.
45. Article of manufacture, according to claim 44, characterized by the fact that at least one contact center metric is at least one of revenue generation, customer satisfaction, and average treatment time.
46. Article of manufacture, according to claim 41, characterized by the fact that the probabilistic network flow model is a network flow model restricted by agent skills and contact skill needs.
47. Article of manufacture, according to claim 46, characterized by the fact that the probabilistic network flow model is adjusted to minimize the imbalance of agent usage according to the constraints of agent skills and the skill needs of contact.
48. Article of manufacture, according to claim 41, characterized by the fact that the network flow model
Petition 870190109113, of 10/28/2019, p. 27/29
10. System, according to claim 9, characterized by the fact that the probabilistic model is a network flow model for the use of balancing agent.
11. System, according to claim 9, characterized by the fact that the probabilistic model is a network flow model to apply a quantity of agent usage slope.
12. System, according to claim 9, characterized by the fact that the probabilistic model is a network flow model to optimize a global expected value of at least one contact center metric.
13. System, according to claim 12, characterized by the fact that at least one contact center metric is at least one of revenue generation, customer satisfaction, and average treatment time.
14. System, according to claim 9, characterized by the fact that the probabilistic model is a network flow model restricted by agent skills and contact skill needs.
15. System, according to claim 14, characterized by the fact that the network flow model is adjusted to minimize the imbalance of agent usage according to the restrictions of agent skills and contact skill needs.
Petition 870190109113, of 10/28/2019, p. 20/29
[11]
Probabilistic 11/11 incorporates expected return values based on an analysis of at least one of contact-agent result data from history and contact attribute data.

类似技术:

---

公开号 | 公开日 | 专利标题

---

BR112019022538A2|2020-05-12|TECHNIQUES FOR BEHAVIORAL PAIRING IN A CONTACT CENTER SYSTEM

---

US20200382645A1|2020-12-03|Techniques for behavioral pairing model evaluation in a contact center system

---

JP2021530180A|2021-11-04|Techniques for adapting behavior pairing to run-time conditions in task assignment systems

---

JP2019205186A|2019-11-28|Technique for l3 pairing and manpower control in contact center system

同族专利:

---

公开号 | 公开日

---

CN112085319A|2020-12-15|

---

CA3032337A1|2018-11-01|

---

KR20190002703A|2019-01-08|

---

US20190222697A1|2019-07-18|

---

US20180316793A1|2018-11-01|

---

KR102188646B1|2020-12-08|

---

JP2019522907A|2019-08-15|

---

EP3590081A1|2020-01-08|

---

KR102054362B1|2019-12-11|

---

JP2020108167A|2020-07-09|

---

US10404861B2|2019-09-03|

---

AU2021203487A1|2021-06-24|

---

US20210058516A1|2021-02-25|

---

CN109155020A|2019-01-04|

---

AU2019210608A1|2019-08-22|

---

US10659613B2|2020-05-19|

---

KR102361995B1|2022-02-14|

---

AU2019210594A1|2019-08-22|

---

US9942405B1|2018-04-10|

---

KR20200138446A|2020-12-09|

---

AU2018206690A1|2018-11-15|

---

KR20190137183A|2019-12-10|

---

US10116800B1|2018-10-30|

---

WO2018197943A1|2018-11-01|

---

JP6765023B2|2020-10-07|

---

AU2018206837A1|2018-11-22|

---

US11218597B2|2022-01-04|

---

US20200280636A1|2020-09-03|

---

JP2021016193A|2021-02-12|

---

US20190394335A1|2019-12-26|

---

JP6935571B2|2021-09-15|

---

US9930180B1|2018-03-27|

---

JP6816164B2|2021-01-20|

---

US10834263B2|2020-11-10|

---

CN109155020B|2020-10-02|

---

US20180316794A1|2018-11-01|

---

US10284727B2|2019-05-07|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

US5155763A|1990-12-11|1992-10-13|International Business Machines Corp.|Look ahead method and apparatus for predictive dialing using a neural network|

---

US5206903A|1990-12-26|1993-04-27|At&T Bell Laboratories|Automatic call distribution based on matching required skills with agents skills|

---

US5327490A|1991-02-19|1994-07-05|Intervoice, Inc.|System and method for controlling call placement rate for telephone communication systems|

---

US5537470A|1994-04-06|1996-07-16|At&T Corp.|Method and apparatus for handling in-bound telemarketing calls|

---

US6222919B1|1994-09-12|2001-04-24|Rockwell International Corporation|Method and system for routing incoming telephone calls to available agents based on agent skills|

---

US5594791A|1994-10-05|1997-01-14|Inventions, Inc.|Method and apparatus for providing result-oriented customer service|

---

US6539336B1|1996-12-12|2003-03-25|Phatrat Technologies, Inc.|Sport monitoring system for determining airtime, speed, power absorbed and other factors such as drop distance|

---

EP0740450B1|1995-04-24|2006-06-14|International Business Machines Corporation|Method and apparatus for skill-based routing in a call center|

---

US5907601A|1995-05-26|1999-05-25|Eis International Inc.|Call pacing method|

---

US5702253A|1995-07-10|1997-12-30|Bryce; Nathan K.|Personality testing apparatus and method|

---

US5903641A|1997-01-28|1999-05-11|Lucent Technologies Inc.|Automatic dynamic changing of agents' call-handling assignments|

---

US7020264B1|1997-02-10|2006-03-28|Genesys Telecommunications Laboratories, Inc.|Negotiated routing in telephony systems|

---

US5926538A|1997-02-11|1999-07-20|Genesys Telecommunications Labs, Inc|Method for routing calls to call centers based on statistical modeling of call behavior|

---

US6088444A|1997-04-11|2000-07-11|Walker Asset Management Limited Partnership|Method and apparatus for value-based queuing of telephone calls|

---

JP3311972B2|1997-09-19|2002-08-05|富士通株式会社|Telephone connection device, telephone connection method, and recording medium storing a program for causing a computer to execute the method|

---

US5903642A|1997-09-24|1999-05-11|Call-A-Guide, Inc.|Method for eliminating telephone hold time|

---

US6134315A|1997-09-30|2000-10-17|Genesys Telecommunications Laboratories, Inc.|Metadata-based network routing|

---

GB9723813D0|1997-11-11|1998-01-07|Mitel Corp|Call routing based on caller's mood|

---

US6052460A|1997-12-17|2000-04-18|Lucent Technologies Inc.|Arrangement for equalizing levels of service among skills|

---

US6801520B2|1998-02-17|2004-10-05|Genesys Telecommunications Laboratories, Inc.|Queue prioritization based on competitive user input|

---

CA2262044C|1998-04-09|2001-10-30|Lucent Technologies Inc.|Optimizing call-center performance by using predictive data to distribute agents among calls|

---

US6173053B1|1998-04-09|2001-01-09|Avaya Technology Corp.|Optimizing call-center performance by using predictive data to distribute calls among agents|

---

GB2339643A|1998-05-18|2000-02-02|Callscan Limited|Call centre management|

---

US6233332B1|1998-06-03|2001-05-15|Avaya Technology Corp.|System for context based media independent communications processing|

---

US20020087393A1|1998-07-31|2002-07-04|Laurent Philonenko|Dynamically updated QoS parameterization according to expected business revenue|

---

US6389400B1|1998-08-20|2002-05-14|Sbc Technology Resources, Inc.|System and methods for intelligent routing of customer requests using customer and agent models|

---

JP3313075B2|1998-08-24|2002-08-12|株式会社エヌ・ティ・ティ・データ|Call center system, receiving terminal setting method, and recording medium|

---

US6535601B1|1998-08-27|2003-03-18|Avaya Technology Corp.|Skill-value queuing in a call center|

---

US6064731A|1998-10-29|2000-05-16|Lucent Technologies Inc.|Arrangement for improving retention of call center's customers|

---

US7068775B1|1998-12-02|2006-06-27|Concerto Software, Inc.|System and method for managing a hold queue based on customer information retrieved from a customer database|

---

US6333979B1|1998-12-17|2001-12-25|At&T Corp.|Method and apparatus for assigning incoming communications to communications processing centers|

---

US6798876B1|1998-12-29|2004-09-28|At&T Corp.|Method and apparatus for intelligent routing of incoming calls to representatives in a call center|

---

US6434230B1|1999-02-02|2002-08-13|Avaya Technology Corp.|Rules-based queuing of calls to call-handling resources|

---

US6496580B1|1999-02-22|2002-12-17|Aspect Communications Corp.|Method and apparatus for servicing queued requests|

---

US6424709B1|1999-03-22|2002-07-23|Rockwell Electronic Commerce Corp.|Skill-based call routing|

---

US6519335B1|1999-04-08|2003-02-11|Lucent Technologies Inc.|Apparatus, method and system for personal telecommunication incoming call screening and alerting for call waiting applications|

---

US6445788B1|1999-06-17|2002-09-03|Genesys Telecommunications Laboratories, Inc.|Method and apparatus for providing fair access to agents in a communication center|

---

JP2003502950A|1999-06-18|2003-01-21|シュムアル オコン|System, method and program for managing calls with a communication service operating on a telephone network|

---

US6829348B1|1999-07-30|2004-12-07|Convergys Cmg Utah, Inc.|System for customer contact information management and methods for using same|

---

US7092509B1|1999-09-21|2006-08-15|Microlog Corporation|Contact center system capable of handling multiple media types of contacts and method for using the same|

---

FR2799593B1|1999-10-11|2002-05-31|Cit Alcatel|METHOD FOR DISTRIBUTING CALLS|

---

US6389132B1|1999-10-13|2002-05-14|Avaya Technology Corp.|Multi-tasking, web-based call center|

---

US6775378B1|1999-10-25|2004-08-10|Concerto Software, Inc|Blended agent contact center|

---

US6832203B1|1999-11-05|2004-12-14|Cim, Ltd.|Skills based contact routing|

---

US20060233346A1|1999-11-16|2006-10-19|Knowlagent, Inc.|Method and system for prioritizing performance interventions|

---

US6535492B2|1999-12-01|2003-03-18|Genesys Telecommunications Laboratories, Inc.|Method and apparatus for assigning agent-led chat sessions hosted by a communication center to available agents based on message load and agent skill-set|

---

US6535600B1|1999-12-06|2003-03-18|Avaya Technology Corp.|System for automatically routing calls to call center agents in an agent surplus condition based on service levels|

---

US6408066B1|1999-12-15|2002-06-18|Lucent Technologies Inc.|ACD skill-based routing|

---

US6661889B1|2000-01-18|2003-12-09|Avaya Technology Corp.|Methods and apparatus for multi-variable work assignment in a call center|

---

US7050567B1|2000-01-27|2006-05-23|Avaya Technology Corp.|Call management system using dynamic queue position|

---

US6724884B2|2000-01-27|2004-04-20|Avaya Technology Corp.|Call management system using fast response dynamic threshold adjustment|

---

US6714643B1|2000-02-24|2004-03-30|Siemens Information & Communication Networks, Inc.|System and method for implementing wait time estimation in automatic call distribution queues|

---

US6763104B1|2000-02-24|2004-07-13|Teltronics, Inc.|Call center IVR and ACD scripting method and graphical user interface|

---

US6707904B1|2000-02-25|2004-03-16|Teltronics, Inc.|Method and system for collecting reports for call center monitoring by supervisor|

---

US6587556B1|2000-02-25|2003-07-01|Teltronics, Inc.|Skills based routing method and system for call center|

---

US6603854B1|2000-02-25|2003-08-05|Teltronics, Inc.|System and method for evaluating agents in call center|

---

US6324282B1|2000-03-02|2001-11-27|Knowlagent, Inc.|Method and system for delivery of individualized training to call center agents|

---

US20010032120A1|2000-03-21|2001-10-18|Stuart Robert Oden|Individual call agent productivity method and system|

---

US6956941B1|2000-04-12|2005-10-18|Austin Logistics Incorporated|Method and system for scheduling inbound inquiries|

---

US20020046030A1|2000-05-18|2002-04-18|Haritsa Jayant Ramaswamy|Method and apparatus for improved call handling and service based on caller's demographic information|

---

US7245719B2|2000-06-30|2007-07-17|Matsushita Electric Industrial Co., Ltd.|Recording method and apparatus, optical disk, and computer-readable storage medium|

---

US6774932B1|2000-09-26|2004-08-10|Ewing Golf Associates, Llc|System for enhancing the televised broadcast of a golf game|

---

US6970821B1|2000-09-26|2005-11-29|Rockwell Electronic Commerce Technologies, Llc|Method of creating scripts by translating agent/customer conversations|

---

US6978006B1|2000-10-12|2005-12-20|Intervoice Limited Partnership|Resource management utilizing quantified resource attributes|

---

KR20020044077A|2000-12-04|2002-06-14|성상엽|Web agent center and method for operating the same|

---

US6889222B1|2000-12-26|2005-05-03|Aspect Communications Corporation|Method and an apparatus for providing personalized service|

---

US6539271B2|2000-12-27|2003-03-25|General Electric Company|Quality management system with human-machine interface for industrial automation|

---

US6639976B1|2001-01-09|2003-10-28|Bellsouth Intellectual Property Corporation|Method for parity analysis and remedy calculation|

---

US20020111172A1|2001-02-14|2002-08-15|Dewolf Frederik M.|Location based profiling|

---

US7039166B1|2001-03-05|2006-05-02|Verizon Corporate Services Group Inc.|Apparatus and method for visually representing behavior of a user of an automated response system|

---

US6922466B1|2001-03-05|2005-07-26|Verizon Corporate Services Group Inc.|System and method for assessing a call center|

---

US20020138285A1|2001-03-22|2002-09-26|Decotiis Allen R.|System, method and article of manufacture for generating a model to analyze a propensity of customers to purchase products and services|

---

JP2002297900A|2001-03-30|2002-10-11|Ibm Japan Ltd|Control system for reception by businesses, user side terminal device, reception side terminal device, management server queue monitoring device, method of allocating reception side terminals, and storage medium|

---

US7478051B2|2001-04-02|2009-01-13|Illah Nourbakhsh|Method and apparatus for long-range planning|

---

US6647390B2|2001-04-30|2003-11-11|General Electric Company|System and methods for standardizing data for design review comparisons|

---

CA2930709A1|2001-05-17|2002-11-21|Bay Bridge Decision Technologies, Inc.|System and method for generating forecasts and analysis of contact center behavior for planning purposes|

---

US6954480B2|2001-06-13|2005-10-11|Time Domain Corporation|Method and apparatus for improving received signal quality in an impulse radio system|

---

US7110525B1|2001-06-25|2006-09-19|Toby Heller|Agent training sensitive call routing system|

---

US6782093B2|2001-06-27|2004-08-24|Blue Pumpkin Software, Inc.|Graphical method and system for visualizing performance levels in time-varying environment|

---

US6856680B2|2001-09-24|2005-02-15|Rockwell Electronic Commerce Technologies, Llc|Contact center autopilot algorithms|

---

GB2383915B|2001-11-23|2005-09-28|Canon Kk|Method and apparatus for generating models of individuals|

---

US7103172B2|2001-12-12|2006-09-05|International Business Machines Corporation|Managing caller profiles across multiple hold queues according to authenticated caller identifiers|

---

US7245716B2|2001-12-12|2007-07-17|International Business Machines Corporation|Controlling hold queue position adjustment|

---

JP2003187061A|2001-12-19|2003-07-04|Fuji Mach Mfg Co Ltd|User support system, server device of user support system, operator selecting program and operator selecting method of user support system|

---

US6925155B2|2002-01-18|2005-08-02|Sbc Properties, L.P.|Method and system for routing calls based on a language preference|

---

US20030169870A1|2002-03-05|2003-09-11|Michael Stanford|Automatic call distribution|

---

US7023979B1|2002-03-07|2006-04-04|Wai Wu|Telephony control system with intelligent call routing|

---

US7372952B1|2002-03-07|2008-05-13|Wai Wu|Telephony control system with intelligent call routing|

---

US7336779B2|2002-03-15|2008-02-26|Avaya Technology Corp.|Topical dynamic chat|

---

US7379922B2|2002-04-29|2008-05-27|Avanous, Inc.|Pricing model system and method|

---

JP4142912B2|2002-07-19|2008-09-03|富士通株式会社|Transaction distribution program|

---

US7457403B2|2002-08-08|2008-11-25|Rockwell Electronic Commerce Technologies, Llc|Method and apparatus for determining a real time average speed of answer in an automatic call distribution system|

---

US6754331B2|2002-09-19|2004-06-22|Nortel Networks Limited|Determining statistics about the behavior of a call center at a past time instant|

---

US6937715B2|2002-09-26|2005-08-30|Nortel Networks Limited|Contact center management|

---

US20040098274A1|2002-11-15|2004-05-20|Dezonno Anthony J.|System and method for predicting customer contact outcomes|

---

US6847714B2|2002-11-19|2005-01-25|Avaya Technology Corp.|Accent-based matching of a communicant with a call-center agent|

---

US20040210475A1|2002-11-25|2004-10-21|Starnes S. Renee|Variable compensation tool and system for customer service agents|

---

US7184540B2|2002-11-26|2007-02-27|Rockwell Electronic Commerce Technologies, Llc|Personality based matching of callers to agents in a communication system|

---

GB0227946D0|2002-11-29|2003-01-08|Univ East Anglia|Signal enhancement|

---

US7545925B2|2002-12-06|2009-06-09|At&T Intellectual Property I, L.P.|Method and system for improved routing of repair calls to a call center|

---

JP2004227228A|2003-01-22|2004-08-12|Kazunori Fujisawa|Order accepting system by portable telephone|

---

US7418095B2|2003-03-06|2008-08-26|At&T Knowledge Ventures, L.P.|System and method for providing caller activities while in queue|

---

US7676034B1|2003-03-07|2010-03-09|Wai Wu|Method and system for matching entities in an auction|

---

US8478645B2|2003-04-07|2013-07-02|Sevenecho, Llc|Method, system and software for digital media narrative personalization|

---

US7877265B2|2003-05-13|2011-01-25|At&T Intellectual Property I, L.P.|System and method for automated customer feedback|

---

US7050566B2|2003-06-13|2006-05-23|Assurant, Inc.|Call processing system|

---

US7725339B1|2003-07-07|2010-05-25|Ac2 Solutions, Inc.|Contact center scheduling using integer programming|

---

US20050013428A1|2003-07-17|2005-01-20|Walters James Frederick|Contact center optimization program|

---

US7158628B2|2003-08-20|2007-01-02|Knowlagent, Inc.|Method and system for selecting a preferred contact center agent based on agent proficiency and performance and contact center state|

---

US8010607B2|2003-08-21|2011-08-30|Nortel Networks Limited|Management of queues in contact centres|

---

US7170991B2|2003-08-25|2007-01-30|Cisco Technology, Inc.|Method and system for utilizing proxy designation in a call system|

---

US7315617B2|2003-08-25|2008-01-01|Cisco Technology, Inc.|Method and system for managing calls of an automatic call distributor|

---

US20050071223A1|2003-09-30|2005-03-31|Vivek Jain|Method, system and computer program product for dynamic marketing strategy development|

---

US7231034B1|2003-10-21|2007-06-12|Acqueon Technologies, Inc.|“Pull” architecture contact center|

---

US20050129212A1|2003-12-12|2005-06-16|Parker Jane S.|Workforce planning system incorporating historic call-center related data|

---

US7027586B2|2003-12-18|2006-04-11|Sbc Knowledge Ventures, L.P.|Intelligently routing customer communications|

---

US7899177B1|2004-01-12|2011-03-01|Sprint Communications Company L.P.|Call-routing system and method|

---

US7353388B1|2004-02-09|2008-04-01|Avaya Technology Corp.|Key server for securing IP telephony registration, control, and maintenance|

---

US20050187802A1|2004-02-13|2005-08-25|Koeppel Harvey R.|Method and system for conducting customer needs, staff development, and persona-based customer routing analysis|

---

US7349535B2|2004-03-03|2008-03-25|Cisco Technology, Inc.|Method and system for automatic call distribution based on location information for call center agents|

---

US8000989B1|2004-03-31|2011-08-16|Avaya Inc.|Using true value in routing work items to resources|

---

US7734032B1|2004-03-31|2010-06-08|Avaya Inc.|Contact center and method for tracking and acting on one and done customer contacts|

---

US8126133B1|2004-04-01|2012-02-28|Liveops, Inc.|Results-based routing of electronic communications|

---

US20050286709A1|2004-06-28|2005-12-29|Steve Horton|Customer service marketing|

---

US8234141B1|2004-09-27|2012-07-31|Avaya Inc.|Dynamic work assignment strategies based on multiple aspects of agent proficiency|

---

US8180043B2|2004-12-07|2012-05-15|Aspect Software, Inc.|Method and apparatus for customer key routing|

---

WO2006062987A2|2004-12-09|2006-06-15|Inneroptic Technology, Inc.|Apparatus, system and method for optically analyzing substrate|

---

US20060124113A1|2004-12-10|2006-06-15|Roberts Forest G Sr|Marine engine fuel cooling system|

---

WO2006102270A2|2005-03-22|2006-09-28|Cooper Kim A|Performance motivation systems and methods for contact centers|

---

US7398224B2|2005-03-22|2008-07-08|Kim A. Cooper|Performance motivation systems and methods for contact centers|

---

US20060222164A1|2005-04-04|2006-10-05|Saeed Contractor|Simultaneous usage of agent and service parameters|

---

US8885812B2|2005-05-17|2014-11-11|Oracle International Corporation|Dynamic customer satisfaction routing|

---

US7995717B2|2005-05-18|2011-08-09|Mattersight Corporation|Method and system for analyzing separated voice data of a telephonic communication between a customer and a contact center by applying a psychological behavioral model thereto|

---

US8094790B2|2005-05-18|2012-01-10|Mattersight Corporation|Method and software for training a customer service representative by analysis of a telephonic interaction between a customer and a contact center|

---

US7773736B2|2005-05-18|2010-08-10|At&T Intellectual Property I, L.P.|VPN PRI OSN independent authorization levels|

---

US7837851B2|2005-05-25|2010-11-23|Applied Materials, Inc.|In-situ profile measurement in an electroplating process|

---

JP4068629B2|2005-06-08|2008-03-26|富士通株式会社|Incoming call distribution program|

---

US8175253B2|2005-07-07|2012-05-08|At&T Intellectual Property I, L.P.|System and method for automated performance monitoring for a call servicing system|

---

US20070025540A1|2005-07-07|2007-02-01|Roger Travis|Call center routing based on talkativeness|

---

US7904144B2|2005-08-02|2011-03-08|Brainscope Company, Inc.|Method for assessing brain function and portable automatic brain function assessment apparatus|

---

US8577015B2|2005-09-16|2013-11-05|Avaya Inc.|Method and apparatus for the automated delivery of notifications to contacts based on predicted work prioritization|

---

US20070219816A1|2005-10-14|2007-09-20|Leviathan Entertainment, Llc|System and Method of Prioritizing Items in a Queue|

---

US7907718B2|2005-11-18|2011-03-15|Cisco Technology, Inc.|VoIP call routing|

---

US7864944B2|2005-11-29|2011-01-04|Cisco Technology, Inc.|Optimal call speed for call center agents|

---

US7974398B2|2005-11-30|2011-07-05|On-Q Telecom Systems Co., Inc.|Virtual personal assistant for handling calls in a communication system|

---

US7826597B2|2005-12-09|2010-11-02|At&T Intellectual Property I, L.P.|Methods and apparatus to handle customer support requests|

---

US20070136342A1|2005-12-13|2007-06-14|Sap Ag|Processing a user inquiry|

---

DE202005021786U1|2005-12-22|2010-02-25|Epoq Gmbh|Device for agent-optimized operation of a call center|

---

US8457297B2|2005-12-30|2013-06-04|Aspect Software, Inc.|Distributing transactions among transaction processing systems|

---

US20070174111A1|2006-01-24|2007-07-26|International Business Machines Corporation|Evaluating a performance of a customer support resource in the context of a peer group|

---

US8112298B2|2006-02-22|2012-02-07|Verint Americas, Inc.|Systems and methods for workforce optimization|

---

US8108237B2|2006-02-22|2012-01-31|Verint Americas, Inc.|Systems for integrating contact center monitoring, training and scheduling|

---

US8300798B1|2006-04-03|2012-10-30|Wai Wu|Intelligent communication routing system and method|

---

US8331549B2|2006-05-01|2012-12-11|Verint Americas Inc.|System and method for integrated workforce and quality management|

---

US7856095B2|2006-05-04|2010-12-21|Interactive Intelligence, Inc.|System and method for providing a baseline for quality metrics in a contact center|

---

JP2007324708A|2006-05-30|2007-12-13|Nec Corp|Telephone answering method, call center system, program for call center, and program recording medium|

---

US7798876B2|2006-06-01|2010-09-21|Finis Inc.|Kickboard for swimming|

---

US7961866B1|2006-06-02|2011-06-14|West Corporation|Method and computer readable medium for geographic agent routing|

---

US20080046386A1|2006-07-03|2008-02-21|Roberto Pieraccinii|Method for making optimal decisions in automated customer care|

---

WO2008044227A2|2006-07-17|2008-04-17|Open Pricer|Customer centric revenue management|

---

US20080065476A1|2006-09-07|2008-03-13|Loyalty Builders, Inc.|Online direct marketing system|

---

US20090043671A1|2006-09-14|2009-02-12|Henrik Johansson|System and method for network-based purchasing|

---

US8223953B2|2006-11-17|2012-07-17|At&T Intellectual Property I, L.P.|Methods, systems, and computer program products for rule-based direction of customer service calls|

---

US7577246B2|2006-12-20|2009-08-18|Nice Systems Ltd.|Method and system for automatic quality evaluation|

---

US7940917B2|2007-01-24|2011-05-10|International Business Machines Corporation|Managing received calls|

---

US20080199000A1|2007-02-21|2008-08-21|Huawei Technologies Co., Ltd.|System and method for monitoring agents' performance in a call center|

---

US9088658B2|2007-02-23|2015-07-21|Cisco Technology, Inc.|Intelligent overload control for contact center|

---

US8270593B2|2007-10-01|2012-09-18|Cisco Technology, Inc.|Call routing using voice signature and hearing characteristics|

---

US8249245B2|2007-11-13|2012-08-21|Amazon Technologies, Inc.|System and method for automated call distribution|

---

US9712676B1|2008-01-28|2017-07-18|Afiniti Europe Technologies Limited|Techniques for benchmarking pairing strategies in a contact center system|

---

EP3182685A1|2008-01-28|2017-06-21|Afiniti International Holdings, Ltd.|Routing callers from a set of callers in an out of order sequence|

---

HUE038623T2|2008-08-29|2018-10-29|Afiniti Europe Tech Ltd|Call routing methods and systems based on multiple variable standardized scoring|

---

ES2710290T3|2015-09-30|2019-04-24|Afiniti Int Holdings Ltd|Behavioral matching techniques for a contact center system|

---

US9781269B2|2008-01-28|2017-10-03|Afiniti Europe Technologies Limited|Techniques for hybrid behavioral pairing in a contact center system|

---

US8670548B2|2008-01-28|2014-03-11|Satmap International Holdings Limited|Jumping callers held in queue for a call center routing system|

---

US8718271B2|2008-01-28|2014-05-06|Satmap International Holdings Limited|Call routing methods and systems based on multiple variable standardized scoring|

---

US8903079B2|2008-01-28|2014-12-02|Satmap International Holdings Limited|Routing callers from a set of callers based on caller data|

---

US20090190745A1|2008-01-28|2009-07-30|The Resource Group International Ltd|Pooling callers for a call center routing system|

---

US9787841B2|2008-01-28|2017-10-10|Afiniti Europe Technologies Limited|Techniques for hybrid behavioral pairing in a contact center system|

---

US20090190750A1|2008-01-28|2009-07-30|The Resource Group International Ltd|Routing callers out of queue order for a call center routing system|

---

US20090232294A1|2008-01-28|2009-09-17|Qiaobing Xie|Skipping a caller in queue for a call routing center|

---

US9712679B2|2008-01-28|2017-07-18|Afiniti International Holdings, Ltd.|Systems and methods for routing callers to an agent in a contact center|

---

US9300802B1|2008-01-28|2016-03-29|Satmap International Holdings Limited|Techniques for behavioral pairing in a contact center system|

---

US8781100B2|2008-01-28|2014-07-15|Satmap International Holdings Limited|Probability multiplier process for call center routing|

---

US8938059B2|2008-03-28|2015-01-20|Avaya Inc.|System and method for displaying call flows and call statistics|

---

US8200189B2|2008-06-19|2012-06-12|Verizon Patent And Licensing Inc.|Voice portal to voice portal VoIP transfer|

---

US20100020961A1|2008-07-28|2010-01-28|The Resource Group International Ltd|Routing callers to agents based on time effect data|

---

US8295468B2|2008-08-29|2012-10-23|International Business Machines Corporation|Optimized method to select and retrieve a contact center transaction from a set of transactions stored in a queuing mechanism|

---

US8644490B2|2008-08-29|2014-02-04|Satmap International Holdings Limited|Shadow queue for callers in a performance/pattern matching based call routing system|

---

US8781106B2|2008-08-29|2014-07-15|Satmap International Holdings Limited|Agent satisfaction data for call routing based on pattern matching algorithm|

---

US20100086120A1|2008-10-02|2010-04-08|Compucredit Intellectual Property Holdings Corp. Ii|Systems and methods for call center routing|

---

US8140441B2|2008-10-20|2012-03-20|International Business Machines Corporation|Workflow management in a global support organization|

---

US20100111288A1|2008-11-06|2010-05-06|Afzal Hassan|Time to answer selector and advisor for call routing center|

---

WO2010053701A2|2008-11-06|2010-05-14|The Resource Group International Ltd|Systems and methods in a call center routing system|

---

US8472611B2|2008-11-06|2013-06-25|The Resource Group International Ltd.|Balancing multiple computer models in a call center routing system|

---

US10567586B2|2008-11-06|2020-02-18|Afiniti Europe Technologies Limited|Pooling callers for matching to agents based on pattern matching algorithms|

---

US8824658B2|2008-11-06|2014-09-02|Satmap International Holdings Limited|Selective mapping of callers in a call center routing system|

---

US8634542B2|2008-12-09|2014-01-21|Satmap International Holdings Limited|Separate pattern matching algorithms and computer models based on available caller data|

---

US8340274B2|2008-12-22|2012-12-25|Genesys Telecommunications Laboratories, Inc.|System for routing interactions using bio-performance attributes of persons as dynamic input|

---

US8295471B2|2009-01-16|2012-10-23|The Resource Group International|Selective mapping of callers in a call-center routing system based on individual agent settings|

---

CN101998361B|2009-08-31|2015-04-15|华为技术有限公司|Calling method, equipment and system|

---

US8259924B2|2009-09-21|2012-09-04|Genesys Telecommunications Laboratories, Inc.|System for creation and dynamic management of incoming interactions|

---

MY148164A|2009-12-31|2013-03-15|Petroliam Nasional Berhad Petronas|Method and apparatus for monitoring performance and anticipate failures of plant instrumentation|

---

CN102118521B|2010-01-05|2013-12-04|华为技术有限公司|Call routing method, device and system|

---

US8634543B2|2010-04-14|2014-01-21|Avaya Inc.|One-to-one matching in a contact center|

---

US8699694B2|2010-08-26|2014-04-15|Satmap International Holdings Limited|Precalculated caller-agent pairs for a call center routing system|

---

US8724797B2|2010-08-26|2014-05-13|Satmap International Holdings Limited|Estimating agent performance in a call routing center system|

---

US8750488B2|2010-08-31|2014-06-10|Satmap International Holdings Limited|Predicted call time as routing variable in a call routing center system|

---

US8913736B2|2011-01-18|2014-12-16|Avaya Inc.|System and method for delivering a contact to a preferred agent after a set wait period|

---

CN103037110B|2011-09-30|2017-04-12|塔塔咨询服务有限公司|Predicting call center performance|

---

US8761380B2|2012-02-28|2014-06-24|Avaya Inc.|Adaptive estimated wait time predictor|

---

KR101379888B1|2012-02-29|2014-04-02|전화성|System and method for call roughting of call center|

---

US8565410B2|2012-03-26|2013-10-22|The Resource Group International, Ltd.|Call mapping systems and methods using variance algorithm and/or distribution compensation|

---

US8879715B2|2012-03-26|2014-11-04|Satmap International Holdings Limited|Call mapping systems and methods using variance algorithm and/or distribution compensation|

---

US8634541B2|2012-04-26|2014-01-21|Avaya Inc.|Work assignment deferment during periods of agent surplus|

---

US8879697B2|2012-08-10|2014-11-04|Avaya Inc.|System and method for determining call importance using social network context|

---

US8718269B2|2012-09-20|2014-05-06|Avaya Inc.|Risks for waiting for well-matched|

---

US8792630B2|2012-09-24|2014-07-29|Satmap International Holdings Limited|Use of abstracted data in pattern matching system|

---

US9042540B2|2012-10-30|2015-05-26|Teletech Holdings, Inc.|Method for providing support using answer engine and dialog rules|

---

US8767947B1|2012-11-29|2014-07-01|Genesys Telecommunications Laboratories, Inc.|System and method for testing and deploying rules|

---

CN103095937B|2012-12-14|2015-06-24|广东电网公司佛山供电局|Prediction method for number of seats in call center based on telephone traffic prediction|

---

US8995647B2|2013-05-20|2015-03-31|Xerox Corporation|Method and apparatus for routing a call using a hybrid call routing scheme with real-time automatic adjustment|

---

US9106750B2|2013-08-20|2015-08-11|Avaya Inc.|Facilitating a contact center agent to select a contact in a contact center queue|

---

US10298756B2|2014-03-25|2019-05-21|Interactive Intelligence, Inc.|System and method for predicting contact center behavior|

---

US8831207B1|2014-03-26|2014-09-09|Amazon Technologies, Inc.|Targeted issue routing|

---

CN105657201B|2016-01-26|2019-06-04|北京京东尚科信息技术有限公司|A kind of call processing method and system based on decision-tree model|

---

CN105704335B|2016-03-02|2018-12-18|重庆大学|Predictive outbound algorithm, interchanger dialing method and device based on dynamic statistics process|

---

US9930180B1|2017-04-28|2018-03-27|Afiniti, Ltd.|Techniques for behavioral pairing in a contact center system|US8300798B1|2006-04-03|2012-10-30|Wai Wu|Intelligent communication routing system and method|

---

US8724797B2|2010-08-26|2014-05-13|Satmap International Holdings Limited|Estimating agent performance in a call routing center system|

---

US8792630B2|2012-09-24|2014-07-29|Satmap International Holdings Limited|Use of abstracted data in pattern matching system|

---

US9888121B1|2016-12-13|2018-02-06|Afiniti Europe Technologies Limited|Techniques for behavioral pairing model evaluation in a contact center system|

---

US10135981B2|2017-03-24|2018-11-20|Microsoft Technology Licensing, Llc|Routing during communication of help desk service|

---

US10182156B2|2017-03-24|2019-01-15|Microsoft Technology Licensing, Llc|Insight based routing for help desk service|

---

US20180276676A1|2017-03-24|2018-09-27|Microsoft Technology Licensing, Llc|Communication conduit for help desk service|

---

US10970658B2|2017-04-05|2021-04-06|Afiniti, Ltd.|Techniques for behavioral pairing in a dispatch center system|

---

US9930180B1|2017-04-28|2018-03-27|Afiniti, Ltd.|Techniques for behavioral pairing in a contact center system|

---

US10623565B2|2018-02-09|2020-04-14|Afiniti Europe Technologies Limited|Techniques for behavioral pairing in a contact center system|

---

US11250359B2|2018-05-30|2022-02-15|Afiniti, Ltd.|Techniques for workforce management in a task assignment system|

---

US20190370714A1|2018-05-30|2019-12-05|Afiniti Europe Technologies Limited|Techniques for behavioral pairing in a task assignment system|

---

US10496438B1|2018-09-28|2019-12-03|Afiniti, Ltd.|Techniques for adapting behavioral pairing to runtime conditions in a task assignment system|

---

US10867263B2|2018-12-04|2020-12-15|Afiniti, Ltd.|Techniques for behavioral pairing in a multistage task assignment system|

---

US11144344B2|2019-01-17|2021-10-12|Afiniti, Ltd.|Techniques for behavioral pairing in a task assignment system|

---

US20200401982A1|2019-06-18|2020-12-24|Afiniti, Ltd.|Techniques for multistep data capture for behavioral pairing in a task assignment system|

---

CN111277712A|2019-07-11|2020-06-12|上海联逾信息技术有限公司|Telephone calling-out system based on language type classification processing|

---

US10757261B1|2019-08-12|2020-08-25|Afiniti, Ltd.|Techniques for pairing contacts and agents in a contact center system|

---

US20210067627A1|2019-08-26|2021-03-04|Afiniti, Ltd.|Techniques for behavioral pairing in a task assignment system|

---

US10757262B1|2019-09-19|2020-08-25|Afiniti, Ltd.|Techniques for decisioning behavioral pairing in a task assignment system|

---

US20210243303A1|2020-02-03|2021-08-05|Afiniti, Ltd.|Techniques for behavioral pairing in a task assignment system|

---

US11258905B2|2020-02-04|2022-02-22|Afiniti, Ltd.|Techniques for error handling in a task assignment system with an external pairing system|

---

US20210240530A1|2020-02-05|2021-08-05|Afiniti, Ltd.|Techniques for behavioral pairing in a task assignment system with an external pairing system|

---

WO2021158955A1|2020-02-05|2021-08-12|Afiniti, Ltd.|Techniques for assigning tasks in a task assignment system with an external pairing system|

---

WO2021158793A1|2020-02-05|2021-08-12|Afiniti, Ltd.|Techniques for sharing control of assigning tasks between an external pairing system and a task assignment system with an internal pairing system|

---

US20210241201A1|2020-02-05|2021-08-05|Afiniti, Ltd.|Techniques for benchmarking pairing strategies in a task assignment system|

---

US20210240531A1|2020-02-05|2021-08-05|Afiniti, Ltd.|Techniques for pairing in a task assignment system with an external pairing system|

法律状态:
2021-10-19| B350| Update of information on the portal [chapter 15.35 patent gazette]|

优先权:

---

申请号 | 申请日 | 专利标题

---

US15/582,223|2017-04-28|

---

US15/582,223|US9930180B1|2017-04-28|2017-04-28|Techniques for behavioral pairing in a contact center system|

---

US15/691,106|US9942405B1|2017-04-28|2017-08-30|Techniques for behavioral pairing in a contact center system|

---

US15/691,106|2017-08-30|

---

PCT/IB2018/000443|WO2018197943A1|2017-04-28|2018-04-05|Techniques for behavioral pairing in a contact center system|

---