data learning server, air conditioner, user terminal that controls an air conditioner, network syste

专利摘要:
data learning server, air conditioner, user terminal that controls an air conditioner, network system, method to generate a learning model from a data learning server, method to use a learning model from a learning server data, method to provide a recommended temperature of an air conditioner, method to control an air conditioner from a user terminal, method to generate a learning model of a network system including an air conditioner and a model server learning, method for providing a recommended temperature in a grid system, and method for controlling an air conditioner in a grid system an apparatus and a method for a data learning server are provided. the disclosure apparatus includes a communicator configured to communicate with an external device, at least one processor configured to acquire a temperature set in an air conditioner and a moment temperature of the air conditioner when setting the temperature through the communicator, and generate or renew a learning model using the defined temperature and the moment temperature and a storage configured to store the generated or renewed learning model to provide a recommended temperature to be set in the air conditioner as a result of generating or renewing the model of learning. for example, the disclosure data learning server can generate a learned learning model to provide a recommended temperature using a neural network algorithm, a deep learning algorithm, a linear regression algorithm or the like as an artificial intelligence algorithm.
公开号:BR112019020372A2
申请号:R112019020372
申请日:2018-03-30
公开日:2020-04-28
发明作者:Shin Dong-Jun；Seo Hyeong-Joon；Ock Hyun-Woo；Song Hyung-Seon；Kim Min-Kyong；Im Sung-Bin；Kim Tan；Joo Young-Ju
申请人:Samsung Electronics Co Ltd；
IPC主号:

专利说明:

DATA LEARNING SERVER, AIR CONDITIONER, USER TERMINAL THAT CONTROLS AN AIR CONDITIONER, NETWORK SYSTEM, METHOD FOR GENERATING A LEARNING MODEL FOR A DATA LEARNING SERVER, METHOD FOR USING A LEARNING MODEL FOR A LEARNING MODEL DATA, METHOD FOR PROVIDING A RECOMMENDED AIR CONDITIONER TEMPERATURE, METHOD FOR CONTROLLING AN AIR CONDITIONER FROM A USER TERMINAL, METHOD FOR GENERATING A MODEL FOR LEARNING A NETWORK SYSTEM INCLUDING AN AIR CONDITIONER AND A SERVER LEARNING, METHOD TO PROVIDE A RECOMMENDED TEMPERATURE IN A NETWORK SYSTEM, AND METHOD TO CONTROL AN AIR CONDITIONER IN A NETWORK SYSTEM
TECHNICAL FIELD [0001] Disclosure refers to a method for generating a learning model and a data learning server using the generated learning model.
FUNDAMENTALS OF THE INVENTION [0002] In recent years, they automatically recognize motion and text data to provide intelligent services that like voice, image, image in information related to data or data related services have been used in various fields.
[0003] An artificial intelligence technology used in intelligent services is a technology that implements intelligence on the human level. Unlike existing rules-based intelligent systems, artificial intelligence technology allows machines to perform learning and judgment and become intelligent at will
Petition 870190097162, of 27/09/2019, p. 61/159
2/68 own. As artificial intelligence technology is used, a recognition rate is increasing and users' tastes can be more accurately understood, so that existing rules-based technology is gradually being replaced by artificial intelligence technology.
[0004] The artificial intelligence technique includes machine learning and element technologies that use machine learning.
[0005] Machine learning is an algorithm technique that classifies / learns characteristics of the input data on its own. The element technique is a technique that simulates functions such as recognition and judgment of a human brain using machine learning algorithms and includes technical fields such as linguistic understanding, visual understanding, inference / prediction, knowledge representation and movement control.
[0006] The applications of artificial intelligence technology are diverse as follows. Linguistic understanding is a technique for recognizing and applying / processing human language / characters and includes natural language processing, machine translation, dialogue system, response to consultation, speech recognition / synthesis and the like. Visual understanding is a technique for recognizing and processing objects such as human vision and includes object recognition, object tracking, image search, human recognition, understanding of scenes, spatial understanding and enhancement of images or the like. Inference prediction is a technique for judging, inferring, and logically predicting information and including inference based on
Petition 870190097162, of 27/09/2019, p. 62/159
3/68 knowledge / probability, optimization forecasting, planning based on preference, recommendation and the like. Knowledge representation is a technique for automating information from human experience into knowledge data and includes knowledge construction (data generation / classification), knowledge management (data use) or similar. Motion control is a technique for controlling the automatic driving of a vehicle and the movement of a robot, and includes motion control (navigation, collision, direction), operation control (behavior control) and the like.
[0007] The information above is presented as basic information only to assist in understanding the disclosure. No determination has been made, and no statement is made, as to whether any of the above may apply as prior art with respect to disclosure.
REVELATION
TECHNICAL PROBLEM [0008] Representative disclosure modalities overcome the above disadvantages and other disadvantages not described above. Furthermore, the present invention is not necessary to overcome
the disadvantagesrepresentative of describeddisclosure above, it may not isovercome modality none From problems described above.[0009] Disclosure is to define a temperature one
air conditioner using artificial intelligence technology.
TECHNICAL SOLUTION [00010] Therefore, disclosure is to provide a method
Petition 870190097162, of 27/09/2019, p. 63/159
4/68 to generate and use a learning model to define the temperature of the air conditioner.
[00011] In addition, the technical subjects of the disclosure are not limited to the technical subjects described above, and other technical matters that are not mentioned can be clearly understood by a person versed in the technique to which the disclosure belongs from the description below.
[00012] According to one aspect of the disclosure, a data learning server is provided. The data learning server includes a communicator configured to communicate with an external device, at least one processor configured to acquire a temperature set in an air conditioner and a moment temperature of the air conditioner at the time of setting the temperature through the communicator, and generate or renew a learning model using the set temperature and the current temperature and a storage configured to store the generated or renewed learning model to provide a recommended temperature to be set in the air conditioner as a result of the generation or renewal of the learning model.
[00013] According to another aspect of the disclosure, a data learning server is provided. The data learning server includes storage configured to store a learned learning model to provide a recommended temperature to be set in the air conditioner, at least one processor configured to acquire an air conditioner moment temperature and enter the temperature of the air conditioner. moment in the learning model to acquire the recommended temperature to be set in the air conditioner
Petition 870190097162, of 27/09/2019, p. 64/159
5/68 air and a communicator configured to transmit the recommended temperature to an external device.
[00014] According to another aspect of the disclosure, a network system is provided. The system includes an air conditioner and a learning model server configured to generate a learning model using learning data acquired from the device, where the device includes a temperature sensor configured to detect a moment temperature around the device, a configured fan discharges cooling air to the outside based on the temperature set in the air conditioner and an air conditioner communicator configured to communicate with an external device and at least one air conditioner processor configured to control the air conditioner communicator. air conditioner to transmit the detected current temperature and the defined temperature to the external device, and the learning model server includes at least one server processor that acquires the current temperature and the defined temperature and generates a learning model using the acquired set temperature and the moment temperature and a storage configured to store the generated learning model to provide a recommended air conditioner temperature as a result of generating the learning model.
[00015] According to another aspect of the disclosure, a network system is provided. The network system includes an air conditioner and a learning model server configured to provide a recommended temperature using recognition data acquired from the air conditioner, where the air conditioner includes a temperature sensor
Petition 870190097162, of 27/09/2019, p. 65/159
6/68 configured to detect the air conditioner moment temperature, a blowing fan configured to discharge the cooling air generated from an air purifier to the outside and an air conditioner communicator transmitting the moment temperature to a first external device, where the learning model server includes storage configured to store a learned learning model to provide a recommended air conditioner temperature, at least one server processor configured to acquire the current temperature and enter the temperature of moment in the learning model to acquire the recommended temperature of the air conditioner, and a server communicator configured to transmit the recommended temperature to a second external device.
[00016] According to another aspect of the disclosure, an air conditioner is provided. The air conditioner includes a blowing fan configured to discharge cooling air outside, a temperature sensor configured to detect a moment temperature around the air conditioner, a communicator configured to communicate with an external device and the at least one processor configured to control the communicator to transmit the moment temperature to the external device, control the communicator to receive a recommended temperature, a result obtained by applying the moment temperature in a learning model, from the external device, depending on a temperature transmission of the moment, and set the received the temperature recommended in the air conditioner, where the learning model is a
Petition 870190097162, of 27/09/2019, p. 66/159
7/68 learning model learned using a plurality of
temperatures defined previously defined at the current conditioner. of air and a plurality of temperatures [00017] From a deal with another aspect disclosure, is provided one user terminal. 0 terminal user includes one
display configured to display a screen, a communicator configured to communicate with an external device, an input configured to receive a user input, and at least one processor configured to control the communicator to transmit a corresponding artificial intelligence operation request signal to a artificial intelligence operation user interface for the air conditioner in response to a user input signal, depending on a user input, selecting the artificial intelligence operation user interface included in the screen being received by the input and controlling the screen to display the recommended temperature acquired in response to the recommended temperature defined in the air conditioner being acquired, a result obtained by applying the air conditioner moment temperature to the learning model, depending on the artificial intelligence operation request signal, via communicator .
[00018] According to another aspect of the disclosure, a method is provided to generate a learning model from a data learning server. The method includes acquiring a temperature set in an air conditioner and a moment temperature of the air conditioner when setting the temperature, generating or renewing a learning model using the set temperature and the set temperature.
Petition 870190097162, of 27/09/2019, p. 67/159
8/68 moment and store the generated or renewed learning model to provide a recommended temperature to be adjusted in the air conditioner as a result of generating or renewing the learning model.
[00019] In accordance with another aspect of the disclosure, a method is provided for using a learning model of a data learning server. The method includes storing a learned learning model to provide a recommended temperature to be set as an air conditioner, acquiring a moment temperature from the air conditioner, entering the moment temperature into the learned learning model to acquire the recommended temperature to be set in the air conditioner and transmission of the recommended temperature to an external device.
[00020] According to another aspect of the disclosure, a method is provided to provide a recommended temperature for an air conditioner. The method includes detecting a moment temperature from the air conditioner, transmitting the detected moment temperature to an external device, receiving a recommended temperature, a result obtained by applying the moment temperature to a learning model, from the external device, depending on a transmitting the current temperature and defining the recommended temperature received in the air conditioner, where the learning model is a learning model learned using a plurality of defined temperatures previously defined in the air conditioner and a plurality of prevailing temperatures.
[00021] In accordance with another aspect of the disclosure, a method is provided to control an air controller from a
Petition 870190097162, of 27/09/2019, p. 68/159
9/68 user terminal. The method includes receiving a user input signal, depending on whether a user input selects an artificial intelligence operation user interface, transmitting an artificial intelligence operation request signal corresponding to the artificial intelligence operation user interface to the air conditioner, acquire a recommended temperature defined in the air conditioner which is a result obtained by applying an air conditioner moment temperature to a learning model, depending on the artificial intelligence operation request signal and display the acquired recommendation temperature on a screen. [00022] In accordance with another aspect of the disclosure, a method is provided to generate a learning model of a network system, including an air conditioner and a learning model server. The method includes receiving, by the air conditioner, a control signal from the user defining a temperature, a transmission operation, by the air conditioner, the set temperature and the moment temperature of the air conditioner to an external device, generating, at least server learning model, a learning model using the defined temperature and the moment temperature and storing, by the learning model server, the generated learning model to provide the recommended temperature of the air conditioner. [00023] In accordance with another aspect of the disclosure, a method is provided to provide a recommended temperature in a grid system, including an air conditioner and a learning model server. The method includes transmitting, through the air conditioner, a moment temperature from the air conditioner to an external device,
Petition 870190097162, of 27/09/2019, p. 69/159
10/68 acquiring a recommended temperature of the air conditioner through the learning model server by applying the current temperature to a learning model and transmitting the recommended temperature to the external device through the air conditioner.
[00024] In accordance with another aspect of the disclosure provided a method for controlling an air conditioner from a network system, including an air conditioner and a user terminal. The method includes receiving a user input signal from the user terminal, depending on a user input, selecting an artificial intelligence operation user interface, transmitting an artificial intelligence operation request signal corresponding to the user interface through the user terminal. of the artificial intelligence operation for the air conditioner, transmitting, through the air conditioner, a moment temperature from the air conditioner to an external device if the artificial intelligence operation request signal is received, receiving, through the air conditioner, a recommended temperature, a result obtained by applying the moment temperature to a learning model, from the external device, depending on a moment temperature transmission, and setting, by the air conditioner, of the recommended temperature received in the air conditioner, where the learning model is a learned learning model uses a plurality of temperatures previously defined in the air conditioner and a plurality of prevailing temperatures.
[00025] According to a disclosure mode, how the temperature set in the air conditioner is automatically
Petition 870190097162, of 27/09/2019, p. 70/159
11/68 recommended using artificial intelligence technology, the convenience of the user who controls the temperature can be greatly improved. In particular, it is possible to provide the user with the recommended temperature most ideal for the user.
[00026] In addition, according to the method for using a disclosure learning model, the learning model can be updated continuously based on the user's temperature configuration history that defines the air conditioner and the performance of the model. learning can be improved, such that as the learning model according to the disclosure is used, the most ideal recommended temperature can be provided to the user.
[00027] That is, the personalized learning model for each of the users who use the air conditioner can be generated and, therefore, the most suitable ideal temperature for each of the multiple users can be provided.
[00028] In addition, the effects that can be acquired or expected by various disclosure modalities must be directly or implicitly disclosed in the detailed disclosure description. For example, various effects that can be expected from the various disclosure modalities should be disclosed in the detailed description to be described below.
[00029] Other salient aspects, advantages and characteristics of the disclosure will be evident to those skilled in the art from the detailed description below, which, taken in conjunction with the attached drawings, discloses various types of disclosure.
DESCRIPTION OF THE DRAWINGS [00030] The above and / or other aspects of the disclosure will be more apparent when describing certain modalities of
Petition 870190097162, of 27/09/2019, p. 71/159
12/68 disclosure with reference to the attached drawings, in which:
Figures IA and 1B are diagrams showing a network system to generate and use a learning model according to a mode of dissemination;
Figures 2A and 2B are diagrams showing a configuration of a data learning server according to a disclosure modality;
Figures 3A and 3B are flowcharts of a network system according to an embodiment of the disclosure;
Figure 4 is a table that shows an example of a generation of a learning model according to a mode of dissemination;
Figure 5 is a diagram showing an example of giving weight to the learning data according to a modality of dissemination;
Figure 6 is a diagram showing a structure of a cloud server according to a disclosure modality;
Figures 7A and 7B are diagrams showing a procedure for generating a learning model according to a disclosure modality;
Figure 8 is a block diagram showing an air conditioner configuration according to a disclosure modality;
Figure 9 is a block diagram showing a configuration of a user terminal U according to a disclosure modality;
Figures 10A and 10B are diagrams showing a screen of a user terminal in which a recommended temperature is displayed, according to a disclosure modality;
Petition 870190097162, of 27/09/2019, p. 72/159
13/68
Figure 11 is a flowchart showing a method for generating a learning model for a data learning server according to a disclosure modality;
Figure 12 is a flowchart showing a method for using a learning model for a data learning server according to a disclosure modality;
Figure 13 is a flow chart showing a method for providing a recommended temperature for an air conditioner according to a disclosure modality;
Figure 14 is a flow chart showing a method for controlling an air conditioner from a user terminal according to a disclosure modality; and
Figure 15 is a flow chart of a network system including a user terminal and an air conditioner according to a disclosure modality.
[00031] Throughout the drawings, similar reference numbers will be understood as references to similar parts, components and contours.
MODE FOR CARRYING OUT THE INVENTION [00032] The following description, with reference to the accompanying drawings, is provided to assist in the comprehensive understanding of various modalities of disclosure, as defined by the claims and their equivalents. It includes several specific details to assist in this understanding, but these should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications to the various modalities described in this document can be made without departing from the scope and spirit of the disclosure. In addition, descriptions of known functions and constructs can be omitted for clarity and conciseness.
Petition 870190097162, of 27/09/2019, p. 73/159
14/68 [00033] Here above, the disclosure is described based on an exemplary method. The terms and words used here are for description and are not limited to bibliographic meanings, but are merely used by the inventor to allow a clear and consistent understanding of the disclosure. Disclosure may be varied and varied in accordance with the above content. Therefore, unless mentioned further, disclosure may be practiced freely within the scope of claims.
[00034] Various modalities described in the specification and configurations shown in the drawings are merely preferred examples of the disclosed disclosure, and several modifications that may replace the various modalities and designs of the present specification may be present at the time of submitting this application.
[00035] In addition, similar reference numbers or symbols in each drawing of this specification denote parts or components that perform substantially the same functions.
[00036] In addition, the terms used in this specification are used only to describe a specific modality rather than limiting the disclosed disclosure. The singular forms used here are intended to include plural forms, unless the context explicitly indicates otherwise. Throughout this specification, it will be understood that the term understand and its variations, as comprising and understands, specify the presence of characteristics, numbers, steps, operations, components, parts or combinations thereof, described in the specification, but do not exclude the presence or adding one or more other features, numbers,
Petition 870190097162, of 27/09/2019, p. 74/159
15/68 stages, operations, components, parts or combinations thereof.
[00037] In addition, terms including ordinals such as first and second used here can be used to describe various components, but the components are not limited by the terms and the terms are used only for the purpose of distinguishing one component from other components. For example, a 'first' component can be named a 'second' component and the 'second' component can also be similarly called the 'first' component, without departing from the scope of the disclosure. The term 'and / or' includes a combination of a plurality of items or any one of a plurality of terms.
[00038] In addition, if any component (for example: first) is (functionally or communicatively) connected or coupled to another component (for example: second), any component can be directly connected to another component or be connected to the other component through of another component (for example: third component).
[00039] In the following, various disclosure modalities will be described in detail with reference to the attached drawings.
[00040] Figures IA and 1B are diagrams showing a network system to generate and use a learning model according to a disclosure modality.
[00041] With reference to Figure IA, a network system can include an air conditioner A (Aa or Ab), a user terminal U (Ua or Ub) and a cloud server C. Air conditioner A can be a device to control the temperature or humidity of an indoor environment. Air conditioner A can be divided into a type mounted on the
Petition 870190097162, of 27/09/2019, p. 75/159
16/68 wall, as the air conditioner Aa, and a type of support, as the air conditioner Ab.
[00042] User terminal U can be a device to control air conditioner A remotely. Like the user terminal Ua, the user terminal U can be a smart phone, a cell phone or a tablet PC in which an air conditioner control application (or app) is installed. Alternatively, like the user terminal Ub, the user terminal U can be a remote controller (or remote control) dedicated to the air conditioner. In addition, the user terminal U can be a smart TV, a digital camera, a personal digital assistant (PDA), a portable multimedia player (PMP), a notebook, a desktop computer or similar, but it is not limited to the examples mentioned above.
[00043] The user terminal U can control air conditioner A remotely. For example, the user terminal U can use RF communication technologies such as ZigBee, WIFI, Bluetooth, mobile communications, local area network (LAN), wide area network (WAN), infrared data association (IrDA), UDA and UHF to transmit a control command to air conditioner A.
[00044] 0 server in a cloud C can to be connected or directly connected to conditioner air A across one third device (per example, a dot access (AP), one
repeater, a router, a 'gateway' , one 'hub' or similar). [00045] 0 server cloud C can include one or more servers. For example, the server cloud C can include at least one from a bridge server BS, a service server
SS smart home and a learning server
Petition 870190097162, of 27/09/2019, p. 76/159
17/68 DS data. In this case, two or more of the BS bridge server, the SS smart home service server and the DS data learning server can be integrated into one server. Alternatively, at least one of the BS bridge servers, the SS smart home service server and the DS data learning server can be separated into a plurality of sub-servers.
[00046] The BS bridge server (or a device to import device status information) can import status information from smart home appliances (for example, an air conditioner, a washing machine, a refrigerator, a cleaner, an oven or something similar).
[00047] The BS bridge server can include a BS1 connectivity API and a DB BS2 device status database.
[00048] The BS1 connectivity API can include an application programming interface (hereinafter referred to as API) that serves as an interface between different devices operating depending on heterogeneous protocols. The API can be defined as a set of subroutines or functions that can be called from any protocol for any other protocol processing. That is, the API can provide the environment in which the operation of another protocol can be performed on any of the protocols.
[00049] The BS bridge server can import air conditioner status information using the BS1 connectivity API. The BS bridge server can then store status information imported from the air conditioner in the status data of the DB BS2 device.
[00050] 0 smart home service SS server (or a
Petition 870190097162, of 27/09/2019, p. 77/159
18/68 external environment information import server) can import information from the external environment. External environment information can include, for example, at least one external temperature and external humidity as weather information provided by an external CP content server (for example, weather station server, weather forecast server or the like).
[00051] The DS data learning server can generate a learning model and obtain results from the learning model application using the learned generation model.
[00052] The DS data learning server includes a DS1 data import API, a DS2 data analysis engine, an analysis DB (DS3) and a data service API (DS4).
[00053] Figure IA shows a network system in which a DS data learning server generates a learning model, and Figure 1B shows a network system in which the learning model generated from the DS data learning server is used.
[00054] First, a network system procedure in which a DS data learning server generates a learning model will be described with reference to Figure IA.
[00055] In operation (T), air conditioner A can transmit status information (for example, set temperature, moment temperature and the like) from air conditioner A to cloud server C via the third device (for example, example, an AP access point, repeater, router, 'gateway', 'hub' or similar). The BS bridge server of cloud server C can import status information from air conditioner A, transmitted from air conditioner A
Petition 870190097162, of 27/09/2019, p. 78/159
19/68 using the BS1 connectivity API and store the status information imported from air conditioner A in the DB BS2 device status data.
[00056] Air conditioner status information A can include the temperature set in air conditioner A and the current temperature (eg room temperature and room temperature) of the air conditioner at the time of setting the temperature, depending on the temperature desired by the user.
[00057] The temperature desired by the user can generally be the same as the temperature set in air conditioner A, but it can be the temperature set step by step by air conditioner A until the desired temperature is reached.
[00058] In addition, the moment temperature (or room temperature and room temperature) at the time of setting the temperature can include at least one of, for example, temperature detected by air conditioner A at the time of setting the temperature ( for example, when a user operation that sets the temperature of air conditioner A is performed), the temperature detected by air conditioner A within a certain period of time (for example, 10 minutes) after setting the temperature and a recent temperature that is previously detected before the set temperature and is being stored.
[00059] Air conditioner status information A may include the operating mode information defined in air conditioner A. The operating mode may include, for example, an intelligent comfort mode, a tropical sleep mode with sound night, a tropical sleep mode with no sound
Petition 870190097162, of 27/09/2019, p. 79/159
20/68 ventilation during the night mode, a two-stage cooling mode or similar, but is not limited to the modes described above.
[00060] According to various modalities, the time information when defining the air conditioner temperature A can also be stored in the status data of the DB BS2 device. Time information at the time of setting a temperature includes, for example, at least one user operating time that sets a temperature, the time that the BS bridge server receives the set temperature and the time at which the set temperature is stored in the DB BS2 device status data.
[00061] According to various modalities, the positional information of the air conditioner A can also be stored in the status data of the DB BS2 device. In this case, positional information from air conditioner A can be stored when received at the time of setting the temperature or stored in advance.
[00062] In operation @, the SS smart home service server can import information from the external environment (or weather information) at each predetermined period (for example, between 5 minutes and 30 minutes) from the external content server in CP communication and store the information of the imported external environment in a DB SS1 meteorological data. [00063] Information from the external environment can include at least one of an external temperature, an external humidity, a concentration of dust, a precipitation and an amount of sunlight, but it is not limited to the example described above.
[00064] In operations (3) and (3) ’, the DS data learning server can use the DS1 data import API to
Petition 870190097162, of 27/09/2019, p. 80/159
21/68 acquire air conditioner status information A stored in the DB BS2 device status data of the BS bridge server. In addition, the DS data learning server can use the DS1 data import API to acquire the external environment information stored in the SS1 DB of weather data from the SS smart home service server.
[00065] In this case, the external environment information is external environmental information at the time of setting the air conditioner temperature A and can be searched for information in the DB SSI meteorological database based on the time information at the time of setting the temperature. air conditioner A stored in the DB BS2 device status data.
[00066] Specifically, the external environment information at the time of setting the temperature can include, for example, at least one external environmental information at the time a user sets a temperature, external environmental information in a time zone (for example, morning / day / afternoon or morning / afternoon), in which a user sets a temperature and information of the external environment in a month or season, when a user sets a temperature.
[00067] In addition, external environment information can be acquired weather information based on positional information from air conditioner A. For example, external environment information can be weather information searched in the DB SSI weather database, based on in positional information for air conditioner A stored in the DB BS2 device status data.
[00068] In operation @, the DS2 data analysis engine
Petition 870190097162, of 27/09/2019, p. 81/159
22/68 of the DS data learning server can generate the learning model using the status information acquired from air conditioner A and the information from the external environment as learning data.
[00069] According with various modalities, the mechanism in DS2 data analysis of data learning server DS can also generate O model in learning using at weather information at the time in set a temperature of air conditioner A as data in learning.[00070] Furthermore, O mechanism data analysis DS2
it can also generate a plurality of learning models for each mode of operation of air conditioner A at the time of setting the temperature of air conditioner A.
[00071] For example, the DS2 data analysis engine can generate the learning model available in smart comfort mode, the learning model available in tropical night sleep mode, the learning model available in tropical night sleep mode without ventilation and model learning available in two-stage cooling mode, respectively.
[00072] In addition, the DS data learning server can be run in units of, for example, time, day and month as a modeling period during which the DS data learning server generates the learning model (or updates the learning model) using the learning data, or can be performed at the time of generating a vent, but the modeling period is not limited to the above period.
[00073] The process for the DS data learning server to generate the learning model will be described
Petition 870190097162, of 27/09/2019, p. 82/159
23/68 later in more detail with reference to Figures 4, 5 and 7.
[00074] In operation @, the DS data learning server can store the generated learning model in an analytical DS3 DB. In this case, the learning model may not be a generic learning model, but it may be a learning model configured or built to provide the recommended temperature for air conditioner A.
[00075] With reference to Figure 1B, a procedure of a network system using the learning model generated by the DS data learning server will be described.
[00076] In operation, air conditioner A can receive a control command requesting an execution (for example, AI ON mode) of an artificial intelligence function from user terminal U.
[00077] In operation @, air conditioner A can transmit status information (for example, moment temperature, operating mode and the like) from air conditioner A to cloud server C via the third device (for example , an AP access point). The DS data learning server of cloud server C can acquire the status information from air conditioner A using the DS4 data service API.
[00078] In operation ®, the DS data learning server can enter the status information acquired from air conditioner A as a learning model learned to provide the recommended temperature of air conditioner A stored in analytical DB DS3.
[00079] In operation @, the DS data learning server can reach the recommended temperature conditioner
Petition 870190097162, of 27/09/2019, p. 83/159
24/68 ar A as a result of applying the learning model.
[00080] In operation (10), the DS data learning server can transmit the recommended temperature acquired from air conditioner A to air conditioner A via the third device (for example, AP access point). In addition, in step (10) ’, the DS data learning server can transmit the recommended temperature acquired from air conditioner A to user terminal U.
[00081] In operation @, air conditioner A that received the recommended temperature can set the temperature of air conditioner A as the recommended temperature received.
[00082] In addition, in operation @, the user terminal U having received the recommended temperature can display the recommended temperature received, so that the user can confirm the recommended temperature received. Alternatively, as in operation, the user terminal U having received the recommended temperature can display visual information indicating that the preferred recommended temperature is adopted in comparison with the defined temperature history predetermined by the user.
[00083] Figures 2A and 2B are diagrams showing a configuration of a data learning server according to a disclosure modality.
[00084] The DS data learning server of Figure 2A is a functional block diagram for generating a learning model and the DS data learning server of Figure 2B is a functional block diagram using the generated learning model.
[00085] In Figures 2A and 2B, the DS data learning server may include a communication unit 201, a
Petition 870190097162, of 27/09/2019, p. 84/159
25/68 storage 202 and processor 203.
[00086] The communication unit 201 can communicate with an external device.
[00087] The external device can include at least one external server (for example, a bridge server, a smart home service server or similar) and the air conditioner A.
[00088] The communication unit 201 can communicate with the external device in a wired or wireless way. Wireless communication can include, for example, cellular communication, near field communication or communication by global satellite navigation system (GNSS). Cellular communication may include, for example, long-term evolution (LTE), LTE advancement (LTE-A), code division multiple access (CDMA), broadband CDMA (WCDMA), universal mobile telecommunications system (UMTS) ), wireless broadband (WiBro), global mobile communications system (GSM) or similar. Near-field communication can include, for example, wireless fidelity (WiFi), direct WiFi, light fidelity (LiFi), Bluetooth, low-power Bluetooth (BLE), Zigbee, near-field communication (NEC), secure magnetic transmission , radio frequency (RE) and body area network (BAN). Communication unit 201 can also be referred to as a communicator.
[00089] The DS data learning server may include storage 202. Storage 202 may store the learning model generated by the DS data learning server.
[00090] Storage 202 may include volatile and / or non-volatile memory. Volatile memory can include, for example,
Petition 870190097162, of 27/09/2019, p. 85/159
26/68 a random access memory (RAM) (for example, DRAM, SRAM or SDRAM). Non-volatile memory can include, for example, a programmable read-only memory (OTPROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a Mask ROM, flash ROM, flash memory, hard disk or solid state drive (SSD).
[00091] The 203 processor may include one or more of a central processing unit, an application processor, a graphics processing unit (GPU), a camera image signal processor and a communication processor (CP). According to one embodiment, processor 203 can be implemented as a chip system (SoC) or a packaged system (SiP). The 203 processor can run, for example, an operating system or an application program to control at least one other component (for example, hardware or software component) of the data learning server (DS) connected to the 203 processor and can run various data processes and operations. Processor 203 can load a command or data received from other components (e.g. communication unit 201) into volatile memory and process the loaded command or data and can store the resulting data in non-volatile memory.
[00092] Figures 2A and 2B are diagrams showing the configuration of a data learning server according to the mode of disclosure.
[00093] The DS data learning server of Figure 2A is a functional block diagram for generating a learning model and the DS data learning server of
Petition 870190097162, of 27/09/2019, p. 86/159
27/68
Figure 2B is a functional block diagram using the generated learning model. [00094] With reference to Figures 2A and 2B, the DS data learning server can include communication unit 201, storage 202 and processor 203. [00095] Communication unit 201 can communicate with the external device. [00096] The external device can include at least one external server (for example, a bridge server, a smart home service server or similar) and the air conditioner A. [00097] Communication unit 201 can communicate with the external device in a wired or wireless way of communication. Wireless communication can include, for example, cellular communication, near-field communication or global satellite navigation system (GNSS) communication. The cellular communication unit may include, for example, long-term evolution (LTE), LTE advancement (LTE-A), code division multiple access (CDMA), broadband CDMA (WCDMA), universal mobile telecommunications system (UMTS), wireless broadband system (WiBro), global mobile communications system (GSM) or similar. Near-field communication can include, for example, wireless fidelity (WiFi), direct WiFi, light fidelity (LiFi), Bluetooth, low-power Bluetooth (BLE), Zigbee, near-field communication (NEC), secure magnetic transmission , radio frequency (RE) and body area network (BAN). [00098] The DS data learning server can include storage 202. Storage 202 can store the model
Petition 870190097162, of 27/09/2019, p. 87/159
28/68 of learning generated by the DS data learning server.
[00099] Storage 202 may include volatile or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) (for example, DRAM, SRAM or SDRAM). Non-volatile memory may include, for example, a programmable read-only memory (OTPROM), a programmable read-only memory (FROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a mask ROM, a flash ROM, a flash memory, a hard disk or a solid state drive (SSD).
[000100] The 203 processor may include one or more of a central processing unit, an application processor, a graphics processing unit (GPU), a camera image signal processor and a communication processor (CP). According to one embodiment, processor 203 can be implemented as a chip system (SoC) or a packaged system (SiP). The 203 processor can run, for example, an operating system or an application program to control at least one other component (for example, hardware or software component) of the data learning server (DS) connected to the 203 processor and can run various data processes and operations. Processor 203 can load a command or data received from other components (e.g. communication unit 201) into volatile memory and process the loaded command or data and can store the resulting data in non-volatile memory.
[000101] The processor 203 of Figure 2A can be described as a functional block diagram to generate a model of
Petition 870190097162, of 27/09/2019, p. 88/159
29/68 learning.
[000102] In Figure 2A, processor 203 may include a learning data acquisition unit 203a and a model learning unit 203b.
[000103] The learning data acquisition unit 203a can acquire the temperature set in air conditioner A and the moment temperature of air conditioner A, at the time of setting the temperature through communication unit 201. For example, the learning data acquisition unit 203a can acquire the defined temperature and the moment temperature of the BS bridge server communicatively connected to air conditioner A. Alternatively, the learning data acquisition unit 203a can also acquire the defined temperature and temperature moment of air conditioner A or the third device communicatively connected to air conditioner A.
[000104] In addition, the learning data acquisition unit 203a can further acquire information from the external environment via communication unit 201. Information from the external environment can include at least one external temperature and one external humidity. For example, the learning data acquisition unit 203a can acquire information from the external environment of the SS smart home service server communicatively connected to an external content that provides the CP server.
[000105] The 203b model learning unit can generate or update the learning model using the defined set temperature and the current temperature. When the learning data acquisition unit 203a acquires further information from the external environment, the learning unit
Petition 870190097162, of 27/09/2019, p. 89/159
30/68 model 203b learning can generate or update the learning model using the set temperature, the moment temperature and the external environment information. In addition, when the learning data acquisition unit 203a still acquires the time information when defining the air conditioner temperature A, the learning model unit 203b can generate or update the learning model using the defined temperature, the current temperature and time information.
[000106] Storage 202 can store the learned learning model to provide the recommended temperature to be adjusted in air conditioner A as the result of generating or updating the learning model.
[000107] On the other hand, when the model 203b learning unit generates or updates a plurality of learning models for each mode of operation of air conditioner A, storage 202 can store a plurality of learning models, respectively.
[000108] Processor 203 of Figure 2B can be described as the functional block diagram for using the learning model.
[000109] In Figure 2B, processor 203 may include a recognition data acquisition unit 203c and a model applicator 203d. In this case, storage 202 can store the learned learning model to provide the recommended temperature to be set in air conditioner A.
[000110] In Figure 2B, the recognition data acquisition unit 203c can acquire the air conditioner moment temperature A.
Petition 870190097162, of 27/09/2019, p. 90/159
31/68 [000111] The model 203d applicator can insert the moment temperature acquired in the storage learning model 202 and acquire the recommended temperature to be adjusted in air conditioner A.
[000112] When the recognition data acquisition unit 203c acquires further information from the external environment, the model applicator 203d can insert the current temperature and external information into the learning model to acquire the recommended temperature to be adjusted in the air conditioner A.
[000113] Furthermore, when storage 202 stores a plurality of learning models for each air conditioner operating mode A, model 203d applicator can set the moment temperature for the learning model corresponding to the current operating mode of air conditioner A to get the recommended temperature of air conditioner A.
[000114] Communication unit 201 can transmit the recommended temperature acquired to the external device. The external device can be, for example, air conditioner A or a third device connected communicatively to air conditioner A.
[000115] Figures 3A and 3B are flowcharts of a network system according to a disclosure modality.
[000116] The network system flowchart shows a data flow procedure between air conditioner A, user terminal U and cloud server C.
[000117] Referring to Figures 3A and 3B, the network system flowchart may include a 351 data import procedure for importing learning data, a
Petition 870190097162, of 27/09/2019, p. 91/159
32/68 procedure 352 to generate a data model based on the learning data, a procedure 353 to operate the artificial intelligence function and a procedure 354 to configure the preferred modes for each function.
[000118] In Figure 3A, air conditioner A may include a microcomputer 301 and a near-field communication module (e.g., Wi-Fi module) 302. Microcomputer 301 corresponds to processor 203 of Figures 2A and 2B, and the near field communication module 302 can correspond to the communication unit 201 of Figures 2A and 2B. Air conditioner A can communicate with user terminal U and cloud server C over the network using the near field communication module 302. In addition, air conditioner A can receive the recommended temperature, recommended by the server at cloud C via API call to near field communication module 302 and set the air conditioner temperature A, depending on the recommended temperature.
[000119] The user terminal U can include a mobile application (or mobile application) 303. The mobile application 303 can define the artificial intelligence function and operating mode of air conditioner A and perform the function of displaying the recommended temperature provided by the C cloud server on the U user terminal.
[000120] The C cloud server can include the BS bridge server, the database server (304) and the DS data learning server. Database server 304 may be a part of the BS bridge server or a third server physically separate from the BS bridge server.
[000121] First, in operation 311, the user terminal U can receive user input to change (or define) the
Petition 870190097162, of 27/09/2019, p. 92/159
33/68 desired temperature via the 303 mobile app. The 303 mobile app can be, for example, an app that provides a user interface to control air conditioner A.
[000122] In operation 312, depending on the user input, the user terminal U can transmit a control command to the microcomputer 301 through the near field communication module 302 to set the air conditioner A to the desired temperature.
[000123] Alternatively, in operation 311 ', the user can change the desired temperature using the Ub remote control device. In operation 312 ', the remote control device Ub can transmit the control command to set air conditioner A as the desired temperature for microcomputer 301 according to the user's change input.
[000124] In operation 313, microcomputer 301 of air conditioner A can generate a desired temperature change event in response to the user's desired temperature change request and transmit the desired temperature change event generated to the BS bridge server via near field communication module 302 At this time, the desired temperature change event can include event data. Event data can include, for example, status information for air conditioner A. Status information for air conditioner A can include a desired temperature (or set temperature) and a moment temperature at the time of setting the temperature desired.
[000125] In addition, event data may include, for example,
Petition 870190097162, of 27/09/2019, p. 93/159
34/68 example, operating mode information and air conditioner time information A. Operating mode information may include, for example, information indicating the mode of operation of air conditioner A at the time of receiving the user control command or the air conditioner operating mode A at the time of generating the desired temperature change event. Time information can include, for example, information about the time when the user receives the control command or information about the time when the desired temperature change event is generated.
[000126] In operation 314, the BS bridge server can transmit event data to database server 304. In operation 315, database server 304 can store received event data.
[000127] In operation 316, database server 304 can transmit stored event data to the DS data learning server at regular periods. For example, the database server 304 can transmit event data daily in a daily batch file form. At this time, the daily batch file can include a plurality of event data. For example, when the user's desired temperature change request is generated several times a day, the plurality of event data can be generated, which in turn is stored on the DB 304 server. The plurality of generated event data can be generated transmitted to the DS data learning server when included in the daily batch file.
[000128] In operation 317, the DS data learning server can generate the learning model using the data from
Petition 870190097162, of 27/09/2019, p. 94/159
35/68 events received as learning data. For example, the DS data learning server can generate the learning model using at least a defined temperature of the air conditioner A, the current temperature, the information of the external environment, the information of the mode of operation, and the information of time.
[000129] In the situation in which the learning model was generated, as in operation 318, the user terminal U can receive a user input that activates the artificial intelligence function of air conditioner A. The partial screen 318a shows a part of the screen U terminal user, including the user interface to activate the artificial intelligence function. In the partial screen 318a, the user terminal U can receive a user input that selects an execution object 318b of 'custom operation AI' to activate the AI function.
[000130] In operation 319, depending on the user input, the user terminal U can transmit an activation command for the artificial intelligence function to the microcomputer 301 through the near field communication module 302 to activate the AI function of air conditioner A.
[000131] Based on the command to activate the artificial intelligence function, microcomputer 301 can transmit the status information of the device indicating that the artificial intelligence function of the air conditioner A is activated to the user terminal U via the communication module near field 302 as in operation 320. In this case, air conditioner status information A can be transmitted when included in a notification event. [000132] Alternatively, as in operation 321, the terminal
Petition 870190097162, of 27/09/2019, p. 95/159
36/68 User U can transmit a device information request command by requesting status information from air conditioner A to microcomputer 301 through the near field communication module 302. The device information request command can be transmitted by included, for example, in the message 'GETDEVICE'.
[000133] Based on the device information request command, the microcomputer 301 can transmit the device information response to the user terminal U via the near field communication module 302 as in operation 322. In this case, the information response of the device may include the artificial intelligence configuration information indicating that the artificial intelligence function of air conditioner A is configured to be activated as the status information of air conditioner A.
[000134] That is, considering the situation where there is a plurality of user terminals U to control the artificial intelligence function of air conditioner A, air conditioner A can notify the user terminal U about whether the artificial intelligence function of air conditioner A is activated periodically or when generating the event. [000135] As such, when the artificial intelligence function of air conditioner A is activated, the user terminal U can receive the user input to define the operating mode.
[000136] With reference to Figure 3B, in operation 323, the user terminal U can receive the user input requesting the execution of the intelligent comfort mode.
[000137] In operation 324, depending on the user input, the user terminal U can transmit the intelligent comfort control command to the 301 microcomputer through the module
Petition 870190097162, of 27/09/2019, p. 96/159
37/68 near-field communication 302 to run air conditioner A's intelligent comfort mode.
[000138] Based on the intelligent comfort control command, microcomputer 301 can transmit the recommended temperature request command (or preferred temperature) to the DS data learning server via the near field communication module 302, as in operation 325. At that time, the recommended temperature request The command can include, for example, the air conditioner moment temperature A as the air conditioner status information A. Alternatively, the recommended temperature request command can include still at least one of the operating mode information indicating the current operating mode and the position information of the air conditioner A.
[000139] In operation 326, the DS data learning server can achieve the recommended air conditioner temperature A as a result of applying the air conditioner status information learning model A. That is, the air learning server DS data can insert air conditioner status information A into the learning model stored on the DS data learning server to achieve the recommended temperature of air conditioner A.
[000140] In this case, the DS data learning server can apply the status information of the air conditioner A to the learning model corresponding to the mode of operation of the air conditioner A, based on the information of the mode of operation of the air conditioner. air A to acquire the recommended temperature of air conditioner A. In mode, the
Petition 870190097162, of 27/09/2019, p. 97/159
38/68 DS data learning server can acquire the recommended temperature of air conditioner A by applying the status information of air conditioner A to the learning model corresponding to the intelligent comfort mode. [000141] Once the recommended temperature is acquired, in operation 327, the DS data learning server can transmit the recommended temperature acquired to the microcomputer 301 through the near field communication module 302.
[000142] In operation 328, microcomputer 301 that receives the recommended temperature can change the recommended temperature to the set temperature. Then, microcomputer 301 can control air conditioner A, depending on the altered temperature set.
[000143] On the other hand, if there is no response from the DS data learning server for a predetermined time (for example, 30 seconds) 329 after microcomputer 301 requests the recommended temperature for the DS data learning server, in operation 330 , microcomputer 301 can maintain the existing set temperature. The existing set temperature can be, for example, a predetermined temperature before the user input to request the execution of the intelligent comfort mode, the predetermined temperature corresponding to the current operating mode (for example, intelligent comfort mode) or similar.
[000144] Figure 4 is a table that shows an example of a generation of a learning model according to a dissemination modality.
[000145] With reference to Figure 4, the DS data learning server can perform a 404 learning procedure
Petition 870190097162, of 27/09/2019, p. 98/159
39/68 using different learning data 403, depending on type 401 of air conditioner A and mode 402 of air conditioner A. For example, type 401 of air conditioner A may include a type of air conditioner of floor (FAC) (or support type air conditioner) and a type of room air conditioner (wall mounted type air conditioner) (RAC). In this case, the DS data learning server can generate the learning models corresponding to each of the intelligent comfort modes, tropical night sound suspension mode and tropical ventilation sound suspension mode without ventilation as the conditioner operation mode. floor air. In addition, the DS data learning server can generate the learning models corresponding to each of the two-stage cooling modes, tropical nighttime sound suspension mode and tropical ventless nighttime sound suspension mode as the operating mode. of the ambient air conditioner.
[000146] If each learning model according to the 404 learning procedure, considering type 401 of air conditioner A and mode 402 of air conditioner A, is generated, the DS data learning server can use the model to acquire the recommended temperature. In this case, the recommended temperature can be acquired considering a 405 configuration range for each operating mode. For example, when the recommended temperature acquired by the DS data learning server is outside the 405 configuration range, the temperature in the 405 configuration range closest to the recommended temperature can be determined as the recommended end temperature.
Petition 870190097162, of 27/09/2019, p. 99/159
40/68 [000147] Describing an example of the learning model generation procedure in smart comfort mode 411 with reference to Figure 4, the internal temperature (or moment temperature) and the desired temperature (or set temperature) can be used . In that case, the ambient temperature can be an ambient temperature measured at the time of changing the desired temperature. In addition, as learning data, data imported during a specific period of time can be used. The specific time period can be, for example, data imported in a specific year, a specific month or a specific season. Specific data can be imported based on information from the air conditioner temperature setting history of unspecified users using products that are the same or similar to air conditioner A, as well as the user of air conditioner A. At that time, the unspecified users may be limited to, for example, a user in the same or similar area or in the same environment or similar to that of air conditioner A.
[000148] In intelligent comfort mode 411, the DS data learning server can use the current temperature (or room temperature), the external temperature, the external humidity and the desired temperature as learning data. [000149] In addition, the DS data learning server can use information from the external environment based on local information from air conditioner A as learning data. On the other hand, when the DS data learning server may not confirm local information for air conditioner A, the data learning server can generate, learn and renew the learning model
Petition 870190097162, of 27/09/2019, p. 100/159
41/68 using the moment temperature and the desired temperature as learning data.
[000150] The DS data learning server can acquire the recommended temperature to be configured in air conditioner A using the generated, learned and renewed learning models.
[000151] In this case, if the recommended temperature acquired is outside the range of 22 ° C to 26 ° C, the DS data learning server can determine the recommended final temperature, considering the setting range.
[000152] For example, if the recommended temperature acquired using the learning model is less than 22 ° C, the DS data learning server can determine that the recommended temperature is 22 ° C. In addition, if the recommended temperature acquired with the learning model is greater than or equal to 26 ° C, the DS data learning server can determine that the recommended temperature is 26 ° C [000153] According to various modalities, when generating In the learning model, the DS data learning server can also give weight to the newly imported learning data to generate the learning model.
[000154] Figure 5 is a diagram that shows an example of how to give weight to a learning data according to a disclosure modality.
[000155] With reference to Figure 5, the DS data learning server can assign weights differently to the imported learning data for 1 day, 2 days and 3 days, respectively, such as 501, 502 and 503 in Figure 5) [000156] For example, at 501 in Figure 5, the DS data learning server can assign a weight of 0.8 to all
Petition 870190097162, of 27/09/2019, p. 101/159
42/68 data (for example, data imported from unspecified users) from last year and assign a weight of 0.2 to the user's personal data (desired temperature and user moment temperature or similar) of the imported air conditioner A on the first day. Likewise, at 502 of Figure 5, the DS data learning server can assign a weight of 0.8 to all of the data from last year and the personal data of the user of air conditioner A that is imported on the first day, and a weight of 0.2 to the personal data of the user of the imported air conditioner A on the second day. In addition, at 503 of Figure 5, the DS data learning server can assign a weight of 0.8 to all data from last year and the personal data of air conditioner user A that is imported on the first day and on second day and a weight of 0.2 for the user personal data imported on the third day.
[000157] On the other hand, the aforementioned weight value is just an example, and the DS data learning server can be preset to have different values by a manufacturer, manager, operating system, application provider or similar to the learning of Dice. For example, in Figure 5, instead of a weight of 0.8 and a weight of 0.2, a weight of 0.9 and a weight of 0.1 can be used. As another example, in Figure 5, instead of a weight of 0.8 and a weight of 0.2, a weight of 0.7 and a weight of 0.3 can be used.
[000158] On the other hand, the weight mentioned above can be a variable type that is changed depending on the situation and not a predetermined fixed type.
[000159] In this case, the weight can be changed manually by the administrator of the DS data learning server, the user of the air conditioner or similar, or it can be
Petition 870190097162, of 27/09/2019, p. 102/159
43/68 changed automatically, depending on the specific condition. For example, as the total amount of imported learning data increases, the weight of the most recently imported personal data can also be increased accordingly.
[000160] Figure 6 is a diagram showing a structure of a cloud server according to a disclosure modality.
[000161] The C cloud server may include a doser 601, a data collector from the content provider (CP) 602, a manufacturer of CSV 603, a manufacturer of model 604 and a learning temperature providing API 605 of the server. Cloud server components 601 to 604 described above use and process data stored in cloud server C storage (or database) to generate the appropriate recommended temperature for air conditioner A.
[000162] First, the C cloud server can store, in a 651 device status store, the device status data, including the status information of the air conditioner A acquired depending on the generation of the status change event of the device. air conditioner A. The 651 device status store can correspond to the DB BS2 device status data of Figures IA and 1B, for example. The C cloud server can acquire the status information stored in the 651 device's status store every predetermined period (for example, every day) and store raw data generated depending on a certain criterion (for example, by date) in a 652 object storage.
[000163] The doser 601 of the C cloud server can acquire and
Petition 870190097162, of 27/09/2019, p. 103/159
44/68 filter the row data in the object store 652 and store the filtered data in a distributed environment database (for example, not just SQL DB, NoSQL DB) 653. The filtered data can be, for example, data including air conditioner device status data A or status information extracted from metadata.
[000164] In addition, the CP 602 data collector can store weather data, including weather information imported from the external content server CP in an object storage 654.
[000165] * 180 The CSV marker 603 of the C cloud server refines the data acquired from the data of the distributed environment of DB objects 653 and from the storage of objects 654 to generate data of a specific format (for example, CSV format) suitable for the model generation and learning storage the data generated in the 655 object store.
[000166] The model maker 604 can acquire data of a specific format from the 655 object store, generate the learning model using the data and store the learning model generated in the 656 object store.
[000167] The C cloud server can temporarily store the learning model stored in the 655 object store in a 657 cache, which is a high-speed storage memory when the use of the learning model is required.
[000168] Under the situation where the use of the learning model is necessary, the recommended temperature provided by API 605 of cloud server C can acquire the recommended temperature of air conditioner A using the learning model stored in cache 657.
Petition 870190097162, of 27/09/2019, p. 104/159
45/68 [000169] The cloud server C can transmit the recommended temperature acquired through the recommended temperature acquired, providing API 605 for the mobile applications of air conditioner A and user terminal U.
[000170] Meanwhile, in Figure 6, for convenience of explanation, object stores 652, 654, 655 and 656 are indicated by different reference numbers, but the object stored in 652, 654, 655 and 656 can denote the same object storage or can mean two or more distributed object stores.
[000171] Figures 7A and 7B are diagrams showing a procedure for generating a learning model according to a disclosure modality.
[000172] The learning model can be generated using the artificial intelligence algorithm. For example, the learning model can be generated using a decision tree algorithm, a support vector machine algorithm, a linear discrimination analysis algorithm, a genetic algorithm or a neural network algorithm that simulates neurons in a network human neural. The neural network algorithm can include a plurality of weighted network nodes. The plurality of network nodes can establish a connection relationship for neurons to simulate the synaptic activity of transmitting and receiving signals through synapses. In addition, the learning model can be generated using a deep learning algorithm developed in the neural network algorithm. In the deep learning algorithm, the plurality of network nodes can transmit and receive data, depending on the relationship of the convolution connection, while it is located at different depths (or
Petition 870190097162, of 27/09/2019, p. 105/159
46/68 layers). The learning model can include models such as deep neural network (DNN), a recurrent neural network (RNN) and a bidirectional recurrent deep neural network (BRDNN) can be provided, but is not limited to the example mentioned above. [000173] For convenience of description, the disclosure describes a method for providing a recommended temperature using linear regression as an algorithm used for generating the learning model.
[000174] The DS data learning server can derive the learning model, such as the following Equation 1, according to the linear regression algorithm y = aO + alxl + a2x2 + a3x3 ... Equation 1 [000175] In Equation 1 above, y is a variable related to the temperature defined in air conditioner A, and aO, ai, a2 and a3 are constant values. In addition, xl is a variable related to the moment temperature, x2 is a variable related to the external temperature and x3 is a variable related to the external humidity.
[000176] To facilitate understanding, the learning model in the event that the number of learning variables (or learning elements) in Equation 1 above is two is expressed by Equation 2 below.
y = aO + alxl ... Equation 2
[000177] In this if Figure table 7A show The set temperature (for example, temperature in adjustment of user) 712, depending on temperature time (or temperature environment, room temperature) 711 of
air conditioner.
[000178] Based on the linear regression algorithm, the server
Petition 870190097162, of 27/09/2019, p. 106/159
47/68 DS data learning can derive a learning model which is a calculation expression that expresses the relationship of the set temperature 712, depending on the moment temperature 711.
[000179] This is shown in a graph as shown in Figure 7B.
[000180] With reference to Figure 7B, the moment temperature 711 and the set temperature 712 in Figure 7A can correspond to the 'X' mark on the graph when they are plotted on the x and y axes.
[000181] In this case, a linear regression line 721 using a linear regression algorithm can be acquired so that a sum of errors from the plurality of 'X' markers is small. That is, in Equation 2 above, constant values aO and al can be calculated with the smallest difference between the set temperature 712 of air conditioner A and the predicted temperature.
[000182] An example of the linear regression model that reflects the calculated constant value is as follows.
y = 29.91840623 + (-0.3717125) xl ... Equation 3 [000183] Therefore, the DS data learning model can provide air conditioner A with the recommended temperature according to the recommended temperature request command of the air conditioner A based on the following Equation 3.
[000184] For example, when the current ambient temperature around air conditioner A is 26 ° C, the recommended temperature provided by the learning model in Equation 3 above can be 19 ° C.
[000185] According to various modalities, the model of
Petition 870190097162, of 27/09/2019, p. 107/159
48/68 learning can be continually renewed (or updated). [000186] For this purpose, the DS data learning server may also include a model renewer (not shown). The model renewer can determine whether the learning model is renewed by analyzing the relevance between the basic learning data used in the learning model that was previously built and the newly introduced learning data. At that time, relevance can be determined based on the area and time when the learning data is generated, on the schedule, on the model of the air conditioner that provides the learning data and the like.
[000187] For example, the model renewer can continually renew the learning model already built using the user's temperature setting history to set the air conditioner temperature A, the user's change history to the recommended temperature or something similar to the learning data.
[000188] According to various modalities, the learning model can be stored in the storage of air conditioner A, not on a separate server. In this case, the learning model built on the DS data learning server can be transmitted to the air conditioner A periodically or when generating the event.
[000189] When the learning model is provided in air conditioner A, air conditioner A can acquire the recommended temperature using the stored learning model. For example, air conditioner A can acquire the recommended temperature by entering the currently detected temperature in the learning model. In this case, the
Petition 870190097162, of 27/09/2019, p. 108/159
49/68 air conditioner A can acquire the recommended temperature using the moment temperature detected without user intervention and can automatically set the temperature of air conditioner A, depending on the recommended temperature. [000190] Figure 8 is a block diagram showing a
configuration of a conditioner air of a deal with The modality of[000191] With disclosure.reference to Figure 8, the air conditioner THE can include a temperature sensor 810, one fan in blow 82 0, a communication unit 830, one storage
840 and a processor 850. In various embodiments, air conditioner A may omit at least one of the components described above, or may additionally include other components.
[000192] The temperature sensor 810 can detect the temperature of the room around air conditioner A.
[000193] The 820 blowing fan can discharge the cooling air to the outside through an opening / closing portion (not shown). Alternatively, in the non-vented mode, the blowing fan 820 can discharge the cooling air to the outside through a plurality of micro-holes (not shown) at a predetermined flow rate or less. At this time, the predetermined flow rate can be 0.25 m / s or less, preferably 0.15 m / s or less.
[000194] The 830 communication unit can communicate with the external device. At this time, the external device can include at least one C cloud server, the DS data learning server and the U user terminal. The communication of the communication unit 830 with a
Petition 870190097162, of 27/09/2019, p. 109/159
50/68 external device may include communication with the external device through the third device or the like. For example, the communication unit 830 can receive a remote control signal to control the air conditioner A from the user's U terminal.
[000195] The 830 communication unit can communicate with an external device via wired or wireless communication. For example, the communication unit 830 can communicate with a control terminal device via cellular communication, near field communication and an Internet network, as well as a port to be connected by a cable, and carry out the communication according to standards such as universal serial bus Communication (USB), Wi-Fi, Bluetooth, Zigbee, infrared data association (IrDA), RF like UHF and VHF and ultra-broadband communication (UWB).
[000196] Storage 840 stores various software and programs to perform the function of air conditioner A. Specifically, storage 840 can store a temperature control algorithm according to a plurality of operating modes. The temperature control algorithm can include the change in the set temperature, the intensity of the ventilation speed, the direction of the ventilation speed or similar, depending on a predetermined period for each mode of operation. In addition, according to the disclosure, storage 840 can store the learning model learned based on the set temperature and the current temperature.
[000197] The 850 processor can read the program or the like stored in the 840 storage. Specifically, to perform the function of air conditioner A, the 850 processor
Petition 870190097162, of 27/09/2019, p. 110/159
51/68 can read programs including a series of readable instructions and operate the air conditioner according to the set temperature.
[000198] The 850 processor can detect the pressure and / or temperature of the refrigerant in the internal heat exchanger (not shown) to detect whether the air conditioner is normally run. For example, the 850 processor can detect whether the tube of the internal heat exchanger is damaged or covered with ice and whether the water generated by the condensation of vapor in the air is properly removed.
[000199] Processor 850 can control a speed of the blowing fan 820. Specifically, the processor 850 can control the moment temperature measured by the temperature sensor 810 and the speed at which the blowing fan 820 rotates depending on the set temperature. Specifically, processor 850 can control the speed at which the blowing fan 820 spins depending on the difference between the current temperature and the set temperature. For example, if the difference between the current temperature and the set temperature is large, the rotation speed of the 820 blowing fan is controlled to quickly reach the set temperature quickly and if the difference between the room temperature and the set temperature is small or the room temperature reaches the set temperature, the room temperature drops very dramatically, the rotation speed of the 820 blowing fan can be slow so that the compressor of an external unit is not turned off. For example, the 850 processor can control the rotation speed of the 820 blowing fan between 500 RPM and 900 RPM.
[000200] The 850 processor can control the drive
Petition 870190097162, of 27/09/2019, p. 111/159
52/68 communication 830 to transmit the current temperature and the defined temperature detected by the temperature sensor 810 to an external device.
[000201] In addition, processor 850 can control communication unit 830 to receive the recommended temperature received from the external device and control the recommended temperature acquired through communication unit 830 to be set in air conditioner A as the set temperature.
[000202] In addition, processor 850 can control communication unit 830 to transmit the moment temperature detected by temperature sensor 810 to the external device and can receive the recommended temperature depending on the transmission of the moment temperature from the external device and set the recommended temperature received in an air conditioner. In this case, the recommended temperature can be the result of applying the moment temperature detected by the temperature sensor 810 to the learning model learned using a plurality of defined temperatures and a plurality of current temperatures defined in air conditioner A. In this case, the external device can include at least one C cloud server, the DS learning model server and the third device communicatively connected to the C cloud server or the DS learning model server.
[000203] In wake up with several modalities, could have O system in network that includes the conditioner of air A and O server of model DS learning process generating the model in learning using the data of learning acquired of
air conditioner A.
Petition 870190097162, of 27/09/2019, p. 112/159
53/68 [000204] In this case, the air conditioner A of the mains system can include the temperature sensor 810 upon detection of the current temperature, the blowing fan 820 discharging the cooling air to the outside and the communication unit 830 capable of communicating with an external device. Air conditioner A may include processor 850 that controls communication unit 830 to transmit the temperature set in air conditioner A and the moment temperature detected by temperature sensor 810 to an external device.
[000205] In this case, the external device may include at least one C cloud server, the DS learning model server and the third device connected communicatively to the C cloud server or the DS learning model server.
[000206] In addition, the DS learning model server of the network system may include the learning data acquisition unit (e.g., learning data acquisition unit 203a of Figure 2A) that acquires the moment temperature and the set temperature transmitted from air conditioner A, the learning unit model (for example, model 203b learning unit in Figure 2A) that generates the learning model using the set temperature and the moment temperature, and storage (for example , storage 202 of Figure 2A) which stores the learned learning model to provide the recommended temperature of air conditioner A as a result of generating the learning model.
[000207] According to various modalities, there may be a network system that includes air conditioner A and
Petition 870190097162, of 27/09/2019, p. 113/159
54/68 DS learning model server, providing the recommended temperature using the recognition data acquired from air conditioner A. [000208] In this case, the air conditioner A of the network system includes the temperature sensor 810 which detects the moment temperature, the blowing fan 820 discharging the cooling air to the outside, the communication unit 830 capable of communicating with the external device and the processor 850 controlling the communication unit 830 to transmit the moment temperature detected by the sensor temperature 810 for the external device.
[000209] In this case, the external device can include at least one C cloud server, the DS learning model server and the third device connected communicatively to the C cloud server or the DS learning model server.
[000210] In addition, the DS learning model server may include storage (for example, storage 202 in Figure 2B) storing learned learning models to provide the recommended temperature of air conditioner A, the data acquisition unit recognition unit (for example, recognition data acquisition unit 203c of Figure 2B) acquiring the moment temperature of the air conditioner A and the model applicator (for example, the model 203d applicator of Figure 2B) acquiring the recommended temperature air conditioner A by inserting the current temperature as a learning model and a communication unit (for example, communication unit 201 in Figure 2B) transmitting the recommended temperature acquired to the external device. The external device
Petition 870190097162, of 27/09/2019, p. 114/159
55/68 can include air conditioner A or the third device connected communicatively to air conditioner A. In addition, the external device can include user terminal U or the third device connected communicatively to user terminal U to transmit the recommended temperature.
[000211] Figure 9 is a block diagram showing a configuration of a user terminal according to a disclosure modality.
[000212] With reference to Figure 9, the user terminal U can include a display 910, a communication unit 920, an input 930, a storage 940 and a processor 950.
[000213] The display 910 can visually provide information to the user of the user terminal U. For example, the display 910 can display a screen including the artificial intelligence operation UI under the control of the 950 processor.
[000214] The communication unit 920 can establish a channel of the communication unit wired or wireless between the user terminal U and the external device and support the performance of the communication through the established communication channel. The external device can include at least one of, for example, the C cloud server, the DS learning model server, and the third device communicatively connected to the C cloud server or the DS learning model server.
[000215] The communication unit 920 can communicate with the external device through the near field communication networks (for example, Bluetooth, WiFi direction or infrared data association (IrDA) or similar) or through the remote communication networks ( for example, cellular network, Internet or computer network (for example, LAN or WAN) or similar) using
Petition 870190097162, of 27/09/2019, p. 115/159
56/68 wireless communication modules (for example, cellular communication module, local area wireless communication module and global navigation satellite system (GNSS) communication module) or the wired communication module (eg example, local area network (LAN) communication module or power line communication module). Various types of communication modules described above can be implemented as a single chip or each can be implemented as a separate chip.
[000216] Input 930 can receive commands or data to be used for components (for example, 950 processor) of user U terminal from outside (for example, user) of user U terminal. Input 930 can include, for example example, a button, a microphone, a touch panel or the like. Input 930 can transmit the generated user input signal depending on the user input to control the user terminal U to the 950 processor.
[000217] The storage 940 can store various data used by at least one component (for example, processor 950) of the user terminal U, for example, software (for example, a program) and can store the input data or the data of output for the command associated with it. Storage 940 may include volatile and / or non-volatile memory.
[000218] The program is software stored in storage
940 and may include, for example, an operating system, middleware or application.
[000219] Processor 950 can drive, for example, software (for example, program) stored in storage 940 to control at least one other component (for example
Petition 870190097162, of 27/09/2019, p. 116/159
57/68 example, hardware or software components) of the U user terminal connected to the 950 processor and perform various data processing and operations. The 950 processor can load a command or data received from other components (for example, communication unit 920) into volatile memory and process the loaded command or data and can store the resulting data in non-volatile memory. According to one embodiment, the 950 processor can include main processors (for example, a central processing unit or an application processor) and subprocessors (for example, a graphics processor, an image signal processor, a hub processor 'sensor or a communication processor) which are operated independently of the main processor and, in addition or alternatively, use less power than the main processor or are specialized in the designated functions. The subprocessor can be operated separately from the main processor or can be operated while it is being incorporated.
[000220] According to various modalities, if the user input signal, depending on the user input that selects the user interface of the artificial intelligence operation included in the screen provided by the screen 910, is received via input 930, the processor 950 can control the communication unit 920 for transmitting the artificial intelligence operation request signal corresponding to the artificial intelligence operation user interface for air conditioner A. If the recommended temperature set in air conditioner A, depending on the operation request signal of artificial intelligence, is acquired through the 920 communication unit, the 950 processor can
Petition 870190097162, of 27/09/2019, p. 117/159
58/68 control display 910 to display the recommended temperature acquired. At this time, the recommended temperature can be acquired as a result, allowing air conditioner A to apply the moment temperature of air conditioner A to the learning model. In this case, the 950 processor can control the screen 910 so that the user can display the set temperature, which has been set in air conditioner A in the past, at the current temperature, along with the recommended temperature.
[000221] According to various modalities, there may be a network system including air conditioner A and user terminal U controlling air conditioner A.
[000222] In this case, if the user input signal, depending on the user input, selects the user interface of the artificial intelligence operation UI included in the screen provided by the display 910 of the user terminal U is received through input 930, the processor 950 can control the communication unit 920 to transmit the artificial intelligence operation request signal corresponding to the UI of the artificial intelligence operation UI to the air conditioner A.
[000223] If air conditioner A receives a request for artificial intelligent operation via communication unit 830 of air conditioner A, processor 850 of air conditioner A can control communication unit 830 to transmit the moment temperature of air conditioner A to the external device. Processor 850 for air conditioner A can control communication unit 830 to receive the recommended temperature, depending on the current temperature transmission from the external device. The 850 processor can set the
Petition 870190097162, of 27/09/2019, p. 118/159
59/68 recommended temperature received via communication unit 830 in air conditioner A. In this case, the recommended temperature can be the result obtained by applying the current temperature to the learning model learned based on the plurality of temperatures previously defined in the air conditioner. air A and the plurality of prevailing temperatures. In that case, the external device can include at least one C cloud server, the DS learning model server, and the third device communicatively connected to the C cloud server or DS learning model server.
[000224] Figures 10A and 10B are diagrams showing a screen of a user terminal on which a recommended temperature is displayed, according to a disclosure modality.
[000225] With reference to Figure 10A, the user terminal U can display an air conditioner 1010 control screen by running an application capable of controlling air conditioner A.
[000226] The air conditioner control screen 1010 can include a user interface 1011 turning air conditioner A on / off, a user interface 1012 selecting an air conditioner operating mode A, moment temperature information 1013, information whether the artificial intelligence mode operates 1014, a ventilation port defining the user interface 1015, a ventilation intensity interface 1016, a non-ventilation operator interface 1017, a user interface on whether the air cleaning operation 1018, a artificial intelligence interface of the 1019 interface, a reserve configuration of the 1020 user interface and the like.
Petition 870190097162, of 27/09/2019, p. 119/159
60/68 [000227] In this case, when the 1010 air conditioner control screen is out of reach of the user terminal user interface screen display window, the user can display the 1110 air conditioner control screen, which is out of reach of the viewport, in the viewport range through a drag gesture.
[000228] With reference to Figures 10A and 10B, in this situation, if the user input to select the artificial intelligence configuration UI 1019 is received, the user terminal U can display the artificial intelligence control screen 1020 in operation mode (for example, example, intelligent comfort mode) of air conditioner A as shown in Figure 10B. The artificial intelligence control screen
1020 may include artificial intelligence UI operation
1021 for the operation in the artificial intelligence mode of the air conditioner A and the information of the artificial intelligence operation 1022 indicating the operation in the artificial intelligence mode of the air conditioner A.
[000229] In this case, if the user input to select the AI 1021 artificial intelligence operation is received, the user terminal U can acquire the recommended temperature defined in the air conditioner based on the user input. For example, the user terminal U can acquire the recommended temperature through the third device (for example, access point (AP)) connected communicatively to the cloud server C.
[000230] The user terminal U can then display the recommended temperature 1023 on the artificial intelligence control screen 1020. At that time, the temperature
Petition 870190097162, of 27/09/2019, p. 120/159
61/68 recommended 1023 can be acquired as a result obtained by allowing air conditioner A to apply the moment temperature of air conditioner A to the DS learning model server, based on user input, selecting the AI artificial intelligence operation 1021.
[000231] The user terminal U can display not only the recommended temperature 1023 on the artificial intelligence control screen 1020, but also the set temperature 1024 that the user of air conditioner A has set directly on air conditioner A in the past. In this case, the recommended temperature 1023 and the set temperature 1034 can be displayed on the graph together to be comparable with each other.
[000232] Figure 11 is a flow chart showing a method for generating a learning model for a data learning server according to a disclosure modality.
[000233] With reference to Figure 11, in operation 1101, the DS data learning server can acquire the temperature defined in air conditioner A and the moment temperature of air conditioner A at the time of setting the temperature. In addition, the DS data learning server can also acquire information from the external environment of air conditioner A.
[000234] At that time, the DS data learning server can acquire the defined temperature and the moment temperature of the BS bridge server communicatively connected to air conditioner A and obtains the external environment information from the communicatively connected SS smart home server. to the external content delivery server (CP).
Petition 870190097162, of 27/09/2019, p. 121/159
62/68 [000235] In addition, the DS data learning server can acquire even more time information when setting the temperature in air conditioner A.
[000236] In operation 1103, the DS data learning server can generate or renew the learning model using the defined acquired temperature and the current temperature.
[000237] When the DS data learning server acquires further information from the external environment, the DS data learning server can generate or renew the learning model using the defined set temperature, the moment temperature and the environment information external.
[000238] Furthermore, when the DS data learning server acquires even more time information at the time of setting the temperature, the DS data learning server can generate or renew the learning model using the defined temperature acquired, the moment temperature and time information.
[000239] In operation 1105, the DS data learning server can store the learned learning model to provide the recommended temperature to be adjusted in air conditioner A as a result of generating and renewing the learning model.
[000240] Meanwhile, the DS data learning server can generate or renew the plurality of learning models for each air conditioner A operating mode. In this case, the DS data learning server can store the plurality of models of learning.
[000241] Figure 12 is a flowchart showing a method for using a learning model of a data learning server according to a disclosure modality.
Petition 870190097162, of 27/09/2019, p. 122/159
63/68 [000242] Referring to Figure 12, in operation 1201, the DS data learning server can store the learned learning model to provide the recommended temperature to be adjusted in air conditioner A.
[000243] In a situation where the learned learning model is stored, in operation 1203, the DS data learning server can acquire the air conditioner moment temperature A. In this case, the DS data learning server can acquire further information about the external environment of air conditioner A.
[000244] In operation 1205, the DS data learning server can insert the moment temperature acquired in the learned learning model to acquire the recommended temperature to be configured in air conditioner A.
[000245] In addition, when the DS data learning server acquires further information from the external environment, the DS data learning server can insert the recommended external temperature and environment information acquired in the learning model to acquire the recommended temperature to be adjusted in air conditioner A.
[000246] Meanwhile, the DS data learning server can store the plurality of learning models for each air conditioner A operating mode. In this case, the DS data learning server can enter the moment temperature acquired in the learning model corresponding to the current operating mode of the air conditioner A and insert the moment temperature acquired in the learning model corresponding to the current operating mode of the air conditioner A to acquire the
Petition 870190097162, of 27/09/2019, p. 123/159
64/68 recommended temperature to be adjusted in air conditioner A.
[000247] In operation 1207, the DS data learning server can transmit the recommended temperature acquired to the external device. The external device can be, for example, air conditioner A or the third device connected communicatively to air conditioner A to transmit the recommended temperature. In addition, the external device can be the user terminal U or the third device connected communicatively to the user terminal U to transmit the recommended temperature.
[000248] Figure 13 is a flow chart showing a method for providing a recommended temperature for an air conditioner A according to a disclosure modality.
[000249] With reference to Figure 13, in operation 1301, air conditioner A can detect the current temperature of air conditioner A.
[000250] Then, in operation 1303, air conditioner A can transmit the currently detected temperature to the external device. For example, air conditioner A can transmit the detected moment temperature to at least one of the C cloud servers, DS learning model server and third device that communicates with the C cloud server or learning model server DS.
[000251] In operation 1305, air conditioner A can receive the recommended temperature, which is the result of applying the moment temperature to the learning model, from the external device, depending on the moment temperature transmission. In this case, the recommended temperature
Petition 870190097162, of 27/09/2019, p. 124/159
65/68 can be the result obtained by applying the moment temperature to the learning model learned based on the plurality of temperatures previously defined in air conditioner A and the plurality of prevailing temperatures.
[000252] In operation 1307, air conditioner A can set the recommended temperature received in the air conditioner.
[000253] Figure 14 is a flow chart showing a method for controlling an air conditioner from a user terminal according to a disclosure modality.
[000254] With reference to Figure 14, in operation 1401, the user terminal U can receive the user input signal, depending on the user input, selecting the user interface of the artificial intelligence operation.
[000255] In operation 1403, the user terminal U can transmit the artificial intelligence operation request signal corresponding to the artificial intelligence operation user interface to air conditioner A in response to the user input signal.
[000256] In operation 1405, user terminal U can acquire the recommended temperature set in air conditioner A as a result of applying the air conditioner moment temperature A to the learning model, depending on the artificial intelligence operation request signal . [000257] In operation 1407, the user terminal U can display the recommended temperature acquired on the screen. In this case, the user terminal U can display the temperature previously set by the user in air conditioner A, together with the recommended temperature, at the current temperature.
Petition 870190097162, of 27/09/2019, p. 125/159
66/68 [000258] Figure 15 is a flow chart of a network system including a user terminal and an air conditioner according to a disclosure modality.
[000259] With reference to Figure 15, in operation 1501, the user terminal U can receive the user input signal, depending on the user input, selecting the user interface of the artificial intelligence operation.
[000260] In operation 1503, user terminal U can transmit the artificial intelligence operation request signal corresponding to the artificial intelligence operation user interface for air conditioner A.
[000261] In operation 1505, air conditioner A can detect the moment temperature of air conditioner A. [000262] Then, in operation 1507, air conditioner A can transmit the detected moment temperature to an external device 1500. The external device can include at least one C cloud server, the DS learning model server, and the third device communicatively connected to the C cloud server or the DS learning model server.
[000263] In operation 1509, air conditioner A can receive the recommended temperature, which is the result of applying the moment temperature to the learning model, from the external device 1500, depending on the moment temperature transmission. In this case, the learning model can be the learning model learned using the plurality of defined temperatures previously defined in air conditioner A and the plurality of prevailing temperatures.
[000264] In operation 1511, air conditioner A can
Petition 870190097162, of 27/09/2019, p. 126/159
67/68 set the recommended temperature received in the air conditioner.
[000265] The disclosed modalities can be implemented as an S / W program that includes instructions stored in a computer-readable storage medium.
[000266] The computer is a device that calls stored instructions from the storage medium and can be operated according to the disclosed modality, depending on the instructions called, and can include the data learning server according to the disclosed modalities or the server external communicatively connected to the server data learning. Alternatively, the computer can include the air conditioner or the external server connected communicatively to the air conditioner, according to the disclosed modalities. [000267] The computer-readable storage medium may be provided in the form of a non-transitory storage medium. The 'non-transitory' means that the storage medium does not include a signal and a chain and is tangible, but the 'non-transitory' does not distinguish whether the data is stored semi-permanently or temporarily in the storage medium. As an example, the non-transitory storage medium can be temporarily stored on media such as record, cache and buffer, as well as non-transitible readable recording media such as CD, DVD, hard drive, Blu-ray disc, USB, internal memory, memory card, ROM and RAM.
[000268] In addition, the method according to the disclosed modalities can be provided as a computer program product.
[000269] The product of the computer program may include an S / W program, a computer-readable storage medium
Petition 870190097162, of 27/09/2019, p. 127/159
68/68 in which the S / W program is stored or a product marketed between a seller and a buyer.
[000270] For example, a computer program product may include a product (for example, downloadable application) in the form of a software program distributed electronically through the data learning server, the air conditioner manufacturer or the market electronic (for example, Google Play Store, AppStore) For electronic distribution, at least part of the software programs can be stored on a storage medium or be generated temporarily. In that case, the storage medium can be a manufacturer or an electronic market server or a storage medium for a relay server.
[000271] Although disclosure modalities have been illustrated and described, the disclosure is not limited to the specific modality mentioned above, but can be modified in various ways by those skilled in the technique to which the disclosure belongs, without departing from the spirit and scope of the disclosure. disclosure, as claimed in the claims. In addition, these changes should also be understood to fall within the scope of the disclosure.
[000272] Although the disclosure has been shown and described with reference according to various modalities of the same, it will be understood by those skilled in the art that various changes in form and details can be made in it without departing from the spirit and scope of the disclosure, as defined by the appended claims and their equivalents.

权利要求:
Claims (14)
[1]
1. DATA LEARNING SERVER, characterized by understanding:
A communicator configured to communicate with an external device;
at least one processor configured to:
acquire a temperature set in an air conditioner and an air conditioner moment temperature when defining a temperature, through the communicator, and generate or renew a learning model using the set temperature and the moment temperature; and a storage configured to store the generated or renewed learning model to provide a recommended temperature set in the air conditioner as a result of generating or renewing the learning model.
[2]
2/14 acquire the set temperature and the current temperature from a bridge server connected communicatively to the air conditioner through the communicator, and acquire the external environment information from an intelligent home service server that is connected communicatively to a server providing external content through the communicator.
2. Data learning server, according to claim 1, characterized in that the at least one processor is still configured to:
acquire external information about the environment and generate or renew the learning model using the information of defined temperature, moment temperature and external environment.
[3]
3/14 to acquire a moment temperature of the air conditioner, and to insert the moment temperature in the learned learning model to acquire the recommended temperature to be adjusted in the air conditioner; and a communicator configured to transmit the recommended temperature to an external device.
3. Data learning server, according to claim 2, characterized in that the information from the external environment comprises at least one of an external temperature and an external humidity at the time of setting the temperature.
[4]
4/14 a communicator configured to communicate with an external device; and at least one processor configured to:
controlling the communicator to receive a recommended temperature, a result obtained by applying a temperature defined in a learning model, and defining the recommended temperature received in the air conditioner, where the learning model is a learning model learned from a plurality of defined temperatures previously defined in the air conditioner.
4. Data learning server, according to claim 2, characterized in that at least one processor is still configured to:
Petition 870190097162, of 27/09/2019, p. 129/159
[5]
5/14 artificial intelligence operation, which is being acquired through the communicator.
5. Data learning server, according to claim 1, characterized in that at least one processor is still configured to:
acquire time information at the time of setting the temperature, and generate or renew the learning model using the set temperature, the moment temperature and the time information.
[6]
6/14 acquire the moment temperature and the set temperature, generate a learning model using the acquired set temperature and the moment temperature, and a storage configured to store the generated learning model to provide a recommended air conditioner temperature as result of the generation of the learning model.
14. NETWORK SYSTEM, characterized by comprising:
an air conditioner; and a learning model server configured to provide a recommended temperature using recognition data acquired from the air conditioner, where the air conditioner comprises:
a fan configured to discharge cooling air outside, a temperature sensor configured to detect an air conditioner's current temperature, an air conditioner communicator configured to communicate with an external device, and at least one air processor air conditioner configured to control the air conditioner communicator to transmit the moment temperature detected by the temperature sensor to the external device, and in which the learning model server comprises:
a storage configured to store a learning model learned to provide the recommended air conditioner temperature,
Petition 870190097162, of 27/09/2019, p. 134/159
6. Data learning server, according to claim 1, characterized in that the at least one processor is further configured to generate or renew a plurality of learning models for each air conditioner operation mode, and in which the storage it is also configured to store the plurality of learning models.
[7]
7/14 at least one server processor configured to:
acquire the moment temperature, and insert the moment temperature into the learning model learned to acquire the recommended temperature of the air conditioner, and a server communicator configured to transmit the recommended temperature to the external device.
15. NETWORK SYSTEM, characterized by comprising:
an air conditioner; and a user terminal configured to control the air conditioner, where the user terminal comprises:
a display configured to display a screen, a terminal communicator configured to communicate with an external device, an input receiver configured to receive user input, and at least one terminal processor configured to control the terminal communicator to transmit a signal request for artificial intelligence operation corresponding to an AI artificial intelligence operation for the air conditioner in response to a user input signal dependent on a user input that selects the AI artificial intelligence operation included in the screen being received by the receiver inlet, where the air conditioner comprises:
a fan configured to discharge the cooling air outside,
Petition 870190097162, of 27/09/2019, p. 135/159
7. DATA LEARNING SERVER, characterized by understanding:
a storage configured to store a learned learning model to provide a recommended temperature to be set as an air conditioner;
at least one processor configured to:
Petition 870190097162, of 27/09/2019, p. 130/159
[8]
8/14 a temperature sensor configured to detect a moment temperature around the air conditioner, an air conditioner communicator configured to communicate with an external device, and at least one air conditioner processor configured to:
control the air conditioner communicator to transmit the moment temperature to the external device and receive a recommended temperature, dependent on a transmission of the moment temperature from the external device in response to the request for intelligence operation
artificial that it is being received by the communicator from conditioner air, and define the recommended temperature received in the conditioner air, andin that recommended temperature is a
result obtained by applying the current temperature to a learning model learned based on a plurality of defined temperatures previously defined in the air conditioner and a plurality of current temperatures.
16. METHOD FOR GENERATING A LEARNING MODEL FROM A DATA LEARNING SERVER, the method characterized by comprising:
to acquire a defined temperature established in an air conditioner and a moment temperature of the air conditioner at the time of setting of the temperature;
generate or renew the learning model using the set temperature and the current temperature; and
Petition 870190097162, of 27/09/2019, p. 136/159
8. Data learning server, according to claim 7, characterized in that at least one processor is additionally configured to:
to acquire external information about the environment, and to insert the moment temperature and the information of the external environment in the learning model learned to acquire the recommended temperature to be adjusted in the air conditioner.
[9]
9/14 store the generated or renewed learning model to provide a recommended temperature set in the air conditioner as a result of generating or renewing the learning model.
17. Method according to claim 16, characterized in that it additionally comprises:
acquire external environmental information from
conditioner air, in that generation or renovation of model in learning comprises generating or renew the model in learning using temperature defined, the temperature in
moment and the information of the external environment.
18. Method according to claim 17, characterized in that the information from the external environment comprises at least one of an external temperature and an external humidity at the time of setting the temperature.
19. The method of claim 17, using a to c and using. d.o by:
the acquisition of the defined temperature and the moment temperature include the acquisition of the defined temperature and the moment temperature of a bridge server communicatively connected to the air conditioner, and in which the acquisition of information from the external environment comprises the acquisition of information from the external environment from a smart home service server that is communicatively connected to an external content delivery server.
20. Method according to claim 16, characterized in that it additionally comprises:
Petition 870190097162, of 27/09/2019, p. 137/159
Data learning server, according to claim 7, characterized in that, when the storage stores a plurality of learning models for each air conditioner operation mode, at least one processor inserts the moment temperature in the temperature model. learning learned corresponding to a current air conditioner operating mode to acquire the recommended temperature.
[10]
10/14 acquire time information when adjusting the temperature,
in that generation or renovation of model in learning comprises generating or renew the model in learning using temperature defined, the temperature in moment and the21. time information.Method, according with claim 16, characterized by:the generation or renewal of model of learning comprises generating or renewing a plurality of models in
learning for each mode of operation of the air conditioner, and where the storage of the learning model comprises the storage of the plurality of learning models.
22. METHOD FOR USING A MODEL FOR LEARNING A DATA LEARNING SERVER, the method characterized by comprising:
store a learned learning model to provide a recommended temperature to be set as an air conditioner;
acquire a moment temperature of the air conditioner;
introduce the current temperature in the learning model learned to acquire the recommended temperature to be adjusted in the air conditioner; and transmit the recommended temperature to an external device.
23. The method of claim 22, further comprising:
Petition 870190097162, of 27/09/2019, p. 138/159
10. AIR CONDITIONER, characterized by comprising:
a fan configured to discharge the cooling air outside;
a temperature sensor configured to detect a moment temperature around the air conditioner;
Petition 870190097162, of 27/09/2019, p. 131/159
[11]
11/14 to acquire external environmental information from the air conditioner, in which the acquisition of the recommended temperature to be adjusted in the air conditioner comprises introducing the moment temperature and the information of the external environment in the learning model learned to acquire the recommended temperature to be set on the air conditioner.
24. Method according to claim 22, characterized in that the storage of the learned learning model comprises the storage of a plurality of learning models for each mode of operation of the air conditioner, and in which the acquisition of the recommended temperature to be adjusted in the air conditioner comprises the entry of the moment temperature in the learned learning model corresponding to a current mode of operation of the air conditioner to acquire the recommended temperature to be adjusted in the air conditioner.
25. METHOD FOR PROVIDING A RECOMMENDED TEMPERATURE OF AN AIR CONDITIONER, the method characterized by comprising:
detect a moment temperature of the air conditioner;
transmit the currently detected temperature to an external device;
receive a recommended temperature, which is a result obtained by applying the moment temperature to a learning model, from the external device dependent on a moment temperature transmission; and
Petition 870190097162, of 27/09/2019, p. 139/159
11. USER TERMINAL THAT CONTROLS AN AIR CONDITIONER, the user terminal characterized by comprising:
a display configured to display a screen;
a communicator configured to communicate with an external device;
an input receiver configured to receive a user input; and at least one processor configured to:
control the communicator to transmit an AI artificial intelligence operation request signal to the air conditioner in response to a user input signal, dependent on a user input select the AI artificial intelligence operation included on the screen being received by the receiver input, and control the display to display a recommended temperature in response to the recommended temperature set in the air conditioner, which is a result obtained by applying a moment temperature of the air conditioner to a learning model, depending on the request signal.
Petition 870190097162, of 27/09/2019, p. 132/159
[12]
12/14 define the recommended temperature received in the air conditioner, where the learning model is a learning model learned using a plurality of previously defined temperatures set in the air conditioner and a plurality of prevailing temperatures.
26. METHOD TO CONTROL AN AIR CONDITIONER FROM A USER TERMINAL, the method characterized by comprising:
receiving a user input signal, dependent on a user input that selects an artificial intelligence UI operation;
transmitting an artificial intelligence operation request signal corresponding to the UI artificial intelligence operation user interface to the air conditioner;
acquire a recommended temperature defined in the air conditioner, which is a result obtained by applying an air conditioner moment temperature to a learning model, dependent on the artificial intelligence operation request signal; and display the acquired recommendation temperature on a screen.
27. The method of claim 26, further comprising:
display a previously set temperature in the air conditioner at the current temperature, along with the recommended temperature.
28. METHOD TO GENERATE A LEARNING MODEL FROM A NETWORK SYSTEM INCLUDING AN AIR CONDITIONER AND A LEARNING MODEL SERVER, the method comprising:
Petition 870190097162, of 27/09/2019, p. 140/159
12. User terminal, according to claim 11, characterized in that the processor controls the display to display a previously defined temperature set in the air conditioner at the current temperature, together with the recommended temperature.
[13]
13/14 receive, by the air conditioner, a user control signal defining a temperature;
transmit, by the air conditioner, the set temperature and the moment temperature of the air conditioner to an external device;
generate, through the learning model server, a learning model using the defined temperature and the moment temperature; and store, by the learning model server, the generated learning model to provide a recommended temperature for the air conditioner.
29. METHOD OF PROVIDING A RECOMMENDED TEMPERATURE IN A NETWORK SYSTEM, including an air conditioner and a learning model server, the method characterized by comprising:
transmit, by the air conditioner, a moment temperature from the air conditioner to an external device;
acquire, through the learning model server, a recommended air conditioner temperature by applying the current temperature to a learning model; and transmit, through the air conditioner, the recommended temperature to the external device.
30. METHOD TO CONTROL AN AIR CONDITIONER FROM A NETWORK SYSTEM, including the air conditioner and a user terminal, the method characterized by comprising:
receive, by the user terminal, a user input signal, dependent on a user input, by selecting an artificial intelligence operation UI;
transmit an artificial intelligence UI operation request signal via the user terminal
Petition 870190097162, of 27/09/2019, p. 141/159
13. Network system, characterized by comprising:
an air conditioner; and a learning model server configured to generate a learning model using learning data acquired from the air conditioner, where the air conditioner comprises:
a fan configured to discharge cooling air outside, a temperature sensor configured to detect a moment temperature around the air conditioner, a communicator configured to communicate with an external device, and at least one air conditioner processor air configured to control the communicator to transmit a defined temperature, established in the air conditioner and the moment temperature detected by the temperature sensor to an external device, and in which the learning model server comprises:
at least one server processor configured to:
Petition 870190097162, of 27/09/2019, p. 133/159
[14]
14/14 corresponding to the user interface of the artificial intelligence operation for the air conditioner;
transmit, through the air conditioner, a moment temperature from the air conditioner to an external device in response to the artificial intelligence operation request signal being received;
receive, by the air conditioner, a recommended temperature, which is a result of the application of the moment temperature in a learning model, from the external device, dependent on a moment temperature transmission; and defining, by the air conditioner, the recommended temperature received in the air conditioner, where the learning model is a learning model learned using a plurality of defined temperatures previously established in the air conditioner and a plurality of moment temperatures.

类似技术:

---

公开号 | 公开日 | 专利标题

---

BR112019020372A2|2020-04-28|data learning server, air conditioner, user terminal that controls an air conditioner, network system, method to generate a learning model from a data learning server, method to use a learning model from a learning server data, method to provide a recommended temperature of an air conditioner, method to control an air conditioner from a user terminal, method to generate a learning model of a network system including an air conditioner and a model server learning, method for providing a recommended temperature in a grid system, and method for controlling an air conditioner in a grid system

---

US11137161B2|2021-10-05|Data learning server and method for generating and using learning model thereof

---

US10270609B2|2019-04-23|Automatically learning and controlling connected devices

---

US9869484B2|2018-01-16|Predictively controlling an environmental control system

---

US9449229B1|2016-09-20|Systems and methods for categorizing motion event candidates

---

US10102738B2|2018-10-16|Portable security device

---

US9933177B2|2018-04-03|Enhanced automated environmental control system scheduling using a preference function

---

US20170046574A1|2017-02-16|Systems and Methods for Categorizing Motion Events

---

JP2020503715A|2020-01-30|Controlling connected devices using relational graphs

---

US20160201933A1|2016-07-14|Predictively controlling an environmental control system

---

CN106196433A|2016-12-07|A kind of airconditioning control parameter determination device and method, air-conditioning and server

---

EP3152981B1|2021-08-11|Light scene creation or modification by means of lighting device usage data

---

US10679618B2|2020-06-09|Electronic device and controlling method thereof

---

US9772116B2|2017-09-26|Enhanced automated control scheduling

---

US20180323996A1|2018-11-08|Automatic generation of scenes using an assistant device

---

US10976714B2|2021-04-13|Systems and methods for evaluating sensor data of internet-of-things | devices and responsively controlling control devices

---

US20200192309A1|2020-06-18|Providing integrative comfort in a structure

---

US20200341436A1|2020-10-29|Interactive environmental controller

---

CN108227513A|2018-06-29|Intelligent window control method, device and computer readable storage medium

---

US10917259B1|2021-02-09|Computing device interaction with surrounding environment

---

US20190316794A1|2019-10-17|Server, air conditioner and method for controlling thereof

---

US10605470B1|2020-03-31|Controlling connected devices using an optimization function

---

US11277277B2|2022-03-15|Indoor environment personalization preferences

---

US20200382335A1|2020-12-03|Indoor environment personalization preferences

---

JP2021518004A|2021-07-29|Use of contextual information in the environment component area for event / activity prediction

同族专利:

---

公开号 | 公开日

---

AU2018246843A1|2019-09-26|

---

RU2019134550A3|2021-11-08|

---

RU2019134550A|2021-04-30|

---

EP3411634A1|2018-12-12|

---

US20220018567A1|2022-01-20|

---

CN110494697A|2019-11-22|

---

EP3411634A4|2019-06-26|

---

CA3058373A1|2018-10-04|

---

KR20180112653A|2018-10-12|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

CN1173134C|2001-12-17|2004-10-27|乐金电子电器有限公司|Refrigeration control method of air conditioner|

---

CN103138395B|2011-12-05|2015-08-19|中国科学院沈阳自动化研究所|Building intelligent power consuming administrative system|

---

KR20140094125A|2013-01-21|2014-07-30|삼성전자주식회사|display apparatus and method of providing customer-built information using the apparatus|

---

GB201313444D0|2013-07-29|2013-09-11|Ambi Labs Ltd|Energy efficient indoor climate controller|

---

US10012965B2|2013-12-27|2018-07-03|Quirky Ip Licensing Llc|Window air conditioning apparatus and controller|

---

US9817375B2|2014-02-26|2017-11-14|Board Of Trustees Of The University Of Alabama|Systems and methods for modeling energy consumption and creating demand response strategies using learning-based approaches|

---

JP6720170B2|2014-11-11|2020-07-08|ウェビー・コーポレーション|System and method for smart space|

---

CN105717960B|2014-12-04|2018-01-19|台达电子工业股份有限公司|Environmental degree of comfort control system and its control method|

---

US10386800B2|2015-02-24|2019-08-20|Siemens Industry, Inc.|Variable air volume modeling for an HVAC system|US10970128B2|2018-04-13|2021-04-06|Samsung Electronics Co., Ltd.|Server, air conditioner and method for controlling thereof|

---

KR102040505B1|2018-09-21|2019-11-05|엘지전자 주식회사|Air cleaning apparatus based on artificial intelligence and air cleaning system including the same|

---

JP6760348B2|2018-10-11|2020-09-23|株式会社富士通ゼネラル|Air conditioner, data transmission method and air conditioner system|

---

KR102208037B1|2018-12-21|2021-01-26|한국기술교육대학교 산학협력단|Method for automatically providing recommendations of optimal activities for improving indoor air atmosphere|

---

KR20200092484A|2019-01-09|2020-08-04|삼성전자주식회사|Electronic device and control method thereof|

---

WO2020204221A1|2019-04-02|2020-10-08|엘지전자 주식회사|Air conditioner|

---

KR20200120557A|2019-04-12|2020-10-21|삼성전자주식회사|Electronic device, Server and operating method for updating a artificial intelligence model|

---

KR102286137B1|2019-07-22|2021-08-06|엘지전자 주식회사|Artificial intelligence for guiding arrangement location of air cleaning device and operating method thereof|

---

KR102114989B1|2019-12-10|2020-05-26|한국산업기술시험원|System for precision training of air conditioning device using deep reinforcement learning algorithm and method thereof|

---

KR102296329B1|2020-01-13|2021-09-01|주식회사 유러스|Smart Air Conditioning System for Optimized Operation with Predictive Co-operation|

---

KR20210100355A|2020-02-06|2021-08-17|엘지전자 주식회사|Air conditioner and method for controlling for the same|

---

GB2592215A|2020-02-19|2021-08-25|Daimler Ag|Method of controlling air conditionersetting in a vehicle, and system thereof|

---

CN111649465A|2020-06-05|2020-09-11|哈尔滨工业大学|Automatic control method and system for air conditioning equipment|

---

KR20220014620A|2020-07-29|2022-02-07|삼성전자주식회사|Air conditioner, air conditioner system and cotrol method thereof|

---

KR102264390B1|2020-10-08|2021-06-17|제이비씨엔지니어링 주식회사|Air dome autonomous driving system according to iot intelligent control|

---

CN112856727A|2021-01-21|2021-05-28|广州三星通信技术研究有限公司|Method and apparatus for controlling electronic device|

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

---

US201762479207P| true| 2017-03-30|2017-03-30|

---

KR1020170123239A|KR20180112653A|2017-03-30|2017-09-25|Data learning server and method for generating and using thereof|

---

PCT/KR2018/003774|WO2018182357A1|2017-03-30|2018-03-30|Data learning server and method for generating and using learning model thereof|

---