• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    Summary Method and Apparatus for Estimating Demographics of Users Using Social Media This is a method, apparatus, systems, and manufacturing article that is revealed for estimating demographic data for users who employ social media. an exemplary method disclosed herein to include (1) identifying a social media message in relation to an active component, the social media message associated with a user-associated user identifier, (2) determining demographic data associated with a group people exposed to the active component, (3) associate the user identifier with the active component, and (4) repeat (1) to (3). The exemplary method also includes (5) combining demographic data associated with two or more different groups of people with which the user identifier is associated to estimate a demographic profile for the user.
    公开号:BR112015009526A2
    申请号:R112015009526
    申请日:2014-08-25
    公开日:2019-12-17
    发明作者:Richard Sheppard Michael；B. Reid Matthew；Terrazas Alejandro；Otto Robert Lipa Peter；George Schiller Brian
    申请人:The Nielsen Company；Llc；
    IPC主号:
    专利说明:

    METHOD AND APPARATUS FOR ESTIMATING DEMOGRAPHIC DATA OF USERS USING SOCIAL MEDIA RELATED APPLICATION [001] This patent claims priority for Serial Patent Application No. US 14 / 142,411, which is entitled METHODS AND APPARATUS TO ESTIMATE DEMOGRAPHY OF USERSPLANTS. was filed on December 27, 2013, and also claims priority for Provisional Patent Application Serial No. US 61 / 871,243, which is entitled METHODS AND APPARATUS TO ESTIMATE DEMOGRAPHICS OF USERS EMPLOYING SOCIAL MEDIA and was filed on August 28, 2013 Serial Patent Application No. US 14 / 142,411 and Provisional Patent Application No. US 61 / 871,243 are hereby incorporated by reference in their entirety for reference.
    FIELD OF REVELATION [002] This disclosure refers, in general, to an audience measurement and, more particularly, to methods and apparatus for estimating the demographic data of users who employ social media.
    BACKGROUND [003] The measurement of media audience (for example, any type of content and / or advertisements such as television and / or broadcast radio, stored audio and / or video reproduced from memory such as a digital video recorder or a digital video disc, a webpage, audio and / or video presented (for example, broadcast) over the Internet, a video game, etc.) generally involves collecting media identification data (for example, subscription (s) , fingerprint (s),
    2/58 code (s), adjusted channel identification information, exposure time information, etc.) and people data (e.g. user identifier (s), demographic data associated with audience member (s), etc.). Media identification data and people data can be combined to generate, for example, indicative of media exposure data for quantity (s) and / or type (s) of people who were exposed to the specific piece (s) from media.
    BRIEF DESCRIPTION OF THE DRAWINGS [004] Figure 1 is a diagram of an exemplary system built in accordance with the teachings of this disclosure to estimate the demographic data of users who employ social media.
    [005] Figure 2 is an example data table that can be stored by the example audience measurement entity in Figure 1.
    [00 6] Figure 3 is a block diagram of an exemplary deployment of the audience measurement entity server in Figure 1 that can facilitate estimating the demographic data of users who employ social media.
    [007] Figure 4 is a block diagram of an exemplary deployment of the identified identifying agent in Figure 3 that can facilitate marking the identifiers of users of social media with demographic information of active component.
    [008] Figure 5 is an exemplary data table that stores data that represent identifiers of social media users marked with active component demographic data that can be collected by the data server.
    3/58 example audience measurement entity from Figures 1, 3 and 4.
    [009] Figure 6 is an exemplary data table that stores data representing estimated demographic data that corresponds to social media user identifiers that can be collected by the example audience measurement entity server in Figures 1, 3 and 4 .
    [010] Figure 7 is a representative flowchart of exemplary machine-readable instructions that can be executed to estimate the demographic data of users who employ social media.
    [Oil] Figure 8 is a representative flowchart of exemplary machine-readable instructions that can be executed to tag user identifiers for social media messages with demographic data of active components of interest.
    [012] Figure 9 is a representative flowchart of exemplary machine-readable instructions that can be executed to generate demographic data to estimate the profiles of users who employ social media.
    [013] Figure 10 is a block diagram of an exemplary processing platform capable of executing the machine readable instructions of Figures 7 to 9 to deploy the exemplary audience measurement entity server in Figures 1, 3 and / or 4.
    DETAILED DESCRIPTION [014] Exemplary methods, systems and apparatus disclosed in this document can be used to
    4/58 imputing demographic information from a first known group of people to a second known group of people. For example, the techniques revealed in this document make it possible to estimate the demographic data of users who employ social media.
    [015] The social messaging system has become a widely used medium in which users disseminate and receive information. Online social messaging services (like Twitter or Facebook) allow users to send social media messages or instant messages to many users at once. Some social messaging services allow users to follow or add other users as friends (for example, sign up to receive messages sent by selected users (for example, through the Twitter® service), status updates (for example, through Facebook® service or Google + ™ social service), etc.). For example, a user who follows (for example, subscribed to, online friends, etc.) a celebrity on the Twitter® service can receive referrals through a customer application (for example, the TweetDeck® customer application or any other application social media messaging client) when the celebrity sends or posts a social media message.
    [016] Social media messages (sometimes referred to in this document as messages, status, texts or tweets) can be used to convey many different types of information. In some instances, social media messages are used to relay general information about a user. For example, a
    5/58 message sender can send a social media message indicating that they are bored. In some examples, social media messages are used to conduct self-reporting activity by the message sender in relation to an active component such as a media event, product or service. For example, a message sender may conduct a social media message that indicates that the message sender is watching a certain television program, listening to a certain song, or has just purchased a certain book. Social media messages in relation to the active component are social media messages that are disseminated to a mass audience and indicate exposure to the active component. In some examples revealed in this document, social media messages are collected and then filtered to identify social media messages in relation to the active component.
    [017] It is useful, however, to link demographic data and / or other user information to message senders. For example, companies and / or individuals want to understand the scope and exposure of the active component (for example, a media event, a product and / or a service) that they distribute, produce and / or provide. For example, a media event that is associated with large numbers of exposure and / or large numbers of occurrences of an association can be considered more effective in influencing user behavior.
    [018] In some examples, the demographic data developed for a panel (for example, a television panel, a loyalty card panel, etc.) is used
    6/58 to infer demographic data for users of online social messaging services that send social media messages in relation to the same active component as a media event, a product and / or a service. In some examples, demographic data of speakers developed for a first media event such as television programs, advertisements, etc. can be used to estimate demographics of users of social media who post contemporary messages and / or contemporary messages close to the media event. For example, timestamp recordings that identify exposure to the media event (eg, television content and / or advertisements) and timestamp social media messages that comment on the media event are identified. Users who post messages that correspond to (for example, mention and / or make reference) media of interest (for example, television content and / or advertising) within a time window close to (for example, adjacent, is covered by a time limit of and / or overlapping a) a time window of presentation of the corresponding media are considered in the audience of the referenced media event and, thus, within demographic data of the audience of the media event. Demographic data for the media event (for example, an active component of interest) can be identified by, for example, an audience measurement entity (for example, Nielsen Company (US), LLC) based on a panel consumers. Demographic data for a single media event (for example, a private television program and / or advertising) may be disclosed
    7/58 among many demographic segments (for example, 20% male aged 20 to 25, 25% female aged 20 to 25, 10% male aged less than 20.3% female aged less than 20.30% male aged 40 to 50, 12% female aged 40 to 50). Therefore, identifying users of social media as being in the audience for that single media event provides an indication that the user fits within any one of any of these demographic segments (sometimes referred to in this document as demographic ranges, demographic groups, demographic categories , demographic composition or niche markets). The percentage of audience composition can be used as a proxy for the likelihood that the social media user will fit into one of the demographic ranges (for example, the 12% chance that the user is female aged 40 to 50). These percentages can be modified based on known social media usage patterns. For example, if females aged 40 to 50 are more likely to use social media than males aged 40 to 50, the percentages of the demographic composition may be weighted or otherwise adjusted to reflect those probabilities.
    [019] Although using a user message in relation to a media event may not be an accurate indicator of the demographic data of the social network user due to the variety of demographic data associated with that event, which aggregate messages by the same user for multiple media event results in granularity and / or increasing accuracy. For example, statistical methods like Bayesian analysis can be applied to groupings
    8/58 different demographics associated with different media events for which the same user is known to have sent a social media message (for example, is known to have been in the audience for the media event) to obtain an estimate of data more accurate demographic data for that user. For example, if a second media event to which the social media user sends a message is only 1% female aged 40 to 50, no male aged 40 to 50 and 50% female aged 20 to 25, then joins the set of probabilities for the second media event with the set of probabilities for the first media event for the example above, the probability that the social media user is a female aged 40 to 50 or a male aged 40 the 50 is decreased and the probability of the user being a male aged 20 to 25 is greatly increased.
    [020] Demographic information can be used from different types of panels to estimate the demographics of social media users. For example, demographic data from a television panel can be used as explained above. Alternatively, demographic data from a consumer purchase panel (eg, Homescan ™ Nielsen panel, a loyalty card panel, etc.) can be used. Participants registered with Homescan ™ scan product identifiers (for example, bar codes) after purchasing the product. A speaker identifier is associated with the product identifier and, as the demographic data for the speaker is known, the demographic information for the corresponding product can be determined. In
    9/58 some examples, demographic data for two or more different types of panels are used (for example, a television panel and the Homescan ™ panel). For example, a social media user may send a first message that mentions a television program or feature of a television program, and then send a second message that mentions a product (eg running shoes) or a feature of a product. In some instances, demographic data known to viewers of the television show collected through, for example, a television panel, can be combined with the demographic data known to people who purchased running shoes collected through, for example, a Homescan ™ panel, to estimate the demographics of the social media user.
    [021] In some instances, certain active component owners (for example, distributors, producers and / or suppliers of active components such as a retailer (for example, Amazon.com)) allow a user to post a message (for example, a tweet, status update, etc.) after the user has made a purchase. In some examples, when a user chooses to post a message, the message may include a specific phrase like I just purchased, the active component purchased (for example, a box of protein bars) and an active component owner identifier (for example, example, through © Amazon). In some instances, the active component owner may write an identifier (for example, a Twitter identifier) to the user when posting the message. In some such
    10/58 examples, the active component owner can associate demographic information to the informed user from previous purchases made by the user and / or other users.
    [022] In some examples, the active component owner may not record a social media user identifier when the user posts the message. The exemplary methods disclosed in this document to identify a set of posted messages associated with the purchase of a particular active component (for example, an active component of interest such as protein bars) thereby enabling the collection of a set of user identifiers associated companies. Each of the user identifiers can be associated with the demographic data associated with that particular active component. As discussed above, although a case of a posted message provides some demographic information in relation to the individual posting the message, collecting demographic data associated with a plurality of messages posted by the user allows a more accurate and more granular user demographic profile to be generated (e.g., specific). Thus, examples revealed in this document analyze the plurality of messages over time to predict the demographic data associated with a particular user through the user identifier. In some examples, statistical analysis (for example, Bayesian analysis, principal component analysis, etc.) is used to develop the estimation of demographic data. In some examples, different weights are associated with the respective demographic data for
    11/58 generate a demographic profile of greater precision and accuracy.
    [023] Figure 1 is an illustration of an exemplary environment 100 in which examples revealed in this document can be deployed to estimate demographic data of users who employ social media. The exemplary environment 100 in Figure 1 includes an audience measurement entity (AME) 102, a message hosting server 104 and an active component owner 10 6. The AME 102 in the illustrated example is an entity that monitors and / or reports social media message posts. In the illustrated example in Figure 1, AME 102 operates and / or hosts an exemplary AME server 108. The AME server 108 in the illustrated example is a server and / or database that collects and / or receives related social media messages active components (for example, media events, products and / or services) and estimates demographics of the individual who posts messages. In some examples, the AME server 108 is deployed using multiple devices and / or the message hosting server 104 is deployed using multiple devices. For example, the AME server 108 and / or the message hosting server 104 may include disk arrangements or multiple workstations (for example, desktop computers, workstation servers, laptop computers, etc.). ) in communication with each other. In the illustrated example, the AME server 108 is in selective communication with the message hosting server 104 and / or the active component owner 106 through one or more wireless and / or wired networks represented by network 110. A network
    12/58
    example 110 can to be implanted how to use in any network (s) with thread and / or wireless suitable (s) what includes, for example, one or more data buses, an
    or more Local Area Networks (LANs), one or more wireless LANs, one or more cellular networks, the Internet, etc. As used herein, the term in communication, which includes variations thereof, encompasses direct communication and / or indirect communication through one or more intermediate components and does not require constant communication and / or direct physical communication (for example, wired) , but instead additionally includes selective communication at periodic and non-periodic intervals, as well as events of an occurrence.
    [024] In the example shown in Figure 1, an online social messaging service operates and / or hosts the message hosting server 104 that responds to the requirements for social media messages by the AME server 108. Additionally or alternatively , the message hosting server 104 may be in communication with a geographically separate message database (for example, a third party server hired by the online social messaging service) that hosts the social media messages. In such examples, the message hosting server 104 retrieves messages from the separate message database to service the messages for the requirement AME server 108. Alternatively, the separate message database can be provided with a server to service messages hosted directly to the 108 AME server requirement. In addition, for simplicity, only one
    13/58 message hosting 104 is shown in Figure 1, although multiple message hosting servers are likely to be present.
    [025] In the illustrated example, a user signs on an online social media service with a user identifier (for example, an example 112 user identifier) in order to read and / or conduct (or send) social media messages. The exemplary user identifier 112 is then associated with activities for the user. For example, user identifier 112 can be displayed (or displayed) along with the social media message.
    [026] In the illustrated example, when a message sender posts or sends a social media message 114, that social media message 114 is sent to the message hosting server 104. The example message hosting server 104 hosts messages from social media in relation to active component 114A and non-active component in relation to social media messages 114B. In the illustrated example, social media messages regarding active component 114A include reference (s) (for example, text) at least partially directed to an active component of interest and also include characteristics that indicate exposure to the active component of interest. For example, an active component of interest may be The Daily Program with Jon Stewart. In such cases, a social media message regarding active component 114A may include the text Jon Stewart is very funny on the Daily Show right now! and can include a message data / time stamp 116 that
    14/58 indicates that the social media message regarding active component 114A was posted by the message sender during the broadcast of the active component of interest.
    [027] In contrast, a non-active component in relation to the social media message 114B does not include reference to an active component of interest and / or does not include a characteristic that indicates exposure to an active component of interest. For example, a non-active component in relation to the 114B social media message may include reference to an active component of interest (for example, the text I just met with Jon Stewart from the Daily Show at my favorite pizzeria!), But the message may not have been posted by the message sender during the broadcast times associated with the television program. In the illustrated example, message hosting server 104 presents social media messages with respect to active component 114A and non-active component with respect to social media messages 114B to AME server 108 in the same way. For example, message hosting server 104 processes a request for a social media message 114 in a similar manner regardless of whether the social media message 114 is a social media message in relation to the active component 114A or a non-active component in regarding the social media message 114B.
    [028] In the illustrated example in Figure 1, the active component owner 106 distributes and / or provides media events, products and / or services to large numbers of subscribers. In exchange for the provision of the active component, subscribers register with the active component owner
    15/58
    106. As part of this registration, subscribers provide detailed demographic user information. Examples of such active component owners 106 include retailers and / or service providers such as Amazon.com, eBay, Pandora, Hulu, etc.
    [029] The ΑΜΕ exemplificative 108 server in the illustrated example operates to imput demographic information from ο the first known group of people to a second known group of people. For example, to infer demographic data for social media users who send social media messages in relation to an active component, the AME 108 server can use demographic data developed for a panel (for example, a television panel, a loyalty card, etc.). In some instances, the AME server 108 periodically and / or not periodically queries the message hosting server 104 for social media messages using a keyword list. The social media messages 115 returned by the message hosting server 104 are processed to determine whether they correspond to an active component of interest such as a media event, a product and / or a service. In the example in Figure 1, the social media messages 114 and 115 are the same message at two different points in time. Message 114 is the message before being provided to the AME server 108 (for example, while hosted on the message hosting server 104). Message 115 is the message after passing through the server. The exemplary AME server 108 identifies user identifier 112 associated with the returned social media message 115 and marks the
    16/58 user identifier 112 with known demographic information for the active component.
    [030] In the illustrated example, to mark user identifier 112 with known demographic information for an active component of interest, AME 102 in the illustrated example also collects and / or has access to demographic information for the active component (s) of interest . For example, AME 102 can collect information about identifying private media information that is displayed in a media display environment (for example, a television room, a family room, a living room, a bar, a restaurant, warehouse, cafeteria, etc.) by a media presentation device such as a television and to store demographic information. AME 102 can then correlate data collected from a plurality of speaker sites with the demographic data of speakers on those sites. For example, for each speaker site where a first piece of media is detected in the monitored environment in the first half, information identifying the media for the first piece of media is correlated to the presence of information detected in the environment in the first half. The data and / or results from multiple speaker sites are combined and / or analyzed to provide demographic information representative of the exposure of a population as a whole for the first piece of media.
    [031] In the example shown in Figure 1, AME 102 includes an exemplary reference database 118 to identify active components of interest and to
    17/58 mark user identifier 112 associated with social media messages in relation to active component 114A with known demographic information (for example, a set of different demographic ranges that correspond to a known audience composition) of the active component included in the database reference data 118. As described in detail below, the exemplary reference database 118 may include, for example, an active component of interest identifying 120 (for example, The Daily Program with Jon Stewart), one or more rule (s ) 122 associated with the active component (for example, it is displayed between 10:00 pm Central Standard Time (CST) and 10:30 pm CST from Monday to Thursday), the known demographic information 124 about the active component (eg example, segments or niche markets such as 70% male aged 20 to 29, 20% female aged 20 to 29, 6% male aged less than 20, 4% female aged less than 20) and a demographic data tag 126 associated with demographic segments (for example, brand A). The exemplary reference database 118 may include a volatile memory (for example, a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and / or a non-volatile memory (eg flash memory). The exemplary reference database 118 may include one or more dual data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The exemplary reference database 118 may additionally or alternatively include one or more mass storage devices
    18/58 as hard disk (s), compact disk driver (s), digital versatile disk driver (s), etc. Although in the illustrated example the reference database 118 is illustrated as a single database, the reference database 118 can be deployed by any number and / or type (s) of databases.
    [032] In some instances, AME 102 uses demographic data from a consumer purchase panel (eg Homescan ™ Nielsen panel, loyalty card panel, Nielsen television panel, Nielsen online panel, Nielsen radio panel, etc. .). In such speaker-based systems (for example, television panels, consumer purchase panels, etc.), user demographic information is obtained from a user when, for example, the user joins and / or registers for the panel (for example, it accepts to be monitored in a panel). User demographic information (eg, race, age or age range, gender, income, educational level, etc.) can be obtained from the user, for example, through a telephone interview, a face-to-face interview, having the user completed a survey (for example, an online survey), etc. In some instances, AME 102 uses the demographic information collected from registered persons (for example, speakers) so that subsequent correlations can be made between the exposure of the active component to those speakers and different demographic markets. For example, AME 102 can monitor those panel members to determine active components (eg, media events, products, services, etc.) exposed to those ways of
    19/58 panel. ΑΜΕ 102, then, compiles the data collected in statistical reports that precisely identify different demographic ranges of people exposed to the active component.
    [033] In some examples, AME 102 can collect and / or obtain active component demographic information 124 from active component owner 106. In some such examples, AME 102 can leverage existing databases of the active component owner 106 to collect more extensive demographic information from active component 124 and / or user data to associate with social media users. Collecting user demographic information associated with registered speakers and / or users of the active component owner 10 6 allows AME 102 to extend or complete its panel data with substantially reliable demographic information from external sources (for example, the active component owner 106) thereby extending the cover, accuracy and / or completeness of your known demographic information to active components. The use of demographic information from results from unequal data sources (for example, high-quality demographic information from an audience measurement entity (s) and / or registered user data from the active component owner 106) enhanced forecasting of demographic data associated with a particular social media user by AME.
    [034] In the illustrated example, the AME 108 server generates user profiles 128 for users using the demographic information associated with the user through
    20/58 your user identifier 112. For example, the AME server 108 may periodically and / or not periodically identify the demographic data tags 126 associated with user identifier 112 and perform statistical analysis as Bayesian analysis of the corresponding demographic data. In some examples, the AME 108 server performs statistical analysis of variations within demographic data to generate user profile 128. In some examples, the AME 108 server combines the demographic composition of multiple events for the same user (for example, one or more exposures to one or more television programs and / or one or more product purchases) to more precisely determine demographic data for the user. For example, combining the probabilities that the user fits into different demographic categories based on different audience compositions of two or more event results in a combined probability set for the user's demographic data. Demographic categories (eg, segments or niche markets) with the highest probability are identified as demographic data for the user. Large numbers of event / audience participation that can be associated with a given user over time (for example, through user identifier 112) achieve better accuracy of demographic data assignments. AME 102 of the illustrated example can provide the generated profiles 128 for companies and / or individuals that produce the active component.
    [035] Figure 2 illustrates an example data table 200 that can be stored by the database.
    21/58 example reference data 118 from example ΆΜΕ 102 of Figure 1 to facilitate the association of users of social media services with demographic information. In the illustrated example in Figure 2, data table 200 associates an active component identifier 120 with one or more rule (s) 122, with active component demographics 124 and with a demographic data tag 126. The association is achieved by placing data in the appropriate column of the same row in data table 200. In the illustrated example, the active component identifier 120 identifies an active component of interest as a television program (for example, the active component (The Daily Program with Jon Stewart ) in row 202), a book (for example, the active component (Twilight (book)) in row 204), a product (for example, the active component (Necklace) in row 206), etc. The one or more exemplary rule (s) 122 includes one or more values and / or data that match a criterion associated with the corresponding active component identifier 120. In some examples, one or more rule (s) 122 includes run time
    locks during which a program in television is displayed. For example, in row 202, The one or more rules) 122 associated with active component (0 Program
    Jon Stewart Diary) indicates that the active component (The Jon Stewart Daily Program) is broadcast from Monday to Thursday and between 10:00 p.m., Central Standard Time (CST) and 10:30 p.m. (CST). In some examples, one or more rule (s) 122 includes sellers and / or traders who sell products and / or provide media (for example, active components of interest) included in the database
    Reference 22/58 118. For example, in row 208, one or more rule (s) 122 associated with the active component (End of the World (film)) indicates that the active component (End of the World (film)) can be accessed (for example, purchased, broadcast, etc.) from Amazon.com and / or through iTunes®.
    [036] As discussed above, demographic information for an active component can be collected and / or driven by AME 102. Data table 200 in Figure 2 includes demographic information for active component 124 (eg demographic segments, niche market, etc.) associated with the corresponding active component. Demographics of active component 124 may include data and / or value (s) indicative of one or more of an age or age range (e.g., 20 to 29), gender, educational level, etc. associated with active component identifier 120. In some instances, AME 102 collects and / or has access to demographic information for the active component (s) of interest. For example, AME 102 can correlate data collected from a plurality of monitored speaker sites with the demographics of speakers on those sites and / or user demographics associated with registered speakers and / or users of the active component owner 106. For example, in row 206, the active component demographic information 124 associated with the active component (Necklace) indicates that a buyer of the active component (Necklace) has a 70% probability of being female and a 30% probability of being male. Additionally, in row 210, the
    23/58 active component demographics 124 associated with the active component (End of the World (music)) indicates that a user accessing (for example, purchases, flows, etc.) the active component (End of the World (music) ) has a 70% probability of being between the ages of 20 to 29, a 20% probability of being under the age of 20, and a 10% probability of being between the ages of 30 to 39. In the example shown in Figure 2, the demographic data tag 126 corresponds to the active component demographic information 124 and can be used to refer to the demographic segments of the associated active component identifier 120. For example, in row 206, the demographic data tag 126 associated with the component Active (Paste) indicates that the demographic segments of the active component (Paste) can be called a brand (Brand C). One or more demographic brands (for example, one or more values or data) can be applied to any given active component. In this way, the demographic data tag 126 can be populated with one or more tags.
    [037] Figure 3 is a block diagram of an example deployment of server 108 of the audience measurement entity (AME) in Figure 1 that can facilitate estimating the demographic data of users who employ social media. The exemplary AME server 108 of the illustrated example includes an exemplary tagged identifier agent 302, an exemplary tagged identifier database 304, an exemplary profile generator 306, an exemplary profile database 314, an image stamp example time 316, an example data store 318 and a
    24/58 exemplificative rapporteur 320.
    [038] In the example shown in Figure 3, the ΑΜΕ 108 server includes ο exemplary tagged identifier agent 302 for registering user identifiers associated with social media messages posted by users in relation to active components of interest. As described in detail below, the exemplary tagged identifying agent 302 marks a user identifier 112 associated with the social media message in relation to the active component 114a with known demographic information associated with the active component. For example, tagged agent 302 can query the message hosting server (for example, message hosting server 104 in Figure 1) for social media messages 114 associated with an active component identifier 120. The tagged agent identifier example 302 processes the returned social media message 115 and when the identified identifier agent exemplary 302 of the illustrated example determines that the returned social media message 115 includes reference to an active component of interest and includes characteristics that indicate exposure to the active component of interest ( for example, the returned social media message 115 is a social media message in relation to the active component 114A), the identifying agent marked 302 uses the exemplary reference database 118 in Figure 1 to identify the demographic information associated with the active component identified. The exemplary tagged identifier agent 302 in Figure 3 identifies user identifier 112 associated with the media message
    25/58 social in relation to the active component 114A and brand (for example, associates) the user identifier 112 with the active component demographic information 124 retrieved from the reference database 118.
    [039] In the illustrated example in Figure 3, the tagged identifier agent 302 stores the recording of the tagged user identifier in the exemplary tagged identifier database 304. The tagged identifier database 304 may include a volatile memory (e.g. a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and / or a non-volatile memory (for example, flash memory). tagged identifier data 304 may include one or more
    rate memories of data double (DDR), like DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The database in identifiers marked 304 can additional or alternatively includes one or more devices in
    mass storage such as hard disk (s), compact disk drive (s), digital versatile disk drive (s), etc. Although in the illustrated example the database of tagged identifiers 304 is illustrated as a single database, the database of tagged identifiers 304 can be deployed by any number and / or type (s) of databases.
    [040] In the example illustrated in Figure 3, the AME server 108 includes the example profile generator 306 to generate user profiles 128 that include estimated demographic data for the corresponding users who post
    26/58 social media messages in relation to the active components of interest (for example, the example social media messages in relation to the active component 114A). For example, profiler 306 can periodically and / or not periodically process a user identifier 112 included in the database of tagged identifiers 304 and perform statistical analysis of the active component demographic information 124 tagged for user identifier 112. With Using the results of the analysis, the example profile generator 306 estimates demographic data for the user associated with user identifier 112.
    [041] In some examples, profiler 306 generates user profiles 128 when required. For example, profiler 306 may receive a request from, for example, exemplary reporter 320 to generate a user profile 128 for a certain user. In some examples, profiler 306 generates user profiles 128 not periodically (for example, when profiler 306 detects a change in the information stored in the exemplary marked identifier database 304). For example, when the tagged identifier agent 302 writes a tagged identifier to the tagged identifier database 304, profiler 306 can detect the new recording and process the new recording. For example, profiler 306 can update a previously generated user profile 128 associated with user identifier 112 from the new recording. In some examples, profiler 306 periodically generates a user profile 128. For example, profiler 306 can generate a user profile 128 for one or more
    27/58 user identifier 112 included in the database of identified identifiers 304 every 24 hours. The profiler 306 of the illustrated example includes an example demographic data filter 308, an example demographic data analyzer 310 and an example estimator 312.
    [042] In the example illustrated in Figure 3, profiler 306 includes the example demographic data filter 308 to identify the demographic information associated with a specific user identifier. For example, demographic filter 308 can analyze the database of tagged identifiers 304 and identify different tagged demographic data for user identifier 112. In some instances, demographic filter 308 sorts and / or combines the recording in the database of tagged identifiers 304 based on the distinct user identifier 112. For example, demographic filter 308 can join one or more demographic data tags 126 associated with user identifier 112. In some examples, the demographic filter 308 can aggregate demographic information for two or more user identifiers 112 included in the database of tagged identifiers 304. For example, the demographic data filter 308 can associate different user identifiers 112 with the same user. For example, the demographic data filter 308 can access a data structure such as a visualization table, a file, a database, a list, etc. which cross-references based on information received from, for example, one or more
    28/58 active component 106. For example, a user can register with a first online social media service using a first user identifier (for example, @JohnDoe) and register with a second online social media service using a second user identifier (for example, Johnny_Doe). In some examples, the demographic data filter 308 can identify two or more user identifiers that are sufficiently the same (for example, the user identifier @Jane_Doe, Jane Doe and Doe, Jane) and associate different user identifiers with the same user. In some such examples, the demographic data filter 308 combines the tagged demographic information with the first user identifier and the second user identifier to generate the profile for the user.
    [043] In the example illustrated in Figure 3, the profiler 306 includes the example demographic data analyzer 310 to analyze the demographic information identified by the demographic data tag 126 and determine the probabilities that the user fits in different demographic ranges. In some examples, the demographic data analyzer 310 performs statistical analysis of variations within the identified demographic data associated with the user. For example, demographic data analyzer 310 can apply Bayesian analysis or principal component analysis to different demographic data to develop the probabilities. In some such examples, the demographic data analyzer 310 applies statistical methods (for example,
    29/58
    Bayesian) to the different demographic groupings associated with the user to obtain a more accurate demographic estimate for that user. For example, combining the probabilities that the user fits into different demographic categories based on different audience compositions from two or more recordings of tagged identifiers (for example, one or more exposures to one or more television programs and / or one or plus product purchases) results in a combined set of probabilities for user demographics. In some examples, the demographic data analyzer 310 associates weights with the different demographic information marked for the user. However, the exemplary demographic data analyzer 310 can use other statistical producers (for example, principal component analysis) to determine the probabilities that the user fits in different demographic ranges.
    [044] In the example shown in Figure 3, the profiler 306 includes the example estimator 312 to estimate the demographic data for the user based on the analysis results performed by the sample demographic analyzer 310. For example, the estimator 312 can identify the demographic category (or categories) with the highest probability and associate the corresponding demographic category to the user. In general, larger numbers of tagged identifier recordings (and corresponding demographic information) associated with a given user over time increase the accuracy of demographic data assignments. In the illustrated example of
    30/58
    Figure 3, profiler 306 uses the results of estimator 312 to generate user profile 128.
    [045] In the example shown in Figure 3, the profiler 306 stores the generated user profile 128 in the example profile database 314. The profile database 314 can include a volatile memory (for example, a Memory Synchronous Dynamic Random Access (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and / or a non-volatile memory (eg flash memory). 314 can include one or more dual data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The profile database 314 can additionally or alternatively include one or more storage devices in mass such as hard disk (s), compact disk drive (s), digital versatile disk drive (s), etc. Although in the illustrated example the profile database 314 is illustrated as a single database, the database profile data 314 can be deployed by any number and / or type (s) of databases.
    [046] The exemplary time stamp 316 in Figure 3 includes a clock and a calendar. The pusher exemplary time 316 associates a period of time (eg, 1:00 am Central Standard Time (CST) at 1:01 am (CST) and / or date (for example, the I January 2013) the each user profile generated 128 by, for example, appending the time period and / or date information to an end of the data in user profile 128.
    [047] In the example shown in Figure 3, the AME server 108 includes the example data store 318
    31/58 for storing marked identifier recordings, marked by the exemplary marked identifier agent 302 and / or user profiles 128 generated by the exemplary profile generator 306.
    [048] In the illustrated example, the rapporteur 320 generates reports based on the generated user profiles. In some examples, the rapporteur 320 generates reports for a certain user. For example, reporter 320 may receive a query for a certain user from, for example, AME 102. In some such examples, reporter 320 causes profiler 306 to generate a report for the specified user. In some examples, reports are presented to companies and / or individuals that produce the different active components. The report can identify different aspects of active component exposure such as which age group (s) and / or gender are most likely to send social media messages when exposed to an active component. For example, the report can determine whether those who send social media messages about a media event (for example, a television program) in real time are from the same demographic distribution as the viewers of the media event. Reports can also show that social media users are young for a first media event, but relatively older for a second media event.
    [049] Although an exemplary way to deploy the audience measurement entity (AME) server 108 in Figure 1 is illustrated in Figure 3, one or more of the elements, processes and / or devices illustrated in Figure 3 can be combined, divided , arranged again,
    32/58 omitted, eliminated and / or implanted in any other way. Additionally, the exemplary tagged identifier agent 302, the exemplary tagged identifier database 304, the example profile generator 306, the example demographic data filter 308, the example demographic data analyzer 310, the example estimator 312, the database example profile data 314, example time stamp 316, example data store 318, example report 320 and / or, more generally, example AME server 108 in Figure 1 can be deployed by hardware, software, firmware and / or any combination of hardware, software and / or firmware. Thus, for example, any of the exemplary tagged identifier agent 302, the exemplary tagged identifier database 304, the example profile generator 306, the example demographic data filter 308, the example demographic data analyzer 310, the sample estimator 312, sample database 314, sample time stamp 316, sample data store 318, sample report 320 and / or, more generally, sample AME server 108 can be deployed by a or more analog or digital circuit (s), logic circuits, programmable processor (s), application-specific integrated circuit (s) (ASIC (s)), programmable logic device (s) ( (s) (PLD (s)) and / or field programmable logic device (s) (FPLD (s)). When you read any claim for the apparatus or system in this patent
    33/58 cover a software and / or firmware deployment completely, at least one of the exemplary tagged identifier agent 302, the exemplary tagged identifier database 304, the example profile generator 306, the example demographic data filter 308, the example demographic data analyzer 310, the example estimator 312, the example profile database 314, the example time stamp 316, the example data store 318 and / or the example report 320 is / are, therefore, expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. which stores the software and / or firmware. Still further, the exemplary AME server 108 of Figure 1 can include one or more elements, processes and / or devices in addition to, or instead of those illustrated in Figure 3, and / or can include more than one of any or all the illustrated elements, processes and devices.
    [050] Figure 4 is a block diagram of an exemplary deployment of the identifier agent marked 302 of Figure 3 that can facilitate marking a user identifier associated with a social media message posted by a user in relation to an active component of interest. with known demographic information associated with the active component. The exemplary tagged identifier agent 302 of the illustrated example includes an example message retriever 402, an example message analyzer 404, a stamp retriever
    34/58 data / hour exemplificative 406, an example rule checker 408 and an exemplary identifier marker 410.
    [051] In the example illustrated in Figure 4, the identifying agent marked 302 includes example message retriever 402 for retrieving social media messages (for example, the social media messages example
    114, 115 of Figure 1) of server in accommodation in posts (for example, O server in accommodation in example message 104 of the Figure D. For example, O recuperator message 402 can consult the server in accommodation message 104 for media message social 114 at intervals periodicals (for example, every 24
    hours, every Monday, etc.), non-periodic breaks (for example, when required), and / or as a one-time event. In the example shown in Figure 4, message retriever 402 uses an exemplary keyword list 412 that includes one or more keyword (s) when analyzing message hosting server 104. As used herein, the expression keyword includes words and / or expressions that have a dictionary definition and / or correspond to a name and / or correspond to colloquies that may not have an accepted dictionary definition. In addition, although the examples disclosed in this document are described in connection with a list, many other methods of deploying the 412 keyword list can alternatively be used. For example, the revealed techniques can also be used in connection with a table (for example, a visualization table), a file, a database, etc.
    35/58 [052] In the illustrated example, the keyword list 412 includes example keywords 412A, 412B,
    412C, 412D. When example message retriever 402 in the illustrated example queries message hosting server 104 for social media messages, message retriever 402 requires only those social media messages 114 that include keywords in keyword list 412 In this way, the example message retriever 402 reduces (for example, minimizes) the number of social media messages 115 that are returned by the message hosting server 104 that were not posted by a user associated with an active component of identifying interest. 120. For example, in addition to analyzing the message hosting server 104 for social media messages 114 that include a television program (ER) name, which can return 115 social media messages posted by users waiting in a room emergency, the example message retriever 402 in the illustrated example can also include the keywords as a media provider who can allow you to watch and / or distribute the television program (for example, @Hulu). In some examples, message retriever 402 requires one or more social media messages 114 from message hosting server 104 and then uses keyword list 412 to filter social media messages 115 to reduce the set of social media messages 115 to process subsequently. For example, message retriever 402 may require all social media messages 114 posted to the
    36/58 message hosting 104 within a period of time (for example, 5:00 p.m. Central Standard Time (CST) to 5:59 p.m. (CST)) and / or a date or date range. Sample message retriever 402 can subsequently filter social media messages 115 using keyword list 412. In some instances, message retriever 402 uses one or more keywords when retrieving social media messages . For example, message retriever 402 can query message hosting server 104 for social media messages 114 using a first keyword (for example, an active component identifier 120, such as ER) and filter so subsequent social media messages returned 115 using a second keyword (for example, I’m watching through @Hulu). Filtering can be performed using any combination of Boolean operations (for example, AND, OR, etc.).
    [053] While analyzing the message hosting server 104 using the keywords 412D, it can reduce the number of social media messages returned 115 to those in relation to an active component (for example, a television program), the television program included in social media messages 115 may not be in relation to a television program of interest. In the illustrated example of Figure 4, the tagging agent 302 includes the example message analyzer 404 to determine whether the returned social media message 115 includes an active component of interest. For example, the 404 message analyzer can compare the text of the social media message 115 to the
    37/58 active component identifiers 120 listed in reference database 118. In some examples, if the returned social media message 115 does not include an active component of interest (for example, the example component not active in relation to message 114b ), the message analyzer 404 discards the social media message (for example, messages 114b, 115).
    [054] In the example shown in Figure 4, the identifying agent marked 302 includes the exemplary data / time stamp retriever 406 to obtain a data / time stamp that corresponds to when the returned social media message 115 was posted (for example , when the message was sent by a user, when the status was updated, etc.). In some examples, the data / time stamp retriever 406 analyzes social media message 115 to identify the data / time stamp message 116. In some examples, the 406 data / time stamp retriever may require the stamp corresponding message data / time from message hosting server 104. As described in detail below, in some examples, message data / time stamp 116 can be used to determine whether the returned social media message 115 has been posted simultaneously and / or almost simultaneous for an active component of interest (for example, a media event).
    [055] In the illustrated example in Figure 4, the tagging agent marked 302 includes the exemplary rule checker 408 to ensure that only claims that indicate appropriate exposure to an active component are reflected in the social media message claim.
    38/58 example rule checker 408 works to increase the likelihood that the example server 108 will properly allocate demographic data to a social media service user. In some instances, the 408 rule checker functions as a false positive checker. In the illustrated example, rule checker 408 compares characteristics of the returned social media message 115 to one or more rule (s) 122 associated with active component identifier 120 identified in social media message 115. For example, rule checker 408 can determine whether text from the social media message 115 includes a known seller or merchant who supplies (e.g., sells) the identified active component (e.g., a product of interest). In some instances, rule checker 408 compares message data / time stamp 116 retrieved by data / time stamp retriever 406 to determine if message data / time stamp 116 is close enough to time ( s) broadcasting a television program in order to safely conclude the exposure to the television program that has occurred, thereby connecting the user through user identifier 112 to the demographic data of the television program audience. In some instances, the 408 rule checker may use a time window based on broadcast times. For example, rule checker 408 can perform a serial time analysis of the message timestamp to determine an interval between real-time broadcast of a television program and when messages related to the television program are posted by
    39/58 users. The exemplary rule checker 408 of the illustrated example uses the interval to determine whether the social media message 115 was sent in response to a user watching the television program (for example, during or shortly after (for example, within fifteen minutes of ) broadcasting the television program).
    [056] In the example illustrated in Figure 4, the identifying agent marked 302 includes the exemplary identifying marker 410 to associate the known demographic information of the active component of interest to the user. In some examples, identifier 410 analyzes the social media message against active component 114A and identifies user identifier 112 associated with message 114A. The exemplary identifier marker 410 in the illustrated example then marks user identifier 112 with active component demographic information 124 associated with the active component of interest. For example, identifier 410 may retrieve the active component demographic information 124 and / or the demographic data tag 126 associated with identified active component identifier 120 from the example reference database 118 and associate the active component demographic information 124 and / or demographic data tag 126 to user identifier 112. In some instances, identifier 410 may include additional information next to the identifier marked as text included in the social media message in relation to active component 114A and / or an identifier (for example, a message identifier) to access message 114A at a subsequent time, which keyword (s)
    40/58 of keyword list 412 were used by message retriever 402 to retrieve the social media message in relation to active component 114A, the active component of interest identifier 120 identified by message analyzer 404, the data stamp / message time 116 associated with the social media message in relation to active component 114A, etc.
    [057] Although an exemplary way of implanting the identified identifying agent 302 of Figure 3 is illustrated in Figure 4, one or more of the elements, processes and / or devices illustrated in Figure 4 can be combined, divided, disposed again, omitted, eliminated and / or deployed in any other way. Additionally, the example message retriever 402, the example message analyzer 404, the example data / time stamp retriever 406, the example rule checker 408, the example identifier marker 410 and / or, more generally, the identifying agent exemplary marked 302 of Figure 3 can be deployed by hardware, software, firmware and / or any combination of hardware, software and / or firmware. Thus, for example, anyone between the example message retriever 402, the example message analyzer 404, the example data / time stamp retriever 406, the example rule checker 408, the example identifier marker 410 and / or, more generally, the exemplary tagged identifying agent 302 can be deployed by one or more analog or digital circuit (s), logic circuits, processor (s)
    41/58 programmable (s), application-specific integrated circuit (s) (ASIC (s)), programmable logic device (s) (PLD (s)) and / or device (s) ) field programmable logic (s) (FPLD (s)). When you read any claim of the apparatus or system of this patent to cover a software and / or firmware deployment completely, at least one of the example message retriever 402, the example message analyzer 404, the example time stamp retriever 406 , the exemplary rule checker 408 and / or the exemplary identifier marker 410 is / are therefore expressly defined to include a tangible computer-readable storage device or storage disk as a memory, a digital versatile disk (DVD), a compact disc (CD), a Blu-ray disc, etc. which stores the software and / or firmware. Still further, the exemplary tagged identifying agent 302 of Figure 3 can include one or more elements, processes and / or devices in addition to, or instead of, those illustrated in Figure 4 and / or can include more than one of any or all the illustrated elements, processes and devices.
    [058] Figure 5 illustrates an exemplary data table 500 that stores data representing marked identifiers that can be collected by the example AME server 108 of Figures 1, 3 and / or 4. In the illustrated example in Figure 5, the table of data 500 identifies a user identifier 112, a demographic data tag 126, a message identifier 502, message keyword information 504, a
    42/58 active component identifier 120 and a message data / time stamp 116. In the illustrated example, the AME server 108 extracts user identifier 112 from the social media message in relation to active component 114A when message 114A corresponds to an active component of interest (for example, includes a reference to active component identifier 120). For example, in row 514, user identifier 112 indicates that a user associated with user identifier 112 (@ user3) posted the corresponding social media message in relation to active component 114A. In addition, the AME server 108 identifies demographic information associated with active component identifier 120 (Paste) and marks user identifier 112 (@ user3) with the corresponding demographic data tag 12 6 (Mark C). In the illustrated example, the AME server 108 also stores the additional information from the social media message in relation to the active component 114A in the tagged identifier recordings. For example, in row 510, the identifying agent marked 302 associates the social media message in relation to the active component 114A with a message identifier 502 (101101), stores the keyword (s) 504 (I just bought through @amazon) used by message retriever 402 when retrieving the social media message in relation to active component 114A, stores the active component identifier 120 (Twilight (book)) in the social media message in relation to active component 114A and the data stamp / message time 116 retrieved by the data / time stamp retriever
    43/58
    406 (10/11/2013 at 9:45:05 a.m.) which indicates when the social media message regarding active component 114A was posted by the user.
    [059] Figure 6 illustrates an exemplary data table 600 that stores data representing estimated demographic data from identifiers of social media users that can be collected by the example AME server 108 in Figures 1, 3 and / or 4. In the example shown in Figure 6, data table 600 identifies a user identifier 112 and active component demographic information 124 marked for user identifier 112. In the illustrated example, the AME server 108 extracts the marked identifier information from the database of tagged identifiers 304. For example, profiler 306 can analyze tagged identifiers stored in the tagged identifier database 304 and match the recording that matches the same user identifier 112. For example, in row 604, demographic information active component 124 associated with user identifier 112 (@ user2) indicates that the user is associated associated with user identifier 112 (@ user2) posted three social media messages regarding active component 114A that were recorded by the identifying agent marked 302. Additionally, data table 600 includes the results of the demographic analysis performed by the AME server 108 (for example, demographic data analysis results 610). For example, demographic data analyzers 310 can apply statistical methods like Bayesian analysis to different demographic segments associated with media messages
    44/58 different social with respect to active component 114A to which the same user is known to have sent different messages 114A as determined by, for example, user identifier 112 associated with different social media messages in relation to the active component 114A. In the illustrated example, data table 600 includes estimated user demographics 612 based on the corresponding results of demographic data analysis 610. In the illustrated example, the AME server 108 can identify the demographic segment with the highest probability as the data demographics for the user (for example, estimated 612 user demographics). In some instances, when estimating user demographic information 612, the percentages of demographic analysis results 610 can be modified based on known social media usage patterns (for example, if women under the age of 20 are more likely to use social media than male under the age of 20, the percentages of the 610 demographic analysis results can be weighted or otherwise adjusted to reflect those probabilities).
    [060] The flowcharts representative of exemplary machine-readable instructions for deploying the AME 108 server of Figures 1, 3 and / or 4 are shown in Figures 7 to 9. In this example, the machine-readable instructions comprise a program for execution by a processor like the 1012 processor shown on the example processor platform 1000 discussed below in connection with Figure 10. The program can be incorporated into software stored on a readable storage medium by
    45/58 tangible computer such as a CD-ROM, a floppy disk, a hard disk, a versatile digital disk (DVD), a Blu-ray disk or a memory associated with the 1012 processor, but the entire program and / or parts of it can alternatively be executed by a device in addition to the 1012 processor and / or incorporated in firmware or dedicated hardware. In addition, although the example program is described with reference to the flowcharts illustrated in Figures 7 to 9, many other methods of deploying the exemplary AME server 108 of Figures 1, 3 and / or 4 can alternatively be used. For example, the execution order of the blocks can be changed and / or some of the described blocks can be changed, deleted or combined.
    [061] As mentioned above, the exemplary process of Figures 7 to 9 can be implemented using coded instructions (for example, computer and / or machine-readable instructions) stored in a tangible computer-readable storage medium as a trigger hard disk, flash memory, read-only memory (ROM), compact disk (CD), versatile digital disk (DVD), cache, random access memory (RAM) and / or any other device storage or storage disk on which information is stored for any duration (for example, for extended periods of time, permanently, for brief moments, to temporarily store and / or to cache information). As used herein, the term tangible computer-readable storage medium is expressly defined to include
    46/58 any type of computer-readable storage device and / or storage disk and to exclude propagation signals and to exclude transmission media. As used herein, tangible computer-readable storage medium and tangible machine-readable storage medium are used interchangeably. Additionally or alternatively, the exemplary process of Figures 7 to 9 can be implemented using coded instructions (for example, computer and / or machine-readable instructions) stored on a non-transitory computer and / or machine-readable medium as a hard disk drive, a flash memory, a read-only memory, a compact disk, a digital versatile disk, a cache, a random access memory and / or any other storage device or storage disk on which the information is stored stored for any duration (for example, for extended periods of time, permanently, for brief moments, to temporarily store and / or to cache information). As used herein, the term non-transitory computer-readable medium is expressly defined to include any type of computer-readable storage device and / or storage disk and to exclude propagation signals and to exclude transmission media. As used herein, when the term at least is used as the transitional term in a preamble to a claim, it is unlimited in the same way that the term you understand is unlimited.
    [062] The example program 700 in Figure 7 estimates
    47/58 demographic data of users who employ social media on the exemplary AME server 108 (Figures 1, 3 and / or 4). The example program 700 in Figure 7 starts at block 702 when the AME server 108 identifies a social media message in relation to the active component 114A. For example, the identifying agent marked 302 (Figures 3 and / or 4) can retrieve the returned social media message 115 from the message hosting server 104 (Figure 1) and analyze the text of the social media message 115 to determine if a user posted the social media message 115 in relation to an active component of interest (for example, identified through a reference to an active component identifier 120) included in the reference database 118 (Figure 1).
    [063] In block 704, the AME 108 server determines active component demographic information associated with the active component of interest. For example, the tagging agent 302 can retrieve the active component demographic information 124 from data table 200 stored in reference database 118. In block 706, the AME server 108 tags (for example, associates) a tag identifier user associated with the social media message in relation to the active component 114A with the determined active component demographics 124. For example, the tagging agent 302 can identify the user identifier 112 associated with the social media message in relation to the active component 114A and marks user identifier 112 with active component demographic information 124. In some instances, identifier agent marked 302 records the
    48/58 identifier marked in the database of marked identifiers 304 (Figure 3).
    [064] In block 708, the AME server 108 determines whether to generate a user profile associated with user identifier 112. For example, the rapporteur 320 (Figure 3) can consult the profile generator 306 for a profile for a certain user. If, in block 708, profiler 306 determines to generate a user profile, then, in block 710, profiler 306 generates a user profile using demographic information marked for user identifier 112 associated with the user. For example, profiler 306 can identify one or more tagged identifiers that are associated with a user from the tagged identifier database 304 and perform statistical analysis on active component demographics 124 tagged for user identifier 112. In some For example, profiler 306 stores the generated user profile 128 in profile database 314 (Figure 3).
    [065] If, in block 708, profiler 306 determines not to generate user profile 128 or after profiler 306 generates user profile 128 in block 710, control proceeds to block 712 in which the server AME 108 determines whether it continues to estimate demographic data of users who employ social media. If, in block 712, the AME server 108 determines to continue to estimate demographic data of users employing social media (for example, the identifying agent marked 302 continues to retrieve social media messages 115 from the message hosting server 104, the generator profile
    49/58
    306 continues to receive requirements for user profiles 128, etc.), control returns to block 702 to identify another social media message associated with an active component (for example, the social media message in relation to active component 114A) . Otherwise, if, in block 712, the AME 108 server determines to complete the estimation of demographic data of users who employ social media (for example, due to a server closing the event, etc.), the example process 700 of Figure 7 then ends.
    [066] The example program 800 in Figure 8 marks a user identifier associated with social media messages in relation to the active component with demographic information associated with the same active component of interest on the AME 108 server in Figures 1, 3 and / or 4 The example program in Figure 8 can be used to deploy blocks 702, 704 and 706 of Figure 7. The example program 800 in Figure 8 starts at block 802 in which the identifying agent marked 302 (Figures 3 and / or 4) retrieves a social media message that includes one or more word (s) included in a keyword list. For example, message retriever 402 may receive social media message 115 in response to a query to message hosting server 104 for social media messages 114 that include the one or more word (s) included in the keyword list. key 412.
    [067] In block 804, the identifying agent marked 302 determines whether the returned social media message 115 references an active component of interest. For example, the 404 message analyzer can compare the text of the
    50/58 social media message 115 to active component identifiers 120 included in data table 200. If, in block 804, message analyzer 404 identifies a reference that corresponds (for example, it is the same or almost the same) a active component identifier 120, then, in block 806, the identifier agent marked 302 retrieves the data / time stamp 116 associated with when the social media message 115 was posted (for example, sent or ported by the message sender). For example, the 406 data / time stamp retriever may retrieve the message data / time stamp 116 from the social media message text 115. In some instances, the 406 data / time stamp retriever may require the message data / time 116 from media hosting server 104.
    [068] In block 808, the identifying agent marked 302 determines whether characteristics of the social media message 115 satisfy one or more rule (s) (for example, specific criterion) associated with the identified active component of interest. For example, rule checker 408 can determine whether the message data / time stamp 116 is close enough to the broadcast time (s) of a television program to safely complete exposure to the user-experienced television program. In some instances, rule checker 408 can determine whether the text of the social media message 115 includes a known vendor who provides (e.g., distributes, sells and / or supplies) the active component of interest. In some instances, rule checker 408 may perform a serial time stamp analysis
    51/58 message time 116 to determine an interval between real-time broadcasting of a television program and when social media messages related to the television program are sent by users. The exemplary rule checker 408 can use the interval to determine if the social media message is sent by the user in response to the user watching the television program (for example, during or shortly after (for example, within fifteen minutes of) broadcasting. television program).
    [069] If, in block 808, rule checker 408 determines that the social media message 115 satisfies one or more rule (s) associated with the identified active component of interest (for example, the social media message 115 is a social media message in relation to active component 114A), then, in block 810, the identifying agent marked 302 marks the user identifier associated with the social media message in relation to active component 114A with active component demographic information associated with the active component of interest. For example, identifier 410 analyzes the social media message against active component 114A to identify user identifier 112. Identifier marker 410 can also retrieve demographic information for active component 124 from data table 200 based on identifier active component 120 identified in the social media message in relation to active component 114A and tag (for example, associate) the active component demographic information 124 for user identifier 112. In block 812, the agent
    52/58 tagged identifier 302 stores a recording of the tagged identifier in the tagged identifier database 304.
    [070] If, in block 804, the message parser 404 determines that the social media message 115 does not include a reference to an active component of interest (for example, the social media message 115 does not include a reference to an identifier for active component 120 included in data table 200 and thus is a non-active component in relation to social media message 114B), or, if, in block 808, rule checker 408 determines that social media message 115 does not satisfy one or more rule (s) associated with the active component of interest (for example, social media message 115 is a non-active component in relation to social media message 114B), or after the tagging agent marked 302 stores a recording of the tagged identifier in the tagged identifier database 304 in block 812, control proceeds to block 814 in which the tagged identifier agent 302 determines whether to continue to the user identifier of brands with demographic information associated with identified active components of interest. If, in block 814, the tagging agent 302 determines to continue tagging the user identifier with demographic information associated with identified active components of interest (for example, the tagging agent 302 continues to retrieve social media messages 115 from the hosting server message 104), the control returns to block 804 to determine whether the returned social media message 115 references an active component
    53/58 of interest. Otherwise, if, at block 814, the tagged identifier agent 302 determines to end the tagging of user identifiers with demographic information associated with the identified active components of interest (for example, there are no additional social media messages to process, due to a server ends event, etc.), the example process 800 in Figure 8 then ends.
    [071] The example program 900 in Figure 9 generates a user profile to estimate demographic data of a user who employs social media on the example AME server 108 (Figures 1, 3 and / or 4). The example program 900 in Figure 9 can be used to deploy block 710 in Figure 7. The example program 900 in Figure 9 starts at block 902 when the AME server 108 identifies the demographic information associated with a user identifier. For example, the demographic data filter 308 (Figure 3) can analyze the tagged identifier recordings stored in the tagged identifier database 304 for the tagged active component demographic information 124 (e.g., associated) with user identifier 112. In some instances, the demographic data filter 308 combines the active component demographics 124 marked with two or more user identifiers 112 that are associated with the same user.
    [072] In block 904, the AME server 108 performs statistical analysis of the identified demographic information of active component 124. For example, the demographic data analyzer 310 (Figure 3) can
    54/58 apply statistical methods such as Bayesian analysis to active component demographic information 124 to determine the likelihood of the user fitting into different demographic segments (for example, the results of analysis of demographic data 610 included in data table 600). In block 90 6, the AME server 108 estimates the demographic data for the user associated with user identifier 112. For example, the estimator 312 (Figure 3) can identify the demographic category (or categories) with the highest probability and associate the demographic category corresponding to the user (for example, the estimated 612 user demographics included in data table 600). In general, large numbers of tagged identifier recordings (and corresponding demographic information) associated with a given user over time increase the accuracy of demographic data assignments (for example, estimated demographic user data).
    [073] In block 908, the AME 108 server stores a user profile for the user that includes the estimated demographic user data for the user. For example, profiler 306 (Figure 3) can generate user profile 128 for the user using estimated user demographic information 612 and store the generated user profile 128 in the profile database 314 (Figure 3 ). In block 910, the AME server 108 stores a data / time stamp with estimated user demographic information 612. For example, the time stamp
    316 (Figure 3) can associate a time period (for example, 1:00 a.m. Central Standard Time (CST) with 1:01 a.m.
    55/58 (CST) and / or a date (for example, the I January 2013) with each user profile 128 generated by, for example, attaching the time-out period and / or date information to one end of data in user profile 128.
    [074] In block 912, the AME 108 server determines whether it continues to generate user profiles. If, in block 912, the AME server 108 determines to continue generating user profiles (for example, profiler 306 continues to receive requirements for user profiles 128, etc.), control returns to block 902 to identify demographic information associated with another user. Otherwise, if, in block 912, the AME 108 server determines that the end generates user profiles (for example, there are no additional requirements for generating user profiles, due to a server terminating an event, etc.), the process example 900 of Figure 9 then ends.
    [075] Figure 10 is a block diagram of an example 1000 processor platform capable of executing the instructions in Figures 7 to 9 to deploy the example AME server 108 in Figures 1, 3 and / or 4. The platform processor 1000 can be, for example, a server, a personal computer, a mobile device (for example, a cell phone, a smart phone, a tablet computer like an iPad ™), a personal digital assistant (PDA), a Internet tool, a DVD player, a CD player, a digital video recorder, a Blu-ray player, a video game console, a personal video recorder, a set-top box or any other type of computing device .
    56/58 [076] The processor platform 1000 in the illustrated example includes a 1012 processor. The processor 1012 in the illustrated example is hardware. For example, the 1012 processor can be deployed by one or more integrated circuits, logic circuits, microprocessors or controllers from any desired manufacturer or family.
    [077] Processor 1012 in the example shown includes local memory 1013 (for example, a cache). The processor 1012 in the example illustrated is in communication with a main memory that includes a volatile memory 1014 and a non-volatile memory 1016 via a bus 1018. The volatile memory 1014 can be deployed by Synchronous Dynamic Random Access Memory (SDRAM), Memory Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM) and / or any other type of random access memory device. Non-volatile memory 1016 can be deployed by flash memory and / or any other desired type of device memory. Access to main memory 1014, 1016 is controlled by a memory controller.
    [078] The processor platform 1000 in the example illustrated also includes a 1020 interface circuit. The 1020 interface circuit can be deployed by any type of standard interface, such as an Ethernet interface, a universal serial bus (USB) and / or an express PCI interface.
    [07 9] In the illustrated example, one or more insertion devices 1022 are connected to interface circuit 1020. Insertion device (s) 1022 allow a user to enter data and commands into the 1012 processor.
    57/58 insertion device (s) can be implanted by, for example, an audio sensor, a microphone, a camera (still or video), a keyboard, a button, a mouse, a touchscreen, a track -pad, a rolling ball, isopoint and / or a voice recognition system.
    [080] One or more 1024 emission devices are also connected to the 1020 interface circuit of the illustrated example. 1024 emission devices can be implanted, for example, by display devices (for example, a light-emitting diode (LED), an organic light-emitting diode (OLED), a liquid crystal display, a glass tube display cathode ray (CRT), a touch screen, a tactile emission device, a printer and / or speakers). The interface circuit 1020 of the example illustrated, therefore, typically includes a graphics driver card, a graphics driver chip or a graphics driver processor.
    [081] The 1020 interface circuit in the illustrated example also includes a communication device such as a transmitter, receiver, transceiver, modem and / or network interface card to facilitate data exchange with external machines (for example, devices computing devices of any kind) over a 1026 network (for example, an Ethernet connection, a digital signature line (DSL), a telephone line, coaxial cable, a cell phone system, etc.).
    [082] The processor platform 1000 in the example illustrated also includes one or more mass storage devices 1028 for storing software and / or data. Examples of such a storage device in
    58/58 mass 1028 includes floppy drives, hard drives, compact disk drives, Blu-ray disk drives, RAID systems and versatile digital (DVD) disk drives.
    [083] The coded instructions 1032 of Figures 7 to 9 can be stored on mass storage device 1028, on volatile memory 1014, on non-volatile memory 1016, and / or on a removable, tangible computer-readable storage medium such as a CD or DVD.
    [084] From the above, it will be verified that methods, devices and articles of manufacture have been revealed that allow to insert demographic information of a first known group of people in a second known group of people and, thus, allow to track the reach and effectiveness of an active component based on the exposure reported for the active component by the second group of people. Such charges may be based on (1) posts made through social media sites by the second group of people and (2) demographic data and media exposure data collected for the first group of people. The first group of people may be speakers from an audience and / or market research study.
    [085] Although certain methods, apparatus and exemplary articles of manufacture have been disclosed in this document, the scope of this patent is not limited to them. On the contrary, this patent covers all methods, apparatus and articles of manufacture reasonably covered within the scope of the claims of this patent.
    权利要求:
    Claims (10)
    [1]
    AMENDED CLAIMS
    1. Method for estimating demographic data of a social media user, where the method is CHARACTERIZED by the fact that it comprises:
    identify, with a processor, a first social media message that mentions a first active component, in which the first social media message originated or received by the user;
    determine, with the processor, the first demographic data associated with a first group of people exposed to the first active component;
    associate, with the processor, the first demographic data to the user;
    identify, with the processor, a second social media message that mentions a second active component, in which the second social media message originated or received by the user;
    determine, with the processor, second demographic data associated with a second group of people exposed to the second active component; and combine, with the processor, the first demographic data and the second demographic data to estimate a demographic profile for the user.
    [2]
    2. Method, according to claim 1, CHARACTERIZED by the fact that identifying the first social media message includes:
    identify a reference to the first active component in the text of a social media message; and
    2/10 determine whether a feature of the social media message meets a rule associated with the first active component.
    [3]
    3. Method, according to claim 2, CHARACTERIZED by the fact that the first active component is a media event, and the rule associated with the first active component specifies a relationship for a diffusion time of the active component.
    [4]
    4. Method, according to claim 2, CHARACTERIZED by the fact that determining whether the characteristic of the social media message meets the rule associated with the first active component further includes determining whether a timestamp associated with the social media message is covered for a period of time defined by the rule.
    [5]
    5. Method, according to claim 2, CHARACTERIZED by the fact that the first active component is a product, and the rule associated with the first component
    active identifies a salesman what provides the first active component. 6. Method, of wake up with the claim 5, CHARACTERIZED BY fact of what determine whether the
    feature of the social media message satisfies the rule associated with the first active component includes additionally determining whether the text of the social media message mentions the seller.
    7. Method, according to claim 6, CHARACTERIZED by the fact that the first group of people exposed to the first active component are buyers of the first active component.
    3/10
    8. Method, according to claim 1, CHARACTERIZED by the fact that the first group of people exposed to the first active component is an audience for the first active component.
    9. Method, according to claim 1, CHARACTERIZED by the fact that the first social media message, and the second social media message are associated with a first user identifier, in which the method additionally includes:
    identify a third social media message that mentions a third active component, where the third social media message is associated with a second user identifier associated with the user, where the second user identifier is different from the first user identifier; and estimating the demographic profile for the user includes combining demographic data associated with two or more different groups with which the first user identifier and the second user identifier are associated.
    10. Method, according to claim 1, CHARACTERIZED by the fact that the first group of people exposed to the first active component are an audience for the first active component, and the second group of people exposed to the second active component are buyers of the second active component.
    11. Method, according to claim 1, CHARACTERIZED by the fact that the estimation of the demographic profile for the user additionally includes:
    4/10 analyze the first demographic data and the second demographic data;
    determine a demographic category with a higher probability based on the results of the analysis; and associate the demographic category with the highest probability for the user.
    12. Method, according to claim 11, CHARACTERIZED by the fact that the analysis of the first demographic data and the second demographic data includes performing Bayesian analysis on the first demographic data and the second demographic data.
    13. Method, according to claim 11, CHARACTERIZED by the fact that the analysis of the first demographic data and the second demographic data includes carrying out principal component analysis on the first demographic data and the second demographic data.
    14. System CHARACTERIZED by the fact that it comprises: an identifying agent marked for:
    identify a first social media message that mentions a first active component, in which the first social media message is originated or received by a user;
    determine first demographic data associated with a first group of people exposed to the first active component;
    associate the first demographic data to the user;
    identify a second social media message that mentions a second active component, where the second
    5/10 social media message is originated or received by the user;
    determine second demographic data associated with a second group of people exposed to the second active component; and a profiler to combine the first demographic data and the second demographic data to estimate a demographic profile for the user.
    15. System, according to claim 14, CHARACTERIZED by the fact that it additionally includes:
    a message analyzer to determine whether the first social media message mentions the first active component; and a rule checker to determine whether a feature of the first social media message satisfies a rule associated with the first active component.
    16. System, according to claim 15, CHARACTERIZED by the fact that the first active component is a media event, and the rule associated with the first active component specifies a relationship for a diffusion time of the first active component.
    17. System, according to claim 16, CHARACTERIZED by the fact that the rule checker must determine whether the characteristic of the first social media message satisfies the rule associated with the first active component when determining whether a timestamp associated with the first social media message is covered by a time limit on the broadcast time of the first active component.
    [6]
    6/10
    18. System, according to claim 16, CHARACTERIZED by the fact that the first group of people exposed to the first active component are an audience for the first active component.
    19. System, according to claim 15, CHARACTERIZED by the fact that the first active component is a product and the rule associated with the first active component specifies a seller who supplies the first active component.
    20. System according to claim 19, CHARACTERIZED by the fact that the rule checker must determine whether the feature of the first social media message meets the rule associated with the first active component when determining whether the first social media message includes a reference to the seller.
    21. System, according to claim 19, CHARACTERIZED by the fact that the first group of people exposed to the first active component are buyers of the first active component.
    22. System according to claim 14, CHARACTERIZED by the fact that the first group of people exposed to the first active component are an audience for the first active component, and the second group of people exposed to the second active component are buyers of the second active component.
    23. System, according to claim 14, CHARACTERIZED by the fact that it additionally includes:
    an analyzer to analyze the first demographic data and the second demographic data; and
    [7]
    7/10 an estimator to determine a demographic category with the highest probability based on an emission from the analyzer, where the estimator associates the demographic category with the highest probability to the user.
    24. System, according to claim 23, CHARACTERIZED by the fact that the analyzer applies Bayesian analysis to the first demographic data and the second demographic data.
    25. System, according to claim 23, CHARACTERIZED by the fact that the analyzer applies principal component analysis to the first demographic data and the second demographic data.
    26. Tangible computer-readable storage medium CHARACTERIZED by the fact that it comprises instructions that, when executed, cause a processor to at least:
    identify a first social media message that mentions a first active component, in which the first social media message is originated or received by the user;
    determine first demographic data associated with a first group of people exposed to the first active component;
    associate the first demographic data with the user;
    identify a second social media message that mentions a second active component, in which the second social media message is originated or received by the user;
    [8]
    8/10 determine second demographic data associated with a second group of people exposed to the second active component; and combine the first demographics and second demographics to estimate a demographic profile for the user.
    27. Tangible computer-readable storage medium according to claim 26, CHARACTERIZED by the fact that the instructions cause the processor to identify the first social media message by:
    identify a reference to the first active component in the text of a social media message; and determine whether a feature of the social media message meets a rule associated with the first active component.
    28. Tangible computer-readable storage medium according to claim 27, CHARACTERIZED by the fact that the first active component is a media event, and the rule specifies a schedule after a diffusion time of the first active component.
    29. Tangible computer-readable storage medium according to claim 28, CHARACTERIZED by the fact that the instructions cause the processor to determine whether the characteristic of the first social media message meets the rule when determining whether a date / time associated with the first social media message occurs within the timeline.
    30. Tangible computer-readable storage medium according to claim 27, CHARACTERIZED by the fact that the first active component is a product,
    [9]
    9/10 and where the rule specifies a vendor who supplies the first active component.
    31. Tangible computer-readable storage medium according to claim 30, CHARACTERIZED by the fact that the instructions additionally cause the processor to determine whether the text of the first social media message mentions the seller.
    32. Tangible computer-readable storage medium according to claim 26, CHARACTERIZED by the fact that the instructions additionally cause the processor to:
    analyze the first demographic data and the second demographic data;
    determine a demographic category with a higher probability based on the results of the analysis; and associate the demographic category with the highest probability for the user.
    33. Tangible computer-readable storage medium according to claim 32, CHARACTERIZED by the fact that the instructions cause the processor to analyze the first demographic data and the second demographic data by performing Bayesian analysis on the first demographic data and on the second demographic data.
    34. Tangible computer-readable storage medium according to claim 32, CHARACTERIZED by the fact that the instructions cause the processor to analyze the first demographic data and the second demographic data by performing main component analysis
    [10]
    10/10 in the first demographics and the second demographics.
    类似技术:
    公开号 | 公开日 | 专利标题
    BR112015009526A2|2019-12-17|method and apparatus for estimating demographic data of users employing social media
    US20210150553A1|2021-05-20|Methods and apparatus to analyze and adjust demographic information
    US9252961B2|2016-02-02|Identify experts and influencers in a social network
    Porten-Cheé et al.2015|Spiral of silence online: How online communication affects opinion climate perception and opinion expression regarding the climate change debate
    Duda et al.2010|The fallacy of online surveys: No data are better than bad data
    Gong et al.2012|Intergenerational income mobility in urban China
    West et al.2006|“Catastrophic” pathways to smoking cessation: findings from national survey
    Devine et al.2012|Cost-effectiveness of Identification and Referral to Improve Safety |, a domestic violence training and support programme for primary care: a modelling study based on a randomised controlled trial
    CN103189856A|2013-07-03|Methods and apparatus to determine media impressions
    US20170011420A1|2017-01-12|Methods and apparatus to analyze and adjust age demographic information
    Huang et al.2015|Impact of the ‘Giving Cigarettes is Giving Harm’campaign on knowledge and attitudes of Chinese smokers
    US20120226521A1|2012-09-06|Utilize Experts and Influencers in a Social Network
    Li et al.2015|Smoking-related thoughts and microbehaviours, and their predictive power for quitting
    Dhamija et al.2013|Poverty in rural India: Variations in factors influencing dynamics of chronic poverty
    CN103268562A|2013-08-28|Internet advertisement audience population ascribed characteristic monitoring method and system
    Soares et al.2019|Social media marketing communication: effect of interactivity and vividness on user engagement
    O'Dwyer et al.2014|Using G oogle a dwords to recruit family carers of people with dementia
    Valente et al.2017|Response bias over time: interviewer learning and missing data in egocentric network surveys
    Sequist et al.2006|Addressing racial and ethnic disparities in health care: using federal data to support local programs to eliminate disparities
    Niu et al.2020|The influence of media consumption on public risk perception: a meta-analysis
    Li et al.2004|Influenza and pneumococcal vaccination demand responses to changes in infectious disease mortality
    JP2017107371A|2017-06-15|Contribution analyzer
    Requena et al.2021|The increasing incidence and prevalence of hypereosinophilic syndrome in the United Kingdom
    Kelling2018|An Integrated Data Quality System for Species Observations
    AU2015264866A1|2015-12-24|Methods and apparatus to analyze and adjust demographic information
    同族专利:
    公开号 | 公开日
    KR101706745B1|2017-02-14|
    AU2014311451A1|2015-05-14|
    US10333882B2|2019-06-25|
    HK1212130A1|2016-06-03|
    CN104756504A|2015-07-01|
    US20190379629A1|2019-12-12|
    KR20150067224A|2015-06-17|
    EP3039875A4|2017-03-22|
    JP6115901B2|2017-04-19|
    EP3039875A1|2016-07-06|
    KR102347083B1|2022-01-04|
    US20150067075A1|2015-03-05|
    KR20170018467A|2017-02-17|
    KR102355826B1|2022-01-26|
    WO2015031262A1|2015-03-05|
    CA2889349A1|2015-03-05|
    KR20210006505A|2021-01-18|
    JP2016505975A|2016-02-25|
    KR20220003661A|2022-01-10|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    GB2176639B|1985-05-31|1988-11-23|Mars Inc|Data acquisition system|
    CA2041210C|1991-04-25|1998-12-29|Michel Dufresne|Television audience data gathering|
    JP3400068B2|1994-03-18|2003-04-28|富士通株式会社|Response amount prediction system|
    CA2119970A1|1994-03-25|1995-09-26|Michael A. Lyons|Program monitoring system|
    US5594934A|1994-09-21|1997-01-14|A.C. Nielsen Company|Real time correlation meter|
    US5758257A|1994-11-29|1998-05-26|Herz; Frederick|System and method for scheduling broadcast of and access to video programs and other data using customer profiles|
    WO1996028904A1|1995-03-16|1996-09-19|Bell Atlantic Network Services, Inc.|Simulcasting digital video programs for broadcast and interactive services|
    US5675510A|1995-06-07|1997-10-07|Pc Meter L.P.|Computer use meter and analyzer|
    US5848396A|1996-04-26|1998-12-08|Freedom Of Information, Inc.|Method and apparatus for determining behavioral profile of a computer user|
    JP3191855B2|1996-06-28|2001-07-23|日本電気株式会社|MOVING IMAGE RECEIVING DEVICE AND METHOD FOR COMPENSING DISCARDED PACKET|
    US6108637A|1996-09-03|2000-08-22|Nielsen Media Research, Inc.|Content display monitor|
    US5948061A|1996-10-29|1999-09-07|Double Click, Inc.|Method of delivery, targeting, and measuring advertising over networks|
    US6035339A|1997-03-13|2000-03-07|At&T Corporation|Network information delivery system for delivering information based on end user terminal requirements|
    US6643696B2|1997-03-21|2003-11-04|Owen Davis|Method and apparatus for tracking client interaction with a network resource and creating client profiles and resource database|
    US5796952A|1997-03-21|1998-08-18|Dot Com Development, Inc.|Method and apparatus for tracking client interaction with a network resource and creating client profiles and resource database|
    US6098093A|1998-03-19|2000-08-01|International Business Machines Corp.|Maintaining sessions in a clustered server environment|
    US7240022B1|1998-05-19|2007-07-03|Mypoints.Com Inc.|Demographic information gathering and incentive award system and method|
    US6434614B1|1998-05-29|2002-08-13|Nielsen Media Research, Inc.|Tracking of internet advertisements using banner tags|
    US6223215B1|1998-09-22|2001-04-24|Sony Corporation|Tracking a user's purchases on the internet by associating the user with an inbound source and a session identifier|
    US7949565B1|1998-12-03|2011-05-24|Prime Research Alliance E., Inc.|Privacy-protected advertising system|
    US6055573A|1998-12-30|2000-04-25|Supermarkets Online, Inc.|Communicating with a computer based on an updated purchase behavior classification of a particular consumer|
    US6460079B1|1999-03-04|2002-10-01|Nielsen Media Research, Inc.|Method and system for the discovery of cookies and other client information|
    US6529952B1|1999-04-02|2003-03-04|Nielsen Media Research, Inc.|Method and system for the collection of cookies and other information from a panel|
    US6102406A|1999-06-07|2000-08-15|Steven A. Miles|Internet-based advertising scheme employing scavenger hunt metaphor|
    US7010497B1|1999-07-08|2006-03-07|Dynamiclogic, Inc.|System and method for evaluating and/or monitoring effectiveness of on-line advertising|
    AUPQ206399A0|1999-08-06|1999-08-26|Imr Worldwide Pty Ltd.|Network user measurement system and method|
    US6415323B1|1999-09-03|2002-07-02|Fastforward Networks|Proximity-based redirection system for robust and scalable service-node location in an internetwork|
    US8108245B1|1999-09-17|2012-01-31|Cox Communications, Inc.|Method and system for web user profiling and selective content delivery|
    US6839680B1|1999-09-30|2005-01-04|Fujitsu Limited|Internet profiling|
    US6691163B1|1999-12-23|2004-02-10|Alexa Internet|Use of web usage trail data to identify related links|
    US6993590B1|2000-01-13|2006-01-31|Inktomi Corporation|Method of creating data streams for user-specific usage data gathering systems|
    US7065503B2|2000-01-14|2006-06-20|Matsushita Electric Industrial Co., Ltd.|Cookie data stored on transportable recording medium|
    US20010049620A1|2000-02-29|2001-12-06|Blasko John P.|Privacy-protected targeting system|
    US7260837B2|2000-03-22|2007-08-21|Comscore Networks, Inc.|Systems and methods for user identification, user demographic reporting and collecting usage data usage biometrics|
    US7181412B1|2000-03-22|2007-02-20|Comscore Networks Inc.|Systems and methods for collecting consumer data|
    JP2001338176A|2000-03-23|2001-12-07|Casio Comput Co Ltd|Method and system for information transmission and intermediation|
    JP2001282982A|2000-03-28|2001-10-12|Hisahiro Negi|Web marketing system|
    US7039699B1|2000-05-02|2006-05-02|Microsoft Corporation|Tracking usage behavior in computer systems|
    US7523191B1|2000-06-02|2009-04-21|Yahoo! Inc.|System and method for monitoring user interaction with web pages|
    US7962603B1|2000-06-06|2011-06-14|Nobuyoshi Morimoto|System and method for identifying individual users accessing a web site|
    JP2001357192A|2000-06-12|2001-12-26|Toshiba Corp|Method and system for customer awareness research and storage medium storing program|
    JP2004504674A|2000-07-18|2004-02-12|ヤフー！　インコーポレイテッド|System and method for selecting another advertising inventory instead of a sold-out advertising inventory|
    KR20020037980A|2000-11-16|2002-05-23|김형순|System for retrieving and providing information|
    JP2002163562A|2000-11-27|2002-06-07|Dainippon Printing Co Ltd|Information distribution server device|
    US6879960B2|2000-12-01|2005-04-12|Claritas, Inc.|Method and system for using customer preferences in real time to customize a commercial transaction|
    US20030006911A1|2000-12-22|2003-01-09|The Cadre Group Inc.|Interactive advertising system and method|
    US20020111172A1|2001-02-14|2002-08-15|Dewolf Frederik M.|Location based profiling|
    JP4248183B2|2001-02-26|2009-04-02|パナソニック株式会社|Cookie processing program and image data display device|
    WO2002082214A2|2001-04-06|2002-10-17|Predictive Media Corporation|Method and apparatus for identifying unique client users from user behavioral data|
    WO2002084507A1|2001-04-13|2002-10-24|Netiq Corporation|User-side tracking of multimedia application usage within a web page|
    US20030037131A1|2001-08-17|2003-02-20|International Business Machines Corporation|User information coordination across multiple domains|
    JPWO2003027860A1|2001-09-19|2005-01-13|株式会社エヌ・ティ・ティ・アド|Content distribution system for distributing content changing on time axis, content distribution server, log collection server, content relay server, user terminal, content viewing state grasping method, recommendation method, and content providing method|
    US6877007B1|2001-10-16|2005-04-05|Anna M. Hentzel|Method and apparatus for tracking a user's interaction with a resource supplied by a server computer|
    US7343417B2|2001-11-30|2008-03-11|Knowledge Networks, Inc.|System and method for rating media information|
    US20030177488A1|2002-03-12|2003-09-18|Smith Geoff S.|Systems and methods for media audience measurement|
    US20030229884A1|2002-05-21|2003-12-11|Hewlett-Packard Development Company|Interaction manager template|
    US20040088212A1|2002-10-31|2004-05-06|Hill Clarke R.|Dynamic audience analysis for computer content|
    JP2006524009A|2003-03-25|2006-10-19|セドナ・パテント・サービシズ・エルエルシー|Generating audience analysis results|
    CA2686265A1|2003-06-17|2004-12-17|Ibm Canada Limited - Ibm Canada Limitee|Multiple identity management in an electronic commerce site|
    US8464290B2|2003-08-01|2013-06-11|Tacoda, Inc.|Network for matching an audience with deliverable content|
    JPWO2005024689A1|2003-09-04|2007-11-08|株式会社インタースコープ|Method and apparatus for analyzing consumer purchasing behavior|
    US20050144069A1|2003-12-23|2005-06-30|Wiseman Leora R.|Method and system for providing targeted graphical advertisements|
    US7792954B2|2004-04-02|2010-09-07|Webtrends, Inc.|Systems and methods for tracking web activity|
    US20050267799A1|2004-05-10|2005-12-01|Wesley Chan|System and method for enabling publishers to select preferred types of electronic documents|
    US7546370B1|2004-08-18|2009-06-09|Google Inc.|Search engine with multiple crawlers sharing cookies|
    JP2006127321A|2004-10-29|2006-05-18|Solid Technology Kk|Terminal attribute addition device and terminal attribute addition method|
    JP2006127320A|2004-10-29|2006-05-18|Solid Technology Kk|Terminal attribute estimation apparatus and terminal attribute estimation method|
    EP1817919A4|2004-11-29|2011-07-20|Arbitron Inc|Systems and processes for use in media and/or market research|
    US8131861B2|2005-05-20|2012-03-06|Webtrends, Inc.|Method for cross-domain tracking of web site traffic|
    US8856279B2|2005-05-26|2014-10-07|Citrix Systems Inc.|Method and system for object prediction|
    JP4764103B2|2005-08-18|2011-08-31|株式会社東芝|Content data distribution system and information processing apparatus|
    CN100452781C|2005-10-26|2009-01-14|华为技术有限公司|Method for transmitting partial unavailable information to destination user|
    US20080086356A1|2005-12-09|2008-04-10|Steve Glassman|Determining advertisements using user interest information and map-based location information|
    US20090030780A1|2006-01-03|2009-01-29|Ds-Iq, Inc.|Measuring effectiveness of marketing campaigns presented on media devices in public places using audience exposure data|
    JP2007201742A|2006-01-25|2007-08-09|Ntt Software Corp|Content distribution system|
    JP5034279B2|2006-03-15|2012-09-26|富士通株式会社|Attribute estimation program and attribute information providing system|
    CA2666199C|2006-03-27|2015-08-25|Nielsen Media Research, Inc.|Methods and systems to meter media content presented on a wireless communication device|
    US7941525B1|2006-04-01|2011-05-10|ClickTale, Ltd.|Method and system for monitoring an activity of a user|
    US20080004958A1|2006-06-29|2008-01-03|Tony Ralph|Client side counting verification testing|
    CN100456298C|2006-07-12|2009-01-28|百度在线网络技术（北京）有限公司|Advertisement information retrieval system and method therefor|
    US7933843B1|2006-08-26|2011-04-26|CommEq Ltd.|Media-based computational influencer network analysis|
    US7996456B2|2006-09-20|2011-08-09|John Nicholas and Kristin Gross Trust|Document distribution recommender system and method|
    WO2008045792A2|2006-10-06|2008-04-17|Technorati, Inc.|Methods and apparatus for conversational advertising|
    US20090132349A1|2006-10-09|2009-05-21|Splashcast Corp.|Targeted-demographic rich-media content, branding, and syndicated user-node distribution|
    US20080104225A1|2006-11-01|2008-05-01|Microsoft Corporation|Visualization application for mining of social networks|
    US8700457B2|2007-01-03|2014-04-15|William H. Bollman|Mobile phone based rebate device for redemption at a point of sale terminal|
    CN101222348B|2007-01-10|2011-05-11|阿里巴巴集团控股有限公司|Method and system for calculating number of website real user|
    US20080215607A1|2007-03-02|2008-09-04|Umbria, Inc.|Tribe or group-based analysis of social media including generating intelligence from a tribe's weblogs or blogs|
    US8874563B1|2007-03-07|2014-10-28|Comscore, Inc.|Detecting content and user response to content|
    KR100910517B1|2007-03-21|2009-07-31|엔에이치엔비즈니스플랫폼 주식회사|System and method for expanding target inventory according to borwser-login mapping|
    US20080250450A1|2007-04-06|2008-10-09|Adisn, Inc.|Systems and methods for targeted advertising|
    US8229458B2|2007-04-08|2012-07-24|Enhanced Geographic Llc|Systems and methods to determine the name of a location visited by a user of a wireless device|
    US20080276179A1|2007-05-05|2008-11-06|Intapp Inc.|Monitoring and Aggregating User Activities in Heterogeneous Systems|
    US20090024546A1|2007-06-23|2009-01-22|Motivepath, Inc.|System, method and apparatus for predictive modeling of spatially distributed data for location based commercial services|
    US7890592B2|2007-06-29|2011-02-15|Microsoft Corporation|Processing data obtained from a presence-based system|
    US8229780B2|2007-07-30|2012-07-24|Silvercarrot, Inc.|System and method for online lead generation|
    US7698422B2|2007-09-10|2010-04-13|Specific Media, Inc.|System and method of determining user demographic profiles of anonymous users|
    US20090076899A1|2007-09-14|2009-03-19|Gbodimowo Gbeminiyi A|Method for analyzing, searching for, and trading targeted advertisement spaces|
    US8302120B2|2008-02-19|2012-10-30|The Nielsen Company , Llc|Methods and apparatus to monitor advertisement exposure|
    US20090217315A1|2008-02-26|2009-08-27|Cognovision Solutions Inc.|Method and system for audience measurement and targeting media|
    US8112301B2|2008-04-14|2012-02-07|Tra, Inc.|Using consumer purchase behavior for television targeting|
    US20090292587A1|2008-04-17|2009-11-26|Arbitron, Inc.|Cross-media interactivity metrics|
    US8380562B2|2008-04-25|2013-02-19|Cisco Technology, Inc.|Advertisement campaign system using socially collaborative filtering|
    US9384186B2|2008-05-20|2016-07-05|Aol Inc.|Monitoring conversations to identify topics of interest|
    US9083853B2|2008-06-02|2015-07-14|Intent IQ, LLC|Targeted television advertisements associated with online users' preferred television programs or channels|
    US8549163B2|2008-09-18|2013-10-01|Jonathan M. Urdan|Passive parameter based demographics generation|
    US20100088152A1|2008-10-02|2010-04-08|Dominic Bennett|Predicting user response to advertisements|
    CA2741421A1|2008-10-28|2010-05-06|Norwell Sa|Audience measurement system|
    KR101066619B1|2008-11-07|2011-09-22|주식회사 케이티|Prediction system and method using USSD message|
    US20100121676A1|2008-11-11|2010-05-13|Yahoo! Inc.|Method and system for logging impressions of online advertisments|
    JP2010134733A|2008-12-05|2010-06-17|Dainippon Printing Co Ltd|Information recommendation device, information recommendation method, and program|
    US20100153175A1|2008-12-12|2010-06-17|At&T Intellectual Property I, L.P.|Correlation of Psycho-Demographic Data and Social Network Data to Initiate an Action|
    US8356247B2|2008-12-16|2013-01-15|Rich Media Worldwide, Llc|Content rendering control system and method|
    US8462160B2|2008-12-31|2013-06-11|Facebook, Inc.|Displaying demographic information of members discussing topics in a forum|
    US20100179856A1|2009-01-14|2010-07-15|Yahoo! Inc.|Conditional incentive presentation, tracking and redemption|
    JP2012516514A|2009-01-29|2012-07-19|ザニールセンカンパニー（ユーエス）エルエルシー|Method and apparatus for measuring market statistics|
    US20100205057A1|2009-02-06|2010-08-12|Rodney Hook|Privacy-sensitive methods, systems, and media for targeting online advertisements using brand affinity modeling|
    KR101168705B1|2009-02-18|2012-08-02|김기미|Customized and intellectual symbol, icon internet information searching system utilizing a mobile communication terminal and IP-based information terminal|
    US10262337B2|2009-03-06|2019-04-16|AppNexus Inc.|Advertising platform transaction management|
    CN101505247A|2009-03-09|2009-08-12|成都市华为赛门铁克科技有限公司|Detection method and apparatus for number of shared access hosts|
    US8150974B2|2009-03-17|2012-04-03|Kindsight, Inc.|Character differentiation system generating session fingerprint using events associated with subscriber ID and session ID|
    US8266687B2|2009-03-27|2012-09-11|Sophos Plc|Discovery of the use of anonymizing proxies by analysis of HTTP cookies|
    JP5492630B2|2009-03-31|2014-05-14|株式会社ビデオリサーチ|Content contact investigation system and content contact investigation method|
    US20100268540A1|2009-04-17|2010-10-21|Taymoor Arshi|System and method for utilizing audio beaconing in audience measurement|
    US10008212B2|2009-04-17|2018-06-26|The Nielsen Company , Llc|System and method for utilizing audio encoding for measuring media exposure with environmental masking|
    US20100268573A1|2009-04-17|2010-10-21|Anand Jain|System and method for utilizing supplemental audio beaconing in audience measurement|
    EP2427831A4|2009-05-08|2013-07-10|Arbitron Mobile Oy|System and method for behavioural and contextual data analytics|
    US20100325051A1|2009-06-22|2010-12-23|Craig Stephen Etchegoyen|System and Method for Piracy Reduction in Software Activation|
    US9178634B2|2009-07-15|2015-11-03|Time Warner Cable Enterprises Llc|Methods and apparatus for evaluating an audience in a content-based network|
    US8412796B2|2009-07-31|2013-04-02|University College Dublin—National University of Ireland, Dublin|Real time information feed processing|
    US8612860B2|2009-08-12|2013-12-17|Warner Music Inc.|Systems, methods, and media for coordinating the presentation of media with an event|
    US9529864B2|2009-08-28|2016-12-27|Microsoft Technology Licensing, Llc|Data mining electronic communications|
    US20120192214A1|2009-12-22|2012-07-26|Resonate Networks|Method and apparatus for delivering targeted content to television viewers|
    KR101118741B1|2009-08-31|2012-03-12|주식회사 나스미디어|A method for providing internet advertisement popularity rating|
    US20110087519A1|2009-10-09|2011-04-14|Visa U.S.A. Inc.|Systems and Methods for Panel Enhancement with Transaction Data|
    US8595058B2|2009-10-15|2013-11-26|Visa U.S.A.|Systems and methods to match identifiers|
    US9390438B2|2009-12-08|2016-07-12|Comscore, Inc.|Systems and methods for capturing and reporting metrics regarding user engagement including a canvas model|
    US20110191184A1|2010-01-29|2011-08-04|Bank Of America Corporation|Mobile location integrated merchant offer program and customer shopping|
    US20110246306A1|2010-01-29|2011-10-06|Bank Of America Corporation|Mobile location tracking integrated merchant offer program and customer shopping|
    US20110191664A1|2010-02-04|2011-08-04|At&T Intellectual Property I, L.P.|Systems for and methods for detecting url web tracking and consumer opt-out cookies|
    CA2789224C|2010-02-08|2017-09-05|Facebook, Inc.|Communicating information in a social network system about activities from another domain|
    US8280844B2|2010-02-15|2012-10-02|Bank Of America Corporation|Anomalous activity detection|
    US20120310729A1|2010-03-16|2012-12-06|Dalto John H|Targeted learning in online advertising auction exchanges|
    US9946775B2|2010-03-24|2018-04-17|Taykey Ltd.|System and methods thereof for detection of user demographic information|
    KR101682579B1|2010-03-30|2016-12-05|삼성전자 주식회사|Method and apparatus for providing character inputting virtual keypad in a touch terminal|
    US8626901B2|2010-04-05|2014-01-07|Comscore, Inc.|Measurements based on panel and census data|
    US8775400B2|2010-06-30|2014-07-08|Microsoft Corporation|Extracting facts from social network messages|
    US8307006B2|2010-06-30|2012-11-06|The Nielsen Company , Llc|Methods and apparatus to obtain anonymous audience measurement data from network server data for particular demographic and usage profiles|
    US9747605B2|2010-08-02|2017-08-29|Facebook, Inc.|Measuring quality of user interaction with third party content|
    US20130210455A1|2010-08-10|2013-08-15|Telefonaktiebolaget L M Ericsson |Aggregating demographic distribution information|
    US8886773B2|2010-08-14|2014-11-11|The Nielsen Company , Llc|Systems, methods, and apparatus to monitor mobile internet activity|
    US9262517B2|2010-08-18|2016-02-16|At&T Intellectual Property I, L.P.|Systems and methods for social media data mining|
    AU2013203898B2|2010-09-22|2015-07-02|The Nielsen Company , Llc|Methods and apparatus to determine impressions using distributed demographic information|
    US8713168B2|2010-09-22|2014-04-29|The Nielsen Company , Llc|Methods and apparatus to determine impressions using distributed demographic information|
    US9092797B2|2010-09-22|2015-07-28|The Nielsen Company , Llc|Methods and apparatus to analyze and adjust demographic information|
    US8495143B2|2010-10-29|2013-07-23|Facebook, Inc.|Inferring user profile attributes from social information|
    US8484241B2|2010-10-29|2013-07-09|Russell Kent Bouse|Systems and methods to consolidate and communicate user profiles and modality preferences information for content delivery or interaction experiences|
    US10248960B2|2010-11-16|2019-04-02|Disney Enterprises, Inc.|Data mining to determine online user responses to broadcast messages|
    US20120130802A1|2010-11-19|2012-05-24|Jerome Shimizu|Systems, methods and apparatus to design an advertising campaign|
    US8631122B2|2010-11-29|2014-01-14|Viralheat, Inc.|Determining demographics based on user interaction|
    US20120143713A1|2010-12-06|2012-06-07|Campaigngrid, Llc|Electronic and network-based franking|
    US9009298B2|2010-12-10|2015-04-14|The Nielsen Company , Llc|Methods and apparatus to determine audience engagement indices associated with media presentations|
    US9497154B2|2010-12-13|2016-11-15|Facebook, Inc.|Measuring social network-based interaction with web content external to a social networking system|
    US8468559B2|2010-12-13|2013-06-18|Google Inc.|Inferring demographic compositions of television audiences|
    US20120323675A1|2010-12-15|2012-12-20|Ari Paparo|Methods and apparatus to measure comparative performance of internet and television ad campaigns|
    WO2012087954A2|2010-12-20|2012-06-28|The Nielsen Company , Llc|Methods and apparatus to determine media impressions using distributed demographic information|
    US8874639B2|2010-12-22|2014-10-28|Facebook, Inc.|Determining advertising effectiveness outside of a social networking system|
    US20120173701A1|2010-12-30|2012-07-05|Arbitron Inc.|Matching techniques for cross-platform monitoring and information|
    US20120209920A1|2011-02-10|2012-08-16|Microsoft Corporation|Social influencers discovery|
    EP2686779A4|2011-03-18|2014-09-17|Nielsen Co Us Llc|Methods and apparatus to determine media impressions|
    US8315620B1|2011-05-27|2012-11-20|The Nielsen Company , Llc|Methods and apparatus to associate a mobile device with a panelist profile|
    US9282158B2|2011-06-06|2016-03-08|Google Inc.|Reducing redirects|
    US8560683B2|2011-06-10|2013-10-15|Google Inc.|Video and site analytics|
    US9210208B2|2011-06-21|2015-12-08|The Nielsen Company , Llc|Monitoring streaming media content|
    US20130060629A1|2011-09-07|2013-03-07|Joshua Rangsikitpho|Optimization of Content Placement|
    US20130080263A1|2011-09-23|2013-03-28|Jonathan Goldman|Per-view charging for video advertisements|
    US20130124478A1|2011-11-11|2013-05-16|Simply Measured, Inc.|Data analytics reporting system and methods|
    US20130151311A1|2011-11-15|2013-06-13|Bradley Hopkins Smallwood|Prediction of consumer behavior data sets using panel data|
    WO2013078640A1|2011-11-30|2013-06-06|Google Inc.|Estimating user demographics|
    US9331975B2|2011-12-16|2016-05-03|The Nielsen Company , Llc|Systems, methods, and apparatus to identify media presentation devices|
    US20130204711A1|2012-02-02|2013-08-08|Unity Works! Llc|Method and system for creating data-driven multimedia advertisements for dynamically targeted audience|
    US9015255B2|2012-02-14|2015-04-21|The Nielsen Company , Llc|Methods and apparatus to identify session users with cookie information|
    US9659105B2|2012-03-15|2017-05-23|The Nielsen Company , Llc|Methods and apparatus to track web browsing sessions|
    US20130282817A1|2012-03-22|2013-10-24|Gerard J. Montgomery|Targeting Media Based on Viewer Attributes and Elements|
    US9516360B2|2012-04-12|2016-12-06|Qualcomm Incorporated|Estimating demographic statistics of media viewership via context aware mobile devices|
    AU2013204865B2|2012-06-11|2015-07-09|The Nielsen Company , Llc|Methods and apparatus to share online media impressions data|
    US20130346154A1|2012-06-22|2013-12-26|Josephine Holz|Systems and methods for audience measurement analysis|
    US20150206183A1|2012-09-18|2015-07-23|Beijing Yidian Wangju Technology Co., Ltd.|Method and system for facilitating users to obtain content|
    US9055021B2|2012-11-30|2015-06-09|The Nielsen Company , Llc|Methods and apparatus to monitor impressions of social media messages|
    US8935713B1|2012-12-17|2015-01-13|Tubular Labs, Inc.|Determining audience members associated with a set of videos|
    US9609386B2|2012-12-18|2017-03-28|Rentak Corporation|System and methods for analyzing content engagement in conjunction with social media|
    US9832155B2|2013-01-31|2017-11-28|The Nielsen Company , Llc|Methods and apparatus to monitor impressions of social media messages|
    US10333882B2|2013-08-28|2019-06-25|The Nielsen Company , Llc|Methods and apparatus to estimate demographics of users employing social media|
    US8910195B1|2014-02-20|2014-12-09|Google Inc.|Systems and methods for enhancing audience measurement data|US10333882B2|2013-08-28|2019-06-25|The Nielsen Company , Llc|Methods and apparatus to estimate demographics of users employing social media|
    US9344387B1|2014-02-08|2016-05-17|Twitter, Inc.|Analysis of content sharing in a messaging platform|
    WO2016118425A1|2015-01-23|2016-07-28|Tigerlogic Corporation|Multi-dimensional command center|
    US10565601B2|2015-02-27|2020-02-18|The Nielsen Company , Llc|Methods and apparatus to identify non-traditional asset-bundles for purchasing groups using social media|
    US10219039B2|2015-03-09|2019-02-26|The Nielsen Company , Llc|Methods and apparatus to assign viewers to media meter data|
    US10045082B2|2015-07-02|2018-08-07|The Nielsen Company , Llc|Methods and apparatus to correct errors in audience measurements for media accessed using over-the-top devices|
    US20170090718A1|2015-09-25|2017-03-30|International Business Machines Corporation|Linking selected messages in electronic message threads|
    CN106557513A|2015-09-29|2017-04-05|腾讯科技（深圳）有限公司|Event information method for pushing and event information pusher|
    US10187675B2|2015-10-12|2019-01-22|The Nielsen Company , Llc|Methods and apparatus to identify co-relationships between media using social media|
    CN108701322A|2016-02-12|2018-10-23|开利公司|The method for examining cold chain distribution system|
    US9912424B2|2016-05-27|2018-03-06|The Nielsen Company , Llc|Methods and apparatus to estimate ratings for media assets using social media|
    US10547906B2|2016-06-07|2020-01-28|The Nielsen Company , Llc|Methods and apparatus to impute media consumption behavior|
    US10600067B2|2016-06-16|2020-03-24|Accenture Global Solutions Limited|Demographic based adjustment of data processing decision results|
    US10791355B2|2016-12-20|2020-09-29|The Nielsen Company , Llc|Methods and apparatus to determine probabilistic media viewing metrics|
    CN107330091A|2017-07-04|2017-11-07|百度在线网络技术（北京）有限公司|Information processing method and device|
    US11244363B1|2018-10-25|2022-02-08|Sprinklr, Inc.|Rating and review integration system|
    法律状态:
    2018-11-06| B06F| Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]|
    2020-06-02| B06U| Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]|
    2021-10-13| 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
    US201361871243P| true| 2013-08-28|2013-08-28|
    US14/142,411|US10333882B2|2013-08-28|2013-12-27|Methods and apparatus to estimate demographics of users employing social media|
    PCT/US2014/052537|WO2015031262A1|2013-08-28|2014-08-25|Methods and apparatus to estimate demographics of users employing social media|
    [返回顶部]