Information processing device, information processing method, and information processing program

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program that can estimate the attribute of a user whose attribute cannot be estimated.SOLUTION: An information processing apparatus according to the present application comprises: an acquisition unit that acquires user information indicating information on users and action information including users' search histories; a model storage unit that stores a plurality of models that have learned the relationship between the user information, action information, and specific characteristics of users; a calculation unit that calculates indices for the specific characteristics for every user by using the plurality of models; a questioning unit that asks a question related to the specific characteristics to the users for whom the calculation unit has calculated the indices for the specific characteristics; an extraction unit that extracts users for whom the values of the indices are calculated as values within a predetermined range for each of the plurality of models; and a specification unit that inputs the user information of the users extracted by the extraction unit and the action information to the plurality of models, and thereby specifies models in which the values of the indices are calculated as values within the predetermined range.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Attribute information indicating the attributes of users to whom information is to be distributed is registered in advance as distribution destination information, and targeted distribution is carried out in which advertisements corresponding to the attribute information of the users to whom information is to be distributed are selectively distributed.

[0003] For example, Patent Document 1 below discloses a technology for calculating the true relevance between an advertisement and attribute information based on the apparent degree of relevance between the advertisement and attribute information and the average degree of relevance between multiple advertisements and attribute information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-1956 Summary of the Invention [Problem to be solved by the invention]

[0005] When guessing user attribute information, there are cases where users whose attributes cannot be guessed are included. In such cases, it is not possible to meet the needs of businesses that wish to deliver advertisements based on user attributes. Therefore, there is a need to guess the attributes of users whose attributes cannot be guessed.

[0006] In view of the above-described problems, the present disclosure aims to provide an information processing device, an information processing method, and an information processing program that are capable of inferring attributes of a user whose attributes cannot be inferred. [Means for solving the problem]

[0007] In order to solve the above-described problems and achieve the object, an information processing device according to the present disclosure includes an acquisition unit that acquires user information indicating information about a user and behavioral information including a search history of the user, and a learning unit that learns the relationship between the user information, the behavioral information, and specific characteristics of the user. A set of models for each specific feature of a user, which outputs an index relating to the specific feature of the user as a value between 0 and 1 when the user information and the behavioral information are input. a model storage unit that stores a plurality of models; Among the specified models Using , model a calculation unit that calculates an index for a specific feature for each of the plurality of images; By model For users who calculate indicators related to specific features, By model To specific features Regarding whether it applies Ask a question Accept the answer to the question. a query unit and the plurality of models Using the predetermined model group, The value of the index is A value between 0 and 1 an extraction unit that extracts users whose values ​​are calculated to fall within a predetermined range; using a group of models other than the predetermined group of models among the plurality of models, User information of the user extracted by the extraction unit To line dynamic information Womo Dell Every and the value of the index is A value between 0 and 1 and an identifying unit that identifies a model calculated to fall within a predetermined range of values. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to provide an information processing device, an information processing method, and an information processing program that are capable of inferring attributes of a user whose attributes cannot be inferred. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in the user information storage unit of the information processing device according to the embodiment. [Figure 5]FIG. 5 is a diagram illustrating an example of information stored in the behavior information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of information stored in the model storage unit of the information processing apparatus according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the configuration of a user terminal according to the embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 9] FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0011] (Embodiment) 1-1. Example of information processing according to the embodiment First, an example of information processing according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to an embodiment. First, an overview of the information processing according to the embodiment will be described, and then each process will be described in detail.

[0012] 1 shows a process in which an information processing device 100 acquires user information and behavioral information from multiple user terminals 200, inputs the acquired user information and behavioral information into multiple models, calculates an index for a specific feature, asks the users questions related to the specific feature, extracts users whose index values ​​fall within a predetermined range for each of the multiple models, calculates an index for the specific feature using the user information and behavioral information of the extracted users, and identifies a model whose index is calculated to fall within the predetermined range. Hereinafter, an example of information processing according to an embodiment will be described in detail step by step using FIG. 1.

[0013] First, the information processing device 100 acquires user information and behavioral information from multiple user terminals 200 (step S1). For example, the information processing device 100 acquires user information and behavioral information from user terminals 200A to 200F of users U1 to U6, as shown in Fig. 1. Note that users U1 to U6 and user terminals 200A to 200F shown in Fig. 1 are examples, and the information processing device 100 may acquire user information and behavioral information from user terminals 200 of more users.

[0014] Next, the information processing device 100 uses multiple models to calculate an index for a specific feature for each of the multiple models (step S2). Note that the model here refers to a model that has learned the relationship between user information, behavioral information, and an index related to the user's specific feature. When the user information and behavioral information of the user are input to the model, an index related to the user's specific feature is output as a value between 0 and 1. The specific feature here can also be referred to as user attribute information, and refers to the user's hobbies, preferences, etc., such as "I like glasses" or "I like books," or user characteristics. The information processing device 100 inputs the user information and behavioral information acquired from the multiple user terminals 200 into multiple models that calculate an index for the specific feature, and calculates an index for the user's specific feature for each model.

[0015] Next, the information processing device 100 transmits question information related to the specific characteristic to the plurality of user terminals 200 (step S3). For example, the information processing device 100 may transmit question information, which asks a multiple-choice or input-type question as to whether or not the specific characteristic "likes glasses" applies to the user terminals 200 of the plurality of users for whom the index for the specific characteristic was calculated in step S2, and the plurality of user terminals 200 that have received the question information may display the question information on the output unit 230, thereby asking the users for whom the index for the specific characteristic was calculated in step S3 whether or not the specific characteristic applies to them.

[0016] Next, the information processing device 100 receives answer information to a question related to the specific feature from the multiple user terminals 200 (step S4). For example, the information processing device 100 may receive answer information from the user terminal 200 that a user U inputs via the input unit 220 of the user terminal 200 after checking a question related to the specific feature displayed on the user terminal 200. In this case, the answer information that the user U inputs into the input unit 220 of the user terminal 200 may be an answer to the question expressed as "yes" or "no," or an answer to the question expressed in sentences. As shown in FIG. 1, the information processing device 100 receives answer information input by the user U from the multiple user terminals 200.

[0017] Next, the information processing device 100 extracts users whose index values ​​fall within a predetermined range for each of the multiple models (step S5). For example, the information processing device 100 may extract users whose index for a specific feature is calculated to be a value ranging from 0.0 to 0.4 for each of the multiple models. Note that a user whose index for a specific feature is calculated to be a low value, for example, a value ranging from 0.0 to 0.4, is estimated to not have the specific feature. Therefore, when an advertisement distribution company wishes to distribute advertisements to users with an attribute such as "glasses lover," users whose attribute cannot be estimated will not be targeted for advertisement distribution, and therefore it is necessary to understand the user's attribute. In step S5, users whose index for a specific feature is calculated to be low are extracted based on this background.

[0018] Next, the information processing device 100 calculates an index for the specific feature using the extracted user information and behavioral information of the user, and identifies a model for which the index is calculated within a predetermined range (step S6). For example, as shown in FIG. 1, the information processing device 100 may calculate an index for the specific feature of the user extracted in step S5 using the user information and behavioral information of the user extracted in step S5, using models D to F that are different from models A to B used to calculate the index for the specific feature in step S2. Then, the information processing device 100 identifies a model for which the index for the specific feature of the user calculated using models D to F is calculated to be within a predetermined range, for example, a value ranging from 0.8 to 1.0. Because the specific feature defined for each model is different, identifying a model makes it possible to grasp the specific feature possessed by the user.

[0019] This enables the information processing device 100 to estimate the attributes of users whose attributes could not be estimated before. Therefore, when an advertisement distribution company narrows down its target users to users with specific characteristics, it is possible to identify users with the specific characteristics and narrow down its target users to users with the specific characteristics when distributing advertisements.

[0020] 1-2. Another example of information processing according to an embodiment 1 The information processing device 100 calculates an index for a specific characteristic of a user for each category of multiple models, extracts users whose index values ​​are within a predetermined range for each category of multiple models, and identifies models whose index values ​​are calculated to be within a predetermined range for each category of multiple models.

[0021] This information processing will be explained step by step. First, the information processing device 100 executes the same processing as step S1 shown in Fig. 1. The processing of step S1 is the same as the processing described above, and therefore the explanation will be omitted.

[0022] Next, the information processing device 100 calculates an index for a specific feature for each of the multiple models (step S2). In this case, the information processing device 100 calculates an index for a specific feature of the user for each category of the multiple models. Here, as described above, the model is a model that calculates an index for a specific feature when user information and behavioral information are input. The specific feature indicates the user's hobbies, preferences, and characteristics, such as "I like glasses" or "I like books." The specific features are classified into categories such as "fashion," "sports," and "movies," and multiple specific features are defined for each category. For example, in the "fashion" category, "I like glasses," "I like hats," and "I like jackets" are defined. That is, in this case, the information processing device 100 calculates an index for a specific feature of the user for each category using multiple models that calculate indices for specific features such as "I like glasses," "I like hats," and "I like jackets" that belong to the "fashion" category.

[0023] Next, the information processing device 100 executes the same processing as that from step S3 to step S4 shown in Fig. 1. The processing from step S3 to step S4 is the same as that described above, and therefore a description thereof will be omitted.

[0024] Next, the information processing device 100 extracts users whose index values ​​are in a predetermined range for each model (step S5). In this case, the information processing device 100 extracts users whose index values ​​for specific user features are in a predetermined range for each category of multiple models. That is, in step S2, the information processing device 100 calculates the indexes for specific user features for each category, and therefore extracts users whose index values ​​for specific user features are in a predetermined range for each category. For example, the information processing device 100 extracts users whose indexes for specific features "likes glasses," "likes hats," and "likes jackets" belonging to the category "fashion" are calculated to be in a predetermined range, for example, a range from 0.0 to 0.4.

[0025] Next, the information processing device 100 calculates an index for a specific feature using the user information and behavioral information of the extracted users, and identifies a model for which the index is calculated to fall within a predetermined range (step S6). In this case, the information processing device 100 calculates an index for a specific feature for each category of multiple models using the user information and behavioral information of the users extracted in step S5, and identifies a model for which the index for the specific feature is calculated to fall within a predetermined range for each category of multiple models. For example, assume that the information processing device 100 extracts users in step S5 for which the index value for any of the specific features "likes glasses," "likes hats," and "likes jackets" belonging to the category "fashion" is calculated to fall within a predetermined range, for example, a value from 0.0 to 0.4. In this case, the information processing device 100 calculates an index for the specific feature of the extracted user using a model that calculates an index for specific features other than the specific features "likes glasses," "likes hats," and "likes jackets" belonging to the category "fashion." Then, the information processing device 100 identifies a model for which the calculated index value for the specific feature falls within a predetermined range, for example, a value between 0.8 and 1.0. Since specific features are defined for each model, the features possessed by the user can be grasped by identifying the model.

[0026] This makes it possible to estimate the attributes of users whose attributes cannot be estimated for each category. Therefore, it is possible to identify users who are interested in categories that belong to the business field of the business operator that wishes to distribute advertisements, and to identify users who are the target of advertisement distribution for each category.

[0027] [2. Information Processing System Configuration] Next, the configuration of an information processing system according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of an information processing system according to an embodiment. As shown in Fig. 2, an information processing system 1 includes an information processing device 100 and a user terminal 200. Note that the information processing system 1 shown in Fig. 2 may be configured to include a plurality of information processing devices 100 and a plurality of user terminals 200. The information processing device 100 and the user terminal 200 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication.

[0028] The information processing device 100 may be, for example, a personal computer (PC), a workstation (WS), a computer with server functions, etc. The information processing device 100 performs processing based on information transmitted from the user terminal 200 via the network N.

[0029] The user terminal 200 is an information processing device used by a user. The user terminal 200 may be, for example, an information processing device such as a smartphone, a tablet terminal, a desktop PC, a notebook PC, a mobile phone, or a PDA (Personal Digital Assistant). In the example shown in FIG. 1, the user terminal 200 is a smartphone.

[0030] 3. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information processing device according to the embodiment.

[0031] 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Although not shown in FIG. 3, the information processing device 100 may also include an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0032] (Regarding the communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC), etc. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 200.

[0033] (Regarding the storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk, a solid state drive (SSD), an optical disk, etc. As shown in FIG. 3 , the storage unit 120 has a user information storage unit 121, a behavior information storage unit 122, and a model storage unit 123.

[0034] (Regarding the user information storage unit 121) The user information storage unit 121 stores information about the user, i.e., user information. The user information is, for example, personal information about the user that is provided to an information service provider when the user uses a predetermined information service. Here, an example of information stored in the user information storage unit 121 will be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of information stored in the user information storage unit of the information processing device according to the embodiment.

[0035] In the example shown in FIG. 4, the user information storage unit 121 stores information relating to the items "user ID," "date of birth," "gender," and "occupation" in association with each other.

[0036] "User ID" is an identifier that identifies a user and is represented by a string of characters or a number. "Date of birth" is information about the user's date of birth linked to the "User ID". "Gender" is information about the user's gender linked to the "User ID". "Occupation" is information about the user's occupation linked to the "User ID".

[0037] That is, FIG. 4 shows that the date of birth of the user identified by the user ID "UID#1" is "date of birth #U1", the gender is "female", and the occupation is "occupation #U1".

[0038] The information stored in the user information storage unit 121 is not limited to information relating to the items "user ID," "date of birth," "gender," and "occupation," and any other personal information of the user may be stored.

[0039] (Regarding the behavioral information storage unit 122) The behavioral information storage unit 122 stores information indicating the behavior of a user, i.e., behavioral information. The behavioral information is information indicating the behavior of a user using a predetermined information service, which is generated as a result of the user's use of the predetermined information service. Here, an example of information stored in the behavioral information storage unit 122 will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of information stored in the behavioral information storage unit of the information processing device according to the embodiment.

[0040] In the example shown in FIG. 5, the behavior information storage unit 122 stores information relating to the items "user ID," "search history," "browsing history," "purchase history," "route search history," and "bulletin board posting history" in association with each other.

[0041] "User ID" is an identifier that identifies a user and is represented by a string of characters, a number, etc. "Search history" is information that includes the search query used by a user linked to a "User ID" for a search and the time of entry. "Browsing history" is information that includes the sites viewed by a user linked to a "User ID" and the time of viewing. "Purchase history" is information that includes the products or services purchased by a user linked to a "User ID" on an internet mail order site or a specified service contract site and the time of purchase. "Route search history" is information that includes the route search results and the search time of a user linked to a "User ID". "Bulletin board posting history" is information that includes the bulletin board posts by a user linked to a "User ID" and the time of posting.

[0042] That is, in Figure 5, the search history of the user identified by the user ID "UID#1" is "Search History #U1", the user's browsing history is "Browse History #U1", the purchase history is "Purchase History #U1", the route search history is "Route Search History #U1", and the message board posting history is "Message board posting history #U1".

[0043] The information stored in the behavioral information storage unit 122 is not limited to information relating to the items "user ID," "search history," "browsing history," "purchase history," "route search history," and "bulletin board posting history," but may also store any other information relating to the behavior of the user.

[0044] (Regarding the model storage unit 123) The model storage unit 123 stores a plurality of models that have been trained on the relationship between user information, behavioral information, and specific characteristics of users. When user information and behavioral information are input to the model, an index for the specific characteristic is calculated. Fig. 6 is a diagram showing an example of information stored in the model storage unit of the information processing device according to the embodiment.

[0045] In the example shown in FIG. 6, the model storage unit 123 stores information relating to the items "model ID" and "model data" in association with each other.

[0046] "Model ID" is an identifier that identifies a machine learning model and is represented by a character string, a number, or the like. "Model data" indicates the model data of the machine learning model. For example, the machine learning model may be a neural network.

[0047] 6, the model identified by the model ID "M#1" indicates the machine learning model M#1. Also, model data "MDT#1" indicates the model data of the machine learning model M#1.

[0048] Here, if the machine learning model is a neural network, the model data "MDT#1" includes various information, such as connection information on how the nodes included in each of the multiple layers that make up the neural network are connected to each other, and connection coefficients that are multiplied by the numerical values ​​input and output between the connected nodes.

[0049] The model storage unit 123 is not limited to storing information related to the items "model ID" and "model data," and may store information related to any other machine learning model. The model storage unit 123 may also store models for each category of specific features, or may associate category information with models so that models can be searched for by category.

[0050] (Regarding the control unit 130) Next, returning to Fig. 3, the control unit 130 will be described. The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device of the information processing device 100 using RAM as a work area. The control unit 130 may also be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array), for example.

[0051] As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a calculation unit 132, a question unit 133, an extraction unit 134, and an identification unit 135.

[0052] (Regarding the acquisition unit 131) The acquisition unit 131 acquires user information indicating information about a user and behavioral information indicating the user's behavior. Here, the user information is information about a user, such as information provided to an information service provider when the user uses a predetermined information service. The behavioral information is information indicating the user's behavior using the predetermined information service, which is generated as a result of the user's use of the predetermined information service. After acquiring the user information, the acquisition unit 131 stores the acquired user information in the user information storage unit 121. After acquiring the behavioral information, the acquisition unit 131 stores the acquired behavioral information in the behavioral information storage unit 122. Note that the acquisition unit 131 may acquire either or both of the user information and the behavioral information at each predetermined date and time, or may acquire either or both of the user information and the behavioral information every time the user accesses the information processing device 100.

[0053] Furthermore, the source from which the acquisition unit 131 acquires user information and behavioral information is not limited to the user terminal 200, but may be acquired from other server devices that provide various information services such as search services, shopping services, payment services, route search services, map provision services, travel services, restaurant introduction services, weather forecast services, schedule management services, news provision services, auction services, video content distribution services, and financial trading (stock trading, etc.) services, or may be acquired from external storage media.

[0054] (Regarding the calculation unit 132) The calculation unit 132 uses a plurality of models to calculate an index for a specific feature of the user for each model. When user information and behavioral information are input, the calculation unit 132 inputs the user information and behavioral information into a model that calculates an index for the specific feature, thereby calculating an index for the specific feature of the user for each model. Note that the models used to calculate the index are read from the model storage unit 123 and used, and the calculation unit 132 calculates the index for the specific feature of the user for each model. Furthermore, the number of models used by the calculation unit 132 to calculate an index for the specific feature of the user may be any number.

[0055] Furthermore, the calculation unit 132 may calculate an index for a specific feature of a user for each category of a plurality of models. The specific features are classified into categories such as "fashion," "sports," and "movies," and a plurality of specific features are defined for each category. For example, the calculation unit 132 may use a plurality of models that calculate indices for specific features such as "likes glasses," "likes hats," and "likes jackets" that belong to the category "fashion," and input user information and behavioral information of the user into the plurality of models to calculate an index for the specific feature of the user for each category.

[0056] (Regarding Question 133) The questioning unit 133 asks a question related to the specific feature to a user for whom an index related to the specific feature has been calculated. As shown in FIG. 1 , the calculation unit 132 calculates an index related to the specific feature for each user. Therefore, the questioning unit 133 asks a question related to the specific feature to a user for whom the calculation unit 132 has calculated an index related to the specific feature. For example, the questioning unit 133 may ask a question related to the specific feature to the user terminals 200 of multiple users for whom the calculation unit 132 has calculated an index related to the specific feature by transmitting question information, in a multiple-choice or input format, asking whether or not the specific feature "likes glasses." In this case, the questioning unit 133 may cause the multiple user terminals 200 that have received the question information to display the question information on the output unit 230, and may receive answer information from the user terminal 200 that a user U inputs via the input unit 220 of the user terminal 200 after confirming the question related to the specific feature displayed on the user terminal 200.

[0057] (Regarding the extraction unit 134) The extraction unit 134 extracts users whose index values ​​are calculated to be within a predetermined range for each of the multiple models. For example, the extraction unit 134 may extract users whose index values ​​for a specific feature are calculated to be within a predetermined range for each of the multiple models. Furthermore, the extraction unit 134 may extract users whose index values ​​are calculated to be within a predetermined range across the multiple models. For example, if the user information and behavioral information of user U1 are input into model A to calculate the index, the index value is calculated to be 0.2, the index value is calculated using model B, and the index value is calculated to be 0.4 when the index is calculated using model C, then the index value for user U1 is calculated to be within a range from 0.0 to 0.4 using the three models, model A, model B, and model C. Therefore, in this case, the extraction unit 134 may extract user U1 as a user whose index values ​​are calculated to be within a predetermined range even when multiple models are used, and whose features could not be estimated.

[0058] Furthermore, the extraction unit 134 may extract users whose index values ​​are in a predetermined range for each category of a plurality of models. When the calculation unit 132 calculates an index for a specific feature of a user for each category, the extraction unit 134 may extract users whose index values ​​for the specific feature of a user are in a predetermined range for each category. For example, the extraction unit 134 extracts users whose index values ​​for the specific features "like glasses," "like hats," and "like jackets," which belong to the category "fashion," are calculated by the calculation unit 132 as values ​​in a predetermined range, for example, a range from 0.0 to 0.4.

[0059] (Regarding the identification unit 135) The identification unit 135 inputs the user information and behavioral information of the user extracted by the extraction unit 134 into multiple models and identifies a model in which the index value is calculated to be within a predetermined range. For example, the identification unit 135 may calculate an index for the extracted specific feature of the user using the user information and behavioral information of the user extracted by the extraction unit 134, using a model different from the model used by the calculation unit 132 to calculate the index for the specific feature of the user. The identification unit 135 identifies a model in which the index for the specific feature of the user calculated using a model different from the model used by the calculation unit 132 to calculate the index is calculated to be within a predetermined range, for example, a value ranging from 0.8 to 1.0. Here, since the specific feature defined for each model is different, it is possible to grasp the specific feature possessed by the user by identifying the model.

[0060] Furthermore, the identification unit 135 may identify a model for which the index value is calculated to be within a predetermined range for each category of multiple models. For example, assume that the extraction unit 134 extracts a user for whom the index values ​​of the specific features "likes glasses," "likes hats," and "likes jackets" belonging to the category "fashion" are all calculated to be within a predetermined range, for example, from 0.0 to 0.4. In this case, the identification unit 135 calculates the index for the specific feature of the extracted user using a model that calculates indexes for specific features other than the specific features "likes glasses," "likes hats," and "likes jackets" belonging to the category "fashion." Then, the identification unit 135 identifies a model for which the index value for the calculated specific feature is calculated to be within a predetermined range, for example, from 0.8 to 1.0. Since specific features are defined for each model, identifying a model makes it possible to understand the features possessed by a user.

[0061] Here, examples of reasons why a model that calculates an index for a specific user characteristic may calculate a low value for the index, i.e., be unable to estimate the user characteristic, include overlapping of features due to the use of features from a specific anime, estimation using a model that belongs to a specific category, a small amount of data used to train the model, using a search query as a feature, averaging or variance processing of the data used to train the model, or using a special neural network.

[0062] [4. User terminal configuration] Next, the configuration of the user terminal 200 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of the configuration of the user terminal according to the embodiment. As shown in Fig. 7, the user terminal 200 has a communication unit 210, an input unit 220, an output unit 230, and a control unit 240.

[0063] The communication unit 210 is realized by, for example, a NIC etc. The communication unit 210 is connected to a network N by wire or wirelessly, and transmits and receives various information to and from the information processing device 100 via the network N.

[0064] Various types of operation information are input from the user to the input unit 220. For example, the input unit 220 may accept various operations from the user via a display surface (e.g., the output unit 230) using a touch panel. The input unit 220 may also accept various operations from buttons provided on the user terminal 200 or a keyboard or mouse connected to the user terminal 200.

[0065] The output unit 230 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. In other words, if the input unit 220 of the user terminal 200 is a touch panel, the display screen of the output unit 230 accepts input from the user and also outputs the input to the user. The output unit 230 may also be a speaker, and may output sound from the speaker.

[0066] The control unit 240 is realized, for example, by a CPU, an MPU, or the like executing various programs stored in the user terminal 200 using RAM as a work area. The control unit 240 may also be realized, for example, by an integrated circuit such as an ASIC or an FPGA.

[0067] As shown in FIG. 7, the control unit 240 includes a receiving unit 241.

[0068] The reception unit 241 receives answers to questions from users. The reception unit 241 receives question information transmitted from the information processing device 100 via the communication unit 210, displays the question information on the output unit 230, and receives answers to the questions from users via the input unit 220. Note that the answer information received by the reception unit 241 may include "yes" or "no" that the user has answered to the question included in the question information, or a sentence that expresses the answer to the question.

[0069] [5. Information Processing Flow] Next, a procedure of information processing by the information processing device 100 according to the embodiment will be described with reference to FIG. 8. FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment. For example, the information processing device 100 acquires user information indicating information about a user and behavioral information including the user's search history (step S101). Then, the information processing device 100 stores a plurality of models that have been trained to learn the relationships between the user information, the behavioral information, and specific characteristics of the user (step S102). Then, the information processing device 100 calculates an index for the specific characteristic for each user using the plurality of models (step S103). Then, the information processing device 100 asks a question related to the specific characteristic to the user for whom the index for the specific characteristic has been calculated (step S104). Then, the information processing device 100 extracts users whose index values ​​are within a predetermined range for each of the plurality of models (step S105). Then, the information processing device 100 inputs the user information and behavioral information of the extracted users into models and identifies models for which the index values ​​have been calculated to fall within a predetermined range (step S106).

[0070] [6. Hardware Configuration] The information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in Fig. 9, for example. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090.

[0071] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device that stores data used by the arithmetic device 1030 for various calculations and various databases, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, or the like.

[0072] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, scanner, etc., and is realized by a USB, etc.

[0073] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0074] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0075] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0076] For example, when the computer 1000 functions as the information processing device 100, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 130 of the information processing device 100 by executing a program loaded onto the primary storage device 1040.

[0077] [7. Composition and Effects] The information processing device 100 according to the present disclosure includes an acquisition unit 131 that acquires user information indicating information about a user and behavioral information including the user's search history; a model storage unit 123 that stores a plurality of models that have been trained to learn the relationship between the user information, the behavioral information, and specific characteristics of the user; a calculation unit 132 that calculates an index for the specific characteristic for each user using the plurality of models; a questioning unit 133 that asks questions related to the specific characteristic to users for whom the calculation unit 132 has calculated an index for the specific characteristic; an extraction unit 134 that extracts users for whom the index value has been calculated to be within a predetermined range for each of the plurality of models; and an identification unit 135 that inputs the user information and behavioral information of the users extracted by the extraction unit 134 into a plurality of models and identifies models for which the index value has been calculated to be within a predetermined range.

[0078] This configuration makes it possible to estimate the attributes of users whose attributes cannot be estimated. As a result, it is possible to effectively utilize the accumulated user information and behavioral information to meet the needs of businesses that wish to deliver advertisements to users with specific characteristics.

[0079] The calculation unit 132 of the information processing device 100 according to the present disclosure calculates an index for a specific characteristic of a user for each category of a plurality of models, the extraction unit 134 extracts users whose index values ​​fall within a predetermined range for each category of a plurality of models, and the identification unit 135 identifies models whose index values ​​are calculated to fall within a predetermined range for each category of a plurality of models.

[0080] This configuration makes it possible to extract users whose attributes cannot be estimated for each category and estimate the attributes of users for each category. This meets the needs of businesses wishing to distribute advertisements by specifying the characteristics of users belonging to a specific category.

[0081] The information processing method according to the present disclosure includes the steps of acquiring user information indicating information about a user and behavioral information including the user's search history, storing a plurality of models that have been trained to learn the relationship between the user information, the behavioral information, and specific characteristics of the user, calculating an index for the specific characteristic for each user using the plurality of models, asking questions related to the specific characteristic to the users for whom the index for the specific characteristic has been calculated, extracting users for each of the plurality of models whose index values ​​have been calculated to fall within a predetermined range, and inputting the user information and behavioral information of the extracted users into a model to identify models whose index values ​​have been calculated to fall within a predetermined range.

[0082] This configuration makes it possible to grasp the characteristics of users whose characteristics are difficult to grasp. As a result, by effectively utilizing the accumulated user information and behavioral information, it is possible to meet the needs of businesses that wish to deliver advertisements to users with specific characteristics.

[0083] The information processing program disclosed herein causes a computer to execute the following steps: acquiring user information indicating information about a user and behavioral information including the user's search history; storing multiple models that have been trained to learn the relationship between the user information, behavioral information, and specific characteristics of the user; calculating an index for the specific characteristic for each user using the multiple models; asking users for whom an index for the specific characteristic has been calculated questions related to the specific characteristic; extracting users for each of the multiple models whose index values ​​have been calculated to fall within a predetermined range; and inputting the user information and behavioral information of the extracted users into a model to identify models whose index values ​​have been calculated to fall within a predetermined range.

[0084] This configuration makes it possible to ascertain the attributes of users whose attributes are not readily available, thereby effectively utilizing the accumulated user information and behavioral information to meet the needs of businesses wishing to deliver advertisements to users with specific characteristics.

[0085] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0086] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, the acquisition unit 131 can be read as acquisition means or acquisition circuit. [Explanation of symbols]

[0087] 100 Information processing device 110 Communications Department 120 Storage section 121 User information storage unit 122 Behavior information storage unit 123 Model Memory Unit 130 Control Unit 131 Acquisition Department 132 Calculation Unit 133 Questions 134 Extraction part 135 Specific part 200 User terminals 210 Communications Department 220 Input section 230 Output section 240 Control Unit 241 Reception Department N Network

Claims

1. an acquisition unit that acquires user information indicating information about a user and behavioral information including a search history of the user; a model storage unit that stores a plurality of models, each of which is a set of models for each specific feature of a user that have learned the relationship between the user information, the behavioral information, and the specific feature of the user, and that outputs an index relating to the specific feature of the user as a value between 0 and 1 when the user information and the behavioral information are input; a calculation unit that calculates an index of a specific feature for each model using a predetermined group of models from among the plurality of models; a questioning unit that asks a user about which indexes for the specific features of each model have been calculated by the calculation unit whether or not the user corresponds to the specific features of each model, and receives answer information to the question; an extraction unit that uses the predetermined group of models from the plurality of models to extract users whose index values ​​are calculated to be within a predetermined range from 0 to 1 for each model; an identification unit that uses a group of models other than the predetermined group of models among the plurality of models, inputs user information and behavior information of the user extracted by the extraction unit for each model, and identifies a model for which the value of the index is calculated to be within a predetermined range of values ​​from 0 to 1, Information processing device.

2. the calculation unit calculates an index for a specific feature of the user for each category of the plurality of models; the extraction unit extracts users whose index values ​​are within a predetermined range for each category of the plurality of models; the identification unit identifies a model for which the index value is calculated to be within a predetermined range for each category of the plurality of models. The information processing device according to claim 1 .

3. An information processing method executed by an information processing device, comprising: acquiring user information indicating information about the user and behavioral information including the user's search history; a step of storing a plurality of models, each of which is a set of models for each specific feature of a user that have been trained to learn the relationship between the user information, the behavioral information, and the specific feature of the user, and which outputs an index relating to the specific feature of the user as a value between 0 and 1 when the user information and the behavioral information are input; calculating an index for a specific feature for each model using a predetermined group of models from among the plurality of models; a step of asking a user who has calculated an index related to a specific feature for each model whether or not the index corresponds to the specific feature for each model, and receiving answer information to the question; extracting users whose index values ​​are calculated to be within a predetermined range of values ​​between 0 and 1 for each model using the predetermined group of models from among the plurality of models; and using a group of models other than the predetermined group of models among the plurality of models, inputting the user information and behavior information of the extracted user for each model, and identifying a model in which the value of the index is calculated to be within a predetermined range of values ​​from 0 to 1. Information processing methods.

4. acquiring user information indicating information about the user and behavioral information including the user's search history; a step of storing a plurality of models, each of which is a set of models for each specific feature of a user that have been trained to learn the relationship between the user information, the behavioral information, and the specific feature of the user, and which outputs an index relating to the specific feature of the user as a value between 0 and 1 when the user information and the behavioral information are input; calculating an index for a specific feature for each model using a predetermined group of models from among the plurality of models; a step of asking a user who has calculated an index related to a specific feature for each model whether or not the index corresponds to the specific feature for each model, and receiving answer information to the question; extracting users whose index values ​​are calculated to be within a predetermined range of values ​​between 0 and 1 for each model using the predetermined group of models from among the plurality of models; using a group of models other than the predetermined group of models among the plurality of models, inputting the user information and behavioral information of the extracted users for each model, and identifying a model that has calculated the value of the index to be within a predetermined range of values ​​from 0 to 1; An information processing program that causes a computer to execute the above.

Images