JP2020035166A - Device, method, and program for processing information - Google Patents

Abstract

To enhance benefit of use.SOLUTION: An information processing device of the present invention includes an acquisition unit and a generation unit. The acquisition unit acquires feature information, including at least either of a model for estimating user features using a user attribute and an estimation result regarding the user features estimated using the user attribute, from each of different services. The generation unit generates new feature information by combining the pieces of feature information acquired by the acquisition unit according to inclusion information representing inclusion relationship among categories corresponding to the pieces of feature information.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing device, an information processing method, and an information processing program.

  2. Description of the Related Art Conventionally, for example, there is an information processing apparatus that provides various services to a user and analyzes the attributes of the user obtained by using the services to estimate the characteristics of the user. In this type of information processing apparatus, the service provided by the user may be optimized based on the estimated characteristics of the user.

JP 2018-32252 A

  However, the above-mentioned technology estimates the characteristics of the user by unique analysis of each service, and applies the estimation result to optimization of its own service, and uses the estimation result of another service. Was not taken into account.

  If a plurality of services cooperate, it is expected that estimation results of other services can be shared with each other. However, if only the estimation result is shared, the utility value may not be sufficiently increased.

  The present application has been made in view of the above, and an object of the present invention is to provide an information processing apparatus, an information processing method, and an information processing program that can increase the use value.

  An information processing device according to the present application includes an acquisition unit and a generation unit. The acquisition unit acquires, from each of the different services, a model for estimating a feature of the user using an attribute of the user, and feature information including at least one of estimation results on the feature estimated using the attribute. The generation unit generates new feature information by combining the feature information acquired by the acquisition unit based on correspondence information indicating a correspondence relationship of each category corresponding to the feature information.

  According to an aspect of the embodiment, there is an effect that a use value can be increased.

FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of the shared information. FIG. 5 is a diagram illustrating an example of the service information. FIG. 6 is a diagram illustrating an example of the model program information. FIG. 7 is a diagram illustrating an example of the inclusion information. FIG. 8A is a diagram (part 1) illustrating a specific example of a process performed by the generation unit; FIG. 8B is a diagram (part 2) illustrating a specific example of a process performed by the generation unit; FIG. 8C is a diagram (part 3) illustrating a specific example of a process performed by the generation unit; FIG. 8D is a diagram (part 4) illustrating a specific example of a process performed by the generation unit; FIG. 9 is a diagram illustrating an example of the reception screen. FIG. 10 is a flowchart illustrating a procedure of a process performed by the information processing apparatus according to the embodiment. FIG. 11 is a flowchart illustrating a procedure of a providing process performed by the information processing apparatus according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus according to the embodiment.

  First, an example of information processing performed by the information processing apparatus according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 1 illustrates an information processing system S including an information processing apparatus 1 according to the embodiment. As illustrated in FIG. 1, the information processing system S according to the embodiment includes an information processing device 1, a service providing server 10 (10-1, 10-2, 10-3), and a user terminal 100.

  The user terminal 100 is a terminal device owned by the user U. The user U uses the service Y (Y1, Y2, Y3) provided by each service providing server 10 by operating the user terminal 100 and accessing the service providing server 10 (steps S1-1 and S1-2). , S1-3).

  The service providing server 10 is a server device that provides various services Y to the user U. The service Y provided by the service providing server 10 is a service that distributes information via various applications installed on the user terminal 100, for example. Such services include, for example, a news providing service, an auction service, a weather forecast service, a shopping service, a financial transaction (stock trading, etc.) service, a route search service, a map providing service, a travel service, a restaurant introduction service, and a blog. There are services etc. Note that the service Y is not limited to a service to which information is distributed via an application, and may be, for example, a service in which the user U provides information by accessing a browser.

  In FIG. 1, the service Y1 is a shopping service for providing a shopping site, the service Y2 is a map providing service for providing a function related to a map, and the service Y3 is a search site for searching various information. The case of a search service will be described as an example.

  In addition, each service providing server 10 estimates the characteristics of the user U by analyzing the attribute of the user U using the service Y. Specifically, each service providing server 10 has at least one of a model for estimating the characteristics of the user U using the attributes of the user U and an estimation result regarding the characteristics of the user U estimated using the attributes of the user U. Is generated (steps S2-1, S2-2, S2-3).

  The attribute referred to here is an attribute determined by the user U or a characteristic of the user U, and includes, for example, action information on the action of the user U when using the service Y such as a search log and a purchase history. This is a concept including demographic attributes such as gender, age, address, etc., and psychographic attributes such as life cycle, values, personality, purchase motivation, and the like.

  In addition, the characteristics of the user U are properties of the user U estimated by including various attributes of the user U, or attributes estimated, and include, for example, interests, hobbies, preferences, and behaviors of the user U. Includes patterns (search behavior, purchase behavior, etc.).

  In the above-described model in the feature information, for example, the attribute of the user U can be input and the feature of the user U can be output as a score. The above estimation result in the feature information is, for example, a score output by the model. Note that the estimation result may be information that does not depend on the model, for example, information obtained by simply digitizing the attribute of the user U (for example, a score that increases or decreases according to the number of searches). In the example shown in FIG. 1, the service Y1 as a shopping service generates a “fishing lover” model, and outputs a score “8.6” as an estimation result.

  The service Y2 as a map providing service generates a “drive liking” model and outputs a score “8.5” as an estimation result. Further, the service Y3 as a search site service generates a “travel lover” model and outputs a score “9.8”. FIG. 1 shows that the higher the score, the stronger the feature.

  In addition, the above-described score has been described as being a continuous value, but may be a discrete value, for example. Specifically, whether or not the user likes fishing may be represented by a discrete value score of either “1” (like) or “0” (dislike). Alternatively, although the score is shown as an example of the estimation result, the estimation result is not limited to the score, and may be textual information such as “I like fishing”.

  In this way, when the estimation results of the plurality of services Y are summarized, as shown in FIG. 1, it can be seen that the user U likes fishing, drives, and travels. That is, it is estimated that the user U likes the outdoors.

  However, for example, if there is no “outdoor lover” model among the registered models, it may not be possible to determine whether the user U likes the outdoor. In other words, there is room for improvement in increasing the use value.

  Therefore, in the information processing method according to the embodiment, new specific information is generated based on the specific information of a plurality of services Y. That is, in the information processing method according to the embodiment, new feature information is generated by combining the estimation results of the respective feature information based on the correspondence information indicating the correspondence between the categories corresponding to the respective feature information. In the following, the case where the above model is generated as the feature information will be described. However, the present invention is not limited to the model, and a new estimation result (score list) can be generated.

  Specifically, the information processing apparatus 1 according to the embodiment causes the specific information generated for each service Y to be registered as shared information for each user (steps S3-1, S3-2, and S3-3).

  Subsequently, the information processing device 1 generates a new model based on the estimation result and the inclusion information of the feature information registered by each service Y (S4). The inclusion information is, for example, an index such as a tree structure, and indicates each category for each hierarchy. The inclusion information is an example of correspondence information. Further, the correspondence information is not limited to the inclusion information, and may be other information as long as the information indicates the correspondence of each category.

  In other words, the inclusion information includes information such as “I like outdoor” as a superordinate concept of “I like fishing”, “I like driving” and “I like traveling”. For example, the information processing device 1 can newly generate an “outdoor lover” model by combining the respective feature information based on the above inclusion information.

  In the example shown in FIG. 1, a case is shown in which the user U who likes “fishing outdoors”, “likes driving” and “travels like” is estimated as “outdoors favorite”. That is, in the example illustrated in FIG. 1, “I like the outdoors” is the logical product of the users U who satisfy “I like fishing”, “I like driving”, and “I like traveling”.

  Note that the information processing apparatus 1 is not limited to the logical product, and can generate new feature information using a logical sum. Further, the information processing apparatus 1 can generate a model corresponding to a lower concept of the category by combining a plurality of pieces of feature information included in one category, but such a point will be described later.

  As described above, the information processing device 1 according to the embodiment can automatically generate a new model. As a result, it is possible to share the estimation result of the new model, and it is possible to increase the utility value.

  Further, when requested by the service Y, the information processing apparatus 1 provides the provision information based on the registered characteristic information (steps S5-1, S5-2, and S5-3). For example, there are the following two methods for providing the provided information.

  The first is a method in which the service providing server 10 designates a specific user U and provides a feature (estimated result) of the user U based on the shared information.

  The second is a method in which the service providing server 10 specifies a specific feature and provides a list of users U having the feature based on the shared information.

  That is, in the information processing method according to the embodiment, the characteristic information generated comprehensively for the attribute of the user U is accumulated as the analysis result. Thereby, the other service Y acquires the estimation result of each model, that is, the attribute associated with the user U or the information of the user U associated with the attribute is comprehensively acquired by the other service Y. it can.

  Therefore, in the information processing method according to the embodiment, the technical difficulties can be solved because the other service Y can comprehensively acquire the information of the user U as the shared information. That is, according to the information processing method according to the embodiment, the analysis result of another service Y can be obtained without being conscious of the gap between the services Y.

  Next, the configuration of the information processing system S according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the information processing system S according to the embodiment. As illustrated in FIG. 2, the information processing system S according to the embodiment includes an information processing apparatus 1, a plurality of service providing servers 10-1 to 10-n, and a plurality of user terminals 100-1 to 100-m. Including. The information processing apparatus 1, the plurality of service providing servers 10-1 to 10-n, and the plurality of user terminals 100-1 to 100-m are connected via a network N. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (a mobile telephone network, a fixed telephone network, or the like), a regional IP (Internet Protocol) network, the Internet, or the like. The network N may include a wired network or a wireless network.

  The user terminal 100 is a terminal device used by the user U as described above. The user terminal 100 is, for example, a smart device (smartphone or tablet), a mobile phone, a personal computer, or the like. The user terminal 100 transmits a request for information to the service providing server 10 according to the operation of the user U.

  The information processing device 1 is a server device that functions as an upper server of the service providing server 10. The information processing apparatus 1 causes each service providing server 10 to register characteristic information to generate shared information, and provides the service providing server 10 with various information using the generated shared information.

  The service providing server 10 is a server device that provides the service Y to the user U as described above. The service providing server 10 generates feature information using, for example, the attribute of the user U using the service Y. In addition, the service providing server 10 requests information to be provided from the information processing apparatus 1. The request for the provided information is transmitted from the service providing server 10 by, for example, operating the dedicated terminal connected to the service providing server 10 by the administrator of the service Y.

  In the information processing system S, the information processing apparatus 1 and the plurality of service providing servers 10-1 to 10-n are configured to be owned by, for example, one business operator. That is, one company can provide a plurality of services Y. In addition, one business entity collects the analysis results (feature information) of each service Y as shared information in the information processing apparatus 1, and acquires and uses provided information based on the shared information.

  In addition, the information processing apparatus 1 and the plurality of service providing servers 10-1 to 10-n may be configured by different businesses. That is, another service Y as viewed from a certain service Y of a certain company may be another service Y of the same company or a service Y of another company. Further, the plurality of service providing servers 10-1 to 10-n may be configured to be owned by different operators. Further, in addition to the information processing system S described above, a server of a business entity that uses only the provided information may be connected.

  Note that FIG. 2 illustrates a case where the information processing apparatus 1 is configured separately from the service providing server 10 and has a function of generating and providing shared information. Some or all of the functions of the information processing device 1 may be performed instead.

  FIG. 2 illustrates a case where the information processing apparatus 1 has all the functions of generating and providing shared information. However, for example, even when a plurality of information processing apparatuses 1 share and perform the above-described functions. Good.

  Next, the configuration of the information processing apparatus 1 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus 1 according to the embodiment.

  As shown in FIG. 3, the information processing device 1 includes a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes an acquisition unit 31, an association unit 32, a generation unit 33, a reception unit 34, an extraction unit 35, an estimation unit 36, and a provision unit 37.

  The communication unit 2 is realized by, for example, an NIC (Network Interface Card) or the like. The communication unit 2 is connected to the network N by wire or wirelessly, and transmits and receives information via at least the service providing server 10 via the network N.

  The storage unit 4 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2, the storage unit 4 stores shared information 41, service information 42, model program information 43, and inclusion information 44.

  The shared information 41 is information including the characteristic information acquired from the service providing server 10. FIG. 4 is a diagram illustrating an example of the shared information 41. As shown in FIG. 4, the shared information 41 is, for example, a table in which a column item is “UID” and a line item is “feature information”. Further, a score, which is an output of the model in the feature information, is input to each set of data items of the column items and the row items.

  “UID” is identification information for identifying the user U. “Feature information” is information on a model and a score generated in each of the service providing servers 10. In FIG. 4, a model name is input to each item of “feature information”.

  As shown in FIG. 4, the shared information 41 is information including scores of “UID” and “feature information”. In the example shown in FIG. 4, the user whose UID is “U1” has a score of “2.3” for the model “fishing lover” of the service Y1, and has a score of “3. 5 ". The user whose UID is “U1” has a score of “9.8” for the model “travel lover” of the service Y3.

  Further, in FIG. 4, the shared information 41 is shown as a score, but the shared information 41 is not limited to the score, and is divided into stages such as “○, Δ and ×”, “excellent, good, and acceptable”. Information may be used. Similarly, in FIG. 4, the degrees of reliability are indicated by numerical values, but may be indicated by stages such as “○, Δ and X”, “excellent, good, and acceptable”.

  Next, the service information 42 is information on the service Y provided by each service providing server 10. FIG. 5 is a diagram illustrating an example of the service information 42. As shown in FIG. 5, the service information 42 includes items such as “service ID”, “provided service”, and “number of registered models”.

  “Service ID” is identification information for identifying the service Y (or the service providing server 10). “Provided service” is information indicating the content of service Y. “Number of registered models” is information indicating the number of models of feature information registered in shared information 41.

  Next, the model program information 43 is information including model program data in the feature information. FIG. 6 is a diagram illustrating an example of the model program information 43. The model program information 43 is information including program data of a model in the feature information acquired by the acquisition unit 31 described later. As shown in FIG. 6, the model program information 43 includes items such as “model ID”, “model name”, “group”, “service ID”, and “model data”.

  “Model ID” is identification information for identifying a model in the feature information. “Model name” is identification information indicating the name of the model in the feature information. “Group” is identification information for identifying each group when the models in the feature information are grouped.

  “Service ID” is identification information for identifying the service Y (or the service providing server 10). “Model data” is model program data in the feature information.

  “Model data” is, for example, a regression model in which the attributes of the user U are used as explanatory variables. For example, “model data” is a regression model represented by the following equation. That is, it can be represented as a regression model of y = ω1 · x1 + ω2 · x2 +... + Ωn · xn.

In the above equation, “x” is an explanatory variable corresponding to the attribute of the user U. “Y” is an objective variable corresponding to a score indicating the characteristics of the user U. “Ω” is a coefficient of “x” and indicates a predetermined weight value. Specifically, “ω1” is a weight value of “x1”, “ω2” is a weight value of “x2”, and “ωn” is a weight value of “xn”. As described above, the above formula is created by combining the explanatory variable “x” corresponding to the attribute of the user U and the variable (for example, “ω1 · x1 _” ) including the predetermined weight value “ω”. .

  The “model data” may be feature information generated using an SVM (Support Vector Machine) or another machine learning method. Further, the feature information may be generated using a technique of deep learning (deep learning). For example, the service Y can generate feature information by appropriately using various deep learning techniques such as a DNN (Deep Neural Network), an RNN (Recurrent Neural Network), and a CNN (Convolutional Neural Network).

  Next, the inclusion information 44 is information indicating the inclusion relationship of each category. FIG. 7 is a diagram illustrating an example of the inclusion information 44. As shown in FIG. 7, the inclusion information 44 is information in which a root hierarchy, a first hierarchy, a second hierarchy, a third hierarchy,... Are associated with each other.

  The root hierarchy indicates the highest category, and indicates that it is included in each category as it goes to the first hierarchy, the second hierarchy, and the third hierarchy. The example shown in FIG. 7 shows a case where the first hierarchy for the root hierarchy “outdoor” includes “fishing”, “drive”, “travel”, and the like.

  The second layer of the first layer "fishing" is further subdivided into categories such as "river fishing" and "sea fishing". For example, the information processing apparatus 1 can extract information on a category from a web encyclopedia or a shopping site and acquire the information as inclusion information 44.

  Returning to the description of FIG. 3, the control unit 3 will be described. The control unit 3 is a controller, and various programs stored in a storage device inside the information processing apparatus 1 use a RAM as a work area by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). It is realized by being executed as. The control unit 3 is, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  The acquisition unit 31, the association unit 32, the generation unit 33, the reception unit 34, the extraction unit 35, the estimation unit 36, and the provision unit 37 each partially or entirely include an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). ) May be configured with hardware.

  The control unit 3 registers the characteristic information acquired from the service providing server 10 in the shared information, and corrects or updates the registered characteristic information. Further, the control unit 3 provides various services to the service Y based on the characteristic information.

  The acquiring unit 31 provides a model for estimating a feature of the user U using an attribute of the user U and a feature information including at least one of an estimation result regarding the feature of the user U estimated using the attribute of the user U to a different service. Y from each. For example, the acquisition unit 31 acquires feature information generated in a format designated in advance for the service Y. Thereby, the format of the feature information can be made uniform between the services Y, and thus, the unified reference feature information can be obtained.

  In addition, the acquisition unit 31 acquires information including the above-described model and an initial score value output from the model as feature information. The initial value of the score may be calculated in advance by the service providing server 10, for example, or the obtaining unit 31 may obtain and calculate the model data. When the acquisition unit 31 calculates the initial value, only the model data of the feature information is obtained first, and then the attribute of the user U is obtained from the service providing server 10 to calculate the score.

  Note that the acquiring unit 31 may have a check function for checking whether or not the characteristic information is generated according to a specified format when the characteristic information is acquired.

  Further, the acquisition unit 31 may acquire the attribute of the user U as the model input in the feature information from a service Y different from the service Y from which the model is acquired. That is, the attribute of the user U may be obtained from the service Y of the acquisition source of the model registered as the shared information 41 and the score may be output, or the user U acquired from the service Y different from the service Y of the acquisition source The score may be output using the attribute of. Thereby, for example, the model registered in the shared information 41 can be shared between the services Y of different operators.

  In addition, the acquisition unit 31 registers the acquired feature information as the shared information 41 and performs an update process for updating the registered feature information. Specifically, at the first time, the acquiring unit 31 first acquires the model data of the feature information and the initial value of the score and registers them as the shared information 41, and acquires the attribute of the user U from the service Y for the second and subsequent times. Then, only the score of the shared information 41 is updated.

  The acquisition unit 31 can also update the shared information 41 by updating the model according to the change in the attribute of the user U or updating the score provided from each service Y.

  The associating unit 32 associates feature information with each category included in the inclusion information 44. For example, the association unit 32 compares the model name shown in FIG. 6 with each category of the inclusion information 44 shown in FIG. That is, the category of “fishing” is associated with the model name of “fishing lover”. Then, the association unit 32 notifies the generation unit 33 of the result of association of each category. When the feature information is only the estimation result, the association unit 32 can associate the estimation result with each category of the inclusion information 44.

  The generation unit 33 generates a new model by combining the feature information acquired by the acquisition unit 31 based on the inclusion information 44. Specifically, the generation unit 33 can newly generate a model of a higher concept and a lower concept based on one category by combining the models based on the inclusion information.

  8A to 8D are diagrams illustrating specific examples of the processing performed by the generation unit 33. First, a case where the generation unit 33 generates a model corresponding to a category of a higher concept will be described with reference to FIGS. 8A and 8B. 8A to 8C, the inclusion information 44 is shown in a tree structure.

  When generating the model “outdoor lover” illustrated in FIG. 8A, the generation unit 33 generates the model “outdoor lover” based on, for example, a combination of the models included in the “outdoor lover”.

  For example, the generation unit 33 can generate the logical product P1 of “fishing enthusiast”, “drive enthusiast”, and “travel enthusiast” included in “outdoor enthusiast” as a model “outdoor enthusiast”.

  That is, as shown in FIG. 8A, the user U corresponding to outdoor lovers is a person who likes “fishing”, “drives”, and “travels”. For example, the score of each user U in the newly generated model “outdoor enthusiast” is a value obtained by dividing the sum of the scores of each model included in “outdoor enthusiast” by the number of each model.

  Here, the case where a model corresponding to the superordinate concept of the three models is generated based on the logical product of the three models has been described, but the present invention is not limited to this. That is, the newly generated model may be a logical product of an arbitrary number of models among a plurality of models, or may be a logical sum of such models.

  When logical product is used, it is possible to generate a model with higher accuracy, and when logical sum is used, it is possible to generate a model that includes all of them. In addition, it is also possible to generate a model using a logical product and a logical sum, respectively, and appropriately select a model to be used for the provided information based on a request from the service providing server 10.

  When a model is generated based on one category, sufficient accuracy of the estimation result may not be obtained in some cases. That is, as shown in FIG. 8B, “car lover” includes “company A lover” and “company B lover”, each indicating an automobile manufacturer.

  At this time, for example, if the model "I like company B" is generated without considering "I like company A", all the user groups who like "I like company B" occupy a part of "I like cars" as they are. . That is, for example, when “car lover” is defined as a group of users who are “company A lover” and “company B lover”, this is contrary to the definition of “car lover”.

  Therefore, when generating the model “like company B”, the generation unit 33 considers “like company A” that is in a parallel relationship with “like company B”. That is, as shown in FIG. 8B, for example, the model “like company B” is calculated from the scores of the models included in the likes of company B (“like DD car”, “like EE car” and “like FF car”). It is obtained by subtracting the score of the model "I like company A".

  Therefore, the model “I like company B” extracts a group of users who are interested in each model of company B, but are less interested in the model of company A. In other words, it is possible to generate a model with higher accuracy by considering the scores of categories that are competitors.

  Here, the case of generating a model using subtraction between scores has been described, but it is also possible to generate a model using addition between scores. That is, for example, when the model “car lover” is generated, it is estimated that the user group in which the sum of the score of the model “company A lover” and the model “model B lover” score is equal to or more than a predetermined value is “car lover”. It is also possible to generate a model that performs

  Further, in the above-described example, the case has been described where the generation unit 33 generates a model corresponding to the category of the higher concept, but it is also possible to generate a model corresponding to the category of the lower concept.

  For example, as shown in FIG. 8C, a user group who is purely “drive enthusiast” is a group of users who are “fishing enthusiasts” and another user group that is “travel enthusiasts” from the group of users “outdoor enthusiasts” Each is obtained by subtraction.

  Therefore, the generation unit 33 can generate the model “drive enthusiast” by dividing each score of the model “fishing enthusiast” and the model “travel enthusiast” from the score of the model “outdoor enthusiast”.

  This makes it possible to generate a model corresponding to a more subdivided category. When generating a new model, the generating unit 33 registers the new model in the model program information 43 (see FIG. 6).

  Specifically, as illustrated in FIG. 8D, for example, when registering a model with a model name “outdoor lover” with a model ID “M4”, the generation unit 33 also registers the generation history together with the service ID.

  As described above, the model “outdoor lover” is generated based on a combination of the model “fishing lover”, the model “drive lover”, and the model “travel lover”. A service ID corresponding to the model is registered. This makes it possible to sequentially trace the models that are the basis of each model.

  That is, by associating the generation histories, for example, when a certain model is updated or deleted, it is possible to easily update or delete the model generated based on the model. That is, each model can be easily managed.

  Note that the generation unit 33 can generate a new model by combining the generated model and the model of each service, or generate a new model by combining the generated models. That is, a new model can be generated by appropriately combining models corresponding to each category included in the inclusion information 44.

  Returning to FIG. 3, the receiving unit 34 will be described. The receiving unit 34 receives various requests from the service providing server 10. For example, the receiving unit 34 receives, from the service Y, a feature designation request for designating a specific feature. In the feature specification, a model ID, a model name, and the like of the feature information included in the shared information 41 are specified. The specification by the feature specification may be one piece of feature information or a plurality of pieces of feature information. Alternatively, the feature designation may be a designation including a plurality of pieces of feature information such as a field designation.

  The receiving unit 34 receives a user-specified request for specifying a specific user U from the service Y. The user U specified by the user specification may be one or more. Alternatively, the user specification may be a group specification including a plurality of users. In the case of group designation, the name of a specific group is designated by user designation.

  Further, the receiving unit 34 may include a period designation in the above request. For example, in the case of feature designation, feature information registered in a period designated by a period designation may be set as a feature designation target. Further, in the case of the user designation, the user U who used the service Y during the period designated by the period designation may be set as the user designation target.

  The extraction unit 35 extracts a user U corresponding to a specific feature specified by the feature specification based on the feature information. For example, the extraction unit 35 extracts the user U whose score of the specified feature is equal to or more than a predetermined value.

  FIG. 9 is a diagram illustrating an example of a reception screen, and is an example of a screen displayed on the service providing server 10. As shown in FIG. 9, selection conditions are displayed on the reception screen together with each category of feature specification.

  In the example shown in FIG. 9, for example, when a newly generated “outdoor lover” is selected, a check box for designating “and condition” and “or condition” is displayed. Here, the “and condition” indicates, for example, the estimation result of the model using the logical product explained in FIG. 8A, and the “or condition” indicates the estimation result of the model using the logical sum.

  That is, the user of the service providing server 10 can select the “and condition” or the “or condition” based on the accuracy of the provided information desired by the user. That is, it is possible to provide the provided information according to the request of the user.

  In addition, the receiving unit 34 can also receive a user-specified request for specifying a specific user U from the service Y, as described above. The user U specified by the user specification may be one or more. Alternatively, the user specification may be a group specification including a plurality of users. In the case of group designation, the name of a specific group is designated by user designation.

  Further, the receiving unit 34 may include a period designation in the above request. For example, in the case of feature designation, a model registered in a period designated by the period designation may be set as a feature designation target. Further, in the case of the user designation, the user U who used the service Y during the period designated by the period designation may be set as the user designation target.

  The extracting unit 35 can also extract a model whose estimation result is similar to the new model generated by the generating unit 33. Specifically, the extraction unit 35 refers to the shared information 41 and extracts a model similar to the score of the new model in the score of each user U using various statistical methods such as cluster analysis.

  That is, the extraction unit 35 can extract models that seemingly have no relation using the statistical method. For example, it is assumed that the estimation results of the newly generated model “outdoor lover” and the known model “interior lover” are similar.

  In such a case, the user U of “outdoor enthusiast” is highly likely to be also “interior enthusiast”. For this reason, for example, by distributing an electronic advertisement related to “interior” to the user U who likes “outdoors”, it is possible to efficiently purchase “interior”.

  That is, the extraction unit 35 can open up a new market by extracting a model whose estimation result is similar to the new model. In other words, the extraction unit 35 can discover potential needs of each user U.

  The estimating unit 36 estimates the feature of the specific user U specified by the user based on the estimation result of the model. For example, the estimating unit 36 estimates that among the models of the designated user U, a model whose score is equal to or more than a predetermined value is a feature of the user U.

  When there is a model whose score is less than a predetermined value among the models of the designated user U, the estimation unit 36 may estimate that the user U does not have the feature of the model.

  The providing unit 37 provides the provided information based on the shared information 41 to another service Y. For example, the providing unit 37 provides provided information based on the score to another service Y. Specifically, the providing unit 37 generates the provided information based on the information acquired from the extracting unit 35 or the estimating unit 36, and provides the provided information to the service Y.

  For example, the providing unit 37 generates provided information including a list of the users U extracted by the extracting unit 35 based on the feature designation, and provides the service Y to the service Y. The list may be sorted in any order, such as score order, alphabetical order, alphabetical order, and the like.

  At this time, as described above, when one of the models extracted based on the score similarity by the extraction unit 35 is specified by the feature specification, a list including the estimation result of the other model is provided as the provided information. . As a result, better information can be shared by the entire information processing system S.

  Further, the providing unit 37 provides provided information including information indicating the characteristics of the user U estimated by the estimating unit 36 based on the user designation to another service Y. For example, the providing unit 37 provides provided information including information in which the features of the user U estimated by the estimating unit 36 are arranged in a list.

  Further, the providing unit 37 may provide provided information including only some of the features of the user U estimated by the estimating unit 36. For example, the providing unit 37 may provide provided information in which only the feature whose score is the highest-ranked model or only the feature whose score is the highest-ranked model is selected.

  Next, a processing procedure executed by the information processing apparatus 1 according to the embodiment will be described with reference to FIGS. 10 and 11. FIG. 10 and FIG. 11 are flowcharts illustrating a processing procedure executed by the information processing apparatus 1 according to the embodiment. FIG. 10 illustrates a flow of a series of processes until a model is generated.

  As illustrated in FIG. 10, first, the acquisition unit 31 calculates a model for estimating the characteristics of the user U using the attributes of the user U, and an estimation result regarding the characteristics of the user U estimated using the attributes of the user U. The feature information including at least one is acquired from each of the different services Y (step S101).

  Subsequently, the generation unit 33 determines whether or not there is a combination that satisfies a new model generation condition based on the inclusion information 44 (Step S102). When there is no combination that satisfies the generation condition (No at Step S102), the generation unit 33 ends the process.

  On the other hand, when there is a combination that satisfies the generation condition (step S102, Yes), the generation unit 33 generates a new model based on the combination (step S103).

  Subsequently, the generation unit 33 updates the model program information 43 based on the newly generated model (Step S104), and the extraction unit 35 extracts a model whose estimation result is similar to the generated model (Step S105). , And the process ends. It is assumed that the generation unit 33 newly satisfies the generation condition using the generated new model. For this reason, the generation unit 33 may perform the process of step S102 subsequent to the process of step S105.

  Next, a series of processing until the information processing apparatus 1 provides the provided information to the service providing server 10 will be described with reference to FIG.

  As shown in FIG. 11, in the providing process, first, the receiving unit 34 determines whether a request for designating a characteristic has been received from the service Y (step S201). When the accepting unit 34 accepts the feature designation (Yes at Step S201), the extracting unit 35 extracts the user U having the specific feature designated by the feature designation (Step S202).

  Subsequently, the providing unit 37 provides the provided information including the list of the user U extracted by the extracting unit 35 to the service Y (Step S203), and ends the process.

  On the other hand, if the request for specifying the feature has not been received (No at Step S201), the receiving unit 34 determines whether or not the request for specifying the user has been received (Step S204). In addition, the order of the processes of step S201 and step S204 may be changed.

  When the accepting unit 34 accepts the request of the user designation (Step S204, Yes), the estimating unit 36 estimates the characteristics of the user U designated by the user designation (Step S205).

  Subsequently, the providing unit 37 provides the service Y with the provided information including the information indicating the characteristic of the user U estimated by the estimating unit 36 (Step S206), and ends the process.

  On the other hand, when the reception unit 34 does not receive the request specified by the user (No at Step S204), the process proceeds to Step S201.

  Next, a procedure of a providing process executed by the information processing apparatus 1 according to the embodiment will be described with reference to FIG. FIG. 12 is a flowchart illustrating a procedure of a providing process performed by the information processing apparatus 1 according to the embodiment.

  Further, the information processing apparatus 1 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 10 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the information processing device 1 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program that depends on hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from another device via the network N, sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the network N.

  The CPU 1100 controls output devices such as a display and a printer and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 obtains data from an input device via the input / output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc), 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. And so on.

  For example, when the computer 1000 functions as the information processing apparatus 1 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 3 by executing a program loaded on the RAM 1200. The HDD 1400 stores data in the storage unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800. However, as another example, these programs may be obtained from another device via the network N.

  As described above, the information processing device 1 according to the embodiment includes the acquisition unit 31 and the generation unit 33. The acquisition unit 31 acquires, from each of the different services Y, a model for estimating a feature of the user U using the attribute of the user U and feature information including at least one of estimation results on the feature estimated using the attribute. The generation unit 33 generates new feature information by combining the feature information acquired by the acquisition unit 31 based on the correspondence information indicating the correspondence between the categories corresponding to the models. Therefore, according to the information processing apparatus 1 according to the embodiment, the utility value can be increased.

  Further, the generation unit 33 according to the embodiment associates the generation history of the new model with the generation history of the model. Therefore, according to the information processing apparatus 1 according to the embodiment, the management of the model can be facilitated.

  In addition, the generation unit 33 according to the embodiment generates a new model corresponding to one category based on a logical product or a logical sum of estimation results of the models corresponding to a plurality of categories included in one category. Therefore, according to the information processing apparatus 1 according to the embodiment, it is possible to generate a model corresponding to the high-level concept.

  Further, the generation unit 33 according to the embodiment is included in the one category based on a difference between the estimation result of the model corresponding to the one category and the estimation result of the model corresponding to the category included in the one category. Generate models corresponding to other categories. Therefore, according to the information processing apparatus 1 according to the embodiment, it is possible to generate a model corresponding to a lower concept.

  Further, the generation unit 33 according to the embodiment generates a new model based on the estimation result of the plurality of models and the addition result or the subtraction result. Therefore, according to the information processing apparatus 1 according to the embodiment, it is possible to generate a model with high accuracy of the estimation result.

  Further, the information processing apparatus 1 according to the embodiment includes an extraction unit 35 that extracts a model whose estimation result is similar to the new model generated by the generation unit 33. Therefore, the information processing device 1 according to the embodiment can open up a new market.

  The information processing apparatus 1 according to the embodiment includes a receiving unit 34 that receives a provision request for feature information from a service, and a providing unit 37 that provides feature information based on the provision request received by the receiving unit 34. The providing unit 37 provides the provided information including the estimation result of the similar model extracted by the extracting unit 35. Therefore, according to the information processing apparatus 1 according to the embodiment, better information can be shared by the entire information processing system S.

  Further, of the processes described in the above embodiment, all or a part of the processes described as being performed automatically can be manually performed, or the processes described as being performed manually can be performed. All or part can be performed automatically by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown.

  Each component of each device illustrated is a functional concept, and does not necessarily need to be physically configured as illustrated. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or a part thereof may be functionally or physically distributed / arbitrarily divided into arbitrary units according to various loads and usage conditions. Can be integrated and configured.

  Further, the processes described in the above-described embodiments can be appropriately combined within a range that does not contradict the processing contents.

  Further, the above-mentioned “section (section, module, unit)” can be read as “means”, “circuit”, or the like. For example, the acquisition unit 31 can be read as a registration unit or a registration circuit.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 2 Communication part 3 Control part 4 Storage part 10 Service providing server 31 Acquisition part 32 Correlation part 33 Generation part 34 Reception part 35 Extraction part 36 Estimation part 37 Provision part 41 Shared information 42 Service information 43 Model program information 44 Inclusion information 100 User terminal S Information processing system

Claims (9)

A model for estimating the feature of the user using the attribute of the user, and an acquisition unit for acquiring feature information including at least one of estimation results regarding the feature estimated using the attribute from each of the different services,
A generation unit configured to generate new feature information by combining the feature information acquired by the acquisition unit based on correspondence information indicating a correspondence relationship between the categories corresponding to the feature information. apparatus. The generation unit includes:
The information processing apparatus according to claim 1, wherein a generation history of the characteristic information is associated with the generated new characteristic information. The generation unit includes:
Generating the new feature information corresponding to the one category based on a logical sum or a logical product of the estimation results of the feature information respectively corresponding to the plurality of categories included in the one category. The information processing apparatus according to claim 1, wherein The generation unit includes:
The new feature included in the one category based on a difference between the estimation result of the feature information corresponding to one category and the estimation result of the feature information corresponding to the category included in the category The information processing device according to claim 1, wherein the information is generated. The generation unit includes:
The information processing apparatus according to any one of claims 1 to 4, wherein the new feature information is generated based on an addition result or a subtraction result of each of the plurality of estimation results of the feature information. The information processing apparatus according to claim 1, further comprising: an extraction unit configured to extract the feature information whose estimation result is similar to the new feature information generated by the generation unit. A receiving unit that receives a provision request for the feature information from the service,
A providing unit that provides providing information based on the providing request received by the receiving unit,
The providing unit,
The information processing apparatus according to claim 6, wherein the provided information includes an estimation result of the similar feature information extracted by the extraction unit. An information processing method executed by a computer,
A model for estimating the characteristics of the user using the attributes of the user, and an acquiring step of acquiring characteristic information including at least one of the estimation results related to the characteristics estimated using the attributes from each of the different services,
Generating a new feature information by combining the feature information obtained in the obtaining step based on correspondence information indicating a correspondence relationship of each category corresponding to the feature information. Processing method. A model for estimating the feature of the user using the attribute of the user, and an acquisition procedure for acquiring feature information including at least one of estimation results regarding the feature estimated using the attribute from each of the different services,
And generating a new feature information by combining the feature information acquired by the acquisition procedure based on the correspondence information indicating the correspondence relationship between the categories corresponding to the feature information. Information processing program.

Images