JP2023028840A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

An object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can analyze content that is targeted and distributed using a plurality of models. [Solution] An information processing device according to the present application includes an acquisition unit that acquires user information indicating information about the user and behavior information indicating the user's behavior, and a dummy user having specific characteristics. a preparation unit that prepares user information and the behavioral information; and a plurality of models that learn user characteristics based on the user information and the behavioral information and output indicators regarding specific characteristics. a calculation unit that calculates the index for each model using a distribution unit that distributes content to users having specific characteristics based on the index output for each model by the plurality of models; and an analysis unit that analyzes content distributed to the dummy user. [Selection diagram] Figure 3

Description

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

2. Description of the Related Art Along with the dramatic spread of information services using the Internet, information distribution based on information acquired via networks is being actively performed. For example, as described in Patent Document 1, attribute information indicating attributes of users to whom information is to be distributed is registered in advance as distribution destination information, and advertisements corresponding to the attribute information of users to be distribution destinations are selected. Targeting delivery is being carried out.

However, there are users who feel uncomfortable with such targeting distribution, and such users express their intentions, such as opting out, to the information service provider that performs targeting distribution. Even if an information service provider receives a user's declaration of intention to opt out, it is difficult to identify from which model the information is distributed when there are multiple targeting distribution models. In addition, when information service providers receive targeting distribution from multiple models, it has been difficult for information service providers to consider the reasons why users expressed their intention to opt out, and to make use of this information in improving the targeting distribution model.

JP 2015-1956 A

In view of the above problems, an object of the present disclosure is to provide an information processing device, an information processing method, and an information processing program capable of analyzing content targeted and distributed in a plurality of models.

In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present disclosure includes an acquisition unit that acquires user information indicating information about a user and behavior information indicating behavior of the user, a preparation unit that prepares the user information and the behavior information of a dummy user having specific characteristics; A calculation unit that calculates the index for each model using a plurality of models that output indices for the characteristics of a distribution unit that distributes content to the dummy user; and an analysis unit that analyzes the content distributed to the dummy user.

According to one aspect of the embodiments, it is possible to provide an information processing device, an information processing method, and an information processing program capable of analyzing content targetedly distributed in a plurality of models.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to the embodiment; FIG. 3 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; 4 is a diagram illustrating an example of information stored in a user information storage unit of the information processing apparatus according to the embodiment; FIG. 5 is a diagram illustrating an example of information stored in an action information storage unit of the information processing apparatus according to the embodiment; FIG. 6 is a diagram illustrating an example of information stored in a model storage unit of the information processing apparatus according to the embodiment; FIG. 7 is a diagram illustrating an example of information stored in a content storage unit of the information processing apparatus according to the embodiment; FIG. FIG. 8 is a diagram illustrating a configuration example of a user terminal according to the embodiment; FIG. 9 is a diagram illustrating a configuration example of a provider terminal according to the embodiment; FIG. 10 is a flowchart illustrating an example of information processing according to the embodiment; FIG. 11 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment.

(embodiment)
[1-1. Example of information processing according to the embodiment]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 1 shows an example in which information processing according to an embodiment is executed by an information processing apparatus 100 .

In FIG. 1, the information processing apparatus 100 acquires user information and behavior information from a plurality of user terminals 200, prepares the user information and behavior information of dummy users, and identifies users for each model. Enter user information and behavior information of users, including dummy users, into a model that calculates indices for characteristics, calculate indices, and select users to whom content is distributed based on the calculated indices. , distributes the content to the selected user, and analyzes the content distributed to the dummy user. An example of information processing according to the embodiment will be described step by step with reference to FIG.

First, the information processing device 100 receives content input by the business operator and request information from the business operator terminal 300 (step S1). For example, the information processing apparatus 100 receives content input by the business operator M1 from the business operator terminal 300 for the purpose of distributing it to users having specific characteristics. Further, the information processing apparatus 100 receives request information regarding content distribution of the business operator M1 from the business operator terminal 300 . Here, the request information may be, for example, information indicating the "specific characteristics" of the user to whom the business wishes to distribute the content.

Next, the information processing device 100 acquires user information and action information from the plurality of user terminals 200 (step S2). For example, as shown in FIG. 1, the information processing apparatus 100 acquires user information and action information from user terminals 200A to 200F of users U1 to U6. Note that the users U1 to U6 and the user terminals 200A to 200F shown in FIG. Information and may be obtained.

Next, the information processing device 100 receives opt-out intention information from the user terminal 200 of the user (step S3). For example, as shown in FIG. 1, the information processing apparatus 100 receives opt-out intention information of the user U6 from the user terminal 200F of the user U6. Here, the opt-out intention information is information indicating the user's intention to stop distribution of targeting distribution, for example, information indicating the "field of content" for which the user wishes to stop distribution. and the like may be included.

Next, the information processing device 100 prepares user information and action information of the dummy user (step S4). For example, the information processing apparatus 100 generates user information such as the "user ID" and "date of birth" of the dummy user, and generates the "field of content" included in the opt-out intention information of the user U6. ', prepare dummy user behavior information related to the specified 'content field'. For example, the information processing apparatus 100 uses, as the “browsing history” included in the behavior information, a click history of a URL (Uniform Resource Locator) pasted in a direct mail related to the “contents field”, or a “contents field”. You may prepare the click history etc. of the banner advertisement related to .

Next, the information processing apparatus 100 uses a plurality of models to calculate an index of specific features of users including dummy users for each model, and selects users to whom content is distributed for each model. (Step S5). For example, as shown in FIG. 1, the information processing apparatus 100 inputs user information and behavior information of users including dummy users to a model 1 that calculates an index for specific features of users. Then, for each model, we calculate indices for specific features. In FIG. 1, according to model 1, the index 1 of the dummy user whose user ID is "UID#DM" is 0.8, the index 1 of the user whose user ID is "UID#1" is 0.3, and the index 1 of the user whose user ID is "UID#DM" is 0.3. This indicates that the index 1 of the user with the user ID "UID#2" is 0.8 and the index 1 of the user with the user ID "UID#3" is 0.6. Next, the information processing apparatus 100 selects content distribution targets for each model based on the calculated index. In FIG. 1, according to model 1, for example, users with user IDs "UID#DM", "UID#2", and "UID#3" whose index 1 is 0.6 or more are selected by model 1. It indicates that the distribution target 1 indicating the target is selected. The information processing apparatus 100 performs similar processing for other models.

Next, the information processing apparatus 100 distributes the contents for each model to users selected as distribution targets for each model (step S6). For example, the information processing apparatus 100, as shown in FIG. deliver content to. The information processing apparatus 100 similarly distributes content for each model to users selected as content distribution targets in other models.

Next, the information processing device 100 analyzes the content distributed to the dummy user (step S7). For example, the information processing apparatus 100 can determine the number of contents distributed to the account of the dummy user, the distribution source of the contents, the data format of the contents, the frequency of receiving similar contents, the details of the contents, and the attributes of the dummy user. and the degree of conformity between behavior and content content. The information processing apparatus 100 may graph these analysis results and summarize them in the form of a report.

As a result, the information processing apparatus 100, when the user has expressed his/her intention to opt out of the content that is targeted and distributed based on the user's specific characteristics, the information processing apparatus 100 can Distributed content can be parsed based on user specific characteristics related to the content field. Therefore, businesses that conduct targeted distribution can consider the reasons for opting out of users based on the analysis results.

[1-2. Another example 1 of information processing according to the embodiment (how to create learning data)]
The information processing apparatus 100 collects the user information and the behavior information of the dummy user whose index of the specific feature is within an arbitrary range from the acquired user information and behavior information. Prepare user information and action information.

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S3 shown in FIG. Since the processing from steps S1 to S3 is the same as the processing described above, the description thereof is omitted.

Next, the information processing apparatus 100 uses a plurality of models to calculate an index for specific features of the user. Note that the specific feature for which the information processing apparatus 100 calculates the index is the specific feature related to the "field of content" for which the user has indicated his or her intention to opt out.

Next, the information processing apparatus 100 extracts the user information and the behavior information of the users whose calculated indices for the specific features fall within an arbitrary range. For example, the information processing apparatus 100 extracts user information and action information of users whose indices for specific features are in the range of 0.5 to 0.8. The information processing apparatus 100 performs predetermined processing on the extracted user information and behavior information, for example, rewrites the “user ID” included in the user information to a dummy user ID, performs behavior Processing such as rewriting the "user ID" included in the information to the ID of a dummy user is performed. Then, the information processing apparatus 100 prepares the user information and behavior information on which these processes have been performed as the user information and behavior information of the dummy user.

Next, the information processing apparatus 100 executes the processes from steps S5 to S7 shown in FIG. That is, in this information processing, as described above, the user information and the behavior information of the dummy user to be input to the model for calculating the index for the specific feature are set so that the index for the specific feature is within an arbitrary range. User information and behavior information of value users are collected and processed in a predetermined manner. Except for the processing for preparing the user information of the dummy user and the action information, the processing from steps S5 to S7 is the same as the above-described processing, so the description is omitted.

As a result, the information processing apparatus 100 can easily prepare the user information and the behavior information of the dummy user based on the user information and the behavior information that have already been acquired without newly preparing the user information and the behavior information. It becomes possible. In addition, by not using the user information and behavior information of users with extremely high or extremely low values as the user information and behavior information of dummy users, It is possible to prevent the generation of dummy users whose characteristic indices are calculated to extreme values. Therefore, it is possible to perform a realistic content distribution simulation.

[1-3. Another example 2 of information processing according to the embodiment (identifying a distribution source)]
The information processing apparatus 100 analyzes the content distributed to the dummy user and identifies the distribution source that distributed the content based on the specific characteristics of the dummy user.

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S6 shown in FIG. Since the processing from steps S1 to S6 is the same as the processing described above, the description thereof is omitted.

Next, the information processing apparatus 100 analyzes the content distributed to the dummy user and identifies the distribution source that distributed the content based on the specific characteristics of the dummy user. For example, the information processing apparatus 100 may identify the model of the content distributor by checking the mail address of the content distributor.

As a result, the information processing apparatus 100 can identify the model that distributed the content based on the specific characteristics of the dummy user. For this reason, when there are multiple models for targeted distribution, information service providers may choose to distribute content based on specific characteristics related to the "field of content" for which users have opted out. can be specified.

[1-4. Another example 3 of information processing according to the embodiment (distribution of the specified distribution source is stopped)]
The information processing apparatus 100 stops content distribution from the identified distribution source.

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S7 shown in FIG. Since the processing from steps S1 to S7 is the same as the processing described above, the description thereof is omitted. In this information processing, in step S7, the content delivered to the dummy user is analyzed, and the model of the delivery source that delivered the content is specified based on the specific characteristics of the dummy user. This is a different point from the process of step S7 described above, and the rest is the same as the process of step S7 described above.

Next, the information processing apparatus 100 stops content distribution from the model of the identified distribution source to the user who has indicated an intention to opt out. For example, the information processing apparatus 100 is a model of a distribution source that distributes content to a dummy user based on the specific characteristics of the dummy user related to the "field of content" in which the model 1 has expressed an intention to opt out. If it is specified, content distribution to users who have indicated their intention to opt out from model 1 will be stopped. Note that, when a plurality of models to which content is distributed are specified based on the characteristics of the dummy user, the information processing apparatus 100 stops content delivery to users who have indicated their intention to opt out from all of the specified models. .

As a result, the information processing apparatus 100 identifies a model for distributing content related to the "field of content" for which the user has indicated his/her intention to opt out, and the identified model has indicated his/her intention to opt out. Content delivery to users can be stopped. Therefore, even if there are multiple targeting delivery models, it is possible to fail to deliver content related to the "field of content" where the opt-out intention was expressed to the user who has indicated the opt-out intention. It is possible to stop without

[1-5. Another example 4 of information processing according to the embodiment (analysis of reason for content distribution)]
The information processing apparatus 100 analyzes the dummy user's attribute or behavior that is the reason for content distribution from the distribution source to the dummy user.

This information processing will be described step by step. First, the information processing apparatus 100 executes the same processes as steps S1 to S7 shown in FIG. Since the processing from steps S1 to S7 is the same as the processing described above, the description thereof is omitted. In this information processing, in step S7, the content delivered to the dummy user is analyzed, and the model of the delivery source that delivered the content is specified based on the specific characteristics of the dummy user. This is a different point from the process of step S7 described above, and the rest is the same as the process of step S7 described above.

Next, the information processing apparatus 100 analyzes the attribute or behavior of the dummy user, which is the reason for distributing the content from the specified distribution source to the dummy user. For example, the information processing apparatus 100 selects the user information and behavior information of the dummy user for each model specified as the content distribution source, and selects the user information and behavior information that is highly sensitive to the index of the specific feature. Identify information. For example, by comparing the index when one behavioral information is excluded and the index when all behavioral information is used, the magnitude of the effect of the excluded behavioral information on the index, that is, the sensitivity Analyze the magnitude of Similarly, for attributes such as "date of birth" and "occupation" included in user information, by comparing the index when the attribute is excluded and the index when the attribute is added, Analyze the magnitude of the effect, ie the magnitude of the sensitivity. For example, the information processing apparatus 100 calculates the sensitivity to the index for each information unit included in the user information and behavior information of the dummy user, and calculates the sensitivity for all the user information and behavior information of the dummy user. , a sensitivity table for the indicators may be developed.

As a result, the information processing apparatus 100 identifies a model for performing content distribution related to the "field of content" for which the user has indicated an opt-out intention, and uses the identified model as a decisive factor in targeting distribution. It becomes possible to analyze the attributes and behavior of a person. Therefore, it is possible to provide analytical information about the model that is useful for improving the model of targeting delivery.

[2. Configuration of information processing system]
Next, the configuration of the information processing system according to the embodiment will be described using FIG. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to the embodiment; As shown in FIG. 2 , the information processing system 1 includes an information processing device 100 , a user terminal 200 and a business operator terminal 300 . The information processing system 1 shown in FIG. 2 may include a plurality of information processing apparatuses 100 , a plurality of user terminals 200 , and a plurality of business operator terminals 300 . The information processing device 100, the user terminal 200, and the operator terminal 300 are connected to communicate by wire or wirelessly via a predetermined communication network (network N).

The information processing apparatus 100 may be an information processing apparatus such as a PC (Personal Computer), a WS (Work Station), or a computer having server functions. The information processing device 100 performs processing based on information transmitted via the network N from the user terminal 200 and the operator terminal 300 .

A 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 smart phone, tablet terminal, desktop PC, notebook PC, mobile phone, PDA (Personal Digital Assistant). Note that the example shown in FIG. 1 shows a case where the user terminal 200 is a smart phone.

The operator terminal 300 is an information processing device used by the operator. The business terminal 300 may be, for example, an information processing device such as a smart phone, a tablet terminal, a desktop PC, a notebook PC, a mobile phone, or a PDA. Note that the example shown in FIG. 1 shows a case where the business terminal 300 is a notebook PC.

[3. Configuration of Information Processing Device]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described using FIG. FIG. 3 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; As shown in FIG. 3, the information processing apparatus 100 has a communication section 110, a storage section 120, and a control section . Although not shown in FIG. 3, the information processing apparatus 100 includes an input unit (for example, a keyboard, a mouse, etc.) for receiving various operations from the administrator of the information processing apparatus 100, and a display for displaying various information. You may have a part (for example, a liquid crystal display etc.).

(Regarding communication unit 110)
The communication unit 110 is implemented by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information between the user terminal 200 and the operator terminal 300 .

(Regarding storage unit 120)
The storage unit 120 is implemented by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk, SSD (Solid State Drive), or optical disc. As shown in FIG. 3, the storage unit 120 has a user information storage unit 121, an action information storage unit 122, a model storage unit 123, and a content storage unit .

(Regarding the user information storage unit 121)
The user information storage unit 121 stores information about users, that is, user information. An example of information stored in the user information storage unit 121 will now be described with reference to FIG. 4 is a diagram illustrating an example of information stored in a user information storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 4, the user information storage unit 121 associates and stores information related to items such as "user ID", "date of birth", "sex", and "occupation".

A “user ID” is an identifier that identifies a user and is represented by a character string, number, or the like. “Date of birth” is information related to the date of birth of the user associated with the “user ID”. “Gender” is information about the gender of the user associated with the “user ID”. "Occupation" is information on the occupation of the user linked to the "user ID".

That is, in FIG. 4, 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". ”.

The information stored in the user information storage unit 121 is not limited to information related to items such as "user ID", "date of birth", "sex", and "occupation". of users may be stored.

(Regarding the action information storage unit 122)
The behavior information storage unit 122 stores information indicating user behavior, that is, behavior information. Behavior information is information that indicates the user's behavior using a predetermined information service, which is caused by the user's use of the predetermined information service. Here, an example of information stored by the behavior information storage unit 122 will be described with reference to FIG. 5 is a diagram illustrating an example of information stored in an action information storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 5, the behavior information storage unit 122 stores information related to items such as "user ID", "search history", "browsing history", "purchase history", "route search history", and "bulletin board posting history". Link and store information.

A “user ID” is an identifier that identifies a user and is represented by a character string, number, or the like. “Search history” is information including search queries used for searches by users associated with “user IDs” and input times. The “browsing history” is information including the browsing site and browsing time of the user associated with the “user ID”. “Purchase history” is information including the purchased product or purchased service and the purchase time on the Internet mail-order site or the predetermined service contract site of the user associated with the “user ID”. "Route search history" is information including route search results and search times of users associated with "user IDs". “Bulletin board posting history” is information including bulletin board postings and posting times of users associated with “user IDs”.

That is, in FIG. 5, the search history of the user identified by the user ID "UID#1" is "search history #U1", the browsing history of the user is "browsing history #U1", and the purchase history is "browsing history #U1". It indicates that the history is "purchase history #U1", the route search history is "route search history #U1", and the bulletin board posting history is "bulletin board posting history #U1".

The information stored in the action information storage unit 122 relates to the items "user ID", "search history", "browsing history", "purchase history", "route search history", and "posting history on bulletin board". It is not limited to information, and any other information related to user behavior may be stored.

(Regarding the model storage unit 123)
The model storage unit 123 stores a plurality of models for learning user characteristics based on user information and behavior information and calculating indices for specific characteristics when user information and behavior information are input. . 6 is a diagram illustrating an example of information stored in a model storage unit of the information processing apparatus according to the embodiment; FIG.

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

A “model ID” is an identifier that identifies a machine learning model and is represented by a character string, number, or the like. "Model data" indicates model data of a machine learning model. For example, "model data" stores data for a model that calculates an index for a specific feature when user information and behavior information are input. Note that the machine learning model may be a neural network or the like.

That is, in FIG. 6, the model identified by the model ID "M#1" indicates the machine learning model M#1, and the model data "MDT#1" indicates the model data of the machine learning model M#1. ing.

Here, when the machine learning model M#1 is a neural network, the model data "MDT#1" includes, for example, how the nodes included in each of the multiple layers constituting the neural network are connected to each other. It contains various types of information for machine learning models, such as connection information such as whether or not, and connection coefficients that are multiplied by numerical values that are input and output between connected nodes.

Note that the model storage unit 123 may store information related to any other machine learning model without being limited to the information related to the items “model ID” and “model data”.

(Regarding the content storage unit 124)
The content storage unit 124 stores the content input by the provider received from the provider terminal 300 . 7 is a diagram illustrating an example of information stored in a content storage unit of the information processing apparatus according to the embodiment; FIG.

In the example shown in FIG. 7, the content storage unit 124 associates and stores information related to the items "enterprise ID", "content ID", "content data", and "specific feature".

"Business ID" is an identifier that identifies a business and is represented by a character string, number, or the like. The “content ID” is an identifier for identifying content received from the business operator, and is represented by a character string, number, or the like. "Content data" is data of contents that the business wishes to distribute. “Specific characteristics” is information indicating characteristics of users that are used as criteria for selecting users to whom the business operator wishes to distribute content.

That is, in FIG. 7, the content data indicated by the content data "CD#1" as the content identified by the content ID "CT#1" from the business indicated by the business ID "M1" has the specific feature " FT#1” indicates that the user's characteristics are designated and input to the operator terminal 300, accepted by the reception unit 132 of the information processing apparatus 100, and stored in the content storage unit 124.

Note that the content storage unit 124 is not limited to information related to items such as "enterprise ID", "content ID", "content data", and "specific features", and can store any other information related to content. may be stored.

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

As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a reception unit 132, a calculation unit 133, a preparation unit 134, a distribution unit 135, an analysis unit 136, a stop unit 137, and an analysis unit 138. and have

(Regarding the acquisition unit 131)
The acquisition unit 131 acquires user information indicating information about the user and behavior information indicating behavior of the user. Here, the user information is information about the user, for example, information provided to an information service provider when the user uses a predetermined information service. Further, the action information is information indicating the user's action using the predetermined information service caused by the use of the user's predetermined information service.

After obtaining the user information, the obtaining unit 131 stores the obtained user information in the user information storage unit 121 . After obtaining the behavior information, the obtaining unit 131 stores the obtained behavior information in the behavior information storage unit 122 . Note that the acquisition unit 131 may acquire one or both of the user information and the behavior information at predetermined dates and times, or acquire the user information each time the user accesses the information processing apparatus 100 . , and behavior information, or both.

In addition, the acquisition source from which the acquisition unit 131 acquires the user information and behavior information is not limited to the user terminal 200, and other search services, shopping services, payment services, route search services, map provision, etc. 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. may be obtained from an external storage medium.

(Regarding the reception unit 132)
The accepting unit 132 accepts content input by the operator from the operator terminal 300 . Upon receiving content from the operator terminal 300 , the receiving unit 132 stores the received content in the content storage unit 124 .

The reception unit 132 also receives request information input by the business operator from the business operator terminal 300 . Here, the request information is information relating to the provider's content delivery request, and may be information including, for example, "specific characteristics" of the user to whom the content is to be delivered.

In addition, the receiving unit 132 receives opt-out intention information input by the user from the user terminal 200 . Here, the opt-out intention information is information that indicates the user's intention to stop targeting distribution. It may be information including

(Regarding the calculator 133)
The calculation unit 133 learns the characteristics of the user based on the user information and the behavior information, and uses a plurality of models for outputting an index for the specific characteristics to output an index for the specific characteristics for each of the plurality of models. Calculate Note that the model used by the calculation unit 133 to calculate the index is read from the model storage unit 123 and used. Calculate the index of Moreover, the number of models used by the calculation unit 133 to calculate the index for the specific feature of the user may be any number.

(Regarding the preparation unit 134)
The preparation unit 134 prepares user information and action information of a dummy user having specific characteristics. For example, the preparation unit 134 prepares the user information of the dummy user by generating user information such as "user ID" and "date of birth" of the dummy user. , prepare dummy user behavior information related to the "content field" included in the user's opt-out information. For example, the preparation unit 134 may include click histories of URLs (Uniform Resource Locators) pasted in direct mails related to the "field of content" as "browsing history" included in the behavior information, and You may prepare the click history etc. of the banner advertisement which carries out as dummy user's action information.

The preparation unit 134 collects the user information and the behavior information of the users whose index of the specific feature is within an arbitrary range from the user information and the behavior information obtained by the obtaining unit 131 . User information and action information of the user are prepared. For example, the preparation unit 134 calculates an index using a plurality of models for a specific feature related to the "field of content" for which the user has indicated his or her intention to opt out, based on the result of the calculation by the calculation unit 133. , and extracts user information and behavior information of users whose indices are in an arbitrary range, for example, in the range of 0.5 to 0.8. The preparation unit 134 performs predetermined processing on the extracted user information and behavior information, for example, rewrites the “user ID” included in the user information to a dummy user ID, or performs processing on the behavior information. Processing such as rewriting the included "user ID" to the ID of a dummy user is performed. Then, the preparation unit 134 prepares the user information and behavior information on which these processes have been performed as the user information and behavior information of the dummy user.

(About distribution unit 135)
The distribution unit 135 distributes content to users having specific characteristics based on the indices output by each of the models. For example, assume that the calculation unit 133 uses a plurality of models to calculate index 1, index 2, and index 3 for all users including the dummy user. In this case, the distribution unit 135 selects users whose index 1 is equal to or greater than a predetermined value from among all users including dummy users as distribution targets 1, and Users whose index 2 is greater than or equal to a predetermined value are selected as distribution targets 2, and users whose index 3 is greater than or equal to a predetermined value are selected as distribution targets 3 from among all users including dummy users. In other words, the distribution unit 135 may select the same user as a distribution target redundantly in a plurality of models. The distribution unit 135 distributes the content to the users selected as distribution targets by such processing.

(Regarding the analysis unit 136)
The analysis unit 136 analyzes the content distributed to the dummy user. For example, the analysis unit 136 determines the number of contents distributed to the account of the dummy user, the distribution frequency of contents of the same type, the data format of the contents, the contents of the contents, the attributes and actions of the dummy user and the contents of the contents. Analyze the fitness of Also, the analysis unit 136 may graph these analysis results and summarize them in the form of a report.

The analysis unit 136 analyzes the content distributed to the dummy user and identifies the distribution source that distributed the content based on the specific characteristics of the dummy user. For example, the analysis unit 136 may identify the model of the distributor by checking the mail address of the distributor of the content.

(Regarding stop portion 137)
The stop unit 137 stops content distribution from the distribution source identified by the analysis unit 136 . That is, the stopping unit 137 stops content distribution to the user who has indicated an intention to opt out from the distribution source model that distributed the content based on the specific characteristics of the dummy user identified by the analysis unit 136 . Note that if there are multiple models that distribute content based on the specific characteristics of the dummy user identified by the analysis unit 136, the stop unit 137 has indicated that all of the identified models have opted out. Stop delivering content to users.

(Regarding the analysis unit 138)
The analysis unit 138 analyzes the dummy user's attribute or behavior that is the reason for content distribution from the distribution source to the dummy user. The analysis unit 138 selects, from among the user information and behavior information of the dummy user for each model identified as the content distribution source, user information and behavior information that are highly sensitive to indicators of specific characteristics. Identify. For example, by comparing the index when one behavioral information is excluded and the index when all behavioral information is used, the magnitude of the effect of the excluded behavioral information on the index, that is, the sensitivity Analyze the degree of magnitude of Similarly, for attributes such as "date of birth" and "occupation" included in user information, by comparing the index when the attribute is excluded and the index when the attribute is added, Analyze the magnitude of the effect, ie the magnitude of the sensitivity. For example, the analysis unit 138 calculates the sensitivity to the index for each information unit included in the user information and behavior information of the dummy user, and creates a sensitivity table for the index for all user information and behavior information. may be created.

[4. Configuration of user terminal]
Next, the configuration of the user terminal 200 according to the embodiment will be described using FIG. FIG. 8 is a diagram illustrating a configuration example of a user terminal according to the embodiment; As shown in FIG. 8 , the user terminal 200 has a communication section 210 , an input section 220 , an output section 230 and a control section 240 .

The communication unit 210 is implemented by, for example, a NIC. The communication unit 210 is connected to the network N by wire or wirelessly, and transmits and receives various information to and from the information processing apparatus 100 via the network N.

The input unit 220 receives various kinds of operation information from the user. For example, the input unit 220 may receive various operations from the user via the display surface (for example, the output unit 230) of a touch panel. The input unit 220 may also receive various operations from buttons provided on the user terminal 200 or from a keyboard or mouse connected to the user terminal 200 .

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

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

As shown in FIG. 8 , the control unit 240 has a receiving unit 241 and a providing unit 242 .

The receiving unit 241 receives opt-out intention information from the user. Here, opt-out intention information is information that indicates the user's intention to stop distribution of targeted distribution, and includes information such as information indicating the "field of content" for which distribution is desired to be stopped. you can For example, when the user wishes to stop distribution of content about romance movies, the user designates romance movies as the 'field of content' and accepts opt-out information through the input unit 220 of the user terminal 200. input to part 241 .

The providing unit 242 provides the content distributed from the information processing device 100 to the user. For example, when the content distributed from the information processing apparatus 100 is a moving image, the providing unit 242 causes the output unit 230 to output the moving image and provides the distributed content to the user. Further, for example, when the content distributed from the information processing apparatus 100 is audio, the providing unit 242 may provide the distributed content to the user by causing the output unit 230 to output the audio of the content. Further, for example, when the content distributed from the information processing apparatus 100 is text data, the providing unit 242 may display the text on the output unit 230 to provide the distributed content to the user.

[5. Configuration of operator terminal]
Next, the configuration of the operator terminal 300 according to the embodiment will be described using FIG. FIG. 9 is a diagram illustrating a configuration example of a provider terminal according to the embodiment; As shown in FIG. 9 , the operator terminal 300 has a communication section 310 , an input section 320 , an output section 330 and a control section 340 .

The communication unit 310 is implemented by, for example, a NIC. The communication unit 310 is connected to the network N by wire or wirelessly, and transmits and receives various information to and from the information processing apparatus 100 via the network N.

The input unit 320 receives various kinds of operation information from the operator. For example, the input unit 320 may receive various operations of the operator from a keyboard or mouse connected to the operator terminal 300 . Further, the input unit 320 may receive various operations from the operator via the display surface (for example, the output unit 330) of the touch panel.

The output unit 330 is a display screen realized by, for example, a liquid crystal display or an organic EL display, and is a display device for displaying various information. When the input unit 320 of the business operator terminal 300 receives various operations from the business operator via the touch panel, the display screen serving as the output unit 330 receives input from the user and outputs to the user. Also, the output unit 230 is a speaker, and may output sound through the speaker.

The control unit 340 is implemented, for example, by executing various programs stored in the business operator terminal 300 using the RAM as a work area, using a CPU, MPU, or the like. Also, the control unit 340 may be implemented by an integrated circuit such as an ASIC or FPGA, for example.

As shown in FIG. 9, the control section 340 has a receiving section 341 .

The reception unit 341 receives content from businesses. The content may be, for example, data including characters, voice, still images, moving images, etc. advertising products and services of the business. For example, the reception unit 341 receives content from a business operator in association with a user's specific characteristics. That is, the receiving unit 341 receives from the business operator a business ID that identifies the business, data indicating the content, and the “specific characteristics” of the user to whom the business wishes to distribute the content.

In addition, the reception unit 341 receives request information regarding content distribution from the business operator. Here, the request information may be, for example, information indicating the "specific characteristics" of the user to whom the provider wishes to distribute the content, the "distribution frequency" of the content, and the like.

[6. Information processing flow]
Next, the procedure of information processing by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. 10 . FIG. 10 is a flowchart illustrating an example of information processing according to the embodiment; For example, the information processing apparatus 100 acquires user information indicating information about a user and behavior information indicating behavior of the user (step S101). Then, the information processing apparatus 100 prepares user information and action information of a dummy user having specific characteristics (step S102). Then, the information processing apparatus 100 calculates an index for each of a plurality of models using a plurality of models that output indices for specific features (step S103). Then, the information processing apparatus 100 distributes content to users having specific characteristics based on the indices output by each of the plurality of models (step S104). The information processing apparatus 100 then analyzes the content distributed to the dummy user (step S105).

[7. Hardware configuration]
Also, the information processing apparatus 100 according to the above-described embodiment is implemented by a computer 1000 configured as shown in FIG. 11, for example. FIG. 11 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus. A computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic 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 by a bus 1090. have

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the 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 in which data used for various calculations by the arithmetic device 1030 and various databases are stored. It is realized by

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various types of information such as a monitor and a printer. It is realized by a connector conforming to a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Also, 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, for example, USB.

Note that the input device 1020 includes, for example, optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase change rewritable discs), magneto-optical recording media such as MOs (Magneto-Optical discs), and tapes. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Also, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends the data to arithmetic device 1030, and also transmits data generated by arithmetic device 1030 via network N to other devices.

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

For example, when the computer 1000 functions as the information processing device 100, the arithmetic device 1030 of the computer 1000 implements the functions of the control unit 130 of the information processing device 100 by executing a program loaded on the primary storage device 1040. do.

[8. Configuration and effect]
The information processing apparatus 100 according to the present disclosure includes an acquisition unit 131 that acquires user information indicating information about a user and behavior information indicating user behavior, and a dummy user user having specific characteristics. A preparation unit 134 that prepares information and behavior information, and a plurality of models that learn user characteristics based on user information and behavior information and output indices for specific characteristics. a calculating unit 133 that calculates an index for each model; a distributing unit 135 that distributes content to users having specific characteristics based on the indices output by a plurality of models for each model; and an analysis unit 136 that analyzes the distributed content.

According to this configuration, the information processing apparatus 100, when the user expresses his/her intention to opt out of the content that is targeted and distributed based on the user's specific characteristics, does not express his/her intention to opt out. Distributed content can be analyzed based on specific user characteristics. Therefore, businesses that conduct targeted distribution can consider the reasons for opting out of users based on the analysis results.

In addition, the preparation unit 134 of the information processing apparatus 100 according to the present disclosure selects a user whose index for a specific characteristic from among the user information and the behavior information acquired by the acquisition unit 131 has a value within an arbitrary range. User information and behavior information of a dummy user are prepared by collecting information and behavior information.

According to this configuration, the information processing apparatus 100 can easily prepare based on already acquired user information and behavior information without newly preparing the user information and behavior information of the dummy user. It becomes possible to In addition, by not using the user information and behavior information of users with extremely high or extremely low values for the index for specific characteristics, the index for specific characteristics is calculated to be an extreme value. It is possible to prevent the generation of dummy users that Therefore, it is possible to perform a realistic content distribution simulation.

Also, the analysis unit 136 of the information processing apparatus 100 according to the present disclosure analyzes the content distributed to the dummy user, and identifies the distribution source that distributed the content based on the specific characteristics of the dummy user. .

According to this configuration, the information processing apparatus 100 can identify the model that distributed the content based on the specific characteristics of the dummy user. For this reason, when there are multiple models for targeted distribution, information service providers may choose to distribute content based on specific characteristics related to the "field of content" for which users have opted out. can be specified.

Further, the information processing apparatus 100 according to the present disclosure further includes a stop unit 137 that stops content distribution from the distribution source identified by the analysis unit 136 .

According to this configuration, the information processing apparatus 100 identifies a model for distributing content related to the “field of content” for which the user has indicated his/her opt-out intention, and selects the specified model to indicate his/her opt-out intention. You can stop the distribution of content to users who have Therefore, even if there are multiple targeting delivery models, the information service provider will not use content related to the "area of content" where the opt-out intention has been manifested. It is possible to stop delivery to all users without omission.

The information processing apparatus 100 according to the present disclosure further includes an analysis unit 138 that analyzes attributes or behaviors of dummy users that are reasons for content distribution from the distribution source to the dummy users.

According to this configuration, the information processing apparatus 100 identifies a model for performing content distribution related to the "field of content" for which the user has indicated his/her intention to opt out, and selects a decisive factor for targeting distribution for each identified model. It is possible to analyze the attributes and behavior of users who become Therefore, it is possible to provide analytical information useful for improving the model of targeting delivery.

An information processing method according to the present disclosure includes a step of acquiring user information indicating information about a user and behavior information indicating user behavior, user information of a dummy user having specific characteristics, a step of preparing behavioral information; learning user characteristics based on the user information and the behavioral information; a step of delivering content to a user having specific characteristics based on indicators output by a plurality of models for each model; and a step of analyzing the content delivered to a dummy user. and a step.

According to the information processing method with this configuration, when the user expresses his/her intention to opt out of the content that is targeted and distributed based on the user's specific characteristics, the user expresses his/her intention to opt out. Distributed content can be analyzed based on the user's specific characteristics. Therefore, businesses that conduct targeted distribution can consider the reasons for opting out of users based on the analysis results.

An information processing program according to the present disclosure includes a step of acquiring user information indicating information about a user and behavior information indicating user behavior, user information of a dummy user having specific characteristics, a step of preparing behavioral information; learning user characteristics based on the user information and the behavioral information; a step of delivering content to a user having specific characteristics based on indicators output by a plurality of models for each model; and a step of analyzing the content delivered to a dummy user. cause a computer to perform steps and

According to the information processing program with this configuration, when the user expresses his/her intention to opt out of the content that is targeted and distributed based on the user's specific characteristics, the user expresses his/her intention to opt out. Distributed content can be analyzed based on the user's specific characteristics. Therefore, businesses that conduct targeted distribution can consider the reasons for opting out of users based on the analysis results.

As described above, the embodiments of the present application have been described in detail with reference to the drawings, but these are examples, and various modifications and improvements, including the aspects described in the section of the disclosure of the invention, can be made based on the knowledge of those skilled in the art. It is possible to implement the invention in other forms.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit 131 can be read as acquisition means or an acquisition circuit.

100 information processing device 110 communication unit 120 storage unit 121 user information storage unit 122 behavior information storage unit 123 model storage unit 124 content storage unit 130 control unit 131 acquisition unit 132 reception unit 133 calculation unit 134 preparation unit 135 distribution unit 136 analysis unit 137 stop unit 138 analysis unit 200 user terminal 300 provider terminal N network

Claims (7)

an acquisition unit that acquires user information indicating information about a user and behavior information indicating behavior of the user;
a preparation unit that prepares the user information and the behavior information of a dummy user having specific characteristics;
a calculation unit that learns user characteristics based on the user information and the behavior information and calculates the index for each model using a plurality of models that output an index for specific characteristics;
a distribution unit that distributes content to users having specific characteristics based on the indicators output by the plurality of models for each model;
an analysis unit that analyzes the content distributed to the dummy user;
Information processing equipment. The preparation unit acquires the user information and the behavior information of a user whose index of a specific feature has a value within an arbitrary range from the user information and the behavior information acquired by the acquisition unit. preparing the user information and the behavior information of the dummy user by collecting them;
The information processing device according to claim 1 . The analysis unit analyzes the content distributed to the dummy user and identifies the distribution source that distributed the content based on the specific characteristics of the dummy user.
The information processing apparatus according to claim 1 or 2. further comprising a stop unit that stops content distribution from the distribution source identified by the analysis unit;
The information processing apparatus according to claim 3. an analysis unit that analyzes the attribute or behavior of the dummy user that is the reason for distributing the content from the distribution source to the dummy user;
The information processing apparatus according to claim 3 or 4. obtaining user information indicating information about the user and behavior information indicating the behavior of the user;
preparing the user information and the behavior information of a dummy user having specific characteristics;
a step of learning the features of a user based on the user information and the behavior information, and calculating the indicator for each of a plurality of models using a plurality of models that output an indicator for a specific feature;
a step of distributing content to users having specific characteristics based on the indicators output by the plurality of models for each model;
analyzing content delivered to the dummy user;
Information processing method including. obtaining user information indicating information about the user and behavior information indicating the behavior of the user;
preparing the user information and the behavior information of a dummy user having specific characteristics;
a step of learning the features of a user based on the user information and the behavior information, and calculating the indicator for each of a plurality of models using a plurality of models that output an indicator for a specific feature;
a step of distributing content to users having specific characteristics based on the indicators output by the plurality of models for each model;
analyzing content delivered to the dummy user;
An information processing program that causes a computer to execute

Images