JP6827305B2 - Selection device, selection method and selection program - Google Patents

Description

The present invention relates to a selection device, a selection method and a selection program.

Conventionally, there is known a technique of estimating the interests of users who use terminal devices such as smartphones and tablet terminals, and distributing contents according to the estimated interests. As an example of such a technology, there is known a technology that estimates a user's interest based on the attribute information of a user who uses a terminal device and selects an advertisement of a type according to the estimation result as a distribution target. .. Further, for example, there is known a technique of selecting a product or service that is presumed to be of interest to a user based on a purchase history of the user or a browsing history of product information browsed by the user.

Japanese Unexamined Patent Publication No. 2014-086096 Japanese Unexamined Patent Publication No. 2013-257793

However, in the above-mentioned prior art, the accuracy of estimating the tendency of the content that the user is interested in may not always be good.

For example, in the above-mentioned prior art, the interest of the user is estimated based on the information that can be obtained from the user. However, since the information that can be obtained from the user changes according to the content of the service provided to the user, it may not always reflect the interest of the user.

The present application has been made in view of the above, and an object of the present application is to improve the accuracy of estimating the tendency of the content that the user is interested in.

The selection device according to the present application is the first information which is the information about the user's behavior acquired through the first service and the second information which is the information about the user's behavior acquired through the second service. It is characterized by having an acquisition unit for acquiring information and a selection unit for selecting a tendency of content provided to a user based on the first information and the second information.

According to one aspect of the embodiment, it is possible to improve the accuracy of estimating the tendency of the content that the user is interested in.

FIG. 1 is a diagram showing an example of a selection process executed by the selection device according to the embodiment. FIG. 2 is a diagram showing an example of a process of selecting the tendency of the music distributed by the selection device according to the embodiment. FIG. 3 is a diagram showing an example of a process of selecting a tendency of an electronic book distributed by a selection device according to an embodiment. FIG. 4 is a diagram showing an example of a process in which the selection device according to the embodiment generates buzz information. FIG. 5 is a diagram showing a configuration example of the selection device according to the embodiment. FIG. 6 is a diagram showing an example of information registered in the web-related information database according to the embodiment. FIG. 7 is a diagram showing an example of information registered in the terminal-related information database according to the embodiment. FIG. 8 is a diagram showing a configuration example of the distribution server according to the embodiment. FIG. 9 is a flowchart showing an example of a flow of information providing processing executed by the information selection system according to the embodiment. FIG. 10 is a diagram showing an example of a hardware configuration.

Hereinafter, a selection device, a selection method, and a mode for carrying out the selection program according to the present application (hereinafter, referred to as “the embodiment”) will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the selection device, selection method, and selection program according to the present application. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

(Embodiment)
[1-1. Example of selection device]
First, an example of the selection process executed by the selection device will be described with reference to FIG. FIG. 1 is a diagram showing an example of a selection process executed by the selection device according to the embodiment. In the example shown in FIG. 1, an example of the information providing process executed by the information providing system 1 having the selection device 10 is described. In the following description, an example of the selection process executed by the selection device 10 as a part of the information provision process provided by the information provision system 1 will be described, but the embodiment is not limited to this. For example, the selection process may be executed independently of the information providing process.

The information providing system 1 includes a web service server 100, a terminal service server 200, a distribution server 300, and user terminals 401 and 402 that can communicate with each other via a predetermined network N such as the Internet. The information providing system 1 may have an arbitrary number of web service servers 100, terminal service servers 200, distribution servers 300, and user terminals 401 and 402. Further, the information providing system 1 may have not only the user U01 but also an arbitrary number of user terminals 400 used by an unspecified number of users.

First, user terminals 401 and 402 (hereinafter, collectively referred to as "user terminal 400") will be described. The user terminal 400 is a terminal device used by an arbitrary user U01, and is realized by a smart device such as a smartphone or tablet, a PC (Personal Computer), or the like. Further, the user terminal 400 is a web service server 100, a terminal service server 200, a distribution server 300, etc. via an arbitrary network such as 3G (3rd Generation), LTE (Long Term Evolution), LAN (Local Area Network), etc. , A terminal device capable of communicating with any server device.

In addition to the terminal devices described above, the user terminal 400 includes, for example, wearable devices, cameras, AV (Audio Visual) devices such as televisions and recorders, IoT (Internet of Things) related devices, game devices, and the like. Any device can be adopted as long as it is a device that executes an arbitrary process by operating the U01.

The web service server 100 is a server device that provides various web services to the user U01, and is realized by, for example, a server device or a cloud system. Here, the web service server 100 may provide the user U01 with any kind of web service.

For example, the web service server 100 can be used for searches such as text search and image search, portal sites, map searches, route searches, weather forecasts, various bulletin boards, news distribution, navigation services, auctions, electronic shopping streets, and the like. It is possible to provide various services via the Internet, such as commercial transactions, sales and distribution of electronic books, sales and distribution of music (including audio, etc.), that is, arbitrary web services. The web service provided by the web service server 100 to the user U01 may be provided via a general-purpose application such as a browser, and the application for providing the service may be provided. It may be provided via.

Here, the web service server 100 collects various information of the user U01 as a log as the web service is provided. For example, the web service server 100 can be used in electronic commerce, user attribute information indicating the user's age, address, gender, hobbies, etc., history of search queries entered by the user, history of web contents viewed by the user, and electronic commerce. Providing web services such as purchase history, browsing history and payment history, viewing history and purchase history of e-books and songs, data of e-books and songs viewed or purchased, departure points, destinations in navigation, location information of users, etc. Collect any information that can be obtained via as a log. In the following description, the information acquired through the web service is collectively referred to as the first information. Here, the first information is information that can be acquired via the web service in addition to the above-mentioned information, and any information can be adopted as long as it is information about the user U01. Further, the web service server 100 may generate demographic information, psychographic information, and the like of the user U01 based on the collected log, and the generated information may be used as the first information.

The terminal service server 200 is a server device that provides various services related to the user terminal 400 (hereinafter, collectively referred to as "terminal service"), and is realized by, for example, a server device or a cloud system. Here, the terminal service server 200 can provide any service as long as it is a service related to the user terminal 400. For example, the terminal service server 200 sells the user terminal 400, updates the application executed by the user terminal 400, distributes applications such as games executed by the user terminal 400, and various entertainments played on the user terminal 400. Various services related to the user terminal 400, such as distribution of contents, may be provided as terminal services.

Here, the terminal service server 200 collects various information of the user U01 as a log as the terminal service is provided. For example, the terminal service server 200 collects the history of applications installed on the user terminal 400, the operation history of the user terminal 400 by the user, the information input by the user to the user terminal 400, and the like. To give a more specific example, when the user terminal 400 is a recorder, the terminal service server 200 has a history of programs viewed by user U01, a history of programs recorded by user U01, programs viewed and recorded. The tendency of the program, the keyword input by the user U01 when searching or reserving the recording target or the search target, etc. are collected as a log.

Further, for example, when the user terminal 400 is a television, the terminal service server 200 collects a history of programs viewed by the user U01 as a log. Further, for example, when the user terminal 400 is a game machine, the terminal service server 200 collects downloaded games, games played by user U01, operation contents at the time of games, game play history, and the like as logs. That is, the terminal service server 200 collects information regarding the operation of the user terminal 400 by the user U01 via the terminal service. In the following description, the information collected by the terminal service server 200 is collectively referred to as the second information.

The distribution server 300 is an information processing device that distributes various contents to the user U01, and is realized by, for example, a server device or a cloud system. For example, the distribution server 300 generates content to be distributed according to the tendency of the content selected by the selection device 10 by executing the selection process described later, and distributes the generated content to the user terminal 400.

To give a more specific example, when the content to be distributed is a musical piece, the distribution server 300 acquires tendency information showing various tendencies indicating the characteristics of the musical piece such as tempo, musical tone, and genre. In such a case, the distribution server 300 generates a music piece obtained by editing the characteristics of the existing music piece according to the tendency information, and distributes the generated music piece. An example of the content generated and distributed by the distribution server 300 will be described later.

The selection device 10 is an information processing device that executes a selection process for selecting the tendency of the content to be distributed, and is realized by, for example, a server device or a cloud system. For example, by executing the selection process, the selection device 10 selects the tendency of the content to be generated according to the hobby and taste of the user U01 to which the content is distributed and the purpose of distributing the content. To give a more specific example, the selection device 10 has a tendency of content that is presumed to be liked by user U01, a tendency of trendy content, and content that user U01 will like or will be popular in the future. The tendency may be estimated, and when the content is delivered for the purpose of advertising, the tendency of the content that is presumed to be of interest to the user who is the delivery destination is estimated. Then, the selection device 10 transmits the tendency information indicating the estimated tendency to the distribution server 300.

[1-2. Example of selection process]
By the way, as a method of estimating the content tendency estimated to be of interest to the user U01, a method of estimating from the history information of the user U01 such as the history of the contents purchased by the user U01 up to that point can be considered. However, the information that can be obtained via the web service is generally limited, and the accuracy of estimating the tendency of interest of the user U01 may not always be good.

For example, a method of estimating the type of music that the user U01 is presumed to be interested in can be considered based on the history of the music purchased by the user U01. However, with such a technique, it is not possible to estimate the type of music that is presumed to be of interest to the user U01 based on the content actually viewed by the user U01 even though the user U01 has purchased it.

Therefore, the information providing system 1 causes the selection device 10 to execute the following selection process. First, the selection device 10 has a first information which is information about the user's behavior acquired through the first service and a second information which is information about the user's behavior acquired through the second service. Get information and. Then, the information providing system 1 selects the tendency of the content to be provided to the user based on the first information and the second information.

For example, the selection device 10 considers not only the first information acquired via the web service but also the second information acquired via a service other than the web service (for example, a terminal service), and the user U01 Select trends in the content provided to. To give a more specific example, the selection device 10 acquires the first information through the first service such as a web service, and is provided by a business operator different from the business operator that provides the first service. The second information is acquired through the second service. Then, the distribution server 300 generates the content to be distributed according to the tendency of the content selected by the selection device 10, and provides the generated content to the user U01.

Hereinafter, an example of the selection process executed by the selection device 10 will be described with reference to FIG. For example, the information providing system 1 executes a service phase process for providing the first service and the second service to the user U01 prior to the execution of the selection process. For example, the web service server 100 provides various web services to the user U01 as a first service (step S1). Then, the web service server 100 collects information about the first service as the first information (step S2).

For example, the web service server 100 acquires information regarding the behavior of the user U01 as the first information, which is information acquired through a service provided on the web as the first information. To give a more specific example, the web service server 100 has, as the first information, the history of the content delivered to the user, the browsing history of the content, the history of the search query, and the history delivered to the user. Acquire information including at least one of advertisement history, electronic commerce history, or user location history. That is, the web service server 100 collects information indicating the behavior of the user U01 related to the service provided on the web as the first information.

On the other hand, the terminal service server 200 provides various services related to the user terminal 400 as a second service (step S3). Then, the terminal service server 200 collects information about the behavior of the user U01 as the second information, which is information acquired through the terminal service as the second information which is the information about the second service (step). S4). For example, the terminal service server 200 acquires, as the second information, the hardware used by the user U01, that is, the information regarding the behavior of the user U01 acquired through the user terminal 400. To give a more specific example, the terminal service server 200 provides second information such as a usage history of the user terminal 400, an operation history of the user terminal 400, or a keyword input by the user U01 to the user terminal 400. Information including at least one of (for example, a keyword indicating a program to be recorded) is collected as the second information.

In this way, the web service server 100 and the terminal service server 200 provide various services to the user U01, and collect information on the behavior of the user U01 regarding each service as the first information and the second information. Then, the information providing system 1 selects and selects the tendency of the content to be delivered to the user U01 (hereinafter referred to as "delivered content") using the collected first information and the second information. The processing of the generation phase that generates and distributes the content according to the tendency is executed.

For example, the selection device 10 collects information about the first service from the web service server 100, that is, the first information (step S5). Further, the selection device 10 collects information about the second service from the terminal service server 200 (step S6). Then, the selection device 10 selects the tendency of the distribution content to be generated based on the first information and the second information (step S7).

For example, the selection device 10 stores a model in which the tendency of the content designated to be of interest by the user U01 is learned in advance when the predetermined first information and the predetermined second information are acquired. Further, in another example, the selection device 10 stores a model in which the tendency of the content that is popular when the predetermined first information and the predetermined second information are acquired is learned in advance. The selection device 10 may store a model in which the tendency of the content designated to be of interest to the future user U01 and the tendency of the content to be popular in the future are learned in advance.

That is, it is considered that the setting of the tendency of the distribution content to be distributed when the predetermined first information and the predetermined second information are acquired changes according to the distribution purpose of the distribution content. .. Therefore, the selection device 10 is a tendency of the first information and a tendency of the second information, and a tendency of the distribution content to be distributed when the first information and the second information are acquired, and is intended for the distribution purpose of the distribution content. Memorize the model that learned the relationship with the corresponding tendency. Then, the selection device 10 selects the tendency of the distribution content from the first information and the second information acquired from the web service server 100 and the terminal service server 200 by using the model.

Further, the selection device 10 proposes the tendency of the distribution content by transmitting the tendency of the selected content to the distribution server 300 (step S8). In such a case, the distribution server 300 generates distribution content according to the proposed tendency (step S9), and provides the generated content to the user U01 (step S10).

For example, when the distribution content is a musical piece, the selection device 10 is not only the first information about the web service such as what kind of music was purchased, but also the user terminal 400 such as how many times the music is played. The tendency of the music that the user U01 and other users are interested in is estimated in consideration of the second information regarding the operation. That is, the selection device 10 includes not only the first information which is the information that can be acquired through the first service, but also the information that can be acquired through the second service different from the first service and the information of different types. The tendency of the distributed content is estimated in consideration of the second information which is the information. As a result, the selection device 10 can accurately select the tendency of the content presumed to be of interest to the user U01.

[1-3. About the ecosystem]
Here, the selection device 10 acquires information on the action performed by the user U01 in relation to the distribution content as the first information and the second information, and further based on the acquired first information and the second information. You may select the tendency of the distribution content provided to the user U01.

For example, the web service server 100 collects information on actions taken by the user U01 in relation to the distribution content delivered to the user U01 as the first information regarding the first service (step S11). For example, when the distribution content is a music, the selection device 10 has a history of search queries related to the distribution content, a distribution history and purchase history of the distribution content, various types of distribution content posted on the SNS (Social Networking Service), and the like. Information acquired via a web service such as comments and evaluations of distributed contents is acquired as the first information.

In addition, the terminal service server 200 collects information on the actions taken by the user U01 in relation to the distribution content delivered to the user U01 as the second information regarding the second service (step S12). For example, the selection device 10 collects the number of times the distribution content is played, the playback history, the operation history of the user terminal 400 related to the distribution content, and the like as second information.

In such a case, as shown in steps S5 to S7, the selection device 10 further selects the tendency of the content to be distributed to the user U01 based on the first information and the second information related to the distribution content. To do. As a result, the selection device 10 can realize the hobbies and tastes of the user U01 and the generation of contents having a tendency in line with the fashion.

[1-4. About monetization accompanying delivery]
In addition, the information providing system 1 may perform various monetization associated with the distribution of the distributed content. For example, the information providing system 1 distributes the reward generated by purchasing the distributed content and the reward generated by viewing the advertisement distributed together with the distributed content to the first service provider and the second service provider. You may. In addition, the information providing system 1 may distribute the distributed content as an advertisement and distribute the reward generated by the distribution to each provider. In addition, the information providing system 1 may generate an advertisement as the distributed content, or may distribute the distributed content as free content.

In addition, the information providing system 1 may distribute the distributed content as the content related to the first service or the second service. For example, the information providing system 1 may generate distribution content as content distributed in a web service such as a music distribution site or an electronic book distribution site. Further, when the user terminal 400 is a recorder or the like, the information providing system 1 may generate search query candidates to be automatically recorded as distribution contents and distribute the information.

That is, the information providing system 1 selects the tendency of the distribution content based on the first information regarding the first service and the second information regarding the second service, and generates the distribution content with the selected tendency. In addition, the information providing system 1 returns the reward associated with the distribution of the generated distribution content to the first service and the second service, and at the same time, a new first method relating to the user's behavior performed in connection with the distribution content. Acquire information and second information. Then, the information providing system 1 selects the tendency of the distributed content to be newly distributed to the user U01 based on the newly acquired first information and the second information. In this way, the information providing system 1 can form an ecosystem starting from the first information and the second information acquired through a plurality of services. As a result, the information providing system 1 can improve the estimation accuracy of the tendency of the distribution content to be provided to the user U01 by repeatedly executing the information providing process including the selection process.

[1-5. About learning trends]
Here, the selection device 10 generates a model that learns the relationship between the tendency of the first information and the tendency of the second information and the tendency of the distribution content, and selects the tendency of the distribution content using the generated model. To do. For example, the selection device 10 uses an arbitrary learning technique such as SVM (Support Vector Machine), associative memory, and deep learning to relate the tendency of the first information and the tendency of the second information to the tendency of the distributed content. You may generate a model that trains.

For example, when the first information and the second information are input, the selection device 10 outputs the tendency of the content to be distributed as the distribution content when the set of the first information and the second information is acquired. Using techniques such as backpropagation, the coupling coefficient between nodes possessed by DNN (Deep Neural Network) and CNN (Convolutional Neural Network) is sequentially corrected. As a result of such processing, the selection device 10 tends to distribute the tendency of the first information, the tendency of the second information, and the content to be distributed as the distribution content when the set of the first information and the second information is acquired. It is possible to make the model deeply learn the relationship with.

Here, as the tendency of the content to be distributed as the distribution content, any tendency can be adopted according to the distribution purpose of the distribution content. That is, the tendency of the content to be distributed as the distribution content is whether the user U01 wants to distribute the distribution content having a tendency to be interested, the distribution content having a trend to be popular, the distribution content to be talked about, etc. Any tendency can be adopted according to the distribution purpose of the distribution content. Then, the selection device 10 may deep-learn the relationship between the arbitrary tendency according to the distribution purpose of the distribution content and the tendency of the first information and the second information as a model.

Further, the selection device 10 uses a model in which the relationship between the tendency of the first information, the tendency of the second information, and the tendency of the distributed content is deeply learned, and the distributed content is obtained from the newly acquired first information and the second information. The tendency of is specified, and the specified tendency is output as the selected tendency. As a result of such processing, the selection device 10 can accurately acquire the tendency of the distribution content to be distributed to the user U01 from the tendency of the first information and the tendency of the second information.

[1-6. About content generation]
Here, the selection device 10 may generate the distribution content according to the selected tendency. When generating such distribution contents, the selection device 10 is realized by the same server device, cloud system, or the like as the distribution server 300.

For example, when the selection device 10 generates the distribution content, the selection device 10 acquires information including the same type of content as the distribution content provided to the user U01 as the first information or the second information. For example, when generating music, the selection device 10 acquires the music distributed to the user U01 and the music viewed by the user U01 as the first information and the second information. In such a case, the selection device 10 may generate the music to be the distribution content by converting the rhythm, the music tone, etc. of the acquired music according to the selected tendency.

Here, when the selection device 10 executes the selection process using DNN or CNN, the selection device 10 may also generate the distribution content using DNN or CNN. For example, the selection device 10 outputs the distribution content to be distributed to the user U01 when the first information and the second information are input and the first information and the second information are acquired. Learn DNN and CNN. Here, the information input to the DNN or CNN may or may not include the same type of content as the distributed content.

Then, the selection device 10 inputs the acquired first information and the second information to the generated DNN and CNN. In such a case, the DNN or CNN that has performed the above-mentioned learning will output the content to be distributed to the user U01 when the input first information and the second information are acquired. Therefore, the selection device 10 distributes the content output by the DNN or CNN to the user U01 as the distribution content.

[1-7. About trends]
Here, the selection device 10 may select the tendency of the distribution content based on an arbitrary method, or may select the tendency of the distribution content according to the distribution purpose of the arbitrary distribution content. For example, the selection device 10 may select the tendency of the distributed content based on the tendency of the first information and the tendency of the second information. To give a more specific example, in the selection device 10, the tendency of the content that the user U01 often purchases (that is, the tendency of the first information) and the tendency of the content that the user U01 often watches (that is, the tendency of the first information). That is, the tendency of the content presumed to be of interest to the user U01 may be specified based on the commonality with the tendency of the second information), and the specified tendency may be used as the tendency of the distributed content.

Further, the selection device 10 may specify the tendency of the content that the user U01 is presumed to be interested in in the future as the tendency of the distributed content as the tendency of the distributed content. Further, the selection device 10 extracts a plurality of identifiable trends from the first information and the second information, and among the extracted trends, the tendency that the user U01 is most likely to be interested in is determined by the distribution content. It may be a tendency.

Further, the selection device 10 may select the tendency of the distribution content to be distributed to the user U01 from the first information and the second information related to the behavior of the user U01, and may be used for the behavior of another user. From the related first information and the second information, the tendency of the distribution content to be distributed to the user U01 may be selected. For example, the selection device 10 is a distribution content to be distributed to the user U01 from the first information and the second information related to the behavior of another user whose attribute information such as age and gender is common to the user U01. You may choose a trend.

Further, the selection device 10 may select the tendency of the distributed content that is popular or is estimated to be popular in the future from the first information and the second information of an unspecified number of users. That is, the selection device 10 may select the tendency of the distribution content to be distributed for any purpose from the first information and the second information of any user, and distributes to a specific user or any user. You may select the tendency of the delivered content to be delivered.

Further, the selection device 10 may select not only the tendency of the distribution content itself but also the tendency of the distribution content provision timing, provision mode, and the like. For example, the selection device 10 may specify the tendency of the timing at which the user U01 views the content from the first information and the second information, and further select the delivery timing of the distribution content based on the specified tendency. ..

[1-8. About the purpose of delivery]
Here, the selection device 10 may select the tendency of the distribution content according to any distribution purpose. For example, the selection device 10 may select the tendency of the distributed content that the user U01 is interested in or is estimated to have in the future, or the tendency of the distributed content that is popular or is estimated to be popular in the future. .. Further, the selection device 10 may select the tendency of the distribution content according to the group of users to whom the distribution content is distributed. For example, it is estimated that the distribution device 10 is of interest to the user according to the age of the user who is the distribution destination, the group of the user who is the distribution destination, the community to which the user who is the distribution destination belongs, and the like. You may select the tendency of the delivered content. That is, the distribution device 10 may estimate the tendency of the distribution content for each user or for each cluster of users.

Further, the selection device 10 may select the tendency of the distribution content presumed to be desired by the user U01. For example, the selection device 10 selects the tendency of the music that the user U01 will like based on the information acquired by the user terminal 400 such as the IoT device and the web-related information. More specifically, the selection device 10 uses deep learning, classification techniques such as SVM, and the like to identify a tendency of what kind of music is preferred when the user performs a certain action.

Here, the selection device 10 is a music piece preferred by the user U01 based on the general tendency of what kind of music is preferred when an unspecified number of users perform an action. You may select a tendency, and if the user U01 performs a certain action, the music that the user U01 prefers is based on the personal tendency of what kind of music the user U01 prefers to select. You may choose the tendency of. Then, the distribution server 300 can automatically select the music that the user U01 would like by outputting the music having the selected tendency as the distribution content from the IoT device.

[2. An example of the relationship between the information to be acquired and the content to be generated]
Next, an example of a process of selecting a tendency of the distribution content from the first information and the second information and distributing the distribution content of the selected tendency will be described with reference to FIGS. 2 to 4. In the following description, the selection device 10 selects the tendency of the distribution content from the tendency of the first information and the tendency of the second information from the first information and the second information, and generates the distribution content having the selected tendency. An example of the processing flow will be described.

[2-1. An example of processing to generate music]
First, an example of a process of distributing music will be described with reference to FIG. FIG. 2 is a diagram showing an example of a process of selecting the tendency of the music distributed by the selection device according to the embodiment. For example, as shown in FIG. 2A, the selection device 10 acquires the web-related information C10, which is information acquired via the web service such as search history, browsing history, advertising profit, etc., as the first information. .. Further, as shown in FIG. 2A, the selection device 10 purchased music data which is data of the music purchased by the user U01, playback data which is data of the music played by the user U01, and music. The terminal-related information C20, which is information acquired through the user terminal 400 such as purchaser data indicating the user, is collected as the second information.

In such a case, as shown in FIG. 2B, the selection device 10 selects and has a tendency of the music to be the distribution content based on the web-related information C10 and the terminal-related information C20. Generate music. For example, the selection device 10 estimates the user's tendency toward the music that is the distribution content from the web-related information C10 and the terminal-related information C20. Then, the selection device 10 generates a musical piece having an estimated tendency.

For example, the selection device 10 estimates the tendency of the music that is presumed to be of interest to the user to whom the distribution content is distributed, from the tendency of the web-related information C10 and the tendency of the terminal-related information C20. Then, the selection device 10 edits the music data included in the terminal-related information C20 to generate music that is presumed to be of interest to the user as the distribution destination.

In addition to the process of editing the existing music data, the selection device 10 may generate music to be the distribution content by any music generation technology. For example, when the music data is acquired as the terminal-related information C20, the selection device 10 divides the music indicated by the music data into predetermined units, and shows the tendency of the characteristics of the music such as chord progression, modulation, melody line, and rhythm. Identify. Then, the selection device 10 generates music data of the music to be the distribution content by generating and reconstructing the music having the characteristics of the specified tendency.

For example, when the selection device 10 inputs the predetermined web-related information C10 or the predetermined terminal-related information C20, the selection device 10 obtains the predetermined web-related information C10 or the predetermined terminal-related information C20, and delivers the music to be distributed. Deep learning such as DNN and CNN is performed in advance so as to output. That is, the selection device 10 generates a model in which the relationship between the tendency of the web-related information C10, the tendency of the terminal-related information C20, and the tendency of the distributed content is deeply learned. Then, the selection device 10 may generate the music by inputting the newly collected web-related information C10 and terminal-related information C20 into the generated DNN and CNN.

Further, as shown in FIG. 2C, the selection device 10 performs a performance to distribute the generated music to the user. For example, the selection device 10 provides the music free of charge or for a fee, and obtains advertising income associated with the provision of the music and income associated with the sale. Further, the selection device 10 acquires the user's behavior regarding the music, such as the playback history of the music. Then, as shown in FIG. 2D, the selection device 10 sets the newly acquired user behavior as new web-related information C10 and terminal-related information C20, and generates a new musical piece.

[2-2. An example of the process of generating an e-book]
Next, an example of the process of distributing the electronic book will be described with reference to FIG. FIG. 3 is a diagram showing an example of a process of selecting a tendency of an electronic book distributed by a selection device according to an embodiment. For example, as shown in FIG. 3A, the selection device 10 first uses the web-related information C10 including the purchase data of the electronic book, the data of the electronic book purchased by the user, and the like as the information related to the web service. Get as information. Further, as shown in FIG. 3A, the selection device 10 collects the terminal-related information C20 as the second information.

In such a case, as shown in FIG. 3B, the selection device 10 selects the tendency of the electronic book to be the distribution content based on the web-related information C10 and the terminal-related information C20, and selects the selected tendency. Generate an e-book to have. For example, the selection device 10 estimates the tendency of the electronic book that is presumed to be of interest to the user as the distribution destination from the tendency of the web-related information C10 and the tendency of the terminal-related information C20. Then, the selection device 10 edits the book content included in the terminal-related information C20 to generate an electronic book that is presumed to be of interest to the user as the distribution destination.

The selection device 10 may generate an electronic book as distribution content by using an arbitrary sentence generation technique or image generation technique. For example, the selection device 10 may estimate the tendency of plots and stories that the user is presumed to be interested in, and generate a novel or comic of the estimated plots or stories. More specifically, the selection device 10 may create a plot that the user is interested in by generating a branched plot in advance and changing the plot to be selected according to the estimated tendency.

Further, for example, the selection device 10 may estimate the tendency of the character or design that the user is presumed to be interested in, and generate a comic of the character or story that reflects the estimated tendency. Such a generation technology is realized by, for example, a combination of deep learning such as plotting, story, character character, design using DNN, CNN, etc., and sentence generation technology, 2D image or 3D image generation technology. It is possible.

Then, as shown in FIG. 3C, the selection device 10 provides the generated electronic book free of charge or for a fee, and obtains advertising income associated with the provision of the electronic book and income associated with the sale. Further, the selection device 10 acquires the user's behavior regarding the electronic book, such as the browsing history of the electronic book. Then, as shown in FIG. 3D, the selection device 10 sets the newly acquired user behavior as new web-related information C10 and terminal-related information C20, and generates a new electronic book.

[2-3. An example of processing to generate buzz information]
Next, with reference to FIG. 4, an example of a process of generating buzz information indicating content in which the interest from the user exceeds a predetermined threshold value within a predetermined period, that is, content such as a buzzword will be described. FIG. 4 is a diagram showing an example of a process in which the selection device according to the embodiment generates buzz information. For example, as shown in FIG. 4A, the selection device 10 acquires the web-related information C10 including the search history, the browsing history, the advertisement history which is the history of the advertisement viewed by the user, and the like as the first information. .. Further, for example, as shown in FIG. 4A, the selection device 10 uses a reservation history, which is a recording reservation history set by the user for the recorder, and a keyword input by the user for the reserved recording. The terminal-related information C20 including a certain reserved keyword, a playback history indicating a played program among the recorded programs, and the like is collected as the second information.

Here, the search history, browsing history, and advertisement history included in the web-related information C10 can be indicators of popular words and topics, that is, targets of interest to the user. In addition, the reservation keyword included in the terminal-related information C20 and the information related to the program to be reserved can also be an index indicating the target that the user is interested in. Therefore, as shown in FIG. 4B, the selection device 10 estimates the user's tendency toward the epidemic based on the web-related information C10 and the terminal-related information C20, and generates buzz information indicating the estimated tendency. To do.

For example, the selection device 10 acquires, as the first information, information indicating the content in which the interest from the user exceeds a predetermined threshold value within a predetermined period. Further, the selection device 10 selects the tendency of the content whose interest from the user exceeds a predetermined threshold value within a predetermined period from the first information. Then, the selection device 10 generates content indicating the selected tendency as distribution content.

For example, the selection device 10 generates article content that introduces topics and words that are popular among users. Then, as shown in FIG. 4C, the selection device 10 provides the generated article content free of charge or for a fee, and obtains advertising income associated with the provision of the article content and income associated with the sale. In addition, the selection device 10 acquires the user's behavior regarding the distributed article content such as the browsing history of the article content, and as shown in FIG. 4D, the newly acquired user's behavior is recorded on the new web. The related information C10 and the terminal related information C20 are used to generate new article contents.

[2-4. Others]
In the above-described example, the selection device 10 estimates the user's tendency toward the predetermined type of content from the first information and the second information related to the predetermined type of content, and according to the estimation result, the predetermined type. Content was generated as distribution content. For example, the tendency of the user with respect to the music was estimated from the data related to the music of the selection device 10, and the music having the estimated tendency was generated as the distribution content. However, the embodiments are not limited to this.

For example, the selection device 10 may estimate the user's tendency toward the electronic book from various first information and the second information related to the music, and generate the electronic book according to the estimation result. Further, for example, the selection device 10 estimates the user's tendency toward the music from the first information and the second information related to the electronic book and the buzz information as well as the music, and generates the music according to the estimation result. You may. That is, the selection device 10 uses not only the first information and the second information related to the content of the same type as the distributed content but also the first information and the second information related to the content of a type different from the distributed content. You may.

Further, the selection device 10 may select the tendency of the distribution content based on the relationship between the first information and the second information. For example, the selection device 10 is of interest to users who have a predetermined play tendency based on the tendency of the game play history of the unspecified logarithm user and the tendency of the viewing history of the content of the unspecified logarithm user. Identify content trends. Then, the selection device 10 may estimate the tendency of the content that the user U01 is interested in from the tendency of the game play history of the user U01, and may use the estimated tendency as the tendency of the distribution content.

[3. Configuration of selection device]
Hereinafter, an example of the functional configuration of the selection device 10 that realizes the above selection process will be described. FIG. 5 is a diagram showing a configuration example of the selection device according to the embodiment. In the following description, an example of the functional configuration of the selection device 10 that acquires the web-related information as the first information and executes the process of acquiring the terminal-related information as the second information will be described.

As shown in FIG. 5, the selection device 10 includes a communication unit 20, a storage unit 30, and a control unit 40. The communication unit 20 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 20 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the web service server 100, the terminal service server 200, the distribution server 300, and the user terminal 400.

The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. In addition, the storage unit 30 stores the web-related information database 31, the terminal-related information database 32, and the model database 33.

The web-related information collected as the first information is registered in the web-related information database 31. For example, FIG. 6 is a diagram showing an example of information registered in the web-related information database according to the embodiment. For example, information having items such as "user ID (Identifier)", "search history", and "browsing history" is registered in the web-related information database 31.

The "user ID" is information for identifying a user. The "search history" is a history of search queries entered by the user identified by the associated "user ID". Further, the "browsing history" is a history of the web contents browsed by the user identified by the associated "user ID". In addition to the information shown in FIG. 6, any information can be registered in the web-related information database 31 as web-related information as long as it is user information that can be obtained through the web service. To do.

For example, in the example shown in FIG. 6, information such as user ID "user # 1", search history "search history # 1", and browsing history "browsing history # 1" is registered. For such information, the search query indicated by the search history "search history # 1" is input by the user ID "user # 1", and the web content indicated by the browsing history "browsing history # 1" is browsed. Indicates that. In the example shown in FIG. 6, conceptual values such as "user # 1", "search history # 1", and "browsing history # 1" are described, but in reality, the web-related information database 31 contains , The character string that identifies the user, the character string that becomes the search query, the URL (Uniform Resource Locator) of the browsed web content, and the like are registered.

Returning to FIG. 5, the description will be continued. The terminal-related information collected as the second information is registered in the terminal-related information database 32. For example, FIG. 7 is a diagram showing an example of information registered in the terminal-related information database according to the embodiment. For example, in the example shown in FIG. 7, information having items such as "terminal ID", "user ID", "terminal type", and "terminal data" is registered in the terminal-related information database 32.

Here, the "terminal ID" is information for identifying the user terminal 400. Further, the "user ID" shown in FIG. 7 is a user ID that identifies a user who uses the user terminal 400 indicated by the associated "terminal ID". Further, the "terminal type" is information indicating the type of the user terminal 400 indicated by the associated "terminal ID". Further, the "terminal data" is data acquired via the user terminal 400 indicated by the associated "terminal ID", and is, for example, an operation history by the user, a playback history of various contents, and a game replay data. , Reservation history, reservation keywords, and any other data that can be acquired via the user terminal 400 is applied.

For example, in the example shown in FIG. 7, information such as terminal ID "terminal # 1", user ID "user # 1", terminal type "mobile phone", and terminal data "terminal data # 1" are registered in association with each other. Has been done. Such information is used by the user indicated by the user ID "user # 1" in the user terminal 400 identified by the terminal ID "terminal # 1", and the terminal type is the terminal type "mobile phone". It indicates that it is. Further, such information indicates that the data acquired through the user terminal 400 identified by the terminal ID "terminal # 1" is the terminal data "terminal data # 1". In the example shown in FIG. 7, conceptual values such as "terminal # 1" and "terminal data # 1" are described, but in reality, a character string that identifies the user terminal 400 and the user terminal 400 are described. Various data acquired from the above will be registered in the terminal-related information database 32.

Returning to FIG. 5, the description will be continued. In the model database 33, a model that has learned the relationship between the tendency of the first information and the tendency of the second information and the tendency of the distributed content is registered. For example, in the model database 33, data of DNN or CNN whose relationship between the tendency of the first information and the tendency of the second information and the tendency of the distributed content is deeply learned by the learning unit 45 described later is registered. There is.

The control unit 40 is a controller, and for example, various programs stored in a storage device inside the selection device 10 by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) store a RAM or the like. It is realized by being executed as a work area. Further, the control unit 40 is a controller, and may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 4, the control unit 40 includes an acquisition unit 41, a selection unit 42, a proposal unit 43, and a learning unit 44. The acquisition unit 41 includes the first information which is the information about the user's behavior acquired through the first service and the second information which is the information about the user's behavior acquired through the second service. To get.

For example, the acquisition unit 41 acquires, as the first information, information on the behavior of the user acquired through the service provided on the web, that is, web-related information from the web service server 100. In addition, the acquisition unit 41 obtains information regarding the behavior of the user U01 from the terminal service server 200 as the second information, which is information acquired through the hardware used by the user U01 such as the user terminal 400. get.

More specifically, as the first information, the acquisition unit 41 has a history of contents delivered to the user U01, a history of browsing the contents, a history of search queries, and a history of advertisements delivered to the user. , Acquire information including at least one of the history of electronic commerce or the user's location history. In addition, the acquisition unit 41 includes at least one of the usage history of the hardware such as the user terminal 400, the operation history of the hardware, or the keyword input by the user U01 for the hardware as the second information. Get information.

The acquisition unit 41 may acquire information including the same type of content as the content distributed to the user U01 as the first information or the second information. For example, when the acquisition unit 41 distributes the voice of music or the like as the distribution content, the acquisition unit 41 may acquire the information including the voice delivered to the user U01 as the first information or the second information. Further, when the electronic book is distributed as the distribution content, the acquisition unit 41 may acquire information including the information of the electronic book distributed to the user U01 as the first information.

Further, the acquisition unit 41 may acquire, as the first information or the second information, information indicating the content in which the interest from the user U01 exceeds a predetermined threshold value within a predetermined period. For example, the acquisition unit 41 may acquire the search history or browsing history indicating the buzzword as the first information, or may acquire the information including the reservation keyword or the like input by the user U01 as the second information. Good. Then, the acquisition unit 41 registers the acquired web-related information in the web-related information database 31, and registers the terminal-related information in the terminal-related information database 32.

In addition, the acquisition unit 41 may acquire information about the action performed by the user U01 in relation to the distribution content distributed by the distribution server 300 as the first information or the second information. For example, the acquisition unit 41 acquires information on the behavior of the user acquired through the first service, and information on the behavior performed by the user U01 in relation to the distributed content as the first information. May be good. Further, for example, the acquisition unit 41 uses the information regarding the behavior of the user U01 acquired through the second service as the second information, and the information regarding the behavior performed by the user U01 in relation to the distributed content. You may get it.

The selection unit 42 selects the tendency of the content provided to the user U01 based on the first information and the second information. Specifically, the selection unit 42 selects the tendency of the distributed content provided to the user U01 based on the tendency of the first information and the tendency of the second information. For example, the selection unit 42 estimates the tendency of the content that the user U01 is interested in based on the first information and the second information, and selects the tendency of the distributed content based on the estimation result.

In addition, the selection unit 42 of the distribution content, such as the tendency of the content that the user U01 is presumed to be interested in in the future, the tendency of the content that is presumed to be popular in the future, etc. The tendency according to the distribution purpose may be estimated, and the tendency of the distribution content may be selected based on the estimation result. Further, the selection unit 42 estimates the tendency of the content whose interest from the user exceeds a predetermined threshold value within a predetermined period from the first information and the second information, and selects the estimated tendency as the tendency of the distribution content. You may.

For example, the selection unit 42 reads the web-related information from the web-related information database 31 and reads the terminal-related information from the terminal-related information database 32. Further, the selection unit 42 uses the model database 33 to learn the model learned by the learning unit 44, that is, the tendency of the first information and the tendency of the second information, and the tendency of the distribution content according to the distribution purpose of the distribution content. Read out a model that has deeply learned the relationship with. Then, the selection unit 42 selects the tendency of the distribution content provided to the user U01 from the first information and the second information by using the read model.

The proposal unit 43 proposes to the distribution server 300 the tendency of the distribution content selected by the selection unit 42. For example, the proposal unit 43 transfers the tendency of the distribution content selected from the first information and the second information by the selection unit 42 and the first information and the second information used when selecting the tendency of the distribution content to the distribution server 300. Output to.

The learning unit 44 learns the relationship between the tendency of the first information and the tendency of the second information and the tendency of the distributed content according to the distribution purpose of the distributed content as a model. For example, the learning unit 44 acquires the first information and the second information. Subsequently, the learning unit 44 provides and manages the information providing service to provide information indicating the tendency of the distributed content to be provided to the user U01 when the acquired first information and the second information are acquired. Accept from the administrator who does. That is, the learning unit 44 has a tendency according to the purpose of distributing the distributed content, and the tendency of the distributed content to be provided to the user U01 when the acquired first information and the second information are acquired. Accepts information that indicates.

Then, the learning unit 44 performs deep learning of DNN and CNN so as to output the information received from the administrator when the acquired first information and the second information are input. As a result, the learning unit 44 can deeply learn the relationship between the tendency of the first information, the tendency of the second information, and the tendency of the distributed content according to the distribution purpose of the distributed content as a model. Then, the learning unit 44 registers in the model database 33 in which the learning has been performed.

[4. Distribution server configuration]
Next, an example of the functional configuration of the distribution server 300 that generates the distribution content will be described. FIG. 8 is a diagram showing a configuration example of the distribution server according to the embodiment. As shown in FIG. 8, the distribution server 300 includes a communication unit 320, a storage unit 330, and a control unit 340. The communication unit 320 is realized by, for example, a NIC or the like. Then, the communication unit 320 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the selection device 10, the user terminal 400, and the like.

The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. In addition, the storage unit 30 stores the generation model database 331.

A generative model for generating distribution contents is registered in the generative model database 331. For example, when the first information and the second information and the information indicating the tendency of the distribution content selected by the selection device 10 are input to the generative model database 331, the distribution content having the tendency selected by the selection device 10 is stored. Generative models such as DNN and CNN that have been deep-learned to output are registered. When the selection device 10 and the distribution server 300 are realized by the same device, when the first information and the second information are input to the generation model database 331, the first information and the second information are displayed. A generative model in which deep learning is performed may be registered so as to output the distribution content having a tendency to be provided to the user U01 when the information is acquired.

Returning to FIG. 8, the description will be continued. The control unit 340 is a controller, and is realized by, for example, a processor such as a CPU or MPU executing various programs stored in a storage device inside the distribution server 300 using RAM or the like as a work area. Further, the control unit 40 is a controller, and may be realized by an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 8, the control unit 340 includes a reception unit 341, a generation unit 342, and a distribution unit 343. The reception unit 341 receives the first information and the second information and the information indicating the tendency of the distribution content from the selection device 10.

The generation unit 342 generates the distribution content according to the tendency selected by the selection device 10. For example, the generation unit 342 generates the distribution content from the content included in the first information or the second information according to the tendency selected by the selection device 10. To give a more specific example, the generation unit 342 reads the generation model from the generation model database 331, and inputs the first information and the second information and the information indicating the tendency of the distribution content into the generation model. Then, the generation unit 342 provides the distribution content to the user U01 by transmitting the distribution content generated by the generation model to the user terminal 400 or the like.

The generation unit 342 may generate the distribution content by modifying the first information and the content included in the second information according to the tendency selected by the selection device 10. For example, the generation unit 342 may generate the sound obtained by editing the sound included in the second information according to the tendency selected by the selection device 10 as the distribution content. Further, the generation unit 342 may generate an electronic book according to the tendency selected by the selection device 10 as the distribution content from the electronic book included in the first information. Further, when the distribution content is buzz information, the generation unit 342 may generate the distribution content indicating the tendency selected by the selection device 10.

The distribution unit 343 distributes the reward associated with the distribution of the distributed content to the provider who provides the first service and the provider who provides the second service. For example, when the distribution content is provided free of charge, the distribution unit 343 distributes the income associated with the distribution of the advertisement viewed in connection with the provision of the distribution content to each provider. In addition, when the distribution content is provided for a fee, the distribution unit 343 distributes the income associated with the purchase of the distribution content to each provider.

[5. An example of the flow of selection processing]
Next, an example of the flow of the information providing process including the selection process will be described with reference to FIG. FIG. 9 is a flowchart showing an example of a flow of information providing processing executed by the information selection system according to the embodiment.

For example, the selection device 10 acquires web-related information as information regarding the first service (step S101). Further, the selection device 10 acquires terminal-related information as information related to the second service (step S102). Then, the selection device 10 selects a tendency according to the distribution purpose of the distribution content based on each information (step S103). Then, the distribution server 300 generates the distribution content having the selected tendency (step S104), and provides the generated distribution content to the user U01 (step S105).

[6. Modification example]
In the above, an example of the selection process by the selection device 10 has been described. However, the embodiments are not limited to this. Hereinafter, variations of the selection process executed by the selection device 10 will be described.

[6-1. About the method used in information provision processing]
In the above description, the selection device 10 selects the tendency of the distributed content by using a technique related to deep learning such as DNN and CNN. However, the embodiments are not limited to this. For example, in addition to deep learning, the selection device 10 provides arbitrary information such as deep reinforcement learning, information search, information classification, natural language processing, abnormal value detection, voice processing, image processing, behavior recognition, biological recognition, and life science. The processing technique may be used to select the tendency of the delivered content according to the purpose of delivering the delivered content.

Further, the distribution server 300 may generate distribution contents by using AR (Augmented Reality) or VR (Virtual Reality) technology in addition to the technology related to deep learning. For example, when the user terminal 400 has a display function for displaying AR or VR, the distribution server 300 may generate distribution content displayed as AR or VR.

[6-2. Information used by the selection device]
Here, if the information providing system 1 acquires information via the first service and the second service different from the first service, any service can be used as the first service and the second service. It may be adopted as a service of. For example, the information providing system 1 may use any system such as a web service, a management system for various entertainment contents, and a financial system as the first service and the second service.

Further, even for the same type of service, it is expected that the information that can be acquired from the user through each service will be different. Therefore, the information providing system 1 may acquire information via the first service and the second service of the same type as the first service as the first information and the second information, respectively. Further, the information providing system 1 may acquire information on user behavior common to each service as the first information and second information, and acquire information on user behavior not common to each service. You may. That is, the information providing system 1 may use any system as the first service and the second service as long as different information is included.

Here, the selection device 10 may select the tendency of the distributed content by further using the information that can be acquired through the first service and the third service different from the second service. For example, the selection device 10 may further use information that can be acquired via public services to select trends in distributed content.

To give a more specific example, the selection device 10 includes web-related information, terminal-related information, information on the distribution of illegally parked bicycles, information on land readjustment, traffic volume survey results, hourly usage rates of bicycle parking lots and parking lots, and the like. Information related to public services such as is acquired as the third information. Then, the selection device 10 may select the tendency of the distribution content to be distributed to the user based on the tendency of the web-related information, the terminal-related information, and the information related to the public service.

[6-3. Device configuration〕
In the example shown in FIG. 1, the selection device 10 operates as a back-end server that executes selection processing, and the distribution server 300 operates as a front-end server that generates and distributes distribution content. However, the embodiments are not limited to this. For example, the selection device 10 and the distribution server 300 may be realized by the same server device, cloud system, or the like. Further, the selection device 10 and the distribution server 300 distribute the back-end server that executes the selection process and the generation process that generates the distribution content according to the selected tendency, and the distribution content generated by the back-end server. It may be realized by operating in cooperation with the front-end server.

[6-4. Others]
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in any unit according to various loads and usage conditions. It can be integrated and configured. In addition, the above-described embodiments can be appropriately combined as long as the processing contents do not contradict each other.

[7. program〕
Further, the selection device 10 and the distribution server 300 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 10 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to the output device 1010 and the input device 1020, and the arithmetic unit 1030, the primary storage device 1040, the secondary storage device 1050, the output IF (Interface) 1060, the input IF 1070, and the network IF 1080 are connected by the bus 1090. Has.

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

The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various information such as a monitor and a printer. For example, USB (Universal Serial Bus), DVI (Digital Visual Interface), and the like. It is realized by a connector of a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, USB.

The input device 1020 is, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), or a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Further, the input device 1020 may be an external storage medium such as a USB memory.

The network IF1080 receives data from another device via the network N and sends it to the arithmetic unit 1030, and also transmits the data generated by the arithmetic unit 1030 to the other device via the network N.

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

For example, when the computer 1000 functions as the selection device 10, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 40 by executing the program loaded on the primary storage device 1040. When the computer 1000 functions as the distribution server 300, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 340 by executing the program loaded on the primary storage device 1040.

[8. effect〕
As described above, as described above, the selection device 10 has the first information which is the information about the behavior of the user acquired through the first service and the user acquired through the second service. Acquire the second information which is the information about the behavior of. Then, the selection device 10 selects the tendency of the distribution content based on the first information and the second information. In this way, the selection device 10 selects the tendency of the delivered content based on not only the information acquired through a single service but also the information acquired through different services. As a result, the selection device 10 can improve the accuracy of estimating the tendency of the content that the user is interested in, for example.

In addition, the selection device 10 acquires information on the user's behavior acquired through the first service, and acquires information on the user's behavior in relation to the distributed content as the first information, and the first information Information on the user's behavior acquired through the service of 2 and information on the behavior performed by the user in relation to the distributed content is acquired as the second information. Therefore, since the selection device 10 selects a new tendency of the distributed content based on the information about the action taken by the user in relation to the distributed content, the accuracy of estimating the tendency of the content that the user is interested in is accurate. Can be further improved.

Further, the selection device 10 acquires information on the user's behavior acquired through the service provided on the web as the first information, that is, the web-related information C10, and the user obtains the web-related information C10 as the second information. Information on the behavior of the user acquired through the user terminal 400 to be used, that is, terminal-related information C20 is acquired. In this way, the selection device 10 selects the tendency of the distributed content based on the information acquired on the web and the information acquired on the terminal, so that the tendency of the content that the user is interested in is estimated. The accuracy of the operation can be further improved.

Further, as the first information, the selection device 10 includes a history of contents delivered to users, a history of browsing contents, a history of search queries, a history of advertisements delivered to users, and a history of electronic commerce. , Or obtain information including at least one of the user's location history. Further, as the second information, the selection device 10 includes information including at least one of the usage history of the user terminal 400, the operation history of the user terminal 400, or the keyword input by the user to the user terminal 400. To get. Therefore, the selection device 10 can select the tendency of the distributed content from various viewpoints.

Further, the selection device 10 selects the tendency of the distributed content based on the tendency of the first information and the tendency of the second information. Further, in another example, the selection device 10 selects the tendency of the distributed content based on the tendency of the relationship between the first information and the second information. Further, the selection device 10 estimates the tendency of the content that the user is interested in based on the first information and the second information, and selects the tendency of the distributed content based on the estimation result. Further, the selection device 10 estimates the tendency of the content estimated to be of interest to the user in the future based on the first information and the second information, and selects the tendency of the delivered content based on the estimation result. To do. In this way, the selection device 10 selects the tendency of the distributed content based on the relevance of each information, the relevance of the tendency, and the like, so that the tendency of the content presumed to be of interest to the user is set as the distribution content. It can be reflected in the tendency.

Further, the distribution server 300 generates distribution contents according to the tendency selected by the selection device 10. For example, the selection device 10 acquires information including the same type of content as the content distributed to the user as the first information or the second information. Then, the distribution server 300 generates distribution content from the content included in the first information or the second information according to the tendency selected by the selection device 10.

To give a more specific example, the selection device 10 acquires information including voice to be delivered to the user as the second information. Then, the distribution server 300 generates the audio obtained by editing the audio included in the second information according to the tendency selected by the selection device 10 as the distribution content. Further, in another example, the selection device 10 acquires information including the information of the book distributed to the user as the first information. Then, the distribution server 300 generates the information of the book according to the tendency selected by the selection unit as the distribution content from the information of the book included in the first information. Further, in another example, the selection device 10 acquires, as the first information or the second information, information indicating the content in which the interest from the user exceeds the predetermined threshold value within the predetermined period, and obtains the first information or the information indicating the content indicating the content exceeding the predetermined threshold value. From the second information, the tendency of the content whose interest from the user exceeds the predetermined threshold within the predetermined period is selected. Then, the distribution server 300 generates content indicating the tendency selected by the selection device 10 as distribution content.

In this way, the selection device 10 and the distribution server 300 select the tendency of the distribution content based on various information, and generate the content of the selected tendency based on various generation methods as the distribution content. Therefore, the selection device 10 and the distribution server 300 can, for example, realize the provision of distribution content that is presumed to be of interest to the user.

Further, the selection device 10 uses a model in which the relationship between the tendency of the first information, the tendency of the second information, and the tendency of the content according to the distribution purpose of the content is deeply learned, and the first information and the first information. 2 Select the tendency of the delivered content from the information. Therefore, the selection device 10 can accurately select the tendency of the distribution content that is presumed to be of interest to the user.

Further, the distribution server 300 distributes the reward associated with the distribution of the distribution content generated based on the selection of the selection device 10 to the provider who provides the first service and the provider who provides the second service. .. Therefore, the distribution server 300, for example, is a provider that provides the first information and the second information, and equally distributes the reward associated with the distribution of the distributed content to the economically or socially different providers. be able to.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

In addition, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the distribution unit can be read as a distribution means or a distribution circuit.

10 Selection device 20, 320 Communication unit 30, 330 Storage unit 31 Web-related information database 32 Terminal-related information database 33 Model database 40, 340 Control unit 41 Acquisition unit 42 Selection unit 43 Proposal unit 44 Learning unit 100 Web service server 200 Terminal service Server 300 Distribution server 331 Generation model database 341 Reception part 342 Generation part 343 Distribution part 400 User terminal

Claims (12)

The first information which is the information about the user's behavior acquired through the first service and the information about the user's behavior acquired through the second service different from the first service. 2 Acquisition department to acquire information and
Selection to select the tendency of the content provided to the user through the first service and the third service different from the second service based on the first information and the second information. Department and
A generation unit for generating information indicating the trend of the content selected in the previous SL selection unit,
A selection device characterized by having. The acquisition unit is information on the user's behavior acquired through the first service, and is related to the behavior performed by the user in relation to the content generated based on the selection by the selection unit. The information is acquired as the first information, and is information about the behavior of the user acquired through the second service, and is related to the content generated based on the selection by the selection unit. The selection device according to claim 1, wherein the information on the action performed by the user is acquired as the second information. As the first information, the acquisition unit acquires information on the user's behavior acquired through a service provided on the Web, and as the second information, via the hardware used by the user. The selection device according to claim 1 or 2, wherein the acquired information on the behavior of the user is acquired. As the first information, the acquisition unit includes a history of contents delivered to users, a history of browsing contents, a history of search queries, a history of advertisements delivered to users, a history of electronic commerce, and the like. The selection device according to claim 3, further comprising acquiring information including at least one of the user's position histories. As the second information, the acquisition unit acquires information including at least one of the usage history of the hardware, the operation history of the hardware, or the keyword input by the user for the hardware. The selection device according to claim 3 or 4. The selection unit is characterized in that the tendency of the content provided to the user via the third service is selected based on the tendency of the first information and the tendency of the second information. The selection device according to any one of claims 1 to 5. The selection unit is characterized in that it selects the tendency of the content provided to the user via the third service based on the tendency of the relationship between the first information and the second information. The selection device according to any one of claims 1 to 6. The selection unit estimates the tendency of the content that the user is interested in based on the first information and the second information, and based on the estimation result, the user via the third service. The selection device according to any one of claims 1 to 7, wherein the tendency of the content provided to the user is selected. The selection unit estimates the tendency of the content that the user is presumed to be interested in in the future based on the first information and the second information, and based on the estimation result, provides the third service. The selection device according to claim 8, wherein the tendency of the content provided to the user is selected through the method. The selection unit uses a model in which the relationship between the tendency of the first information, the tendency of the second information, and the tendency of the content according to the distribution purpose of the content is deeply learned by the acquisition unit. Of claims 1 to 9, the tendency of the content provided to the user via the third service is selected from the acquired first information and the second information. The selection device according to any one. The selection method performed by the selection device
The first information which is the information about the user's behavior acquired through the first service and the information about the user's behavior acquired through the second service different from the first service. 2 Acquisition process to acquire information and
Selection to select the tendency of the content provided to the user through the first service and the third service different from the second service based on the first information and the second information. Process and
A generation step of generating information indicating the trend of the selected content in the previous SL selection step,
A selection method characterized by including. On the computer
The first information which is the information about the user's behavior acquired through the first service and the information about the user's behavior acquired through the second service different from the first service. 2 Acquisition procedure to acquire information and
Selection to select the tendency of the content provided to the user through the first service and the third service different from the second service based on the first information and the second information. Procedure and
A generating step of generating information indicating the trend of the selected content in the previous SL selection procedure,
Selection program to execute.

Images