JP6838007B2 - Information processing system - Google Patents

Description

The present invention relates to an information processing system.

Conventionally, a technique for providing a user with information that the user is personally interested in has been proposed.
For example, in Patent Document 1, the content is classified into a plurality of categories, the user's interest level for each category is evaluated based on the user's browsing history, and the content belonging to the category whose interest level is equal to or higher than a certain reference value is the user. The technology provided to is disclosed.
Further, Patent Document 2 discloses a technique for providing a user with not only information that the user is personally interested in but also content that has a high degree of social attention.

Japanese Unexamined Patent Publication No. 2008-176491 JP-A-2015-079396

When learning the degree of interest of a category based on the user's browsing history, the learning time becomes longer as the number of categories increases, so it takes time to be able to provide content that matches the user's hobbies and tastes. Will be required. Therefore, an efficient learning method is important.

The learning speed can be adjusted by adjusting learning parameters such as the point addition width for the browsing operation and the attenuation width with the passage of time. For example, the learning speed can be increased by increasing the point addition width for one browsing or reducing the attenuation width with the passage of time.
However, in the parameter adjustment as described above, when the learning speed is increased, there is an adverse effect that the convergence and the followability are deteriorated, and it is difficult to obtain the desired accuracy.

The present invention has been made in view of such circumstances, and provides an information processing system capable of realizing efficient learning of user interest without affecting convergence and followability. The purpose is.

The first aspect of the present invention includes a plurality of client terminals and a server connected to the plurality of client terminals, and each of the client terminals is an input operation by the user for the content provided to the user by the client terminal. The first information creation unit that creates the first interest level information in which the degree of interest according to the content is indicated for each category to which the content belongs, the transmission unit that transmits the first interest level information to the server, and the server. a receiver for receiving the category correlation information, and on the basis of the input operation category correlation information by the user, second information creation unit that creates a second interest degree information interestingness is shown for each category, a plurality from the contents of, based on said second interest degree information to obtain the contents belonging to the category at a frequency corresponding to the height of the categories of interest degree, Turkey content determination section provides the acquired content to the user The server has a receiving unit that receives the first interest degree information from the plurality of client terminals , and the correlation degree between the plurality of the categories is based on the plurality of the first interest degree information. It is an information processing system having a correlation information creation unit that creates the indicated category correlation information and a transmission unit that transmits the category correlation information to each of the client terminals.

A second aspect of the present invention is the client terminal applied to an information processing system including a plurality of client terminals and a server connected to the plurality of client terminals, and the client terminal is provided to a user. The first information creation unit that creates the first interest degree information in which the degree of interest in the content according to the input operation by the user is shown for each category to which the content belongs, and the first interest degree information are transmitted to the server. a transmission unit, is generated based on the plurality of the first interest degree information received from a plurality of said client terminals, the receiving section for receiving category correlation information correlation was shown between the plurality of the categories from the server And the second information creation unit that creates the second interest degree information in which the interest degree is shown for each category based on the category correlation information and the input operation by the user, and the first from a plurality of contents . based on 2 interest degree information to obtain the contents belonging to the category at a frequency corresponding to the height of the categories of interest degree is the client terminal and a benzalkonium content determining section provides the acquired content to the user ..

A third aspect of the present invention is a program that is applied to an information processing system including a plurality of client terminals and a server connected to each of the client terminals and executed by the client terminals, and is a user at the client terminals. The first information creation process for creating the first interest degree information in which the degree of interest in the content provided in the above according to the input operation by the user is shown for each category to which the content belongs, and the first interest degree information are described above. a transmission process of transmitting to the server, category correlation information correlation was shown between the plurality of categories with created by the server based on the plurality of the first interest degree information received from a plurality of said client terminal Based on the second information creation process for creating the second interest degree information in which the interest degree is shown for each category based on the input operation by the user and the second interest degree information from the plurality of contents. Te, acquires the contents belonging to the category at a frequency corresponding to the height of the category of interest of a program containing a determined and constant process that provides the acquired content to the user.

According to the present invention, there is an effect that efficient learning of user interest can be realized without affecting convergence and followability.

It is a figure which showed the whole structure of the information processing system which concerns on one Embodiment of this invention. It is a figure which showed schematic the hardware configuration of the client terminal which concerns on one Embodiment of this invention. It is a figure which showed schematic the hardware configuration of the aggregation server which concerns on one Embodiment of this invention. It is a functional block diagram which showed an example of the function which the client terminal which concerns on one Embodiment of this invention has. It is a figure which showed an example of the category correlation information. It is a figure which showed an example of the 1st interest degree information. It is a figure which showed an example of the 2nd interest degree information. It is a functional block diagram which showed an example of the function which the aggregation server which concerns on one Embodiment of this invention has. It is a figure which showed an example of a plurality of first interest degree information received from each client terminal stored in the storage part of the aggregation server. It is a figure which showed an example of the flowchart which showed the procedure of operation of the information processing system which concerns on one Embodiment of this invention.

Hereinafter, an embodiment of the information processing system according to the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing an overall configuration of the information processing system 1 according to the present embodiment. As shown in FIG. 1, the information processing system 1 includes a plurality of client terminals 10a, 10b, 10c, and an aggregation server 50 as main configurations. In the following, when it is necessary to distinguish the client terminals 10a, 10b and 10c, they are referred to as client terminals 10a, 10b and 10c, and when it is not necessary to distinguish them, they are simply referred to as the client terminal 10. The plurality of client terminals 10 and the aggregation server 50 are connected to each other so as to be able to communicate with each other via the network 2. An internet line is given as an example of the network 2, but another network line may be used.

FIG. 2 is a diagram schematically showing a hardware configuration of the client terminal 10 according to the present embodiment. The client terminal 10 is a so-called information processing device such as a notebook PC, a tablet terminal, a mobile phone, or a smartphone. For example, a CPU 11, a ROM (Read Only Memory) 12 for storing a program executed by the CPU 11, and each program execution. A RAM (Random Access Memory) 13 that functions as a work area at the time, a hard disk drive (HDD) 14 as a large-capacity storage device, a communication interface 15 for connecting to a network, an input unit 16 consisting of a keyboard, a mouse, etc., and a display. The unit 17 is provided as a main configuration. Each of these parts is connected via a bus 18.
Various programs are stored in the ROM 12, and the CPU 11 reads the programs from the ROM 12 into the RAM 13 and executes the programs to realize various functions. The storage medium for storing the program or the like executed by the CPU 11 is not limited to the ROM 12, and may be another recording medium composed of a magnetic disk, a magneto-optical disk, a semiconductor memory, or the like.

Similarly, the aggregation server 50 is also a so-called computer system, and as shown in FIG. 3, functions as a CPU 51, a ROM (Read Only Memory) 52 for storing programs executed by the CPU 51, and a work area when each program is executed. It includes a RAM (Random Access Memory) 53, a hard disk drive (HDD) 54 as a large-capacity storage device, a communication interface 55 for connecting to a network, an input unit 56 including a keyboard, a mouse, and a display unit 57. .. Each of these parts is connected via a bus 58.
Various programs are stored in the ROM 52, and various functions are realized by the CPU 51 reading the programs from the ROM 52 to the RAM 53 and executing the programs. The storage medium for storing the program or the like executed by the CPU 51 is not limited to the ROM 52, and may be another recording medium composed of a magnetic disk, a magneto-optical disk, a semiconductor memory, or the like.
The aggregation server 50 does not necessarily have to have the display unit 57. Further, the aggregation server 50 may be configured such that the input unit 56 is installed in a remote place via a network or the like and an input operation can be performed from the remote place.

FIG. 4 is a functional block diagram showing an example of the functions included in the client terminal 10a. Since the functions provided by the other client terminals 10b and 10c are the same, the client terminal 10a will be described in detail here as a representative.
As shown in FIG. 4, the client terminal 10a includes a plurality of service applications 20a to 20c, and a higher-level application 30 for displaying information acquired by the service applications 20a to 20c on the display unit 17. By operating these service applications 20a to 20c and the higher-level application 30 on a platform such as an OS, various functions shown below are realized. Although three service applications 20a to 20c are illustrated in FIG. 4, the number of installed applications for acquiring contents is not particularly limited, and at least one may be provided.

The service applications 20a, 20b, and 20c access, for example, various content servers (not shown) connected via the network 2 at predetermined timings or at predetermined time intervals, and acquire the contents provided by the content servers. In the present embodiment, for convenience of explanation, the service application 20a acquires various news information such as sports news, music news, and movie news, and the service application 20b acquires event information such as sports event, music event, and movie event. The application and service application 20c will be described as an application for acquiring sales information of various products such as sports equipment, music CDs, and videos. The acquisition method of these information may be a push method or a pull method.
When the service applications 20a to 20c receive the content, they output it to the higher-level application 30.

The higher-level application 30 functions as a content storage unit 31, a storage unit 32, a learning unit 33, a content determination unit 34, a transmission unit 35, and a reception unit 36.
The content storage unit 31 stores a plurality of contents acquired by the service applications 20a to 20c. Here, each content is associated with categorical information according to the content of the content.
As for the category information, for example, one or a plurality of categories are set for each of the above-mentioned service applications 20a to 20c according to the content. For example, in the service application 20a, "sports news", "music news", "movie news" and the like are set as categories. Further, in the case of the service application 20b, for example, "sports event", "music event", "movie event" and the like are set as categories. Similarly, in the case of the service application 20c, for example, "sports equipment", "music CD", "movie DVD" and the like are set as categories.

This category information may be given by the higher-level application 30 when the upper-level application 30 has a function of classifying categories from the contents of the content, and each service application 20a to 20c has a function of category classification. If you have, you may give it in each service application 20a to 20c. Alternatively, the information may be given on the server side in which the service applications 20a to 20c acquire these contents.

The storage unit 32 stores category correlation information, first interest level information, and second interest level information.
The category correlation information is information created by the aggregation server 50, and as shown in FIG. 5, the degree of mutual correlation is set in each category. In the category correlation information shown in FIG. 5, the degree of correlation between category 1 (for example, sports news) and category 2 (for example, sports event) is set to "0.8", and category 1 (for example, sports news) and category 3 are set. The correlation degree of (for example, music CD) and the correlation degree of category 2 (for example, sports event) and the correlation degree of category 3 (score: 0) are both set to "0". That is, in the category correlation information shown in FIG. 5, it can be seen that category 1 and category 2 have a correlation, and category 1 and category 3 and category 2 and category 3 have no correlation. The details of how to create the category correlation information will be described later.

The first interest level information is information created by the first information creation unit 33a, which will be described later, and as illustrated in FIG. 6, responds to the user's input operation for the content provided to the user on the client terminal 10a. The degree of interest is shown for each category. Various operations can be targeted as input operations, such as content browsing operations and content purchasing operations of products and services. In the following description, the degree of interest according to the input operation related to browsing by the user A is shown for each category. For example, in the content displayed on the display unit 17, when the user performs an input operation related to browsing (for example, an operation of clicking the content), a predetermined score is added to the category to which the content belongs.

The second degree of interest information is information created by the second information creation unit 33b, which will be described later, and is based on the category correlation information and the input operation related to browsing by the user A of the client terminal 10a, as illustrated in FIG. The degree of interest is shown for each category. That is, the second interest level information is common to the first interest level information in that the degree of interest for each category is shown, but the first interest level information is added based only on the input operation by the user A. On the other hand, the second interest degree information is different from the first interest degree information in that points are added to other categories having a correlation with the added category in addition to the points added by the input operation by the user A. The details of the method of creating the first interest degree information and the second interest degree information will be described later.

The learning unit 33 includes a first information creation unit 33a and a second information creation unit 33b.
The first information creation unit 33a creates the first interest degree information based on the input operation related to browsing by the user A of the client terminal 10a. Specifically, when the user A performs an input operation related to browsing, a predetermined score is added to the category to which the content belongs. For example, when the content of the category of "sports news" displayed on the display unit 17 is viewed by the user A, the first information creation unit 33a is described in the first interest degree information stored in the storage unit 32 as " Add a given score to the degree of interest in the "sports news" category.

The second information creation unit 33b creates the second interest degree information based on the input operation and the category correlation information regarding the browsing by the user A of the client terminal 10a. Specifically, when the user A performs an input operation related to browsing, a predetermined score is added to the category to which the content belongs. Further, another category having a correlation with the category to which the content belongs is specified from the category correlation information, and a predetermined score is added to the specified other category. The score to be added at this time may be the same value as the category in which the input operation related to browsing is performed by the user A, or may be a score according to the degree of correlation with the category. For example, a score obtained by multiplying the score added to the category in which the input operation related to browsing is performed by the user by the degree of correlation may be added.

The content determination unit 34 determines the content to be provided to the user based on the second interest level information stored in the storage unit 32. For example, the content determination unit 34 acquires content belonging to the category from the content storage unit 31 at a frequency corresponding to the high degree of interest in each category in the second interest level information, and displays the acquired content on the display unit 17. indicate.
The transmission unit 35 transmits the first interest degree information stored in the storage unit 32 to the aggregation server 50 at a predetermined timing or a predetermined time interval.
The receiving unit 36 receives the category correlation information from the aggregation server 50 at a predetermined timing or a predetermined time interval. The received category correlation information is stored in the storage unit 32. As described above, the category correlation information stored in the storage unit 32 is information that is updated as needed.

Next, the aggregation server 50 will be described. FIG. 8 is a functional block diagram showing an example of the functions included in the aggregation server 50. The aggregation server 50 includes a receiving unit 61, a storage unit 62, a correlation information creating unit 63, and a transmitting unit 64 as main configurations.
The receiving unit 61 receives the first interest degree information from each of the client terminals 10a to 10c.
The storage unit 62 stores the first interest level information received from each of the client terminals 10a to 10c, and also stores the category correlation information created by the correlation information creation unit 63, which will be described later.

The correlation information creation unit 63 calculates the correlation degree between categories using a plurality of first interest degree information received from the plurality of client terminals 10a to 10c stored in the storage unit 62, and the correlation degree between categories is calculated. Create the indicated category correlation information. For example, the degree of correlation (correlation coefficient) α between category a and category b can be calculated based on the following equation (1). The method for calculating the degree of correlation is not limited to this example, and known techniques can be appropriately used.

For example, in the first interest level information received from each client terminal 10a to 10c, when the degree of interest for each category shows a score as shown in FIG. 9, the correlation information creation unit 63 relates to each user A to C. Calculate the correlation between categories based on the degree of interest in each category. As a result, for example, the category correlation information as shown in FIG. 5 is created. In FIG. 9, user A is a user of the client terminal 10a, user B is a user of the client terminal 10b, and user C is a user of the client terminal 10c.
When the correlation information creation unit 63 creates the category correlation information, it stores it in the storage unit 62.
When the category correlation information stored in the storage unit 62 is updated, the transmission unit 64 transmits the category correlation information to the client terminals 10a to 10c.

Next, the operation of the information processing system 1 having the above-described configuration will be described with reference to FIG. FIG. 10 is a diagram showing an example of a flowchart showing a procedure of the information processing system 1 according to the embodiment of the present invention.
First, in the client terminal 10a, the content determination unit 34 causes the display unit 17 to display the content (SA1). Specifically, the content determination unit 34 determines the content to be provided to the user based on the second interest level information stored in the storage unit 32. Then, the acquired display candidate contents are sequentially displayed on the display unit 17.
Next, when the input operation related to browsing is performed by the user A (SA2: YES), the first information creation unit 33a performs the input operation by the user A in the first interest degree information stored in the storage unit 32. The first interest level information is updated by adding points to the interest level score related to the content category (SA3). Similarly, in the second interest degree information stored in the storage unit 32, the second information creation unit 33b adds a predetermined score to the interest degree score regarding the content category for which the input operation is performed by the user A (). SA4). Further, the second information creation unit 33b identifies another category having a correlation with the category to be added by referring to the category correlation information (SA5), and assigns a predetermined score to the interest score of the specified category. Add points (SA6).

As a result, for example, when the user A performs an input operation related to browsing for the content belonging to category 1, the interest level score related to category 1 is updated in the first interest level information, and the interest level information is updated in the second interest level information. The score of the degree of interest regarding category 1 is updated, and the score of the degree of interest of category 2 having a correlation with category 1 is also updated based on the category correlation information shown in FIG.
When the second interest level information is updated in this way, the content determination unit 34 displays the content based on the updated second interest level information (SA1). For example, increase the frequency of providing content belonging to the category of high interest in the second interest information. Alternatively, increase the frequency of providing content that belongs to a category that has increased interest in the most recent predetermined period. Alternatively, increase the frequency of providing content that belongs to a category that was of high interest in a particular period in the past. Alternatively, content belonging to a category with a low degree of interest is intentionally provided at a predetermined frequency, for example, a frequency lower than that of a category with a high degree of interest. As described above, the second interest degree information can be used from various viewpoints to provide the content based on the updated second interest degree information.

Further, in the client terminal 10a, the first interest degree information is transmitted from the client terminal 10a to the aggregation server 50 at a predetermined timing or the like. Similarly, in the client terminals 10b and 10c, the first interest degree information according to the interest degree of each user B and C is transmitted to the aggregation server.
In the aggregation server 50, the correlation degree between categories is calculated by the correlation information creating unit 63 based on the plurality of first interest degree information received from the client terminals 10a to 10c, and the category correlation information is created. Then, the created category correlation information is transmitted to each client terminal 10a to 10c via the transmission unit 64. As a result, the category correlation information stored in the storage unit 32 is updated in each of the client terminals 10a to 10c. Then, the second interest degree information is updated based on the updated category correlation information.

As described above, according to the information processing system 1 according to the present embodiment, when an input operation related to browsing is performed by a user, the information processing system 1 has a correlation not only with the category in which the input operation is performed but also with the category. Interest in other categories will also be added. As a result, the user's input operation can be reflected in the interest level of more categories, and the learning of the user interest level can be promoted. As a result, efficient learning can be performed, and a wider range of learning can be performed in a short period of time.
Further, since the learning parameters are not adjusted, the learning can be performed efficiently without affecting the convergence and the followability.

Further, according to the present embodiment, the first interest level information to which the interest level is added is created based only on the input operation of the user, and the first interest level information is transmitted to the aggregation server 50. Then, the aggregation server 50 creates category correlation information based on a plurality of first interest degree information received from the plurality of client terminals 10a to 10c. As a result, it becomes possible to grasp the correlation of the categories more accurately, and it is possible to improve the accuracy of the second interest degree information.

Although the present invention has been described above using the respective embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. Various changes or improvements can be made to the above embodiments without departing from the gist of the invention, and the modified or improved forms are also included in the technical scope of the present invention. In addition, the above embodiments may be combined as appropriate.
Further, the operation flow described in the above embodiment is also an example, and unnecessary steps may be deleted, new steps may be added, or the processing order may be changed within a range not deviating from the gist of the present invention. ..

1 Information processing system 10 (10a-10c) Client terminal 17 Display unit 20 (20a to 20c) Service application 30 High-level application 31 Content storage unit 32 Storage unit 33 Learning unit 33a First information creation unit 33b Second information creation unit 34 Content Decision unit 35 Transmission unit 36 Reception unit 50 Aggregation server 61 Reception unit 62 Storage unit 63 Correlation information creation unit 64 Transmission unit

Claims (6)

With multiple client terminals
A server connected to a plurality of the client terminals is provided.
Each of the client terminals
A first information creation unit that creates first interest level information in which the degree of interest in the content provided to the user on the client terminal according to the input operation by the user is shown for each category to which the content belongs.
A transmission unit that transmits the first interest level information to the server, and
A receiver that receives category correlation information from the server,
A second information creation unit that creates a second interest level information in which the degree of interest is shown for each category based on the category correlation information and the input operation by the user.
From among a plurality of contents, on the basis of the second interest degree information to obtain the contents belonging to the category at a frequency corresponding to the height of the categories of interest degree, Turkey content determined to provide the acquired content to the user Has a part and
The server
A receiving unit that receives the first interest level information from the plurality of client terminals, and
Based on the plurality of the first interest degree information, and correlation information creation unit for creating the category correlation information correlation was shown between the plurality of categories,
An information processing system having a transmission unit that transmits the category correlation information to each of the client terminals. When the user performs an input operation on the content, the second information creating unit updates the degree of interest of the category to which the content is the target of the input operation, and inputs the input from the category correlation information. The second aspect of claim 1, wherein another category having a correlation with the category of the content to be operated is specified, and the interest degree of the specified other category is updated to create the second interest degree information. Information processing system. The information processing system according to claim 2, wherein the second information creating unit creates the second interest degree information by adding a score corresponding to the correlation degree to the interest degree corresponding to the other category. Each of the client terminals is equipped with a plurality of application software for acquiring a plurality of contents.
The information processing system according to any one of claims 1 to 3, wherein one or a plurality of the above categories are set for each application software. The client terminal applied to an information processing system including a plurality of client terminals and a server connected to the plurality of client terminals.
A first information creation unit that creates first interest level information in which the degree of interest in the content provided to the user on the client terminal according to the input operation by the user is shown for each category to which the content belongs.
A transmission unit that transmits the first interest level information to the server, and
Was created from the plurality of the first interest degree information received from a plurality of said client terminals, a receiver for receiving a category correlation information correlation was shown between the plurality of the categories from the server,
A second information creation unit that creates a second interest level information in which the degree of interest is shown for each category based on the category correlation information and the input operation by the user.
From among a plurality of contents, on the basis of the second interest degree information to obtain the contents belonging to the category at a frequency corresponding to the height of the categories of interest degree, Turkey content determined to provide the acquired content to the user A client terminal equipped with a department. A program applied to an information processing system including a plurality of client terminals and a server connected to each of the client terminals, and executed by the client terminals.
The first information creation process for creating the first interest level information in which the degree of interest in the content provided to the user on the client terminal according to the input operation by the user is shown for each category to which the content belongs, and the first information creation process.
A transmission process for transmitting the first interest level information to the server, and
The category correlation information created by the server based on the plurality of first interest degree information received from the plurality of client terminals and showing the degree of correlation between the plurality of categories and the input operation by the user. Based on the second information creation process that creates the second interest level information in which the degree of interest is shown for each category,
From among a plurality of contents, on the basis of the second degree of interest information to obtain the contents belonging to the category at a frequency corresponding to the height of the categories of interest degree, acquired decision process content that provides to the user Programs that include and.

Images