JP2002014964A - Information providing system and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To present secure information following each user by reflecting the tendency of not a part but the entire of the interest and liking of the user to information selection even when the interest and liking include many things. SOLUTION: A score calculation part 17 calculates a score for arranging contents based on similarity by using the using history of the user and a cluster sorting part 20 sorts the contents to be clusters based on this score. A contents selection part 18 selects the contents from the respective clusters in accordance with a relation between the user and the cluster to present information on the selected contents to the user.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information providing system and an information providing method suitable for application to a network information providing system in the Internet, personal computer communication, etc. And a method for providing information.

[0002]

2. Description of the Related Art In recent years, with the spread of the Internet and personal computer communication, for example, the WWW (World Wi
Services for providing information to a large number of users via a network, such as an information providing service using de Web), are widely performed. However, the amount of information available to network users is increasing, and it is becoming difficult to search for necessary information from many pieces of information. Therefore, there is a demand for selecting and presenting only appropriate information that matches the interests and preferences of the user from many pieces of information.

[0003] On the other hand, conventionally, an information search method and an information filtering method for selecting information suitable for a user's interest and taste have been proposed, for example, a method called social filtering has been proposed. This means that many users who use the information evaluate each information, calculate the similarity between users based on the evaluation information,
This is a method of providing information suitable for the information requester's interests and preferences by preferentially providing information highly evaluated by other users who have a high degree of similarity to the information requester.

[0004]

However, it has been difficult for conventional information retrieval systems and information filtering systems to accurately grasp the interests and preferences of users when they are diverse. For example, in a service that provides music information, there may be a user who mainly evaluates information of “rock” highly, but also highly evaluates information of a very small number of “enka”. In general,
Since there are few people who rate "Rock" and "Enka" both highly, in the process of calculating the similarity with other users, only the evaluation of "Rock", which is frequently evaluated by this user, is used. In some cases, the evaluation of "enka" was not reflected in the similarity calculation and was not reflected in the final information selection result.

[0005] As described above, when a user's tastes vary widely, only a part of the preferences may be reflected in information selection.

[0006] The present invention has been made in view of the above-mentioned problems, and even when the interests and preferences of users are diverse, information selection is performed based on the entire tendency instead of a part of the interests and preferences. It is an object of the present invention to provide an information providing system and an information providing method capable of presenting accurate information in accordance with each user.

[0007]

Therefore, in order to solve the above problems, the present invention provides the following information providing system and information providing method. (1) An information providing system in which a server for providing content and a terminal device of a user are connected via a network, wherein the server is content identification information for identifying the content registered in content storage means. Together with content attribute storage means for storing content attribute information of the content, and use history storage for storing, along with content identification information indicating the content used by the user, user identification information of a user who has used the content Means, use frequency information forming means for forming use frequency information representing the use frequency of each content of each user based on the content identification information and user identification information stored in the use history storage means, and the use frequency Based on the usage frequency information formed by the information forming means, each component is stored in the information space. Score calculating means for calculating a score for arranging contents based on the similarity; cluster classification means for classifying each content into clusters for each content having high similarity based on the calculation result of the score calculating means; Content selecting means for calculating the degree of relevance between a user and each of the clusters, and selecting content based on the degree of relevance; and content identification information and content attribute information of the content selected by the content selecting means, An information providing system comprising: a transmitting unit that reads out from the storing unit and transmits the readout to the terminal device side. (2) An information providing system in which a server for providing content and a terminal device of a user are connected via a network, wherein the server is content identification information for identifying the content registered in content storage means. A content attribute storage unit for storing content attribute information of the content, and an evaluation value obtained by each user evaluating the content in association with the content identification information and the user identification information for identifying each user. Evaluation information storage means for storing as information, score calculation means for calculating a score for arranging each content in an information space based on the similarity based on the evaluation information, and a score calculation means for calculating the score. Cluster classification means for classifying each content into clusters for each content having high similarity, Calculating a degree of association between the user and each of the clusters, and selecting content based on the degree of association; and content identification information and content attribute information of the content selected by the content selection means, A transmitting unit that reads out from the attribute storing unit and transmits the readout to the terminal device side. (3) An information providing method for providing content from a server to a user's terminal device via a network, the content providing information indicating content used by the user, and use of the user using the content. User identification information is stored as a usage history, and based on the usage history, usage frequency information representing the usage frequency of each user for each content is formed. Based on the usage frequency information, each content is stored in an information space. Score calculating means for calculating a score to be arranged based on the similarity; and, based on the calculation result of the score, classifying each content into clusters for each content having high similarity, and a degree of association between each user and each cluster. Is calculated, the content is selected based on the relevance, and the content identification information and the content attribute of the selected content are selected. And transmitting the sex information to the terminal device. (4) An information providing method for providing content from a server to a user's terminal device via a network, wherein each user evaluates the content by evaluating the content with content identification information for identifying the content and Generates evaluation information associated with user identification information for identifying a user, calculates a score for arranging each content in the information space based on the similarity based on the evaluation information, and calculates a score of the score. Categorizing each content into clusters each having high similarity, calculating the degree of relevance between each user and each cluster, selecting content based on the degree of relevance, and selecting the content. An information providing method, comprising transmitting content identification information and content attribute information to a terminal device. (5) In the information providing system according to the above (1) or (2), the content selection means ranks higher in the selected content in accordance with the calculated relevance, as the content belongs to a cluster having a higher relevance. The content is ranked so as to be located, and the transmitting unit transmits the ranking information resulting from the ranking performed by the content selecting unit to the terminal device together with the content identification information and the content attribute information. Information providing system. (6) In the information providing method according to the above (3) or (4), with respect to the content selected based on the relevance, a content belonging to a cluster having a higher relevance is ranked higher according to the relevance. So that the ranking information of the result of the ranking performed on the selected content is transmitted to the terminal device together with the content identification information and the content attribute information of the selected content. Characteristic information provision method.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a first preferred embodiment of an information providing system and an information providing method according to the present invention will be described with reference to the drawings. The present invention can be applied to an information providing system as shown in FIG.

[Structure of Embodiment] FIG. 1 shows the whole structure of an information providing system according to an embodiment of the present invention. FIG. 1 is also an information providing system to which an embodiment of the information providing method of the present invention is applied. As shown in FIG. 1, the present information providing system is configured by connecting a server 1 for providing contents and a terminal device 2 of a user via a network 3 such as a LAN, a telephone network, and a dedicated line. I have.

The server 1 has the following configuration. A transmission / reception unit 11 for controlling the network 3; A content storage unit 12 for storing data format contents such as text, audio, still image, and video; A content attribute storage unit 13 that stores a content ID for identifying each content and attribute data such as a title, an author, and a registration date of the content. A user attribute storage unit 14 for storing a user ID and a password of the user; Content ID of used content and user ID of user who used it
Usage history storage unit 15 for recording and storing the information. Usage history storage unit 1
A use frequency information forming unit 16 that creates data representing the use frequency of the content for each user with reference to the attribute data in the content attribute storage unit 13 based on the data of No. 5; Score calculation unit 1 that calculates a score for arranging each content in the information space based on the similarity using the usage frequency information
7. A cluster classification unit 20 that classifies each content into clusters using the result of the score calculation unit. A content selection unit 1 that calculates the degree of association between each user using the terminal device 2 and each cluster and selects content based on the calculated degree.
8. The control unit 19 controls the entire server 1.

In FIG. 1, each part of the server 1 is shown in hardware, but this is
To 20 may be realized by software as built-in program processing. Thus, the server 1 can be realized by a personal computer, a workstation, or another computer.

The terminal device 2 includes a CPU, a RAM, a ROM,
It is composed of a network control circuit, an input device such as a keyboard and a mouse, and a display device such as a display, and performs a processing operation by a built-in program. A general personal computer can be used as the terminal device 2.

[Operation of the Embodiment] Next, the operation of the information providing system according to the embodiment having such a configuration will be described.

[User Registration Operation] In the information providing system of the present embodiment, the user performs user registration on the server 1 side in order to receive the information providing service. This user registration is performed according to the flowchart shown in FIG. 2. When performing user registration, the user operates the terminal device 2 in step S1 to, for example, input the user's name and gender. , Address, date of birth and other user attributes are input. The user attribute information indicating the user attribute input by the user is stored in the network 3
Is transmitted to the server 1 through the server.

The server 1 receives the user attribute information transmitted from the user via the transmission / reception unit 11 under the control of the control unit 19, and supplies the user attribute information to the user attribute storage unit 14.
In the user attribute storage unit 14, in a format as shown in FIG.
A user attribute table including attributes such as a user ID for uniquely identifying a user, a password, and a name input by the user is provided.

After confirming that the user attribute information transmitted from the user is not already stored in the user attribute table in step S2, the control unit 19 sets the unused user ID and the corresponding user ID. Create a password. Then, in step S3, a new entry is allocated to the user attribute storage unit 14, and the formed user ID and password are stored in the user attribute table together with the received user attribute information. Further, the control unit 19
Along with such storage control, the formed user ID and password are transmitted to the terminal device 2 via the transmission / reception unit 11.

The user obtains the user ID and the password transmitted from the server 1 through the terminal device 2 and thereafter receives an information providing service in the information providing system using the user ID and the password. It will be.

[Information Providing Operation] Next, when the user attribute is registered in the server 1 and the user acquires the user ID and the password, the information providing service in the information providing system can be received. Becomes

This information providing service is performed according to the flowchart shown in FIG. 4. When receiving the information providing service, in step S11, the user operates the terminal device 2 and operates the terminal device 2 to obtain the obtained user ID. And enter the password. The terminal device 2 transmits the user ID and the password input by the user to the server 1.

The control unit 19 of the server 1 sends the user ID
The password is received via the transmission / reception unit 11 and compared with the user ID and password registered in the user attribute table of the user attribute storage unit 14 in step S12. And only when a match between them is detected,
An information providing service described below is provided. If they do not match, an error code is returned to the terminal device 2 side. As a result, the user notices an input error of the user ID and the password, etc.
Alternatively, a password is input.

Next, the control unit 19 of the server 1 compares the user ID and password transmitted from the user with the user ID and password registered in the user attribute table of the user attribute storage unit 14. If a match is detected, a content menu is created individually for the user in step S13 and transmitted to the user.

[Content Menu Creation Operation] Specifically, this content menu is created according to the flowchart shown in FIG. This flowchart is similar to the flowchart of FIG.
Starts by detecting the coincidence between the two, and the process proceeds to step S21.

(Operation of Creating Usage Frequency Data) Step S
At 21, the usage frequency information forming unit 16 shown in FIG. 1 creates usage frequency data A in a matrix format as described below. In the following, the number of users stored in the usage history storage unit 15 is M, and the number of contents is N.

The usage frequency data creation unit 16 performs a search by linking the table of the content attribute storage unit 13 and the table of the usage history storage unit 15 by using the “content ID” which is common to both as a key. From among the 15 tables, the user i (i = 1 to M) selects the content j (j
= 1 to N). Let L be the number of records. The number of records L is used as the use frequency aij for the content j of the user i. User i
If a does not use the content j, aij is set to 0.

The use frequency information forming section 16 creates the use frequency data A of an M-row, N-column matrix having the use frequencies aij (i = 1 to M, j = 1 to N) as elements. When the use frequency data A is created, the server 1 proceeds to step S22 in FIG.

(Score Calculation Operation) Next, step S2
In 2, the score calculation unit 17 shown in FIG. 1 calculates a score for arranging each content in the information space based on the similarity.

More specifically, the score calculation unit 17 obtains a score by applying, for example, a principal component analysis, which is a method of multivariate analysis, to the usage frequency data A. When this is applied, the score (eigenvector or principal component load amount) Yjq (j = 1 to
N, q = 1 to Q) are obtained. The constant Q is the number of valid components, where Q <min (M, N). The difference (distance) between the scores Yjq as an index indicating the degree of similarity between any two contents
Use

In the present embodiment, the principal component analysis is applied to the score calculation. However, this may be achieved by using another statistical method that can obtain the same result.

(Cluster Classification Operation) Next, step S2
In 3, the cluster classification unit 20 classifies each content into clusters based on the score Yjq. Specifically, a known cluster analysis method is applied to the score Yjq. Any two
The distance between the two contents (between the contents 1 and the contents m) is calculated according to the following equation (1), and the contents having the smaller distances are sequentially combined into one cluster. The number of clusters formed according to the type of content is set. Here, as shown in FIG. 6, it is assumed that each content always belongs to one cluster.
It is assumed that clusters are formed. In this embodiment, the Euclidean distance is used as shown in Expression (1), but a Mahalanobis distance or the like may be used.

[0030]

(Equation 1)

(Operation for calculating the degree of association between the user and the cluster)
Next, in step S24, the content selection unit 18
Is the user i using the terminal device 2 and the cluster k (k
= 1 to C). Various formulas are conceivable as equations for obtaining the degree of association. For example, the degree of association Rik between the user i and the cluster k is calculated based on the following equation (2). Here, Fi is the number of times the user i has used the content, and Fik is the number of times the user i has used the content belonging to the cluster k. The degree of relevance Rik calculated by equation (2) takes a value from 0 to 1, and the sum of relevance of each cluster is 1.

[0032]

(Equation 2)

(Content Selection Operation) Next, when the degree of association between the user and the cluster is calculated in this way, in step S25, the content selection unit 18 determines from each cluster according to the following equation (3). Determine the number of content to select. Here, Ga is the number of contents to be included in the content menu transmitted to the terminal device 2 side,
Gik is the number selected from the contents belonging to the cluster k for the user i who uses the terminal device 2.

[0034]

(Equation 3)

Next, in step S26, the content selection section 18 selects Gik content from each cluster k (1 to C). There are several methods for selecting content from each cluster. If the number of clusters C is large, content may be randomly selected from each cluster. Alternatively, a content used by the user i may be selected from the contents belonging to the cluster k, and a content having a small difference between the content and the score Yjq may be selected. If the user uses the same content only once in a download type service or the like, the content is selected excluding the content already used by the user.

Next, in step S27, for the Ga contents selected in this way, the content ID, title,
Take out the author, genre, etc. and create a content menu. A content attribute table is formed in the content attribute storage unit 13 in a format as shown in FIG.
Attributes such as a title, an author, a genre, a registration date, a storage location of the content body, and the like are stored for each content ID that uniquely identifies the content. Here, the author is not limited to the person who produced the content, but also includes a director, a performer, an editor, a performer, and the like. The content menu created in this way is transmitted from the server 1 to the terminal device 2, and all the routines in the flowchart shown in FIG. 5 are completed.

The content menu is, for example, the terminal device 2
Are displayed in a display format as shown in FIG. The display order of the contents in the content menu (for example, numbers 1, 2, 3,... In FIG. 7 are numbers indicating the display order) is determined based on the relevance Rik between the user i and the cluster k. The selection unit 18 may set it. For example, the contents are ranked so that the display belonging to the cluster having the higher relevance Rik is ranked higher, and a content menu is created including the rank information as a result of the ranking. The content menu is transmitted from the server 1 to the terminal device 2 side, and the display of the terminal device 2 is displayed in a display format according to the display order. In this case, since the content belonging to the cluster having a higher degree of relevance to the user is displayed at a higher position, the user can more easily select the content having a higher degree of relevance to the user.

When all the routines in the flowchart shown in FIG. 5 are completed, the information providing system proceeds to step S14 in the flowchart shown in FIG.

[Content Selection Operation by User] In step S14 of the flowchart shown in FIG. 4, the user selects a desired content from the content menu received via the terminal device 2.

That is, a title, an author, a genre, and the like are displayed on the display of the terminal device 2 in a display format as shown in FIG. 7, for example, and the user selects a desired content from these. Thereby, the terminal device 2
Transmits a content ID corresponding to the content selected by the user to the server 1.

[Content ID Selected by Server
Next, when the content ID corresponding to the content selected by the user is transmitted from the terminal device 2, in step S15, the control unit 19 of the server 1
Is the user ID together with the transmitted content ID.
And the use date and time are stored in the use history storage unit 15. As a result, a use history table including attributes such as a content ID, a user ID, and a use date and time is formed in the use history storage unit 15 in a format as shown in FIG.

[Transmission Operation of Content Data] Next, in step S16, the control unit 19 searches for content data corresponding to the received content ID together with such storage control, and stores the relevant content data in the terminal device 2. Send to

The control unit 19 searches the storage location of the content data main body from the content attribute table based on the content ID transmitted from the user terminal device 2.
The content data main body is stored in the content storage unit 12, and the control unit 19 reads out the content data main body from the searched storage location (from the content storage unit 12) and transmits it to the terminal device 2.

Thus, in step S17, the user can obtain the audio output or the video corresponding to the content data (the content selected by the user) transmitted from the server 1 via the terminal device 2.

As is clear from the above description, the information providing system of the first embodiment calculates a score for arranging content based on similarity using the usage history of the user, and divides the content based on the score. The content is classified into clusters, content is selected from each cluster according to the degree of association between the user and the cluster, and information on the selected content is presented to the user. Therefore, this information provision system,
Each piece of content information in a wide range of fields can be selected and provided while reflecting the user's preferences, so even if the user's preferences are diverse, it is more accurate for each user without being biased to a specific field. Content information can be presented.

Next, a second preferred embodiment of the information providing system and the information providing method according to the present invention will be described with reference to the drawings. [Structure of Embodiment] FIG. 10 shows the entire structure of an information providing system according to a second embodiment of the present invention.
FIG. 10 is also an information providing system to which an embodiment of the information providing method of the present invention is applied. As in the first embodiment shown in FIG. 1, a server 1a for providing contents and a user terminal device 2 are connected via a network 3, such as a LAN, a telephone network, and a dedicated line. Have been.

The server 1a has the following configuration. A transmission / reception unit 11 for controlling the network 3; A content storage unit 12 for storing data format contents such as text, audio, still image, and video; A content ID for identifying each content, a title of the content,
A content attribute storage unit 13 for storing attribute data such as an author and a registration date. An evaluation information storage unit 25 for storing evaluation information for the content of the user; An evaluation matrix generation unit 26 that generates matrix data from the evaluation information. A score calculation unit 17 that calculates a score for arranging each content in the information space based on the similarity using an evaluation matrix generated from the evaluation information. A cluster classification unit 20 that classifies each content into clusters using the result of the score calculation unit. A content selection unit 18 that calculates the degree of association between the user using the terminal device 2 and each cluster and selects content based on the calculated degree. The control unit 19 controls the entire server 1a.

In FIG. 10, the server 1a
Are shown in hardware, but this may be realized by software as built-in program processing. Thus, the server 1a can be realized by a personal computer, a workstation, or another computer.

The terminal device 2 includes a CPU, a RAM, a ROM,
It is composed of a network control circuit, an input device such as a keyboard and a mouse, and a display device such as a display, and performs a processing operation by a built-in program. A general personal computer can be used as the terminal device 2.

[Operation of Embodiment] Next, the operation of the information providing system of the embodiment having such a configuration will be described.

[User Registration Operation] In the information providing system of the present embodiment, in order to receive the information providing service, the user performs user registration on the server 1a side. This user registration is performed in accordance with the flowchart shown in FIG. 11. When performing user registration, the user operates the terminal device 2 in step S31, for example, the user's name and gender. , Address, date of birth and other user attributes are input. The user attribute information indicating the user attribute input by the user is transmitted to the server 1a via the network 3.

Under the control of the control unit, the server 1a receives the user attribute information transmitted from the user via the transmission / reception unit 11, and supplies this to the user attribute storage unit 14. The user attribute storage unit 14 stores, in a format as shown in FIG. 3, a user ID for uniquely identifying a user, a password,
A user attribute table including attributes such as names input by the user is provided.

In step S32, the control unit confirms that the user attribute information transmitted from the user is not already stored in the user attribute table, and then uses the unused user ID and the corresponding password. Create
Then, in step S33, the user attribute storage unit 1
4, a new entry is assigned, and the formed user ID and password are stored in the user attribute table together with the received user attribute information. The control unit 19 transmits the formed user ID and password to the terminal device 2 via the transmission / reception unit 11 together with such storage control.

The user obtains the user ID and password transmitted from the server 1a via the terminal device 2,
Thereafter, the information providing service in the information providing system is received by using the user ID and the password. Next, in step S34, the control unit 19 selects an appropriate content from the content attribute storage unit 13 and creates an evaluation content list. The evaluation content list includes the title, author, and the like of each content. Then, this is transmitted to the terminal device 2 via the transmission / reception unit 11. In step S35, the user performs an evaluation operation on the content described in the evaluation content list. For example, a degree of interest ranging from 1 (no interest at all) to 5 (very interested)
The evaluation is performed in stages, and this evaluation information is transmitted to the server. The user does not need to evaluate contents that he does not know. In step S36, the server 1a stores the evaluation information on the content evaluated by the user in the evaluation information storage unit 35 in a format as shown in FIG. The user's evaluation information registration is performed not only at the time of user registration but also at the time of providing information.

[Information Providing Operation] Next, the user attribute and the evaluation information are registered in the server 1a as described above, and when the user acquires the user ID and the password, the user receives the information providing service in the information providing system. It becomes possible.

This information providing service is performed according to the flowchart shown in FIG. 13. When the information providing service is received, in step S41,
The user operates the terminal device 2 and obtains the obtained user ID.
And enter the password. The terminal device 2 transmits the user ID and the password input by the user to the server 1a.
Send to

The control unit 19 of the server 1 a
D and the password are received via the transmission / reception unit 11, and are compared with the user ID and the password registered in the user attribute table of the user attribute storage unit 14 in step S42. Only when a match between the two is detected, the information providing service described below is performed. If they do not match, an error code is returned to the terminal device 2 side. As a result, the user notices an input error of the user ID or the password or the like, and inputs the correct user ID or the password again.

Next, the control unit 19 of the server 1a compares the user ID and password transmitted from the user with the user ID and password registered in the user attribute table of the user attribute storage unit 14. If a match is detected, a content menu is created individually for the user in step S43 and transmitted to the user.

[Content Menu Creation Operation] Specifically, this content menu is created according to the flowchart shown in FIG. This flowchart is different from the control unit 1 in step S42.
9 is started by detecting the coincidence between the two, and the process proceeds to step S51.

In the following description, it is assumed that M users are evaluating a total of N contents. In step S51, the evaluation matrix generation unit 26 reads out the user ID, the content ID, and the evaluation value from the evaluation information storage unit 25, and creates a data evaluation matrix B in a matrix format. The element bij of the evaluation matrix B is a user i (i = 1 to M)
However, when the content j (j = 1 to N) is evaluated, the evaluation value is obtained. When the content j is not evaluated, a value corresponding to moderate interest is set.

(Score Calculation Operation) Next, step S5
In 2, the score calculation unit 17 shown in FIG. 1 calculates a score for arranging each content in the information space based on the similarity.

More specifically, the score calculation unit 17 obtains a score by applying, for example, principal component analysis, which is a method of multivariate analysis, to the evaluation matrix B. When this is applied, the score (eigenvector or principal component load amount) Yjq (j = 1 to N, q = 1) corresponding to each content
To Q) are obtained. The constant Q is the number of valid components, Q
<Min (M, N). The difference (distance) between the scores Yjq is used as an index indicating the degree of similarity between any two contents.

In the present embodiment, the principal component analysis is applied to the calculation of the score. However, this may be achieved by using another statistical method that can obtain a similar result.

(Cluster Classification Operation) Next, step S5
In 3, the cluster classification unit 20 classifies each content into clusters based on the score Yjq. Specifically, a known cluster analysis method is applied to the score Yjq. Any two
The distance between two pieces of content (between the content 1 and the content m) is calculated according to the formula (1), and the content having the smaller distance is sequentially collected into one cluster. The number of clusters formed according to the type of content is set. Here, as shown in FIG. 6, each content always belongs to one cluster, and C clusters are formed. In this embodiment, the Euclidean distance is used as shown in Expression (1), but a Mahalanobis distance or the like may be used.

[0065]

(Equation 4)

(Calculation Operation of Degree of Association between User and Cluster)
Next, in step S54, the content selection unit 18
Is the user i using the terminal device 2 and the cluster k (k
= 1 to C). Various formulas are conceivable as equations for obtaining the degree of association. For example, the degree of association Rik between the user i and the cluster k is calculated based on the following equation (4). Here, Ei is the number of contents for which the user i has given a higher rating than a certain value, and Eik is the cluster k among the contents for which the user i has given a higher rating than a certain value.
Is the number of contents belonging to. The degree of relevance Rik calculated by equation (4) takes a value from 0 to 1, and the sum of relevance of each cluster becomes 1.

[0067]

(Equation 5)

(Content Selection Operation) Next, when the degree of association between the user and the cluster is calculated in this way, in step S55, the content selection unit 18 sets each cluster in accordance with the following equation (3). Determine the number of contents to select from. Here, Ga is the number of contents to be included in the content menu to be transmitted to the terminal device 2 side, and Gik is the number selected from the contents belonging to the cluster k for the user i using the terminal device 2. is there.

[0069]

(Equation 6)

Next, in step S56, the content selection section 18 selects Gik content from each cluster k (1 to C). There are several methods for selecting content from each cluster. If the number of clusters C is large, content may be randomly selected from each cluster. Alternatively, a content that is highly evaluated by the user i may be selected from the contents belonging to the cluster k, and a content having a small difference between the content and the score Yjq may be selected. If the user uses the same content only once in a download type service or the like, the content is selected excluding the content already used by the user.

For the Ga contents selected in this way, in step S57, the contents ID, title, author,
Take out the genre and create a content menu. The created content menu is transmitted from the server 1a to the terminal device 2 side, and all the routines in the flowchart shown in FIG. 14 are completed.

The content menu is, for example, the terminal device 2
Are displayed in a display format as shown in FIG. The display order of the contents in the content menu (for example, numbers 1, 2, 3,... In FIG. 7 are numbers indicating the display order) is determined based on the relevance Rik between the user i and the cluster k. The selection unit 18 may set it. For example, the contents are ranked so that the display belonging to the cluster having the higher relevance Rik is ranked higher, and a content menu is created including the rank information as a result of the ranking. The content menu is transmitted from the server 1a to the terminal device 2 side, and the display of the terminal device 2 displays the content menu in the display format according to the display order. In this case, since the content belonging to the cluster having a higher degree of relevance to the user is displayed at a higher position, the user can more easily select the content having a higher degree of relevance to the user.

When all the routines in the flowchart shown in FIG. 14 are completed, the information providing system proceeds to step S44 in the flowchart shown in FIG.

[Content Selection Operation by User] Next, in step S44 of the flowchart shown in FIG. 13, the user selects a desired content from the content menu received via the terminal device 2.

That is, a title, an author, a genre, and the like are displayed on the display of the terminal device 2 in a display format as shown in FIG. 7, for example, and the user selects a desired content from these. Thereby, the terminal device 2
Transmits a content ID corresponding to the content selected by the user to the server 1a.

Next, at step S45, the control unit 1
9 is the content I transmitted from the user terminal device 2
The storage location of the content data body is searched from the content attribute table based on D, and the content data is transmitted to the terminal device 2. The content data main body is stored in the content storage unit 12, and the control unit 19 reads out the content data main body from the searched storage location (from the content storage unit 12) and transmits it to the terminal device 2.

As a result, in step S46, the user enters a text corresponding to the content data (the content selected by the user) transmitted from server 1a.
Audio or video can be obtained via the terminal device 2. Thereafter, in step S47, after displaying and reproducing the content, the user can perform an evaluation operation on the content. The user's evaluation information is transmitted from the terminal device 2 to the server 1a, and is stored in the evaluation information storage unit 25 as described above in step S48. If the user does not want to perform the evaluation work after the content is reproduced, this can be omitted.

As is clear from the above description, the second
The information providing system according to the embodiment uses the evaluation information of the user to calculate a score for arranging the content based on the similarity, classify the content into clusters based on the score, and determine the degree of association between the user and the cluster. The content is selected from each cluster in accordance with, and the information of the selected content is presented to the user. Therefore, this information provision system can select and provide each type of content information in a wide range of fields while reflecting the user's preferences, so even if the user's preferences are diverse, it is biased to a specific field Content information that is more appropriate for each user.

Finally, the description of the above embodiment is an example of the present invention. For this reason, the present invention is not limited to this embodiment, and various changes can be made in other than this embodiment without departing from the technical idea of the present invention. Of course.

[0080]

As described above, according to the present invention, using the usage history of the user or using the evaluation information of the user,
Calculate a score that positions content based on similarity,
The content is classified into clusters based on the score, the content is selected from each cluster according to the degree of association between the user and the cluster, and information on the selected content is presented to the user. Therefore, the present invention can select and provide each piece of content information in a wide range of fields while reflecting the user's preferences, so that even if the user's preferences are diverse, each content information can be selected without bias to a specific field. It is possible to present accurate content information according to the user. Further, according to the present invention, there is no need for the content provider to classify the content in advance, and the number of steps and costs involved in providing the content can be significantly reduced.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an overall configuration of an information providing system according to a first embodiment to which an information providing system and an information providing method according to the present invention are applied.

FIG. 2 is a flowchart showing a user registration procedure in the information providing system shown in FIG. 1;

FIG. 3 is a diagram showing a data format of a user attribute storage unit provided on a server side of the information providing system shown in FIGS. 1 and 10;

FIG. 4 is a flowchart for explaining an information providing operation of the information providing system shown in FIG. 1;

FIG. 5 is a flowchart illustrating an operation of forming a content menu in the information providing system illustrated in FIG. 1;

FIG. 6 is a conceptual diagram of a cluster classification result in a cluster classification unit provided on a server side of the information providing system shown in FIGS. 1 and 10;

FIG. 7 is a diagram showing a display example of a content menu displayed on the terminal device side of the information providing system shown in FIGS. 1 and 10;

8 is a diagram showing a data format of a usage history storage unit provided on the server side of the information providing system shown in FIG.

9 is a diagram showing a data format of a content attribute storage unit provided on the server side of the information providing system shown in FIGS. 1 and 10. FIG.

FIG. 10 is a block diagram illustrating an overall configuration of an information providing system according to a second embodiment to which the information providing system and the information providing method according to the present invention are applied.

FIG. 11 is a flowchart showing a user registration procedure in the information providing system shown in FIG. 10;

12 is a diagram showing a data format of an evaluation information storage unit provided on the server side of the information providing system shown in FIG.

FIG. 13 is a flowchart for explaining an information providing operation of the information providing system shown in FIG. 10;

FIG. 14 is a flowchart illustrating an operation of forming a content menu in the information providing system illustrated in FIG. 10;

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Server 2 ... Terminal device 3 ... Network 11 ... Transmission / reception part 12 ... Content storage part 13 ... Content attribute storage part 14 ... User attribute storage part 15 ... Usage history storage part 16 ... Usage frequency information creation part 17 ... Score calculation part 18 Content selection unit 19 Control unit 20 Cluster classification unit

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G06F 17/60 318 G06F 17/60 318G

Claims (6)

[Claims] 1. An information providing system in which a server for providing content and a terminal device of a user are connected via a network, wherein the server identifies the content registered in content storage means. Content attribute storage means for storing the content attribute information of the content together with the identification information; and use of storing the user identification information of the user who used the content together with the content identification information indicating the content used by the user History storage means; usage frequency information forming means for forming usage frequency information representing the usage frequency of each user for each content based on the content identification information and the user identification information stored in the usage history storage means; Based on the usage frequency information formed by the usage frequency information forming means, the information A score calculating means for calculating a score for arranging each content in the content based on the similarity; Calculating a degree of relevance between each user and each of the clusters, and selecting content based on the degree of relevance; and content identification information and content attribute information of the content selected by the content selecting means. Transmitting means for reading from the content attribute storing means and transmitting to the terminal device side. 2. An information providing system in which a server for providing content and a terminal device of a user are connected via a network, wherein the server identifies the content registered in content storage means. Content attribute storage means for storing the content attribute information of the content together with the identification information, and associating an evaluation value obtained by each user who has evaluated the content with the content identification information and the user identification information for identifying each user; Evaluation information storage means for storing the content as evaluation information, a score calculation means for calculating a score for arranging each content in the information space based on the similarity based on the evaluation information, and a calculation result of the score calculation means. Cluster classification that classifies each content into clusters based on highly similar content A step, a degree of relevance between each user and each of the clusters, content selection means for selecting a content based on the degree of relevance, content identification information and content attribute information of the content selected by the content selection means Transmitting means for reading out from the content attribute storing means and transmitting the read out to the terminal device side. 3. An information providing method for providing a content from a server to a user's terminal device via a network, the content providing information indicating content used by the user, and a user using the content. The user identification information is stored as a usage history. Based on the usage history, usage frequency information indicating the usage frequency of each user for each content is formed. Based on the usage frequency information, each content is stored in an information space. Score calculating means for calculating a score to arrange based on the similarity; and, based on a result of the score calculation, classifying each content into a cluster for each content having high similarity. The relevance is calculated, the content is selected based on the relevance, and the content identification information and the content of the selected content are selected. Transmitting the Ceiling attribute information to the terminal device side, information providing method, characterized in that. 4. An information providing method for providing content from a server to a user's terminal device via a network, wherein an evaluation value obtained by each user evaluating content is used as content identification information for identifying the content. And generating evaluation information associated with user identification information for identifying each user, calculating a score for arranging each content in the information space based on the similarity based on the evaluation information, and calculating the score. Based on the result, each content is classified into clusters for each content with high similarity, the degree of relevance between each user and each cluster is calculated, and the content is selected based on the degree of relevance. An information providing method, comprising transmitting content identification information and content attribute information of a content to a terminal device side. 5. The information providing system according to claim 1, wherein the content selection unit performs a process on the selected content.
According to the calculated degree of relevance, the contents belonging to the cluster having the higher degree of relevance are ranked so as to be positioned higher, and the transmitting unit transmits the order information obtained as a result of the ranking performed by the contents selecting unit. And transmitting the content identification information and the content attribute information to the terminal device side. 6. The information providing method according to claim 3, wherein, for the content selected based on the relevance, content belonging to a cluster having a higher relevancy is ranked higher according to the relevancy. And transmitting the order information of the result of the ordering performed on the selected content to the terminal device together with the content identification information and the content attribute information of the selected content. Information provision method.