JP6028582B2 - Server apparatus, program, and communication system - Google Patents

Description

  The present invention relates to a server device, a program, and a communication system that provide services that support exchange between persons in a virtual space constructed on the Internet.

  In recent years, with the development of network technologies such as WWW (World Wide Web) and the progress of portable information communication terminal devices (hereinafter referred to as “communication terminal devices”) represented by smartphones and the like, communication in a virtual space is performed. As a tool, an Internet community represented by social networking services (hereinafter referred to as “SNS”) and electronic bulletin boards has spread, and the number of users (hereinafter referred to as “users”) has been increasing year by year.

  For example, in the virtual space on the WWW, the SNS has released and disclosed each information (hereinafter referred to as “user information”) such as personal history, face photo, hobby preference, work place, and residence area. Friends can be recruited based on user information, and it can be used as a tool to deepen exchanges between users.

  In addition, in SNS, a user can upload (post) a photograph taken by the user, a current situation, a text corresponding to a diary, etc. as content to a server device for providing the SNS so that it can be viewed by a friend or the like. In addition to being able to receive comments on the content from friends or the like.

  On the other hand, in this SNS, several to several hundred users in the SNS create a group (also referred to as “community”, hereinafter referred to as “group”), and a bulletin board unique to the group is stored in the SNS. It is also possible to create and exchange information.

  In particular, recently, the similarity of writing contents of each group is calculated on the bulletin board corresponding to each group based on the history information of writing performed by group members (that is, users belonging to the group). Supporting exchanges between groups by recommending groups to other groups (for example, Patent Document 1), or recommending groups that match hobbies and preferences included in the user information of each user to other groups (For example, patent document 2) is proposed.

JP 2003-345888 A JP 2008-242521A

  However, in the system disclosed in Patent Document 1, it is difficult to recommend another group to the group based on the preferences of individual users belonging to the group.

  Further, in the system described in Patent Document 2, since a recommendation target is determined based on user information registered in advance, it is difficult to recommend a group in accordance with user preferences or changes in the preferences.

  The present invention has been made to solve the above-described problems, and its purpose is to provide information regarding a group that matches the user's preference as recommendation information while reflecting changes in the preference of the individual user. Thus, it is to provide a server device or the like that can activate exchanges between users and promote communication between users in the SNS.

  (1) In order to solve the above-described problem, a server device according to the present invention is a server device that provides, as recommended information, information desired by a user to a communication terminal device connected via a network. Management database in which group identification information for identifying the group and information including at least user identification information corresponding to each user belonging to the group is recorded as group information in order to manage a group constituted by users Group management means for managing the content, and content data acquisition means for acquiring the user identification information from the communication terminal device, and acquiring data of content provided to the group posted by the user as a posting user, as content data; , When the content data is obtained, Based on the user's instruction and the acquired user identification information, a group specifying means for specifying a group to which the user who posted the content belongs and a group to which the content is provided as a posting target group, the acquired content data, Content management means for associating user identification information with the group identification information of the specified posting target group and recording them in a content database, and showing each user's preference based on content data posted by each user User preference information generating means for generating user preference information, and group preference information generation for generating group preference information indicating the preference of the entire group for each group, based on the content data posted by users belonging to each group Means and a specific said user The user preference information of the specific user and the group preference information of each group when receiving the recommendation information distribution request transmitted by the communication terminal device based on the request of the specific user. A similarity calculation means for calculating a similarity indicating the similarity, a recommendation group specifying means for specifying a group for which the calculated similarity satisfies a predetermined condition as a recommendation group, and information on the specified recommendation group The recommendation information includes a distribution means for distributing to the corresponding communication terminal device.

  With this configuration, when a specific user requests recommendation information, the server device according to the present invention can generate user preference information based on content data posted by each user in a timely manner. The preference of a specific user at the time of requesting recommendation information can be specified, and the preference at the time of requesting the recommendation information can also be specified in a group to be recommended, for example.

  Therefore, the server device according to the present invention can provide information regarding a recommended group that matches the user's preference as recommendation information while reflecting changes in individual user's preference and group preference. Thus, it is possible to recommend a new group, newly join the recommended group, and start a new exchange with another member belonging to the recommended group.

  As a result, the server device according to the present invention can activate AC in the SNS and promote communication between users.

  (2) In the server device according to the present invention, the similarity calculation unit calculates the similarity in the group preference information of the group to which the specific user does not belong and the user preference information. It has a configuration.

  With this configuration, the server device according to the present invention can perform the group specifying process while generating the group preference information only for the unaffiliated group, excluding the group to which the recommendation request user has already joined, While reducing the processing load, it is possible to specify a recommended group that exactly matches the posting user's preference.

  (3) Further, in the server device according to the present invention, the user preference information generating unit and the group preference information generating unit are configured to use the user preference based on an appearance frequency of a word included in a character string constituting the content data. It has the structure which produces | generates information or the said group preference information.

  With this configuration, the server device according to the present invention can use a material commonly used by SNS or the like as content, and therefore can easily and easily recommend a group that matches a specific user's preference. it can.

  (4) Moreover, when the user preference information generation unit and the group preference information generation unit receive the recommendation information distribution request, the server device according to the present invention may post by the time when the distribution request is received. The user preference information or the group preference information is generated based on the obtained content data.

  With this configuration, each time a posting user posts content data, the server device according to the present invention accumulates the content data. Therefore, while reflecting the changes in individual user preferences and group preferences, Information relating to the recommendation group that matches the user's preference can be provided as recommendation information.

  (5) Further, the server device according to the present invention has a configuration in which the content includes post information newly posted by the user and a comment provided for the posted post information. ing.

  With this configuration, when a user other than the posting user posts a comment, the server device according to the present invention can generate user preference information in consideration of the comment.

  In other words, since comments by other users include words, links, images, and the like that match the posting user's preference, the server device according to the present invention can further improve the accuracy of the user preference information. In addition, the specific accuracy of the recommendation group can be improved.

  (6) In the server device according to the present invention, the content includes an image, and the user preference information generation unit and the group preference information generation unit include a category to which a subject corresponding to the image belongs, and The user preference information or the group preference information is generated based on at least one of the character strings assigned to the image.

  With this configuration, the server device according to the present invention can accurately generate user preference information from the content even when the posting user posts an image such as a photo as the content.

  (7) Further, in order to solve the above-described problem, a program according to the present invention provides a computer system that functions as a server device that provides information desired by a user as recommended information to a communication terminal device connected via a network. In order to manage a group composed of a plurality of the users, group identification information for identifying the group and information including at least user identification information corresponding to each user belonging to the group are recorded as group information. A group management means for managing a management database, wherein the user identification information is acquired from the communication terminal device, and content data provided to the group posted by the user as a posting user is acquired as content data Acquisition means, said content Group specifying means for specifying a group to which the user who has posted the content belongs and to which the content is provided as a posting target group based on the instruction of the posting user and the acquired user identification information when the data is acquired Content management means for associating the acquired content data and user identification information with the group identification information of the specified posting target group and recording them in a content database, based on the content data posted by each user User preference information generating means for generating user preference information indicating the preference of each user, group preference information indicating the preference of the entire group based on the content data posted by users belonging to each group, for each group Generate group preference information Means, upon receiving a request for distribution of the recommendation information transmitted by the communication terminal device based on a request of a specific user who is the specific user, the user preference information of the specific user, Similarity calculation means for calculating similarity indicating the similarity of preference in group preference information, recommended group specifying means for specifying a group satisfying a predetermined condition for the calculated similarity as a recommended group, and It has the structure which functions as a delivery means to deliver the information regarding the specified recommendation group to the said communication terminal device concerned as the recommendation information.

  With this configuration, when a specific user requests recommendation information, the program according to the present invention can generate user preference information based on content data posted by each user in a timely manner. For example, the recommendation information The preference of a specific user at the time of requesting the user can be specified, and the preference at the time of requesting the recommendation information can be specified in the group to be recommended, for example.

  Therefore, the program according to the present invention can provide information regarding a recommended group that matches the user's preference as recommendation information while reflecting changes in individual user's preference and group preference. It is possible to recommend a new group, newly join the recommended group, and start a new exchange with another member belonging to the recommended group.

  As a result, the program according to the present invention can activate the exchange in the SNS and promote communication between users.

  (8) In order to solve the above-described problem, the communication system according to the present invention recommends information desired by a user to a communication terminal device connected to a network and a communication terminal device connected via the network. A server device provided as information, and the server device manages a group composed of a plurality of users, so that the group identification information for identifying the group and each of the groups belonging to the group Group management means for managing a management database in which information including at least user identification information corresponding to a user is recorded as group information, and acquiring the user identification information from the communication terminal device and posting the user as a posting user Acquire content data to be provided to the group as content data When acquiring the content data, and posting the group to which the user who posted the content belongs and to which the content is provided based on the instruction of the posting user and the acquired user identification information when the content data is acquired A group specifying means for specifying as a target group, content management means for associating the acquired content data and user identification information with the group identification information of the specified posting target group, and recording them in a content database; Based on the content data posted by the user, user preference information generating means for generating user preference information indicating the preference of each user, and on the content data posted by users belonging to each group, Group preference indicating preference The group preference information generating means for generating information for each group and the specific information when receiving the distribution request for the recommended information transmitted by the communication terminal device based on the request of the specific user who is the specific user Similarity calculation means for calculating similarity indicating preference similarity in the user preference information of the user and the group preference information of each group, and recommending a group in which the calculated similarity satisfies a predetermined condition It has a configuration comprising: a recommended group specifying unit that specifies a group; and a distribution unit that distributes information relating to the specified recommended group to the corresponding communication terminal device as the recommended information.

  With this configuration, when a specific user requests recommendation information, the communication system according to the present invention can generate user preference information based on content data posted by each user in a timely manner. The preference of a specific user at the time of requesting information can be specified, and the preference at the time of requesting the recommendation information can also be specified in the group to be recommended, for example.

  Therefore, the communication system according to the present invention can provide information regarding a recommended group that matches the user's preference as recommendation information while reflecting changes in individual user's preference and group preference. Thus, it is possible to recommend a new group, newly join the recommended group, and start a new exchange with another member belonging to the recommended group.

  As a result, the communication system according to the present invention can activate AC in the SNS and promote communication between users.

  The server device, program, and communication system according to the present invention recommend a new group to a user, newly join the recommended group, and other members belonging to the recommended group. It is possible to start new exchanges between them and activate the exchanges in the SNS to promote communication between users.

1 is a system configuration diagram showing a configuration of a communication system in an embodiment according to the present invention. It is a block diagram which shows the structure of the information provision server apparatus of one Embodiment. It is a figure which shows an example of the data recorded on the user management database provided in the information provision server apparatus of one Embodiment. It is a figure which shows an example of the data recorded on the group management database provided in the information provision server apparatus of one Embodiment. It is a figure which shows an example of the data recorded on the content data database provided in the information provision server apparatus of one Embodiment. It is a figure which shows an example of the data recorded on the user preference information database provided in the information provision server apparatus of one Embodiment. It is a figure which shows an example of the data recorded on the group preference information database provided in the information provision server apparatus of one Embodiment. It is an image figure which shows notionally the user preference information generation process performed in the information provision server apparatus of one Embodiment. It is a flowchart which shows the process performed at the time of contribution of content data in the communication system of one Embodiment. It is a flowchart which shows the process performed when providing recommendation information in the communication system of one Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following embodiments, a server device, a program, and a communication system according to the present invention are provided for a communication system having a communication terminal device and an information providing server device connected to the communication terminal device via a network. It is an embodiment in the case of applying.

[1] Communication System First, the configuration and outline of the communication system 1 according to the present embodiment will be described with reference to FIG. FIG. 1 is a system configuration diagram showing the configuration of the communication system 1 in the present embodiment. Further, in order to prevent the figure from becoming complicated, only some users are shown in FIGS. 1 and 2. That is, in the actual communication system 1, there are a larger number of users and communication terminal devices 10 than displayed.

  The communication system 1 according to the present embodiment matches a user's preference based on a user's request from a group composed of a plurality of users according to a given item (for example, hobbies, occupations, etc.) on the SNS. A system for identifying a group and providing information about the identified group as recommendation information to a user who has requested the information (hereinafter referred to as “recommendation requesting user” or “specific user”). And a system for promoting communication.

  In order to realize the above functions, the communication system 1 according to the present embodiment provides a plurality of communication terminal devices 10, a network 20, and an SNS service possessed by each SNS user as shown in FIG. 1. On the other hand, the information providing server device 30 generates recommendation information and distributes it to the corresponding communication terminal device 10.

  Each communication terminal apparatus 10 is connected to the network 20 via the base station BS. The network 20 is configured by interconnecting a public telephone network including a mobile telephone network and an IP (Internet Protocol) network, for example. However, the configuration of the network 20 is not limited to this.

  The communication terminal device 10 has a camera function and is a communication terminal device that can be carried by a user such as a portable music player, a portable game machine, a tablet information terminal device, a smartphone, or a portable telephone.

  In particular, the communication terminal apparatus 10 receives resource data for the WWW system described in a markup language such as XML (extensible Markup Language) and a unique URL (Uniform Resource Locator) indicating a network address of the resource data. While using, it has a browsing function for performing data communication with the information providing server device 30.

  In addition, the communication terminal device 10 receives resource data from the information providing server device 30 using the browsing function, and displays the content configured by the resource data so that the user can browse the base station BS and the network. The information providing server device 30 is connected to the information providing server device 30 to log in to the SNS based on the user's operation, and various data is transmitted from the information providing server device 30 as the logged-in user (hereinafter referred to as “logged-in user”). It is configured to be able to receive and provide SNS services.

  Then, when the communication terminal device 10 logs in to the SNS, the data to be posted (hereinafter referred to as “content data”) of content data including an image such as a photograph or a text corresponding to a diary or the current status. (Ie, one group specified from among the groups to which the login user belongs), as post information of the login user, or as comment information for post information of other users of the group to which the login user belongs Uploading is made to the providing server device 30.

  Further, as described above, the communication terminal device 10 receives post information, comment information, or both posted by other users of the group to which the login user belongs based on the operation of the login user during login to the SNS. Receives and allows the logged-in user to browse, download data when necessary, and share various types of information

  The information providing server device 30 is a system used to provide each SNS service, and has various databases (hereinafter also referred to as “DB”) in order to provide the SNS service. Then, the information providing server device 30 executes processing (hereinafter referred to as “posting processing”) for performing registration and recording management of content data posted by the user using the communication terminal device 10.

  In addition, when the information providing server device 30 receives a group recommendation request from a recommendation requesting user via the communication terminal device 10, the recommendation requesting user is a group to which the recommendation requesting user does not belong (hereinafter referred to as “unaffiliated group”). Then, a process (hereinafter referred to as “recommendation group identification process”) that identifies a group that matches the preference of the recommendation requesting user (hereinafter referred to as “recommendation group identification process”) is executed, and information regarding the recommendation group is recommended. The information is distributed to the communication terminal device 10 of the recommendation requesting user as information.

  In particular, in the recommendation group specifying process, the information providing server device 30 includes content data that the recommendation requesting user has posted in the past to the group to which the recommendation request user belongs, and other users (hereinafter, “comments”). Based on the comment data posted by the user)), a process for generating user preference information indicating the preference of the recommendation request user (hereinafter referred to as “user preference information generation process”) is executed and a recommendation request is made. A process of identifying all unaffiliated groups to which the user does not belong and generating group preference information indicating the overall preference of the unaffiliated group for each identified unaffiliated group (hereinafter referred to as “group preference information generation process”) ")") Is executed.

  And the information provision server apparatus 30 calculates the similarity between both based on the group preference information corresponding to each generated unaffiliated group and the user preference information corresponding to the recommendation requesting user, A non-affiliation group that satisfies a predetermined condition, such as the calculated similarity exceeding a predetermined threshold, is identified as a recommendation group that matches the preference of the recommendation requesting user, and information regarding the specified recommendation group is used as recommendation information and the recommendation requesting user To the communication terminal device 10.

  By having such a configuration, when the recommendation requesting user requests recommendation information, the communication system 1 of the present embodiment generates user preference information based on the content data posted by each user in a timely manner. Therefore, for example, it is possible to specify the preference of a specific user at the time of requesting the recommendation information, and also specify the preference at the time of requesting the recommendation information in the group to be recommended, for example. Can be done.

  Therefore, the communication system 1 according to the present embodiment can provide information regarding a recommended group that matches the user's preference as recommendation information while reflecting changes in individual user's preference and group preference. On the other hand, it is possible to recommend a new group, newly join the recommended group, and start a new exchange with other members belonging to the recommended group, and as a result, SNS It is possible to revitalize exchanges and promote communication between users.

  In particular, in the communication system 1 of the present embodiment, each time content data including comment data is posted, the comment data is accumulated. Based on the accumulated comment data, user preference information indicating the preference of the recommendation requesting user. Since group preference information indicating the preference of each group to be recommended can be generated, changes in individual user preferences and changes in group preferences can be reflected.

  In other words, each user's preference and a change in the group to which each user belongs appear in the posted content such as posted information or comment information. Therefore, the change in the preference of the user and the group is generated based on the posted content data. Will be reflected in the user preference information or group preference information.

  Therefore, in this embodiment, the user's preference when requesting the recommendation information is specified by identifying the recommendation group based on the posted content data and distributing the information related to the recommendation group as the recommendation information to the recommendation requesting user. It is possible to accurately provide information relating to a recommendation group that meets the requirements as recommendation information.

  Further, the communication system 1 according to the present embodiment employs a configuration in which a group requesting process is performed while generating group preference information only for an unaffiliated group, excluding groups to which a recommendation request user has already joined. Therefore, the recommended group can be accurately identified while reducing the amount of calculation in the information providing server device 30 and reducing the processing load on the information providing server device 30.

[2] Information Providing Server Device [2.1] Configuration of Information Providing Server Device Next, the configuration of the information providing server device 30 of the present embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing the configuration of the information providing server device 30 of this embodiment.

  As shown in FIG. 2, the server device 30 of the present embodiment includes a communication control unit 310 connected to the network 20, a ROM / RAM 320 functioning as various memories, a recording device 330 having various DBs, and a device Recommend to recommendation requesting user while performing group management process including server management control unit 340 that controls the whole, process for creating a group, posting process, user preference information generation process and group preference information generation process A data processing unit 350 that supplies (distributes) information.

  The above-described units are connected to each other by a bus B, and data transfer is performed between the components.

  The communication control unit 310 is a predetermined network interface, establishes a communication channel with the communication terminal device 10, and exchanges various data.

  Various programs necessary for driving the server device 30 are recorded in the ROM / RAM 320. The ROM / RAM 320 is used as a work area when various processes are executed.

  The recording device 330 is configured by an HDD or an SSD (Solid State Drive). The recording device 330 includes at least a user management DB 331, a group management DB 332, a content data DB 333, a user preference information DB 334, a group preference information DB 335, and a dictionary DB 336.

  Note that the user management DB 331 and the group management DB 332 of this embodiment constitute a management database of the present invention, and the content data DB 333 constitutes a content database of the present invention. Details of the recording apparatus 330 of this embodiment will be described later.

  The server management control unit 340 is mainly configured by a central processing unit (CPU), and integrally controls each unit of the information providing server device 30 by executing a program.

  When the data processing unit 350 obtains a login request based on a user instruction from the communication terminal device 10 in conjunction with the recording device 330 under the control of the server management control unit 340, the data processing unit 350 receives each user's SNS based on the request. The log-in process is executed, and the post-process for registering content data including post information and comment information posted by the logged-in user and managing recording of the content data in each database is executed.

  In addition, when receiving a recommendation request from the communication terminal device 10, the data processing unit 350 executes group specifying processing including user preference information generation processing and group preference information generation processing, and sends recommendation information to the corresponding communication terminal device 10. Execute processing for distribution.

  Specifically, the data processing unit 350 executes a posting process by executing an application in order to execute the above-described processes, and manages DBs provided in the recording device 330. 351, a user preference information generation unit 352 that executes a user preference information generation process, a group preference information generation unit 353 that executes a group preference information generation process, and the similarity between the user preference information and the user preference information Meanwhile, a similarity calculation unit 354 that identifies a group that matches the preference of the recommendation requesting user as a recommendation group, and generates recommendation information based on the specified recommendation group information, and distributes the recommendation information to the communication terminal device 10 of the recommendation requesting user. The recommendation information generation / distribution unit 355 is realized.

  For example, the DB management unit 351 of this embodiment constitutes a group management unit, a content data acquisition unit, a group identification unit, and a content management unit of the present invention, and the user preference information generation unit 352 User preference information generating means is configured. Further, for example, the group preference information generation unit 353 of the present embodiment constitutes a group preference information generation unit of the present invention. Furthermore, details of the data processing unit 350 of the present embodiment will be described later.

[2.2] Recording Device Next, details of the recording device 330 of this embodiment will be described with reference to FIGS. 3 is a diagram illustrating an example of data recorded in the user management DB 331 of the present embodiment, and FIG. 4 is a diagram illustrating an example of data recorded in the group management DB 332 of the present embodiment. FIG. 5 is a diagram illustrating an example of data recorded in the content data DB 333 of the present embodiment, and FIG. 6 is a diagram illustrating an example of data recorded in the user preference information DB 334 of the present embodiment. . Furthermore, FIG. 7 is a diagram illustrating an example of data recorded in the group preference information DB 335 of the present embodiment.

The user management DB 331 is a database in which information for managing each user who has registered for use of the SNS is stored as data. As illustrated in FIG.
(1) a user ID corresponding to each user;
(2) a group ID corresponding to the group to which the user belongs (hereinafter referred to as “belonging group ID”);
(3) user information indicating the attributes of the user (for example, gender age and address);
Are registered (recorded) in association with each other.

The group management DB 332 is a database for managing the created group in the SNS. As illustrated in FIG.
(1) a group ID corresponding to each group;
(2) a user ID of a user belonging to the group (hereinafter referred to as “affiliated user ID”);
(3) Group information including group attributes such as group name, group introduction, membership requirements, etc.
Are registered in association with each other.

For example, in the case illustrated in FIG. 4, a state where users corresponding to the user IDs “U001”, “U002”, “U003”, and “U004” belong to the group specified by the group ID “GR001”. Show. In the case of FIG. 4, as group information of the group corresponding to “GR001”,
(A) Group name: Sweets love (b) Group introduction: Sweets like information exchange group.
(C) Subscription requirement: This indicates a state where sweet favorite information is recorded.

The content data DB 333 is a database for recording and managing content data posted by a user and comment data. As illustrated in FIG.
(1) a user ID (hereinafter also referred to as “posting user ID”) of a user who posted content (hereinafter referred to as “posting user”);
(2) a group ID corresponding to a group to which the posting user has posted posting information (hereinafter also referred to as “posting group ID”);
(3) Posting information body posted by the posting user (that is, content data);
(4) Comment information of other users (hereinafter also referred to as “comment users”) and user IDs of comment users (hereinafter referred to as “comment user IDs”) for posted information;
Are recorded in association with each other.

  In the present embodiment, unlike the comment information freely described by the comment user for each post information, by selecting a predetermined comment “Like”, the information (that is, information on the number of selections (hereinafter referred to as “the number of selections”) , Also referred to as “standard comment information”)))). In the present embodiment, the content data DB 333 does not register the user ID for the standard comment information but records only the selection count information. However, the user ID of the comment user who selected the standard comment information is also recorded. It may be recorded.

  For example, in the case illustrated in FIG. 5, a user having a user ID “U001” has “Data001” as a posting user for two groups having group IDs “GR001” and “GR002”. In addition, two content data “Data002” are posted and the content data is recorded in the content data DB 333.

  In the case illustrated in FIG. 5, for example, for “Data001”, the user “U002” posts comment data including a comment sentence “Nice cafe” as a comment user, and “U003” The user “” has posted comment data including a comment sentence “Sweets here!” As a comment user.

  Further, in the case illustrated in FIG. 5, the content data “Data001” is “liked” by another user 50 times and the numerical value “50” is stored.

  The user preference information DB 334 is a database for recording and managing generated user preference information when the data processing unit 350 executes user preference information generation processing. For example, in the user preference information DB 334, as shown in FIG. 6, the user preference information generated by the data processing unit 350 executing the user preference information generation process and the user ID of the user corresponding to the user preference information Are recorded in association with each other.

  In the case illustrated in FIG. 6, the following information is stored as the user preference information of the user corresponding to the user IDs “U001” and “U002”.

<For users of “U001”>
“Sweets” = “2”
“Cafe” = “2”
"Cake" = "1"
"Waffle" = "1"
"Asian" = "1"
"Modern" = "1"
"Interior" = "3"

<For users of “U002”>
“Cafe” = “5”
“Chinese Chinese” = “2”
"Four leaves" = "1"
"Clover" = "1"
"Nature" = "1"
"Nice" = "1"
"Women's Association" = "1"

  The user preference information is generated for the recommendation requesting user when a group recommendation request is made, and is sequentially recorded and accumulated in the user preference information DB 334 in the order of generation. In FIG. 6, the number associated with each word indicates the number of appearances of the corresponding word calculated when the user preference information generation process is executed. Furthermore, the user preference information generation process in the present embodiment will be described in detail later.

  The group preference information DB 335 is a database for recording and managing group preference information generated by the data processing unit 350 of the information providing server device 30. For example, in the user preference information DB 334, group preference information corresponding to each group is recorded in association with the corresponding group ID, as shown in FIG.

  For example, when group information as illustrated in FIG. 4 is recorded in the group management DB 332 and the group preference generation process is executed for the group 1, the user IDs “U001” to “U” are stored in the group preference information DB 335. Group preference information corresponding to “GR1” generated based on the content data posted by the user corresponding to “U003” is recorded.

  The group preference information is generated based on the posted information and comment information posted by all users belonging to each group, as with the user preference information, and calculated when the group preference information generation process is executed. Indicates the number of occurrences of the corresponding word. However, group preference information and user preference information differ in reference data.

  The dictionary DB 336 is a DB in which various dictionaries for use in the user preference information generation process and the group preference information generation process are registered.

  In particular, in this embodiment, the dictionary DB 336 includes, for example, “te”, “ni”, “wo”, “ha”, “me”, “me”, “you”, “today”, “yesterday”, “tomorrow”. General sentences for excluding words such as general nouns, conjunctions, particles / auxiliary verbs / utilized endings (hereinafter referred to as “general words”), which are less likely to indicate user preference, from the content data A word dictionary is recorded.

[2.3] Data Processing Unit Next, the data processing unit 350 of the present embodiment will be described with reference to FIG. FIG. 8 is an image diagram conceptually showing user preference information generation processing executed when user preference information is generated in the present embodiment.

  The DB management unit 351, in conjunction with each communication terminal device 10, also executes SNS login management and login state management. In particular, the DB management unit 351, based on the login request to the SNS transmitted from the communication terminal device 10, associates the user ID corresponding to the user of the communication terminal device 10 with the group ID recorded in the user management DB 331. And various processes for logging in to the SNS and maintaining the state thereof are executed.

  The DB management unit 351 also records (reads and updates) each data in the user management DB 331, the group management DB 332, the content data DB 333, the user preference information DB 334, and the group preference information DB 335, and the communication terminal of the read and read data. Manage the provision to the device 10.

  In particular, the DB management unit 351, when posting information is posted (uploaded) as content data while specifying a posting target group from the communication terminal device 10 in the login state, or comment information for the posted information. Is posted as content data, various content data are registered in the content data DB 333, and a posting process for performing various recording management processes is executed.

  Further, as will be described later, when the group specifying process including the user preference information generation process and the group preference information generation process is executed, the DB management unit 351 generates the user preference information and the group preference information. The generated user preference information is recorded in the user preference information DB 334, and the group preference information is recorded in the group preference information DB 335.

  When the recommendation request transmitted from the communication terminal device 10 is received by the communication control unit 310, the user preference information generation unit 352 executes a user preference information generation process.

  Specifically, the user preference information generation unit 352 reads all the content data of post information and comment information posted by the user who made the recommendation request recorded in the content data DB 333. Then, the user preference information generation unit 352 extracts all text clauses and phrases included in the read content data, performs morphological analysis on the extracted clauses and phrases, and includes them in the clauses and phrases. Identify the words

  Further, the user preference information generation unit 352 extracts only words that are not included in the general word dictionary stored in the dictionary DB 336, and user preference information, that is, post information and comment information, based on the extracted words. Information consisting of the word that is the main topic of and the number of occurrences of the word is generated as user preference information

  When the recommendation request transmitted from the communication terminal device 10 is received by the communication control unit 310, the group preference information generation unit 353 displays the group ID in which the recommendation request user does not belong to the group ID stored in the user management DB 331. And the group preference information generation process is executed for each identified group.

  Specifically, the group preference information generating unit 353 reads the content data of posted information and comment information posted for each unaffiliated group recorded in the content data DB 333. Then, the group preference information generation unit 353 extracts all text clauses and phrases included in the read content data, and performs morphological analysis on the extracted clauses and phrases as in the user preference information generation process. Execute and identify the words contained in the phrase and phrase.

  In addition, the group preference information generation unit 353 removes general words from the identified words, as in the user preference information generation processing, and the words that are the central topics of the posting information and comment information, and Information composed of the number of appearances of the word is generated as group preference information.

  The similarity calculation unit 354 generates user preference information when the recommendation request transmitted from the communication terminal device 10 is received by the communication control unit 310 and the user preference information generation process and the group preference information generation process are executed. Based on the user preference information of the recommendation request user generated by the process and the group preference information in each unaffiliated group to which the recommendation request user generated by the user preference information generation process does not belong, TF-IDF (Term Frequency- While calculating each value of (Inverse Document Frequency), an unaffiliated group similar to the preference of the recommendation requesting user is specified.

  Specifically, as shown in (Formula 1), the similarity calculation unit 354 calculates each value of TF-IDF based on the number of appearances of words included in the user preference information of the recommendation requesting user. That is, the similarity calculation unit 354 calculates the number of appearances in all content data for each word (Keym) included in the content data including all post information and comment information recorded in the content data DB 333, except for general words. A vector A of the product Key (TF / IDF) of the reciprocal Keym (IDF) and the appearance frequency Keym (TF) of the word included in the user preference information is calculated.

In (Expression 1), “key _m ” on the left side indicates a word, and the subscript “m” is an identification ID (for example, a number or alphabet) assigned to each word. Also, “t” on the left side indicates the number of appearances of each word.

  For example, as shown in FIG. 8, the posting user has image data of a photograph of a four-leaf clover, and “Today, when I went to the mountain, I found a four-leaf clover by chance! Posting information that includes text data such as “It's nice!” Is posted to a given group, and comment users belonging to that group say, “It ’s nice! There seems to be something good!” An example of a state in which comment information is posted.

  In this case, as shown in FIG. 8, “Today” is once in the posting information and comment information (the number of applications included in all content data is “o”), and “Mountain” is once (all contents). The number of applications included in the data is “p”, “coincidence” is 1 time (the number of applications included in all content data is “q”), and “four leaves” is 1 time (included in all content data) The number of applications is “r”), “Clover” is 1 time (the number of applications included in all content data is “u”), and “Nature” is 1 time (the number of applications included in all content data is “v”) ), “Nice” has appeared twice (the number of applications included in all content data is “w”), so the user preference information generation unit 352 excludes “today” as a general word, According to Equation 1, user preference information (mountain, Deer, four-leaf, clover, nature, nice) = (1 / o, 1 / p, 1 / q, 1 / r, 1 / u, 1 / v, 2 / w) made to generate vector data.

  Moreover, as shown in (Formula 2), the similarity calculation unit 354 calculates each value of TF-IDF based on the number of appearances of the word included in the group preference information in the unaffiliated group to which the recommendation request user does not belong. To do. That is, the similarity calculation unit 354 calculates the number of appearances in all content data for each word (Keym) included in the content data including all post information and comment information recorded in the content data DB 333, except for general words. Each vector Bn of the product Key (TF / IDF) of the reciprocal Keym (IDF) and the appearance frequency Keym (TF) of the word included in each group preference information is calculated.

“N” indicates a serial number (identification number) of an unaffiliated group. Similarly to (Expression 1), “key _n ” on the left side in (Expression 2) indicates a word, The letter “n” is an identification ID (for example, a number or alphabet) assigned to each word. Also, “Sn” on the left side indicates the number of appearances of each word.

  Then, the similarity calculation unit 354 calculates the similarity between the recommendation requesting user value and each unaffiliated group value based on the distance in the vector space. That is, the similarity calculation unit 368 calculates the cosine similarity sim by (Equation 3) for the vector A indicating the preference of the recommendation requesting user and each vector Bn indicating the preference of each unaffiliated group. In (Expression 3), “n” indicates an identification number of an unaffiliated group.

  In particular, the similarity calculation unit 354 specifies an unaffiliated group in which the calculated similarity “sim” exceeds a predetermined threshold α, and in order from the unaffiliated group in descending order of similarity, for example, Three groups from the top are identified as recommended groups.

  In the present embodiment, the similarity calculation unit 368 calculates the similarity between the recommendation requesting user and each unaffiliated group using the cosine similarity according to (Equation 3) while using TF-IDF. However, the present invention is not limited to this method, and other methods such as Pearson correlation may be used.

  The recommendation information generation unit 356 is linked with the DB management unit 351, reads group information corresponding to the recommendation group identified by the similarity calculation unit 354 from the group management DB 331, and recommends information based on the read group information. (For example, data in XML format) is generated, the recommendation information is supplied to the communication control unit 310, and is distributed to the communication terminal device 10 of the recommendation requesting user.

[3] Operation of Communication System Next, specific processing executed in the communication system of the present embodiment will be described with reference to FIGS. 9 and 10. In each of the following operations, the usage registration method to the SNS is the same as that of the conventional SNS, and thus the description thereof is omitted.

[3.1] Posting process of content data including post information and comment information First, operation of a post process of content data including post information and comment information executed in the communication system 1 of the present embodiment with reference to FIG. Will be described. FIG. 9 is a flowchart showing an operation of posting content data including post information and comment information executed in the communication system 1 of the present embodiment.

  Prior to this process, each user is in a state where SNS use registration has been completed, that is, various types of information have been registered in the user management DB 341, a group on the SNS has been created, and a group management DB 342 has been created. It is assumed that various data has already been stored.

  Moreover, in the communication terminal device 10, the application for logging in to SNS based on a user's instruction | indication shall be starting, and the login instruction | indication by a user is displayed, displaying the screen which prompts the user to log in to SNS It is assumed that it is in a state waiting for input.

  First, when the communication terminal device 10 acquires the user ID or account name and password input by the user (step Sa100), the communication terminal device 10 provides the login request with the input user ID and the like using the browser function. It transmits to the server apparatus 30 and shifts to a reception standby state (step Sa101).

  Next, in the information providing server device 30, when the communication control unit 310 receives the login request (step Sa200), the DB management unit 351 extracts the user ID included in the login request and associates it with the user ID. Then, the group ID recorded in the user management DB 341 and the group information (such as the group ID of the group to which the user has belonged) are read (step Sa201).

  Next, the DB management unit 351 generates data indicating a list of groups to which a user who has made a login request belongs based on the read group information (hereinafter referred to as “group list data”), and the generated group The list data is transmitted to the corresponding communication terminal device 10 to shift to the reception standby state (step Sa202).

  Next, when the communication terminal apparatus 10 receives the group list data transmitted from the information providing server apparatus 30 (step Sa102), the user can browse the list of groups to which the user of the own device belongs according to the received group list data. It is displayed (step Sa103).

  Next, when the communication terminal device 10 detects selection of one group by the user's operation (step Sa104), the communication terminal device 10 identifies a group ID corresponding to the group, and a photograph is taken by the user or corresponds to a diary or the like. Then, various processes (hereinafter also referred to as “content data reception process”) for receiving input of content of post information or comment information by the user such as text input are executed (step Sa105).

  At this time, the communication terminal device 10 can be viewed by the user while receiving the posted information posted in the group specified in conjunction with the information providing server device 30 or the posted information including the comment information. It may be displayed.

  Next, when the communication terminal apparatus 10 detects content input together with the type of post information or comment information (hereinafter also referred to as “comment type”) (step Sa106), it generates content data based on the detected input. (Step Sa107).

  Next, the communication terminal device 10 includes, in the generated content data, a group ID of a group selected and specified by the user, a user ID of a logged-in user (as a posting user or a comment user), a comment type, and comment information Is added with various necessary information for identifying the corresponding posted information and transmitted to the information providing server device 30 (step Sa108), and this operation is terminated.

  On the other hand, in the information providing server device 30, when the communication control unit 310 receives the content data (step Sa203), the DB management unit 351, the group ID added to the received content data, the content type, the login user ID, the posting The associated content data is associated and recorded in the content data DB 333 (step Sa204), and the process is terminated.

  In the present embodiment, content data is posted sequentially by each user, the posted content is stored in the content data DB 333, and is disclosed and shared among users belonging to the posting group. Become.

[3.2] Operation at the time of providing recommendation information Next, an operation of a process for providing recommendation information including a recommendation group specifying process executed in the communication system 1 of the present embodiment will be described with reference to FIG. FIG. 10 is a flowchart showing an operation of a process for providing recommendation information including a recommendation group specifying process executed in the communication system 1 of the present embodiment.

  In this operation, it is assumed that registration (recording) of content data and comment data in the content data DB 333 and registration of various data in the user management DB 331 and the group management DB 332 have been completed. The start timing of this operation is arbitrary, and may be executed following the content data posting process described above.

  In the present embodiment, in order to clarify the description, it is assumed that the process in FIG. 10 starts at a timing desired by the user. Further, since this operation needs to be executed in a state where the user is logged in to the SNS, it is assumed that a predetermined application is activated and the user is logged in to the SNS.

  First, when the communication terminal device 10 detects an input for instructing transmission of a recommendation request based on a user operation (step Sb100), the communication terminal device 10 adds a user ID and transmits the recommendation request to the information providing server device 30 and receives it. The process shifts to a standby state (step Sb101).

  Next, in the information providing server device 30, when the communication control unit 310 receives the recommendation request transmitted from the communication terminal device 10 (step Sb200), the DB management unit 351 extracts the user ID added to the recommendation request. At the same time, based on the extracted user ID, all unaffiliated groups to which the user has not yet joined are specified (step Sb201).

  Specifically, the DB management unit 351 searches the user management DB 331 based on the extracted user ID, specifies the group ID stored in association with the user ID, and other than the specified group ID. A group having a group ID is identified as an unaffiliated group.

  At this time, the DB management unit 351 searches the group management DB 332 based on the extracted user ID, specifies the group ID corresponding to the specified unaffiliated group, and stores the group information having the specified group ID as In association with the extracted user ID (that is, the user ID of the recommendation requesting user), it is temporarily recorded in the ROM / RAM 320 (step Sb202).

  Next, the user preference information generation unit 342 searches the content data DB 333 based on the recommendation request user ID recorded in the ROM / RAM 320 and stores the content data DB 333 including the posting information of the recommendation request user and comment information. All recorded content data is read, and user preference information corresponding to the recommendation requesting user is generated (step Sb203).

  Next, for each unaffiliated group, the group preference information generation unit 353 reads all content data including posted information and comment information posted to the unaffiliated group and recorded in the content data DB 333. Group preference information corresponding to the group is generated (step Sb204).

  Next, the similarity calculation unit 354 calculates the similarity according to (Expression 1) to (Expression 3) based on the generated user preference information and the group preference information in each unaffiliated group (step Sb205).

  Next, the similarity calculation unit 354 compares each calculated similarity with a predetermined threshold value α, and the upper predetermined number (for example, three) unaffiliated groups that exceed the threshold value α and have the highest similarity. Is identified as a recommended group (step Sb206).

  Next, the recommendation information generation / distribution unit 356 reads the group ID and group information corresponding to the specified recommendation group from the group management DB 342, and generates recommendation information based on the group information and the like (step Sb207). ). For example, the recommendation information generation / distribution unit 356 generates data in XML format having information such as the group name of the recommended group, the group introduction, the users belonging to the group, and the subscription requirements based on the read group information.

  Next, the recommendation information generation / distribution unit 356 distributes it to the corresponding communication terminal device 10 (step Sb208), and ends this operation.

  On the other hand, when receiving the recommendation information transmitted from the information providing server device 30 (step Sb102), the communication terminal device 10 executes display processing based on the received recommendation information (step Sb103) and ends this operation. .

  In addition, in the state where the recommended group is displayed in the communication terminal device 10, the recommended user can designate a predetermined group and participate in the group, but for new participation in the group, Since it is the same as that of the conventional SNS, details are omitted.

[4] Modification [4.1] Modification 1
In the above embodiment, a configuration is adopted in which user preference information and group preference information are generated based on the number of appearances of words included in a character string (sentence) included in content data of post information and comment information. The character string may indicate a URL.

  In this case, the user preference information and the group preference information are generated based on the number of words appearing in the character string included in the resource data indicated by the URL.

[4.2] Modification 2
In the above embodiment, when image data is included in content data and comment data, or a character string included in content data and comment data indicates a URL, and resource data indicated by the URL When image data is included, user preference information and group preference information may be generated based on the image data.

  In this case, image recognition processing is performed on the image data included in the content data, the contour of the subject is extracted, and pattern matching is performed by a method such as comparing the contour with a template prepared in advance to identify the subject. Then, the user preference information indicating the appearance frequency of the genre of the subject (for example, flowers) or group preference information may be generated to calculate the similarity.

  In addition, when a title or a file name is attached to the image data, user preference information or the like may be generated based on text included in the title or file name.

  Furthermore, among the images included in the content data and comment data, the last posted image is considered to best indicate the current preference of the user, so the latest posted image is specified, For the group, the latest posted image may be specified, and the image similarity between the two images may be calculated using a color space vector based on the difference between the images.

[4.3] Modification 3
In the above embodiment, the information providing server device 30 is configured to hold various DBs. However, each DB may be managed and operated by a different computer system.

[4.4] Modification 4
In the above-described embodiment, a predetermined number is specified as a recommendation group from the one with the highest similarity, and the recommendation information for recommending only the group is generated. However, the recommendation information is generated in the ranking format. Also good.

[4.5] Modification 5
In the above embodiment, a program for realizing the function of the information providing server device 30, downloaded from the network 20, or recorded on a recording medium such as a CD, DVD, or USB memory, and distributed. it can.

[4.6] Modification 6
In the above-described embodiment, user preference information and group preference information are generated based on all content data. However, since the user preference information generation processing and group preference information generation processing are executed based on a recommendation request, the past 1 Each process may be executed based on content data of a predetermined period such as a year.

  In this case, since the user preference information and the group preference information remarkably represent the user preference and the group preference at the time of the request for recommendation, it is possible to recommend a group that exactly matches the user preference.

  As described above, in the communication system 1 of the present embodiment, the posted information posted by the logged-in user and the comment information posted by other users belonging to the group to which the user belongs are stored in the content data DB 333 as content data. At the same time, when a group recommendation request is received from the recommendation requesting user via the communication terminal device 10, the information providing server device 30 executes a recommendation group specifying process, and communication of the recommendation requesting user with the information regarding the recommendation group as recommendation information. The data is distributed to the terminal device 10.

  Therefore, the communication system 1 according to the present embodiment can provide information regarding a recommended group that matches the user's preference as recommendation information while reflecting changes in individual user's preference and group preference. On the other hand, it is possible to recommend a new group, newly join the recommended group, and start a new exchange with other members belonging to the recommended group, and as a result, SNS The communication between users can be activated and communication between users can be promoted.

  In particular, the communication system 1 according to the present embodiment accumulates data every time content data including comment data is posted. Based on the accumulated data, the user preference information indicating the preference of the recommendation requesting user and the recommendation preference are stored. Since group preference information indicating the preference of each target group can be generated, changes in individual user preferences and changes in group preferences can be reflected.

DESCRIPTION OF SYMBOLS 1 ... Communication system 10 ... Communication terminal device 30 ... Information provision server device 310 ... Communication control part 320 ... ROM / RAM
330 ... Recording device 331 ... User management DB
332 ... Group management DB
333 ... Content data DB
334 ... User preference information DB
335 ... Group preference information DB
336 ... Dictionary DB
340 ... Server management control unit DB
350 ... Data processing unit 351 ... DB management unit 352 ... User preference information generation unit 353 ... Group preference information generation unit 354 ... Similarity calculation unit 355 ... Recommended group identification unit 356 ... Recommended information generation / distribution unit

Claims (8)

A server device that provides information desired by a user as recommendation information to a communication terminal device connected via a network,
In order to manage a group composed of a plurality of users, group identification information for identifying the group and information including at least user identification information corresponding to each user belonging to the group are recorded as group information. A group management means for managing the management database;
Content data acquisition means for acquiring, as content data, content data provided to the group posted by the user as a posting user, while acquiring the user identification information from the communication terminal device;
A group that identifies a group to which a user who has posted the content belongs and to which the content is provided as a posting target group based on the instruction of the posting user and the acquired user identification information when the content data is acquired Specific means,
Based on the acquired content data and user identification information, the content management means for associating the group identification information of the specified posting target group with the content database and the content data posted by each user, User preference information generating means for generating user preference information indicating the preference of each user;
Based on the content data posted by users belonging to each group, group preference information generating means for generating group preference information indicating the preference of the entire group for each group;
When receiving the recommendation information distribution request transmitted by the communication terminal device based on the request of the specific user who is the specific user, the user preference information of the specific user and the group preference of each group Information and a similarity calculation means for calculating a similarity indicating the similarity of the preference,
A recommended group specifying means for specifying a group in which the calculated similarity satisfies a predetermined condition as a recommended group;
Distribution means for distributing information relating to the specified recommendation group as the recommendation information to the corresponding communication terminal device;
A server device comprising: The server device according to claim 1,
The server apparatus in which the similarity calculation means calculates the similarity in the group preference information of the group to which the specific user does not belong and the user preference information. In the server apparatus according to claim 1 or 2,
The server device in which the user preference information generation unit and the group preference information generation unit generate the user preference information or the group preference information based on the appearance frequency of words included in a character string constituting the content data. In the server apparatus according to any one of claims 1 to 3,
When the user preference information generation unit and the group preference information generation unit receive the distribution request for the recommendation information, based on the content data posted up to the time when the distribution request is received, the user preference information or A server device that generates the group preference information. In the server apparatus according to any one of claims 1 to 4,
The server device, wherein the content includes post information newly posted by the user and a comment provided for the posted post information. In the server apparatus according to any one of claims 1 to 5,
The content includes an image,
The user preference information generating means and the group preference information generating means are
A server device that generates the user preference information or the group preference information based on at least one of a category to which a subject corresponding to the image belongs and a character string assigned to the image. A computer system that functions as a server device that provides information desired by a user as recommendation information to a communication terminal device connected via a network,
In order to manage a group composed of a plurality of users, group identification information for identifying the group and information including at least user identification information corresponding to each user belonging to the group are recorded as group information. Group management means for managing the management database
Content data acquisition means for acquiring, as content data, content data provided to the group posted by the user as a posting user, while acquiring the user identification information from the communication terminal device;
A group that identifies a group to which a user who has posted the content belongs and to which the content is provided as a posting target group based on the instruction of the posting user and the acquired user identification information when the content data is acquired Specific means,
Based on the acquired content data and user identification information, the content management means for associating the group identification information of the specified posting target group with the content database and the content data posted by each user, User preference information generating means for generating user preference information indicating the preference of each user;
Group preference information generating means for generating, for each group, group preference information indicating the preference of the entire group based on the content data posted by users belonging to each group;
When receiving the recommendation information distribution request transmitted by the communication terminal device based on the request of the specific user who is the specific user, the user preference information of the specific user and the group preference of each group A similarity calculation means for calculating a similarity indicating the similarity of the information and the preference,
A recommended group specifying means for specifying, as a recommended group, a group in which the calculated similarity satisfies a predetermined condition;
Distribution means for distributing information relating to the specified recommendation group as the recommendation information to the corresponding communication terminal device;
A program characterized by functioning as A communication terminal connected to the network, and
A server device that provides information desired by the user as recommended information to the communication terminal device connected via the network,
The server device is
In order to manage a group composed of a plurality of users, group identification information for identifying the group and information including at least user identification information corresponding to each user belonging to the group are recorded as group information. A group management means for managing the management database;
Content data acquisition means for acquiring, as content data, content data provided to the group posted by the user as a posting user, while acquiring the user identification information from the communication terminal device;
A group that identifies a group to which a user who has posted the content belongs and to which the content is provided as a posting target group based on the instruction of the posting user and the acquired user identification information when the content data is acquired Specific means,
Based on the acquired content data and user identification information, the content management means for associating the group identification information of the specified posting target group with the content database and the content data posted by each user, User preference information generating means for generating user preference information indicating the preference of each user;
Based on the content data posted by users belonging to each group, group preference information generating means for generating group preference information indicating the preference of the entire group for each group;
When receiving the recommendation information distribution request transmitted by the communication terminal device based on the request of the specific user who is the specific user, the user preference information of the specific user and the group preference of each group Information and a similarity calculation means for calculating a similarity indicating the similarity of the preference,
A recommended group specifying means for specifying a group in which the calculated similarity satisfies a predetermined condition as a recommended group;
Distribution means for distributing information relating to the specified recommendation group as the recommendation information to the corresponding communication terminal device;
A communication system comprising: