Information spreading assistance system and information spreading assistance method

Abstract

The present invention increases the content spreading effect in a communication network. A content spreading assistance system stores community information, which is information about a plurality of communities formed through a communication network, spreading effect calculation information, which is information for use in calculating the spreading effect for content in the communication network, and information about relevant communities, which are communities having relevance to recommended content that is content intended to be spread through the communication network, identifies an influencer in each of the relevant communities, selects, as a participation-recommended community, a community in which the spreading effect for the recommended content is greater than or equal to a predetermined first threshold when the influencer in the relevant community participates, and generates, as spreading assistance information, information that urges the influencer to participate in the participation-recommended community.

Description

Information diffusion support system and information diffusion support method

[0001] The present invention relates to an information diffusion support system and an information diffusion support method.

[0002] This application claims priority to Japanese Patent Application No. 2024-104059, filed June 27, 2024, the entire disclosure of which is incorporated herein by reference. Organizations such as companies and government agencies have introduced systems for disseminating and sharing information via their internal communication networks. In these organizations, information that contributes to improving organizational strength is actively spread within the organization, for example, by disseminating content that is highly effective for organizational members through influential members. Furthermore, for example, organizations such as companies that sell or provide content (products, services, etc.) via the Internet actively disseminate (advertise) information about the content through influencers in communities formed on social networking services (SNS).

[0003] Regarding information dissemination via influencers, Patent Literature 1 describes a technology in which a computer displays advertisements to members of a network. The computer determines an influence score for each member of a community by determining the change between the community weight when the member is included in the community and the community weight when the member is excluded from the community. The computer ranks each of the multiple members included in the community based on the member's influence score. The computer displays advertisements on the profiles of multiple influencers who are members of the community with the highest rank. The computer determines the number of advertisements to be displayed on the influencer's profile depending on the influencer's rank in the community.

[0004] Special Publication No. 2010-515160

[0005] In Patent Document 1, influencers whose profiles will display advertisements are determined based on an influence score, which is a static indicator obtained by determining the change between the weight of a community when a member is included in the community and the weight of the community when the member is excluded from the community.

[0006] However, Patent Document 1 does not take into consideration the effect of spreading information when, for example, it is assumed that influencers in the community are actively approached to spread information.

[0007] The present invention has been made in light of the above background, and has as its object to provide an information diffusion support system and an information diffusion support method that can increase the diffusion effect of content in a communication network.

[0008] One aspect of the present invention for achieving the above-mentioned object is a content diffusion support system that is configured using an information processing device having a processor and a storage device, and stores community information, which is information about a plurality of communities formed via a communication network, diffusion effect calculation information, which is information used to calculate the diffusion effect of content in the communication network, and related communities, which are communities related to recommended content, which is content to be diffused in the communication network, identifies influencers in each of the related communities, selects as recommended communities those communities in which the diffusion effect of the recommended content will be equal to or greater than a predetermined threshold when an influencer of the related community participates, and generates diffusion support information that encourages the influencer to join the recommended community.

[0009] Other problems and solutions disclosed in the present application will be made clear in the detailed description and drawings.

[0010] According to the present invention, it is possible to increase the effectiveness of disseminating content in a communication network.

[0011] 1 is a conceptual diagram illustrating main functions of a support system according to a first embodiment. FIG. 1 is a diagram illustrating a schematic configuration of the support system according to the first embodiment. FIG. 2 is a diagram illustrating main functions provided in a support device according to the first embodiment. FIG. 3 is a diagram illustrating main functions provided in an administrator device according to the first embodiment. FIG. 4 is a diagram illustrating main functions provided in a user device according to the first embodiment. FIG. 5 is a diagram illustrating an example of community information. FIG. 6 is a diagram illustrating an example of recommended content information. FIG. 7 is a diagram illustrating an example of diffusion effect calculation information. FIG. 8 is a diagram illustrating an example of diffusion effect estimate information. FIG. 9 is a diagram illustrating an example of a recommended participation community. FIG. 10 is a flowchart illustrating diffusion support processing according to the first embodiment. FIG. 11 is an example of a diffusion support information presentation screen according to the first embodiment. FIG. 12 is an example of an email sent when notifying influencers of related communities of a recommended participation community according to the first embodiment. FIG. 13 is a conceptual diagram illustrating main functions of a support system according to a second embodiment. FIG. 14 is a diagram illustrating a schematic configuration of the support system according to the second embodiment. FIG. 15 is a diagram illustrating main functions provided in a support device according to the second embodiment. FIG. 16 is a diagram illustrating main functions provided in an administrator device according to the second embodiment. FIG. 17 is a diagram illustrating main functions provided in a user device according to the second embodiment. FIG. 18 is a diagram illustrating an example of diffusion effect estimate information according to the second embodiment. FIG. 19 is a diagram illustrating an example of a recommended participation community according to the second embodiment. 10 is an example of a diffusion support information presentation screen in the second embodiment. 11 is an example of an email sent when notifying influencers of related communities of a recommended community to join in the second embodiment. 12 is an example of an information processing device used in configuring the support system of the first or second embodiment.

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings as appropriate. The following description and drawings are examples for explaining the present invention, and some omissions and simplifications have been made as appropriate for clarity of explanation. The present invention can also be implemented in various other forms. Unless otherwise specified, each component may be singular or plural.

[0013] In addition, in the following description, the same or similar components may be denoted by the same reference numerals, and redundant description may be omitted.

[0014] In the following description, the letter "S" added before a reference numeral means a processing step.

[0015] In addition, in the following explanation, various types of information may be described using expressions such as "information" and "data," but the various types of information may also be expressed using other data structures such as "tables" or "lists."

[0016] In the following description, "content" refers to anything that can be the subject of information dissemination via a communication network (information (videos, information, materials, etc.), advertisements for products and services, etc.).

[0017] In the following description, the content to be disseminated will be referred to as "recommended content."

[0018] In the following description, the term "community" refers to, for example, a group or group formed within a department within an organization such as a company or on an online social networking service (SNS). A community is made up of people who share common interests or common goals.

[0019] In the following description, a "user" refers to a person who is currently participating in a community or who has the potential to join a community.

[0020] In the following description, a "member" refers to a user who is participating in a community.

[0021] In the following description, an "influencer" refers to a member of a community who has a strong influence in the community. In SNS, for example, an influencer is someone who has a large number of followers, a large number of channel subscribers, or a large number of users (number of viewers, number of viewers, etc.) (a person who is above a preset threshold). In an organization such as a company, for example, a person in charge, a team leader, an organizer, or a person in a managerial position is identified as an influencer.

[0022] In the following description, a person who intends to spread recommended content will be referred to as an "administrator." For example, in an organization such as a company, an administrator would be a person in a position to manage information handled on a communication network within the organization. Also, for example, an administrator would be a person who intends to spread content over the Internet.

[0023] In the following description, an index representing the degree of diffusion of content is referred to as the “diffusion effect.” The diffusion effect is expressed, for example, by a predicted or actual value of the number of uses of the content, or a predicted or actual value of the usage rate of the content.

[0024] [First Embodiment] Fig. 1 is a diagram illustrating the concept of an information processing system (hereinafter referred to as "support system 1") described as a first embodiment. The support system 1 supports the work and tasks of an administrator when the administrator tries to spread recommended content. In the first embodiment, connections between members within each community are formed, for example, by one member sharing content with another member.

[0025] As shown in the figure, the support system 1 first estimates the current diffusion effect of the recommended content, and determines whether the estimated diffusion effect is equal to or greater than a preset target value (S11).

[0026] If the estimated diffusion effect is less than a predetermined target value, the support system 1 then identifies influencers in a community related to the recommended content (in this example, "Community 1"; hereinafter referred to as "related community") (S12).

[0027] Next, the support system 1 selects, from among other communities (in this example, "community 2" and "community 3"; hereinafter referred to as "candidate communities"), a community (in this example, "community 2"; hereinafter referred to as "recommended community") in which the participation of the influencer identified for the related community is expected to increase the diffusion effect of the recommended content (S13). The candidate community may be another related community.

[0028] The support system 1 generates a policy proposal (hereinafter referred to as "diffusion support information") for the administrator that "encourages the identified influencers to join the selected recommended community (in this example, "Community 2")" and presents (notifies) it to the administrator (S14).

[0029] The administrator receives the diffusion support information from the support system 1 and encourages the identified influencers to join "Community 2," which is a recommended community for participation (S15).

[0030] 2 shows a schematic configuration of the support system 1. As shown in the figure, the support system 1 includes a support device 100, an administrator device 200, and a plurality of user devices 300.

[0031] The assistance device 100, the administrator device 200, and the user device 300 are all configured using information processing devices (computers), and are connected to each other via a communication network 5 in a state where they can perform two-way communication.

[0032] The communication network 5 is, for example, a wireless or wired communication infrastructure constructed using physical communication lines, and is realized by the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), various public communication networks, dedicated lines, etc.

[0033] The support device 100 is an information processing device that provides diffusion support information to the administrator device 200. The functions of the support device 100 will be described in detail later.

[0034] The administrator device 200 is an information processing device used (operated) by an administrator. The administrator operates the administrator device 200 to provide (input) various information to the support device 100 and refer to (use) various information provided by the support device 100. Based on the diffusion support information presented via the administrator device 200, the administrator implements measures to promote the diffusion of recommended content (such as encouraging influencers to join other communities that are expected to have a high diffusion effect on the recommended content).

[0035] The user device 300 is an information processing device operated by a user (including a member or an influencer). For example, the influencer receives a notification from an administrator via the user device 300 (such as a request to join another community that is expected to have a high diffusion effect on recommended content).

[0036] 3A is a diagram illustrating the main functions of the support device 100. As shown in the figure, the support device 100 has the following functions: a storage unit 110, a community information acquisition unit 120, a recommended content information acquisition unit 125, a diffusion target information acquisition unit 130, a related community information acquisition unit 135, an influencer identification unit 140, a diffusion effect estimation unit 145, a recommended community selection unit 150, and a diffusion support information transmission unit 155.

[0037] As shown in the figure, the storage unit 110 stores the following information (data): community information 111, recommended content information 112, diffusion effect calculation information 113, diffusion effect trial calculation information 114, recommended community participation information 115, and diffusion support information 116.

[0038] Of these, the community information 111 includes information (hereinafter referred to as "community information") regarding the community from which potential influencer participation destinations are extracted, which the community information acquisition unit 120 has acquired from the user device 300 or the administrator device 200.

[0039] The community information 111 includes, for example, information indicating the size of the community (such as the number of members), information indicating the type and attributes of the community, information about the members participating in the community, etc. Among these, the information about the members includes, for example, information about the members' skills, information about the members' preferences, information about other communities to which the members belong, information about content that the members have used in the past, etc.

[0040] The recommended content information 112 includes information about the recommended content acquired by the recommended content information acquisition unit 125 from the administrator device 200 (hereinafter referred to as "recommended content information"). The recommended content information includes information identifying the recommended content and information indicating the location of the recommended content, as well as information about the diffusion target set by the administrator (e.g., target viewership and target viewership rating, etc.; hereinafter referred to as "diffusion target information") acquired by the diffusion target information acquisition unit 130 from the administrator device 200. The recommended content information also includes information about the related communities acquired by the related community information acquisition unit 135 from the administrator device 200 (hereinafter referred to as "related community information"). The recommended content information also includes information about each influencer in the related community identified by the influencer identification unit 140.

[0041] The diffusion effect calculation information 113 includes information used when the diffusion effect estimation unit 145 estimates the diffusion effect of the recommended content (hereinafter referred to as "diffusion effect calculation information").

[0042] The diffusion effect estimation information 114 includes information (hereinafter referred to as "diffusion effect estimation information") indicating the diffusion effect of the recommended content when the influencers identified for the related community join a community (which may be another related community) different from the community to which they belong, as estimated by the diffusion effect estimation unit 145. The diffusion effect estimation information 114 also includes information indicating the diffusion effect of the recommended content before the influencers join the other community.

[0043] The recommended participation community information 115 includes information about the recommended participation communities determined by the recommended participation community selection unit 150 based on the diffusion effect estimation information.

[0044] The diffusion support information 116 includes diffusion support information generated by the diffusion support information transmitter 155 based on the recommended community participation information 115 .

[0045] Among the functions shown in FIG. 3A, the community information acquisition unit 120 acquires community information from the user device 300 and the administrator device 200 via the communication network 5, and manages the acquired community information in the storage unit 110 as community information 111.

[0046] 4A shows an example of the community information 111. As shown in the drawing, the illustrated community information 111 includes community body information 111a and community member information 111b.

[0047] Of these, the community main information 111a is made up of a plurality of records each including items such as a community ID 411, a genre 412, and the number of members 413. One record in the community main information 111a corresponds to one community.

[0048] Of the above items, the community ID 411 stores a community identifier (hereinafter referred to as a "community ID").

[0049] The genre 412 stores information indicating the genre of the community.

[0050] The number of members 413 stores the number of members currently participating (belonging) to the community.

[0051] On the other hand, the illustrated community member information 111b is made up of multiple records including items such as a user ID 421, participating communities 422, skills 423, interests 424, and used content 425. One record in the community member information 111b corresponds to one user.

[0052] The user ID 421 stores a user identifier (hereinafter referred to as a "user ID").

[0053] The community ID of the community in which the user is currently participating is stored in the participating community 422. One user may participate in multiple communities.

[0054] The skill 423 stores information indicating the skills (experience, career, qualifications, etc.) of the user.

[0055] Information indicating the main interests (preferences) of the user is stored in the interest 424. There may be multiple interests.

[0056] The used content 425 stores the content IDs of the content (videos that have been viewed, information (data) that has been downloaded, etc.) that the user has used or owned in the past. The user may have used multiple pieces of content in the past.

[0057] Returning to FIG. 3A, the recommended content information acquisition unit 125 acquires recommended content information from the administrator device 200 via the communication network 5 and manages the acquired recommended content information in the storage unit 110 as recommended content information 112 .

[0058] The diffusion target information acquisition unit 130 acquires diffusion target information from the administrator device 200 via the communication network 5 , and manages the acquired diffusion target information in the storage unit 110 as recommended content information 112 .

[0059] The related community information acquisition unit 135 acquires related community information from the administrator device 200 via the communication network 5 and manages the acquired related community information in the storage unit 110 as recommended content information 112. Note that the related community information acquisition unit 135 may, for example, automatically identify as related communities communities whose similarity with recommended content (for example, the distance in feature space between the feature of the recommended content and the feature of the information about the community) is equal to or greater than a preset threshold (second threshold), and acquire information about the identified related community from the community information to use it as the related community information.

[0060] The influencer identification unit 140 identifies influencers in related communities and manages information indicating the identified influencers in the related communities as recommended content information 112 in the storage unit 110. For example, the influencer identification unit 140 identifies as influencers members who share a large number of pieces of content (e.g., the number of commonly viewed channels) with other members in the related community (above a predetermined threshold). Multiple influencers may be identified in one related community. The method for identifying influencers is not limited to the above method. As another method, for example, a person with a high diffusion level (diffusion index) calculated based on the number of followers, the number of likes (e.g., "likes") for the content provided, the number of comments on the content provided, the number of content shares with other members, the number of accesses and plays to the content, the amount of time the content is used, the number of searches by search engines, the number of topics appearing on social media, the history of past diffusion of recommended content (history of recommenders and recommended destinations), etc. may be identified as influencers.

[0061] 4B shows an example of the recommended content information 112. As shown in the figure, the example recommended content information 112 is made up of one or more records including items such as a recommended content ID 431, a target number of uses (current number of uses) 432, a target usage rate (current usage rate) 433, a related community 434, and an influencer ID 435. One record of the recommended content information 112 corresponds to one piece of recommended content.

[0062] Of the above items, the recommended content ID 431 stores an identifier of the recommended content (hereinafter referred to as a "recommended content ID").

[0063] The target number of uses (current number of uses) 432 stores the target number of uses and the current number of uses (in parentheses) of the recommended content.

[0064] The target usage rate (current usage rate) 433 stores the target usage rate and the current usage rate (in parentheses) of the recommended content.

[0065] The community ID of the related community of the recommended content is stored in the related community 434. There may be multiple related communities for one recommended content.

[0066] The influencer ID 435 stores an influencer ID, which is the user ID of an influencer identified by the influencer identification unit 140 for the related community.

[0067] 3A , the diffusion effect estimation unit 145 estimates the current diffusion effect of the recommended content using the diffusion effect calculation information 113, and manages the estimated result in the storage unit 110 as diffusion effect estimation information 114. The diffusion effect estimation unit 145 calculates the diffusion effect described above using, for example, the diffusion effect calculation information 113.

[0068] 4C shows an example of the diffusion effect calculation information 113. The illustrated diffusion effect calculation information 113 includes a graph showing the relationship between the number of community members and the number of uses of content. The black circles in the figure represent actually obtained values, and the straight line is a regression line calculated based on these values. By referring to the illustrated graph, the number and usage rate of content can be obtained from the number of community members.

[0069] 3A , the diffusion effect estimation unit 145, for example, calculates the similarity between the related community in which the influencer currently participates and other communities, or the activity levels of the other communities, extracts candidate communities to join based on the calculated similarity and activity levels, and stores information indicating the extracted candidate communities to join in the candidate communities to join 456 of the diffusion effect estimation information 114. The candidate communities to join may be other related communities. For example, the diffusion effect estimation unit 145 extracts as candidate communities to join other communities whose at least one of the similarity or activity level with the related community is equal to or greater than a predetermined threshold (third threshold).

[0070] Here, the diffusion effect estimation unit 145 calculates the above-mentioned similarity based on the distance (Mahalanobis distance, etc.) in the feature space of the features of each community, which is calculated using parameters such as the profile of the users participating in the community, the user's preferences (areas of interest), the user's skills (past experience (job responsibilities), qualifications held, technologies held, etc.), the category to which the community belongs, the size (dimension) of the community, and the attributes of other communities in which the community members participate.

[0071] In addition, the diffusion effect calculation unit 145 calculates the above-mentioned activity level based on, for example, the results of past content recommendations to the community (such as the number of times the content has been used compared to the number of times the content has been recommended), the number of times the content has been used determined from the size of the community, and the predicted value of the content usage rate.

[0072] Furthermore, the diffusion effect estimation unit 145 estimates the diffusion effect of the recommended content when an influencer of a related community joins the candidate community, generating diffusion effect calculation information 113, and manages the estimated result in the storage unit 110 as diffusion effect estimation information 114. The diffusion effect estimation unit 145 calculates the diffusion effect using, for example, the diffusion effect calculation information 113.

[0073] 4D shows an example of diffusion effect estimation information 114. As shown in the figure, the illustrated diffusion effect estimation information 114 is composed of one or more records having the following fields: recommended content ID 451, influencer ID 452, related communities 453, predicted content usage count (current) 454, predicted content usage rate (current) 455, potential participation communities 456, predicted content usage count (after participation) 457, predicted content usage rate (after participation) 458, and candidate community participation promotion measures 459. One record in diffusion effect estimation information 114 corresponds to one influencer.

[0074] Of the above items, the recommended content ID 451 stores the recommended content ID of the recommended content.

[0075] The influencer ID 452 stores the influencer ID of the influencer identified by the influencer identification unit 140 for each of the relevant communities of the recommended content.

[0076] The related community 453 stores the community ID of the related community to which the influencer belongs.

[0077] The predicted number of uses of content (current state) 454 stores a predicted number of uses of the recommended content in the current state (before the influencer joined the participating community).

[0078] The content usage rate prediction value (current state) 455 stores the current predicted value of the usage rate of the recommended content (before the influencer joined the participating community).

[0079] The participation candidate community 456 stores the community IDs of participation candidate communities extracted by the diffusion effect estimation unit 145 based on at least one of the similarity and activity of the communities.

[0080] The predicted number of uses of content (after participation) 457 stores a predicted number of uses of the recommended content after the influencer joins the candidate community.

[0081] The content usage rate prediction value (after participation) 458 stores a prediction value of the usage rate of the recommended content after the influencer joins the candidate community.

[0082] The candidate community participation promotion measures 459 store candidate notification means (e.g., email, a communication means that is frequently used by users) to be used when encouraging the influencer to join the candidate community. The content of the candidate community participation promotion measures 459 is transmitted to the administrator device 200 together with the diffusion support information when the diffusion support information transmission unit 155 transmits the diffusion support information to the administrator device 200. The content of the candidate community participation promotion measures 459 is set by, for example, a user or an administrator. The content of the candidate community participation promotion measures 459 may be automatically set by the support device 100 based on the influencer's past usage history of the communication network 5, etc.

[0083] Returning to Figure 3A, the recommended participation community selection unit 150 selects communities (hereinafter referred to as "recommended participation communities") to recommend to the influencer to join based on the calculated diffusion effect (predicted number of content uses (after participation) 457 and predicted content usage rate (after participation) 458), and manages information indicating the selected recommended participation communities in the memory unit 110 as recommended participation community information 115.

[0084] 4E shows an example of the recommended participation community information 115. As shown in the figure, the recommended participation community information 115 is composed of one or more records each consisting of the following items: recommended content ID 471, influencer ID 472, participating community 473, and recommended participation community 474. One record of the recommended participation community information 115 corresponds to one recommended participation community selected for one influencer in a related community of one recommended content. There may be multiple influencers for one recommended content. Also, there may be multiple recommended participation communities for one influencer.

[0085] The recommended content ID 471 stores a recommended content ID.

[0086] The influencer ID 472 stores the influencer ID of an influencer identified for the relevant community of the recommended content.

[0087] The participating community 473 stores the community ID of the community in which the influencer is currently participating.

[0088] The recommended community to join 474 stores the community ID of the recommended community to join selected for the influencer.

[0089] 3A , the diffusion support information transmitter 155 generates diffusion support information based on the content of the recommended community information 115 and manages the generated diffusion support information in the storage unit 110 as diffusion support information 116. For example, the diffusion support information transmitter 155 generates, as diffusion support information, content encouraging each influencer in the related community to join the recommended community selected for each influencer. The diffusion support information transmitter 155 also transmits the generated content of the diffusion support information 116 to the administrator device 200 via the communication network 5.

[0090] 3B is a diagram illustrating the main functions of the administrator device 200. As shown in the figure, the administrator device 200 has the following functions: a storage unit 210, a recommended content receiving unit 220, a diffusion target receiving unit 225, a related community receiving unit 230, a diffusion support information receiving unit 235, a diffusion support information presenting unit 240, and a recommended community joining notifying unit 245.

[0091] The storage unit 210 stores information (data) such as recommended content 211 , a spreading target 212 , a related community 213 , and spreading support information 214 .

[0092] The recommended content receiving unit 220 receives recommended content from the administrator via a user interface, and manages the received recommended content in the storage unit 210 as recommended content 211 .

[0093] The diffusion target receiving unit 225 receives a diffusion target for the recommended content from the administrator via the user interface, and manages the received diffusion target as the diffusion target 212 in the storage unit 210 .

[0094] The related community receiving unit 230 receives a related community of the recommended content, and manages the received related community in the storage unit 210 as a related community 213 .

[0095] The diffusion support information receiving unit 235 receives diffusion support information from the support device 100 and manages the received diffusion support information as diffusion support information 214 in the storage unit 210 .

[0096] The diffusion support information presentation unit 240 presents the content of the diffusion support information 214 to the administrator via a user interface.

[0097] The recommended community notification unit 245 sends a message to influencers of related communities encouraging them to join the recommended community in response to an instruction received from the administrator via the user interface.

[0098] 3C is a diagram illustrating main functions of the user device 300. As shown in the figure, the user device 300 has the functions of a storage unit 310, a recommended community receiving unit 320, and a recommended community presenting unit 325.

[0099] The storage unit 310 stores a recommended community 311 for participation.

[0100] The participation recommended community receiving unit 320 receives the participation recommended community sent from the administrator device 200 and manages the received participation recommended community in the storage unit 310 as the participation recommended community 311 .

[0101] The participation recommended community presentation unit 325 presents a message based on the participation recommended community 311 (a message encouraging participation in the participation recommended community) to influencers of related communities via a user interface.

[0102] 5 is a flowchart illustrating the main process (hereinafter referred to as "diffusion support process S500") performed by the support device 100. The diffusion support process S500 will be described below with reference to FIG. It is assumed that the diffusion effect calculation information 113 has already been stored in the storage unit 110 when the diffusion support process S500 starts to be executed.

[0103] First, the community information acquisition unit 120 of the support device 100 acquires community information via the communication network 5 and manages the acquired information as community information 111 in the storage unit 110 (S511).

[0104] Next, the recommended content information acquisition unit 125 acquires (receives) the recommended content information (recommended content ID, location of recommended content, etc.) sent from the administrator device 200, and manages the acquired recommended content information in the memory unit 110 as recommended content information 112 (S512).

[0105] Next, the diffusion target information acquisition unit 130 acquires diffusion target information from the administrator device 200, and manages the acquired diffusion target information in the storage unit 110 as recommended content information 112 (S513).

[0106] Next, the related community information acquisition unit 135 acquires the related community information from the administrator device 200, and manages the acquired related community information in the storage unit 110 as the recommended content information 112 (S514).

[0107] Next, the influencer identification unit 140 identifies influencers for each related community, and manages the influencer IDs of the identified influencers as recommended content information 112 in the storage unit 110 (S515).

[0108] Next, the diffusion effect estimation unit 145 estimates the current diffusion effect of each related community, and manages the estimated results in the storage unit 110 as diffusion effect estimation information 114 (S516).

[0109] Next, the diffusion effect estimation unit 145 determines whether the estimated current diffusion effect is equal to or greater than a preset target value (S517). If the estimated current diffusion effect is equal to or greater than the target value (S517: Yes), the diffusion support process S500 ends. In this way, if the estimated current diffusion effect is equal to or greater than the target value, the diffusion effect estimation and diffusion support information are not generated, thereby preventing influencers from being influenced more than necessary. On the other hand, if the estimated current diffusion effect is less than the target value (S517: No), the process proceeds to S531.

[0110] In S531, the diffusion effect estimation unit 145 extracts candidate communities to join from the communities managed in the community information 111 based on at least one of the similarity and activity level.

[0111] Next, the diffusion effect calculation unit 145 calculates the diffusion effect after each influencer in the related community joins each of the extracted candidate participation communities, and manages the calculated results in the memory unit 110 as diffusion effect calculation information 114 (S532).

[0112] Next, the diffusion effect estimation unit 145 determines whether the estimated diffusion effect is equal to or greater than a predetermined target value (first threshold) (S533). If the estimated current diffusion effect is equal to or greater than the target value (S533: Yes), the process proceeds to S534. Otherwise (S533: No), the process returns to S532. Note that if the diffusion effect does not exceed the target value even when influencers from any related community join the respective candidate communities, the diffusion effect estimation unit 145, for example, transmits information indicating this to the administrator device 200 and terminates the diffusion support process S500.

[0113] In S534, the recommended participation community selection unit 150 selects candidate communities for participation whose diffusion effect is equal to or greater than a target value as recommended participation communities, and stores these in the storage unit 110 as recommended participation community information 115.

[0114] In S535 , the diffusion-support information transmitter 155 generates diffusion-support information based on the recommended community information 115 , stores the information as diffusion-support information 116 in the memory 110 , and transmits the generated diffusion-support information to the administrator device 200 .

[0115] Incidentally, even if the determination in S533 shows that the diffusion effect does not exceed the target value even when influencers from any related community join each of the candidate communities, the diffusion effect estimation information 114 estimated in S532 may be provided to the administrator via, for example, the administrator device 200. In this way, the administrator can use the presented diffusion effect estimation information 114 as reference information, for example, when planning measures to diffuse information.

[0116] FIG. 6A shows an example of a screen (hereinafter referred to as a "diffusion support information presentation screen 610") that is displayed when the diffusion support information presentation unit 240 of the administrator device 200 presents diffusion support information to the administrator.

[0117] FIG. 6B shows an example of information that the recommended community presentation unit 325 of the user device 300 notifies influencers of related communities of the recommended community (by email in this example).

[0118] As described above, the support system 1 of the first embodiment identifies influencers in related communities of recommended content and estimates the diffusion effect of the recommended content if the identified influencers join other communities (candidate communities for participation).The support system 1 then selects communities with a high content diffusion effect as recommended communities based on the results of the estimate, generates diffusion support information recommending participation in the recommended communities, and notifies the administrator of the information.This allows the administrator to be provided with diffusion support information that is expected to have a high content diffusion effect, thereby increasing the diffusion effect of the content.

[0119] In addition, spreading content through influencers can increase awareness, clarify the target audience, and improve community engagement and credibility.

[0120] [Second Embodiment] Fig. 7 is a diagram illustrating the concept of a support system 1 described as a second embodiment. Similar to the first embodiment, the support system 1 of the second embodiment supports the work and tasks of an administrator when the administrator tries to spread recommended content. In the second embodiment, connections (links) between members within a community are generated, for example, by following each other.

[0121] As shown in the figure, the support system 1 first estimates the current diffusion effect of the recommended content, and determines whether the estimated diffusion effect is equal to or greater than a preset target value (S21).

[0122] If the estimated diffusion effect is less than a predetermined target value, the support system 1 then identifies influencers in a community related to the recommended content (in this example, "Community 1"; hereinafter referred to as "related community") (S22).

[0123] Next, the support system 1 selects members (hereinafter referred to as "connection target members") of a community ("community 2" in this example, hereinafter referred to as a "connection recommended community") from among other communities ("community 2" and "community 3" in this example, hereinafter referred to as "connection candidate communities") to which the identified influencer's new connection is expected to increase the diffusion effect (S23). The connection candidate community may be another related community. In this example, influencers in the connection recommended community are selected as connection target members.

[0124] The support system 1 generates a policy proposal (hereinafter referred to as "diffusion support information") for the administrator that "encourages connection target members (influencers in connection recommended communities) to connect with the selected connection target members (in this example, members of "Community 2")" and notifies the administrator (S24).

[0125] The administrator receives the diffusion support information from the support system 1 and encourages influencers in the related communities to connect with the target members of community 2 (S25).

[0126] 8 shows a schematic configuration of the support system 1 of the second embodiment. Note that the configuration of the support system 1 of the second embodiment is the same as that of the first embodiment, and therefore a description thereof will be omitted.

[0127] 9A is a diagram illustrating main functions of the support device 100 according to the second embodiment. As shown in the figure, the support device 100 has the following functions: a storage unit 110, a community information acquisition unit 120, a recommended content information acquisition unit 125, a diffusion target information acquisition unit 130, a related community information acquisition unit 135, an influencer identification unit 160, a diffusion effect estimation unit 170, a connection recommended member selection unit 175, and a diffusion support information transmission unit 180.

[0128] As shown in the figure, the storage unit 110 stores each piece of information (data) such as community information 111, recommended content information 112, diffusion effect calculation information 113, diffusion effect trial calculation information 117, recommended connection member information 118, and diffusion support information 119.

[0129] Of these, the community information 111, the recommended content information 112, and the diffusion effect calculation information 113 are the same as those in the first embodiment, and therefore will not be described further. Note that the community information 111, the recommended content information 112, and the diffusion effect calculation information 113 are, for example, the contents shown in Figures 4A to 4C in the first embodiment.

[0130] The diffusion effect estimation information 117 includes information (hereinafter referred to as "diffusion effect estimation information") indicating the diffusion effect of the recommended content when an influencer of a related community connects to a target member, as estimated by the diffusion effect estimation unit 170. The diffusion effect estimation information 114 includes information indicating the diffusion effect of the recommended content before an influencer of a related community connects to a target member.

[0131] The recommended connection member information 118 includes information on recommended connection members selected by the recommended connection member selection unit 175 based on the diffusion effect estimation information.

[0132] The spreading support information 119 includes spreading support information generated by the spreading support information transmitting unit 180 based on the connection recommended member information 118 .

[0133] Of the functions shown in the figure, the community information acquisition unit 120, the recommended content information acquisition unit 125, the diffusion target information acquisition unit 130, and the related community information acquisition unit 135 are the same as those in the first embodiment, and therefore description thereof will be omitted.

[0134] The influencer identification unit 160 identifies influencers in each of the related communities and manages information indicating the identified influencers in each of the related communities in the storage unit 110 as recommended content information 112. The influencer identification unit 160 also identifies influencers in connection candidate communities and manages information indicating the identified influencers in the storage unit 110 as diffusion effect estimation information 117. Note that the method for identifying influencers in related communities and connection candidate communities is the same as in the first embodiment, and therefore description thereof will be omitted.

[0135] The diffusion effect estimation unit 170 estimates the current diffusion effect of the recommended content using the diffusion effect calculation information 113 , and manages the estimated results in the storage unit 110 as diffusion effect estimation information 117 .

[0136] Furthermore, the diffusion effect estimation unit 170 calculates the similarity between the community in which the influencer of the related community currently participates and other communities, and the activity levels of the other communities, extracts connection candidate communities based on the calculated similarity and activity levels, and stores information indicating the extracted connection candidate communities in the diffusion effect estimation information 117. The connection candidate communities may be other related communities. For example, the diffusion effect estimation unit 145 extracts other communities as connection candidate communities whose at least one of the similarity or activity level with the related community is equal to or greater than a predetermined threshold (fourth threshold). Note that the method of calculating the similarity and activity level is the same as in the first embodiment, and therefore description thereof will be omitted.

[0137] In addition, the diffusion effect estimation unit 170, for example, identifies influencers of the connection candidate community identified by the influencer identification unit 160 as connection candidate members, and stores information indicating the identified connection candidate members in the diffusion effect estimation information 117.

[0138] Note that connection target members may be selected by other methods, such as selecting as connection target members those with a high diffusion level (diffusion index) calculated based on the number of followers, the number of likes (such as "likes") for the provided content, the number of comments for the provided content, the number of times the content has been shared with other members, the number of accesses and plays to the content, the amount of time the content has been used, the number of searches using a search engine, the number of times the topic has appeared on SNS, the history of past diffusion of recommended content (history of recommenders and recommended destinations), etc.

[0139] In addition, the diffusion effect estimation unit 170 uses the diffusion effect calculation information 113 to estimate the diffusion effect of the recommended content when an influencer in a related community connects with a candidate connection member, and stores the estimated result in the memory unit 110 as diffusion effect estimation information 117.

[0140] 10A shows an example of diffusion effect estimation information 117. As shown in the figure, the illustrated diffusion effect estimation information 114 is composed of one or more records having the following fields: recommended content ID 451, influencer ID 452, related community 453, predicted content usage count (current state) 454, predicted content usage rate (current state) 455, connection candidate community / member 461, predicted content usage count (after connection) 462, predicted content usage rate (after connection) 463, and connection promotion measure candidate 464. One record of diffusion effect estimation information 117 corresponds to one influencer.

[0141] Of the above items, the items from recommended content ID 451 to content usage number predicted value (current state) 454 are the same as the items with the same reference numerals in FIG. 4D in the first embodiment, and therefore description thereof will be omitted.

[0142] The connection candidate community / member 461 stores the community ID of the connection candidate community extracted by the diffusion effect estimation unit 145 based on at least one of the community similarity or activity level, and the influencer ID of the influencer identified by the influencer identification unit 140 for the connection candidate community.

[0143] The predicted number of uses of content (after connection) 462 stores a predicted number of uses of the recommended content after the influencer connects with the connection candidate member.

[0144] The content usage rate predicted value (after connection) 463 stores a predicted value of the usage rate of the recommended content after the influencer connects with the connection candidate member.

[0145] The connection promotion measure candidate 464 stores a notification means (e.g., email, a communication means that is frequently used by users) to be used when encouraging the influencer to connect with the connection candidate member. The content of the connection promotion measure candidate 464 is transmitted to the administrator device 200 together with the diffusion support information when the diffusion support information transmission unit 180 transmits the diffusion support information to the administrator device 200. The content of the connection promotion measure candidate 464 is set by, for example, a user or an administrator. The content of the connection promotion measure candidate 464 may be automatically set by the support device 100 based on, for example, the influencer's past usage history of the communication network 5.

[0146] Returning to Figure 9A, the connection recommendation member selection unit 175 selects connection recommendation members who recommend connection to influencers in related communities based on the diffusion effect estimated by the diffusion effect estimation unit 170, and manages information indicating the selected connection recommendation members in the memory unit 110 as connection recommendation member information 118.

[0147] 10B shows an example of the recommended connection member information 118. As shown in the figure, the recommended connection member information 118 is composed of one or more records each consisting of the following items: recommended content ID 471, related community 472, influencer ID 473, recommended connection community 481, and recommended connection member 482. One record of the recommended connection member information 118 corresponds to one recommended connection member selected for one influencer in the related community of one recommended content. There may be multiple influencers for one recommended content. Also, there may be multiple recommended connection members for one influencer.

[0148] Of the above items, the recommended content ID 471 stores a recommended content ID.

[0149] The related community 472 stores a related community ID.

[0150] The influencer ID 473 stores the influencer ID of an influencer in the relevant community.

[0151] The recommended connection community 481 stores the community ID of the recommended connection community.

[0152] The recommended connection members 482 stores the member IDs of recommended connection members selected for the influencer.

[0153] 9A , the diffusion support information transmitter 180 generates diffusion support information based on the content of the recommended connection member information 118 and manages the generated diffusion support information in the storage unit 110 as diffusion support information 119. For example, the diffusion support information transmitter 180 generates, as diffusion support information 119, content encouraging each influencer in the related community to connect to the recommended connection members selected for each influencer. The diffusion support information transmitter 180 also transmits the generated content of the diffusion support information 119 to the administrator device 200 via the communication network 5.

[0154] 9B is a diagram illustrating main functions of the administrator device 200 according to the second embodiment. As shown in the figure, the administrator device 200 includes a storage unit 210, a recommended content receiving unit 220, a spreading target receiving unit 225, a related community receiving unit 230, a spreading support information receiving unit 235, a spreading support information presenting unit 240, and a recommended member notification unit 250.

[0155] The storage unit 210 stores information (data) such as recommended content 211 , a spreading target 212 , a related community 213 , and spreading support information 214 .

[0156] The recommended content receiving unit 220 receives recommended content from the administrator via a user interface, and manages the received recommended content in the storage unit 210 as recommended content 211 .

[0157] The diffusion target receiving unit 225 receives a diffusion target for each recommended content from the administrator via the user interface, and manages the received diffusion target as the diffusion target 212 in the storage unit 210 .

[0158] The related community receiving unit 230 receives a related community of the recommended content, and manages the received related community in the storage unit 210 as a related community 213 .

[0159] The diffusion support information receiving unit 235 receives diffusion support information from the support device 100 and manages the received diffusion support information as diffusion support information 214 in the storage unit 210 .

[0160] The diffusion support information presentation unit 240 presents the content of the diffusion support information 214 to the administrator via a user interface.

[0161] The recommended connection member notification unit 250 sends a message to influencers in related communities urging them to connect with recommended connection members in response to an instruction received from the administrator via the user interface.

[0162] 9C is a diagram illustrating main functions of the user device 300 according to the second embodiment. As shown in the figure, the user device 300 includes a storage unit 310, a recommended connection member receiving unit 350, and a recommended connection member presenting unit 355.

[0163] The storage unit 310 stores a connection recommended member 341 .

[0164] The recommended connection member receiving unit 350 receives recommended connection members sent from the administrator device 200 and manages the received recommended connection members in the storage unit 310 as recommended connection members 341 .

[0165] The connection recommended member presentation unit 355 presents a message based on the connection recommended members 341 (a message recommending connection with the connection recommended members) to influencers of the related community via the user interface.

[0166] 11 is a flowchart illustrating a main process (hereinafter referred to as "diffusion support process S1100") performed by the support device 100 according to the second embodiment. The diffusion support process S1100 will be described below with reference to FIG. It is assumed that the diffusion effect calculation information 113 has already been stored in the storage unit 110 when the diffusion support process S1100 starts to be executed.

[0167] The processes from S511 to S517 in the figure are the same as those in the first embodiment denoted by the same reference numerals, and therefore a description thereof will be omitted.

[0168] In S551, the diffusion effect estimation unit 170 extracts connection candidate communities from the communities managed in the community information 111 based on at least one of the similarity and activity level.

[0169] Next, the influencer identification unit 160 identifies an influencer for each of the extracted connection candidate communities, and stores the community ID of the connection candidate community and the influencer ID of the influencer identified for that connection candidate community in the connection candidate community / member 461 of the diffusion effect estimate information 1117 (S552).

[0170] Next, the diffusion effect after each influencer in the related community connects with a candidate connection member (influencer in this example) in the candidate connection community is calculated, and the calculated results are stored in the predicted content usage number (after connection) 462 and the predicted content usage rate (after connection) 463 in the diffusion effect estimate information 117 (S553).

[0171] Next, the diffusion effect estimation unit 170 determines whether the estimated diffusion effect is equal to or greater than a preset target value (first threshold) (S554). If the estimated current diffusion effect is equal to or greater than the target value (S554: Yes), the process proceeds to S555. Otherwise (S554: No), the process returns to S553. Note that if the diffusion effect does not exceed the target value even when influencers from any related community connect with their respective connection candidate members, the diffusion effect estimation unit 170, for example, transmits information indicating this to the administrator device 200 and terminates the diffusion support process S1100.

[0172] In S555, the recommended connection member selection unit 175 selects connection candidate members whose diffusion effects are equal to or greater than the target value as connection candidate members, and stores the selected connection candidate members as recommended connection member information 118 in the storage unit 110.

[0173] In S556, the diffusion support information transmitting unit 180 generates diffusion support information based on the contents of the connection recommended member information 118, stores it in the memory unit 110 as diffusion support information 119, and transmits the generated diffusion support information to the administrator device 200 via the communication network 5.

[0174] Incidentally, even if the determination in S554 shows that the diffusion effect is less than the target value even when influencers of any related community connect to each of the connection candidate members, the diffusion effect estimation information 117 estimated in S553 may be provided to the administrator via, for example, the administrator device 200. In this way, the administrator can use the presented diffusion effect estimation information 117 as reference information when, for example, planning measures for spreading information.

[0175] FIG. 12A is an example of a screen (hereinafter referred to as the "diffusion support information presentation screen 1210") that is displayed when the diffusion support information presentation unit 240 of the administrator device 200 of the second embodiment presents diffusion support information to the administrator.

[0176] FIG. 12B shows an example of information that the recommended connection member presentation unit 355 of the user device 300 notifies (by e-mail in this example) influencers in related communities of recommended connection members.

[0177] As described above, the support system 1 of the second embodiment identifies influencers in related communities of the recommended content and estimates the diffusion effect of the recommended content when the identified influencers connect with members (influencers in this example) of other communities (connection candidate communities). Based on the results of the estimate, the support system 1 selects members with a high content diffusion effect as recommended connection members, generates diffusion support information recommending connections with the recommended connection members, and notifies the administrator. This allows the administrator to be provided with diffusion support information that is expected to have a high content diffusion effect, thereby increasing the content diffusion effect.

[0178] In addition, spreading content through influencers can increase awareness, clarify the target audience, and improve community engagement and credibility.

[0179] 13 shows an example of the hardware configuration of an information processing device used to realize the above-described support system 1. For example, the support device 100, the administrator device 200, and the user device 300 are realized using one or more of the information processing devices 10 exemplified below.

[0180] The illustrated information processing device 10 includes a processor 11, a main storage device 12 (memory), an auxiliary storage device 13 (external storage device), an input device 14, an output device 15, and a communication device 16. These are communicatively connected via a bus, a communication cable, etc. Examples of the information processing device 10 include a personal computer, a server device, a smartphone, a tablet, an office computer, a general-purpose machine (mainframe), etc.

[0181] All or part of the information processing device 10 may be realized using virtual information processing resources provided using virtualization technology, process space separation technology, or the like, such as a virtual server provided by a cloud system. Furthermore, all or part of the functions provided by the information processing device 10 may be realized by a service provided by a cloud system via an API (Application Programming Interface), for example. Furthermore, all or part of the functions provided by the information processing device 10 may be realized using, for example, Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service (IaaS), or the like.

[0182] The processor 11 is configured using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), an AI (Artificial Intelligence) chip, etc.

[0183] The main memory device 12 is a device used by the processor 11 when executing a program, and is, for example, a read-only memory (ROM), a random access memory (RAM), a non-volatile memory (NVRAM (Non Volatile RAM)), etc. The various functions realized in the assistance system 1 are realized by the processor 11 reading out programs and data stored in the auxiliary memory device 13 into the main memory device 12 and executing them.

[0184] The auxiliary storage device 13 is a device that stores programs and data, and can be configured, for example, by an SSD (Solid State Drive), a hard disk drive, an optical storage device (e.g., a CD (Compact Disc) or a DVD (Digital Versatile Disc)), a storage system, a read / write device for non-transitory recording media such as an IC card, an SD card or an optical recording media, or a non-transitory storage area of ​​a cloud server. Programs and data can be read into the auxiliary storage device 13 from other information processing devices equipped with non-transitory recording media or non-transitory storage devices via a recording media reader or a communication device 16. The programs and data stored in the auxiliary storage device 13 are read into the main storage device 12 as needed.

[0185] The input device 14 is an interface that accepts input of information from the outside, and is, for example, a keyboard, a mouse, a touch panel, a card reader, a pen-input tablet, a voice input device, or the like.

[0186] The output device 15 is an interface that outputs various information such as the progress of processing and the results of processing to the outside. The output device 15 is, for example, a display device (liquid crystal monitor, LCD (Liquid Crystal Display), graphic card, etc.) that visualizes the various information, a device that converts the various information into audio (audio output device (speaker, etc.)), or a device that converts the various information into text (printer, etc.). Note that, for example, the information processing device 10 may be configured to input and output information to and from other devices via the communication device 16.

[0187] The input device 14 and the output device 15 constitute a user interface that realizes interactive processing with the user (receiving information, providing information, etc.).

[0188] The communication device 16 is a device that realizes communication with other devices. The communication device 16 is a wired or wireless communication interface that realizes communication with other devices via the communication network 5, and is, for example, a network interface card (NIC), a wireless communication module, a USB module, or the like.

[0189] The information processing device 10 may be equipped with, for example, an operating system, a file system, a database management system (DBMS) (relational database, NoSQL, etc.), a key-value store (KVS), etc.

[0190] Although the embodiments have been described above, the present invention is not limited to the above-described embodiments, and various modifications are included, and the present invention is not necessarily limited to those including all of the configurations described. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0191] For example, the various similarities and activity levels described above may be calculated using methods other than those described above, such as machine learning techniques using large language models (LLMs) or natural language processing techniques.

[0192] 1 Support system 100 Support device 110 Storage unit 111 Community information 112 Recommended content information 113 Diffusion effect calculation information 114 Diffusion effect estimation information 115 Recommended participation community information 116 Diffusion support information 120 Community information acquisition unit 125 Recommended content information acquisition unit 130 Diffusion target information acquisition unit 135 Related community information acquisition unit 140 Influencer identification unit 145 Diffusion effect estimation unit 150 Recommended participation community selection unit 155 Diffusion support information transmission unit 200 Administrator device 240 Diffusion support information presentation unit 250 Recommended connection member notification unit 300 User device 350 Recommended connection member reception unit 355 Recommended connection member presentation unit S500 Diffusion support processing S1100 Diffusion support processing

Claims

1. A content diffusion support system configured using one or more information processing devices having a processor and a storage device, and storing community information which is information about a plurality of communities formed via a communication network, diffusion effect calculation information which is information used to calculate the diffusion effect of content in the communication network, and information about related communities which are communities related to recommended content which is content to be diffused in the communication network, identifying influencers in each of the related communities, selecting as recommended participation communities those communities in which the diffusion effect of the recommended content will be equal to or greater than a predetermined first threshold when an influencer of the related community joins, and generating diffusion support information that encourages the influencer to join the recommended participation community.

2. A content diffusion support system configured using an information processing device having a processor and a storage device, and storing community information which is information about a plurality of communities formed via a communication network, diffusion effect calculation information which is information used to calculate the diffusion effect of content in the communication network, and information about related communities which are communities related to recommended content which is content to be diffused in the communication network, identifying influencers in each of the related communities, selecting as connection recommended members members of other communities whose diffusion effect on the content when an influencer of the related community connects to a member belonging to the influencer, and which generates diffusion support information to encourage the influencers of the related communities to connect to the connection recommended members.

3. A content diffusion support system as claimed in claim 1 or 2, wherein the community whose similarity with the recommended content is equal to or greater than a second threshold set in advance is stored as the related community.

4. A content diffusion support system as described in claim 1, wherein other communities whose similarity or activity level with the related community is equal to or greater than a predetermined third threshold are extracted as candidate communities to join, and from among the candidate communities to join, a community whose diffusion effect is equal to or greater than the first threshold is selected as the recommended community to join.

5. A content diffusion support system as described in claim 2, which extracts other communities as connection candidate communities whose similarity or activity level with the related community is equal to or greater than a predetermined fourth threshold, identifies influencers in each of the connection candidate communities, and selects, as the recommended connection members, influencers in the connection candidate communities whose content diffusion effect when an influencer in the related community connects to an influencer in the connection candidate community is equal to or greater than the first threshold.

6. A content diffusion support system according to claim 1 or 2, wherein the diffusion effect is obtained based on the number of uses or the usage rate of the recommended content.

7. A content diffusion support system as described in claim 6, which stores information indicating the relationship between the number of members belonging to a community and the number or usage rate of content, obtains from the information the number or usage rate corresponding to the number of members belonging to the community, and obtains the diffusion effect based on the obtained number or usage rate.

8. A content diffusion support system as claimed in claim 1 or 2, which is communicatively connected to an information processing device operated by a person who wishes to spread the recommended content, and which transmits the diffusion support information to the information processing device.

9. A content diffusion support system according to claim 1 or 2, wherein information relating to the related community is acquired via a user interface.

10. A content diffusion support system as described in claim 1, which identifies influencers in each of the related communities by prioritizing those who have shared the most content with other members in the same community.

11. A content diffusion support system as described in claim 2, wherein influencers in each of the related communities are identified by giving priority to those with many connections with others.

12. A content diffusion support method, in which a content diffusion support system configured using one or more information processing devices each having a processor and a storage device performs the steps of: storing community information, which is information about a plurality of communities formed via a communication network; diffusion effect calculation information, which is information used to calculate the diffusion effect of content in the communication network; and information about related communities, which are communities related to recommended content, which is content to be diffused in the communication network; identifying influencers in each of the related communities; selecting, as recommended participation communities, those communities in which the diffusion effect of the recommended content will be equal to or greater than a predetermined first threshold when an influencer of the related community participates; and generating, as diffusion support information, information encouraging the influencer to participate in the recommended participation community.

13. A content diffusion support method as described in claim 12, wherein the content diffusion support system further executes the steps of selecting, as recommended connection members, members of other communities whose content diffusion effect will be equal to or greater than a predetermined first threshold when an influencer of the related community connects to a member belonging to the selected member, and generating information as diffusion support information encouraging influencers of the related communities to connect to the recommended connection members.

14. A content diffusion support method as described in claim 12 or 13, further comprising the step of the content diffusion support system storing, as the related community, the community whose similarity with the recommended content is equal to or greater than a predetermined second threshold.

15. A content diffusion support method as described in claim 12, wherein the content diffusion support system further executes the steps of: extracting other communities as candidate communities to join, the other communities having at least one of a similarity or activity level with the related community that is equal to or greater than a third threshold set in advance; and selecting, from the candidate communities to join, a community whose diffusion effect is equal to or greater than the first threshold as the recommended community to join.

16. A content diffusion support method as described in claim 13, wherein the content diffusion support system further executes the steps of: extracting, as connection candidate communities, other communities whose similarity or activity level with the related community is equal to or greater than a predetermined fourth threshold; identifying influencers in each of the connection candidate communities; and selecting, as the recommended connection members, influencers in the connection candidate communities whose content diffusion effect when an influencer in the related community connects to an influencer in the connection candidate community is equal to or greater than the first threshold.

Images