[go: up one dir, main page]

WO2013178081A1 - Sns社区中的用户推荐方法和系统、计算机存储介质 - Google Patents

Sns社区中的用户推荐方法和系统、计算机存储介质 Download PDF

Info

Publication number
WO2013178081A1
WO2013178081A1 PCT/CN2013/076486 CN2013076486W WO2013178081A1 WO 2013178081 A1 WO2013178081 A1 WO 2013178081A1 CN 2013076486 W CN2013076486 W CN 2013076486W WO 2013178081 A1 WO2013178081 A1 WO 2013178081A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
community
identifier
familiarity
friend
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2013/076486
Other languages
English (en)
French (fr)
Inventor
曾雷
李明娥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to MYPI2014703593A priority Critical patent/MY189277A/en
Publication of WO2013178081A1 publication Critical patent/WO2013178081A1/zh
Priority to US14/556,528 priority patent/US9870406B2/en
Anticipated expiration legal-status Critical
Priority to US15/828,919 priority patent/US10691703B2/en
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G06F16/24578—Query processing with adaptation to user needs using ranking
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles
    • G06F16/337—Profile generation, learning or modification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/02—Details
    • H04L12/16—Arrangements for providing special services to substations
    • H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
    • H04L12/1813—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/535—Tracking the activity of the user
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/02—Details
    • H04L12/16—Arrangements for providing special services to substations
    • H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
    • H04L12/1813—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
    • H04L12/1831—Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status

Definitions

  • the present invention relates to the field of social network services, and in particular, to a user recommendation method and system, and a computer storage medium in an SNS community.
  • SNS Social Networking Services
  • SNS community is a website or platform that provides social networking services. People get to know friends and share information and knowledge with others in the SNS community. SNS has become more and more deeply involved in people's life, work and study.
  • the SNS community has rapidly developed into a comprehensive platform that includes: meeting friends, expanding the relationship circle, presenting themselves, sharing information, and playing games. According to the different function points, it can be divided into different types of SNS communities. For example, some SNS communities have the function of blogs, and users can create their own personal space in the SNS community. Some SNS communities focus on expanding the user relationship circle and providing users with a platform for dating. With the development of information technology and the continuous updating of network applications, the needs of users are constantly changing. The old SNS community has also spawned SNS communities with new functions to meet the needs of users.
  • the SNS community typically has user-recommended features that recommend other users that may be of interest to the user.
  • the user recommendation function of the SNS community can help users to view other users that may be of interest to them, and can effectively help users expand the relationship circle, thereby preventing the loss of community users.
  • the user recommendation method in the traditional SNS community generally associates the SNS community with instant messaging. If the user is a friend in instant communication, the user in the instant messaging is recommended to the user in the SNS community.
  • the traditional user recommendation method in the SNS community only recommends the user's friends in instant communication to the user, and the number of users that can be recommended is small and may miss many people who are more likely to be interested in the user.
  • the user recommendation method in the traditional SNS community will make the expansion of the user relationship circle less efficient.
  • a user recommendation method in an SNS community including the following steps:
  • a second user with a first user's familiarity exceeding a threshold is recommended to the first user in the second community.
  • the interaction record includes at least one operation record of access, comment, reply, praise, forwarding, reprint, and sharing between the first user and the second user.
  • the method further includes:
  • the step of calculating the familiarity of the first user and the second user according to the interaction frequency is:
  • the step of generating the closeness of the first user and the second user according to the user relationship chain of the first community and the user relationship chain of the second community includes:
  • the second user is the friend of the first user, and the second user is the first user
  • the second friend and the second user are the users who listen to or pay attention to the first user
  • the closeness of the first user and the second user is correspondingly increased according to the preset weight.
  • the method further includes:
  • the weight corresponding to the relationship between the first user and the second user is set, and the weights are set from high to low in the following order:
  • the second user is a friend of the first user
  • the second user in the first community is a user who listens or pays attention to the first user
  • the second user is a second friend of the first user
  • the second user is the second friend of the first user.
  • the method further includes:
  • the step of calculating the familiarity of the first user and the second user according to the interaction frequency is:
  • the step of calculating the familiarity of the first user and the second user according to the interaction frequency, the closeness, and the similarity between the first user and the second user includes: setting the first user and the second separately in advance
  • the user's interaction frequency, closeness, and similarity weights increase the familiarity of the first user and the second user according to the interaction frequency, the closeness, the similarity, and the weight of the interaction frequency, the closeness, and the similarity.
  • the first community user identifier of the same user is different from the second community user identifier, and the first community and the second community share the user identifier correspondence relationship library, wherein the user correspondence database stores the first user of the same user. Correspondence between the community user identifier and the second community user identifier;
  • the step of recommending, in the second community, the second user with the first user's familiarity exceeding the threshold to the first user includes:
  • a user recommendation system in the SNS community including:
  • a record obtaining module configured to acquire an interaction record of the first user and the second user in the first community
  • An interaction frequency generating module configured to generate, according to the interaction record, an interaction frequency between the first user and the second user
  • a familiarity calculation module configured to calculate a familiarity between the first user and the second user according to the interaction frequency
  • a recommendation module configured to recommend, to the first user, a second user that has a familiarity with the first user exceeding a threshold in the second community.
  • the interaction record includes at least one operation record of access, comment, reply, praise, forwarding, reprint, and sharing between the first user and the second user.
  • system further comprises:
  • a tightness generating module configured to generate a closeness between the first user and the second user according to the user relationship chain in the first community and the user relationship chain in the second community;
  • the familiarity calculation module is configured to calculate the familiarity of the first user and the second user according to the interaction frequency and the tightness.
  • the tightness generating module is configured to determine, according to the user relationship chain in the first community, which of the following relationships is the first user and the second user in the first community: the second user a user who is a friend of the first user, a second friend who is a second user of the first user, and a user who is the first user to listen to or pay attention to, according to the user relationship chain in the second community, judges in the second community Whether the second user is the second friend of the first user, if the second user is the first user's friend or the second user is the first user's second friend or the second user is the first user listening or paying attention in the first community.
  • the user or the second user in the second community is the second user of the first user, and the closeness of the first user and the second user is correspondingly increased according to the preset weight.
  • the tightness generating module is further configured to preset a weight corresponding to the relationship between the first user and the second user, and set the weights from high to low in the following order:
  • the second user is a friend of the first user
  • the second user in the first community is a user who listens or pays attention to the first user
  • the second user is a second friend of the first user
  • the second user is the second friend of the first user.
  • system further comprises:
  • a similarity calculation module configured to calculate a similarity between the first user and the second user according to the personal data of the first user and the second user in the first community, the personal data of the first user and the second user in the second community ;
  • the familiarity calculation module is configured to calculate the familiarity of the first user and the second user according to the interaction frequency, the closeness, and the similarity.
  • the familiarity calculation module is further configured to separately set weights corresponding to the interaction frequency, the closeness, and the similarity of the first user and the second user, according to the interaction frequency, the closeness, the similarity, and the interaction.
  • the weights corresponding to the frequency, the closeness, and the similarity increase the familiarity of the first user and the second user accordingly.
  • the first community user identifier of the same user is different from the second community user identifier, and the first community and the second community share the user identifier correspondence relationship library, wherein the user correspondence database stores the first user of the same user. Correspondence between the community user identifier and the second community user identifier;
  • the recommendation module is further configured to obtain a second community user identifier of the first user, and search according to the second community user identifier of the first user and the correspondence between the first community user identifier of the same user and the second community user identifier. a first community user identifier of the first user; a first community user identifier of the second user corresponding to the first user identifier of the first user that is more than the threshold of the first user; and the first community user according to the second user And identifying, by the identifier, the second community user identifier of the second user, and displaying, by the first user, the second user list corresponding to the found second community user identifier.
  • One or more computer storage media containing computer executable instructions for performing a user recommendation method in an SNS community, the method comprising the steps of:
  • a second user with a first user's familiarity exceeding a threshold is recommended to the first user in the second community.
  • the user recommendation method and system and the computer storage medium in the SNS community generate an interaction frequency between the first user and the second user according to the interaction record of the first user and the second user in the first community, according to the first user and the second user.
  • the user's interaction frequency calculates the familiarity of the first user and the second user, and in the second community, the second user who has the familiarity of the first user exceeding the threshold is recommended to the first user, and the second user and the first user are familiar with each other.
  • the degree is high, indicating that the second user is a person that the first user may know.
  • the above method and system calculate the familiarity between users according to the interaction frequency of the user in other communities, and recommend other users to the user according to the familiarity, and expand the people that can be used to determine which other users are likely to be recognized by the user.
  • the source of information so that more people can be reached to the users, and improve the efficiency of the user relationship circle.
  • FIG. 1 is a schematic flowchart of a user recommendation method in an SNS community in an embodiment
  • FIG. 2 is a schematic flowchart of generating a closeness between a first user and a second user according to a user relationship chain in a first community and a user relationship chain in a second community in an embodiment
  • FIG. 3 is a schematic structural diagram of a user recommendation system in an SNS community in an embodiment
  • FIG. 4 is a schematic structural diagram of a user recommendation system in an SNS community in another embodiment
  • FIG. 5 is a schematic structural diagram of a user recommendation system in an SNS community in still another embodiment.
  • a user recommendation method in an SNS community includes the following steps:
  • Step S102 Acquire an interaction record of the first user and the second user in the first community.
  • the number of the first community may be multiple, and the types of the first community may also be multiple, such as a microblog platform, a forum community, and the like.
  • Step S102 may acquire an interaction record of the first user and the second user in the plurality of SNS communities.
  • interactions between users in the first community may be pre-recorded and interaction records between the users may be maintained.
  • the interactive operation is any read operation by the user to read relevant information of other users in the community, as well as any write operations for other users' related information in the community.
  • the interaction record includes at least one of an operation record of access, comment, reply, praise, forward, reprint, share, and the like.
  • Step S104 Generate an interaction frequency between the first user and the second user according to the interaction record.
  • a user performing a read operation on other users' related information in the community or a write operation on other users' related information in the community may be recorded as an interactive operation between the users.
  • the number of interaction operations between the first user and the second user in a certain time period may be counted, and the interaction frequency between the first user and the second user is calculated as the ratio of the number of interaction operations to the duration of the time period.
  • Step S106 calculating the familiarity of the first user and the second user according to the interaction frequency.
  • the familiarity and the frequency of interaction may be pre-set in a proportional relationship.
  • the familiarity of the first user and the second user may be increased according to the interaction frequency and the proportional relationship.
  • Step S108 recommending, to the first user, the second user that the first user's familiarity exceeds the threshold in the second community.
  • the second user may be recommended to the first user as a person that the first user may be aware of.
  • the first user may be presented with a list of second users whose first level of familiarity exceeds a threshold for the first user to select a second user that they wish to add as a friend, or who wish to listen to, follow. Further, the second user selected by the first user may be obtained, the selected second user is added as the friend of the first user, or added to the object that the first user listens to or pays attention to.
  • step S108 may filter out a second user who is not a friend in the second community with the first user in the second user whose popularity of the first user exceeds the threshold, and select the second user as the second user.
  • the person that the first user may know is recommended to the first user.
  • filtering the second user who is already the first user friend in the second community may avoid repeatedly recommending the friend to the first user or the user that the first user has listened to or paid attention to.
  • the users in the user recommendation method in the above SNS community are registered users in the first community and the second community.
  • the first community shares a user authentication information base with the second community, and the same user has the same user identity as the second community in the first community.
  • the user identifiers of the user in the first community and the second community are respectively referred to as the first community user identifier of the user and the second community user identifier of the user.
  • the first community user identifier of the same user is different from the second community user identifier, the first community and the second community share the user identity correspondence relationship library, and the first community user of the same user is saved in the user correspondence database.
  • the correspondence between the identifier and the second community user identifier is different from the second community user identifier, the first community and the second community share the user identity correspondence relationship library, and the first community user of the same user is saved in the user correspondence database.
  • step S108 includes: acquiring a second community user identifier of the first user; searching for the first community user identifier of the first user according to the second community user identifier of the first user and the corresponding relationship; a first community user identifier of the second user whose first user identifier is corresponding to the first user, and a second user identifier of the second user according to the first community user identifier of the second user and the corresponding relationship The community user identifier; displaying, to the first user, the second user list corresponding to the found second community user identifier.
  • the user recommendation method in the SNS community generates an interaction frequency between the first user and the second user according to the interaction record between the first user and the second user in the first community, and calculates the interaction frequency according to the interaction frequency between the first user and the second user.
  • the second user is recommended to the first user in the second community, and the second user and the first user have high familiarity, indicating that the second user has a high level of familiarity with the first user.
  • the user is the person that the first user may know.
  • the above method calculates the familiarity between users according to the interaction frequency of the user in other communities, and recommends other users to the user according to the familiarity, and expands the information that can be used to determine which other users are people that the user may know. Source, so that you can get more people who the user may know, and improve the efficiency of expanding the user relationship circle.
  • the user recommendation method in the foregoing SNS community further includes the step of: generating the closeness of the first user and the second user according to the user relationship chain in the first community and the user relationship chain in the second community.
  • the user relationship chain of the first community is a relationship chain established between users in the first community, including social relationships such as friend relationship, listening or attention relationship.
  • the user relationship chain of the second community is the relationship chain established between the users in the second community. Specifically, if the first user and the second user have a social relationship in the first community or the second community, the closeness of the first user and the second user may be increased accordingly.
  • the specific process of step S106 is: calculating the familiarity of the first user and the second user according to the interaction frequency and tightness of the first user and the second user.
  • the weight corresponding to the interaction frequency of the first user and the second user and the weight corresponding to the closeness of the first user and the second user may be separately set in advance.
  • Step S106 may increase the familiarity of the first user and the second user according to the interaction frequency and tightness of the first user and the second user, and the weight corresponding to the interaction frequency and the closeness. The higher the frequency and closeness of interaction between the first user and the second user, the higher the familiarity between the first user and the second user.
  • the specific process of the step of calculating the closeness between users according to the user relationship chain in the first community and the user relationship chain in the second community includes:
  • Step S202 Determine, according to the user relationship chain in the first community, which of the following relationships is the first user and the second user in the first community: the second user is the friend of the first user, and the second user is the first user.
  • the second friend and the second user are the users who are listening or paying attention to the first user.
  • the second user who is the second user of the first user refers to the friend whose second user is the friend of the first user.
  • Step S204 Determine, according to the user relationship chain in the second community, whether the second user is the second user of the first user in the second community.
  • Step S206 If the second user is the first user's friend or the second user is the first user's second friend or the second user is the first user listening or paying attention to, or in the second community, in the first community
  • the second user is the second friend of the first user, and the closeness of the first user and the second user is correspondingly increased according to the preset weight.
  • the weight corresponding to the relationship between the first user and the second user may be preset.
  • the weight may be set from high to low in the following order: the second user is the friend of the first user in the first community.
  • the second user is the first user listening or paying attention
  • the second user is the second user in the second community
  • the second user is the first user in the first community. Friends.
  • the closeness of the relationship between the first user and the second user in the above-mentioned ordering is sequentially reduced, and the weights corresponding to the above-mentioned relationships are also sequentially lowered, so that the more compactness of the first user and the second user can be obtained.
  • the user recommendation method in the above SNS community generates the closeness between the users according to the user relationship chain of the community and the user relationship chain of other communities, and calculates the interaction frequency between the users and the closeness between the users to calculate the user's
  • the user can be recommended to the user in the community, and the comprehensive knowledge of the community and other communities can be used to calculate the familiarity between the users, which can be more accurately obtained.
  • the true familiarity between users thereby improving the accuracy of recommending to the user the people they might know.
  • the user recommendation method in the foregoing SNS community further includes the steps of: according to the personal data of the first user and the second user in the first community, the personal data of the first user and the second user in the second community The similarity between the first user and the second user is calculated.
  • the first user may be correspondingly increased.
  • the similarity of the second user if the personal information of the first user and the second user in the first community are the same or similar, or the personal data of the first user and the second user in the second community are the same or similar, the first user may be correspondingly increased. The similarity of the second user.
  • the personal information includes: hometown, educational experience, work experience, current place of residence, and the like. If the first user and the second user's hometown, educational experience, work experience, and current residence are the same or similar in the first community or the second community, the first user and the second user may be correspondingly increased according to the preset weights. Similarity.
  • step S106 is: calculating the familiarity of the first user and the second user according to the interaction frequency, the closeness, and the similarity of the first user and the second user.
  • the weights of the interaction frequency, the closeness, and the similarity of the first user and the second user may be respectively set in advance according to the interaction frequency, the closeness, the similarity, and the interaction frequency, the closeness, and the similarity.
  • the weight corresponding to the degree increases the familiarity of the first user and the second user accordingly. The higher the degree of interaction between the first user and the second user, the higher the degree of closeness, the higher the familiarity between the first user and the second user.
  • the user recommendation method in the above SNS community calculates the similarity between the users according to the personal data of the users of the community and other communities, and calculates the familiarity between the users by the frequency, closeness and similarity between the users. And according to the familiarity between users, recommending to the users in the community that they may know, and comprehensively calculating the familiarity between the users and other communities to calculate the familiarity between the users, and more accurately obtain the users. True familiarity, thereby improving the accuracy of recommending to the user the people they might know.
  • a user recommendation system in an SNS community includes a record acquisition module 302, an interaction frequency generation module 304, a familiarity calculation module 306, and a recommendation module 308, wherein:
  • the record obtaining module 302 is configured to obtain an interaction record of the first user and the second user in the first community.
  • the number of the first community may be multiple, and the types of the first community may also be multiple, such as a microblogging platform, a forum community, and the like.
  • the record acquisition module 302 can obtain an interaction record of the first user and the second user in the plurality of SNS communities.
  • interactions between users in the first community may be pre-recorded and interaction records between the users may be maintained.
  • the interactive operation is any read operation by the user to read relevant information of other users in the community, as well as any write operations for other users' related information in the community.
  • the interaction record includes at least one of an operation record of access, comment, reply, praise, forward, reprint, share, and the like.
  • the interaction frequency generation module 304 is configured to generate an interaction frequency of the first user and the second user according to the interaction record.
  • a user performing a read operation on other users' related information in the community or a write operation on other users' related information in the community may be recorded as an interactive operation between the users.
  • the interaction frequency generation module 304 can count the number of interaction operations between the first user and the second user in a certain time period, and calculate the interaction frequency between the first user and the second user as the ratio of the number of interaction operations to the duration of the time period. .
  • the familiarity calculation module 306 is configured to calculate the familiarity of the first user and the second user according to the interaction frequency.
  • the familiarity and the frequency of interaction may be pre-set in a proportional relationship.
  • the familiarity calculation module 306 can increase the familiarity of the first user and the second user according to the interaction frequency and the proportional relationship described above.
  • the recommendation module 308 is configured to recommend, to the first user, a second user that has a familiarity with the first user exceeding a threshold in the second community.
  • the recommendation module 308 can recommend the second user to the first user as a person that the first user may know.
  • the recommendation module 308 can present to the first user a list of second users whose first level of familiarity exceeds a threshold for the first user to select a second user that they wish to add as a friend, or wish to listen to, follow user. Further, the recommendation module 308 may acquire the second user selected by the first user, add the selected second user as a friend of the first user, or join the object that the first user listens to or pays attention to.
  • the recommendation module 308 may filter out a second user who is not a friend in the second community with the first user in the second user whose popularity with the first user exceeds the threshold, and the second user to be filtered out.
  • the person who is known as the first user is recommended to the first user.
  • filtering the second user who is already the first user friend in the second community may avoid repeatedly recommending the friend to the first user or the user that the first user has listened to or paid attention to.
  • the users in the user recommendation system in the above SNS community are registered users in the first community and the second community.
  • the first community shares a user authentication information base with the second community, and the same user has the same user identity as the second community in the first community.
  • the user identifiers of the user in the first community and the second community are respectively referred to as the first community user identifier of the user and the second community user identifier of the user.
  • the first community user identifier of the same user is different from the second community user identifier, the first community and the second community share the user identity correspondence relationship library, and the first community user of the same user is saved in the user correspondence database.
  • the correspondence between the identifier and the second community user identifier is different from the second community user identifier, the first community and the second community share the user identity correspondence relationship library, and the first community user of the same user is saved in the user correspondence database.
  • the recommendation module 308 may obtain the second community user identifier of the first user, and search for the first community user identifier of the first user according to the second community user identifier of the first user and the corresponding relationship;
  • the first community user identifier corresponding to the first user whose first user is familiar with the threshold exceeds the threshold;
  • the second community user identifier of the second user is searched according to the first community user identifier of the second user and the corresponding relationship Displaying, to the first user, the second user list corresponding to the found second community user identifier.
  • the user recommendation system in the SNS community generates an interaction frequency between the first user and the second user according to the interaction record of the first user and the second user in the first community, and calculates the interaction frequency according to the interaction frequency between the first user and the second user.
  • the second user is recommended to the first user in the second community, and the second user and the first user have high familiarity, indicating that the second user has a high level of familiarity with the first user.
  • the user is the person that the first user may know.
  • the above method calculates the familiarity between users according to the interaction frequency of the user in other communities, and recommends other users to the user according to the familiarity, and expands the information that can be used to determine which other users are people that the user may know. Source, so that you can get more people who the user may know, and improve the efficiency of expanding the user relationship circle.
  • the user recommendation system in the SNS community includes a record acquisition module 302, an interaction frequency generation module 304, a tightness generation module 404, a familiarity calculation module 406, and a recommendation module 308, where:
  • the tightness generating module 404 is configured to generate the closeness of the first user and the second user according to the user relationship chain in the first community and the user relationship chain in the second community.
  • the user relationship chain of the first community is a relationship chain established between users in the first community, including social relationships such as friend relationship, listening or attention relationship.
  • the user relationship chain of the second community is the relationship chain established between the users in the second community.
  • the tightness generating module 404 is configured to determine, according to the user relationship chain in the first community, which of the following relationships is the first user and the second user in the first community: the second user is a friend of the first user, a second friend of the first user, a user who is the first user to listen to or pay attention to; and a second user in the second community according to the user relationship chain in the second community Whether it is the second friend of the first user; further, if the second user is the friend of the first user or the second user is the second friend of the first user or the second user is listening to the first user or If the user concerned or the second user in the second community is the second friend of the first user, the closeness of the first user and the second user is correspondingly increased according to the preset weight.
  • the second user who is the second user of the first user refers to the friend whose second user is the friend of the first user.
  • the tightness generating module 404 may preset a weight corresponding to the relationship between the first user and the second user.
  • the weight may be set from high to low in the following order: in the first community, the second user is a friend of the first user, a user who listens or pays attention to the first user in the first community, a second user who is the second user of the first user in the second community, and a second user in the first community The second user of the first user.
  • the closeness of the relationship between the first user and the second user in the above-mentioned ordering is sequentially reduced, and the weights corresponding to the above-mentioned relationships are also sequentially lowered, so that the more compactness of the first user and the second user can be obtained.
  • the familiarity calculation module 406 is configured to calculate the familiarity of the first user and the second user according to the interaction frequency and the closeness of the first user and the second user.
  • the weight corresponding to the interaction frequency of the first user and the second user and the weight corresponding to the closeness of the first user and the second user may be separately set in advance.
  • the familiarity calculation module 406 can increase the familiarity of the first user and the second user according to the interaction frequency and tightness of the first user and the second user, and the weight corresponding to the interaction frequency and the closeness. The higher the frequency and closeness of interaction between the first user and the second user, the higher the familiarity between the first user and the second user.
  • the user recommendation system in the above SNS community generates the closeness between the users according to the user relationship chain of the community and the user relationship chain of other communities, and calculates the interaction frequency between the users and the closeness between the users.
  • the user can be recommended to the user in the community, and the comprehensive knowledge of the community and other communities can be used to calculate the familiarity between the users, which can be more accurately obtained.
  • the true familiarity between users thereby improving the accuracy of recommending to the user the people they might know.
  • a user recommendation system in an SNS community includes a record acquisition module 302, an interaction frequency generation module 304, a tightness generation module 404, a similarity calculation module 504, and a familiarity calculation module 506. , recommendation module 308, wherein:
  • the similarity calculation module 504 is configured to calculate the similarity between the first user and the second user according to the personal data of the first user and the second user in the first community, the personal data of the first user and the second user in the second community. .
  • the similarity calculation module 504 may correspondingly Increase the similarity between the first user and the second user.
  • the personal information includes: hometown, educational experience, work experience, current place of residence, and the like. If the first user and the second user's hometown, educational experience, work experience, and current residence are the same or similar in the first community or the second community, the similarity calculation module 504 may increase the first according to the preset weight. The similarity between the user and the second user.
  • the familiarity calculation module 506 is configured to calculate the familiarity of the first user and the second user according to the interaction frequency, the closeness, and the similarity between the first user and the second user.
  • the weights corresponding to the interaction frequency, the closeness, and the similarity of the first user and the second user may be separately set in advance.
  • the familiarity calculation module 506 can increase the interaction frequency, the closeness and the similarity, and the weights corresponding to the interaction frequency, the closeness, and the similarity to increase the familiarity of the first user and the second user. The higher the degree of interaction between the first user and the second user, the higher the degree of closeness, the higher the familiarity between the first user and the second user.
  • the user recommendation system in the above SNS community calculates the similarity between the users according to the personal data of the users of the community and other communities, and calculates the familiarity between the users by the frequency, closeness and similarity between the users. And according to the familiarity between users, recommending to the users in the community that they may know, and comprehensively calculating the familiarity between the users and other communities to calculate the familiarity between the users, and more accurately obtain the users. True familiarity, thereby improving the accuracy of recommending to the user the people they might know.
  • the storage medium may be a magnetic disk, an optical disk, or a read-only storage memory (Read-Only) Memory, ROM) or Random Access Memory (RAM).

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Primary Health Care (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Multimedia (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Description

SNS社区中的用户推荐方法和系统、计算机存储介质
本申请要求于2012年6月1日提交中国专利局、申请号为201210178965.0、发明名称为“SNS社区中的用户推荐方法和系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
【技术领域】
本发明涉及社交网络服务领域，特别地涉及一种SNS社区中的用户推荐方法和系统、计算机存储介质。
【背景技术】
SNS（Social Networking Services）即社交网络服务，专指旨在帮助人们建立社会性网络的互联网应用服务。SNS社区则为提供社交网络服务的网站或平台。人们在SNS社区中结识朋友，与他人即时分享信息和知识，SNS已经越来越深入到人们的生活、工作和学习中。
随着网络技术的发展，SNS社区已经迅速发展为包括：结识朋友、拓展关系圈、展现自我、分享信息、游戏娱乐等多种功能的综合平台。根据侧重功能点的不同，可分为各种不同类型的SNS社区，例如，有的SNS社区具有博客的功能，而且在该SNS社区内用户可打造具有自身特色的个人空间。而有的SNS社区则侧重于拓展用户关系圈，给用户提供一个交友平台。随着信息技术的发展以及网络应用的不断更新，用户的需要在不断发生着变化，旧的SNS社区也不断的衍生出具有新功能的SNS社区，以满足用户的需求。
SNS社区通常都具有用户推荐的功能，即将用户可能感兴趣的其他用户推荐给该用户。SNS社区的用户推荐功能可以帮助用户查看到其可能感兴趣的其他用户，可以有效帮助用户拓展关系圈，从而防止社区用户流失。传统的SNS社区中的用户推荐方法，通常将SNS社区与即时通信相关联，若用户之间在即时通信上为好友，则在SNS社区中将用户在即时通信上的好友推荐给该用户。
然而，传统的这种SNS社区中的用户推荐方法，仅将用户在即时通信上的好友推荐给该用户，可以推荐的用户数量较少且可能会漏掉很多用户更可能感兴趣的人，因此，传统的SNS社区中的用户推荐方法会使得拓展用户关系圈的效率较低。
【发明内容】
基于此，有必要提供一种能提高拓展用户关系圈的效率的SNS社区中的用户推荐方法。
一种SNS社区中的用户推荐方法，包括以下步骤：
获取第一用户和第二用户在第一社区中的互动记录；
根据所述互动记录生成第一用户与第二用户的互动频率；
根据所述互动频率计算第一用户与第二用户的熟识度；
在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户。
在其中一个实施例中，所述互动记录包括第一用户与第二用户之间的访问、评论、回复、赞、转发、转载、分享中的至少一种操作记录。
在其中一个实施例中，所述方法还包括：
根据第一社区中的用户关系链和第二社区中的用户关系链生成第一用户与第二用户的紧密度；
所述根据互动频率计算第一用户与第二用户的熟识度的步骤为：
根据所述互动频率和所述紧密度计算所述第一用户与第二用户的熟识度。
在其中一个实施例中，所述根据所述第一社区的用户关系链和第二社区的用户关系链生成第一用户与第二用户的紧密度的步骤包括：
根据所述第一社区中的用户关系链判断在第一社区中第一用户与第二用户的关系为以下哪一种：第二用户为第一用户的好友、第二用户为第一用户的二度好友、第二用户为第一用户收听或关注的用户；
根据所述第二社区中的用户关系链判断在第二社区中第二用户是否为第一用户的二度好友；
若在第一社区中第二用户为第一用户的好友或第二用户为第一用户的二度好友或第二用户为第一用户收听或关注的用户、或在第二社区中第二用户为第一用户的二度好友，则根据预设的权重相应的增加第一用户与第二用户的紧密度。
在其中一个实施例中，所述方法还包括：
设置第一用户与第二用户的关系对应的权重，且按照以下顺序从高到低设置权重：
在第一社区中第二用户为第一用户的好友、在第一社区中第二用户为第一用户收听或关注的用户、在第二社区中第二用户为第一用户的二度好友、在第一社区中第二用户为第一用户的二度好友。
在其中一个实施例中，所述方法还包括：
根据第一用户和第二用户在第一社区中的个人资料、第一用户和第二用户在第二社区中的个人资料计算第一用户与第二用户的相似度；
所述根据所述互动频率计算第一用户与第二用户的熟识度的步骤为：
根据所述互动频率、所述紧密度和所述相似度计算所述第一用户与第二用户的熟识度。
在其中一个实施例中，所述根据第一用户与第二用户的互动频率、紧密度和相似度计算第一用户与第二用户的熟识度的步骤包括：预先分别设置第一用户与第二用户的互动频率、紧密度、相似度对应的权重，根据互动频率、紧密度、相似度以及互动频率、紧密度、相似度对应的权重相应的增加第一用户与第二用户的熟识度。
在其中一个实施例中，同一用户的第一社区用户标识与第二社区用户标识不同，第一社区与第二社区共享用户标识对应关系库，其中，用户对应关系库中保存同一用户的第一社区用户标识与第二社区用户标识之间的对应关系；
所述在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户的步骤包括：
获取第一用户的第二社区用户标识；
根据第一用户的第二社区用户标识以及同一用户的第一社区用户标识与第二社区用户标识之间的对应关系，查找第一用户的第一社区用户标识；
获取第一用户的第一社区用户标识对应的与第一用户熟识度超过阈值的第二用户的第一社区用户标识；
根据第二用户的第一社区用户标识以及上述对应关系查找第二用户的第二社区用户标识；
向第一用户展示查找到的第二社区用户标识对应的第二用户列表。
基于此，还有必要提供一种能提高拓展用户关系圈的效率的SNS社区中的用户推荐系统。
一种SNS社区中的用户推荐系统，包括：
记录获取模块，用于获取第一用户和第二用户在第一社区中的互动记录；
互动频率生成模块，用于根据所述互动记录生成第一用户与第二用户的互动频率；
熟识度计算模块，用于根据所述互动频率计算第一用户与第二用户的熟识度；
推荐模块，用于在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户。
在其中一个实施例中，所述互动记录包括第一用户与第二用户之间的访问、评论、回复、赞、转发、转载、分享中的至少一种操作记录。
在其中一个实施例中，所述系统还包括：
紧密度生成模块，用于根据第一社区中的用户关系链和第二社区中的用户关系链生成第一用户与第二用户的紧密度；
所述熟识度计算模块用于根据所述互动频率和所述紧密度计算所述第一用户与第二用户的熟识度。
在其中一个实施例中，所述紧密度生成模块用于根据所述第一社区中的用户关系链判断在第一社区中第一用户与第二用户的关系为以下哪一种：第二用户为第一用户的好友、第二用户为第一用户的二度好友、第二用户为第一用户收听或关注的用户，根据所述第二社区中的用户关系链判断在第二社区中第二用户是否为第一用户的二度好友，若在第一社区中第二用户为第一用户的好友或第二用户为第一用户的二度好友或第二用户为第一用户收听或关注的用户、或在第二社区中第二用户为第一用户的二度好友，则根据预设的权重相应的增加第一用户与第二用户的紧密度。
在其中一个实施例中，所述紧密度生成模块还用于预先设置第一用户与第二用户的关系对应的权重，且按照以下顺序从高到低设置权重：
在第一社区中第二用户为第一用户的好友、在第一社区中第二用户为第一用户收听或关注的用户、在第二社区中第二用户为第一用户的二度好友、在第一社区中第二用户为第一用户的二度好友。
在其中一个实施例中，所述系统还包括：
相似度计算模块，用于根据第一用户和第二用户在第一社区中的个人资料、第一用户和第二用户在第二社区中的个人资料计算第一用户与第二用户的相似度；
所述熟识度计算模块用于根据所述互动频率、所述紧密度和所述相似度计算所述第一用户与第二用户的熟识度。
在其中一个实施例中，所述熟识度计算模块还用于预先分别设置第一用户与第二用户的互动频率、紧密度、相似度对应的权重，根据互动频率、紧密度、相似度以及互动频率、紧密度、相似度对应的权重相应的增加第一用户与第二用户的熟识度。
在其中一个实施例中，同一用户的第一社区用户标识与第二社区用户标识不同，第一社区与第二社区共享用户标识对应关系库，其中，用户对应关系库中保存同一用户的第一社区用户标识与第二社区用户标识之间的对应关系；
所述推荐模块还用于获取第一用户的第二社区用户标识；根据第一用户的第二社区用户标识以及同一用户的第一社区用户标识与第二社区用户标识之间的对应关系，查找第一用户的第一社区用户标识；获取第一用户的第一社区用户标识对应的与第一用户熟识度超过阈值的第二用户的第一社区用户标识；根据第二用户的第一社区用户标识以及上述对应关系查找第二用户的第二社区用户标识；向第一用户展示查找到的第二社区用户标识对应的第二用户列表。
此外，还提供一种计算机存储介质。
一个或多个包含计算机可执行指令的计算机存储介质，所述计算机可执行指令用于执行一种SNS社区中的用户推荐方法，所述方法包括以下步骤：
获取第一用户和第二用户在第一社区中的互动记录；
根据所述互动记录生成第一用户与第二用户的互动频率；
根据所述互动频率计算第一用户与第二用户的熟识度；
在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户。
上述SNS社区中的用户推荐方法和系统、计算机存储介质，根据第一用户和第二用户在第一社区中的互动记录生成第一用户与第二用户的互动频率，根据第一用户与第二用户的互动频率计算第一用户与第二用户的熟识度，在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给第一用户，第二用户与第一用户的熟识度高，说明第二用户是第一用户可能认识的人。上述方法和系统，根据用户在其他社区中的互动频率计算用户之间的熟识度，并根据熟识度在本社区中向用户推荐其他用户，拓展了可用于判断哪些其他用户是用户可能认识的人的信息源，从而可更多的获取到用户可能认识的人，提高拓展用户关系圈的效率。
【附图说明】
图1为一个实施例中的SNS社区中的用户推荐方法的流程示意图；
图2为一个实施例中根据第一社区中的用户关系链与第二社区中的用户关系链生成第一用户与第二用户的紧密度的流程示意图；
图3为一个实施例中的SNS社区中的用户推荐系统的结构示意图；
图4为另一实施例中的SNS社区中的用户推荐系统的结构示意图；
图5为又一实施例中的SNS社区中的用户推荐系统的结构示意图。
【具体实施方式】
如图1所示，在一个实施例中，一种SNS社区中的用户推荐方法，包括以下步骤：
步骤S102，获取第一用户和第二用户在第一社区中的互动记录。
在一个实施例中，第一社区的数量可以为多个，第一社区的种类也可以为多种，例如微博平台、论坛社区等等。步骤S102可获取多个SNS社区中的第一用户和第二用户的互动记录。
在一个实施例中，可预先记录在第一社区中用户之间的互动操作，并保存用户之间的互动记录。
在一个实施例中，互动操作为用户读取其他用户在社区中的相关信息的任何读操作、以及针对其他用户的在社区中的相关信息进行的任何写操作。
在一个实施例中，互动记录包括访问、评论、回复、赞、转发、转载、分享等操作中的至少一种操作记录。
步骤S104，根据互动记录生成第一用户与第二用户的互动频率。
在一个实施例中，用户对其他用户在社区中的相关信息进行一次读操作、或针对其他用户的在社区中的相关信息进行的一次写操作，都可记为用户之间的一次互动操作。
具体的，可统计某一时段内第一用户与第二用户之间的互动操作的次数，计算第一用户与第二用户的互动频率为互动操作次数与该时段时长的比值。
步骤S106，根据互动频率计算第一用户与第二用户的熟识度。
在一个实施例中，可预先设置熟识度与互动频率为正比例关系。第一用户与第二用户的互动频率越高，则第一用户与第二用户的熟识度也越高。获取到第一用户与第二用户的互动频率后，可根据该互动频率以及上述正比例关系相应的增加第一用户与第二用户的熟识度。
步骤S108，在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给第一用户。
在一个实施例中，可将第二用户作为第一用户可能认识的人推荐给第一用户。
在一个实施例中，可向第一用户展示与第一用户的熟识度超过阈值的第二用户的列表，供第一用户选择其希望加为好友、或希望收听、关注的第二用户。进一步的，可获取第一用户选择的第二用户，将选择的第二用户加为第一用户的好友，或加入到第一用户收听或关注的对象中。
在一个实施例中，步骤S108可在与第一用户的熟识度超过阈值的第二用户中筛选出与第一用户在第二社区中不是好友的第二用户，将筛选出的第二用户作为第一用户可能认识的人推荐给第一用户。本实施例中，过滤在第二社区中已经是第一用户好友的第二用户，可避免向第一用户重复推荐好友或第一用户已经收听或关注的用户。
上述SNS社区中的用户推荐方法中的用户在第一社区和第二社区都为注册用户。
在一个实施例中，第一社区与第二社区共享用户验证信息库，同一用户在第一社区与第二社区的用户标识相同。用户在第一社区与第二社区的用户标识分别称为用户的第一社区用户标识、用户的第二社区用户标识。
在另一个实施例中，同一用户的第一社区用户标识与第二社区用户标识不同，第一社区与第二社区共享用户标识对应关系库，用户对应关系库中保存同一用户的第一社区用户标识与第二社区用户标识之间的对应关系。
本实施例中，步骤S108的具体过程包括：获取第一用户的第二社区用户标识；根据第一用户的第二社区用户标识以及上述对应关系查找第一用户的第一社区用户标识；获取第一用户的第一社区用户标识对应的与第一用户熟识度超过阈值的第二用户的第一社区用户标识；根据第二用户的第一社区用户标识以及上述对应关系查找第二用户的第二社区用户标识；向第一用户展示查找到的第二社区用户标识对应的第二用户列表。
上述SNS社区中的用户推荐方法，根据第一用户和第二用户在第一社区的中互动记录生成第一用户与第二用户的互动频率，根据第一用户与第二用户的互动频率计算第一用户与第二用户的熟识度，在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给第一用户，第二用户与第一用户的熟识度高，说明第二用户是第一用户可能认识的人。上述方法，根据用户在其他社区中的互动频率计算用户之间的熟识度，并根据熟识度在本社区中向用户推荐其他用户，拓展了可用于判断哪些其他用户是用户可能认识的人的信息源，从而可更多的获取到用户可能认识的人，提高拓展用户关系圈的效率。
在一个实施例中，上述SNS社区中的用户推荐方法还包括步骤：根据第一社区中的用户关系链与第二社区中的用户关系链生成第一用户与第二用户的紧密度。
具体的，第一社区的用户关系链即为第一社区中用户之间所建立的关系链，包括好友关系、收听或关注关系等社交关系。第二社区的用户关系链即为第二社区中用户之间所建立的关系链。具体的，若第一用户与第二用户在第一社区或第二社区中具有社交关系，则可相应的增加第一用户与第二用户的紧密度。本实施例中，步骤S106的具体过程为：根据第一用户与第二用户的互动频率和紧密度计算第一用户与第二用户的熟识度。
具体的，在一个实施例中，可预先分别设置第一用户与第二用户的互动频率对应的权重以及第一用户与第二用户的紧密度对应的权重。步骤S106可根据第一用户与第二用户的互动频率和紧密度以及互动频率和紧密度对应的权重，相应的增加第一用户与第二用户的熟识度。第一用户与第二用户的互动频率和紧密度越高，则第一用户与第二用户的熟识度越高。
如图2所示，在一个实施例中，根据第一社区中的用户关系链与第二社区中的用户关系链统计用户之间的紧密度的步骤的具体过程包括：
步骤S202，根据第一社区中的用户关系链判断在第一社区中第一用户与第二用户的关系为以下哪一种：第二用户为第一用户的好友、第二用户为第一用户的二度好友、第二用户为第一用户收听或关注的用户。
第二用户为第一用户的二度好友指的是第二用户为第一用户的好友的好友。
步骤S204，根据第二社区中的用户关系链判断在第二社区中第二用户是否为第一用户的二度好友。
步骤S206，若在第一社区中第二用户为第一用户的好友或第二用户为第一用户的二度好友或第二用户为第一用户收听或关注的用户、或在第二社区中第二用户为第一用户的二度好友，则根据预设的权重相应的增加第一用户与第二用户的紧密度。
在一个实施例中，可预先设置第一用户与第二用户的关系对应的权重，优选的，可按照以下顺序从高到低设置权重：在第一社区中第二用户为第一用户的好友、在第一社区中第二用户为第一用户收听或关注的用户、在第二社区中第二用户为第一用户的二度好友、在第一社区中第二用户为第一用户的二度好友。上述排序的第一用户与第二用户的关系的紧密度是依次降低的，设置上述关系对应的权重也依次降低，从而可获得更加精确的第一用户与第二用户的紧密度。
上述SNS社区中的用户推荐方法，根据本社区的用户关系链与其他社区的用户关系链生成用户之间的紧密度，并综合上述用户之间的互动频率以及用户之间的紧密度计算用户之间的熟识度，并根据用户之间的熟识度在本社区中向用户推荐其可能认识的人，综合本社区与其他社区的多方面的信息计算用户之间的熟识度，能更加准确的获取用户之间的真实熟识度，从而提高向用户推荐其可能认识的人的准确度。
在一个实施例中，上述SNS社区中的用户推荐方法还包括步骤：根据第一用户和第二用户在第一社区中的个人资料、第一用户和第二用户在第二社区中的个人资料计算第一用户与第二用户的相似度。
具体的，若第一用户和第二用户在第一社区的个人资料相同或相近，或者第一用户和第二用户在第二社区的个人资料相同或相近，则可相应的增加第一用户与第二用户的相似度。
具体的，在一个实施例中，个人资料包括：家乡、教育经历、工作经历、现居住地等。若第一用户与第二用户的家乡、教育经历、工作经历、现居住地在第一社区或第二社区中相同或相近，则可按照预设的权重相应的增加第一用户与第二用户的相似度。
本实施例中，步骤S106的具体过程为：根据第一用户与第二用户的互动频率、紧密度和相似度计算第一用户与第二用户的熟识度。
具体的，在一个实施例中，可预先分别设置第一用户与第二用户的互动频率、紧密度、相似度对应的权重，根据互动频率、紧密度、相似度以及互动频率、紧密度、相似度对应的权重相应的增加第一用户与第二用户的熟识度。第一用户与第二用户的互动频率、紧密度相似度越高，则第一用户与第二用户的熟识度越高。
上述SNS社区中的用户推荐方法，根据本社区与其他社区的用户的个人资料计算用户之间的相似度，并综合上述用户之间的互动频率、紧密度以及相似度计算用户之间的熟识度，并根据用户之间的熟识度在本社区中向用户推荐其可能认识的人，综合本社区与其他社区的多方面的信息计算用户之间的熟识度，能更加准确的获取用户之间的真实熟识度，从而提高向用户推荐其可能认识的人的准确度。
如图3所示，在一个实施例中，一种SNS社区中的用户推荐系统，包括记录获取模块302、互动频率生成模块304、熟识度计算模块306、推荐模块308，其中：
记录获取模块302用于获取第一用户和第二用户在第一社区中的互动记录。
在一个实施例中，第一社区的数量可以为多个，第一社区的种类也可以为多种，例如微博平台，论坛社区等等。记录获取模块302可获取多个SNS社区中第一用户和第二用户的互动记录。
在一个实施例中，可预先记录在第一社区中用户之间的互动操作，并保存用户之间的互动记录。
在一个实施例中，互动操作为用户读取其他用户在社区中的相关信息的任何读操作、以及针对其他用户的在社区中的相关信息进行的任何写操作。在一个实施例中，互动记录包括访问、评论、回复、赞、转发、转载、分享等操作中的至少一种操作记录。
互动频率生成模块304用于根据上述互动记录生成第一用户与第二用户的互动频率。
在一个实施例中，用户对其他用户在社区中的相关信息进行一次读操作、或针对其他用户的在社区中的相关信息进行的一次写操作，都可记为用户之间的一次互动操作。
具体的，互动频率生成模块304可统计某一时段内第一用户与第二用户之间的互动操作的次数，计算第一用户与第二用户的互动频率为互动操作次数与该时段时长的比值。
熟识度计算模块306用于根据互动频率计算第一用户与第二用户的熟识度。
在一个实施例中，可预先设置熟识度与互动频率为正比例关系。第一用户与第二用户的互动频率越高，则第一用户与第二用户的熟识度也越高。熟识度计算模块306可根据互动频率以及上述正比例关系相应的增加第一用户与第二用户的熟识度。
推荐模块308用于在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给第一用户。
在一个实施例中，推荐模块308可将第二用户作为第一用户可能认识的人推荐给第一用户。
在一个实施例中，推荐模块308可向第一用户展示与第一用户的熟识度超过阈值的第二用户的列表，供第一用户选择其希望加为好友、或希望收听、关注的第二用户。进一步的，推荐模块308可获取第一用户选择的第二用户，将选择的第二用户加为第一用户的好友，或加入到第一用户收听或关注的对象中。
在一个实施例中，推荐模块308可在与第一用户的熟识度超过阈值的第二用户中筛选出与第一用户在第二社区中不是好友的第二用户，将筛选出的第二用户作为第一用户可能认识的人推荐给第一用户。本实施例中，过滤在第二社区中已经是第一用户好友的第二用户，可避免向第一用户重复推荐好友或第一用户已经收听或关注的用户。
上述SNS社区中的用户推荐系统中的用户在第一社区和第二社区都为注册用户。
在一个实施例中，第一社区与第二社区共享用户验证信息库，同一用户在第一社区与第二社区的用户标识相同。用户在第一社区与第二社区的用户标识分别称为用户的第一社区用户标识、用户的第二社区用户标识。
在另一个实施例中，同一用户的第一社区用户标识与第二社区用户标识不同，第一社区与第二社区共享用户标识对应关系库，用户对应关系库中保存同一用户的第一社区用户标识与第二社区用户标识之间的对应关系。
本实施例中，推荐模块308可获取第一用户的第二社区用户标识；根据第一用户的第二社区用户标识以及上述对应关系查找第一用户的第一社区用户标识；获取第一用户的第一社区用户标识对应的与第一用户熟识度超过阈值的第二用户的第一社区用户标识；根据第二用户的第一社区用户标识以及上述对应关系查找第二用户的第二社区用户标识；向第一用户展示查找到的第二社区用户标识对应的第二用户列表。
上述SNS社区中的用户推荐系统，根据第一用户和第二用户在第一社区中的互动记录生成第一用户与第二用户的互动频率，根据第一用户与第二用户的互动频率计算第一用户与第二用户的熟识度，在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给第一用户，第二用户与第一用户的熟识度高，说明第二用户是第一用户可能认识的人。上述方法，根据用户在其他社区中的互动频率计算用户之间的熟识度，并根据熟识度在本社区中向用户推荐其他用户，拓展了可用于判断哪些其他用户是用户可能认识的人的信息源，从而可更多的获取到用户可能认识的人，提高拓展用户关系圈的效率。
如图4所示，在一个实施例中，上述SNS社区中的用户推荐系统包括记录获取模块302、互动频率生成模块304、紧密度生成模块404、熟识度计算模块406、推荐模块308，其中：
紧密度生成模块404用于根据第一社区中的用户关系链与第二社区中的用户关系链生成第一用户与第二用户的紧密度。
具体的，第一社区的用户关系链即为第一社区中用户之间所建立的关系链，包括好友关系、收听或关注关系等社交关系。第二社区的用户关系链即为第二社区中用户之间所建立的关系链。
具体的，在一个实施例中，紧密度生成模块404用于根据第一社区中的用户关系链判断在第一社区中第一用户与第二用户的关系为以下哪一种：第二用户为第一用户的好友、第二用户为第一用户的二度好友、第二用户为第一用户收听或关注的用户；并根据第二社区中的用户关系链判断在第二社区中第二用户是否为第一用户的二度好友；进一步的，若在第一社区中第二用户为第一用户的好友或第二用户为第一用户的二度好友或第二用户为第一用户收听或关注的用户、或在第二社区中第二用户为第一用户的二度好友，则根据预设的权重相应的增加第一用户与第二用户的紧密度。
第二用户为第一用户的二度好友指的是第二用户为第一用户的好友的好友。
在一个实施例中，紧密度生成模块404可预先设置第一用户与第二用户的关系对应的权重，优选的，可按照以下顺序从高到低设置权重：在第一社区中第二用户为第一用户的好友、在第一社区中第二用户为第一用户收听或关注的用户、在第二社区中第二用户为第一用户的二度好友、在第一社区中第二用户为第一用户的二度好友。上述排序的第一用户与第二用户的关系的紧密度是依次降低的，设置上述关系对应的权重也依次降低，从而可获得更加精确的第一用户与第二用户的紧密度。
熟识度计算模块406用于根据第一用户与第二用户的互动频率和紧密度计算第一用户与第二用户的熟识度。
具体的，在一个实施例中，可预先分别设置第一用户与第二用户的互动频率对应的权重以及第一用户与第二用户的紧密度对应的权重。熟识度计算模块406可根据第一用户与第二用户的互动频率和紧密度以及互动频率和紧密度对应的权重，相应的增加第一用户与第二用户的熟识度。第一用户与第二用户的互动频率和紧密度越高，则第一用户与第二用户的熟识度越高。
上述SNS社区中的用户推荐系统，根据本社区的用户关系链与其他社区的用户关系链生成用户之间的紧密度，并综合上述用户之间的互动频率以及用户之间的紧密度计算用户之间的熟识度，并根据用户之间的熟识度在本社区中向用户推荐其可能认识的人，综合本社区与其他社区的多方面的信息计算用户之间的熟识度，能更加准确的获取用户之间的真实熟识度，从而提高向用户推荐其可能认识的人的准确度。
如图5所示，在一个实施例中，一种SNS社区中的用户推荐系统包括记录获取模块302、互动频率生成模块304、紧密度生成模块404、相似度计算模块504、熟识度计算模块506、推荐模块308，其中：
相似度计算模块504用于根据第一用户和第二用户在第一社区中的个人资料、第一用户和第二用户在第二社区中的个人资料计算第一用户与第二用户的相似度。
具体的，若第一用户和第二用户在第一社区的个人资料相同或相近，或者第一用户和第二用户在第二社区的个人资料相同或相近，则相似度计算模块504可相应的增加第一用户与第二用户的相似度。
具体的，在一个实施例中，个人资料包括：家乡、教育经历、工作经历、现居住地等。若第一用户与第二用户的家乡、教育经历、工作经历、现居住地在第一社区或第二社区中相同或相近，则相似度计算模块504可按照预设的权重相应的增加第一用户与第二用户的相似度。
熟识度计算模块506用于根据第一用户与第二用户的互动频率、紧密度和相似度计算第一用户与第二用户的熟识度。
具体的，在一个实施例中，可预先分别设置第一用户与第二用户的互动频率、紧密度和相似度对应的权重。熟识度计算模块506可将互动频率、紧密度和相似度以及互动频率、紧密度和相似度对应的权重相应的增加第一用户与第二用户的熟识度。第一用户与第二用户的互动频率、紧密度相似度越高，则第一用户与第二用户的熟识度越高。
上述SNS社区中的用户推荐系统，根据本社区与其他社区的用户的个人资料计算用户之间的相似度，并综合上述用户之间的互动频率、紧密度以及相似度计算用户之间的熟识度，并根据用户之间的熟识度在本社区中向用户推荐其可能认识的人，综合本社区与其他社区的多方面的信息计算用户之间的熟识度，能更加准确的获取用户之间的真实熟识度，从而提高向用户推荐其可能认识的人的准确度。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体（Read-Only Memory，ROM）或随机存储记忆体（Random Access Memory，RAM）等。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。

Claims (17)

  1. 一种SNS社区中的用户推荐方法，包括以下步骤：
    获取第一用户和第二用户在第一社区中的互动记录；
    根据所述互动记录生成第一用户与第二用户的互动频率；
    根据所述互动频率计算第一用户与第二用户的熟识度；
    在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户。
  2. 根据权利要求1所述的SNS社区中的用户推荐方法，其特征在于，所述互动记录包括第一用户与第二用户之间的访问、评论、回复、赞、转发、转载、分享中的至少一种操作记录。
  3. 根据权利要求1所述的SNS社区中的用户推荐方法，其特征在于，所述方法还包括：
    根据第一社区中的用户关系链和第二社区中的用户关系链生成第一用户与第二用户的紧密度；
    所述根据互动频率计算第一用户与第二用户的熟识度的步骤为：
    根据所述互动频率和所述紧密度计算所述第一用户与第二用户的熟识度。
  4. 根据权利要求3所述的SNS社区中的用户推荐方法，其特征在于，所述根据所述第一社区的用户关系链和第二社区的用户关系链生成第一用户与第二用户的紧密度的步骤包括：
    根据所述第一社区中的用户关系链判断在第一社区中第一用户与第二用户的关系为以下哪一种：第二用户为第一用户的好友、第二用户为第一用户的二度好友、第二用户为第一用户收听或关注的用户；
    根据所述第二社区中的用户关系链判断在第二社区中第二用户是否为第一用户的二度好友；
    若在第一社区中第二用户为第一用户的好友或第二用户为第一用户的二度好友或第二用户为第一用户收听或关注的用户、或在第二社区中第二用户为第一用户的二度好友，则根据预设的权重相应的增加第一用户与第二用户的紧密度。
  5. 根据权利要求3或4所述的SNS社区中的用户推荐方法，其特征在于，所述方法还包括：
    设置第一用户与第二用户的关系对应的权重，且按照以下顺序从高到低设置权重：
    在第一社区中第二用户为第一用户的好友、在第一社区中第二用户为第一用户收听或关注的用户、在第二社区中第二用户为第一用户的二度好友、在第一社区中第二用户为第一用户的二度好友。
  6. 根据权利要求3或4所述的SNS社区中的用户推荐方法，其特征在于，所述方法还包括：
    根据第一用户和第二用户在第一社区中的个人资料、第一用户和第二用户在第二社区中的个人资料计算第一用户与第二用户的相似度；
    所述根据所述互动频率计算第一用户与第二用户的熟识度的步骤为：
    根据所述互动频率、所述紧密度和所述相似度计算所述第一用户与第二用户的熟识度。
  7. 根据权利要求6所述的SNS社区中的用户推荐方法，其特征在于，所述根据第一用户与第二用户的互动频率、紧密度和相似度计算第一用户与第二用户的熟识度的步骤包括：预先分别设置第一用户与第二用户的互动频率、紧密度、相似度对应的权重，根据互动频率、紧密度、相似度以及互动频率、紧密度、相似度对应的权重相应的增加第一用户与第二用户的熟识度。
  8. 根据权利要求1所述的SNS社区中的用户推荐方法，其特征在于，同一用户的第一社区用户标识与第二社区用户标识不同，第一社区与第二社区共享用户标识对应关系库， 其中，用户对应关系库中保存同一用户的第一社区用户标识与第二社区用户标识之间的对应关系；
    所述在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户的步骤包括：
    获取第一用户的第二社区用户标识；
    根据第一用户的第二社区用户标识以及同一用户的第一社区用户标识与第二社区用户标识之间的对应关系，查找第一用户的第一社区用户标识；
    获取第一用户的第一社区用户标识对应的与第一用户熟识度超过阈值的第二用户的第一社区用户标识；
    根据第二用户的第一社区用户标识以及上述对应关系查找第二用户的第二社区用户标识；
    向第一用户展示查找到的第二社区用户标识对应的第二用户列表。
  9. 一种SNS社区中的用户推荐系统，其特征在于，包括：
    记录获取模块，用于获取第一用户和第二用户在第一社区中的互动记录；
    互动频率生成模块，用于根据所述互动记录生成第一用户与第二用户的互动频率；
    熟识度计算模块，用于根据所述互动频率计算第一用户与第二用户的熟识度；
    推荐模块，用于在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户。
  10. 根据权利要求9所述的SNS社区中的用户推荐系统，其特征在于，所述互动记录包括第一用户与第二用户之间的访问、评论、回复、赞、转发、转载、分享中的至少一种操作记录。
  11. 根据权利要求9所述的SNS社区中的用户推荐系统，其特征在于，所述系统还包括：
    紧密度生成模块，用于根据第一社区中的用户关系链和第二社区中的用户关系链生成第一用户与第二用户的紧密度；
    所述熟识度计算模块用于根据所述互动频率和所述紧密度计算所述第一用户与第二用户的熟识度。
  12. 根据权利要求11所述的SNS社区中的用户推荐系统，其特征在于，所述紧密度生成模块用于根据所述第一社区中的用户关系链判断在第一社区中第一用户与第二用户的关系为以下哪一种：第二用户为第一用户的好友、第二用户为第一用户的二度好友、第二用户为第一用户收听或关注的用户，根据所述第二社区中的用户关系链判断在第二社区中第二用户是否为第一用户的二度好友，若在第一社区中第二用户为第一用户的好友或第二用户为第一用户的二度好友或第二用户为第一用户收听或关注的用户、或在第二社区中第二用户为第一用户的二度好友，则根据预设的权重相应的增加第一用户与第二用户的紧密度。
  13. 根据权利要求11或12所述的SNS社区中的用户推荐系统，其特征在于，所述紧密度生成模块还用于预先设置第一用户与第二用户的关系对应的权重，且按照以下顺序从高到低设置权重：
    在第一社区中第二用户为第一用户的好友、在第一社区中第二用户为第一用户收听或关注的用户、在第二社区中第二用户为第一用户的二度好友、在第一社区中第二用户为第一用户的二度好友。
  14. 根据权利要求11或12所述的SNS社区中的用户推荐系统，其特征在于，所述系统还包括：
    相似度计算模块，用于根据第一用户和第二用户在第一社区中的个人资料、第一用户和第二用户在第二社区中的个人资料计算第一用户与第二用户的相似度；
    所述熟识度计算模块用于根据所述互动频率、所述紧密度和所述相似度计算所述第一用户与第二用户的熟识度。
  15. 根据权利要求14所述的SNS社区中的用户推荐系统，其特征在于，所述熟识度计算模块还用于预先分别设置第一用户与第二用户的互动频率、紧密度、相似度对应的权重，根据互动频率、紧密度、相似度以及互动频率、紧密度、相似度对应的权重相应的增加第一用户与第二用户的熟识度。
  16. 根据权利要求9所述的SNS社区中的用户推荐系统，其特征在于，同一用户的第一社区用户标识与第二社区用户标识不同，第一社区与第二社区共享用户标识对应关系库，其中，用户对应关系库中保存同一用户的第一社区用户标识与第二社区用户标识之间的对应关系；
    所述推荐模块还用于获取第一用户的第二社区用户标识；根据第一用户的第二社区用户标识以及同一用户的第一社区用户标识与第二社区用户标识之间的对应关系，查找第一用户的第一社区用户标识；获取第一用户的第一社区用户标识对应的与第一用户熟识度超过阈值的第二用户的第一社区用户标识；根据第二用户的第一社区用户标识以及上述对应关系查找第二用户的第二社区用户标识；向第一用户展示查找到的第二社区用户标识对应的第二用户列表。
  17. 一个或多个包含计算机可执行指令的计算机存储介质，所述计算机可执行指令用于执行一种SNS社区中的用户推荐方法，其特征在于，所述方法包括以下步骤：
    获取第一用户和第二用户在第一社区中的互动记录；
    根据所述互动记录生成第一用户与第二用户的互动频率；
    根据所述互动频率计算第一用户与第二用户的熟识度；
    在第二社区中将与第一用户的熟识度超过阈值的第二用户推荐给所述第一用户。
PCT/CN2013/076486 2012-06-01 2013-05-30 Sns社区中的用户推荐方法和系统、计算机存储介质 Ceased WO2013178081A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
MYPI2014703593A MY189277A (en) 2012-06-01 2013-05-30 User recommendation method and system in sns community, and computer storage medium
US14/556,528 US9870406B2 (en) 2012-06-01 2014-12-01 User recommendation method and system in SNS community, and computer storage medium
US15/828,919 US10691703B2 (en) 2012-06-01 2017-12-01 User recommendation method and system in SNS community, and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210178965.0A CN103455515B (zh) 2012-06-01 2012-06-01 Sns社区中的用户推荐方法和系统
CN201210178965.0 2012-06-01

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/556,528 Continuation-In-Part US9870406B2 (en) 2012-06-01 2014-12-01 User recommendation method and system in SNS community, and computer storage medium

Publications (1)

Publication Number Publication Date
WO2013178081A1 true WO2013178081A1 (zh) 2013-12-05

Family

ID=49672431

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/076486 Ceased WO2013178081A1 (zh) 2012-06-01 2013-05-30 Sns社区中的用户推荐方法和系统、计算机存储介质

Country Status (4)

Country Link
US (2) US9870406B2 (zh)
CN (1) CN103455515B (zh)
MY (1) MY189277A (zh)
WO (1) WO2013178081A1 (zh)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104423942A (zh) * 2013-08-28 2015-03-18 腾讯科技（深圳）有限公司 一种社区好友关系展现方法、相关装置和系统
CN103838834B (zh) * 2014-02-25 2020-06-19 北京智谷睿拓技术服务有限公司 一种提及推荐方法、信息处理方法及系统
CN104601438B (zh) * 2014-04-28 2017-12-01 腾讯科技（深圳）有限公司 一种好友推荐方法和装置
CN104572866B (zh) * 2014-12-19 2019-04-16 贵阳语玩科技有限公司 用户关系链获取方法及装置
CN105989501B (zh) * 2015-02-03 2021-03-05 创新先进技术有限公司 一种查询咨询账户的方法及装置
CN105100193B (zh) * 2015-05-26 2018-12-11 小米科技有限责任公司 云名片推荐方法及装置
CN105049325A (zh) * 2015-06-17 2015-11-11 北京乐动卓越科技有限公司 一种基于时间匹配度的目标用户展现方法及系统
US10089363B2 (en) * 2015-10-15 2018-10-02 At&T Intellectual Property I, L.P. Method and apparatus for identifying users who know each other
CN105391562B (zh) * 2015-11-27 2020-01-07 努比亚技术有限公司 一种群聊装置、方法及移动终端
US10901945B2 (en) * 2016-01-05 2021-01-26 The grät Network, PBC Systems and methods concerning tracking models for digital interactions
CN106683025B (zh) * 2017-01-06 2020-06-09 成都全时云信息技术有限公司 老人服务推荐的方法及装置
CN106960014B (zh) * 2017-03-02 2021-02-19 阿里巴巴（中国）有限公司 关联用户推荐方法及装置
JP2018045694A (ja) * 2017-10-06 2018-03-22 ヤフー株式会社 地図検索装置、地図検索方法、および地図検索プログラム
CN108681972B (zh) * 2018-05-23 2020-05-05 北京达佳互联信息技术有限公司 社交关系引导方法、装置、计算机设备及存储介质
CN111865757B (zh) * 2018-08-16 2022-08-26 北京达佳互联信息技术有限公司 社交通信方法、装置、电子设备及存储介质
CN109446427A (zh) * 2018-11-02 2019-03-08 北京奇艺世纪科技有限公司 一种信息推荐方法及装置
CN109766786B (zh) * 2018-12-21 2020-10-23 深圳云天励飞技术有限公司 人物关系分析方法及相关产品
CN110737846B (zh) * 2019-10-28 2022-05-31 北京字节跳动网络技术有限公司 一种社交界面推荐方法、装置、电子设备及存储介质
CN112231590B (zh) * 2020-10-15 2023-06-27 中国联合网络通信集团有限公司 内容推荐方法、系统、计算机设备及存储介质
CN113722601B (zh) * 2021-09-07 2024-04-16 南方电网数字电网研究院股份有限公司 电力量测信息推荐方法、装置、计算机设备和存储介质
JP7312923B1 (ja) * 2021-12-22 2023-07-21 楽天グループ株式会社 情報処理システム、情報処理方法及びプログラム
CN116821517A (zh) * 2023-04-24 2023-09-29 广州趣研网络科技有限公司 一种虚拟房间推荐方法、装置、存储介质及计算机设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1917463A (zh) * 2006-08-30 2007-02-21 中国移动通信集团公司 基于用户操作特征对用户信息关联的方法
CN1937533A (zh) * 2006-08-29 2007-03-28 中国移动通信集团公司 网络社区好友同步管理方法
CN102255890A (zh) * 2011-05-30 2011-11-23 苏宁军 一种用户推荐与信息交互的系统及方法
CN102393843A (zh) * 2011-06-29 2012-03-28 广州市动景计算机科技有限公司 利用移动终端通讯信息建立用户关系的方法及系统

Family Cites Families (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7885901B2 (en) * 2004-01-29 2011-02-08 Yahoo! Inc. Method and system for seeding online social network contacts
US20080126476A1 (en) * 2004-08-04 2008-05-29 Nicholas Frank C Method and System for the Creating, Managing, and Delivery of Enhanced Feed Formatted Content
US8060463B1 (en) * 2005-03-30 2011-11-15 Amazon Technologies, Inc. Mining of user event data to identify users with common interests
US8015484B2 (en) * 2006-02-09 2011-09-06 Alejandro Backer Reputation system for web pages and online entities
US8276079B2 (en) * 2007-12-21 2012-09-25 Jonathan Davar Supplementing user web-browsing
US10826953B2 (en) * 2007-12-21 2020-11-03 Jonathan Davar Supplementing user web-browsing
US8499247B2 (en) * 2008-02-26 2013-07-30 Livingsocial, Inc. Ranking interactions between users on the internet
CN102084354A (zh) * 2008-04-05 2011-06-01 社会传播公司 基于共享虚拟区域通信环境的装置和方法
US9384186B2 (en) * 2008-05-20 2016-07-05 Aol Inc. Monitoring conversations to identify topics of interest
US20100005518A1 (en) * 2008-07-03 2010-01-07 Motorola, Inc. Assigning access privileges in a social network
US9246708B2 (en) * 2008-08-06 2016-01-26 Bindu Rama Rao Social networking website system with automatic registration based on location information
US20100174747A1 (en) * 2009-01-06 2010-07-08 International Business Machines Corporation Methods for recommending new individuals to be invited into a confirmed social network based on mined social data
GB2467597B (en) * 2009-02-10 2012-12-26 Oracle Int Corp Integrated communication system and method
US20100241576A1 (en) * 2009-03-23 2010-09-23 Zohar Beeri System, method and computer program product for social network based transactions
US8489515B2 (en) * 2009-05-08 2013-07-16 Comcast Interactive Media, LLC. Social network based recommendation method and system
WO2011032069A2 (en) * 2009-09-14 2011-03-17 Envio Networks Inc. Context enhanced marketing of content and targeted advertising to mobile device users
FR2953614A1 (fr) * 2009-12-07 2011-06-10 Korea Electronics Telecomm Systeme et procede pour fournir un service de reseau social simple sur une base hors ligne
US20110145719A1 (en) * 2009-12-14 2011-06-16 International Business Machines Corporation People recommendation indicator method and apparatus in a social networking site
US8296175B2 (en) * 2010-01-11 2012-10-23 International Business Machines Corporation Social network marketing plan comparison method and system
US8412770B2 (en) * 2010-02-08 2013-04-02 Yellowpages.Com Llc Providing an answer to a question from a social network site using a separate messaging site
WO2011119859A2 (en) * 2010-03-24 2011-09-29 Hameed Khan Proximity-based social networking
US9252950B2 (en) * 2010-05-28 2016-02-02 Ram Caspi Methods and apparatus for interactive multimedia communication
US10419266B2 (en) * 2010-05-28 2019-09-17 Ram Caspi Methods and apparatus for interactive social TV multimedia communication
LU91967B1 (en) * 2010-07-30 2012-07-29 Infosys Technologies Ltd SYSTEM FOR THE IMPLEMENTATION OF A PLURALITY OF INTERACTIVE SERVICES ASSOCIATED WITH A FINANCIAL ORGANIZATION
WO2012070241A1 (ja) * 2010-11-25 2012-05-31 パナソニック株式会社 コンテンツ共有システムおよびその方法、コンテンツ仲介装置およびその方法、ならびにコンテンツ提供装置およびその方法
US9258264B1 (en) * 2011-03-30 2016-02-09 Google Inc. Processing socially networked entities
AU2011202182B1 (en) * 2011-05-11 2011-10-13 Frequency Ip Holdings, Llc Creation and presentation of selective digital content feeds
US20120330758A1 (en) * 2011-06-21 2012-12-27 Kaushik Sudhir Segmenting ad inventory by creators, recommenders and their social status
US20130018954A1 (en) * 2011-07-15 2013-01-17 Samsung Electronics Co., Ltd. Situation-aware user sentiment social interest models
US8838581B2 (en) * 2011-08-19 2014-09-16 Facebook, Inc. Sending notifications about other users with whom a user is likely to interact
US10217117B2 (en) * 2011-09-15 2019-02-26 Stephan HEATH System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods and services, entertainment and auctions, with geospatial mapping technology
CN103036763A (zh) * 2011-09-30 2013-04-10 腾讯数码（天津）有限公司 Sns社区中拉动沉淀用户的方法及系统
US20130091214A1 (en) * 2011-10-08 2013-04-11 Broadcom Corporation Media social network
US20130097056A1 (en) * 2011-10-13 2013-04-18 Xerox Corporation Methods and systems for recommending services based on an electronic social media trust model
US10290018B2 (en) * 2011-11-09 2019-05-14 Visa International Service Association Systems and methods to communicate with users via social networking sites
US20130262559A1 (en) * 2012-03-28 2013-10-03 Diy Media, Inc. System and method for tracking use of portable objects

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1937533A (zh) * 2006-08-29 2007-03-28 中国移动通信集团公司 网络社区好友同步管理方法
CN1917463A (zh) * 2006-08-30 2007-02-21 中国移动通信集团公司 基于用户操作特征对用户信息关联的方法
CN102255890A (zh) * 2011-05-30 2011-11-23 苏宁军 一种用户推荐与信息交互的系统及方法
CN102393843A (zh) * 2011-06-29 2012-03-28 广州市动景计算机科技有限公司 利用移动终端通讯信息建立用户关系的方法及系统

Also Published As

Publication number Publication date
US9870406B2 (en) 2018-01-16
US20180081883A1 (en) 2018-03-22
CN103455515B (zh) 2017-03-22
US10691703B2 (en) 2020-06-23
CN103455515A (zh) 2013-12-18
US20150088914A1 (en) 2015-03-26
MY189277A (en) 2022-01-31

Similar Documents

Publication Publication Date Title
WO2013178081A1 (zh) Sns社区中的用户推荐方法和系统、计算机存储介质
WO2013170677A1 (zh) 用户社交网络关系圈划分方法和系统、计算机存储介质
WO2015170859A1 (ko) 위치 기반 소셜 커뮤니티 관리 장치 및 방법
WO2018090544A1 (zh) DoS/DDoS攻击检测方法和装置、服务器和存储介质
WO2017157146A1 (zh) 基于用户画像的个性化推荐方法、装置、服务器及存储介质
WO2012163180A1 (zh) 信息推送方法、服务器及系统
WO2017054463A1 (zh) 事件信息推送方法、事件信息推送装置及存储介质
WO2020224246A1 (zh) 基于区块链的数据管理方法、装置、设备和存储介质
WO2019174090A1 (zh) 截屏文件分享的控制方法、装置、设备和计算机存储介质
WO2018018695A1 (zh) 一种应用冻结管理的方法、装置以及终端
WO2013159639A1 (zh) 显示微博话题的方法、终端、服务器、系统及存储介质
WO2014000627A1 (zh) 网络信息推送方法及其系统、计算机存储介质
WO2017142143A1 (en) Method and apparatus for providing summary information of a video
WO2016093630A1 (en) Semantic enrichment of trajectory data
WO2013170643A1 (zh) 社交网络节点分组方法和装置、计算机存储介质
WO2014008858A1 (zh) 实现跨域跳转的方法以及浏览器、域名服务器
WO2015129988A1 (ko) 사용자별 카테고리 선호도 생성 방법, 이를 이용한 상품 추천 방법 및 이를 위한 장치
WO2013131434A1 (zh) 交互界面的展示控制方法及即时通信工具、计算机存储介质
WO2017129079A1 (zh) 在视频直播中插入推送信息的方法、服务器和终端
WO2012165709A1 (ko) 인스턴스 경로 탐색 및 시각화 방법 및 장치
WO2015133856A1 (ko) 정답 키워드 제공 방법 및 장치
WO2017028573A1 (zh) 一种基于移动终端的图片信息处理的方法及系统
WO2023191444A1 (ko) 프로듀서 매칭 서비스 제공 장치 및 방법
WO2017047876A1 (ko) 소셜 미디어에 대한 사용자 행위 분석을 기반으로 한 신뢰성 평가 방법 및 시스템
WO2015129983A1 (ko) 분산 퍼지 연관 규칙 마이닝에 기반한 영화 추천 장치 및 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13796242

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205N DATED 06/02/2015)

122 Ep: pct application non-entry in european phase

Ref document number: 13796242

Country of ref document: EP

Kind code of ref document: A1