Method, device, electronic device and storage medium for obtaining social related information
By generating social association information, obtaining event information and account types, using relationship keywords and public characters in dynamic information to build a user relationship map, the problem of being unable to accurately determine user account relationships in the existing technology is solved, and the account relationship is realized The accurate identification and recommendation of information enhances the accuracy and amount of information acquisition.
Patent Information
- Application Number
- CN202011173353.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-10-28
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2040-10-28
AI Technical Summary
The types of associations between user accounts cannot be accurately determined in existing social networks, resulting in inaccurate information acquisition.
By generating social association information, obtaining event information and account types, using relationship keywords and public characters in dynamic information, building a user relationship map, and accurately determining account relationships.
It realizes accurate identification and recommendation of account relationships, and enhances the amount of information and recommendation accuracy of social information.
Smart Images

Figure CN114417175B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of Internet technology, and in particular to a method, device, electronic device and storage medium for acquiring social association information. Background Art
[0002] With the development of Internet technology, the application of social networks has become more and more popular, and the user scale has also increased. In the existing schemes for obtaining social association information, generally based on the user's follow-up relationship, a user and another user who he follows are determined to be friends, thereby obtaining the user's social association information. Therefore, in the existing schemes, it is confirmed that all users have a unified friend relationship or close relationship, but it is impossible to determine what kind of account relationship the two users have, that is, it is impossible to accurately know the association relationship between the accounts. Summary of the invention
[0003] The present disclosure provides a method, device, electronic device and storage medium for acquiring social association information, which can accurately determine the type of association relationship between accounts.
[0004] According to one aspect of an embodiment of the present disclosure, a method for acquiring social association information is provided, the method comprising:
[0005] generating social association information based on the account relationship in the platform, wherein the social association information includes a plurality of accounts in the platform and an account relationship between any two of the plurality of accounts;
[0006] Acquire event information, and add the event information to the social association information, wherein the event information includes a target event associated with at least one account among the multiple accounts;
[0007] The type of each account in the plurality of accounts is obtained, and the type of each account is added to the social association information.
[0008] In a possible implementation, before generating the social association information based on the account relationship in the platform, the acquisition method further includes:
[0009] Acquire dynamic information published by a first account, where the first account is any account among the multiple accounts, wherein the dynamic information at least includes account information associated with the first account;
[0010] extracting a second account and a relationship keyword from the dynamic information, wherein the relationship keyword is used to represent an account relationship between the first account and the second account, and the second account is any account among the multiple accounts that is different from the first account;
[0011] The account relationship represented by the relationship keyword is determined as a first account relationship between the first account and the second account.
[0012] In another possible implementation, the dynamic information further includes a preset symbol, and the preset symbol is used to indicate that the information after the preset symbol belongs to an account, and extracting the second account and the relationship keyword from the dynamic information includes:
[0013] The information after the preset symbol in the dynamic information is used as the second account.
[0014] In another possible implementation, extracting the second account and the relationship keyword from the dynamic information includes:
[0015] The at least one set relationship keyword is matched with the dynamic information to obtain the relationship keyword contained in the dynamic information.
[0016] In another possible implementation, before generating the social association information based on the account relationship in the platform, the acquisition method further includes:
[0017] Obtaining common characters contained in multiple accounts having a target account relationship in the platform;
[0018] Acquire another account containing the common character, where the another account is any account in the platform;
[0019] The relationship between the another account and each of the multiple accounts having the target account relationship is determined as the target account relationship.
[0020] In another possible implementation, the obtaining of common characters contained in a plurality of accounts having a target account relationship in the platform includes:
[0021] Selecting a preset number of accounts from the multiple accounts having a target account relationship in descending order of the number of followers of the multiple accounts having a target account relationship;
[0022] The same characters included in the preset number of accounts are determined as the common characters.
[0023] In another possible implementation, determining the same characters included in the preset number of accounts as the common characters includes:
[0024] determining the same characters contained in the preset number of accounts as candidate characters;
[0025] Determine the proportion of accounts containing the candidate characters among the multiple accounts having the target account relationship;
[0026] In response to the ratio exceeding a reference ratio, the candidate characters are determined as the common characters.
[0027] In another possible implementation, the obtaining of common characters contained in a plurality of accounts having a target account relationship in the platform includes:
[0028] Taking the same characters contained in any two accounts among the multiple accounts as candidate characters, to obtain multiple candidate characters;
[0029] The longest candidate character among the plurality of candidate characters is determined as the common character.
[0030] In another possible implementation, the step of obtaining another account containing the common character includes:
[0031] Determine the other account that is different from the multiple accounts having a target account relationship and includes the common character and has no text before and after the common character.
[0032] In another possible implementation, before generating the social association information based on the account relationship in the platform, the acquisition method further includes:
[0033] Acquire a second account relationship between a third account and a fourth account, and a third account relationship between the third account and a fifth account in the platform;
[0034] Acquire a fourth account relationship corresponding to the second account relationship and the third account relationship in the relationship knowledge data;
[0035] The fourth account relationship is determined as an account relationship between the fourth account and the fifth account.
[0036] In another possible implementation, the obtaining method further includes:
[0037] Determine that any two accounts in the plurality of accounts that have an account relationship with the same account do not have an account relationship between the two accounts;
[0038] The other account is recommended to one of the two accounts.
[0039] In another possible implementation, the obtaining method further includes:
[0040] According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to the any two accounts are connected through a relationship connection line to obtain a user relationship graph;
[0041] Adding an event node corresponding to the target event in the user relationship graph, connecting the event node with an account node corresponding to the at least one account through an event connection line, to obtain an event relationship graph;
[0042] A type node corresponding to the type is added to the user relationship graph, and the type node is connected to an account node corresponding to at least one account belonging to the type through a type connection line to obtain a type relationship graph.
[0043] In another possible implementation, the obtaining method further includes:
[0044] Determine, according to the social association information, account nodes corresponding to the multiple accounts, event nodes corresponding to the target event, and type nodes corresponding to the type;
[0045] The determined multiple account nodes, the event nodes and the type nodes are connected through connecting lines to obtain a relationship graph, and the connecting lines between any two account nodes, between an account node and an event node, and between an account node and a type node belong to connecting lines of different dimensions.
[0046] In another possible implementation, the multiple account nodes, the event nodes, and the type nodes are connected through connecting lines to obtain a relationship graph, including at least two of the following:
[0047] According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to the any two accounts are connected through a relationship connection line to obtain the relationship map, wherein the relationship connection line represents the account relationship between any two accounts among the multiple accounts;
[0048] Connecting at least one of the plurality of account nodes to the event node through an event connection line to obtain the relationship graph;
[0049] The plurality of account nodes are connected to the type nodes through type connection lines to obtain the relationship graph.
[0050] In another possible implementation, the obtaining method further includes:
[0051] Determine a third relationship connection line between the second account node and the third account node according to the first relationship connection line between the first account node and the second account node, and the second relationship connection line between the first account node and the third account node;
[0052] The second account node is connected to the third account node through the third relationship connection line.
[0053] In another possible implementation, the relationship graph includes at least one user group graph, the user group graph includes a plurality of account nodes, and the account nodes in different user group graphs are not connected.
[0054] In another possible implementation, the obtaining method further includes:
[0055] The plurality of account nodes, the event nodes, and the type nodes are created in the relationship graph.
[0056] In another possible implementation, the obtaining method further includes:
[0057] According to the relationship graph, determining any two account nodes connected to the same node, wherein the same node includes any one of an account node, an event node or a type node, and the two account nodes are not connected to each other;
[0058] An account corresponding to one of the two account nodes is recommended to an account corresponding to the other account node.
[0059] According to another aspect of an embodiment of the present disclosure, a device for acquiring social association information is provided, the device comprising:
[0060] an association information generating unit, configured to generate social association information based on the account relationship in the platform, wherein the social association information includes a plurality of accounts in the platform and an account relationship between any two accounts in the plurality of accounts;
[0061] an event information acquisition unit, configured to acquire event information and add the event information to the social association information, wherein the event information includes a target event associated with at least one account among the multiple accounts;
[0062] The type acquisition unit is configured to acquire the type to which each of the multiple accounts belongs, and add the type to which each account belongs to the social association information.
[0063] In a possible implementation, the acquisition device further includes:
[0064] a dynamic information acquisition unit, configured to acquire dynamic information published by a first account, wherein the first account is any account among the multiple accounts, wherein the dynamic information at least includes account information associated with the first account;
[0065] an extracting unit configured to extract a second account and a relationship keyword from the dynamic information, wherein the relationship keyword is used to represent an account relationship between the first account and the second account, and the second account is any account among the multiple accounts that is different from the first account;
[0066] The relationship determination unit is configured to determine the account relationship represented by the relationship keyword as a first account relationship between the first account and the second account.
[0067] In another possible implementation, the dynamic information also includes a preset symbol, and the preset symbol is used to indicate that the information after the preset symbol belongs to an account. The extraction unit is configured to execute the information after the preset symbol in the dynamic information as the second account.
[0068] In another possible implementation, the extraction unit is configured to perform matching processing between the at least one set relationship keyword and the dynamic information to obtain the relationship keyword included in the dynamic information.
[0069] In another possible implementation, the acquisition device further includes:
[0070] A character acquisition unit, configured to acquire common characters contained in a plurality of accounts having a target account relationship in the platform;
[0071] An account acquisition unit, configured to acquire another account containing the common character, wherein the another account is any account in the platform;
[0072] The relationship determination unit is further configured to determine the relationship between the other account and each of the multiple accounts having the target account relationship as the target account relationship.
[0073] In another possible implementation, the character acquisition unit is configured to execute:
[0074] Selecting a preset number of accounts from the multiple accounts having a target account relationship in descending order of the number of followers of the multiple accounts having a target account relationship;
[0075] The same characters included in the preset number of accounts are determined as the common characters.
[0076] In another possible implementation, the character acquisition unit is configured to execute:
[0077] determining the same characters contained in the preset number of accounts as candidate characters;
[0078] Determine the proportion of accounts containing the candidate characters among the multiple accounts having the target account relationship;
[0079] In response to the ratio exceeding a reference ratio, the candidate characters are determined as the common characters.
[0080] In another possible implementation, the character acquisition unit is configured to execute:
[0081] Taking the same characters contained in any two accounts among the multiple accounts as candidate characters, to obtain multiple candidate characters;
[0082] The longest candidate character among the plurality of candidate characters is determined as the common character.
[0083] In another possible implementation, the account acquisition unit is configured to determine the other account that is different from the multiple accounts having a target account relationship, contains the common character and has no text before and after the common character.
[0084] In another possible implementation, the acquisition device further includes:
[0085] a relationship acquisition unit, configured to acquire a second account relationship between a third account and a fourth account in the platform, and a third account relationship between the third account and a fifth account;
[0086] The relationship acquisition unit is further configured to execute acquisition of a fourth account relationship corresponding to the second account relationship and the third account relationship in the relationship knowledge data;
[0087] The relationship determination unit is further configured to determine the fourth account relationship as an account relationship between the fourth account and the fifth account.
[0088] In another possible implementation, the acquisition device further includes:
[0089] A recommendation unit is configured to determine that any two accounts in the plurality of accounts that have an account relationship with the same account do not have an account relationship between the two accounts;
[0090] The recommendation unit is further configured to recommend another account to one of the two accounts.
[0091] In another possible implementation, the acquisition device further includes:
[0092] A graph determination unit is configured to execute, according to the account relationship between any two accounts among the multiple accounts, connecting the account nodes corresponding to any two accounts through a relationship connection line to obtain a user relationship graph;
[0093] The graph determination unit is further configured to add an event node corresponding to the target event in the user relationship graph, connect the event node with an account node corresponding to the at least one account through an event connection line, and obtain an event relationship graph;
[0094] The graph determination unit is further configured to add a type node corresponding to the type in the user relationship graph, connect the type node with an account node corresponding to at least one account belonging to the type through a type connection line, and obtain a type relationship graph.
[0095] In another possible implementation, the acquisition device further includes:
[0096] a node determination unit configured to determine, according to the social association information, account nodes corresponding to the multiple accounts, event nodes corresponding to the target event, and type nodes corresponding to the type;
[0097] The graph determination unit is further configured to connect the determined multiple account nodes, the event nodes and the type nodes through connecting lines to obtain a relationship graph, and the connecting lines between any two account nodes, between an account node and an event node, and between an account node and a type node belong to connecting lines of different dimensions.
[0098] In another possible implementation, the graph determination unit is further configured to execute:
[0099] According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to the any two accounts are connected through a relationship connection line to obtain the relationship map, wherein the relationship connection line represents the account relationship between any two accounts among the multiple accounts;
[0100] Connecting at least one of the plurality of account nodes to the event node through an event connection line to obtain the relationship graph;
[0101] The plurality of account nodes are connected to the type nodes through type connection lines to obtain the relationship graph.
[0102] In another possible implementation, the graph determination unit is further configured to execute:
[0103] Determine a third relationship connection line between the second account node and the third account node according to the first relationship connection line between the first account node and the second account node, and the second relationship connection line between the first account node and the third account node;
[0104] The second account node is connected to the third account node through the third relationship connection line.
[0105] In another possible implementation, the relationship graph includes at least one user group graph, the user group graph includes a plurality of account nodes, and the account nodes in different user group graphs are not connected.
[0106] In another possible implementation, the acquisition device further includes:
[0107] The node creation unit is configured to create the plurality of account nodes, the event nodes, and the type nodes in the relationship graph.
[0108] In another possible implementation, the acquisition device further includes:
[0109] A recommendation unit is configured to determine any two account nodes connected to the same node according to the relationship graph, wherein the same node includes any one of an account node, an event node or a type node, and the two account nodes are not connected to each other;
[0110] The recommendation unit is further configured to recommend an account corresponding to one of the two account nodes to an account corresponding to another account node.
[0111] According to another aspect of the embodiments of the present disclosure, an electronic device is provided, the electronic device comprising:
[0112] one or more processors;
[0113] volatile or non-volatile memory for storing the one or more processor-executable instructions;
[0114] The one or more processors are configured to execute the method for acquiring social association information described in the above aspects.
[0115] According to another aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the method for acquiring social association information described in the above aspect.
[0116] According to another aspect of an embodiment of the present disclosure, a computer program product is provided. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device can execute the method for acquiring social association information described in the above aspects.
[0117] The beneficial effects brought by the technical solution provided by the embodiments of the present disclosure include at least:
[0118] The method, device, electronic device and storage medium for obtaining social association information provided by the embodiments of the present disclosure generate social association information including the account relationship between any two accounts among multiple accounts, and the social association information can accurately represent the relationship between the accounts, thereby accurately determining the type of association relationship between the accounts. In addition, event information or the type of account can be added to the social association information, so that the social association information includes different dimensions, thereby increasing the amount of information in the social association information.
[0119] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0120] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0121] Figure 1 The figure is a flow chart of a method for acquiring social association information according to an exemplary embodiment.
[0122] Figure 2 The figure is a flow chart of another method for acquiring social association information according to an exemplary embodiment.
[0123] Figure 3 It is a schematic diagram of a user interface according to an exemplary embodiment.
[0124] Figure 4 is a schematic diagram of another user interface according to an exemplary embodiment.
[0125] Figure 5 The following is a flowchart showing a method for determining a common character according to an exemplary embodiment.
[0126] Figure 6 The figure is a flowchart of a method for constructing a relationship graph according to an exemplary embodiment.
[0127] Figure 7 It is a schematic diagram of a relationship map according to an exemplary embodiment.
[0128] Figure 8 is a schematic diagram of another relationship graph according to an exemplary embodiment.
[0129] Fig. 9 is a schematic diagram of another relationship map according to an exemplary embodiment.
[0130] Fig.10 The present invention is a block diagram of a device for acquiring social association information according to an exemplary embodiment.
[0131] Fig.11 The figure is a block diagram of another device for acquiring social association information according to an exemplary embodiment.
[0132] Fig.12 It is a block diagram of a terminal according to an exemplary embodiment.
[0133] Fig.13 It is a block diagram of a server according to an exemplary embodiment. DETAILED DESCRIPTION
[0134] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0135] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned figure descriptions are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0136] It should be noted that the user information involved in this disclosure (including but not limited to user device information, user personal information, etc.) is all information authorized by the user or fully authorized by all parties.
[0137] The embodiments of the present disclosure provide a method for acquiring social association information, which can be applied in various scenarios.
[0138] For example, it is applied in the scenario of account recommendation based on social association information.
[0139] The method for obtaining social association information provided by the embodiment of the present disclosure is adopted to obtain social association information, event information and types of accounts in the platform. When recommending an account to account A, another account B related to account A is determined from the social association information, and account B is recommended to account A.
[0140] For another example, it is applied in a scenario of making account recommendations based on a constructed relationship graph.
[0141] The method for obtaining social association information provided by the embodiment of the present disclosure is used to construct a relationship graph including multiple account nodes, event nodes and type nodes. When recommending an account for account A, another account node that is connected to the same node as the account node corresponding to account A is determined from the relationship graph, and account B corresponding to the other account node is recommended to account A.
[0142] Since the account node corresponding to account A and the account node corresponding to account B are connected to the same node, such as the same type node or the same event node, it means that account B is associated with account A, such as belonging to the same type or having the same event. Therefore, recommending account B to account A can improve the recommendation accuracy.
[0143] Figure 1 is a flowchart of a method for obtaining social association information according to an exemplary embodiment. Figure 1 The method is applied to an electronic device, which is a terminal or a server. The terminal can be a portable, pocket-sized, handheld terminal of various types, such as a mobile phone, a computer, a tablet computer, etc. The server can be a server, or a server cluster composed of several servers, or a cloud computing service center. The method includes the following steps:
[0144] 101. Generate social association information based on account relationships in the platform.
[0145] Among them, platform refers to a social application where users can create accounts on the platform. Account relationship refers to the relationship between any two accounts on the platform. For example, account relationships include friend relationships, partner relationships, cooperative relationships, master-apprentice relationships, etc. Account is an identifier such as ID and nickname that represents the user's identity.
[0146] The electronic device obtains information such as multiple accounts in the platform, accounts followed by each account, or dynamic information published by users based on accounts, and then determines the account relationship between any two accounts based on the obtained information to generate social association information. The social association information includes multiple accounts in the platform and the account relationship between any two accounts among the multiple accounts. The social association information can accurately represent the account relationship between the accounts, thereby accurately determining the type of association relationship between the accounts.
[0147] 102. Obtain event information, and add the event information to the social related information.
[0148] The event information includes a target event associated with at least one of the multiple accounts. The event information may include the event theme, event content, event occurrence time, cause, process and result of the event, people involved in the event, the field to which the event belongs, etc. Adding event information to social association information means adding the event information to the social association information and associating the event information with the account involved in the event information.
[0149] The embodiment of the present disclosure takes a first account as an example. The first account is any one of multiple accounts. The methods for obtaining event information associated with the first account include the following:
[0150] In a possible implementation, when any event information includes a first account, it means that the first user corresponding to the first account is the party to the event, and the event information is used as the associated event information of the first account.
[0151] In another possible implementation, if any terminal has published comment information on an event based on the first account, the event information of the event is determined as the event information associated with the first account.
[0152] In another possible implementation, after any terminal publishes comment information on the event based on the first account, other accounts can operate on the comment information, such as liking or commenting. If more than a preset number of accounts have operated on the comment information, it means that the comment information is relatively popular and has attracted the attention of other users. It can be considered that the first account is associated with the event, and the event information of the event is determined as the event information associated with the first account.
[0153] In addition, the above possible implementation method is to determine the event information associated with the first account from the perspective of the first account, and in another embodiment, the event information associated with the first account can also be determined from the perspective of the event, that is, the electronic device can obtain an event that has been searched more than a preset number of times in the social network, and then determine the account associated with the event, and use the event information of the event as the event information associated with the account. The account associated with the event is an account included in the event information, or an account that has posted comment information on the event, or an account that has posted comment information on the event and more than a preset number of accounts have operated on the comment information.
[0154] 103. Obtain a type of each account in the plurality of accounts, and add the type of each account to the social association information.
[0155] Adding the type of each account to the social association information means adding the type of the account to the social association information and associating accounts of the same type. Optionally, each account belongs to one type or multiple types.
[0156] In a possible implementation, the electronic device obtains the type of the first account, including: the electronic device obtains the introduction information of the first account, performs word segmentation processing on the introduction information, obtains multiple words included in the introduction information, filters out some adjectives, modal particles and other words that are not related to the type in the multiple words, and selects words representing the type from the multiple words remaining after filtering, thereby obtaining type information. The introduction information includes a personal profile or authentication information, the personal profile is information filled in by the user himself, and the authentication information is real information filled in by the user and authenticated. The types of accounts include singing anchors, musicians, fitness experts, game anchors, e-commerce anchors and other types.
[0157] For example, the introduction information of the first account is "the first game anchor on the ×× platform". After word segmentation processing of the introduction information, we can get "×× platform", "first" and "game anchor", among which "×× platform" and "first" are not related to the type, and "game anchor" is related to the type. Therefore, it is determined that the type of the first account is game anchor.
[0158] In another possible implementation, when the first user publishes multimedia data in a social network, the multimedia data, such as a video or an image, will be published based on the first account corresponding to the first user. Therefore, the electronic device obtains the multimedia data published based on the first account, identifies and processes the multimedia data, and determines the type of the multimedia data, that is, the type of multimedia data frequently published by the first account, thereby determining the type of the first account based on the type. For example, the video published by the user based on the corresponding account is a fitness-related video, so it can be determined that the user is a fitness expert.
[0159] The method provided by the embodiment of the present disclosure generates social association information including the account relationship between any two accounts among multiple accounts. The social association information can accurately represent the relationship between the accounts, thereby accurately determining the type of association relationship between the accounts, and can also add event information or the type of account to the social association information, so that the social association information includes different dimensions, thereby increasing the amount of information in the social association information.
[0160] Above Figure 1 The illustrated embodiment generates social association information based on the account relationship in the platform. Before generating the social association information, it is necessary to first obtain the account relationship between any two accounts among the multiple accounts in the platform. The process of obtaining the account relationship in the platform is described below.
[0161] Figure 2 is a flowchart of a method for obtaining social association information according to an exemplary embodiment. Figure 2, the method is applied in an electronic device, the method comprising the following steps:
[0162] 201. For any account, based on the dynamic information published by the account, obtain other accounts associated with the account and the account relationship between the account and the other accounts.
[0163] The disclosed embodiment is described by taking any account as the first account and the other accounts as the second account as an example, the electronic device collects associated user information of the first account, and the associated user information of the first account includes the second account and a relationship keyword, and the relationship keyword is used to represent the account relationship between the first account and the second account.
[0164] In a possible implementation, the associated user information is published dynamic information, which at least includes account information associated with the first account, and the electronic device obtains the dynamic information published based on the first account; the second account and the relationship keyword can be extracted from the dynamic information, and the account relationship represented by the relationship keyword is determined as the first account relationship between the first account and the second account. The dynamic information is text information, audio information, or other types of information.
[0165] In a possible implementation, the dynamic information further includes a preset symbol, and the preset symbol is used to indicate that the information after the preset symbol belongs to an account. Then the electronic device extracts the second account from the dynamic information, including: using the information after the preset symbol in the dynamic information as the second account. The preset symbol is any preset symbol, for example, the preset symbol is "@" or other symbols.
[0166] In a possible implementation, the electronic device pre-sets at least one relationship keyword, and matches the set at least one relationship keyword with the dynamic information to obtain the relationship keyword included in the dynamic information.
[0167] In a possible implementation, after extracting the account and the relationship keyword from the dynamic information, it is necessary to determine whether the position of the second account and the relationship keyword in the dynamic information meets a preset condition, and only when the preset condition is met can it be determined that the account relationship between the first account and the second account is the relationship represented by the relationship keyword. The preset condition is: the relationship keyword is located before the second account, and there is no text between the relationship keyword and the second account.
[0168] That is, if the relationship keyword in the dynamic information is located before the second account, and there is no text between the relationship keyword and the second account, the account relationship between the first account and the second account is the account relationship represented by the relationship keyword. If there is text between the relationship keyword and the second account, even if the relationship keyword and the second account are extracted, since the relationship keyword and the second account are not adjacent, it cannot be determined that the account relationship between the first account and the second account is the account relationship represented by the relationship keyword. The above method improves the accuracy of the determined account relationship.
[0169] If the dynamic information includes multiple second accounts, the relationship keyword is located before the multiple second accounts, there is no text between the multiple second accounts, and there is no text between the relationship keyword and the first second account, then the account relationship represented by the relationship keyword is determined to be the account relationship between the first account and the first second account, and the account relationship between the first account and other second accounts in the multiple second accounts cannot be determined.
[0170] For example, see Figure 3 In the user interface shown, account A has published a video work and the accompanying text corresponding to the video work, "After the dark clouds, there will be a rainbow: @Account B, @Account C", which includes the relationship keyword "Master", the second account "Account B" and the third account "Account C". Among them, there is no text between the relationship keyword "Master" and the second account "Account B", so it can be determined that the user corresponding to account B is the master of the user corresponding to account A.
[0171] In another possible implementation, the introduction information of the first account includes the second account and the relationship keywords, and the second account and the relationship keywords are extracted from the introduction information. The extraction method is similar to the above-mentioned extraction method of extracting the second account and the relationship keywords from the dynamic information, and will not be repeated here.
[0172] For example, see Figure 4 In the user interface shown, the introduction information of account A is "Master: Account B", which includes the relationship keyword "Master" and the second account "Account B". There is no text between the relationship keyword "Master" and the second account "Account B", so it can be determined that the user corresponding to account B is the master of the user corresponding to account A.
[0173] In a possible implementation, a plurality of different relationship keywords can represent the same account relationship. For example, the following Table 1 shows the account relationships represented by various relationship keywords.
[0174] Table 1
[0175] Account Relationship Relationship Keywords Master Master, Master, Respected Master, Family Master, Mentor, Shi, SF, SF, Shi relatives Parents, children, brothers and sisters, sisters, ... Large (big) large Small small
[0176] It should be noted that the embodiment of the present disclosure is only described by taking the dynamic information including the second account and the relationship keyword as an example. In another embodiment, the dynamic information can include multiple accounts and the relationship keyword corresponding to each account.
[0177] 202. Obtain common characters contained in multiple accounts having a target account relationship in the platform.
[0178] The target account relationship refers to the same user group, and any two accounts in the same user group are considered to have a target account relationship. Each user group has a corresponding common character, which is the same character contained in multiple accounts in the user group.
[0179] For each user group, it is necessary to determine the common characters of the user group based on multiple accounts in the user group. In a possible implementation, the electronic device selects a preset number of accounts from multiple accounts in order of the number of followers from the largest to the smallest; and determines the same characters contained in the preset number of accounts as common characters. The number of followers of an account refers to the number of other accounts that follow the account, that is, the number of fans of the account in the social network. The preset number is any number, for example, the preset number is 2, 3 or other numbers.
[0180] For a user group, it is considered that the account with a large number of followers in the user group can represent the user group, so the same characters in multiple accounts with a large number of followers are taken as common characters.
[0181] In another possible implementation, if the same character in a plurality of accounts with a large number of followers is different from the same character in other accounts, the determined common character cannot represent most of the accounts in the user group and is not accurate enough. Therefore, in order to avoid this situation, the electronic device determines the same character contained in a preset number of accounts as candidate characters; determines the proportion of the number of accounts containing the candidate characters in the plurality of accounts; in response to the proportion exceeding the reference proportion, determines the candidate character as a common character, thereby ensuring that most of the accounts in the user group contain the common character and the common character can represent the user group. In response to the proportion not exceeding the reference proportion, the electronic device continues to obtain other candidate characters, or determines that the user group has no common characters.
[0182] In another possible implementation, the electronic device uses the same characters included in any two adjacent accounts among the multiple accounts as candidate characters to obtain multiple candidate characters; the longest candidate character among the multiple candidate characters is determined as the common character. That is, multiple identical characters are determined from the multiple accounts, and then the common character is selected from the multiple identical characters. If the character is short, the account in other user groups may also contain the common character. Therefore, in order to avoid duplication of the common characters in other user groups, the longest candidate character is determined as the common character to ensure that the common character only represents the user group.
[0183] In another possible implementation, see Figure 5 The flowchart shown in the figure first selects the two accounts arranged in the front in the order of the number of followers from most to least, determines the same characters contained in the two accounts, determines the proportion of the number of accounts containing the same characters in multiple accounts of the user group, and determines whether it exceeds the reference proportion. If it exceeds the reference proportion, the same characters are determined as common characters; if it does not exceed the reference proportion, it is determined whether to continue to select the other two accounts after the above two accounts. If the other two accounts are selected, the same characters in the other two accounts are determined, and the above judgment process is continued until the common characters are determined. If the other two accounts after the above two accounts are not selected, the process ends.
[0184] If all accounts are traversed and no ratio corresponding to the same character exceeds the reference ratio, it is considered that the user group has no common characters, and 203 and 204 are no longer executed.
[0185] 203. Obtain another account containing the common characters.
[0186] The other account is any account in the platform, and the other account is different from the multiple accounts in the user group.
[0187] In one possible implementation, the electronic device determines another account that is different from the multiple accounts having a target account relationship and that contains a common character and has no text before or after the common character.
[0188] For example, the common character of a user group is "fork", and the accounts "Zhang San-Fork" and "Li Si Fork" containing "fork" are found. For these two accounts, "Zhang San-Fork" has a "-" before the "fork", and "-" is not a character, and there is no other character after the "fork", so it is determined that the account "Zhang San-Fork" belongs to the user group. However, "Li Si Fork" has a "four" before the "fork", so it is determined that the account "Li Si Fork" does not belong to the user group.
[0189] 204. Determine a relationship between another account and each account in the plurality of accounts having a target account relationship as a target account relationship.
[0190] The other account also belongs to the user group, and the other account and other accounts in the user group have a target account relationship, for example, the target account relationship is a cooperative relationship, a relative relationship, etc. In a possible implementation, the account with the largest number of followers in the user group is determined as the leader account in the user group, and the other account and the account with the largest number of followers are considered to have a target account relationship. The number of followers refers to the number of other accounts that follow the account.
[0191] 205. Determine the account relationship between the fourth account and the fifth account according to the second account relationship between the third account and the fourth account and the third account relationship between the third account and the fifth account in the platform.
[0192] In the embodiment of the present disclosure, based on the account relationships that have been determined between multiple accounts, the relationships between other accounts with undetermined relationships are inferred. For example, the user corresponding to account B and the user corresponding to account A have a kinship relationship.
[0193] The third account in the platform is used as a medium to infer the account relationship between the fourth account and the fifth account. First, the second account relationship between the third account and the fourth account, and the third account relationship between the third account and the fifth account need to be obtained; then the fourth account relationship corresponding to the second account relationship and the third account relationship in the relationship knowledge data is obtained; and the fourth account relationship is determined as the account relationship between the fourth account and the fifth account.
[0194] In addition, in a possible implementation, after the account relationship between multiple accounts is determined, account recommendations can be made based on the known account relationship. The electronic device determines any two accounts in the multiple accounts that have an account relationship with the same account, and there is no account relationship between the two accounts; recommends another account to one of the two accounts, thereby implementing account recommendation.
[0195] In addition, in the above embodiment, different accounts correspond to different users, and the account relationship between accounts indicates the relationship between the corresponding users. For multiple accounts belonging to the same user, for example, the main account, sub-account, work account, life account and enterprise account of the same user, a similar implementation method can also be used to determine the account relationship between multiple accounts belonging to the same user. For example, the user's work account is "Work Account A", the user's life account is "Life Account A", and the user publishes a dynamic message based on Life Account A "For work-related issues, please contact the work account: @Work Account A", then the relationship keywords "Work Account" and "Work Account A" can be extracted from the dynamic information, thereby determining that "Life Account A" and "Work Account A" belong to the same user, and "Work Account A" is the work account of "Life Account A".
[0196] The method provided by the embodiment of the present disclosure can determine what kind of account relationship exists between any two accounts among multiple accounts through the collected relationship keywords, and can also infer the account relationship between accounts with unknown relationships based on the known account relationships between the multiple accounts, and can also determine other accounts that have relationships with the multiple accounts based on common characters, thereby obtaining account relationships between more accounts, further increasing the amount of information in the social association information.
[0197] In the disclosed embodiment, after obtaining social association information including the account relationship between any two accounts among multiple accounts, event information, and the types to which the accounts belong, a relationship graph can be constructed based on the social association information. The relationship graph construction process is described below.
[0198] Figure 6 is a flowchart of a method for constructing a relationship graph according to an exemplary embodiment. Figure 6 , the method is applied in an electronic device, the method comprising the following steps:
[0199] 601. Determine, according to the social association information, account nodes corresponding to the multiple accounts, event nodes corresponding to the target event, and type nodes corresponding to the type.
[0200] Before constructing a relationship graph based on associated information, the electronic device first creates corresponding nodes. Based on multiple accounts, it creates an account node corresponding to each account. Based on event information, it creates an event node corresponding to each event. Based on the type of account, it creates a type node corresponding to each type.
[0201] The electronic device searches for an account node corresponding to each account based on multiple accounts included in the social association information; searches for an event node corresponding to each event based on event information associated with each account; and searches for a type node corresponding to each type based on the type to which each account belongs.
[0202] 602. Connect the determined multiple account nodes, event nodes, and type nodes through connecting lines to obtain a relationship graph.
[0203] Among them, the connection lines between any two account nodes, between an account node and an event node, and between an account node and a type node belong to connection lines of different dimensions. The relationship connection line between two account nodes belongs to the account dimension, and the relationship connection line represents the account relationship between the two accounts; the event connection line between an account node and an event node belongs to the event dimension, and the event connection line represents the association between the account and the event; the type connection line between an account node and a type node belongs to the type dimension, and the type connection line represents that the account belongs to the corresponding type.
[0204] For any two users, the relationship between them in real life is constant, but the relationship obtained is different when looking at the two users from different angles. Different relationships correspond to different relationship lines. For example, the two users corresponding to the two account nodes are in a master-apprentice relationship. The relationship line between the two account nodes can be a master-apprentice line, a master line, or a apprentice line, which can also indicate that the two users corresponding to the two account nodes are in a master-apprentice relationship.
[0205] In one possible implementation, the relationship connection line between two account nodes has a direction, that is, the relationship connection line between the two account nodes is from one account node to another account node, and the relationship connection line represents the relationship of the user corresponding to the pointed account node relative to the user corresponding to the other account node. For example, the relationship connection line between the first account node and the second account node is from the first account node to the second account node, and the relationship connection line represents a master relationship, which means that the user corresponding to the second account node is the master of the user corresponding to the first account node.
[0206] In another possible implementation, the relationship connection line between two account nodes has no direction, that is, the two account nodes are directly connected by a relationship connection line, and the relationship connection line represents the relationship between the accounts corresponding to the two account nodes. For example, the relationship connection line between the first account node and the second account node represents a master-apprentice relationship, which means that the user corresponding to the first account node and the user corresponding to the second account node are in a master-apprentice relationship, but it cannot indicate which user is the master and which user is the apprentice.
[0207] For event links and type links, regardless of whether the links have directions, the meanings of the links are the same. For example, an event link points from an event node to an account node, or from an account node to an event node, both indicate that the user corresponding to the account node is a participant of the event corresponding to the event node. Similarly, a type node points from a type node to an account node, or from an account node to a type node, both indicate that the user corresponding to the account node belongs to the type represented by the type node.
[0208] In an embodiment of the present disclosure, the account relationship between two accounts is determined based on social association information, the account nodes corresponding to the two accounts are connected by a relationship connection line representing the account relationship, the events in which users corresponding to the accounts participate are determined based on the social association information, the account nodes and the event nodes are connected by the event connection line, the type of the account is determined based on the social association information, and the account nodes and the type nodes are connected by the type connection line, thereby obtaining a multidimensional relationship graph including account nodes, event nodes, type nodes and connection lines of various dimensions.
[0209] When constructing a multidimensional relationship graph, the following possible implementation methods are used to connect nodes belonging to different dimensions:
[0210] In one possible implementation, the electronic device connects the account nodes corresponding to any two accounts among the multiple accounts through a relationship connection line according to the account relationship between any two accounts, to obtain a relationship graph, where the relationship graph is a user relationship graph of the user dimension.
[0211] In a possible implementation, the electronic device connects at least one account node among a plurality of account nodes to an event node through an event connection line to obtain a relationship graph, where the relationship graph is an event relationship graph of an event dimension.
[0212] In a possible implementation, the electronic device connects multiple account nodes and type nodes through type connection lines to obtain a relationship graph, which is a type relationship graph of the type dimension.
[0213] By adopting the above methods, relationship maps of different dimensions can be constructed respectively. If at least two of the methods are combined, a multi-dimensional relationship map can be constructed.
[0214] In another possible implementation, the electronic device connects the account nodes corresponding to any two accounts among the multiple accounts through a relationship connection line based on the account relationship between any two accounts, so as to obtain a user relationship map; adds an event node corresponding to the target event to the user relationship map, connects the event node with the account node corresponding to at least one account among the multiple accounts through the event connection line, so as to obtain an event relationship map, and the event relationship map is a multidimensional relationship map including user dimension and event dimension; or, adds a type node corresponding to the type to the user relationship map, connects the type node with the account node corresponding to at least one account belonging to the type through the type connection line, so as to obtain a type relationship map, and the type relationship map is a multidimensional relationship map including user dimension and type dimension; or, adds an event node corresponding to the target event and a type node corresponding to the type to the user relationship map, so as to obtain a relationship map including user dimension, event dimension and type dimension.
[0215] For example, building Figure 7 The event relationship graph shown in the figure, in which the circle represents the account node, the rectangle represents the event node, the event relationship graph includes account node A, account node B, account node C, account node D and target event node, any two account nodes are connected by a relationship connection line, any account node and the target event node are connected by an event connection line, and the relationships represented in the event relationship graph include: the user corresponding to account node B is the wife of the user corresponding to account node D, the user corresponding to account node A and the user corresponding to account node C are both apprentices of the user corresponding to account node D, and the user corresponding to account node D is a participant of the target event corresponding to the target event node.
[0216] For example, building Figure 8 The type relationship graph shown in the figure, in which the circle represents the account node, the diamond represents the type node, the type relationship graph includes account node A, account node B, account node C, account node D and e-commerce anchor node, and the relationships represented in the type relationship graph include: the user corresponding to account node B is the wife of the user corresponding to account node D, the user corresponding to account node A and the user corresponding to account node C are both apprentices of the user corresponding to account node D, and the user corresponding to account node D and the user corresponding to account node B are e-commerce anchors.
[0217] For example, building Fig. 9The multidimensional relationship graph shown in the figure, in which the circle represents the account node, the rectangle represents the event node, and the diamond represents the type node. The multidimensional relationship graph includes account node A, account node B, account node C, account node D, target event node and e-commerce anchor node. The relationships represented by the multidimensional relationship graph include: the user corresponding to account node B is the wife of the user corresponding to account node D, the user corresponding to account node A and the user corresponding to account node C are both apprentices of the user corresponding to account node D, the user corresponding to account node D is a participant of the target event corresponding to the target event node, and the user corresponding to account node D and the user corresponding to account node B are e-commerce anchors.
[0218] In one possible implementation, the relationship graph obtained above includes at least one user group graph, each user group graph includes multiple account nodes, the account nodes in different user group graphs are not connected, but the account nodes in different user group graphs can be connected to the same event node or the same type of node.
[0219] In a possible implementation, the electronic device can infer the relationship between other account nodes based on the relationship between the known account nodes in the relationship graph. Using the first account node as a medium, the electronic device determines the third relationship connection line between the second account node and the third account node based on the first relationship connection line between the first account node and the second account node, and the second relationship connection line between the first account node and the third account node; and connects the second account node and the third account node through the third relationship connection line. The implementation method of determining the relationship between the second account node and the third account node is similar to the implementation method of determining the account relationship between the fourth account and the fifth account in the above step 205.
[0220] In a possible implementation, after constructing the relationship graph, the electronic device applies the relationship graph to account recommendation. The electronic device determines any two account nodes connected to the same node based on the relationship graph, where the same node includes any one of an account node, an event node, or a type node, and any two account nodes are not connected; and recommends an account corresponding to one of the two account nodes to an account corresponding to the other account node.
[0221] In another possible implementation, after constructing the relationship graph, the electronic device can also apply the relationship graph to the live broadcast recommendation scenario. If a user often watches a live broadcast of a certain anchor, other anchors of the same type as the anchor can be obtained according to the relationship graph, so as to recommend other anchors to the user.
[0222] In another possible implementation, after constructing the relationship graph, the electronic device can also apply the relationship graph to the account search scenario. Taking the first user searching for other accounts based on the first account as an example, when the first user searches for the sixth account based on the first account, the first user can obtain other accounts of the same type as the sixth account, or obtain other accounts of participants in the same event as the sixth account according to the relationship graph, so that when displaying the search results, not only the sixth account can be displayed, but also other accounts that may be of interest can be displayed.
[0223] In another possible implementation, after constructing the relationship map, the electronic device can also apply the relationship map to various scenarios such as public opinion analysis and financial risk control.
[0224] In addition, in one possible implementation, if there are new accounts or new event information in the platform later, new account nodes or event nodes are added to the already constructed relationship graph, and the new account nodes or event nodes are connected to other nodes to continue to supplement the relationship graph.
[0225] The method provided by the embodiment of the present disclosure constructs a relationship map based on the acquired social association information. Since the social association information can accurately represent the type of association relationship between accounts, the constructed relationship map can also accurately represent the type of association relationship between accounts. In addition, the social association information includes information of multiple dimensions, and the obtained relationship map is also a multi-dimensional relationship map, which further increases the amount of information in the relationship map.
[0226] Furthermore, when the relationship graph is subsequently used for account recommendation, the relationship graph can provide more information about the account, improve the interpretability of the application results, and can recommend other accounts associated with the same event to the account, or recommend accounts of the same type as the account to the account based on the relationship between the account and the event or the type of the account, thereby improving the accuracy of recommendations.
[0227] Fig.10 is a block diagram of a device for acquiring social association information according to an exemplary embodiment. Fig.10 , the device comprises:
[0228] The association information generating unit 1001 is configured to generate social association information based on the account relationship in the platform, wherein the social association information includes multiple accounts in the platform and the account relationship between any two accounts in the multiple accounts;
[0229] An event information acquisition unit 1002 is configured to acquire event information and add the event information to the social association information, wherein the event information includes a target event associated with at least one of the multiple accounts;
[0230] The type acquisition unit 1003 is configured to acquire the type to which each of the multiple accounts belongs, and add the type to which each account belongs to the social association information.
[0231] The device provided by the embodiment of the present disclosure generates social association information including the account relationship between any two accounts among the multiple accounts, and the social association information can accurately represent the relationship between the accounts, so as to accurately determine the type of association relationship between the accounts. In addition, event information or the type of account can be added to the social association information, so that the social association information includes different dimensions, thereby increasing the amount of information in the social association information.
[0232] In one possible implementation, see Fig.11 , the acquisition device also includes:
[0233] The dynamic information acquisition unit 1004 is configured to acquire dynamic information published by a first account, where the first account is any one of the multiple accounts, wherein the dynamic information at least includes account information associated with the first account;
[0234] An extracting unit 1005 is configured to extract a second account and a relationship keyword from the dynamic information, where the relationship keyword is used to represent an account relationship between the first account and the second account, and the second account is any account among the multiple accounts that is different from the first account;
[0235] The relationship determination unit 1006 is configured to determine the account relationship represented by the relationship keyword as a first account relationship between the first account and the second account.
[0236] In another possible implementation, see Fig.11 The dynamic information also includes a preset symbol, which is used to indicate that the information after the preset symbol belongs to an account. The extraction unit 1005 is configured to execute the information after the preset symbol in the dynamic information as the second account.
[0237] In another possible implementation, see Fig.11 The extraction unit 1005 is configured to perform matching processing between the at least one set relationship keyword and the dynamic information to obtain the relationship keyword contained in the dynamic information.
[0238] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0239] A character acquisition unit 1007 is configured to acquire common characters contained in multiple accounts having a target account relationship in the platform;
[0240] An account acquisition unit 1008 is configured to acquire another account containing the common characters, where the other account is any account in the platform;
[0241] The relationship determining unit 1006 is further configured to determine the relationship between another account and each account in the plurality of accounts having a target account relationship as a target account relationship.
[0242] In another possible implementation, see Fig.11 , the character acquisition unit 1007 is configured to execute:
[0243] Selecting a preset number of accounts from the multiple accounts having a target account relationship in descending order of the number of followers of the multiple accounts having a target account relationship;
[0244] The same characters included in a preset number of accounts are determined as common characters.
[0245] In another possible implementation, see Fig.11 , the character acquisition unit 1007 is configured to execute:
[0246] determining identical characters contained in a preset number of accounts as candidate characters;
[0247] determining a proportion of the number of accounts containing the alternative characters among the multiple accounts having a target account relationship;
[0248] In response to the ratio exceeding the reference ratio, the candidate characters are determined as common characters.
[0249] In another possible implementation, see Fig.11 , the character acquisition unit 1007 is configured to execute:
[0250] Taking the same characters contained in any two accounts among the multiple accounts as candidate characters, a plurality of candidate characters are obtained;
[0251] The longest candidate character among the multiple candidate characters is determined as the common character.
[0252] In another possible implementation, see Fig.11 The account acquisition unit 1008 is configured to determine another account that is different from the multiple accounts having the target account relationship, contains a common character and has no text before and after the common character.
[0253] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0254] The relationship acquisition unit 1009 is configured to execute acquisition of a second account relationship between the third account and the fourth account, and a third account relationship between the third account and the fifth account in the platform;
[0255] The relationship acquisition unit 1009 is further configured to execute acquisition of a fourth account relationship corresponding to the second account relationship and the third account relationship in the relationship knowledge data;
[0256] The relationship determining unit 1006 is further configured to determine the fourth account relationship as an account relationship between the fourth account and the fifth account.
[0257] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0258] The recommendation unit 1010 is configured to determine any two accounts in the plurality of accounts that have an account relationship with the same account, and no account relationship exists between any two accounts;
[0259] The recommendation unit 1010 is further configured to recommend another account to one of any two accounts.
[0260] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0261] A graph determination unit 1011 is configured to execute, according to the account relationship between any two accounts among the multiple accounts, connecting the account nodes corresponding to any two accounts through a relationship connection line to obtain a user relationship graph;
[0262] The graph determination unit 1011 is further configured to add an event node corresponding to the target event in the user relationship graph, connect the event node with an account node corresponding to at least one account through an event connection line, and obtain an event relationship graph;
[0263] The graph determination unit 1011 is further configured to add a type node corresponding to the type in the user relationship graph, connect the type node with an account node corresponding to at least one account belonging to the type through a type connection line, and obtain a type relationship graph.
[0264] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0265] A node determination unit 1012 is configured to determine, based on the social association information, account nodes corresponding to the multiple accounts, event nodes corresponding to the target event, and type nodes corresponding to the type;
[0266] The graph determination unit 1011 is further configured to connect the determined multiple account nodes, event nodes and type nodes through connecting lines to obtain a relationship graph, and the connecting lines between any two account nodes, between an account node and an event node, and between an account node and a type node belong to connecting lines of different dimensions.
[0267] In another possible implementation, see Fig.11 The graph determination unit 1011 is further configured to execute:
[0268] According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to any two accounts are connected through a relationship connection line to obtain a relationship map, and the relationship connection line represents the account relationship between any two accounts among the multiple accounts;
[0269] Connecting at least one of the multiple account nodes to the event node through an event connection line to obtain a relationship graph;
[0270] Connect multiple account nodes and type nodes through type connection lines to obtain a relationship graph.
[0271] In another possible implementation, see Fig.11 The graph determination unit 1011 is further configured to execute:
[0272] Determine a third relationship connection line between the second account node and the third account node according to the first relationship connection line between the first account node and the second account node and the second relationship connection line between the first account node and the third account node;
[0273] The second account node is connected to the third account node through a third relationship connection line.
[0274] In another possible implementation, the relationship graph includes at least one user group graph, the user group graph includes a plurality of account nodes, and the account nodes in different user group graphs are not connected.
[0275] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0276] The node creation unit 1013 is configured to create a plurality of account nodes, event nodes and type nodes in the relationship graph.
[0277] In another possible implementation, see Fig.11 , the acquisition device also includes:
[0278] The recommendation unit 1010 is configured to determine any two account nodes connected to the same node according to the relationship graph, where the same node includes any one of an account node, an event node or a type node, and any two account nodes are not connected to each other;
[0279] The recommendation unit 1010 is further configured to recommend an account corresponding to one of any two account nodes to an account corresponding to another account node.
[0280] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.
[0281] In an exemplary embodiment, an electronic device is provided, which includes one or more processors and a volatile or non-volatile memory for storing executable instructions of the one or more processors; wherein the one or more processors are configured to execute the method for obtaining social association information in the above-mentioned embodiment.
[0282] In a possible implementation manner, the electronic device is provided as a terminal. Fig.12 1 is a block diagram of a terminal 1200 according to an exemplary embodiment. The terminal 1200 may be a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The terminal 1200 may also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.
[0283] Typically, the terminal 1200 includes: a processor 1201 and a memory 1202 .
[0284] The processor 1201 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1201 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1201 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1201 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.
[0285] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1202 is used to store at least one program code, which is executed by the processor 1201 to implement the method for obtaining social association information provided in the method embodiment of the present disclosure.
[0286] In some embodiments, the terminal 1200 may also optionally include: a peripheral device interface 1203 and at least one peripheral device. The processor 1201, the memory 1202 and the peripheral device interface 1203 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1203 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 1204, a display screen 1205, a camera assembly 1206, an audio circuit 1207, a positioning assembly 1208 and a power supply 1209.
[0287] The peripheral device interface 1203 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1201 and the memory 1202. In some embodiments, the processor 1201, the memory 1202, and the peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1201, the memory 1202, and the peripheral device interface 1203 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.
[0288] The radio frequency circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1204 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 1204 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 1204 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1204 may also include circuits related to NFC (Near Field Communication), which is not limited in the present disclosure.
[0289] The display screen 1205 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1205 is a touch display screen, the display screen 1205 also has the ability to collect touch signals on the surface or above the surface of the display screen 1205. The touch signal can be input to the processor 1201 as a control signal for processing. At this time, the display screen 1205 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1205 can be one, set on the front panel of the terminal 1200; in other embodiments, the display screen 1205 can be at least two, respectively set on different surfaces of the terminal 1200 or in a folding design; in other embodiments, the display screen 1205 can be a flexible display screen, set on a curved surface or a folding surface of the terminal 1200. Even, the display screen 1205 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1205 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).
[0290] The camera assembly 1206 is used to capture images or videos. Optionally, the camera assembly 1206 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize the panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.
[0291] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 1201 for processing, or input them into the radio frequency circuit 1204 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 1200. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1207 may also include a headphone jack.
[0292] The positioning component 1208 is used to locate the current geographical location of the terminal 1200 to implement navigation or LBS (Location Based Service). The positioning component 1208 can be a positioning component based on the US GPS (Global Positioning System), China's Beidou system, Russia's Grenas positioning system, or the European Union's Galileo positioning system.
[0293] The power supply 1209 is used to power various components in the terminal 1200. The power supply 1209 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1209 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.
[0294] In some embodiments, the terminal 1200 further includes one or more sensors 1210 , including but not limited to: an acceleration sensor 1211 , a gyroscope sensor 1212 , a pressure sensor 1213 , a fingerprint sensor 1214 , an optical sensor 1215 , and a proximity sensor 1216 .
[0295] The acceleration sensor 1211 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 1200. For example, the acceleration sensor 1211 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 1201 can control the display screen 1205 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1211. The acceleration sensor 1211 can also be used to collect motion data of games or users.
[0296] The gyro sensor 1212 can detect the body direction and rotation angle of the terminal 1200, and the gyro sensor 1212 can cooperate with the acceleration sensor 1211 to collect the user's 3D actions on the terminal 1200. The processor 1201 can implement the following functions based on the data collected by the gyro sensor 1212: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.
[0297] The pressure sensor 1213 can be set on the side frame of the terminal 1200 and / or the lower layer of the display screen 1205. When the pressure sensor 1213 is set on the side frame of the terminal 1200, the user's holding signal of the terminal 1200 can be detected, and the processor 1201 performs left and right hand recognition or shortcut operations according to the holding signal collected by the pressure sensor 1213. When the pressure sensor 1213 is set on the lower layer of the display screen 1205, the processor 1201 controls the operability controls on the UI interface according to the user's pressure operation on the display screen 1205. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.
[0298] The fingerprint sensor 1214 is used to collect the user's fingerprint, and the processor 1201 identifies the user's identity based on the fingerprint collected by the fingerprint sensor 1214, or the fingerprint sensor 1214 identifies the user's identity based on the collected fingerprint. When the user's identity is identified as a trusted identity, the processor 1201 authorizes the user to perform relevant sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings. The fingerprint sensor 1214 can be set on the front, back, or side of the terminal 1200. When a physical button or a manufacturer logo is set on the terminal 1200, the fingerprint sensor 1214 can be integrated with the physical button or the manufacturer logo.
[0299] The optical sensor 1215 is used to collect the ambient light intensity. In one embodiment, the processor 1201 can control the display brightness of the display screen 1205 according to the ambient light intensity collected by the optical sensor 1215. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1205 is increased; when the ambient light intensity is low, the display brightness of the display screen 1205 is reduced. In another embodiment, the processor 1201 can also dynamically adjust the shooting parameters of the camera assembly 1206 according to the ambient light intensity collected by the optical sensor 1215.
[0300] The proximity sensor 1216, also called a distance sensor, is usually arranged on the front panel of the terminal 1200. The proximity sensor 1216 is used to collect the distance between the user and the front of the terminal 1200. In one embodiment, when the proximity sensor 1216 detects that the distance between the user and the front of the terminal 1200 is gradually decreasing, the processor 1201 controls the display screen 1205 to switch from the screen-on state to the screen-off state; when the proximity sensor 1216 detects that the distance between the user and the front of the terminal 1200 is gradually increasing, the processor 1201 controls the display screen 1205 to switch from the screen-off state to the screen-on state.
[0301] Those skilled in the art will understand that Fig.12 The structure shown in the figure does not constitute a limitation on the terminal 1200, and the terminal 1200 may include more or fewer components than those shown in the figure, or combine certain components, or adopt a different component arrangement.
[0302] In another possible implementation, the electronic device is provided as a server. Fig.13 This is a block diagram of a server according to an exemplary embodiment. The server 1300 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 1301 and one or more memories 1302, wherein the memory 1302 stores at least one program code, and the at least one program code is loaded and executed by the processor 1301 to implement the methods provided by the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the server may also include other components for implementing device functions, which will not be described in detail here.
[0303] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, and when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the steps performed by the terminal or the server in the above-mentioned method for obtaining social association information. Optionally, the storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0304] In an exemplary embodiment, a computer program product is also provided. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the steps executed by the terminal or the server in the above-mentioned method for acquiring social association information.
[0305] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0306] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A method for obtaining social association information, characterized in that: The acquisition method comprises: Selecting a preset number of accounts from the multiple accounts having a target account relationship in the platform in descending order of the number of followers of the multiple accounts having a target account relationship, and determining the same characters contained in the preset number of accounts as common characters; Acquire another account containing the common character, where the another account is any account in the platform; determining the relationship between the another account and each of the multiple accounts having the target account relationship as the target account relationship; generating social association information based on the account relationship in the platform, wherein the social association information includes a plurality of accounts in the platform and an account relationship between any two of the plurality of accounts; Acquire event information, and add the event information to the social association information, wherein the event information includes a target event associated with at least one account among the multiple accounts; The type of each account in the plurality of accounts is obtained, and the type of each account is added to the social association information.
2. The acquisition method according to claim 1, characterized in that: Before generating the social association information based on the account relationship in the platform, the acquisition method further includes: Acquire dynamic information published by a first account, where the first account is any account among the multiple accounts, wherein the dynamic information at least includes account information associated with the first account; extracting a second account and a relationship keyword from the dynamic information, wherein the relationship keyword is used to represent an account relationship between the first account and the second account, and the second account is any account among the multiple accounts that is different from the first account; The account relationship represented by the relationship keyword is determined as a first account relationship between the first account and the second account.
3. The acquisition method according to claim 2, characterized in that: The dynamic information further includes a preset symbol, and the preset symbol is used to indicate that the information after the preset symbol belongs to an account. The extracting the second account and the relationship keyword from the dynamic information includes: The information after the preset symbol in the dynamic information is used as the second account.
4. The acquisition method according to claim 2, characterized in that: The extracting the second account and the relationship keyword from the dynamic information includes: The at least one set relationship keyword is matched with the dynamic information to obtain the relationship keyword contained in the dynamic information.
5. The acquisition method according to claim 1, characterized in that: The step of determining the same characters contained in the preset number of accounts as the common characters comprises: determining the same characters contained in the preset number of accounts as candidate characters; Determine the proportion of accounts containing the candidate characters among the multiple accounts having the target account relationship; In response to the ratio exceeding a reference ratio, the candidate characters are determined as the common characters.
6. The acquisition method according to claim 1, characterized in that: The acquisition method further includes: Taking the same characters contained in any two accounts among the multiple accounts as candidate characters, to obtain multiple candidate characters; The longest candidate character among the plurality of candidate characters is determined as the common character.
7. The acquisition method according to claim 1, characterized in that: The acquiring another account containing the common character comprises: Determine the other account that is different from the multiple accounts having the target account relationship, contains the common character and has no text before and after the common character.
8. The acquisition method according to claim 1, characterized in that: Before generating the social association information based on the account relationship in the platform, the acquisition method further includes: Acquire a second account relationship between a third account and a fourth account, and a third account relationship between the third account and a fifth account in the platform; Acquire a fourth account relationship corresponding to the second account relationship and the third account relationship in the relationship knowledge data; The fourth account relationship is determined as an account relationship between the fourth account and the fifth account.
9. The acquisition method according to claim 1, characterized in that: The acquisition method further includes: Determine that any two accounts in the plurality of accounts that have an account relationship with the same account do not have an account relationship between the two accounts; The other account is recommended to one of the two accounts.
10. The acquisition method according to claim 1, characterized in that: The acquisition method further includes: According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to the any two accounts are connected through a relationship connection line to obtain a user relationship graph; Adding an event node corresponding to the target event in the user relationship graph, connecting the event node with an account node corresponding to the at least one account through an event connection line, to obtain an event relationship graph; A type node corresponding to the type is added to the user relationship graph, and the type node is connected to an account node corresponding to at least one account belonging to the type through a type connection line to obtain a type relationship graph.
11. The acquisition method according to claim 1, characterized in that: The acquisition method further includes: Determine, according to the social association information, account nodes corresponding to the multiple accounts, event nodes corresponding to the target event, and type nodes corresponding to the type; The determined multiple account nodes, the event nodes and the type nodes are connected through connecting lines to obtain a relationship graph, and the connecting lines between any two account nodes, between an account node and an event node, and between an account node and a type node belong to connecting lines of different dimensions.
12. The acquisition method according to claim 11, characterized in that: The determined multiple account nodes, the event nodes, and the type nodes are connected through connecting lines to obtain a relationship graph, including at least two of the following: According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to the any two accounts are connected through a relationship connection line to obtain the relationship map, wherein the relationship connection line represents the account relationship between any two accounts among the multiple accounts; Connecting at least one of the plurality of account nodes to the event node through an event connection line to obtain the relationship graph; The plurality of account nodes are connected to the type nodes through type connection lines to obtain the relationship graph.
13. The acquisition method according to claim 11, characterized in that: The acquisition method further includes: Determine a third relationship connection line between the second account node and the third account node according to the first relationship connection line between the first account node and the second account node, and the second relationship connection line between the first account node and the third account node; The second account node is connected to the third account node through the third relationship connection line.
14. The acquisition method according to claim 11, characterized in that: The relationship graph includes at least one user group graph, the user group graph includes a plurality of account nodes, and the account nodes in different user group graphs are not connected.
15. The acquisition method according to claim 11, characterized in that: The acquisition method further includes: The plurality of account nodes, the event nodes, and the type nodes are created in the relationship graph.
16. The acquisition method according to claim 11, characterized in that: The acquisition method further includes: According to the relationship graph, determining any two account nodes connected to the same node, wherein the same node includes any one of an account node, an event node or a type node, and the two account nodes are not connected to each other; An account corresponding to one of the two account nodes is recommended to an account corresponding to the other account node.
17. A device for acquiring social association information, characterized in that: The acquisition device comprises: a character acquisition unit configured to select a preset number of accounts from the multiple accounts having a target account relationship in the platform in descending order of the number of followers of the multiple accounts having a target account relationship, and determine the same characters contained in the preset number of accounts as common characters; An account acquisition unit, configured to acquire another account containing the common character, wherein the another account is any account in the platform; a relationship determination unit configured to determine the relationship between the another account and each of the plurality of accounts having a target account relationship as the target account relationship; an association information generating unit, configured to generate social association information based on the account relationship in the platform, wherein the social association information includes a plurality of accounts in the platform and an account relationship between any two accounts in the plurality of accounts; an event information acquisition unit, configured to acquire event information and add the event information to the social association information, wherein the event information includes a target event associated with at least one account among the multiple accounts; The type acquisition unit is configured to acquire the type to which each of the multiple accounts belongs, and add the type to which each account belongs to the social association information.
18. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: a dynamic information acquisition unit, configured to acquire dynamic information published by a first account, wherein the first account is any account among the multiple accounts, wherein the dynamic information at least includes account information associated with the first account; an extracting unit configured to extract a second account and a relationship keyword from the dynamic information, wherein the relationship keyword is used to represent an account relationship between the first account and the second account, and the second account is any account among the multiple accounts that is different from the first account; The relationship determination unit is configured to determine the account relationship represented by the relationship keyword as a first account relationship between the first account and the second account.
19. The acquisition device according to claim 18, characterized in that: The dynamic information also includes a preset symbol, and the preset symbol is used to indicate that the information after the preset symbol belongs to an account. The extraction unit is configured to execute the information after the preset symbol in the dynamic information as the second account.
20. The acquisition device according to claim 18, characterized in that: The extraction unit is configured to perform matching processing between the at least one set relationship keyword and the dynamic information to obtain the relationship keyword contained in the dynamic information.
21. The acquisition device according to claim 17, characterized in that: The character acquisition unit is configured to execute: determining the same characters contained in the preset number of accounts as candidate characters; Determine the proportion of accounts containing the candidate characters among the multiple accounts having the target account relationship; In response to the ratio exceeding a reference ratio, the candidate characters are determined as the common characters.
22. The acquisition device according to claim 17, characterized in that: The character acquisition unit is further configured to execute: Taking the same characters contained in any two accounts among the multiple accounts as candidate characters, to obtain multiple candidate characters; The longest candidate character among the plurality of candidate characters is determined as the common character.
23. The acquisition device according to claim 17, characterized in that: The account acquisition unit is configured to determine the other account which is different from the plurality of accounts having a target account relationship and contains the common character and has no text before and after the common character.
24. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: a relationship acquisition unit, configured to acquire a second account relationship between a third account and a fourth account in the platform, and a third account relationship between the third account and a fifth account; The relationship acquisition unit is further configured to execute acquisition of a fourth account relationship corresponding to the second account relationship and the third account relationship in the relationship knowledge data; The relationship determination unit is configured to determine the fourth account relationship as an account relationship between the fourth account and the fifth account.
25. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: A recommendation unit is configured to determine that any two accounts in the plurality of accounts that have an account relationship with the same account do not have an account relationship between the two accounts; The recommendation unit is further configured to recommend another account to one of the two accounts.
26. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: A graph determination unit is configured to execute, according to the account relationship between any two accounts among the multiple accounts, connecting the account nodes corresponding to any two accounts through a relationship connection line to obtain a user relationship graph; The graph determination unit is further configured to add an event node corresponding to the target event in the user relationship graph, connect the event node with an account node corresponding to the at least one account through an event connection line, and obtain an event relationship graph; The graph determination unit is further configured to add a type node corresponding to the type in the user relationship graph, connect the type node with an account node corresponding to at least one account belonging to the type through a type connection line, and obtain a type relationship graph.
27. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: a node determination unit configured to determine, according to the social association information, account nodes corresponding to the multiple accounts, event nodes corresponding to the target event, and type nodes corresponding to the type; The graph determination unit is configured to connect the determined multiple account nodes, the event nodes and the type nodes through connecting lines to obtain a relationship graph, and the connecting lines between any two account nodes, between an account node and an event node, and between an account node and a type node belong to connecting lines of different dimensions.
28. The acquisition device according to claim 27, characterized in that: The graph determination unit is further configured to execute: According to the account relationship between any two accounts among the multiple accounts, the account nodes corresponding to the any two accounts are connected through a relationship connection line to obtain the relationship map, wherein the relationship connection line represents the account relationship between any two accounts among the multiple accounts; Connecting at least one of the plurality of account nodes to the event node through an event connection line to obtain the relationship graph; The plurality of account nodes are connected to the type nodes through type connection lines to obtain the relationship graph.
29. The acquisition device according to claim 27, characterized in that: The graph determination unit is further configured to execute: Determine a third relationship connection line between the second account node and the third account node according to the first relationship connection line between the first account node and the second account node, and the second relationship connection line between the first account node and the third account node; The second account node is connected to the third account node through the third relationship connection line.
30. The acquisition device according to claim 17, characterized in that: The relationship graph includes at least one user group graph, the user group graph includes a plurality of account nodes, and the account nodes in different user group graphs are not connected.
31. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: The node creation unit is configured to create the plurality of account nodes, the event nodes, and the type nodes in the relationship graph.
32. The acquisition device according to claim 17, characterized in that: The acquisition device also includes: A recommendation unit is configured to determine any two account nodes connected to the same node according to the relationship graph, wherein the same node includes any one of an account node, an event node or a type node, and the two account nodes are not connected to each other; The recommendation unit is further configured to recommend an account corresponding to one of the two account nodes to an account corresponding to the other account node.
33. An electronic device, characterized in that: The electronic device comprises: one or more processors; volatile or non-volatile memory for storing the one or more processor-executable instructions; The one or more processors are configured to execute the method for acquiring social association information as described in any one of claims 1 to 16.
34. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for acquiring social association information as described in any one of claims 1 to 16.
35. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the method for acquiring social association information as described in any one of claims 1 to 16.
