Social network management method and device, electronic equipment and storage medium
By using the fusion model in the social network to generate user node feature vectors and divide communities, the problem of insufficient social network management accuracy in the prior art is solved, and more accurate user recommendations are achieved.
Patent Information
- Application Number
- CN202311280787.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-28
- Publication Date
- 2025-03-28
AI Technical Summary
The existing social network management methods have poor management accuracy in content or friend recommendations, resulting in inaccurate recommendations.
By inputting the topology of the social network and the attribute vectors of the user nodes into the fusion model, the feature vectors of the user nodes are generated, and the social network is divided into multiple communities according to the feature vectors, thereby improving the accuracy of recommendations.
It improves the management accuracy of social networks, ensures that recommended content or friends are more accurately in line with user interests, and improves user satisfaction.
Smart Images
Figure CN119719514A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a social network management method, device, electronic device and storage medium. Background Art
[0002] With the popularity of social networks, more and more people are using social networks to communicate and share information. Due to the huge amount of information in social networks, it is difficult for users to find content or friends that they are interested in. Therefore, how to quickly and accurately find content or friends of interest has become an important issue. In the related art, content or friend recommendations are achieved by maintaining a social network that represents the relationship between different users, but the management accuracy of social networks is poor, resulting in inaccurate content or friend recommendations. Summary of the invention
[0003] In order to overcome the problems existing in the related art, the embodiments of the present disclosure provide a social network management method, device, electronic device and storage medium to solve the defects in the related art.
[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a social network management method, including:
[0005] Inputting the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model to obtain a feature vector of the at least one user node output by the fusion model, wherein the attribute vector is at least used to characterize the behavior characteristics and interest characteristics of the user node;
[0006] According to the feature vector of the at least one user node, the social network is divided into a plurality of communities, wherein each community includes at least one user node, and each user node of the user social network belongs to at least one community.
[0007] In one embodiment of the present disclosure, the method further includes:
[0008] Generate an attribute vector of a corresponding user node according to an interactive behavior of at least one user node of the social network, wherein the interactive behavior is fed back by a client, and the interactive behavior includes interaction with other user nodes and behavior added to the recommended content for representing attitude.
[0009] In one embodiment of the present disclosure, dividing the social network into a plurality of communities according to the feature vector of the at least one user node includes:
[0010] The community to which each user node in the social network belongs is determined in turn in the following manner:
[0011] Determining the fitness of the community to which each neighbor node of the user node and at least one neighbor node of the user node belongs;
[0012] In response to the presence of a community whose fitness with the user node is greater than a first threshold value in the community to which the at least one neighboring node belongs, determining the community whose fitness with the user node is greater than the first threshold value as the community to which the user node belongs;
[0013] In response to the fact that there is no community whose fitness with the user node is greater than a first threshold in the community to which the at least one neighbor node belongs, the user node is determined as a new community.
[0014] In one embodiment of the present disclosure, dividing the social network into a plurality of communities according to the feature vector of the at least one user node includes:
[0015] The community to which each user node in the social network belongs is determined in turn in the following manner:
[0016] Determine the node similarity between each neighbor node of the user node and the user node according to the feature vector of each neighbor node of the user node and the feature vector of the user node;
[0017] Determine the comprehensive similarity between each community of neighbor nodes of the user node and the user node according to the node similarity between each neighbor node of the user node and the user node;
[0018] In response to the existence of a comprehensive similarity greater than a second threshold value between each community where a neighboring node of the user node exists and the user node, determining the community corresponding to the comprehensive similarity greater than the second threshold value as the community to which the user node belongs;
[0019] In response to the fact that there is no comprehensive similarity greater than a second threshold value between each community where the neighboring node of the user node exists and the user node, the user node is determined as a new community.
[0020] In one embodiment of the present disclosure, the method further includes:
[0021] In response to the user node having no neighboring nodes, or all neighboring nodes of the user node have not yet determined the community to which they belong, the user node is determined as a new community.
[0022] In one embodiment of the present disclosure, the method further includes:
[0023] The at least one user node in the social network is sorted according to the information entropy of the at least one user node.
[0024] In one embodiment of the present disclosure, the method further includes:
[0025] In response to receiving a recommendation request sent by a client, obtaining a user ID logged in on the client;
[0026] Determining recommendation information according to an attribute of at least one community to which a user node corresponding to the user identifier belongs;
[0027] The recommendation information is sent to the client, so that the client displays the recommendation information.
[0028] In one embodiment of the present disclosure, the client is a quick application client.
[0029] According to a second aspect of an embodiment of the present disclosure, a social network management method is provided, the method comprising:
[0030] Sending a user ID and a recommendation request to a server, and receiving recommendation information sent by the client;
[0031] The recommendation information is determined by the server according to the attribute of at least one community to which the user node corresponding to the user identifier belongs, and the user identifier is the identifier of the user logged in on the client;
[0032] The community of user nodes is obtained by the server side dividing the social network according to the social network topology structure and the attribute vector of at least one user node of the social network.
[0033] In one embodiment of the present disclosure, the method further includes:
[0034] Feedback the user identification and interaction behavior to the server, wherein the interaction behavior includes interaction with other user nodes and behavior added to the recommended content to represent attitude.
[0035] According to a third aspect of an embodiment of the present disclosure, a social network management device is provided, the device comprising:
[0036] A feature module, used to input the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model, and obtain the feature vector of the at least one user node output by the fusion model, wherein the attribute vector is used to characterize at least the behavior characteristics and interest characteristics of the user node;
[0037] The management module is used to divide the social network into multiple communities according to the feature vector of the at least one user node, wherein each community includes at least one user node, and each user node of the user social network belongs to at least one community.
[0038] In one embodiment of the present disclosure, the device further includes a generating module, which is used to:
[0039] Generate an attribute vector of a corresponding user node according to an interactive behavior of at least one user node of the social network, wherein the interactive behavior is fed back by a client, and the interactive behavior includes interaction with other user nodes and behavior added to the recommended content for representing attitude.
[0040] In one embodiment of the present disclosure, the management module is used to:
[0041] The community to which each user node in the social network belongs is determined in turn in the following manner:
[0042] Determining the fitness of the community to which each neighbor node of the user node and at least one neighbor node of the user node belongs;
[0043] In response to the presence of a community whose fitness with the user node is greater than a first threshold value in the community to which the at least one neighboring node belongs, determining the community whose fitness with the user node is greater than the first threshold value as the community to which the user node belongs;
[0044] In response to the fact that there is no community whose fitness with the user node is greater than a first threshold in the community to which the at least one neighbor node belongs, the user node is determined as a new community.
[0045] In one embodiment of the present disclosure, the management module is used to:
[0046] The community to which each user node in the social network belongs is determined in turn in the following manner:
[0047] Determine the node similarity between each neighbor node of the user node and the user node according to the feature vector of each neighbor node of the user node and the feature vector of the user node;
[0048] Determine the comprehensive similarity between each community of neighbor nodes of the user node and the user node according to the node similarity between each neighbor node of the user node and the user node;
[0049] In response to the existence of a comprehensive similarity greater than a second threshold value between each community where a neighboring node of the user node exists and the user node, determining the community corresponding to the comprehensive similarity greater than the second threshold value as the community to which the user node belongs;
[0050] In response to the fact that there is no comprehensive similarity greater than a second threshold value between each community where the neighboring node of the user node exists and the user node, the user node is determined as a new community.
[0051] In one embodiment of the present disclosure, the management module is further configured to:
[0052] In response to the user node having no neighboring nodes, or all neighboring nodes of the user node have not yet determined the community to which they belong, the user node is determined as a new community.
[0053] In one embodiment of the present disclosure, the device further includes a sorting module, which is used to:
[0054] The at least one user node in the social network is sorted according to the information entropy of the at least one user node.
[0055] In one embodiment of the present disclosure, the device further includes a recommendation module, which is used to:
[0056] In response to receiving a recommendation request sent by a client, obtaining a user ID logged in on the client;
[0057] Determining recommendation information according to an attribute of at least one community to which a user node corresponding to the user identifier belongs;
[0058] The recommendation information is sent to the client, so that the client displays the recommendation information.
[0059] In one embodiment of the present disclosure, the client is a quick application client.
[0060] According to a fourth aspect of an embodiment of the present disclosure, a social network management device is provided, the device comprising:
[0061] A receiving module, used to send a user identification and a recommendation request to a server, and receive recommendation information sent by the client;
[0062] The recommendation information is determined by the server according to the attribute of at least one community to which the user node corresponding to the user identifier belongs, and the user identifier is the identifier of the user logged in on the client;
[0063] The community of user nodes is obtained by the server side dividing the social network according to the social network topology structure and the attribute vector of at least one user node of the social network.
[0064] In one embodiment of the present disclosure, the device further includes a feedback module, which is used to:
[0065] Feedback the user identification and interaction behavior to the server, wherein the interaction behavior includes interaction with other user nodes and behavior added to the recommended content to represent attitude.
[0066] According to a fifth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions executable on the processor, and the processor is used to implement the social network management method described in the first aspect when executing the computer instructions.
[0067] According to a sixth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method described in the first aspect is implemented.
[0068] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:
[0069] The social network management method provided by the embodiment of the present disclosure inputs the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model to obtain the feature vector of the at least one user node output by the fusion model; and divides the social network into multiple communities according to the feature vector of the at least one user node. Since the feature vector of the user node combines the attribute information of the user node and the topological result of the social network, and the attribute information represents the behavioral characteristics and interest characteristics of the user node, and the topological result represents the association between the user node and other user nodes in the social network, the sub-social network obtained by the division is more accurate and in line with reality, and the calendar accuracy of the social network is improved. When recommending content or friends to the user nodes in the social network according to the community division result, the recommendation accuracy and user satisfaction can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0070] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0071] Figure 1 is a flow chart of a social network management method applied to a server according to an exemplary embodiment of the present disclosure;
[0072] Figure 2 is a flow chart of a method for dividing communities shown in an exemplary embodiment of the present disclosure;
[0073] Figure 3 is a flowchart of a method for dividing communities shown in another exemplary embodiment of the present disclosure;
[0074] Figure 4is a flowchart of a social network management method applied to a client according to an exemplary embodiment of the present disclosure;
[0075] Figure 5 is a structural diagram of a social network management device applied to a server side, shown in an exemplary embodiment of the present disclosure;
[0076] Figure 6 is a structural diagram of a social network management device applied to a client according to an exemplary embodiment of the present disclosure;
[0077] Figure 7 It is a structural block diagram of an electronic device shown in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION
[0078] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. 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.
[0079] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. The singular forms of "a", "said" and "the" used in this disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0080] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0081] With the popularity of social networks, more and more people are using social networks to communicate and share information. Due to the huge amount of information in social networks, it is difficult for users to find content or friends that they are interested in. Therefore, how to quickly and accurately find content or friends of interest has become an important issue. In the related art, content or friend recommendations are achieved by maintaining a social network that represents the relationship between different users, but the management accuracy of social networks is poor, resulting in inaccurate content or friend recommendations.
[0082] Based on this, in the first aspect, at least one embodiment of the present disclosure provides a social network management method, which can divide the social network into communities, so that the user nodes in the social network are divided into at least one community, and then based on the division results, recommendation information (such as recommended content and recommended friends) can be generated for each user node. This method can make the community division more accurate and fit the interests of the user nodes. Among them, the social network includes a topological structure formed by multiple user nodes and edges (i.e., connections) between different user nodes. The social network can be constructed in advance based on the interaction between user nodes. For example, if there is a friend relationship between two user nodes, an edge can be formed between the two user nodes.
[0083] Next, the method is introduced in detail from both the server and client sides, wherein the client may be a quick application client. A quick application is a lightweight application that can be run directly on a mobile phone without installing the application. The emergence of quick applications is to solve the problems of application installation, uninstallation, and update, and improve the user experience.
[0084] Please refer to the attached Figure 1 , which exemplarily shows a flowchart of a social network management method applied to a server, including steps S101 to S102.
[0085] In step S101, the topological structure of the social network and the attribute vector of at least one user node of the social network are input into a fusion model to obtain a feature vector of the at least one user node output by the fusion model, wherein the attribute vector is used to at least characterize the behavioral characteristics and interest characteristics of the user node.
[0086] Among them, the topological result is used to characterize the association relationship between different user nodes, that is, there is an association relationship between two user nodes with an edge, and there is no association relationship between two user nodes without an edge.
[0087] Exemplarily, the attribute vector of each user node may be generated in advance in the following manner: based on the interactive behavior of at least one user node of the social network, the attribute vector of the corresponding user node is generated, wherein the interactive behavior is fed back by the client, and the interactive behavior includes interaction with other user nodes and behavior added to the recommended content to characterize attitude.
[0088] For example, the client can collect user interaction behaviors, such as users chatting with other users, sharing content, liking each other, etc., or users liking, forwarding, editing, etc. certain recommended content. When users interact with other users, it can indicate that the user is interested in it; when users process recommended content, their behavior often indicates their attitude, such as liking to indicate that they like it.
[0089] For example, the server can use the word2vec algorithm to perform NLP (Natural Language Processing) processing on the voice information, interest information, etc. of the interactive behavior fed back by the client to obtain an attribute vector (ie, a word vector).
[0090] As another example, the fusion model may be an ANRL model, wherein the ANRL model includes a neighbor-enhanced autoencoder and an attribute-aware Skip-gram sub-model.
[0091] In step S102, the social network is divided into a plurality of communities according to the feature vector of the at least one user node, wherein each community includes at least one user node, and each user node of the user social network belongs to at least one community.
[0092] Exemplarily, this step may first calculate the information entropy of at least one (e.g., each) user node in the social network, and sort the at least one (e.g., each) user node in the social network in descending order according to the information entropy of at least one (e.g., each) user node in the social network; and then determine in turn the community to which each user node in the social network belongs.
[0093] For example, you can follow Figure 2 The method shown in FIG. 1 is to sequentially determine the community to which each user node in the social network belongs, including steps S201 to S202.
[0094] In step S201, the fitness of the community to which the user node and each of the at least one neighbor node belong is determined.
[0095] The neighbor nodes refer to the neighbor nodes of the user node in the social network.
[0096] Exemplarily, the fitness is determined according to the following formula:
[0097]
[0098] In the above formula, F C is the fitness of the community to which the user node and its neighbor nodes belong, After the user node is added to the community to which the neighbor node belongs, the sum of the node degrees within the community. The node degree of a node refers to the number of edges related to the node. After the user node is added to the community to which the neighbor node belongs, the sum of the connectivity between the internal nodes and the external nodes in the community. The connectivity between a node and an external node refers to the number of edges between the node and the external nodes. δ is a parameter that controls the size of the community. The larger the δ, the smaller the size of the community. The general value is [0.5, 1.5].
[0099] It is understandable that this step is performed when at least one neighbor node of the user node has determined the community to which it belongs. Correspondingly, in response to the user node having no neighbor nodes or all neighbor nodes of the user node not determining the community to which they belong, the user node may be determined as a new community.
[0100] In step S202, in response to the presence of a community whose fitness with the user node is greater than a first threshold value among the communities to which the at least one neighboring node belongs, the community whose fitness with the user node is greater than the first threshold value is determined as the community to which the user node belongs; in response to the absence of a community whose fitness with the user node is greater than the first threshold value among the communities to which the at least one neighboring node belongs, the user node is determined as a new community.
[0101] For example, the communities to which the three neighbor nodes A, B, and C of the user node belong have been determined, and the fitness of the community to which A belongs and the user node is greater than a first threshold, the fitness of the community to which B belongs and the user node is greater than the first threshold, and the fitness of the community to which C belongs and the user node is not greater than the first threshold, then it can be determined that the community to which the user node belongs is the community to which A belongs and the community to which B belongs.
[0102] For example, you can follow Figure 3 The method shown in FIG. 1 is to sequentially determine the community to which each user node in the social network belongs, including steps S301 to S302.
[0103] In step S301, the node similarity between each neighbor node of the user node and the user node is determined based on the feature vector of each neighbor node of the user node and the feature vector of the user node.
[0104] Exemplarily, the node similarity Sim(x) between the user node and the neighbor node is determined according to the following formula: t ,y t ):
[0105]
[0106] In the above formula, x t is the tth element of the k-dimensional feature vector X of the user node, y t is the tth element of the k-dimensional feature vector Y of the user node.
[0107] It is understandable that this step is performed when at least one neighbor node of the user node has determined the community to which it belongs. Correspondingly, in response to the user node having no neighbor nodes or all neighbor nodes of the user node not determining the community to which they belong, the user node may be determined as a new community.
[0108] In step S302, based on the node similarity between each neighboring node of the user node and the user node, the comprehensive similarity between each community of neighboring nodes of the user node and the user node is determined.
[0109] Exemplarily, the comprehensive similarity between the user node v and the community c is determined according to the following formula:
[0110]
[0111] In the above formula, N(v) is the set of neighbor nodes of user node v, F is the set of neighbor nodes of v in community c, and |F| is the number of nodes in F.
[0112] In step S303, in response to the existence of a comprehensive similarity greater than a second threshold value between the comprehensive similarities between each community where the neighboring node of the user node exists and the user node, the community corresponding to the comprehensive similarity greater than the second threshold value is determined as the community to which the user node belongs; in response to the absence of a comprehensive similarity greater than the second threshold value between the comprehensive similarities between each community where the neighboring node of the user node exists and the user node, the user node is determined as a new community.
[0113] For example, the communities to which the three neighbor nodes A, B, C, and D of the user node belong have been determined, and A and B belong to community 1, and C and D belong to community 2; therefore, the comprehensive similarity between the user node and community 1 can be determined based on the node similarity between the user node and A and the node similarity between the user node and B, and the comprehensive similarity between the user node and community 2 can be determined based on the node similarity between the user node and C and the node similarity between the user node and D; when the comprehensive similarity between the user node and community 1 is greater than a second threshold, community 1 is determined to be the community to which the node belongs, and when the comprehensive similarity between the user node and community 2 is not greater than the second threshold, community 1 is determined to be the community to which the node belongs.
[0114] The social network management method provided by the embodiment of the present disclosure inputs the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model to obtain the feature vector of the at least one user node output by the fusion model; and divides the social network into multiple communities according to the feature vector of the at least one user node. Since the feature vector of the user node combines the attribute information of the user node and the topological result of the social network, and the attribute information represents the behavioral characteristics and interest characteristics of the user node, and the topological result represents the association between the user node and other user nodes in the social network, the sub-social network obtained by the division is more accurate and in line with reality, and the calendar accuracy of the social network is improved. When recommending content or friends to the user nodes in the social network according to the community division result, the recommendation accuracy and user satisfaction can be improved.
[0115] In some embodiments of the present disclosure, in response to receiving a recommendation request sent by a client, a user identifier logged in on the client can be obtained; then, recommendation information can be determined based on the attributes of at least one community to which a user node corresponding to the user identifier belongs; finally, the recommendation information can be sent to the client so that the client displays the recommendation information.
[0116] Since the sub-social networks obtained by dividing the social network managed by the present disclosure are more accurate and realistic, the calendar accuracy of the social network is improved, and when content or friends are recommended to user nodes in the social network based on the community division results, the recommendation accuracy and user satisfaction can be improved.
[0117] Please refer to the attached Figure 4 , which exemplarily shows a flowchart of a social network management method applied to a client, including step S401.
[0118] Sending a user ID and a recommendation request to a server, and receiving recommendation information sent by the client;
[0119] The recommendation information is determined by the server according to the attribute of at least one community to which the user node corresponding to the user identifier belongs, and the user identifier is the identifier of the user logged in on the client;
[0120] The community of user nodes is obtained by the server side dividing the social network according to the social network topology structure and the attribute vector of at least one user node of the social network.
[0121] In some embodiments of the present disclosure, the user identification and interaction behavior may also be fed back to the server, wherein the interaction behavior includes interaction with other user nodes and behavior added to the recommended content to represent attitude.
[0122] The details of the above steps have been introduced in detail in the method on the server side of the first aspect and will not be repeated here.
[0123] According to a third aspect of the present disclosure, a social network management device is provided. Figure 5 , the device comprises:
[0124] The feature module 501 is used to input the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model to obtain the feature vector of the at least one user node output by the fusion model, wherein the attribute vector is used to characterize at least the behavior characteristics and interest characteristics of the user node;
[0125] The management module 502 is configured to divide the social network into a plurality of communities according to the feature vector of the at least one user node, wherein each community includes at least one user node, and each user node of the user social network belongs to at least one community.
[0126] In one embodiment of the present disclosure, the device further includes a generating module, which is used to:
[0127] Generate an attribute vector of a corresponding user node according to an interactive behavior of at least one user node of the social network, wherein the interactive behavior is fed back by a client, and the interactive behavior includes interaction with other user nodes and behavior added to the recommended content for representing attitude.
[0128] In one embodiment of the present disclosure, the management module is used to:
[0129] The community to which each user node in the social network belongs is determined in turn in the following manner:
[0130] Determining the fitness of the community to which each neighbor node of the user node and at least one neighbor node of the user node belongs;
[0131] In response to the presence of a community whose fitness with the user node is greater than a first threshold value in the community to which the at least one neighboring node belongs, determining the community whose fitness with the user node is greater than the first threshold value as the community to which the user node belongs;
[0132] In response to the fact that there is no community whose fitness with the user node is greater than a first threshold in the community to which the at least one neighbor node belongs, the user node is determined as a new community.
[0133] In one embodiment of the present disclosure, the management module is used to:
[0134] The community to which each user node in the social network belongs is determined in turn in the following manner:
[0135] Determine the node similarity between each neighbor node of the user node and the user node according to the feature vector of each neighbor node of the user node and the feature vector of the user node;
[0136] Determine the comprehensive similarity between each community of neighbor nodes of the user node and the user node according to the node similarity between each neighbor node of the user node and the user node;
[0137] In response to the existence of a comprehensive similarity greater than a second threshold value between each community where a neighboring node of the user node exists and the user node, determining the community corresponding to the comprehensive similarity greater than the second threshold value as the community to which the user node belongs;
[0138] In response to the fact that there is no comprehensive similarity greater than a second threshold value between each community where the neighboring node of the user node exists and the user node, the user node is determined as a new community.
[0139] In one embodiment of the present disclosure, the management module is further configured to:
[0140] In response to the user node having no neighboring nodes, or all neighboring nodes of the user node have not yet determined the community to which they belong, the user node is determined as a new community.
[0141] In one embodiment of the present disclosure, the device further includes a sorting module, which is used to:
[0142] The at least one user node in the social network is sorted according to the information entropy of the at least one user node.
[0143] In one embodiment of the present disclosure, the device further includes a recommendation module, which is used to:
[0144] In response to receiving a recommendation request sent by a client, obtaining a user ID logged in on the client;
[0145] Determining recommendation information according to an attribute of at least one community to which a user node corresponding to the user identifier belongs;
[0146] The recommendation information is sent to the client, so that the client displays the recommendation information.
[0147] In one embodiment of the present disclosure, the client is a quick application client.
[0148] According to a fourth aspect of the present disclosure, a social network management device is provided. Figure 6 , the device comprises:
[0149] The receiving module 601 is used to send a user identification and a recommendation request to the server, and receive the recommendation information sent by the client;
[0150] The recommendation information is determined by the server according to the attribute of at least one community to which the user node corresponding to the user identifier belongs, and the user identifier is the identifier of the user logged in on the client;
[0151] The community of user nodes is obtained by the server side dividing the social network according to the social network topology structure and the attribute vector of at least one user node of the social network.
[0152] In one embodiment of the present disclosure, the device further includes a feedback module, which is used to:
[0153] Feedback the user identification and interaction behavior to the server, wherein the interaction behavior includes interaction with other user nodes and behavior added to the recommended content to represent attitude.
[0154] Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the first aspect related to the method, and will not be elaborated here.
[0155] According to the fifth aspect of the embodiment of the present disclosure, please refer to the attached Figure 7 , which exemplarily shows a block diagram of an electronic device. For example, the device 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
[0156] Reference Figure 7 , the device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .
[0157] The processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.
[0158] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0159] The power component 406 provides power to the various components of the device 400. The power component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 400.
[0160] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
[0161] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the device 400 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.
[0162] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.
[0163] The sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400 and the temperature change of the device 400. The sensor assembly 414 can also include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 can also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
[0164] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G or 5G or a combination thereof. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0165] In an exemplary embodiment, the apparatus 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the social network management method of the electronic device described above.
[0166] In a sixth aspect, the present disclosure, in an exemplary embodiment, further provides a non-transitory computer-readable storage medium including instructions, such as a memory 404 including instructions, and the instructions can be executed by the processor 420 of the device 400 to complete the social network management method of the electronic device. 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.
[0167] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application 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 intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0168] 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 social network management method, characterized in that: The method comprises: Inputting the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model to obtain a feature vector of the at least one user node output by the fusion model, wherein the attribute vector is at least used to characterize the behavior characteristics and interest characteristics of the user node; According to the feature vector of the at least one user node, the social network is divided into a plurality of communities, wherein each community includes at least one user node, and each user node of the user social network belongs to at least one community.
2. The social network management method according to claim 1, characterized in that: The method further comprises: Generate an attribute vector of a corresponding user node according to an interactive behavior of at least one user node of the social network, wherein the interactive behavior is fed back by a client, and the interactive behavior includes interaction with other user nodes and behavior added to the recommended content for representing attitude.
3. The social network management method according to claim 1, characterized in that: The step of dividing the social network into a plurality of communities according to the feature vector of the at least one user node comprises: The community to which each user node in the social network belongs is determined in turn in the following manner: Determining the fitness of the community to which each neighbor node of the user node and at least one neighbor node of the user node belongs; In response to the presence of a community whose fitness with the user node is greater than a first threshold value in the community to which the at least one neighboring node belongs, determining the community whose fitness with the user node is greater than the first threshold value as the community to which the user node belongs; In response to the fact that there is no community whose fitness with the user node is greater than a first threshold in the community to which the at least one neighbor node belongs, the user node is determined as a new community.
4. The social network management method according to claim 1, characterized in that: The step of dividing the social network into a plurality of communities according to the feature vector of the at least one user node comprises: The community to which each user node in the social network belongs is determined in turn in the following manner: Determine the node similarity between each neighbor node of the user node and the user node according to the feature vector of each neighbor node of the user node and the feature vector of the user node; Determine the comprehensive similarity between each community of neighbor nodes of the user node and the user node according to the node similarity between each neighbor node of the user node and the user node; In response to the existence of a comprehensive similarity greater than a second threshold value between each community where a neighboring node of the user node exists and the user node, determining the community corresponding to the comprehensive similarity greater than the second threshold value as the community to which the user node belongs; In response to the fact that there is no comprehensive similarity greater than a second threshold value between each community where the neighboring node of the user node exists and the user node, the user node is determined as a new community.
5. The social network management method according to claim 3 or 4, characterized in that: The method further comprises: In response to the user node having no neighboring nodes, or all neighboring nodes of the user node have not yet determined the community to which they belong, the user node is determined as a new community.
6. The social network management method according to claim 3 or 4, characterized in that: The method further comprises: The at least one user node in the social network is sorted according to the information entropy of the at least one user node.
7. The social network management method according to claim 1, characterized in that: The method further comprises: In response to receiving a recommendation request sent by a client, obtaining a user ID logged in on the client; Determining recommendation information according to an attribute of at least one community to which a user node corresponding to the user identifier belongs; The recommendation information is sent to the client, so that the client displays the recommendation information.
8. The social network management method according to claim 2, characterized in that: The client is a quick application client.
9. A social network management method, characterized in that: The method comprises: Send user ID and recommendation request to the server, and receive recommendation information sent by the client; The recommendation information is determined by the server according to the attribute of at least one community to which the user node corresponding to the user identifier belongs, and the user identifier is the identifier of the user logged in on the client; The community of user nodes is obtained by the server side dividing the social network according to the social network topology structure and the attribute vector of at least one user node of the social network.
10. The social network management method according to claim 9, characterized in that: The method further comprises: Feedback the user identification and interaction behavior to the server, wherein the interaction behavior includes interaction with other user nodes and behavior added to the recommended content to represent attitude.
11. A social network management device, characterized in that: The device comprises: A feature module, used to input the topological structure of the social network and the attribute vector of at least one user node of the social network into the fusion model, and obtain the feature vector of the at least one user node output by the fusion model, wherein the attribute vector is used to characterize at least the behavior characteristics and interest characteristics of the user node; The management module is used to divide the social network into multiple communities according to the feature vector of the at least one user node, wherein each community includes at least one user node, and each user node of the user social network belongs to at least one community.
12. The social network management device according to claim 11, characterized in that: The device also includes a generating module, which is used to: Generate an attribute vector of a corresponding user node according to an interactive behavior of at least one user node of the social network, wherein the interactive behavior is fed back by a client, and the interactive behavior includes interaction with other user nodes and behavior added to the recommended content for representing attitude.
13. The social network management device according to claim 11, characterized in that: The management module is used for: The community to which each user node in the social network belongs is determined in turn in the following manner: Determining the fitness of the community to which each neighbor node of the user node and at least one neighbor node of the user node belongs; In response to the presence of a community whose fitness with the user node is greater than a first threshold value in the community to which the at least one neighboring node belongs, determining the community whose fitness with the user node is greater than the first threshold value as the community to which the user node belongs; In response to the fact that there is no community whose fitness with the user node is greater than a first threshold in the community to which the at least one neighbor node belongs, the user node is determined as a new community.
14. The social network management device according to claim 11, characterized in that: The management module is used for: The community to which each user node in the social network belongs is determined in turn in the following manner: Determine the node similarity between each neighbor node of the user node and the user node according to the feature vector of each neighbor node of the user node and the feature vector of the user node; Determine the comprehensive similarity between each community of neighbor nodes of the user node and the user node according to the node similarity between each neighbor node of the user node and the user node; In response to the existence of a comprehensive similarity greater than a second threshold value between each community where a neighboring node of the user node exists and the user node, determining the community corresponding to the comprehensive similarity greater than the second threshold value as the community to which the user node belongs; In response to the fact that there is no comprehensive similarity greater than a second threshold value between each community where the neighboring node of the user node exists and the user node, the user node is determined as a new community.
15. The social network management device according to claim 13 or 14, characterized in that: The management module is also used for: In response to the user node having no neighboring nodes, or all neighboring nodes of the user node have not yet determined the community to which they belong, the user node is determined as a new community.
16. The social network management device according to claim 13 or 14, characterized in that: The device also includes a sorting module, which is used to: The at least one user node in the social network is sorted according to the information entropy of the at least one user node.
17. The social network management device according to claim 11, characterized in that: The device also includes a recommendation module, which is used to: In response to receiving a recommendation request sent by a client, obtaining a user ID logged in on the client; Determining recommendation information according to an attribute of at least one community to which a user node corresponding to the user identifier belongs; The recommendation information is sent to the client, so that the client displays the recommendation information.
18. The social network management device according to claim 12, characterized in that: The client is a quick application client.
19. A social network management device, characterized in that: The device comprises: A receiving module, used to send a user ID and a recommendation request to the server, and receive recommendation information sent by the client; The recommendation information is determined by the server according to the attribute of at least one community to which the user node corresponding to the user identifier belongs, and the user identifier is the identifier of the user logged in on the client; The community of user nodes is obtained by the server side dividing the social network according to the social network topology structure and the attribute vector of at least one user node of the social network.
20. The social network management device according to claim 19, characterized in that: The device also includes a feedback module, which is used to: Feedback the user identification and interaction behavior to the server, wherein the interaction behavior includes interaction with other user nodes and behavior added to the recommended content to represent attitude.
21. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store computer instructions executable on the processor, and the processor is used to implement the social network management method according to any one of claims 1 to 10 when executing the computer instructions.
22. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.