CN114265989A - Friend recommendation method, electronic device and computer-readable storage medium - Google Patents
Friend recommendation method, electronic device and computer-readable storage medium Download PDFInfo
- Publication number
- CN114265989A CN114265989A CN202111637979.XA CN202111637979A CN114265989A CN 114265989 A CN114265989 A CN 114265989A CN 202111637979 A CN202111637979 A CN 202111637979A CN 114265989 A CN114265989 A CN 114265989A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- social
- sample
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a friend recommendation method, electronic equipment and a computer-readable storage medium. The method comprises the steps that a second user in a user information base is obtained by aiming at a first user in the user information base; obtaining satisfaction information of the first user to the second user and obtaining satisfaction information of the second user to the first user; obtaining social interest information between the first user and the second user; obtaining social effective information of the second user relative to the first user based on the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information; and in response to the fact that the social effective information meets the preset condition, the second user is determined as the recommended friend of the first user, so that the second user is recommended to the first user, and the accuracy of friend recommendation can be improved.
Description
[ technical field ] A method for producing a semiconductor device
The present disclosure relates to internet technologies, and in particular, to a friend recommendation method, an electronic device, and a computer-readable storage medium.
[ background of the invention ]
In recent years, with the rapid development of internet technology, the use of social platforms is more and more common in people's daily lives, so that people are more and more accustomed to speaking, chatting and making friends through a social network, and a social network friend-making mode is brought out under the circumstance. In order to enable users to hand over to like-minded friends, the current social network friend-making mode also provides a friend recommendation function, friend recommendation is carried out by utilizing interests and connections among the users, the friend recommendation function on the social platform is used as an important means for information filtering, and users with the same or similar interests can be recommended to the users through community division.
In the prior art, most social contact platforms recommend friends of target users based on certain characteristics, such as node importance, common friend number and shortest path. For example: the QQ is friend recommendation according to the number of common friends between the target user and other users. WeChat provides a "shake-shake" function for friend recommendation based on geographic distance.
In the process of implementing the invention, the inventor discovers through research that most of social platforms in the prior art have limitations and sidedness to a certain extent in a method for friend recommendation with a single characteristic, so that the accuracy of friend recommendation is low, effective friend recommendation cannot be implemented, interference on recommended users is likely to be brought, and user experience is reduced.
[ summary of the invention ]
Aspects of the present disclosure provide a friend recommendation method, an electronic device, and a computer-readable storage medium, so as to improve accuracy of friend recommendation.
One aspect of the present application provides a friend recommendation method, including:
aiming at a first user in a user information base, acquiring a second user in the user information base; wherein the second user is a user in the user information base except the first user;
obtaining satisfaction information of the first user to the second user and obtaining satisfaction information of the second user to the first user;
obtaining social interest information between the first user and the second user;
obtaining social effective information of the second user relative to the first user based on the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information;
and in response to the fact that the social effective information meets a preset condition, determining the second user as a recommended friend of the first user, and recommending the second user to the first user.
In another aspect of the present application, there is provided an electronic device including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement video repeatability recognition as provided in an aspect above.
In another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the video repeatability recognition provided in the above aspect.
In a further aspect of the disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the aspect and any possible implementation as described above.
According to the technical scheme, in some embodiments of the application, a second user except for a first user in a user information base is obtained from the user information base, satisfaction information of the first user to the second user, satisfaction information of the second user to the first user and social interest information between the first user and the second user are obtained, then social effective information of the second user relative to the first user is obtained based on the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information, and when the social effective information meets a preset condition, the second user is determined to be a recommended friend of the first user, so that the second user is recommended to the first user. Because the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information are considered at the same time to obtain the social effective information of the second user relative to the first user, the possibility that the second user is used as an effective social friend of the first user can be comprehensively determined from multiple dimensions, the accuracy of friend recommendation is improved, effective friend recommendation can be realized, and effective social interaction is promoted.
In addition, by adopting the technical scheme provided by the application, only when the social effective information meets the preset condition, the second user is determined as the recommended friend of the first user and recommended to the first user, so that the interference of invalid friend recommendation on the user can be effectively avoided, and the user experience can be improved.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to the drawings without inventive labor.
Fig. 1 is a schematic flowchart of a friend recommendation method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a friend recommendation method according to another embodiment of the present application;
fig. 3 is a schematic flowchart of a friend recommendation method according to another embodiment of the present application;
fig. 4 is a flowchart illustrating a friend recommendation method according to yet another embodiment of the present application;
FIG. 5 is a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present application.
[ detailed description ] embodiments
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some but not all embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art without any inventive work based on the embodiments in the present application are within the scope of protection of the present application.
It should be noted that the terminal involved in the embodiments of the present application may include, but is not limited to, a mobile phone, a Personal Digital Assistant (PDA), a wireless handheld device, a Tablet Computer (Tablet Computer), a Personal Computer (PC), an MP3 player, an MP4 player, a wearable device (e.g., smart glasses, smart watch, smart bracelet, etc.), and the like.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
As described in the background art, most of the methods for recommending friends by using a single feature in the social contact platforms in the prior art have limitations and sidedness to a certain extent, so that the accuracy of friend recommendation cannot be low, effective friend recommendation cannot be realized, interference may be brought to recommended users, and user experience is reduced.
Therefore, it is desirable to provide a friend recommendation method, an electronic device and a computer-readable storage medium for improving the accuracy of friend recommendation.
The design idea of the method is to solve the problems that the method for recommending friends by using single characteristic in the prior art is low in friend recommendation accuracy and cannot realize effective friend recommendation. According to the method and the device, the satisfaction degree information of the first user to the second user, the satisfaction degree information of the second user to the first user and the social interest information between the first user and the second user are obtained, then the social effective information of the second user relative to the first user is obtained based on the satisfaction degree information of the first user to the second user, the satisfaction degree information of the second user to the first user and the social interest information, and whether the second user is recommended to the first user is determined according to the social effective information.
The embodiment of the application can be applied to various social platforms such as internet websites and APP (e.g. WeChat, QQ) and the like.
Fig. 1 is a flowchart illustrating a friend recommendation method according to an embodiment of the present application, as shown in fig. 1.
101. And aiming at the first user in the user information base, acquiring a second user in the user information base.
The user information base is a database used for storing user information on the social platform. The user information may include any one or more of the following: the social networking service system comprises the following information of a user, registration information of the user (such as a user name, a user Identification (ID) and the like), information published by the user on the social networking platform (such as videos, friend circles and the like), information uploaded by the user (such as documents, pictures, head portraits and the like), interaction information of the user and other users on the social networking platform (such as chat records, friend application passing records, friend address lists and the like), information used by the user on the social networking platform (such as online time, browsing information, collection information, access information, approval information and the like), and the like.
The first user may be any user in the user information base, and the second user may be any user in the user information base except the first user. In the present application, the user may be identified by a user ID.
Optionally, in some implementation manners, one user (i.e., a user ID) may be sequentially selected from the user information base as a first user, and then, for the first user, one user other than the first user may be sequentially selected from the user information base as a second user (i.e., a user ID), so that friend recommendation for all users in the user information base may be implemented based on the embodiment of the present application.
Optionally, in another implementation manner, one user (i.e., a user ID) with an activity (e.g., an online duration, an interactive information count) meeting a preset activity condition may be sequentially selected from the user information base as a first user, and then, for the first user, one user other than the first user is sequentially selected from the user information base as a second user (i.e., a user ID), so that friend recommendation for a user with a higher activity in the user information base may be implemented based on the embodiment of the present application.
102. And obtaining the satisfaction information of the first user to the second user, and obtaining the satisfaction information of the second user to the first user.
Similarly, the satisfaction information of the second user to the first user is used to represent the satisfaction of the second user to the first user, and the satisfaction information may be specifically represented by a satisfaction value or a satisfaction level, which is not limited in this embodiment of the application.
103. Social interest information between a first user and a second user is obtained.
The social interest information is used to indicate interest of interaction between two users, and the social interest information may be represented by a social interest value or a social interest level, which is not limited in this embodiment of the application.
104. And obtaining the social effective information of the second user relative to the first user based on the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information.
105. And in response to the fact that the social effective information meets the preset condition, determining the second user as a recommended friend of the first user, and recommending the second user to the first user.
It should be noted that part or all of the execution subjects 101 to 105 may be an application located in the terminal, or may also be a functional unit such as a plug-in or Software Development Kit (SDK) in an application for setting the terminal, or may also be an application located in a network side server, which is not particularly limited in this embodiment of the present application.
It is to be understood that the application may be a native app (native app) installed on the terminal, or may also be a web page program (webApp) of a browser on the terminal, which is not limited in this embodiment of the present application.
Therefore, the social effective information of the second user relative to the first user is obtained by simultaneously considering the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information, and the possibility that the second user is used as an effective social friend of the first user can be comprehensively determined from multiple dimensions, so that the friend recommendation accuracy is improved, effective friend recommendation can be realized, and effective social contact is promoted. In addition, only when the social effective information meets the preset condition, the second user is determined as the recommended friend of the first user, and the second user is recommended to the first user, so that interference of invalid friend recommendation on the user can be effectively avoided, and the user experience is improved.
Fig. 2 is a flowchart illustrating a friend recommendation method according to another embodiment of the present application. As shown in fig. 2, on the basis of the embodiment shown in fig. 1, in 102, the satisfaction information of the first user to the second user can be obtained by:
201. and acquiring friend information, social dynamic information and uploaded image information of the first user.
202. And acquiring friend information, social dynamic information and uploaded image information of the second user.
202 and 201 may be executed simultaneously or in any order, which is not limited in this embodiment of the present application.
203. And splicing the friend information, the social dynamic information and the uploaded image information of the first user and the friend information, the social dynamic information and the uploaded image information of the second user according to the sequence to obtain first spliced information.
204. And inputting the first splicing information into a pre-trained first neural network model, and outputting satisfaction information of the first user to the second user through the first neural network model.
Similarly, the satisfaction information of the second user to the first user may be acquired by:
acquiring friend information, social dynamic information and uploaded image information of a second user;
acquiring friend information, social dynamic information and uploaded image information of a first user;
splicing the friend information, the social dynamic information and the uploaded image information of the second user and the friend information, the social dynamic information and the uploaded image information of the first user in sequence to obtain second spliced information;
and inputting the second splicing information into the first neural network model, and outputting the satisfaction information of the second user to the first user through the first neural network model.
The first Neural Network model may be various Neural Network models based on a Deep learning method, such as Deep Neural Network (DNN), Long Short Term Memory (LSTM), LSTM + CRF model composed of LSTM and Conditional Random Fields (CRF), and a model (transform) based on a multi-head attention machine system, which is not limited in the embodiments of the present application.
Based on the embodiment, friend information, social dynamic information and uploaded image information of a first user and friend information, social dynamic information and uploaded image information of a second user can be spliced in sequence to obtain first spliced information, then a first neural network model trained in advance in a deep learning mode is used for predicting satisfaction information of the first user to the second user, and satisfaction information of the second user to the first user in a similar mode can be accurately and quickly predicted due to the fact that the first neural network model trained in advance in the deep learning mode has certain generalization.
Optionally, in some implementations, the friend information may include, but is not limited to, any one or more of the following: the number of friends in the address book and the number of users communicating with the users; and/or, the social dynamic information may include, for example, but not limited to, any one or more of: the click quantity of the released video, the praise number of the released video and the praise number of the information released by the friend circle; and/or, the uploaded image information may include, for example, but is not limited to, any one or more of: the head portrait is a picture uploaded through an interactive interface of the social platform.
Based on the embodiment, the detailed friend information, social dynamic information and uploaded image information of two users are utilized, the satisfaction information of one user to the other user can be predicted more accurately, and therefore the accuracy of the satisfaction information can be improved.
Optionally, in a friend recommendation method of another embodiment, the first neural network model may be obtained by training in advance. Optionally, in some implementations, the first neural network model may be trained by:
obtaining at least one first training sample, wherein the first training sample comprises a target sample user and at least one interactive user of the target sample user, each interactive user of the at least one interactive user has a satisfaction degree label, the satisfaction degree label is used for expressing the satisfaction degree of the target sample user to each interactive user, and the satisfaction degree label is determined according to whether each interactive user applies for friends of the target sample user and social activity;
respectively aiming at each first training sample in the at least one first training sample, acquiring friend information, social dynamic information and uploaded image information of a target sample user, and acquiring friend information, social dynamic information and uploaded image information of each second interaction user;
splicing friend information, social dynamic information and uploaded image information of the target sample user and friend information, social dynamic information and uploaded image information of each interactive user according to a sequence to obtain third spliced information;
inputting the third splicing information into a first neural network model to be trained, and outputting satisfaction information of the target sample user to each interactive user through the first neural network model to be trained;
and training the first neural network model to be trained based on the satisfaction information of the target sample user to each interactive user and the satisfaction label of each interactive user until a preset training completion condition is reached to obtain the first neural network model.
In this embodiment of the application, the process of obtaining the first neural network model through training may be an iterative operation, that is, the process of obtaining the first neural network model through training is iteratively executed until a preset training completion condition is met, and the first neural network model can be obtained from the first neural network model to be trained. The preset training completion condition may include, but is not limited to, any one or more of the following: the difference between the satisfaction information of the target sample user of the at least one first training sample for each interactive user and the satisfaction tag of each interactive user is smaller than a preset difference threshold, or the number of times of iteratively executing the above-mentioned process of training to obtain the first neural network model reaches a preset number of times (for example, 2000 times), and the like, which is not limited in this application.
Based on the embodiment, the first neural network model can be obtained by training in a deep learning mode, so that the trained first neural network model has certain generalization, and the satisfaction information of one user to another user can be accurately and quickly predicted.
Fig. 3 is a flowchart illustrating a friend recommendation method according to another embodiment of the present application. As shown in fig. 3, on the basis of the embodiment shown in fig. 1 or fig. 2, 103 may include:
301. a first face image including a face of a first user is acquired.
302. A second face image including a face of a second user is acquired.
The 302 and the 301 may be executed simultaneously or in any sequence, which is not limited in this application.
303. And inputting the first face image and the second face image into a pre-trained second neural network model, and outputting the feature information of the first user on the preset features, the feature information of the second user on the preset features and the similarity between the face of the first user and the face of the second user through the second neural network model.
Wherein the preset features comprise at least two features with different dimensions, such as features with age dimension, features with gender dimension, and the like. The similarity between the faces is used for representing the similarity between the two faces, and the specific value range of the similarity can be [0,1], wherein 1 represents that the similarity between the two faces is 100% and is the face of the same user. 0 means that the similarity between the two faces is the lowest, and is 0.
The second neural network model may be various neural network models based on a deep learning manner, such as DNN, LSTM + CRF model, transform, and the like, which is not limited in this embodiment of the present application.
304. And determining social interest information between the first user and the second user based on the feature information of the first user on the preset features, the feature information of the second user on the preset features and the similarity between the face of the first user and the face of the second user.
Based on the embodiment, a second neural network model trained in advance can be utilized, based on a first face image of a first user and a second face image of a second user, feature information of the first user and the second user on preset features and similarity between the face of the first user and the face of the second user are predicted quickly and accurately, and further based on feature information of the first user and the second user on the preset features and similarity between the face of the first user and the face of the second user, social interest information between the first user and the second user can be determined accurately.
Optionally, in the friend recommendation method of another embodiment, the second neural network model may be obtained by training in advance. Optionally, in some implementations, the second neural network model may be trained by:
acquiring at least one second training sample, wherein the second training sample comprises a sample pair consisting of a face image of a first sample user and a face image of a second sample user, the sample pair has a feature label of the first sample user on a preset feature, a feature label of the second sample user on the preset feature, and whether the same user label is used for indicating whether the face image of the first sample user and the face image of the second sample user are face images of the same user, the same user label can be 1, and different user labels can be 0 or specific similarity values;
respectively inputting each second training sample into a second neural network model to be trained aiming at each second training sample in the at least one second training sample, and outputting the predicted feature information of the first sample user on the preset features, the predicted feature information of the second user on the preset features and the predicted similarity between the face of the first sample user and the face of the second sample user in each second training sample through the second neural network model to be trained;
and training the second neural network model to be trained based on the predicted feature information of the first sample user on the preset features, the predicted feature information of the second user on the preset features, the predicted similarity between the face of the first sample user and the face of the second sample user, the feature label of the first sample user on the preset features, the feature label of the second sample user on the preset features and whether the same user label exists or not until a preset training completion condition is reached, and obtaining the second neural network model.
In the embodiment of the present application, the process of obtaining the second neural network model through training may be an iterative operation, that is, the process of obtaining the second neural network model through iteratively executing the training is performed until a preset training completion condition is met, that is, the second neural network model can be obtained through the second neural network model to be trained. The preset training completion condition may include, but is not limited to, any one or more of the following: the predicted feature information of the first sample user on the preset feature, the predicted feature information of the second user on the preset feature, and the predicted similarity between the face of the first sample user and the face of the second sample user of the at least one second training sample, and whether the difference between the feature label of the first sample user on the preset feature, the feature label of the second sample user on the preset feature, and the same user label is smaller than a preset difference threshold, or the number of times of performing the process of obtaining the second neural network model by the above training iteratively reaches a preset number of times (for example, 2000 times), and the like, which is not limited by the embodiment of the present application.
Based on the embodiment, a deep learning mode can be adopted to train and obtain the second neural network model, so that the trained second neural network model has certain generalization, and the feature information of the two users on the preset features and the similarity between the faces of the two users can be accurately and quickly predicted.
Optionally, in some implementations of the embodiment shown in fig. 3, in 304, the feature information of the first user on the preset features, the feature information of the second user on the preset features, and the similarity between the face of the first user and the face of the second user may be input into a third neural network model trained in advance, and a social interest value is output via the third neural network model, where the social interest information includes the social interest value.
Optionally, at least one third training sample may be used to train a third neural network model to be trained in advance to obtain the third neural network model. Specifically, each third training sample comprises feature information of two users on preset features and similarity between faces of the two users, and carries a social interest label, at least one third training sample is input into a third neural network model to be trained, the third neural network model to be trained outputs a social interest value, the third neural network model to be trained is used for outputting a difference between the social interest value and the corresponding social interest label, the third neural network model to be trained is trained until a preset training completion condition is reached, and the third neural network model is obtained. The specific implementation manner of the third neural network model obtained by training may refer to the specific implementation manner of the first neural network model and the second neural network model obtained by training in the above embodiments, and details are not repeated here.
The inventor finds that people are easily attracted by people who have common parts and similarities with the inventor. Based on the embodiment, a third neural network model can be obtained by training in a deep learning manner, so that the trained third neural network model has a certain generalization, and the social interest value between two users can be accurately and quickly predicted based on the feature information of the two users on the preset features and the similarity between the faces of the two users.
Optionally, in some implementation manners of the embodiment shown in fig. 3, in 304, a feature difference of a first dimension (for example, age) in the preset feature of the first user and a feature difference of a second dimension (for example, gender) in the preset feature of the second user may also be obtained according to the feature information of the first user on the preset feature and the feature information of the second user on the preset feature; then, a social interest value between the first user and the second user is determined according to the feature difference of the first dimension, the feature difference of the second dimension and the similarity between the face of the first user and the face of the second user, wherein the social interest information comprises the social interest value.
The inventor finds that people are easily attracted by people who have common parts and similarities with the inventor, and particularly, people are easily attracted by opposite sex with age difference within a certain range (for example, within 6 years). Based on the embodiment, the social interest value between the first user and the second user can be determined by utilizing the feature difference of the first dimension (such as age) and the second dimension (such as gender) in the preset features of the first user and the second user and the similarity between the face of the first user and the face of the second user
Fig. 4 is a flowchart illustrating a friend recommendation method according to still another embodiment of the present application. As shown in fig. 3, on the basis of the embodiments shown in fig. 1 to 3, 104 may include:
401. and based on the first preset weight factor, carrying out weighting processing on the satisfaction information of the first user to the second user and the satisfaction information of the second user to the first user to obtain a first weighting processing value.
402. And performing weighting processing on the social interest information based on a second preset weight factor to obtain a second weighting processing value.
403. And obtaining a social effective value based on the first weighted processing value and the second weighted processing value, wherein the social effective information comprises the social effective value.
For example, in one implementation, the socially valid value may be obtained by: the social effective value is (1-a) the satisfaction value of the first user to the second user + a the satisfaction value of the second user to the first user + a social interest value.
The value range of a can be [0,1], and the specific value of a can be preset according to actual requirements and can be adjusted according to specific scenes and services.
Optionally, in some implementations, in 105, the socially valid information satisfies a preset condition, including: the social effective value is larger than a preset threshold value, and the preset condition comprises the preset threshold value. The value of the preset threshold may be preset according to a requirement, and may be adjusted according to a specific scenario and a specific service, for example, when the value range of the social effective value is [0,100], the value of the preset threshold may be 80.
Based on the embodiment, through a formula, the social interest value between two users can be objectively and accurately determined in a quantitative calculation mode, so that the social interest value of the user pair with the social effective value larger than the preset threshold value is promoted to be socialized.
In addition, in a further embodiment of the present application, after the first, second, and third neural network models are obtained through training, social effective value labels may be set for the training samples, and after the social effective values are obtained through calculation based on information output by the first, second, and third neural network models, the first, second, and third neural network models may be further trained end to end by using differences between the obtained social effective values and the corresponding social effective value labels, so as to achieve fine tuning of the overall performance of the first, second, and third neural network models. The specific training mode may refer to the specific implementation modes of the first neural network model and the second neural network model obtained by training in the above embodiments, and details are not repeated here.
According to the technical scheme, because the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information are considered at the same time, the social effective information of the second user relative to the first user is obtained, the possibility that the second user is used as an effective social friend of the first user can be comprehensively determined from multiple dimensions, the friend recommendation accuracy is improved, effective friend recommendation can be achieved, and effective social is promoted.
In addition, by adopting the technical scheme provided by the application, only when the social effective information meets the preset condition, the second user is determined as the recommended friend of the first user and recommended to the first user, so that the interference of invalid friend recommendation on the user can be effectively avoided, and the user experience can be improved.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that the acts and modules involved are not necessarily required for this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
FIG. 5 illustrates a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present application. The computer system/server 12 shown in FIG. 5 is only one example and should not be taken to limit the scope of use or the functionality of embodiments of the present application.
As shown in FIG. 5, computer system/server 12 is in the form of a general purpose computing device. The components of computer system/server 12 may include, but are not limited to: one or more processors or processing units 16, a storage device or system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Computer system/server 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer system/server 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The computer system/server 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
Program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
The computer system/server 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the computer system/server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the computer system/server 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 44. Also, the computer system/server 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via a network adapter 20. As shown, network adapter 20 communicates with the other modules of computer system/server 12 via bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the computer system/server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the friend recommendation method provided in any embodiment corresponding to fig. 1 to 4.
Another embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the friend recommendation method provided in any embodiment of the embodiments corresponding to fig. 1 to 4.
In particular, any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and in actual implementation, there may be other divisions, for example, multiple units or page components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (13)
1. A friend recommendation method is characterized by comprising the following steps:
aiming at a first user in a user information base, acquiring a second user in the user information base; wherein the second user is a user in the user information base except the first user;
obtaining satisfaction information of the first user to the second user and obtaining satisfaction information of the second user to the first user;
obtaining social interest information between the first user and the second user;
obtaining social effective information of the second user relative to the first user based on the satisfaction information of the first user to the second user, the satisfaction information of the second user to the first user and the social interest information;
and in response to the fact that the social effective information meets a preset condition, determining the second user as a recommended friend of the first user, and recommending the second user to the first user.
2. The method of claim 1, wherein the obtaining satisfaction information of the first user with the second user comprises:
acquiring friend information, social dynamic information and uploaded image information of the first user;
acquiring friend information, social dynamic information and uploaded image information of the second user;
splicing the friend information, the social dynamic information and the uploaded image information of the first user and the friend information, the social dynamic information and the uploaded image information of the second user according to a sequence to obtain first spliced information;
inputting the first splicing information into a pre-trained first neural network model, and outputting satisfaction information of the first user to the second user through the first neural network model;
and/or the presence of a gas in the gas,
the obtaining of the satisfaction information of the second user to the first user includes:
acquiring friend information, social dynamic information and uploaded image information of the second user;
acquiring friend information, social dynamic information and uploaded image information of the first user;
splicing the friend information, the social dynamic information and the uploaded image information of the second user and the friend information, the social dynamic information and the uploaded image information of the first user according to a sequence to obtain second spliced information;
inputting the second splicing information into the first neural network model, and outputting satisfaction information of the second user to the first user through the first neural network model.
3. The method of claim 2, wherein the friend information comprises any one or more of the following: the number of friends in the address book and the number of users communicating with the users; and/or the presence of a gas in the gas,
the social dynamic information includes any one or more of: the click quantity of the released video, the praise number of the released video and the praise number of the information released by the friend circle; and/or the presence of a gas in the gas,
the uploaded image information comprises any one or more of the following items: the head portrait is a picture uploaded through an interactive interface of the social platform.
4. The method of claim 2, wherein the training of the first neural network model comprises:
obtaining at least one first training sample, wherein the first training sample comprises a target sample user and at least one interactive user of the target sample user, each interactive user has a satisfaction degree label, the satisfaction degree label is used for representing the satisfaction degree of the target sample user to each interactive user, and the satisfaction degree label is determined according to whether each interactive user applies for friends of the target sample user and social activity;
respectively aiming at each first training sample in the at least one first training sample, acquiring friend information, social dynamic information and uploaded image information of the target sample user, and acquiring friend information, social dynamic information and uploaded image information of each second interaction user;
splicing friend information, social dynamic information and uploaded image information of the target sample user and friend information, social dynamic information and uploaded image information of each interactive user according to a sequence to obtain third spliced information;
inputting the third splicing information into a first neural network model to be trained, and outputting satisfaction information of the target sample user to each interactive user through the first neural network model to be trained;
and training the first neural network model to be trained based on the satisfaction information of the target sample user to each interactive user and the satisfaction label of each interactive user until a preset training completion condition is reached to obtain the first neural network model.
5. The method according to any one of claims 1 to 4, wherein the obtaining of the social interest information between the first user and the second user comprises:
acquiring a first face image including a face of the first user;
acquiring a second face image comprising the face of the second user;
inputting the first face image and the second face image into a pre-trained second neural network model, and outputting feature information of the first user on preset features, feature information of the second user on the preset features, and similarity between the face of the first user and the face of the second user through the second neural network model; wherein the preset features comprise features of at least two different dimensions;
determining social interest information between the first user and the second user based on the feature information of the first user on the preset features, the feature information of the second user on the preset features, and the similarity between the face of the first user and the face of the second user.
6. The method of claim 5, wherein the training of the second neural network model comprises:
acquiring at least one second training sample, wherein the second training sample comprises a sample pair consisting of a face image of a first sample user and a face image of a second sample user, the sample pair has a feature label of the first sample user on the preset feature, a feature label of the second sample user on the preset feature, and whether the same user label is used for indicating whether the face image of the first sample user and the face image of the second sample user are the face images of the same user;
respectively aiming at each second training sample in the at least one second training sample, inputting each second training sample into a second neural network model to be trained, and outputting the predicted feature information of the first sample user on the preset features, the predicted feature information of the second user on the preset features and the predicted similarity between the face of the first sample user and the face of the second sample user in each second training sample through the second neural network model to be trained;
training the second neural network model to be trained based on the predicted feature information of the first sample user on the preset features, the predicted feature information of the second user on the preset features, the predicted similarity between the face of the first sample user and the face of the second sample user, the feature label of the first sample user on the preset features, the feature label of the second sample user on the preset features, and whether the same user label exists or not, until a preset training completion condition is reached, and obtaining the second neural network model.
7. The method of claim 5, wherein the determining social interest information between the first user and the second user based on the feature information of the first user on the preset features, the feature information of the second user on the preset features, and the similarity between the face of the first user and the face of the second user comprises:
inputting the feature information of the first user on the preset features, the feature information of the second user on the preset features and the similarity between the face of the first user and the face of the second user into a pre-trained third neural network model, and outputting a social interest value through the third neural network model, wherein the social interest information comprises the social interest value.
8. The method of claim 5, wherein the determining social interest information between the first user and the second user based on the feature information of the first user on the preset features, the feature information of the second user on the preset features, and the similarity between the face of the first user and the face of the second user comprises:
according to the feature information of the first user on the preset features and the feature information of the second user on the preset features, acquiring the feature difference of a first dimension of the first user and the second user in the preset features and acquiring the feature difference of a second dimension of the first user and the second user in the preset features;
determining a social interest value between the first user and the second user according to the feature difference of the first dimension, the feature difference of the second dimension and the similarity between the face of the first user and the face of the second user, wherein the social interest information comprises the social interest value.
9. The method of claim 5, wherein obtaining socially valid information of the second user relative to the first user based on the satisfaction information of the first user with the second user, the satisfaction information of the second user with the first user, and the social interest information comprises:
based on a first preset weight factor, carrying out weighting processing on the satisfaction information of the first user to the second user and the satisfaction information of the second user to the first user to obtain a first weighting processing value;
based on a second preset weight factor, performing weighting processing on the social interest information to obtain a second weighting processing value;
and obtaining a social effective value based on the first weighted processing value and the second weighted processing value, wherein the social effective information comprises the social effective value.
10. The method of claim 9, wherein the socially valid information satisfies a predetermined condition, comprising:
the social effective value is larger than a preset threshold value, and the preset condition comprises the preset threshold value.
11. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method as claimed in any one of claims 1 to 10.
12. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 10.
13. A computer program product, comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637979.XA CN114265989A (en) | 2021-12-29 | 2021-12-29 | Friend recommendation method, electronic device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637979.XA CN114265989A (en) | 2021-12-29 | 2021-12-29 | Friend recommendation method, electronic device and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114265989A true CN114265989A (en) | 2022-04-01 |
Family
ID=80831263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111637979.XA Pending CN114265989A (en) | 2021-12-29 | 2021-12-29 | Friend recommendation method, electronic device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114265989A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116662654A (en) * | 2023-05-26 | 2023-08-29 | 惠州市西子湖畔网络有限公司 | Big data-based affinity matching system and method |
-
2021
- 2021-12-29 CN CN202111637979.XA patent/CN114265989A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116662654A (en) * | 2023-05-26 | 2023-08-29 | 惠州市西子湖畔网络有限公司 | Big data-based affinity matching system and method |
| CN116662654B (en) * | 2023-05-26 | 2024-04-09 | 惠州市西子湖畔网络有限公司 | Big data-based affinity matching system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11670415B2 (en) | Data driven analysis, modeling, and semi-supervised machine learning for qualitative and quantitative determinations | |
| US9348898B2 (en) | Recommendation system with dual collaborative filter usage matrix | |
| CN110020009B (en) | Online question and answer method, device and system | |
| US20180068028A1 (en) | Methods and systems for identifying same users across multiple social networks | |
| US20220101161A1 (en) | Probabilistic methods and systems for resolving anonymous user identities based on artificial intelligence | |
| CN111279334A (en) | Search query enhancement with contextual analysis | |
| CN107133263B (en) | POI recommendation method, device, equipment and computer readable storage medium | |
| CN109543058A (en) | For the method for detection image, electronic equipment and computer-readable medium | |
| US20200143000A1 (en) | Customized display of emotionally filtered social media content | |
| CN107908641A (en) | A kind of method and system for obtaining picture labeled data | |
| WO2014118614A1 (en) | Social rewards | |
| WO2016138349A1 (en) | Systems and methods of structuring reviews with auto-generated tags | |
| CN110781925A (en) | Software page classification method and device, electronic equipment and storage medium | |
| WO2015148420A1 (en) | User inactivity aware recommendation system | |
| Ilakkuvan et al. | Cameras for public health surveillance: a methods protocol for crowdsourced annotation of point-of-sale photographs | |
| Baumgartner et al. | A novel iOS data donation approach: Automatic processing, compliance, and reactivity in a longitudinal study | |
| CN114265989A (en) | Friend recommendation method, electronic device and computer-readable storage medium | |
| CN110489563B (en) | Method, device, equipment and computer readable storage medium for representing graph structure | |
| CN110955840B (en) | Joint optimization of notifications and pushes | |
| CN116541602A (en) | Recommendation content pushing method and system, electronic equipment and storage medium | |
| CN110796453A (en) | E-commerce club member grade processing method and device | |
| CN107256251B (en) | Application software searching method and device and server | |
| CN110942033B (en) | Method, device, electronic equipment and computer medium for pushing information | |
| CN114265948A (en) | Image pushing method and device | |
| CN114550157A (en) | Bullet screen gathering identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |