Search

CN-115329184-B - Information searching method and device, electronic equipment and storage medium

CN115329184BCN 115329184 BCN115329184 BCN 115329184BCN-115329184-B

Abstract

The disclosure relates to an information searching method and device, electronic equipment and a storage medium, relates to the field of data processing, and can improve the searching efficiency of users. The method comprises the steps of responding to a search instruction carrying source user identification codes and target user names of active users, obtaining behavior data of all target users and behavior data of source users corresponding to the source user identification codes, enabling the target users to correspond to the target user names, determining social relation data of the target users and the source users based on the behavior data of the target users and the behavior data of the source users, enabling the social relation data to be used for representing the degree of social relation between the target users and the source users, obtaining a sorting sequence of the target users according to the social relation data of the target users and the source users, and determining search results of the search instruction based on the sorting sequence of the target users.

Inventors

  • LI JINQI

Assignees

  • 北京达佳互联信息技术有限公司

Dates

Publication Date
20260512
Application Date
20210510

Claims (12)

  1. 1. An information search method, comprising: the method comprises the steps of obtaining behavior data of all sample users, wherein the behavior data comprises any one or more social operations of praise, comment, video browsing, attention, historical information points and search; Determining sample social relationship data between any two sample users according to the behavior data of all the sample users and preset social relationship data corresponding to each social operation, wherein the sample social relationship data is used for representing the degree of social association relationship of the any two sample users; The social relation data model is used for obtaining social relation data of a target user and a source user based on the behavior data of the target user and the behavior data of the source user; Acquiring a user name, a user identity, behavior data and screening characteristics of at least one optional user, wherein the at least one optional user comprises the source user and the target user; determining the association relationship between the user identity of at least one optional user according to the behavior data of the optional user; Determining the user weight of the selectable user according to the behavior data of the selectable user and the preset social weight corresponding to each social operation; establishing a target index according to the user name, the user identity and screening data of the selectable user and the association relationship between the user identity of at least one selectable user; Responding to a search instruction carrying a source user identity code and a target user name of an active user, and acquiring a first associated user identity code associated with the source user identity code and a second associated user identity code corresponding to the target user name by utilizing the target index; Determining a user corresponding to the user identity code which is the first associated user identity code and the second associated user identity code as a target user; Acquiring behavior data of all target users and behavior data of source users corresponding to the source user identification codes, wherein the target users correspond to the target user names; Inputting the behavior data of the target user and the behavior data of the source user into the social relation data model, and determining social relation data of the target user and the source user, wherein the social relation data is used for representing the degree of social association relation between the target user and the source user; Obtaining a sequencing sequence of the target user according to social relation data of the target user and the source user; And determining search results of the search instruction based on the ordered sequence of the target user.
  2. 2. The information searching method according to claim 1, wherein before the step of obtaining the behavior data of all the target users and the behavior data of the source user corresponding to the source user identification code in response to the searching command carrying the source user identification code and the target user name of the source user, the method further comprises: Acquiring behavior data of at least one optional user in real time, wherein the at least one optional user comprises the source user and the target user; And storing the behavior data of the at least one optional user in at least one memory according to a preset rule.
  3. 3. The information searching method according to claim 2, wherein storing the behavior data of the at least one selectable user in at least one memory according to a preset rule includes: Dividing the behavior data of at least one optional user into a plurality of groups according to the user identification codes of the optional users, and storing the behavior data of the optional users in different groups in different memories.
  4. 4. The information searching method of claim 3, wherein the classifying the behavior data of the at least one optional user into a plurality of groups according to the user identification code of the optional user comprises: Calculating the modulus of the user identification code of the selectable user to the target number, wherein the target number is the number of the at least one memory; And classifying the behavior data of the selectable users with the same modulus of the corresponding user identification codes to the target number into a group.
  5. 5. The information searching method according to claim 2, wherein the obtaining the behavior data of all target users and the behavior data of the source user corresponding to the source user identification code includes: acquiring a first associated user identity code associated with the source user identity code and a second associated user identity code corresponding to the target user name by using a target index; Determining a user corresponding to a user identity code which is both a first associated user identity code and a second associated user identity code as a target user; and acquiring behavior data of all the target users and behavior data of the source user corresponding to the source user identification code.
  6. 6. An information search apparatus, comprising: the training module is configured to acquire behavior data of all sample users, wherein the behavior data comprises any one or more social operations of praise, comment, video browsing, attention, historical information points and search; The training module is further configured to determine sample social relationship data between any two sample users according to the behavior data of all the sample users and preset social relationship data corresponding to each social operation, wherein the sample social relationship data is used for representing the degree of social association relationship of the any two sample users; the training module is further configured to train to obtain a social relationship data model by taking the behavior data of all the sample users as training data and taking all the sample social relationship data as supervision information, wherein the social relationship data model is used for obtaining social relationship data of a target user and a source user based on the behavior data of the target user and the behavior data of the source user; the system comprises an acquisition module, a selection module and a selection module, wherein the acquisition module is configured to acquire a user name, a user identity, behavior data and screening characteristics of at least one optional user, and the at least one optional user comprises the source user and the target user; The determining module is configured to determine the association relationship between the user identity identifiers of at least one optional user according to the behavior data of the optional user; the determining module is configured to determine the user weight of the optional user according to the behavior data of the optional user and the preset social weight corresponding to each social operation; The processing module is configured to establish a target index according to the user name, the user identity and the screening data of the optional user and the association relationship among the user identity of at least one optional user; the acquisition module is configured to respond to a search instruction carrying a source user identity code and a target user name of the source user, and acquire a first associated user identity code associated with the source user identity code and a second associated user identity code corresponding to the target user name by utilizing the target index; determining a user corresponding to the user identity code which is both the first associated user identity code and the second associated user identity code as a target user The acquisition module is configured to acquire behavior data of all target users and behavior data of source users corresponding to the source user identification codes, wherein the target users correspond to the target user names; The processing module is configured to input the behavior data of the target user and the behavior data of the source user acquired by the acquisition module into the social relationship data model to determine social relationship data of the target user and the source user, wherein the social relationship data is used for representing the degree of social association relationship between the target user and the source user; the sequencing module is configured to obtain a sequencing sequence of the target user according to the social relationship data of the target user and the source user, which are obtained by the processing module; And the determining module is configured to determine the search result of the search instruction based on the ordered sequence obtained by the ordering module.
  7. 7. The information search apparatus of claim 6, wherein the acquisition module, prior to acquiring the behavior data of all target users and the behavior data of the source user corresponding to the source user identification code, is further configured to: Acquiring behavior data of at least one optional user in real time, wherein the at least one optional user comprises the source user and the target user; And storing the behavior data of the at least one optional user in at least one memory according to a preset rule.
  8. 8. The information search apparatus of claim 7, wherein the acquisition module is specifically configured to: Dividing the behavior data of at least one optional user into a plurality of groups according to the user identification codes of the optional users, and storing the behavior data of the optional users in different groups in different memories.
  9. 9. The information search apparatus of claim 8, wherein the acquisition module is specifically configured to: Calculating the modulus of the user identification code of the selectable user to the target number, wherein the target number is the number of the at least one memory; And classifying the behavior data of the selectable users with the same modulus of the corresponding user identification codes to the target number into a group.
  10. 10. The information search apparatus of claim 8, wherein the acquisition module is specifically configured to: acquiring a first associated user identity code associated with the source user identity code and a second associated user identity code corresponding to the target user name by using a target index; Determining a user corresponding to a user identity code which is both a first associated user identity code and a second associated user identity code as a target user; and acquiring behavior data of all the target users and behavior data of the source user corresponding to the source user identification code.
  11. 11. An electronic device, comprising: A processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the information search method of any of claims 1-5.
  12. 12. A computer readable storage medium having instructions stored thereon, which, when executed by a processor of an electronic device, enable the electronic device to perform the information search method of any one of claims 1-5.

Description

Information searching method and device, electronic equipment and storage medium Technical Field The embodiment of the disclosure relates to the field of data processing, in particular to an information searching method and device, electronic equipment and a storage medium. Background With the advanced internet technology, various applications currently have multiple users, so that user searching is supported for convenience. Most of the existing searching modes are matching searching based on user names, the user names are generally short, and the user names are allowed to be renamed, so that once user data are too huge, a search initiator can receive a plurality of renamed users returned by an application, and the search initiator is difficult to find a required target user. It can be seen that the existing searching method has low searching efficiency and poor user experience. Disclosure of Invention The disclosure relates to an information searching method and device, an electronic device and a storage medium, which can improve the searching efficiency of a user. In order to achieve the above purpose, the embodiments of the present disclosure adopt the following technical solutions: The information searching method includes the steps of responding to a searching command carrying source user identification codes and target user names of source users, obtaining behavior data of all target users and behavior data of the source users corresponding to the source user identification codes, enabling the target users to correspond to the target user names, determining social relation data of the target users and the source users based on the behavior data of the target users and the behavior data of the source users, enabling the social relation data to be used for representing the social relation degree of the target users and the source users, obtaining a sorting sequence of the target users according to the social relation data of the target users and the source users, and determining searching results of the searching command based on the sorting sequence of the target users. Based on the technical scheme, the user searching device capable of using the user searching function is adopted, when a source user searches, after the behavior data of a plurality of target users meeting the searching requirement are obtained, the social relationship data between all the target users and the source user can be determined based on the behavior data of the target users and the behavior data of the source user, and further the target users can be ordered according to the social relationship data between different target users and the source user to obtain an ordering sequence of the target users. The method comprises the steps of obtaining behavior data of all sample users, enabling the behavior data to comprise a plurality of social operations, determining sample social relationship data between any two sample users according to the behavior data of all sample users and preset social relationship data corresponding to each social operation, enabling the sample social relationship data to be used for representing the social association relationship degree of any two sample users, taking the behavior data of all sample users as training data, taking the behavior data of all sample users as supervision information, training to obtain a social relationship data model, and enabling the social relationship data model to be used for obtaining social relationship data of a target user and a source user based on the behavior data of the target user and the behavior data of the source user. Based on the scheme, when the social relationship data model is trained, behavior data of all target users are firstly obtained, then target social relationship data among different users are determined according to the behavior data, finally the behavior data of all target users are used as training data, and all target social relationship data are used as supervision information to train to obtain the social relationship data model. In this way, the obtained social relationship data model can output the social relationship data between the two users after receiving the social relationship data of the two users. Because the samples used in the whole model training are very many and comprise all relevant user data needed to be searched, when the social relation data model can be smoothly applied to the user searching, and in the screening and sorting of all users obtained by searching, the social relation data can reflect the social tightness degree between two users, so that all users obtained by searching are screened and sorted according to the weight, the result obtained by searching of the end user is more accurate, the searching efficiency is higher, and the user experience of the user searching function is further improved. Optionally, before the searching command carrying the source user identification code and the target user name of