Information search method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to an information search method and device, electronic equipment and storage medium, and can improve the search efficiency of a user. The method comprises: in response to a search instruction carrying a source user identity code of a source user and a target user name, obtaining behavior data of all target users and behavior data of the source user corresponding to the source user identity code; the target user corresponds to the target user name; based on the behavior data of the target user and the behavior data of the source user, determining social relationship data of the target user and the source user; the social relationship data is used to represent the degree of social association relationship between the target user and the source user; according to the social relationship data of the target user and the source user, a sorting sequence of the target user is obtained; and determining a search result of the search instruction based on the sorting sequence of the target user.

Description

Technical Field

[0001] This disclosure relates to the field of data processing, and more particularly to an information search method and apparatus, electronic device and storage medium. Background Technology

[0002] With the rapid development of internet technology, various applications now have multiple users, and therefore most support user search to facilitate user growth. Existing search methods are mostly based on username matching. However, usernames are generally short and allow for duplicate names. Therefore, when user data becomes too large, the search initiator will receive many users with the same name, making it difficult to find the target user. Clearly, existing search methods are inefficient and provide a poor user experience. Summary of the Invention

[0003] This disclosure relates to an information search method and apparatus, electronic device and storage medium that can improve the efficiency of user searches.

[0004] To achieve the above objectives, the embodiments of this disclosure adopt the following technical solutions:

[0005] Firstly, an information search method is provided, comprising: in response to a search instruction carrying a source user identification code of a source user and a target username, acquiring behavioral data of all target users and behavioral data of the source user corresponding to the source user identification code; the target user corresponds to the target username; based on the behavioral data of the target user and the behavioral data of the source user, determining social relationship data between the target user and the source user; the social relationship data is used to characterize the degree of social association between the target user and the source user; based on the social relationship data between the target user and the source user, obtaining a ranking sequence of the target user; and determining the search results of the search instruction based on the ranking sequence of the target user.

[0006] Based on the above technical solution and a user search device capable of using user search functionality, when a source user conducts a user search, after obtaining behavioral data from multiple target users that match their search requirements, the source user can determine the social relationship data between all target users and the source user based on the target user's behavioral data and the source user's behavioral data. Furthermore, the source user can be sorted according to the social relationship data between different target users and the source user to obtain a sorted sequence of target users. Because the sorted sequence reflects the degree of social connection between different target users and the source user, and the user the source user wants to search for is likely to have a higher degree of social connection with the source user, the search results are ultimately determined based on this sorted sequence. This allows the source user to find the user they need more quickly and accurately, improving the search efficiency of the user search.

[0007] Optionally, the method further includes: acquiring behavioral data of all sample users; the behavioral data includes multiple social operations; determining sample social relationship data between any two sample users based on the behavioral data of all sample users and the preset social relationship data corresponding to each social operation; the sample social relationship data is used to characterize the degree of social association between any two sample users; training a social relationship data model using the behavioral data of all sample users as training data and the sample social relationship data as supervision information; the social relationship data model is used to obtain the social relationship data between the target user and the source user based on the behavioral data of the target user and the behavioral data of the source user.

[0008] Based on the above scheme, when training the social relationship data model, the first step is to acquire the behavioral data of all target users. Then, based on this behavioral data, the target social relationship data between different users is determined. Finally, the sum of the behavioral data of all target users is used as training data, and all target social relationship data is used as supervision information to train the social relationship data model. In this way, the resulting social relationship data model, upon receiving the social data of two users, can output the social relationship data between them. Because the entire model training uses a large number of samples, encompassing all relevant user data for user searches, this social relationship data model can be successfully applied to the filtering and ranking of all users retrieved during user searches. Since social relationship data reflects the degree of social closeness between two users, filtering and ranking all users retrieved based on this weight can make the final search results more accurate and efficient, thereby improving the user experience of the search function.

[0009] Optionally, in response to a search command carrying a source user identification code and a target username, before acquiring the behavior data of all target users and the behavior data of the source user corresponding to the source user identification code, the method further includes: acquiring the behavior data of at least one optional user in real time; the at least one optional user includes both 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.

[0010] Optionally, the behavioral data of at least one selectable user is stored in at least one memory according to a preset rule, including: dividing the behavioral data of at least one selectable user into multiple groups according to the user identification code of the selectable user; and storing the behavioral data of different groups of selectable users in different memories.

[0011] Optionally, the behavioral data of at least one optional user is divided into multiple groups based on the user identification code of the optional user, including: calculating the modulus of the user identification code of the optional user with respect to the target number; the target number is the number of at least one memory; and grouping the behavioral data of optional users whose corresponding user identification codes have the same modulus of the target number into one group.

[0012] Optionally, obtaining the behavioral data of all target users and the behavioral data of the source users corresponding to the source user identification codes includes: using the target index to obtain the first associated user identification code and the second associated user identification code corresponding to the target username; identifying the user corresponding to the user identification code that is both the first associated user identification code and the second associated user identification code as the target user; and obtaining the behavioral data of all target users and the behavioral data of the source users corresponding to the source user identification codes.

[0013] Secondly, an information search device is provided, comprising: an acquisition module, a processing module, a sorting module, and a determination module. The acquisition module is configured to, in response to a search instruction carrying a source user identification code of a source user and a target username, acquire behavioral data of all target users and behavioral data of the source user corresponding to the source user identification code; the target user corresponds to the target username; the processing module is configured to, based on the behavioral data of the target users and the behavioral data of the source users acquired by the acquisition module, determine social relationship data between the target users and the source users; the social relationship data is used to characterize the degree of social association between the target users and the source users; the sorting module is configured to, based on the social relationship data between the target users and the source users obtained by the processing module, obtain a sorted sequence of target users; the determination module is configured to, based on the sorted sequence obtained by the sorting module, determine the search results of the search instruction.

[0014] Optionally, the device further includes a training module; the training module is specifically configured to: acquire behavioral data of all sample users; the behavioral data includes multiple social operations; determine sample social relationship data between any two sample users based on the behavioral data of all sample users and the preset social relationship data corresponding to each social operation; the sample social relationship data is used to characterize the degree of social association between any two sample users; train a social relationship data model using the behavioral data of all sample users as training data and the sample social relationship data as supervision information; the social relationship data model is used to obtain the social relationship data between the target user and the source user based on the behavioral data of the target user and the behavioral data of the source user.

[0015] Optionally, before acquiring the behavior data of all target users and the behavior data of the source user with the corresponding source user identification code, the acquisition module is further configured to: acquire the behavior data of at least one optional user in real time; the at least one optional user includes both the source user and the target user; and store the behavior data of at least one optional user in at least one memory according to preset rules.

[0016] Optionally, the acquisition module is specifically configured to: divide the behavioral data of at least one optional user into multiple groups based on the user identification code of the optional user; and store the behavioral data of different groups of optional users in different memories.

[0017] Optionally, the acquisition module is specifically configured to: calculate the modulus of the user identification code of the selectable users to the target number; the target number is the number of at least one memory; and group the behavior data of selectable users whose corresponding user identification codes have the same modulus to the target number into one group.

[0018] Optionally, the acquisition module is specifically configured to: use the target index to acquire the first associated user identity code that is associated with the source user identity code and the second associated user identity code corresponding to the target username; identify the user whose identity code is both the first associated user identity code and the second associated user identity code as the target user; and acquire the behavior data of all target users and the behavior data of the source user corresponding to the source user identity code.

[0019] Thirdly, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the information search method provided in the first aspect.

[0020] Fourthly, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the information retrieval method provided in the first aspect.

[0021] Fifthly, a computer program product is provided, comprising instructions that, when executed on an electronic device, cause the electronic device to perform the information search method provided in the first aspect.

[0022] Understandably, the solutions provided in aspects two through five above are all used to implement the corresponding methods provided in aspect one above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0023] It should be understood that, in this application, the names of the aforementioned information search devices and electronic devices do not constitute a limitation on the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those of this invention, they fall within the scope of the claims of this disclosure and their equivalents. Furthermore, it should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit this disclosure. Attached Figure Description

[0024] Figure 1 A schematic diagram of an implementation environment provided for an embodiment of this disclosure;

[0025] Figure 2 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 1 ;

[0026] Figure 3 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 2 ;

[0027] Figure 4 A supplementary flowchart for an information search method provided in this disclosure embodiment. Figure 1 ;

[0028] Figure 5 A supplementary flowchart for an information search method provided in this disclosure embodiment. Figure 2 ;

[0029] Figure 6 Supplementary flowchart of an information search method provided in this disclosure embodiment Figure 3 ;

[0030] Figure 7 Supplementary flowchart of an information search method provided in this disclosure embodiment Figure 4 ;

[0031] Figure 8 This disclosure provides a schematic diagram of a social scenario.

[0032] Figure 9 Supplementary flowchart of an information search method provided in this disclosure embodiment Figure 5 ;

[0033] Figure 10 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 3 ;

[0034] Figure 11 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 4 ;

[0035] Figure 12 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 5 ;

[0036] Figure 13 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 6 ;

[0037] Figure 14 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 7 ;

[0038] Figure 15 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 8 ;

[0039] Figure 16 A flowchart illustrating an information search method provided in this embodiment of the disclosure. Figure 9 ;

[0040] Figure 17 This is a schematic diagram of the structure of an information search device provided in an embodiment of the present disclosure;

[0041] Figure 18 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0042] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0043] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0044] Furthermore, in the description of the embodiments of this disclosure, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; the "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, in the description of the embodiments of this disclosure, "multiple" refers to two or more.

[0045] The data disclosed herein may be data authorized by the user or fully authorized by all parties.

[0046] First, let's introduce the technical terms used in this disclosure:

[0047] Zombie users: Users controlled by hackers, who typically profit by buying and selling followers and boosting engagement through these users.

[0048] Web crawler user: A user used to impersonate another user when using a web crawler to obtain user data.

[0049] Inactive users: Users who have not logged in for a long time.

[0050] First, the application scenarios of the technical solutions provided in this disclosure will be introduced:

[0051] Please refer to Figure 1 This is a schematic diagram of an implementation environment provided by an embodiment of the present disclosure. The implementation environment may include a client 01 and a server 02, with the client 01 communicating with the server 02 via wired or wireless communication.

[0052] For example, the client 01 in this embodiment can be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, as well as cellular phone, personal digital assistant (PDA), augmented reality (AR) / virtual reality (VR) device, etc., which can install and use certain applications (such as Kuaishou). This application embodiment does not impose special limitations on the specific form of the client. It can interact with the user through one or more methods such as keyboard, touchpad, touch screen, remote control, voice interaction, or handwriting device.

[0053] For example, server 02 in this disclosure can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center; this disclosure does not limit this. In this disclosure, server 02 can include multiple application service platforms, each uniquely corresponding to one application. This application is installed on client 01 and can display user search results (generally multiple users arranged in a list) on client 01's content display interface. Server 02 is mainly used to store relevant data of the applications installed on client 01, and can send corresponding data to the client when it receives a search command from client 01. Server 02 can be connected to at least one client 01; this disclosure does not specifically limit the number or type of client 01.

[0054] As described in the background section, most clients currently request relevant data from servers that store user data when they receive a user's query command. However, since most searches are currently conducted using usernames, and usernames can be repeated, the user's target user is often not ranked at the top of the search results, resulting in a poor user experience.

[0055] To address the aforementioned problems, this disclosure provides an information search method that improves user search efficiency and enhances user experience. The specific entity executing this method is an information search device, which can... Figure 1 The server or client shown. When the executing entity is a client, the client itself should have the performance of a server or be a server itself.

[0056] Reference Figure 2 The diagram shown is a flowchart illustrating an information search method provided in an embodiment of this disclosure. This method is executed by an information search device, which may be an electronic device or a part thereof. Figure 1 The client or server shown may employ an information retrieval method that includes 201-204:

[0057] 201. In response to a search instruction carrying a source user identification code and a target username, obtain behavioral data of all target users and behavioral data of the source user corresponding to the source user identification code.

[0058] The target user corresponds to the target username. For example, behavioral data includes at least one or more of the following social operations: liking, commenting, video viewing, following, historical information points (POIs), searching, and sharing.

[0059] Specifically, the behavioral data of all target users and the behavioral data of the source users corresponding to the source user identification codes can be stored on the device where the information search device is located (e.g., a server), or on a device that can communicate with the information search device. This application does not impose any specific restrictions on this. When the data to be obtained in step 201 is stored on a remote device where the information search device is located, it can be obtained from its own memory, which can reduce latency. When the data to be obtained in step 201 is stored on a remote device that can communicate with the device where the information search device is located, the information search device needs to send a relevant data acquisition request to the remote device to obtain the data, so that the remote device can send the data to the information search device. In this way, the storage resource requirements of the information search device itself can be reduced.

[0060] 202. Based on the behavioral data of the target user and the behavioral data of the source user, determine the social relationship data between the target user and the source user.

[0061] Social relationship data is used to characterize the degree of social connection between the target user and the source user (i.e., the closeness of their social relationship); the higher the social relationship data between the target user and the source user, the more likely the target user is the user the source user is looking for. For example, this social relationship data can be a social relationship weight.

[0062] 203. Based on the social relationship data between the target users and the source users, obtain the ranking sequence of the target users.

[0063] For example, using social relationship data as social relationship weights, and considering four target users A, B, C, and D, with social relationship weights between these four target users and the source user being 2, 5, 10, and 8 respectively, the sorting sequence could be C, D, B, A, arranged in descending order of social relationship weights. Of course, in practice, any other feasible method can be used, as long as the social relationship weight between the target user ranked higher and the source user in the sorting sequence is greater than that between the target users ranked lower.

[0064] 204. Determine the search results for the search command based on the target user's sorting sequence.

[0065] For example, the search results can be a sorted sequence of target users, a portion of the sorted sequence that ranks at the top of a preset percentage, or any other feasible method, as long as the social relationship data between the target users and the source users in the search results ranks at the top of the preset percentage of all target users, thereby enabling the source users to quickly find the target users they need.

[0066] Based on the above technical solution and a user search device capable of using user search functionality, when a source user conducts a user search, after obtaining behavioral data from multiple target users that match their search requirements, the source user can determine the social relationship data between all target users and the source user based on the target user's behavioral data and the source user's behavioral data. Furthermore, the source user can be sorted according to the social relationship data between different target users and the source user to obtain a sorted sequence of target users. Because the sorted sequence reflects the degree of social connection between different target users and the source user, and the user the source user wants to search for is likely to have a higher degree of social connection with the source user, the search results are ultimately determined based on this sorted sequence. This allows the source user to find the user they need more quickly and accurately, improving the search efficiency of the user search.

[0067] In one feasible approach, combining Figure 2 , refer to Figure 3 As shown, step 202 can be specifically described as follows:

[0068] 202. Input the behavioral data of the target user and the behavioral data of the source user into the social relationship data model to obtain the social relationship data of the target user and the source user.

[0069] Among them, the social relationship data model can obtain the social relationship data between any two users (e.g., the target user and the source user) based on the behavioral data of any two users (e.g., the behavioral data of the target user and the behavioral data of the source user).

[0070] In this way, pre-trained social relationship data models can be used to quickly obtain social relationship data between target users and source users, thereby improving the efficiency of information retrieval.

[0071] Further, optionally, to obtain the aforementioned social relationship data model, refer to Figure 4 As shown, the method also includes S1-S3:

[0072] S1. Obtain behavioral data from all sample users.

[0073] In this disclosure, all sample users can be all users of a certain application, or all users that can be associated with a certain application.

[0074] S2. Based on the behavioral data of all sample users and the preset social relationship data corresponding to each social operation, determine the sample social relationship data between any two sample users.

[0075] Among them, the sample social relationship data is used to characterize the degree of social connection between any two sample users.

[0076] S3. Using the behavioral data of all sample users as training data and the social relationship data of all samples as supervision information, a social relationship data model is trained.

[0077] Among them, the social relationship data model can obtain the social relationship data of any two users based on their behavioral data.

[0078] In addition, because the training data in practice can be very large, possibly reaching hundreds of millions, the training data will be divided into multiple subsets to train multiple social relationship data models, taking into account the performance and cost of the social relationship data model building device itself. When used later, the social relationship data can be calculated by each social relationship data model and then the average value can be taken or other feasible processing methods can be used.

[0079] Based on the above technical solution, when training the social relationship data model, the first step is to acquire the behavioral data of all target users. Then, based on this behavioral data, the target social relationship data between different users is determined. Finally, the sum of the behavioral data of all target users is used as training data, and all target social relationship data is used as supervision information to train the social relationship data model. In this way, the resulting social relationship data model, upon receiving social data from two users, can output the social relationship data between them. Because the entire model training uses a large number of samples, encompassing all relevant user data for user searches, this social relationship data model can be successfully applied to the filtering and ranking of all users retrieved during user searches. Since social relationship data reflects the degree of social closeness between two users, filtering and ranking all users retrieved based on this weight makes the final search results more accurate and efficient, thereby improving the user experience of the search function.

[0080] Optional, because in reality some users are not normal users and cannot provide beneficial results for training social relationship data models, therefore combining... Figure 4 , refer to Figure 5 As shown, the method includes S1A before step S2:

[0081] S1A. Identify users in the sample who meet the preset conditions as specific users and delete the behavioral data of the specific users.

[0082] For example, the preset conditions include any one or more of the following: number of followers greater than or equal to 100,000; behavioral data volume less than a preset threshold (inactive user); difference between two login times greater than a preset duration (inactive user); frequency of login device changes greater than a preset value (zombie user or crawler user); behavioral data within a preset time period greater than a preset threshold (zombie user or crawler user); and simultaneous viewing of multiple videos at a specific time (crawler user). Alternatively, in practice, specific users can also be determined and anomaly tags added using other methods before implementing the technical solution provided in this disclosure. In this case, if this disclosure needs to determine specific users, it can be based solely on whether sample users have anomaly tags. In this disclosure, specific users are generally users with more than or equal to 100,000 followers, zombie users, crawler users, inactive users, etc. Among them, zombie users and crawler users are not real users and cannot generate real user data, so this disclosure needs to clean the relevant data of these users; while inactive users, because of their small data volume, also have difficulty establishing effective social relationships, so they also need to be cleaned and filtered.

[0083] In this way, the behavioral data of target users, after being cleaned through the S1A step, can better provide data support for the training of social relationship data models.

[0084] In one feasible way, combining Figure 4 , refer to Figure 6 As shown, step S2 can be: based on the behavioral data of all sample users and the preset social relationship data corresponding to each social operation, use the PageRank algorithm to determine the sample social relationship data between any two sample users.

[0085] The preset social relationship data for each social operation is determined according to actual needs. For example, the preset social relationship data for a "like" can be 1, for a "follow" can be 2, and for a "share" can be 3, etc. This disclosure does not impose specific restrictions on this.

[0086] Further optional, combined Figure 6 , refer to Figure 7 As shown, taking social relationship data as the social relationship weight as an example, step S2 can specifically include S21-S23:

[0087] S21. Determine the initial social relationship weight between any two sample users based on the behavioral data of any two sample users and the preset social relationship weight corresponding to each social operation.

[0088] Specifically, if there is absolutely no behavioral data linking two sample users, the initial social relationship weight between them can be set to 0.

[0089] S22. Based on the initial user weights of the sample users and the initial social relationship weights between any two sample users, the initial user weights of all sample users are iteratively updated according to the first preset formula. After all the initial user weights of all sample users are iteratively updated, the initial social relationship weights between any two sample users are iteratively updated according to the second preset formula.

[0090] For example, the first preset formula can be:

[0091]

[0092] Where PR(i) n Let represent the initial user weights updated for the i-th sample user in the nth iteration. Node i represents the i-th sample user, node j represents the j-th sample user, and all neighboring nodes of node i refer to sample users whose unupdated initial social relationship weights are not 0 (including the i-th sample user itself). Similarly, all neighboring nodes of node j refer to sample users whose unupdated initial social relationship weights are not 0 (including the j-th sample user itself). The initial social relationship weights between the i-th and j-th sample users are updated in the (n-1)-th iteration. Let PR(j) be the initial social relationship weight updated in the (n-1)th iteration between the j-th sample user and the k-th sample user. n-1 The initial user weights are updated for the i-th sample user in the (n-1)th iteration.

[0093] For example, the second preset formula can be:

[0094]

[0095] in, Let PR(i) be the initial social relationship weight updated in the nth iteration between the i-th and j-th sample users. n The initial user weights are updated for the j-th sample user in the nth iteration.

[0096] For example, refer to Figure 8 As shown, taking four users a, b, c, and d, where b and c have a social relationship, b and a have a social relationship, c and a have a social relationship, and d has a social relationship with the other three, and taking the updating of user weight of a and social relationship weight between a and b as an example, the above first preset formula can be:

[0097]

[0098] The second preset formula mentioned above can be:

[0099]

[0100] The meanings of each item can be found in the relevant descriptions in the aforementioned formulas, and will not be repeated here.

[0101] Of course, in practice, one could first use a variation of the second preset formula to update the initial social relationship weights, and then, after all the initial social relationship weights between any two sample users have been iterated and updated, use a variation of the first preset formula to update the initial user weights for each sample user.

[0102] This disclosure does not impose specific limitations on this. For example, a variation of the second preset formula can be:

[0103]

[0104] The first preset formula can be transformed as follows:

[0105]

[0106] The meanings of each item can be found in the relevant descriptions in the aforementioned formulas, and will not be repeated here.

[0107] S23. If the number of iterations for updating the initial social relationship weight between any two sample users is greater than or equal to the preset number, or if the initial social relationship weight between any two sample users converges during the iterative update process, stop updating the initial social relationship weight between any two sample users, and determine the initial social relationship weight between any two sample users obtained in the latest iterative update as the sample social relationship weight.

[0108] In this way, the sample social relationship weights between different sample users can be obtained smoothly, providing data support for the training of subsequent social relationship data models.

[0109] It should be noted that although the PageRank algorithm can calculate the social relationship data between any two users, it relies on a specific formula and needs to be recalculated each time, which is computationally intensive and not accurate enough. Therefore, this disclosure only uses the algorithm to calculate the supervision information to be used in subsequent model training.

[0110] Optionally, to improve the accuracy of the social relationship data model in calculating the social relationship data between any two users, combined with Figure 4 , refer to Figure 9 As shown, step S1 is followed by step S1B:

[0111] S1B, Obtain the filtering characteristics of sample users; the filtering characteristics shall include at least one or more of the following: city, gender, age.

[0112] At this point, S3 can specifically be: using the behavioral data and screening features of all sample users as training data, and the social relationship data of all samples as supervision information, to train a social relationship data model.

[0113] In this way, because the training process considers not only the social actions of each sample user, but also the characteristics of each sample user, and when the source user searches for a user, they will also likely consider the characteristics of the user they are searching for (e.g., searching for users of a certain gender or city), the social relationship data model trained by combining the characteristics of each sample user can more accurately reflect the user's search intentions, and the calculated social relationship data will be more accurate.

[0114] Optionally, because user searches are frequent and require low latency, to ensure that the behavioral data of both the source and target users can be quickly retrieved during a search, combined with... Figure 2 , refer to Figure 10 As shown, step 201 includes X1 and X2:

[0115] X1. Acquire behavioral data of at least one selectable user in real time; the at least one selectable user includes the source user and the target user.

[0116] X2. Store the behavioral data of at least one selectable user in at least one memory according to preset rules.

[0117] Specifically, since the storage space of a single memory is very limited, Redis can be used to build a cluster from the memory of multiple servers to store the behavioral data of at least one optional user.

[0118] This ensures timely access to the behavioral data of source users and pending users, improving the efficiency of user searches.

[0119] In one feasible way, combining Figure 10 , refer to Figure 11 As shown, X2 can specifically include X21 and X22:

[0120] X21. Divide the behavioral data of at least one optional user into multiple groups based on the user identification code of the optional user.

[0121] For example, assuming the amount of memory is the target number, the modulus of the user identification code of the selectable users with respect to the target number can be calculated. Then, the behavior data of the selectable users whose user identification codes have the same modulus of the target number are identified as the same group. For example, taking at least one cache as memory 0, memory 1, and memory 2, and the user identification codes corresponding to the 9 selectable users as 1, 2, 3, 4, 5, 6, 7, 8, and 9, the modulus of the user identification codes of the 9 selectable users with respect to the target number are 1, 2, 0, 1, 2, 0, 1, 2, 0. According to the rule in S212, the behavior data of the selectable users whose user identification codes have a modulus of 1 with respect to the target number can be identified as the same group and stored in memory 0; the behavior data of the selectable users whose user identification codes have a modulus of 2 with respect to the target number can be identified as the same user data group and stored in memory 1; and the behavior data of the selectable users whose user identification codes have a modulus of 0 with respect to the target number can be identified as the same user data group and stored in memory 2. This allows for quick grouping of the behavioral data of selectable users, facilitating subsequent use. Of course, other storage methods can also be used in practice, as long as each memory location corresponds to a group of behavioral data for one selectable user.

[0122] X22. Store the behavioral data of different groups of selectable users in different memory locations.

[0123] This allows for efficient storage of selectable user behavior data in memory, facilitating easy access.

[0124] Optional, combined Figure 11 , refer to Figure 12 As shown, step 201 may specifically include 2011-2013:

[0125] 2011. In response to a search instruction carrying a source user identification code and a target username, the system uses the target index to obtain a first associated user identification code that is associated with the source user identification code and a second associated user identification code corresponding to the target username.

[0126] It should be noted that, because sometimes when a source user searches for a user, the target username entered may not be the actual username needed, but rather a username that is similar to the actual username (for example, the needed username is "I am @who", and the entered target username is "who am I"). Therefore, in order to search for all possible target users, this disclosure can perform word segmentation and fuzzy processing on the target username to obtain multiple different fields when obtaining the second associated user identification code based on the target username (for example, dividing "Wild Red Dead Redemption" into "Wild", "Red Dead Redemption", and "Wild Red Dead Redemption"). Then, the user identification codes corresponding to all usernames containing these fields are deduplicated and used as the aforementioned second associated user identification code.

[0127] 2012. The user whose identity code is both the first associated user identity code and the second associated user identity code is identified as the target user.

[0128] 2013. Obtain behavioral data of all target users and behavioral data of source users with corresponding source user identification codes.

[0129] This allows us to combine the target username and the source user's identification code to obtain a smaller and more accurate set of users, which can then be used as a set of pending users in the subsequent user search process. This reduces the computational load of user search and improves the accuracy of user search.

[0130] Further optional, combined Figure 12 , refer to Figure 13 As shown, step 202 may specifically include 2021-2022:

[0131] 2021. Utilize the target index to obtain the user weights of all target users.

[0132] 2022. Input the behavioral data of the first target user and the source user, which are ranked first by the user weight and are the first preset percentage, into the social relationship data model to obtain the social relationship weight between the first target user and the source user.

[0133] It should be noted that, referring to the related explanations following step S3 above, since multiple social relationship data models may exist in practice, step 2022 can input the behavioral data of the first target user and the behavioral data of the source user into each social relationship data model to obtain multiple social relationship data between the first target user and the source user. Then, the average value is calculated as the final social relationship data between the first target user and the source user. The subsequent step 20222 follows the same principle. Of course, besides calculating the average value, any feasible method can be used; this disclosure does not impose specific restrictions.

[0134] This way, data retrieval is faster due to the use of the target index, which can further reduce the amount of computation required for user searches.

[0135] Further optional, combined Figure 13 , refer to Figure 14 As shown, the 2022 steps may include 20221-20222:

[0136] 20221. Use the target index to obtain the feature data of the source user and the filtering features of the first target user.

[0137] For example, the filtering features may include at least one or more of the following: city, gender, and age.

[0138] 20222. Input the behavioral data of the second target user (whose filtering features are more similar to those of the source user than a preset threshold) and the behavioral data of the source user into the social relationship data model to obtain the social relationship data between the second target user and the source user.

[0139] The similarity can be determined based on the specific circumstances. For example, suppose the second target user A is from city A, male, and 15 years old; the source user is from city A, female, and 15 years old, then the similarity of their screening features is 2 / 3.

[0140] This allows for faster data retrieval due to the use of target indexes, further reducing the amount of data that the social relationship data model needs to process and decreasing the computational load for user searches.

[0141] Optionally, to obtain the aforementioned target index, taking social relationship data as the social relationship weight as an example, combined with... Figure 2 , refer to Figure 15 As shown, steps 201 and 204 are preceded by L1-L4:

[0142] L1. Obtain the username, user identity, behavioral data, and filtering features of at least one selectable user; the at least one selectable user includes the source user and the target user.

[0143] Behavioral data includes at least one social interaction.

[0144] L2. Based on the behavioral data of the optional users, determine the association between the user identity identifiers of at least one optional user.

[0145] Specifically, if the behavioral data of one optional user contains relevant data of another optional user, then the user identities of the two optional users can be considered to be related.

[0146] L3. Based on the behavioral data of the selectable users and the preset social weights corresponding to each social operation, the PageRank algorithm is used to determine the user weights of the selectable users.

[0147] For details on how to calculate the user weights of selectable users, please refer to the relevant descriptions in steps S22 and S23 above. The difference is that in step S23, the initial user weights of selectable users obtained from the latest iteration update need to be determined as the target user weights of selectable users.

[0148] L4. Based on the usernames, user identifiers, and filter data of the selectable users, as well as the association between the user identifiers of at least one selectable user, establish a target index.

[0149] This allows user data such as usernames, user identifiers, and filter data to be retrieved and used more quickly, improving the efficiency of the entire user search process.

[0150] Optionally, when the social relationship data model is... Figure 9 When the corresponding implementation example is trained, combined with Figure 3 , refer to Figure 16 As shown, steps 201 and 202 can be specifically described as follows:

[0151] 201. In response to a search command carrying the source user's identity code and the target username, obtain the behavioral data and filtering features of all target users, as well as the behavioral data and filtering features of the source user corresponding to the source user's identity code.

[0152] 202. Input the behavioral data and filtering features of the target users and the behavioral data and filtering features of the source users into the social relationship data model to obtain the social relationship data between the target users and the source users.

[0153] In this way, social relationship data models trained with more data can be used to obtain social relationship data between different users. Although more data needs to be acquired, the calculation results of social relationship weights will be more accurate, thus ensuring the accuracy of user searches.

[0154] The above embodiments primarily describe the solutions provided by the embodiments of this disclosure from the perspective of an information search device (electronic device (client / server)). It is understood that, in order to implement the above methods, the information search device includes hardware structures and / or software modules corresponding to the execution of each method flow, and these hardware structures and / or software modules corresponding to the execution of each method flow can constitute an information search device. Those skilled in the art should readily recognize that, in conjunction with the algorithm steps of the various examples described in the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0155] This disclosure embodiment can divide the information search device into functional modules according to the above method example. For example, the information search device can be divided into functional modules corresponding to each function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0156] When dividing each function into modules according to its corresponding function. Figure 17 This diagram illustrates a possible structure of an information search device 03 used in an electronic device, which can be... Figure 1 The client or server described herein, the information search device 03 includes: an acquisition module 41, a processing module 42, a sorting module 43, and a determination module 44.

[0157] Specifically, the acquisition module 41 is configured to, in response to a search instruction carrying a source user identification code and a target username, acquire behavioral data of all target users and behavioral data of the source user corresponding to the source user identification code; the target user corresponds to the target username; the processing module 42 is configured to, based on the behavioral data of the target users and the behavioral data of the source users acquired by the acquisition module 41, determine the social relationship data between the target users and the source users; the social relationship data is used to characterize the degree of social association between the target users and the source users; the sorting module 43 is configured to, based on the social relationship data between the target users and the source users obtained by the processing module 42, obtain a sorted sequence of target users; and the determination module 44 is configured to, based on the sorted sequence obtained by the sorting module 43, determine the search results of the search instruction.

[0158] Optionally, the device further includes a training module 45; the training module 45 is specifically configured to: acquire behavioral data of all sample users; the behavioral data includes multiple social operations; determine sample social relationship data between any two sample users based on the behavioral data of all sample users and the preset social relationship data corresponding to each social operation; the sample social relationship data is used to characterize the degree of social association between any two sample users; train a social relationship data model using the behavioral data of all sample users as training data and the sample social relationship data as supervision information; the social relationship data model is used to obtain the social relationship data between the target user and the source user based on the behavioral data of the target user and the behavioral data of the source user.

[0159] Further optionally, the processing module 42 can be specifically used to: input the target user's behavior data and the source user's behavior data obtained by the acquisition module 41 into the social relationship data model to obtain the social relationship data of the target user and the source user; the social relationship data model is used to represent the correspondence between the behavior data of two different users and the social relationship data between them.

[0160] Optionally, before acquiring the behavior data of all target users and the behavior data of the source user with the corresponding source user identification code, the acquisition module 41 is further configured to: acquire the behavior data of at least one optional user in real time; the at least one optional user includes the source user and the target user; and store the behavior data of at least one optional user in at least one memory according to preset rules.

[0161] Optionally, the acquisition module 41 is specifically configured to: divide the behavioral data of at least one optional user into multiple groups based on the user identification code of the optional user; and store the behavioral data of different groups of optional users in different memories.

[0162] Optionally, the acquisition module 41 is specifically configured to: calculate the modulus of the user identification code of the selectable user to the target number; the target number is the number of at least one memory; and group the behavior data of selectable users whose corresponding user identification codes have the same modulus of the target number into one group.

[0163] Optionally, the acquisition module 41 is specifically configured to: use the target index to acquire the first associated user identity code that is associated with the source user identity code and the second associated user identity code corresponding to the target username; identify the user whose identity code is both the first associated user identity code and the second associated user identity code as the target user; and acquire the behavior data of all target users and the behavior data of the source user corresponding to the source user identity code.

[0164] Regarding the information search device in the above embodiments, the specific way in which each module performs its operation has been described in detail in the aforementioned embodiments of the information search method, and will not be elaborated here.

[0165] Figure 18 This is a schematic diagram illustrating a possible structure of an electronic device according to an exemplary embodiment, which may be the information search device 03 described above. For example... Figure 18 As shown, the electronic device includes a processor 51 and a memory 52. ​​The memory 52 stores instructions executable by the processor 51, which in turn implements the functions of the various modules in the information search device 03 described in the above embodiments. The memory 52 stores at least one instruction, which is loaded and executed by the processor 51 to implement the information search method provided in the above method embodiments.

[0166] In a specific implementation, as one embodiment, processors 51 (51-1 and 51-2) may include one or more CPUs, for example... Figure 18 CPU0 and CPU1 are shown in the diagram. As one embodiment, the electronic device may include multiple processors 51, such as... Figure 18 The processors 51-1 and 51-2 are shown in the diagram. Each CPU in these processors 51 can be a single-core processor or a multi-core processor. Here, processor 51 can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0167] The memory 52 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), disk computer-readable storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 52 may exist independently and be connected to the processor 51 via bus 53. The memory 52 may also be integrated with the processor 51.

[0168] Bus 53 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. This bus 53 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 18 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0169] In addition, to facilitate information interaction between the electronic device and other devices (e.g., information interaction between the electronic device as a client and a server, or information interaction between the electronic device as a server and a client), the electronic device includes a communication interface 54. The communication interface 54 uses any transceiver-like device for communication with other devices or communication networks, such as control systems, radio access networks (RAN), wireless local area networks (WLAN), etc. The communication interface 54 may include a receiving unit to implement receiving functions and a transmitting unit to implement transmitting functions.

[0170] In some embodiments, when the electronic device is a client, it may optionally include: a peripheral device interface 55 and at least one peripheral device. The processor 51, memory 52, and peripheral device interface 55 can be connected via a bus 53 or signal lines. Each peripheral device can be connected to the peripheral device interface 55 via the bus 53, signal lines, or a circuit board. Specifically, the peripheral device includes at least one of: a radio frequency circuit 56, a display screen 57, a camera 58, an audio circuit 59, a positioning component 60, and a power supply 61.

[0171] The peripheral device interface 55 can be used to connect at least one I / O (input / output) related peripheral device to the processor 51 and the memory 52. ​​In some embodiments, the processor 51, the memory 52, and the peripheral device interface 55 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 51, the memory 52, and the peripheral device interface 55 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0172] The radio frequency (RF) circuit 56 is used to receive and transmit RF (radio frequency) signals, also known as electromagnetic signals. The RF circuit 56 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 56 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 404 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 56 can communicate with other devices via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: metropolitan area networks (MANs), various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks (WLANs), and / or Wi-Fi (wireless fidelity) networks. In some embodiments, the RF circuit 56 may also include circuitry related to NFC (near field communication), which is not limited in this disclosure.

[0173] Display screen 57 is used to display a user interface (UI). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 57 is a display, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 51 for processing. In this case, display screen 57 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, display screen 57 can be a single unit, serving as the front panel of an electronic device; display screen 57 can be made of materials such as LCD (liquid crystal display) or OLED (organic light-emitting diode).

[0174] Camera assembly 58 is used to acquire images or videos. Optionally, camera assembly 58 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the electronic device, and the rear-facing camera is located on the back of the electronic device. Audio circuitry 59 may include a microphone and a speaker. The microphone is used to acquire sound waves from the user and the environment, and convert the sound waves into electrical signals that are input to processor 51 for processing, or input to radio frequency circuitry 56 for voice communication. For stereo acquisition or noise reduction purposes, there may be multiple microphones, each located in a different part of the electronic device. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from processor 51 or radio frequency circuitry 56 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into sound waves that are audible to humans, but also into sound waves that are inaudible to humans for purposes such as distance measurement. In some embodiments, audio circuitry 59 may also include a headphone jack.

[0175] Positioning component 60 is used to locate the current geographic location of an electronic device to enable navigation or LBS (location-based service). Positioning component 60 can be a positioning component based on the US GPS (Global Positioning System), China's BeiDou system, Russia's Granas system, or the EU's Galileo system.

[0176] Power source 61 is used to supply power to various components in an electronic device. Power source 61 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power source 61 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0177] In some embodiments, the electronic device further includes one or more sensors 510. The one or more sensors 510 include, but are not limited to, accelerometers, gyroscopes, pressure sensors, fingerprint sensors, optical sensors, and proximity sensors.

[0178] An accelerometer can detect the magnitude of acceleration along the three axes of a coordinate system established by the electronic device. A gyroscope sensor can detect the orientation and rotation angle of the electronic device; it can work in conjunction with the accelerometer to capture the user's 3D movements on the device. A pressure sensor can be located on the side bezel of the electronic device and / or beneath the display screen 77. When located on the side bezel, it can detect the user's grip on the device. A fingerprint sensor is used to capture the user's fingerprint. An optical sensor is used to capture ambient light intensity. A proximity sensor, also known as a distance sensor, is typically located on the front panel of the electronic device. It is used to detect the distance between the user and the front of the electronic device.

[0179] Those skilled in the art will understand that Figure 18 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0180] This disclosure also provides a computer-readable storage medium storing instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the information search method provided in the foregoing embodiments.

[0181] This disclosure also provides a computer program product containing instructions that, when run on an electronic device, cause the electronic device to execute the information search method provided in the foregoing embodiments.

[0182] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0183] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An information search method, characterized in that, include: Obtain behavioral data from all sample users; the behavioral data includes one or more of the following social operations: likes, comments, video views, following, historical information points, and searches; Based on the behavioral data of all the sample users and the preset social relationship data corresponding to each social operation, determine the sample social relationship data between any two sample users; The sample social relationship data is used to characterize the degree of social connection between any two sample users; Using the behavioral data of all the sample users as training data and the social relationship data of all the samples as supervision information, a social relationship data model is trained; the social relationship data model is used to obtain the social relationship data between the target user and the source user based on the behavioral data of the target user and the behavioral data of the source user. Obtain the username, user identifier, behavioral data, and filtering features of at least one selectable user; The at least one selectable user includes the source user and the target user; Based on the behavioral data of the selectable users, determine the association between the user identity identifiers of at least one selectable user; The user weight of the selectable user is determined based on the behavioral data of the selectable user and the preset social weight corresponding to each social operation; A target index is established based on the usernames, user identifiers, and filtering data of the selectable users, as well as the association between the user identifiers of at least one selectable user; In response to a search instruction carrying a source user identification code and a target username, the target index is used to obtain a first associated user identification code that is associated with the source user identification code and a second associated user identification code corresponding to the target username. The user whose identity code is both the first associated user identity code and the second associated user identity code is identified as the target user; Obtain behavioral data of all target users and behavioral data of the source users corresponding to the source user identification codes; The target user corresponds to the target username; The behavioral data of the target user and the behavioral data of the source user are input into the social relationship data model to determine the social relationship data between the target user and the source user; The social relationship data is used to characterize the degree of social connection between the target user and the source user; Based on the social relationship data between the target users and the source users, a sorted sequence of the target users is obtained; The search results for the search instruction are determined based on the sorting sequence of the target user.

2. The information search method according to claim 1, characterized in that, Before responding to a search instruction carrying the source user identification code and the target username, and obtaining the behavioral data of all target users and the behavioral data of the source user corresponding to the source user identification code, the method further includes: Real-time acquisition of behavioral data from at least one selectable user; the at least one selectable user includes the source user and the target user; The behavioral data of the at least one selectable user is stored in at least one memory according to a preset rule.

3. The information search method according to claim 2, characterized in that, The step of storing the behavioral data of the at least one selectable user in at least one memory according to a preset rule includes: The behavioral data of at least one selectable user is divided into multiple groups based on the user identification code of the selectable user; the behavioral data of different groups of selectable users are stored in different memories.

4. The information search method according to claim 3, characterized in that, The step of dividing the behavioral data of at least one selectable user into multiple groups based on the user identification code of the selectable user includes: Calculate the modulus of the user identification code of the selectable user with respect to the target number; the target number is the number of the at least one memory location; The behavioral data of selectable users whose corresponding user identification codes have the same modulus to the target number are grouped into one group.

5. The information search method according to claim 2, characterized in that, The acquisition of behavioral data of all target users and behavioral data of source users corresponding to the source user identification codes includes: Using the target index, obtain the first associated user identity code that is associated with the source user identity code and the second associated user identity code corresponding to the target username; The user whose identity code is both the first associated user identity code and the second associated user identity code is identified as the target user; Obtain the behavioral data of all target users and the behavioral data of the source users corresponding to the source user identification codes.

6. An information search device, characterized in that, include: The training module is configured to acquire behavioral data from all sample users; the behavioral data includes one or more of the following social operations: likes, comments, video views, following, historical information points, and searches; The training module is also configured to determine sample social relationship data between any two sample users based on the behavioral data of all the sample users and the preset social relationship data corresponding to each social operation. The sample social relationship data is used to characterize the degree of social connection between any two sample users; The training module is further configured to use the behavioral data of all the sample users as training data and the social relationship data of all the samples as supervision information to train a social relationship data model; the social relationship data model is used to obtain the social relationship data between the target user and the source user based on the behavioral data of the target user and the behavioral data of the source user. The acquisition module is configured to acquire the username, user identity, behavioral data, and filtering features of at least one selectable user. The at least one selectable user includes the source user and the target user; The determination module is configured to determine the association between user identifiers of at least one optional user based on the behavioral data of the optional user; The determining module is configured to determine the user weight of the selectable user based on the behavioral data of the selectable user and the preset social weight corresponding to each social operation; The processing module is configured to build a target index based on the usernames, user identifiers, and filter data of the optional users, as well as the association between the user identifiers of at least one optional user; The acquisition module is configured to, in response to a search instruction carrying a source user identification code and a target username, use the target index to acquire a first associated user identification code that is associated with the source user identification code and a second associated user identification code corresponding to the target username. The user whose identity code is both the first associated user identity code and the second associated user identity code is identified as the target user. The acquisition module is configured to acquire the behavior data of all target users and the behavior data of the source user corresponding to the source user identification code; The target user corresponds to the target username; The processing module is configured to input the behavioral data of the target user and the behavioral data of the source user acquired by the acquisition module into the social relationship data model to determine the social relationship data between the target user and the source user; The social relationship data is used to characterize the degree of social connection between the target user and the source user; The sorting module is configured to obtain a sorting sequence of the target users based on the social relationship data between the target users and the source users obtained by the processing module; The determining module is configured to determine the search results of the search instruction based on the sorting sequence obtained by the sorting module.

7. The information search device according to claim 6, characterized in that, Before acquiring the behavior data of all target users and the behavior data of the source user corresponding to the source user's identity code, the acquisition module is further configured to: Real-time acquisition of behavioral data from at least one selectable user; the at least one selectable user includes the source user and the target user; The behavioral data of the at least one selectable user is stored in at least one memory according to a preset rule.

8. The information search device according to claim 7, characterized in that, The acquisition module is specifically configured as follows: The behavioral data of at least one selectable user is divided into multiple groups based on the user identification code of the selectable user; the behavioral data of different groups of selectable users are stored in different memories.

9. The information search device according to claim 8, characterized in that, The acquisition module is specifically configured as follows: Calculate the modulus of the user identification code of the selectable user with respect to the target number; the target number is the number of the at least one memory location; The behavioral data of selectable users whose corresponding user identification codes have the same modulus to the target number are grouped into one group.

10. The information search device according to claim 8, characterized in that, The acquisition module is specifically configured as follows: Using the target index, obtain the first associated user identity code that is associated with the source user identity code and the second associated user identity code corresponding to the target username; The user whose identity code is both the first associated user identity code and the second associated user identity code is identified as the target user; Obtain the behavioral data of all target users and the behavioral data of the source users corresponding to the source user identification codes.

11. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the information search method as described in any one of claims 1-5.

12. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the information search method as described in any one of claims 1-5.

Images