WO2018145610A1

WO2018145610A1 - Data processing method, server, and storage medium

Info

Publication number: WO2018145610A1
Application number: PCT/CN2018/075251
Authority: WO
Inventors: 唐胜; 蒲昊; 杨志伟; 梁汉熙; 刘友森; 黄畅峰; 舒星
Original assignee: 腾讯科技（深圳）有限公司
Priority date: 2017-02-08
Filing date: 2018-02-05
Publication date: 2018-08-16
Also published as: CN108306812B; CN108306812A

Abstract

A data processing method and a server. The method comprises: receiving a user query request sent by a first client, the user query request carrying the location information of the first client; determining, on the basis of the location information, a set of clients of which the distance from the first client is less than a preset distance threshold, the set of clients comprising at least one second client; acquiring the attribute information of the first client, and the user behavior and attribute data of the second clients included in the set of clients; determining the relevance of the first client to the second clients; according to the relevancies, determining, from the set of clients, target second clients matching the first client; and sending a user query response to the first client, the user query response comprising the identifiers of the target second clients.

Description

Data processing method, server, and storage medium

The present application claims priority to Chinese Patent Application No. JP-A No. No. No. No. No. No. No. No. No. No. No. No. No. .

Technical field

The present application relates to the field of Internet technologies, and in particular, to a data processing method, a server, and a storage medium.

background

In a social network, in some cases, users may need to find out who is nearby and contact them to make friends or ask for help. The following search methods can be used: for any user, if it is user X, when it needs to find nearby users, it will report its location information (latitude and longitude information) to the server through the first client used by itself; the server receives After the location information reported by the first client, the second client that is less than the preset distance threshold is found, and the distance between the server and the first client is less than the preset distance threshold. The client identifier of the second client, and the distance between the first client and the second client are returned to the first client.

Technical content

The technical problem to be solved by the embodiments of the present application is to provide a data processing method and a server, which can improve the accuracy of the user query.

The embodiment of the present application provides a data processing method, which is applied to a server, and the method includes:

Receiving a user query request sent by the first client, where the user query request carries location information of the first client;

Determining, according to the location information, a client set that is smaller than a preset distance threshold by the first client, where the client set includes at least one second client;

Obtaining attribute information of the first client, and user behavior and attribute data of each second client included in the client set;

Determining, according to attribute information of the first client and user behavior and attribute data of each of the second clients, a degree of association between the first client and the second client;

Determining, according to the degree of association, a target second client that matches the first client in the client set;

Sending a user query response to the first client, where the user query response includes an identifier of the target second client.

The embodiment of the present application further provides a server, where the server includes a processor and a memory, where the memory stores computer readable instructions, and the processor can be:

The embodiment of the present application further provides a computer readable storage medium storing computer readable instructions, which may cause a processor to execute the methods of the embodiments.

The technical solution of the present application obtains the target second client by referring to multiple dimensions such as location information, attribute information, and behavior data, improves the accuracy of the user query, and improves the recommendation performance of the server. Even if the two users are geographically close, the list of recommendations obtained will not be very similar, and the characteristics of different users can be distinguished.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present application, and other drawings can be obtained according to the drawings without any creative work for those skilled in the art;

1 is a schematic structural diagram of a data processing system provided in an embodiment of the present application;

2 is a schematic flowchart of a data processing method provided in an embodiment of the present application;

3 is a schematic diagram of an interface provided in an embodiment of the present application;

4 is a schematic diagram of an interface provided in another embodiment of the present application;

FIG. 5 is a schematic structural diagram of a server provided in an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a server provided in another embodiment of the present application.

Implementation

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

The embodiment of the present application provides a data processing method, where the server receives the user query request sent by the first client, and determines the distance between the first client and the first client based on the location information of the first client carried by the user query request. a client set of the distance threshold, obtaining attribute information of the first client, and user behavior and attribute data of each second client included in the client set, based on the attribute information of the first client and the user behavior of each second client And attribute data, determining a degree of association between the first client and the second client; determining, according to the degree of association, a target second client that matches the first client in the client set; The first client sends a user query response, where the user query response includes an identifier of the target second client. Receiving, by the traditional server, the user query request sent by the first client, based on the location information of the first client carried by the user query request, determining the client set that is less than the preset distance threshold by the first client, the application The embodiment may determine the target second client that matches the first client in the client set based on the attribute information of the first client and the user behavior and attribute data of each second client, thereby improving the accuracy of the user query.

Based on the above principles, the embodiment of the present application provides a data processing system, which may be an Internet application system such as an instant messaging application system, an SNS (Social Networking Services) application system, or the like. Referring to FIG. 1, the architecture of the data processing system includes at least a server 101, at least one first client 102 accessing the server 101, and at least one second client 103 accessing the server 101. In some examples, the server 101 may be a standalone service device in the Internet or a cluster service device composed of a plurality of independent service devices in the Internet. For example, the server 101 may include a logical server 1010, a storage server 1011, and a recommendation server. 1012, a communication connection is established between the at least one first client 102 and the logical server 1010 and the recommendation server 1012, and at least one second client 103 establishes a communication connection with the recommendation server 1012, and the storage server 1011 and the logical server 1010 respectively And establishing a communication connection between the recommendation servers 1012.

The first client 102 or the second client 103 can be run in a terminal such as a notebook computer, a mobile phone, a PAD (tablet computer), an in-vehicle terminal, or a smart wearable device, and the first client 102 or the second client 103 can Including instant messaging client (such as WeChat client or QQ client, etc.), live client (such as a trick-play client) or video player (such as Tencent video client). At least one type of Internet application can be run in the terminal, including but not limited to: an instant messaging application, an SNS application, and the like. The user can use the Internet application through the terminal. For example, the user can use the instant messaging application such as WeChat or QQ to find nearby users, or the user can interact with other users in the Internet application through the terminal, for example, the user uses the instant communication through the terminal. The application displays a conversation interface with other users, and the user can input social messages and the like on the conversation interface. The server 101 can be used to process various requirements of an Internet application in realizing functions such as searching for nearby users, business processing, and information interaction, and the server 101 can be used for related data, users, and users of users in an Internet application. The inter-communication messages are managed, for example, storing user behavior and attribute data of the first client 102 and user behavior and attribute data of the second client 103.

Exemplarily, the first client 102 can obtain location information of the terminal by using a global positioning system (GPS) built in the terminal, where the terminal is installed with the first client 102, and the location information of the terminal is the first client. The location information of 102, the location information may include latitude and longitude information and the like. In some examples, the first client 102 can obtain location information of the terminal through a base station positioning system built in the terminal. In some examples, the first client 102 can receive a wireless signal (such as a WIFI signal or a Bluetooth signal, etc.) transmitted by the specified terminal device through the terminal, and acquire location information of the terminal according to the signal strength of the wireless signal. Further, the first client 102 can send the location information to the logical server 1010. In some examples, the first client 102 can also send the acquisition time of the location information to the logical server 1010.

The logical server 1010 can process the location information to obtain coordinate information (such as a coordinate ID) of the first client 102 in the preset map, and the logical server 1010 can send the coordinate information to the storage server 1011. In some examples, the logical server 1010 may also send the acquisition time of the location information to the storage server 1011.

The storage server 1011 may search the preset map for the target coordinate information with the length of the coordinate information less than the preset length threshold, and further determine the client set according to the target coordinate information, where each second client included in the client set The distance between the terminal 103 and the first client 102 is less than a preset distance threshold, and the ratio between the preset length threshold and the preset distance threshold may match the reduction ratio of the preset map. Further, the storage server 1011 may send the determined set of clients (ie, raw data) to the recommendation server 1012.

The recommendation server 1012 can obtain the target second client 103 that matches the first client 102 according to the user behavior and attribute data of each second client 103 included in the client set, wherein the target second client 103 can include At least one second client 103 in the client set. The recommendation server 1012 may also obtain the association degree between each second client 103 and the first client 102 according to the attribute information of the first client and the user behavior and attribute data of each second client 103 included in the client set. (for example, recommendation data), sorting each degree of association in a preset order (for example, from high to low or low to high) to obtain a user list, such as the first second client 103 and the first in the user list. The degree of association between a client 102 is the greatest, and the degree of association between the last second client 103 and the first client 102 is the smallest. Further, the recommendation server 1012 may further send the user list to the first client 102 through the logical server 1010, so that the first client 102 displays the user list, and the first client 102 may be associated with each second client in the user list. End 103 performs data interaction.

Based on the structural schematic diagram of the data processing system shown in FIG. 1 , the embodiment of the present application discloses a schematic flowchart of a data processing method shown in FIG. 2 . As shown in FIG. 2, the data processing method may include the following operations:

S201. Receive a user query request sent by the first client, where the user query request carries the location information of the first client.

The server may receive a user query request sent by the first client, where the user query request carries the location information of the first client. Taking the interface diagram shown in FIG. 3 as an example, the user can run the first client (ie, the QQ client) through the terminal, and click the “dynamic” button, then the first client can display the user shown in FIG. 3 in response to the user's click operation. The user can click the “near” button, and the first client can obtain the location information of the first client in response to the click operation of the user, and generate a user query request including the location information of the first client, and the first client can User query requests are sent to the server.

S202. Determine, according to the location information, a client set that is less than a preset distance threshold by the first client, where the client set includes at least one second client.

Specifically, the server may determine, according to the location information, a client set that is less than a preset distance threshold by the first client, where the client set may include at least one second client. For example, the server may obtain coordinate information of the first client according to the location information, and determine, in the preset map, target coordinate information that is shorter than a preset length threshold between the coordinates of the first client, and the client whose coordinate information is the target coordinate information. As a second client, the terminal determines a client set including the second client. The distance between the second client and the first client is less than a preset distance threshold, and the ratio between the preset length threshold and the preset distance threshold matches the reduction ratio of the preset map.

S203. Acquire attribute information of the first client, and user behavior and attribute data of each second client included in the client set.

After determining, by the server, the client set that is less than the preset distance threshold, the server may obtain the attribute information of the first client and the user behavior and attribute data of each second client included in the client set, where User behavior and attribute data can reflect the user's behavioral habits.

In some examples, the attribute information of the first client may include one or more of a webpage access feature, a social state, user preference information, identity information, and a game attribute of the first client; a user of the second client The behavior and attribute data may include at least one of: attribute information for one or more types (eg, different social areas), wherein the attribute information may include webpage access characteristics, social status, user preference information of the second client, One or more of identity information and game attributes; interaction data between the second client and the first client; and a friend level of the second client.

The one or more types may be predefined or determined according to attribute information of the first client and attribute information of the second client.

Table 1 lists the different types of user attribute information. The server may collect attribute information of each second client in a basic field, an advertising field, a recommendation field, a social credit field, or a shopping field, and the server may acquire identity information, user preference information, and webpage access characteristics of the second client in the basic domain. Or the social status or the like, the server may obtain the identity information, the webpage access feature, the social state, or the user preference information of the second client in the advertisement domain, and the server may acquire the identity information, the webpage access feature, or the game attribute of the second client in the recommended domain. The server may obtain the identity information of the second client or the like in the social credit field, and the server may obtain the user preference information of the second client and the like in the shopping field. The webpage access feature may include device information of the terminal running the second client (eg, device identification, an operating system or an Internet Protocol (IP) address, etc.), a time period for accessing the webpage, or a frequency of accessing the webpage. Wait. The social status may include whether the second client is an active actor, or an opinion leader, or the activity of the second client in each relationship set, and the like. The user preference information may include a shopping interest of the second client, a study abroad tendency or a shopping number commercial interest, etc., and the identity information may include a natural attribute such as a gender or age of the second client, a professional attribute, an educational attribute, a family attribute, or a geographical attribute, etc., the game The attributes may include game activity or game type preferences of the second client, and the like.

Specifically, for different types of attributes as shown in Table 1, the server may select an attribute information type that the first client and the second client have in common. For example, the first client and the second client both have attributes such as age, gender, and charm value, and the server may select attribute types such as age, gender, and charm value to obtain the types of the first client and the second client respectively. Attribute information.

Table I

Exemplarily, the interaction data between the second client and the first client may include whether the second client has basic information for viewing the first client, browses photos posted by the first client, or initiates temporary to the first client. Conversation, etc. In some examples, the interaction data between the first client and the second client may include whether the first client has basic information for viewing the second client, browses a photo posted by the second client, or initiates a message to the second client. Temporary sessions, etc.

Exemplarily, the friend level of the second client may be used to indicate the frequency of interaction between the second client and an unfamiliar user other than the friend included in the address book, and interact with the unfamiliar user, for example, to view the basic information of the unfamiliar user, and to visit the stranger. The user's space or a temporary session to a strange user.

Here, the server may also collect attribute information of the first client in a basic field, an advertising field, a recommendation field, a social credit field, or a shopping field, such as in a basic field, an advertising field, a recommendation field, a social credit field, or shopping. The identity information, the user preference information, the webpage access feature, or the social status of the first client are obtained in the domain or the like.

S204. Obtain an association degree between the first client and the second client based on the attribute information of the first client and the user behavior and attribute data of each second client.

The server may determine a target second client that matches the first client in the client set based on the attribute information of the first client and the user behavior and attribute data of each second client. In some instances, the server may obtain the degree of association between the first client and the second client by different methods. For example, S2041, S2042, and S2043 below list three different implementations.

S2041: The server may obtain one or more types of attribute information of the first client, compare one or more types of attribute information of the first client with attribute information of a corresponding type of the second client, and determine the first client and the The number of the same attribute information between the second client, and the number of the same attribute information as a percentage of the total attribute information is used as the association between the first client and the second client. degree.

Exemplarily, the server may obtain N types of attribute information of the first client, where N is a natural number, and each second client in the client set also collects the same number of attribute information of the corresponding type, where each of the first client When the attribute information of the type is compared with the attribute information of the corresponding type of the second client, the degree of association between the second client and the first client may be expressed as: x/N, where x=0, 1, ..., N , x represents the number of identical attribute information between the first client and the second client. For example, the server may obtain the identity information of the first client for the basic domain, and the identity information of each second client in the client set for the basic domain, and target the identity information of the first client to the basic domain with the second client. Comparing the identity information of the basic domain, when the similarity between the identity information of the first client for the basic domain and the identity information of the second client for the basic domain is greater than a preset ratio threshold, the second client and the second client The merity of the degree of association between the clients is increased by one; when the similarity between the identity information of the first client for the basic domain and the identity information of the second client for the basic domain is less than or equal to a preset ratio threshold, the server Keep the degree of association between the second client and the first client unchanged. Further, the server may further obtain user preference information of the first client for the shopping domain, and user preference information of each second client in the client collection for the shopping domain, and the user preference information of the first client for the shopping domain and The second client compares the user preference information of the shopping domain, when the similarity between the user preference information of the first client for the shopping domain and the user preference information of the second client for the shopping domain is greater than a preset ratio threshold, Adding a numerator of the degree of association between the second client and the first client; when the first client is similar to the user preference information of the shopping domain and the user preference information of the second client for the shopping domain When the threshold is less than or equal to the preset ratio threshold, the server keeps the degree of association between the second client and the first client unchanged. After the foregoing method, the server compares the first client and the second client for each attribute information of each social domain, and obtains the degree of association between the first client and the second client, and then determines the first client and the second client. Whether the degree of association between the second client is greater than a preset ratio threshold. When the degree of association between the first client and the second client is greater than a preset ratio threshold, the second client is used as the target second client.

In other examples, the server may also obtain the degree of association between the first client and the second client through S2042.

S2042: Compare the attribute information of each type of the first client with the attribute information of the corresponding type of the second client to obtain a comparison result; based on the second client and the first client Interacting data, acquiring a first feature value of the second client; acquiring a second feature value of the second client based on a friend level of the second client; and based on the comparison result, the first feature value, and the second And obtaining an association degree between the first client and the second client.

In some examples, the server may also obtain the degree of association between the first client and the second client by the following method. The server may compare the attribute information of the first client with the attribute information of the corresponding type for the second client to obtain a comparison result, where the comparison result is used to indicate the first client. Obtaining a similarity degree of all types of attribute information of the second client, and acquiring a first feature value of the second client, where the first feature is based on interaction data between the second client and the first client The value is used to indicate the frequency of interaction between the second client and the first client, and the second feature value of the second client is obtained based on the friend level of the second client, where the second feature value is used by The frequency of the interaction between the first client and the second client is obtained, and the degree of association between the first client and the second client is obtained based on the comparison result, the first feature value, and the second feature value.

Exemplarily, the server compares the attribute information of each type of the first client and the second client to obtain a comparison result of 50%, that is, the similarity of all types of attribute information of the first client and the second client is 50%, based on the interaction data between the second client and the first client, obtaining a first feature value of the second client is 30%, that is, the interaction between the second client and the first client The frequency is 30%, based on the friend level of the second client, obtaining the second feature value of the second client is 40%, that is, the frequency of interaction between the second client and the strange user other than the friend included in the address book is 30. %, the comparison result of the comparison result of all types of attribute information of the first client and the second client pre-configured by the server is 0.7, the weight of the first feature value is 0.2, and the weight of the second feature is 0.1, the server It can be determined that the degree of association between the first client and the second client is 50%*0.7+30%*0.2+20%*0.1=43%.

In some examples, the server may also determine the degree of association between the first client and the second client by the method of S2043 below.

S2043: Obtain a plurality of attribute values according to one or more types of attribute information of the first client and attribute information of a corresponding type of the second client; and process the attribute values by using a preset logistic regression algorithm. The processing result is obtained, and the processing result is used as the degree of association between the first client and the second client.

In some examples, the attribute value may be obtained by digitizing a single attribute information.

The following is described in conjunction with Table 2. As shown in Table 2, a list of attributes of one or more types of the first client (eg, From_uin) and the second client (eg, to_uin) is shown in Table 2. In some examples, the one or more types of attribute information in Table 2 may be digitized. As shown in Table 2, the discarding, denoising, and normalization may be performed on the one or more The attribute information of each type is digitized to obtain the attribute value. Among them, discretization is to reduce the data correspondingly without changing the relative size of the data. When the data is only related to the relative size between them, and discretized according to the specific number, it can be discretized. Taking the schematic diagram of one or more types of attributes and their corresponding construction methods shown in Table 2 as an example, the construction method corresponding to the age of the first client is discretization, and the construction method of the occupation corresponding to the second client is discretization and Completion.

The process of processing a single attribute information to obtain a corresponding attribute value has been described above. In some examples, other attribute values may be further calculated based on two or more attribute information. For example, two or more attribute information is calculated, such as a vector inner product calculation, to obtain the attribute value. For example, the distance between the first client and the second client, the gender intersection between the first client and the second client, and the like can be calculated. The constructing method corresponding to the distance between the first client and the second client is complement and normalization, and the constructing method corresponding to the gender cross between the first client and the second client is a vector inner product.

In some examples, the server may process the attribute value by using a preset logistic regression algorithm (LR) to obtain the degree of association between the first client and the second client. As shown in Table 2, the plurality of attribute values (including the attribute values obtained according to the single attribute information and the attribute values calculated according to the two or more attribute information) are used as the logistic regression algorithm. Entering a variable to obtain a degree of association between the second client and the first client.

In this example, the logistic regression equation is

Where P(e) is the degree of association between the second client and the first client, and x ₁ , x ₂ ... x _k are the plurality of attribute values, b ₀ , b ₁ , b ₂ ...b _k is a predefined coefficient.

In some examples, the server may process the attribute information of the first client and the user behavior and attribute data of each second client included in the client set by using a preset logistic regression algorithm to obtain each second client and the first client. The degree of association between the ends is that the second client with a greater degree of association among the second clients included in the client set is the target second client. For example, the server may use the second client included in the client set with the association degree greater than the preset ratio threshold as the target second client, and the server may include the second client included in the client set. A second client that meets a preset number of related degrees is used as the target second client, wherein the degree of association between the target second client and the first client is greater than the other second client in the client set and the first The degree of association between clients.

Table II

S205. Determine, according to the degree of association, a target second client that matches the first client in the client set.

In some examples, S205 includes:

S2051: Sort each degree of relevance in descending order, and determine a second client corresponding to the first N degrees of association as the target second client, where N is a positive integer.

In other examples S205 includes:

S2052: Pre-set a proportional threshold. When the degree of association between the first client and the second client is greater than a preset ratio threshold, the second client is used as the target second client.

S206: Send a user query response to the first client, where the user query response includes an identifier of the target second client.

In some examples, the server determines, based on the user behavior and the attribute data, a target second client that matches the first client in the client set, and obtains the client identifier of the target second client, and the target second client and Correlation degree between the first clients, the target second client is sorted in descending order based on the degree of association with the first client, and the second client corresponding to the first N association degrees is determined as the target second The client, where N is a positive integer; wherein the identifier of the target second client included in the user query response is: the client identifier of the first N target second clients.

In some examples, the server may send the client identifier of the target second client, and the degree of association between the target second client and the first client, to the first client, so that the first client is based on the first client. The degree of association between the clients sorts the target second client and displays the client identity of the sorted target second client.

Taking the interface diagram shown in FIG. 4 as an example, the first client may display the client identifier of each target second client, where the distance between the target second client and the first client is less than a preset distance threshold, and The relationship between a target second client and the first client is relatively large, and the degree of association between the last target second client and the first client is small.

The technical solution of the present application obtains the target second client by referring to multiple dimensions such as location information, attribute information, and behavior data, thereby improving the accuracy of the user query and improving the recommendation performance of the server. Even if the two users are geographically close, the list of recommendations obtained will not be very similar, and the characteristics of different users can be distinguished.

Referring to FIG. 5, FIG. 5 is a schematic structural diagram of a server provided in an embodiment of the present application. The server may be used to implement some or all operations in the method embodiment shown in FIG. The server in the embodiment may at least include a query request receiving unit 701, a set determining unit 702, a behavior data acquiring unit 703, and a client determining unit 704, where:

The query request receiving unit 701 is configured to receive a user query request sent by the first client, where the user query request carries location information of the first client.

The set determining unit 702 is configured to determine, according to the location information, a client set that is less than a preset distance threshold by the first client, where the client set includes at least one second client.

The behavior data obtaining unit 703 is configured to acquire attribute information of the first client, and user behavior and attribute data of each second client included in the client set.

The client determining unit 704 is configured to determine, according to the attribute information of the first client and the user behavior and attribute data of each of the second clients, the degree of association between the first client and the second client. Determining, according to the degree of association, a target second client that matches the first client in the client set; sending a user query response to the first client, where the user query response includes a target second The identity of the client.

In some examples, the attribute information of the first client includes one or more of a webpage access feature, a social state, user preference information, identity information, and a game attribute of the first client; User behavior and attribute data include at least one of the following:

One or more types of attribute information of the second client, the one or more types of attribute information including webpage access characteristics, social status, user preference information, identity information, and game attributes of the second client One or more.

The interaction data between the second client and the first client, the interaction data is used to indicate whether the second client views related information of the first client or the second client Whether a session has been initiated to the first client.

a friend rating of the second client, wherein the friend rating is used to indicate a frequency at which the second client interacts with an unfamiliar user.

In some examples, the client determining unit 704 is further configured to:

Comparing one or more types of attribute information of the first client with attribute information of a corresponding type of the second client, and determining the number of the same attribute information between the first client and the second client, The percentage of the same attribute information as a percentage of the total attribute information is used as the degree of association between the first client and the second client.

In some examples, the client determining unit 704 is further configured to:

Comparing one or more types of attribute information of the first client with attribute information of a corresponding type of the second client to obtain a comparison result;

Obtaining a first feature value of the second client, based on interaction data between the second client and the first client;

Obtaining a second feature value of the second client based on a friend level of the second client; and

And obtaining, according to the comparison result, the first feature value, and the second feature value, a degree of association between the first client and the second client. In some examples, the client determining unit 704 is further configured to:

Obtaining a plurality of attribute values according to the one or more types of attribute information of the first client and the second client,

The attribute value is processed by a preset logistic regression algorithm to obtain a processing result, and the processing result is used as a degree of association between the first client and the second client.

In some examples, the client determining unit 704 is further configured to:

The ratio threshold is preset, and when the degree of association between the first client and the second client is greater than a preset ratio threshold, the second client is used as the target second client.

In some examples, the server in the embodiment of the present application may further include:

An identifier obtaining unit 705, configured to determine, by the client determining unit 704, a target second client that matches the first client, and obtain the target second client, in the client set according to the degree of association The client identifier of the end, and the degree of association between the target second client and the first client.

The sorting unit 706 is configured to perform the descending ordering on the target second client based on the degree of association with the first client.

The client determining unit 704 further determines the second client corresponding to the first N degrees of association as the target second client, where N is a positive integer;

The identifier sending unit 707 is configured to send the client identifiers of the first N target second clients to the first client.

Referring to FIG. 6, FIG. 6 is a schematic structural diagram of a server provided in another embodiment of the present application. The server provided in this embodiment of the present application may be used to implement the method implemented in the foregoing embodiment of the present application shown in FIG. For convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the embodiment of the present application shown in FIG. 2 .

As shown in FIG. 6, the server includes at least one processor 801, such as a CPU, at least one input device 803, at least one output device 804, a memory 805, and at least one communication bus 802. Among them, the communication bus 802 is used to implement connection communication between these components. The input device 803 may specifically be a network interface or the like for performing data interaction with the first client. The output device 804 may be a network interface or the like for performing data interaction with the first client. The memory 805 may include a high-speed RAM memory, and may also include a non-unstable memory, such as at least one disk storage, specifically for storing user behavior and attribute data of each client. In some examples, memory 805 can include at least one storage device located remotely from processor 801. A set of machine readable instructions are stored in memory 805, and processor 801 calls machine readable instructions stored in memory 805 for performing the following operations:

Receiving, by the input device 803, a user query request sent by the first client, where the user query request carries the location information of the first client;

Determining, according to the attribute information of the first client and the user behavior and attribute data of each of the second clients, a degree of association between the first client and the second client; according to the association degree, Determining, in the set of clients, a target second client that matches the first client; and

In some examples, the processor 801 is configured to determine an association between the first client and the second client based on attribute information of the first client and user behavior and attribute data of each of the second clients. The machine readable instructions of the degree further include instructions that cause the processor 801 to:

In some examples, the processor 801 is configured to determine an association between the first client and the second client based on attribute information of the first client and user behavior and attribute data of each of the second clients. The machine readable instructions further include machine readable instructions that cause the processor 801 to:

And obtaining, according to the comparison result, the first feature value, and the second feature value, a degree of association between the first client and the second client.

In some examples, the processor 801 is caused to determine, in the set of clients, machine readable instructions of the target second client that match the first client in accordance with the degree of association, further causing the processor 801 to perform the following operations :

Obtaining a client identifier of the target second client, and a degree of association between the target second client and the first client;

Sorting the target second client in descending order based on the degree of association with the first client; and

Determining, by the second client corresponding to the first N degrees of association, a target second client, where N is a positive integer;

The identifier of the target second client included in the user query response is: the client identifier of the first N target second clients.

The server introduced in the embodiment of the present application may be used to implement some or all of the processes in the method embodiment introduced in conjunction with FIG. 2 in this application.

A person skilled in the art can understand that all or part of the process of implementing the above embodiment method can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The above is only the preferred embodiment of the present application, and the scope of the application is not limited thereto, and the equivalent changes made in the claims of the present application are still within the scope of the present application.

Claims

A data processing method is applied to a server, wherein the method includes:

Receiving a user query request sent by the first client, where the user query request carries location information of the first client;

Determining, according to the location information, a client set that is smaller than a preset distance threshold by the first client, where the client set includes at least one second client;

Obtaining attribute information of the first client, and user behavior and attribute data of each second client included in the client set;

Determining, according to attribute information of the first client and user behavior and attribute data of each of the second clients, a degree of association between the first client and the second client;

Determining, according to the degree of association, a target second client that matches the first client in the client set;

Sending a user query response to the first client, where the user query response includes an identifier of the target second client.
The method of claim 1, wherein the attribute information of the first client comprises one or more of a webpage access feature, a social state, user preference information, identity information, and game attributes of the first client;

The user behavior and attribute data of the second client includes at least one of the following:

One or more types of attribute information of the second client, the one or more types of attribute information including webpage access characteristics, social status, user preference information, identity information, and game attributes of the second client One or more;

The interaction data between the second client and the first client, the interaction data is used to indicate whether the second client views related information of the first client or