CN113569162A

CN113569162A - Data processing method, device, equipment and storage medium

Info

Publication number: CN113569162A
Application number: CN202110133245.1A
Authority: CN
Inventors: 苏婷; 曾天添; 汪泽; 营堂伟; 李天楚
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-01-29
Filing date: 2021-01-29
Publication date: 2021-10-29

Abstract

The embodiment of the application relates to the technical field of computers, and discloses a data processing method, a device, equipment and a storage medium, wherein the method comprises the following steps: responding to a trigger event for analyzing the sharing operation executed by the target resource link, displaying an analysis setting interface, and acquiring a data identifier of source data of the target resource link and an event identifier corresponding to the sharing operation executed by the target resource link; acquiring source data of the target resource link according to the data identifier, and performing data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link; analyzing and processing the analysis reference data to obtain a plurality of user sets; feedback information generated after the target resource link is shared is obtained, the feedback information is used for determining a target user set when other resource links to be shared are shared from a plurality of user sets, and the propagation condition of the target resource link can be referred to quickly propagate the other resource links.

Description

Data processing method, device, equipment and storage medium

Technical Field

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

Background

In daily production and life, by analyzing and processing different data, rules or connections existing among the data can be known; for example, in a scenario such as campaign planning or commodity selling, it is desirable to analyze the propagation strength and propagation condition of a campaign or a commodity, so that in the process of performing subsequent campaign planning or commodity selling, the propagation strategy can be adjusted based on the analysis result to obtain a maximum propagation effect. However, the current analysis on the propagation condition of a certain activity or a certain commodity is only to simply count the data such as the total number of times of sharing and the total number of users of sharing linked to the target resource of the activity or the commodity, and only the propagation condition of the current activity or the commodity can be simply analyzed, so that the beneficial influence on the propagation of the subsequent activity or the commodity is very limited.

Disclosure of Invention

Embodiments of the present application provide a data processing method, apparatus, device, and storage medium, which can learn about propagation conditions of a target resource link and quickly propagate other resource links.

In one aspect, an embodiment of the present application provides a data processing method, including:

responding to a trigger event for analyzing the sharing operation executed by the target resource link, displaying an analysis setting interface, and acquiring a data identifier of source data of the target resource link and an event identifier corresponding to the sharing operation executed by the target resource link from the analysis setting interface;

acquiring source data of the target resource link according to the data identifier, and performing data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link, wherein the analysis reference data records a plurality of user identifiers and sharing relations of different users about the target resource link;

analyzing the analysis reference data to divide users corresponding to the user identifications recorded in the analysis reference data into different user sets to obtain a plurality of user sets;

and obtaining feedback information generated after each user sharing the target resource link, wherein the feedback information is used for determining a target user set when other resource links to be shared are shared from the plurality of user sets, and the resource types indicated by the other resource links and the target resource link are the same.

In one aspect, an embodiment of the present application provides a data processing apparatus, including:

the display unit is used for responding to a trigger event for analyzing the sharing operation executed by the target resource link and displaying an analysis setting interface;

the acquisition unit is used for acquiring a data identifier of source data of the target resource link and an event identifier corresponding to a sharing operation executed by the target resource link from the analysis setting interface;

the obtaining unit is further configured to obtain source data linked to the target resource according to the data identifier;

the processing unit is used for carrying out data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link, wherein the analysis reference data records a plurality of user identifiers and a sharing relation between different users about the target resource link;

the processing unit is further configured to perform analysis processing on the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets to obtain a plurality of user sets;

the obtaining unit is further configured to obtain feedback information generated after each user sharing the target resource link shares the target resource link, where the feedback information is used to determine, from the multiple user sets, a target user set when sharing other resource links to be shared, and resource types indicated by the other resource links and the target resource link are the same.

In one aspect, an embodiment of the present application provides a data processing device, where the data processing device includes an input interface and an output interface, and further includes:

a processor adapted to implement one or more instructions; and the number of the first and second groups,

a computer storage medium having stored thereon one or more instructions adapted to be loaded by the processor and to execute the above-described data processing method.

In one aspect, an embodiment of the present application provides a computer storage medium, where computer program instructions are stored in the computer storage medium, and when the computer program instructions are executed by a processor, the computer storage medium is configured to execute the data processing method.

In one aspect, embodiments of the present application provide a computer program product or a computer program, where the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; the processor of the data processing device reads the computer instructions from the computer readable storage medium, and executes the computer instructions, and the computer instructions, when executed by the processor, are used for executing the data processing method.

In the embodiment of the application, the data processing equipment firstly acquires a data identifier of source data of a target resource link and an event identifier corresponding to a sharing operation executed by the target resource link on an analysis setting interface; then, source data of the target resource link are obtained according to the data identification, data screening processing is carried out on the obtained source data according to the event identification, and analysis reference data of the target resource link are obtained, wherein the analysis reference data records a plurality of user identifications and sharing relations of different users about the target resource link; further, the data processing device analyzes and processes the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets to obtain a plurality of user sets; then, the data processing device acquires feedback information generated after each user sharing the target resource link, wherein the feedback information is used for determining a target user set when other resource links to be shared are shared from a plurality of user sets, and the resource types indicated by the other resource links and the target resource link are the same; the analysis reference data of the target resource link can be further obtained by obtaining the source data of the target resource link, and the analysis reference data comprises a plurality of user identifications and sharing relations among different users about the target resource link; dividing users corresponding to the user identifications recorded in the analysis reference data according to the analysis reference data to obtain a plurality of user sets; finally, feedback information of the target resource link can be acquired, so that a user can know the propagation condition of the target resource link conveniently; meanwhile, the target user set can be obtained from the plurality of user sets based on the feedback information, so that other resource links of the same type needing to be quickly propagated can be quickly propagated through the target user set, and a good propaganda effect is achieved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a data table of source data linked to a target resource according to an embodiment of the present disclosure;

fig. 2 is a schematic flowchart of a data processing method according to an embodiment of the present application;

FIG. 3a is an interface diagram of an analysis setup interface provided by an embodiment of the present application;

FIG. 3b is a diagram illustrating a switch analysis settings interface according to an embodiment of the present application;

FIG. 4a is a schematic diagram of a trigger display analysis setup interface provided by an embodiment of the present application;

FIG. 4b is a schematic diagram of another trigger display analysis setup interface provided by an embodiment of the present application;

fig. 5 is a schematic diagram of a plurality of user sets obtained by dividing according to an embodiment of the present application;

FIG. 6 is a schematic diagram of processing source data linked to a target resource according to an embodiment of the present application;

FIG. 7 is a schematic flow chart diagram of another data processing method provided in the embodiments of the present application;

FIG. 8a is a schematic diagram of feedback information of a target resource link changing with time according to an embodiment of the present application;

FIG. 8b is a diagram illustrating a comparison of feedback information of different resource links according to an embodiment of the present application;

FIG. 9 is an interface diagram of a set query interface provided by an embodiment of the present application;

FIG. 10a is a diagram illustrating a triggering of displaying user information of a target user set according to an embodiment of the present application;

fig. 10b is a schematic diagram illustrating a sharing relationship of a target user identifier displayed in a sharing relationship display area according to an embodiment of the present application;

fig. 11a is a schematic diagram of importing a target identifier set according to an embodiment of the present application;

fig. 11b is a schematic diagram illustrating triggering user image analysis on a user corresponding to a target identifier set according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly includes several directions, such as computer vision technology, speech processing technology, natural language processing technology, and Machine Learning (ML)/deep Learning. The embodiment of the application mainly relates to machine learning in artificial intelligence, and the machine learning is specially used for researching how a computer simulates or realizes human learning behaviors so as to acquire new knowledge or skills and reorganize an existing knowledge structure to continuously improve the performance of the computer. Based on this, an embodiment of the present application provides a data processing method, so that a data processing device can obtain source data of a target resource link and further obtain analysis reference data of the target resource link, where the analysis reference data includes a plurality of user identifiers and a sharing relationship between different users about the target resource link; therefore, the data processing equipment can divide the users corresponding to the user identifications recorded in the analysis reference data into a plurality of user sets according to the analysis reference data, and finally can acquire feedback information of the target resource link so as to enable the users to know the propagation condition of the target resource link; meanwhile, the target user set can be obtained from the plurality of user sets based on the feedback information, so that other resource links of the same type needing to be quickly propagated can be quickly propagated through the target user set, and a good propaganda effect is achieved.

The target resource link is a link pointing to a target resource page, that is, a user can access the target resource page through the target resource link, when the target resource link points to the target web page, the user can access the target web page through the target resource link, and when the target resource link points to a page in an application program, the user can access the page in the application program through the target resource link. In one embodiment, the data processing device may be a terminal device, which may be, for example, any one or more of a smartphone, a tablet, a laptop, a desktop computer, a smart car, and a smart wearable device; in another embodiment, the data processing device may also be a server, which may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform. The data processing device and the server may be directly or indirectly connected in a wired or wireless communication manner, and the present application is not limited herein.

In one embodiment, a user can share a target resource link, and share the target resource link to other users, so that the other users can access a target resource page through the target resource link; if other users share the target resource link again after receiving the target resource link and share the target resource link to other users, more users can access the target resource page through the target resource link; if the same target resource link is continuously shared by different users to attract more users to visit the target resource page, the sharing and fission effect can be achieved, and the target resource page can be rapidly spread. For example, if the user a shares the target resource link to the user B and the user C; and the user B and the user C access the target resource page through the target resource link, the user B shares the target resource link with the user D and the user E, the user C shares the target resource link with the user F and the user G, and the circulation is repeated, so that the target resource link is rapidly spread among different users in exponential multiple, and a large amount of access is brought to the target resource page. The target resource link can be shared by the user based on a certain channel, for example, the target resource link can be shared to the WeChat friend user or the QQ friend user under the social ecology of WeChat, QQ and the like based on the sharing channels of WeChat, QQ and the like, or the target resource link can be shared through the social platforms of WeChat group, QQ group, WeChat friend circle, QQ space and the like.

In an embodiment, the source data of the target resource link may include related parameters of an access event generated by accessing a target resource page corresponding to the target resource link, related parameters of a sharing event generated by sharing the target resource link, related parameters of a click target resource link event (or referred to as a sharing landing page exposure event) generated by accessing the target resource page through the target resource link, related parameters of a click event of a sharing landing page generated by performing operations such as subsequent clicking on the sharing landing page, and the like, where the sharing landing page is a target resource page entered through a route of the target resource link. The source data linked by the target resource comprises different events with different relevant parameters, and the different relevant parameters have different parameter types, such as a character string type, a number type, a single-precision floating point type, a double-precision floating point type, an integer type and the like; the relevant parameters of the event corresponding to the source data of the target resource link under different application scenes may be different; for example, if in an activity that only wants to promote, the user who does not pay attention to accessing the target resource page is a paid user, in such an application scenario, the relevant parameter of the event may not include the relevant parameter about whether the user is a paid user; however, if the user accessing the target resource page is a paying user in a commodity selling activity, in such an application scenario, the relevant parameter of the event will include a relevant parameter as to whether the user is a paying user, and this application scenario is exemplified in the embodiments of the present application.

As shown in fig. 1, a data table of source data linked to a target resource is provided in an embodiment of the present application, where relevant parameters of an access event include a user identifier (specifically shown as a user id in fig. 1), an event occurrence time, a user attribute, a channel type, a channel identifier (specifically shown as a channel id in fig. 1), and a sharing user identifier _ sharing time (specifically shown as a sharing user id _ sharing time in fig. 1). The sharing user identifier _ sharing time is the recorded user identifier and sharing time shared to the user when the user in the access event accesses the target resource page through the target resource link shared to the user, the user attribute can include whether a new user, whether a user pays, whether the user pays, and the like, and the channel type and the sharing user identifier _ sharing time can be null; the parameters related to sharing the event include a user identifier, an event occurrence time, a user attribute, a channel type, a channel identifier, a scene, a page name, a page module, a content type, a content subtype, a content identifier (specifically shown as content id in fig. 1), a link, and an extension field.

The user corresponding to the user identifier in the sharing event is a user who performs sharing operation on the target resource link, the user attribute may include whether the user is a new user, whether the user is a paid user, and the like, the user content type may indicate the type of the content of the target resource link, and may be, for example, a commodity, a shop or a group store type, the content identifier is a commodity identifier, a shop identifier, a group store identifier, and the like, and the channel type, the scene, the page name, the page module, the content type, the content subtype, the content identifier, the link, and the extension field may be empty; the relevant parameters of the click target resource link event comprise a user identifier, an event occurrence time, a user attribute, a sharing user identifier _ sharing time, a channel type, a channel identifier, a scene, a page name, a page module, a content type, a content subtype, a content identifier, a link and an extension field, wherein a user corresponding to the user identifier in the click target resource link event is a user accessing a target resource page by clicking a target resource link shared to the user, the sharing user identifier _ sharing time is the user identifier and the sharing time shared to the user, the user attribute can comprise whether a new user is used, whether a user is paid, whether the user is paid and the like, and the channel type, the scene, the page name, the page module, the content type, the content subtype, the content identifier, the link and the extension field can be empty; and the related parameters of the click event of the shared landing page are the same as those of the click target resource link event. And the related parameters of the source data of the target resource link are obtained by data embedding at different nodes of the target resource link.

In an embodiment, after obtaining the source data of the target resource link, an analysis user who wants to analyze the propagation condition of the target resource link may upload the source data of the target resource link on an analysis setting interface of a data processing device, where the data processing device may obtain a data identifier of the source data of the target resource link and an event identifier of an event corresponding to a sharing operation performed on the target resource link from the analysis setting interface. The event identification of the event corresponding to the sharing operation executed on the target resource link is the event identification of different corresponding events in the uploaded source data of the target resource link; and then, the data processing equipment acquires the source data of the target resource link according to the data identifier, and performs data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link, wherein the analysis reference data comprises a plurality of user identifiers and sharing relations among different users about the target resource link. The data processing equipment analyzes and processes the analysis reference data and divides users corresponding to the user identification recorded in the analysis reference data into a plurality of user sets; then, the data processing equipment acquires feedback information of the target resource link, and the feedback information can be displayed in the data processing equipment so as to facilitate an analysis user to know the propagation condition of the target resource link; the target user set can be obtained from the plurality of user sets through the feedback information, so that other resource links of the same type needing to be quickly propagated can be quickly propagated through the target user set, and a good propaganda effect is achieved.

In one embodiment, after obtaining the source data of the target resource link and the event identifier, the source data and the event identifier of the target resource can be uploaded to the server, so that the server executes subsequent operations, the obtained plurality of user sets, feedback information and relevant information of the target user set are sent to the data processing device, so that the data processing device displays the information, or, after obtaining the analysis reference data, the analysis reference data may be uploaded to a server, so that the server executes subsequent operation, sends the obtained plurality of user sets, the feedback information and the relevant information of the target user set to the data processing equipment, so that the feedback information is displayed in the data processing equipment, and rapidly propagating other resource links of the same type needing rapid propagation through the target user set.

Based on the data processing system, the embodiment of the application provides a data processing method. Referring to fig. 2, a schematic flow chart of a data processing method according to an embodiment of the present application is shown. The data processing method shown in fig. 2 may be performed by the data processing apparatus described above. The data processing method shown in fig. 2 may include the steps of:

s201, responding to a trigger event for analyzing the sharing operation executed by the target resource link, and displaying an analysis setting interface.

The target resource link is a link pointing to a target resource page, that is, a user can access the target resource page through the target resource link, when the target resource link points to the target web page, the user can access the target web page through the target resource link, and when the target resource link points to a page in an application program, the user can access the page in the application program through the target resource link.

In one embodiment, the data processing device displays an analysis setting interface in response to a trigger event for an analysis user to analyze a sharing operation performed by a target resource link, wherein the analysis setting interface is used for enabling the analysis user to upload source data of the target resource link. As shown in fig. 3a, an interface diagram of an analysis setting interface provided in the embodiment of the present application includes an operation prompt area as denoted by 301, an analysis category option as denoted by 302, a data lead-in area as denoted by 303, and a progress component as denoted by 304. The operation prompt area is used to prompt an operation step of analyzing source data of a target resource link uploaded by a user, and specifically, the prompt message displayed in the operation prompt area may be: "1, selecting data resources, events, fields; 2. selecting a global screening field; 3. commit "; by selecting what kind of analysis is desired to be performed from the analysis category options marked 302, when the analysis user wants to perform propagation analysis on the target resource link, the "sharing fission" category can be selected; when the analysis category option is empty, that is, the analysis user does not select a category to be analyzed from the analysis category options, prompt information for prompting the analysis user to select the analysis category is displayed on the analysis setting interface, for example, the prompt information may be "please select the analysis category," and optionally, the prompt information may be displayed in the analysis setting interface in a pop-up window manner.

If the "sharing fission" category is selected, displaying a data import template corresponding to the "sharing fission" category in a data import area marked as 303, analyzing source data of a target resource link selected by a user through the data import area, selecting an access event, a sharing event, a click target resource link event and a click event on a sharing landing page included in source data of the target resource link, and selecting related parameters of different events, if the source data of the target resource link is selected, displaying a data identifier of the source data of the target resource link on an analysis setting interface, and if different events are selected, displaying event identifiers of different events on the analysis setting interface; optionally, after the source data of the target resource link is selected, the data processing device may automatically match different events and the filling of related parameters of different events according to the data import template; the progress component marked as 304 may include a cancel component and a next step component, and if the cancel component is triggered, the uploading of the source data linked to the target resource is cancelled, and if the next step component is triggered, the analysis setting interface displays the content corresponding to the "select global filter field". Optionally, the analysis setting interface may further include an add real-time data source component, as indicated by 305, for adding real-time data of a target resource link, where the real-time data of the target resource link is consistent with an event included in the source data of the target resource link and related parameters of the event.

In one embodiment, if the next component is triggered, the analysis setting interface displays content corresponding to a "select global filter field", as shown in fig. 3b, which is a schematic diagram of a switching analysis setting interface provided in this embodiment, as indicated by reference numeral 311, the analysis setting interface when the content corresponding to the "global filter field" is displayed includes a field filter option, a share time window and a data source option, where the field filter option is used to filter related parameters commonly owned by a share event, a click target resource link event and a share landing page click event, such as content types, content identifiers and user attributes included in the share event, the click target resource link event and the share landing page click event, the share time window is used to set a time interval from the sharing of the target resource link to the clicking of the target resource link, if the time interval exceeds the time interval, the calculation will not be performed, the data source option is used to set whether the source data linked to the target resource is an offline data source, specifically, the field filtering option may be denoted by a 312 mark, and specifically displayed as "select field for filtering", the sharing time window may be denoted by a 313 mark, and the data source option may be denoted by a 314 mark, and specifically expressed as "whether the data source is offline"; the progress component at this time is specifically, as indicated by 315 mark, composed of a cancel component and a submit component, and if the cancel component is triggered, the contents in the field filtering option, the sharing time window and the data source option are cancelled, and the uploading of the source data linked to the target resource is cancelled, and if the submit component is triggered, the source data linked to the target resource is uploaded.

In one embodiment, the triggering event in response to analyzing the sharing operation performed on the target resource link may include: the data processing device responds to a triggering operation aiming at the application market component and displays an application open market interface, wherein the application open market interface comprises function options, and the function options comprise analysis model options; and if the analysis model option is selected, displaying an analysis model interface comprising a sharing fission module, wherein the sharing fission module is a module for analyzing the propagation condition of the target resource link, and the sharing fission module comprises a module introduction inlet and a module analysis inlet. If the module introduction inlet is triggered, displaying a module introduction interface, wherein the module introduction interface is used for introducing the sharing fission module and comprises an analysis setting inlet; if the analysis setup portal is triggered, displaying an analysis setup interface as shown in FIG. 3 a; if the module analysis entry is triggered, and is triggered for the first time, displaying an analysis setup interface as shown in FIG. 3 a; and if the module analysis entry is triggered and is not triggered for the first time, displaying an analysis billboard interface, wherein the analysis billboard interface is used for displaying an analysis result of the source data linked to the target resource.

As shown in fig. 4a, for a schematic diagram of a triggered display analysis setting interface provided in the embodiment of the present application, as denoted by reference numeral 401, if an application market component as denoted by reference numeral 402 is triggered and an analysis model option is selected, an analysis model interface as denoted by reference numeral 403 is displayed, where a sharing fission module is denoted by reference numeral 404, a module introduction entry is denoted by reference numeral 405, and is specifically displayed as "details", a module analysis entry is denoted by reference numeral 406, and is specifically displayed as "enter", and if the module analysis entry is triggered and is triggered for the first time, that is, the "enter" entry is triggered for the first time, an analysis setting interface as denoted by reference numeral 407 is displayed; as shown in fig. 4b, for another schematic diagram of a triggered display analysis setting interface provided in this embodiment of the present application, if an analysis model interface is shown as reference numeral 411, when a module introduction entry is triggered, that is, a "detail" entry is triggered, a module introduction interface shown as reference numeral 412 is displayed, where the module introduction interface includes an analysis setting entry which may be shown as reference numeral 413 and specifically shown as "configuration", and if an analysis configuration entry is triggered, that is, a "configuration" entry is triggered, an analysis setting interface shown in fig. 3a is displayed.

S202, acquiring a data identifier of source data of the target resource link from the analysis setting interface, and acquiring an event identifier corresponding to a sharing operation executed by the target resource link.

And S203, acquiring the source data linked with the target resource according to the data identifier.

And S204, performing data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link.

In steps S202-S204, after the analysis user triggers the submission component on the analysis setting interface, the data processing device obtains, from the analysis setting interface, a data identifier of source data of a target resource link selected by the analysis user, and an event identifier corresponding to a sharing operation performed on the target resource link, where the event identifier includes an event identifier of an access event, an event identifier of a sharing event, an event identifier of a click target resource link event, and an event identifier of a share landing page click event; and acquiring source data of the target resource link according to the data identifier, and performing data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link. The analysis reference data records a plurality of user identifications and sharing relations among different users about the target resource link.

Specifically, the sharing relationship between different users regarding the target resource link is obtained from the sharing user identifier _ sharing time in the relevant parameter of the target resource link click event of the source data, and the user who accesses the target resource page through the target resource link can be found through the sharing user identifier _ sharing time through which user the shared target resource link is accessed, so that the sharing relationship can be found, for example, the user a accesses the target resource page through the target resource link sent to the user a through the user B, and then the sharing relationship exists between the user a and the user B. For example, if the ratio of clicking the link by the user a is higher than a certain threshold value, the user a and the user B may be considered to belong to the strong sharing relationship, and if the ratio is lower than the certain threshold value, the user a and the user B may be considered to belong to the weak sharing relationship. Optionally, a strong relationship or a weak relationship (or referred to as a pan relationship) exists between users having a sharing relationship, for example, a micro-credit user naturally has a strong-contact friend relationship, and the friend relationship of the micro-credit user belongs to the strong relationship; for example, if there is no direct relationship among the accounts such as the group, the WeChat public number, and the applet, the relationship belongs to a weak relationship, and the relationship generated by indirect behaviors such as a common membership of the group and an applet forwarding relationship is also a weak relationship.

The data processing device may perform analysis processing on the analysis reference data to divide the users corresponding to the user identifiers recorded in the analysis reference data into different user sets, so as to obtain a plurality of user sets, that is, instead, perform step S205.

S205, analyzing the analysis reference data to divide the users corresponding to the user identifications recorded in the analysis reference data into different user sets to obtain a plurality of user sets.

The multiple user sets obtained by dividing the users corresponding to the user identifications are used for enabling the users in the user sets to have a strong sharing relationship and the users between the user sets to have a weak sharing relationship, so that other resource links to be shared can be quickly spread in the user sets.

In one embodiment, the analysis reference data is a knowledge graph constructed by a plurality of nodes, the knowledge graph comprises a node for recording a user identifier, and an edge of the knowledge graph is used for indicating a sharing relationship between users corresponding to the corresponding user identifiers. If the weight between the users is not included in the analysis reference data, the data processing equipment traverses each node in the knowledge graph, determines at least one adjacent node of the traversed current node, and calculates the node association degree between the current node and each adjacent node; performing clustering operation on each node in the knowledge graph according to the node association degree, and stopping performing clustering operation on the knowledge graph when the set association degree of the node set obtained by clustering obtains the maximum value to obtain a plurality of node sets; the node set is used for indicating a user set, and the user identifier recorded by each node in the node set is the user identifier corresponding to the user in the corresponding user set.

The clustering operation is performed on each node in the knowledge graph according to the node association degree, and specifically includes: performing clustering operation on the current node and any adjacent node to obtain a plurality of reference node sets and a set association degree corresponding to each reference node set; and selecting the maximum set association degree from the set association degrees corresponding to each reference node set, and taking the reference node set indicated by the maximum set association degree as the node set to which the current node is clustered.

In specific implementation, the data processing device traverses each node and calculates the node association degree between the current node and each adjacent node, wherein the adjacent node of the current node is a node which is in edge connection with the current node in the knowledge graph, namely, a sharing relation exists between a user corresponding to the adjacent node and a user corresponding to the current node; the node association degree between the current node and one adjacent node may be a weight between the current node and one adjacent node, and a weight between a user corresponding to the current node and a user corresponding to one adjacent node, where the weight may be determined according to a sharing relationship between the user corresponding to the current node and the user corresponding to one adjacent node, or may be determined according to a sharing relationship between the user corresponding to the current node and the user corresponding to one adjacent node, and a strong relationship or a weak relationship.

Performing clustering operation on the current node according to the node association degree of the current node, specifically, performing clustering operation on the current node and any adjacent node to obtain a plurality of reference node sets and a set association degree corresponding to each reference node set; wherein one reference node set comprises the current node and one adjacent node. The maximum set association degree is selected from the set association degrees corresponding to each reference node set, because the clustering operation is carried out on the current node to ensure that the users corresponding to the current node after clustering and the users corresponding to the target adjacent node have strong sharing relation, wherein the target adjacent node is the adjacent node in the reference node set corresponding to the selected maximum set association degree, so to determine whether the maximum set association degree is greater than the condition of the sum of the set association degrees of the node set corresponding to the current node before clustering and the node set corresponding to the target adjacent node, wherein, the node set corresponding to the current node only comprises the current node, the node set corresponding to the target adjacent node only comprises the target adjacent node, if the condition is satisfied, taking the reference node set indicated by the maximum set association degree as a node set to which the current node is clustered; and if the condition is not satisfied, taking the node set corresponding to the current node as the node set to which the current node is clustered. And traversing each node, and performing clustering operation on each node to obtain a clustered node set corresponding to each node, so as to obtain a plurality of clustered node sets, wherein the plurality of nodes can correspond to the same clustered node set. Optionally, the node association degree between the current node and each adjacent node may be calculated, and the current node is subjected to clustering operation according to the node association degree corresponding to the current node; calculating the node association degree between the next node and each adjacent node aiming at the next node, and carrying out clustering operation on the next node according to the node association degree of the next node until all nodes are subjected to clustering operation; and traversing all the nodes, calculating the node association degrees between all the nodes and the adjacent nodes, and then sequentially and respectively carrying out clustering operation on all the nodes.

Wherein, the set association degree can be represented by a set modularity degree, and a specific formula can be shown by the following formula (1):

wherein c is any node set of the association degree of the set to be calculated, m is the sum of the weights of all edges, Σ in is the sum of the weights of the edges in the node set c, and Σ tot is the total weight of the incident node set c, that is, the sum of the weights of all edges connected with the nodes in the node set c. If the node i is subjected to clustering operation, and the node set c is a node set of a target adjacent node in a reference node set corresponding to the maximum set association degree, when it is determined whether the maximum set association degree obtained after clustering is greater than the condition that the sum of the set association degrees of the node set corresponding to the node i before clustering and the node set c corresponding to the target adjacent node is greater than the maximum set association degree obtained after clustering, the difference of the set association degrees, that is, the difference of the set modularity can be used for representing, and specifically, the following formula (2) shows:

where m is the sum of the weights of all edges, k_i,inIs the sum of the weights incident into the node set c from the node i, and Σ tot is the total weight of the incident node set c, i.e., the sum of the weights incident into the node set c from the node iSum of weights, k, of all edges connected by nodes within a union c_iIs the sum of the weights of the edges connected to node i.

And taking each clustered node set as a new node, traversing each new node, carrying out clustering operation on each new node, and stopping clustering operation when the set association degree of the clustered node sets obtains the maximum value to obtain a plurality of node sets, wherein each node set comprises at least one new node.

For example, as shown in fig. 5, a schematic diagram of a plurality of user sets obtained by dividing provided by the embodiment of the present application is provided, where 16 nodes are assumed, different nodes are labeled from 0 to 15, so that the distinction is convenient, an edge between two nodes indicates that a sharing relationship exists between users corresponding to the two nodes, and a node association degree (i.e., a weight) of each node and an adjacent node calculated after traversing each node is assumed to be 1; assuming that the knowledge graph among 16 nodes is shown by 501 labels, the weight values are not labeled because the weight of each node and its neighboring nodes is assumed to be 1. Firstly, according to the node association degree corresponding to the current node, namely according to the weight between the current node and the adjacent node thereof, carrying out clustering operation on the current node and each adjacent node thereof, and assuming that the current node is node 0 and the weights between the current node and the

nodes

2, 3, 4 and 5 are all 1, carrying out clustering operation on the node 0 and the

nodes

2, 3, 4 and 5 respectively to obtain a plurality of reference node sets which are respectively a first reference node set {0, 2}, a second reference node set {0, 3}, a third reference node set {0, 4} and a fourth reference node set {0, 5 }.

Calculating the set association degree of each reference node set, and if the set association degree of a second reference node set {0, 2} in the four reference node sets is the maximum set association degree, judging whether the set association degree of the second reference node set {0, 2} is greater than the condition of the sum of the set association degrees of a node set {0} corresponding to the current node before clustering and a node set {2} corresponding to the target adjacent node; if the condition is satisfied, the second reference node set {0, 2} is taken as a node set into which the node 0 is clustered, and if the condition is not satisfied, the node set {0} corresponding to the current node is taken as a node set into which the node 0 is clustered.

Then, clustering operation as shown by the node 0 is carried out on each node to obtain a clustered node set corresponding to each node, and further a plurality of clustered node sets are obtained. Assuming that 4 clustered node sets marked as 502 are obtained at this time, the 4 clustered node sets are respectively used as new nodes, the weight between each new node can be shown as 503, the clustering operation shown as node 0 is repeatedly performed on each new node, and the clustering operation is stopped when the set association degree of the clustered node sets obtains the maximum value, so as to obtain a plurality of node sets, and finally, a plurality of node sets can be shown as 504, wherein one node set comprises node 0, node 1, node 2, node 4, node 5, node 3, node 6 and node 7, and the other node set comprises node 8, node 9, node 10, node 11, node 12, node 13, node 14 and node 15.

In one embodiment, each node of the knowledge-graph may be clustered by setting a label for each node, such that multiple sets of users may be obtained. Specifically, an independent label may be set for each node in the knowledge graph, that is, each node has one label; clustering each node by adopting an iteration mode, namely changing the label of the current node into the label with the maximum occurrence frequency in the adjacent node of the current node every iteration, and randomly changing the label of the current node into one of the labels with the maximum occurrence frequency if the adjacent node comprises a plurality of labels with the maximum occurrence frequency; and stopping iteration until the label of each node is the same as the label with the largest occurrence frequency in the adjacent points. At this time, a plurality of node sets with different labels may be obtained, where nodes in one node set have the same label, and one node set corresponds to one user set.

And S206, acquiring feedback information generated after the target resource link is shared by each user sharing the target resource link.

The feedback information can be used for measuring the propagation effect of the target resource link, and can also be used for determining a target user set when other resource links to be shared are shared from a plurality of user sets, wherein the resource types indicated by the other resource links and the target resource link are the same.

In one embodiment, the feedback information may include one or more of: the total number of times of sharing the target resource link, the total number of users corresponding to other users sharing the target resource link, the total number of users accessing based on the shared target resource link, the total resource transfer amount generated by resource transfer based on the shared target resource link, and the sharing propagation coefficient of the target resource link; the sharing propagation coefficient of the target resource link is used for measuring the propagation speed of the target resource link, and may be, for example, a virus propagation coefficient, and the total resource transfer amount generated by resource transfer based on the shared target resource link may be a Gross transaction Volume (GMV) brought by the shared target resource link in a commodity selling scene. The propagation effect of the target resource link can be measured based on one of the feedback information, and the propagation effect of the target resource link can also be measured in multiple dimensions based on multiple kinds of the feedback information.

In an embodiment, feedback information generated by a user sharing a target resource link after sharing the target resource link may include: the total number of times that the user shares the target resource link, and the total number of users who access the target resource link shared by the user. Optionally, the total resource transfer amount generated by resource transfer based on the shared target resource link may also be included, specifically, the total transaction amount brought by the target resource link shared by the user and the order number brought by the target resource link shared by the user may be included. Optionally, after obtaining feedback information generated after each user sharing the target resource link, the data processing device may display user information of the user, where the user information may include the feedback information generated after each user shares the target resource link, so that the analysis user can know which users have a better propagation effect on the target resource link.

In one embodiment, the data processing device may perform data screening processing on source data of a target resource link to obtain analysis reference data, and the data processing device may obtain feedback information generated by each user sharing the target resource link after sharing the target resource link, both of which are obtained based on the source data of the target resource link; when the data processing device performs data screening processing on the source data linked with the target resource to obtain the analysis reference data, the weight between the two users can be determined according to the sharing relationship between the users corresponding to the two user identifications, or the weight between the two users can be determined according to the sharing relationship between the users corresponding to the two user identifications and the strong relationship or the weak relationship, and at this time, the analysis reference data further comprises the weight between the two users.

As shown in fig. 6, for a schematic diagram of processing source data of a target resource link provided in an embodiment of the present application, as denoted by reference numeral 601, a data processing device may obtain feedback information from the source data of the target resource link, for example, data displayed in a statistical result table of a sharing user is initiated, and relevant information of a user performing a sharing operation on the target resource link, for example, user attributes (displayed as user _ type) may be included, and statistics may be performed on all users, that is, a total number of users corresponding to the target resource link shared to other users may be obtained, and other indexes such as a sharing permeability may be obtained, where the sharing permeability represents a proportion of new users sharing the target resource link among new users accessing the target resource page through the target resource link; for example, data displayed in a user statistical result table brought by sharing corresponds to relevant information of users accessing a target resource page based on a target resource link, and may also include user attributes and the like, and statistics is performed on all the users, so that the total number of the users accessing the target resource page based on the sharing can be obtained, and a virus propagation coefficient can be obtained, wherein the virus propagation coefficient is the number of new users/the number of users initiating sharing brought by sharing, that is, the number of new users in the users accessing the target resource page based on the target resource link/the total number of users corresponding to other users sharing the target resource link; as indicated by reference numeral 602, the data processing apparatus may perform data filtering processing on source data linked to a target resource, to obtain analysis reference data, where the analysis reference data includes a user identifier (shown as id), a weight (shown as weight) between two users, and the like.

Based on the foregoing method embodiment, the present application provides another data processing method, and referring to fig. 7, a schematic flow chart of the another data processing method provided in the present application is provided. The data processing method shown in fig. 7 may be performed by a data processing apparatus. The data processing method shown in fig. 7 may include the steps of:

and S701, responding to a trigger event for analyzing the sharing operation executed by the target resource link, and displaying an analysis setting interface.

S702, acquiring a data identifier of source data of the target resource link from the analysis setting interface, and acquiring an event identifier corresponding to a sharing operation executed on the target resource link.

And S703, acquiring the source data linked with the target resource according to the data identifier.

S704, performing data screening processing on the acquired source data according to the event identifier to obtain analysis reference data of the target resource link.

S705, performing analysis processing on the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets, so as to obtain a plurality of user sets.

And S706, acquiring feedback information generated after the target resource link is shared by each user sharing the target resource link.

Steps S701 to S705 are identical to steps S201 to S205, and are not described herein again.

In an embodiment, after obtaining feedback information generated by each user sharing a target resource link, the data processing device may determine, according to the feedback information, a target user set when sharing other resource links to be shared from a plurality of user sets, where resource types indicated by the other resource links and the target resource link are the same.

In one embodiment, the user with the best feedback information may be determined as the target user, and the set of users where the target user is located may be determined as the target user set. In a specific implementation, the data processing device may determine, from a plurality of user identifiers of the analysis reference data, a sharing user identifier that performs a sharing operation on the target resource link according to a sharing relationship between users, where a user indicated by the sharing user identifier is a user that shares the target resource link; then determining feedback information generated after the user indicated by each sharing user identification shares the target resource link, and determining target feedback information from the feedback information of the user indicated by each sharing user identification; and determining a target user indicated by the user identification corresponding to the target feedback information, and taking the user set where the target user is located as a target user set. The target feedback information may include one or more of the following: the method comprises the steps of sharing a target resource link for the maximum times, sharing the target resource link to the maximum user sum corresponding to other users, accessing the target resource link based on the shared target resource link, obtaining the corresponding highest resource transfer sum based on the shared target resource link, and obtaining the maximum sharing propagation coefficient of the target resource link. The target user may be determined based on one of the above target feedback information, or may be determined based on a plurality of target feedback information.

For example, if in an event that only publicity is desired, only the maximum total number of users accessing the target resource link shared by the users corresponding to each sharing user identifier may be concerned, that is, the maximum number of users accessing the target resource link shared by the users corresponding to different sharing user identifiers is concerned; however, if the commodity selling activity is in progress, the value of the highest total resource transfer amount corresponding to the resource acquisition based on the shared target resource link may need to be paid attention at the same time. For example, if the maximum total number of users accessing based on the target resource link shared by the user a is 50, the maximum total number of users accessing based on the target resource link shared by the user B is 35, and the maximum total number of users accessing based on the target resource link shared by the user C is 15, the user set corresponding to the user a is determined as the target user set.

In one embodiment, feedback information generated by users included in each user set may be counted to obtain set feedback information, and a user set with the best set feedback information is determined as the target user set. In specific implementation, set feedback information generated after the target resource link is shared by each user set can be determined according to feedback information generated after the target resource link is shared by each user sharing the target resource link; and determining target set feedback information from the set feedback information corresponding to each user set, and taking the user set corresponding to the target set feedback information as a target user set. For example, if the set feedback information of the user set 1 is higher than the user set 2 and higher than the user set 3, the user set 1 is determined as the target user set.

In an embodiment, feedback information generated by each user sharing the target resource link after sharing the target resource link may be obtained, and statistics may be performed on the feedback information, so that the feedback information of the target resource link may be obtained, and then the feedback information of the target resource link may be displayed in the data processing device. Optionally, feedback information generated after the user sharing the target resource link and time information for generating the feedback information may be acquired, the feedback information may be counted at different time nodes according to the time information, feedback information of the target resource link at different time nodes may be acquired, and the feedback information may be displayed in the data processing device. As shown in fig. 8a, a schematic diagram of change of feedback information of a target resource link with time provided in the embodiment of the present application is an interface when a sharing history overview in an analysis billboard interface is selected, where the target resource link is specifically a commodity page link of a certain target commodity, where the feedback information includes: the total number of times of sharing the target resource link (shown as the cumulative number of times of sharing in fig. 8 a), the total number of users who share the target resource link to other users (shown as the cumulative number of users sharing in fig. 8 a), the total number of users who visit based on the shared target resource link (shown as the cumulative number of users brought by sharing forwarding in fig. 8 a), the total amount of resource transfer generated by resource transfer based on the shared target resource link (shown as the cumulative GMV brought by sharing in fig. 8 a), and the sharing propagation coefficient of the target resource link (shown as the sharing virus coefficient K in fig. 8 a), optionally, as shown in fig. 8a, in the schematic diagram of the time variation of the feedback information of the target resource link, other parameters for measuring the propagation effect, such as the share permeability, are also included.

In one embodiment, the source data of the multiple comparison resource links may be analyzed to obtain feedback information of the multiple comparison resource links, and the feedback information of the target resource link is compared with the feedback information of the multiple comparison resource links, so that the resource link with the best feedback information may be obtained. For example, as shown in fig. 8b, in a comparison graph of feedback information linked by different resources provided in the embodiment of the present application, it is assumed that an analysis user wants to analyze the propagation conditions of commodities in the same activity interface, so as to know which commodities have good propagation conditions and which commodities have poor propagation conditions, and what types of commodities a user prefers, so that in a next activity, the commodities a user does not like can be used for the activity, but the commodities a user likes can be selected, so as to improve the effect of the activity, and it is assumed that the activity interface shown as 801 includes the links of the commodities a, b, and c, so as to know the propagation conditions of the commodities by analyzing the propagation effects of the links of the commodities a, b, and c, and it is assumed that the number of shared accumulated users of the commodities a, b, and c is 354 respectively as shown as 802, as the number of shared accumulated users of the commodities a, b, and c is respectively, 35. 651, respectively; the cumulative number of shares for commodity a, commodity b and commodity c is 443, 38 and 919 respectively; the number of accumulated users brought by the sharing and forwarding of the commodity a, the commodity b and the commodity c is 1438, 84 and 3211 respectively; the cumulative GMVs of the shared bands of the product a, the product b, and the product c are 2442243, 111748, and 1565108, respectively, and the shared virus coefficients k of the product a, the product b, and the product c are 4, 2.4, and 4.9, respectively, so that it is known that the propagation effect of the product c is the best.

And S707, responding to the query triggering operation of the user set, and displaying the acquired set information of each user set in a set query interface.

Wherein the set query interface includes set information for each set of users, any set information including one or more of: the set identifier, the total number of times of sharing the target resource link by any set, and the total amount of resource transfer generated by sharing the target resource link by any set.

In one embodiment, a data processing apparatus displays a set query interface in response to analyzing a user's query trigger operation on a set of users. In particular, when a share fission analysis in an analysis kanban interface is selected, a set query interface may be displayed. As shown in fig. 9, an interface diagram of a set query interface provided for an embodiment of the present application is a set query interface, where the set query interface includes an analysis screening area marked as 901, a user set screening area marked as 902, a download component marked as 903, and a set information display area marked as 904, where users in the analysis screening area screen sharing channels of target resource links, user attributes, query date ranges, content types, content identifiers, and the like, for example, the sharing channels may be a wechat applet or a web page (H5 page), the user attributes may screen indexes of a new visiting user, an old visiting user, a new client, an old client, and the like (where the old client and the new client may be displayed as an old client and a new client in the page), the content type is the sharing type shown in fig. 9, and may be used for screening types of target resource links, for example, the type of a commodity, a website, and a website Store type, etc.; the user set screening area labeled 902 may screen the user set according to the number of users in the user set (shown as top community in fig. 9), and the download component labeled 903 may be used to download the user identifications of the users included in the user set displayed in the set information display area labeled 904, the set information display area labeled 904 displaying the information of the user set under the screening condition of the user set screening area, for example, the set information of the user set 5 before the number of users is screened.

The set information may include a set identifier, total sharing times (shown as set accumulated sharing times) of the set to the target resource link, and a total resource transfer amount generated by sharing of the set to the target resource link, where the total resource transfer amount may be a set accumulated transaction amount; optionally, the set information display area may further display information such as the number of set users, the number of shared times of the set users, the number of accumulated trades of the set, the number of trades of the set users, and the amount of trades of the set users. It can be known that the user set with the user set identifier 301 includes the largest number of users, the set accumulated amount of the user set with the user set identifier 210 is the highest, and the average amount of the user set is the highest, so the user set with the user set identifier 210 is the high-conversion head user set. Optionally, the set query interface may further include a selection identifier for querying a user included in any user set, where the selection identifier may be displayed as "view details" in fig. 9 as indicated by reference numeral 905, and the selection identifier is used to trigger display of user information of a user set associated with the selection identifier. In one embodiment, if the set query interface further includes a selection identifier for querying a user included in any user set, when the target selection identifier is triggered, user information of each user included in a target user set associated with the target selection identifier is displayed, and a key propagation user in the target user set is determined according to the user information of each user, where the user information includes one or more of the following: and the user identification of the corresponding user and feedback information generated after the target resource link is shared.

In a specific implementation, as shown in fig. 10a, for a schematic diagram for triggering display of user information of a target user set provided in this embodiment of the application, if a selected set is accumulated to a user set with a highest transaction amount, that is, a selection identifier corresponding to a user set identified as 210 by the user set, user information of a user included in the user set identified as 210 by the user set may be displayed in a user information display area marked as 1001, at this time, the interface further includes a user screening area marked as 1002, a return component marked as 1003, a download component marked as 1004, and a sharing relationship display area marked as 1005, where the user screening area marked as 1002 may screen users according to feedback information of different users, and specifically, the total number of users that can be accessed based on a target resource link in the feedback information may be screened, that is, users who have access to users ranked a few before can be screened, the return component shown by the reference numeral 1003 can return the set query interface on which the set information is displayed, the download component shown by the reference numeral 1004 can be used for downloading user identifiers of users included in the user set, the sharing relationship display area shown by the reference numeral 1005 displays sharing relationship information between users included in the user set, each dot represents one user identifier, that is, corresponds to one user, a connecting line between two dots represents that a sharing relationship exists between users corresponding to the two user identifiers, and the sharing relationship corresponding to the user identifier can be displayed by triggering the dots.

The user information shown in fig. 10a includes: the user identifier of the user shares feedback information generated after the target resource is linked, where the feedback information may specifically include: the total number of times of sharing the target resource link (shown as the number of times of sharing in fig. 10 a), the total number of users accessing based on the shared target resource link (shown as bringing accessing users in fig. 10 a), and the total amount of resource transfer generated by resource transfer based on the shared target resource link, where the total amount of resource transfer may include the number of orders brought based on the shared target resource link (shown as bringing order amount and bringing new orders in fig. 10 a); optionally, the user information may further include a user nickname, a first access user, a number of user purchases, a user transaction amount, and the like. If the information of the user with the access user number of 100 before ranking is screened, and the information display area marked by 1001 exemplarily displays the information of the user with the top ranking 5, it can be known that the user with the user identification of 4464357 brings the most access users, brings the most orders, brings the most new orders, and determines that the user with the user identification of 4464357 is the key propagation user. As shown in fig. 10b, for the schematic diagram that shows the sharing relationship of the target user identifier in the sharing relationship display area according to the embodiment of the present application, as shown by reference numeral 1011, the sharing relationship when the dot with the target user identifier of 4464357 is triggered is shown, and as shown by reference numeral 1012, the sharing relationship when the dot with the target user identifier of 4499782 is triggered is shown.

Optionally, a key propagation user set may be established for a plurality of key propagation users determined from a plurality of user sets, and then other resources to be shared may be shared to the plurality of key propagation users by linking, and the key propagation users are used to share again, so that the propagation effect may be greatly improved. Optionally, if there is a user set with data exception or a key propagation user with data exception in the obtained plurality of user sets, the user set with data exception or the key propagation user with data exception may be processed, for example, to perform processing such as banning words, seal numbers, and the like. For example, if the data abnormality of the key propagation user of one user set is found, the user set can be determined as the user set with the data abnormality, and a plurality of users with the data abnormality closely related to the key propagation user of the data abnormality can be easily processed by processing the user set with the data abnormality, so that the situation that the user set is a wool cluster or a black cluster can be easily attacked.

In one embodiment, the selection operation of the downloading component is detected, and the user identification of the user included in the target user set is downloaded to obtain a target identification set; the data processing equipment responds to the display triggering operation of an analysis user for user management analysis, and displays a user management interface, wherein the user management interface comprises a user identification adding component; detecting the selection operation of a user identifier adding component, importing a target identifier set, and displaying an analysis component for carrying out user portrait analysis on users corresponding to user identifiers in the target identifier set; and when the analysis component is selected, performing user portrait analysis on the user corresponding to the user identification included in the target identification set, and displaying a corresponding user portrait analysis result.

In a specific implementation, as shown in fig. 11a, a schematic diagram of importing a target identifier set provided in an embodiment of the present application is shown, where a displayed user management interface is shown as a reference 1101, and a user identifier adding component is shown as a reference 1102 (specifically, a "create crowd" component is displayed in the user management interface), where the user management interface corresponds to an interface displayed when the "user housekeeping" component is selected, that is, a display trigger operation of the data processing device in response to an analysis user for user management analysis is equivalent to a selection operation of the data processing device in response to the "user housekeeping" component; when the selection operation of the user identifier adding component is detected, a prompt window for adding the user identifier is displayed in the user management interface, the prompt window can be marked as 1103, and specifically, an entry for adding the user identifier is specifically displayed as a local ID list; if the entry for adding the user identifier is selected, a user identifier adding interface shown in 1111 is displayed, a target identifier set downloaded to a local storage may be selected through a user identifier uploading component shown by 1112 label, and a type of the user identifier in the target identifier set may be selected through a Universal Internet Number (UIN) type selection area shown in 1113, for example, a mobile phone Number, a service account Number, and the like, and a set identifier of the target identifier set may be added through an information adding area shown in 1114, for example, a set name, and the like, and a target identifier set is imported by clicking an identifier importing component shown in 1115, wherein (the identifier importing component may be displayed as a "generate crowd" component).

If the target identification set is imported, displaying a set identification of the target identification set on a user management interface, and displaying an analysis component for carrying out user portrait analysis on users corresponding to user identifications in the target identification set; and when the analysis component is selected, performing user portrait analysis on the user corresponding to the user identification included in the target identification set, and displaying a corresponding user portrait analysis result. As shown in fig. 11b, a schematic diagram for triggering user portrait analysis on a user corresponding to a target identifier set provided in the embodiment of the present application is, as indicated by a label 1121, a user management interface on which a set identifier of the target identifier set is displayed, if the set identifier of the target identifier set is set as the set 210, the set 210 is displayed on the user management interface, and an analysis component may be specifically displayed as a "portrait" component, as indicated by a label 1122; if the analysis component corresponding to the target identifier set is triggered, user portrait analysis is performed on the user corresponding to the user identifier included in the target identifier set, and a user portrait analysis result shown as a mark 1131 is displayed, where the user portrait analysis result may display an analysis result of age distribution, gender distribution, urban distribution, industry distribution, and state distribution of the user corresponding to the target identifier set, where the state distribution identifies what life state the user is in, such as a marital status. The user profile analysis results, indicated by reference numeral 1131, may result in the user ages of set 210 being concentrated between 20-35, giving priority to two-three-four line urban users. Optionally, the same user representation analysis may be performed on an identification set corresponding to the user identification of the user included in the plurality of user sets, so as to compare the user representations of different user sets.

In the embodiment of the application, after the data processing device acquires feedback information generated after each user sharing the target resource link shares the target resource link, a target user set when other resource links to be shared are shared can be determined from a plurality of user sets according to the feedback information, wherein the resource types indicated by the other resource links and the target resource link are the same, and the rapid propagation of the other resource links to be shared in the target user set is facilitated; the set information of the plurality of user sets obtained through division can be displayed, the user information of the target user set can be displayed, the user portrait analysis can be performed on the users included in the target user set, the key propagation users of the target user set can be determined, the propagation condition of the target resource link can be perfectly analyzed, the key propagation users can be used for rapidly propagating other resource links to be shared, and the propagation efficiency is improved.

Based on the above data processing method embodiment, the present application provides a data processing apparatus. Referring to fig. 12, for a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application, the data processing apparatus 120 may include a display unit 1201, an obtaining unit 1202, and a processing unit 1203. The data processing apparatus 120 shown in fig. 12 may operate as follows:

the display unit 1201 is configured to display an analysis setting interface in response to a trigger event for analyzing a sharing operation performed on a target resource link;

an obtaining unit 1202, configured to obtain, from the analysis setting interface, a data identifier of source data of the target resource link and an event identifier corresponding to a sharing operation executed by the target resource link;

the obtaining unit 1202 is further configured to obtain source data linked to the target resource according to the data identifier;

a processing unit 1203, configured to perform data screening processing on the obtained source data according to the event identifier, to obtain analysis reference data of the target resource link, where the analysis reference data records multiple user identifiers and a sharing relationship between different users with respect to the target resource link;

the processing unit 1203 is further configured to perform analysis processing on the analysis reference data, so as to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets, so as to obtain multiple user sets;

the obtaining unit 1202 is further configured to obtain feedback information generated after each user sharing the target resource link shares the target resource link, where the feedback information is used to determine, from the multiple user sets, a target user set when sharing other resource links to be shared, where resource types indicated by the other resource links are the same as resource types indicated by the target resource link.

In one embodiment, the analysis reference data is a knowledge graph constructed by using a plurality of nodes, the knowledge graph comprises a node for recording a user identifier, and an edge of the knowledge graph is used for indicating a sharing relationship between users corresponding to the corresponding user identifiers; the processing unit 1203 analyzes and processes the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets, so as to obtain a plurality of user sets, and specifically executes the following operations:

traversing each node in the knowledge graph, determining at least one adjacent node of the traversed current node, and calculating the node association degree between the current node and each adjacent node;

performing clustering operation on each node in the knowledge graph according to the node association degree, and stopping performing clustering operation on the knowledge graph when the set association degree of the node set obtained by clustering obtains the maximum value to obtain a plurality of node sets;

the node set is used for indicating a user set, and the user identifier recorded by each node in the node set is the user identifier corresponding to the user in the corresponding user set.

In an embodiment, when performing clustering operation on each node in the knowledge graph according to the node association degree, the processing unit 1203 specifically performs the following operations:

clustering operation is carried out on the current node and any adjacent node to obtain a plurality of reference node sets and a set association degree corresponding to each reference node set;

and selecting the maximum set association degree from the set association degrees corresponding to each reference node set, and taking the reference node set indicated by the maximum set association degree as the node set to which the current node is clustered.

In one embodiment, the processing unit 1203 is further configured to:

according to the sharing relationship, a sharing user identifier which executes sharing operation on the target resource link is determined from a plurality of user identifiers of the analysis reference data, and a user indicated by the sharing user identifier is a user sharing the target resource link;

determining feedback information generated after the users indicated by each sharing user identification share the target resource link, and determining target feedback information from the feedback information of the users indicated by each sharing user identification;

and determining a target user indicated by the user identification corresponding to the target feedback information, and taking a user set where the target user is located as a target user set.

In one embodiment, the processing unit 1203 is further configured to:

according to feedback information generated after each user sharing the target resource link, determining set feedback information generated after each user sets share the target resource link;

and determining target set feedback information from the set feedback information corresponding to each user set, and taking the user set corresponding to the target set feedback information as a target user set.

In one embodiment, the feedback information includes one or more of: the total number of times of sharing the target resource link, the total number of users corresponding to other users who share the target resource link, the total number of users who visit based on the shared target resource link, the total amount of resource transfer generated by resource transfer based on the shared target resource link, and the sharing propagation coefficient of the target resource link;

the target feedback information includes one or more of: the maximum number of times of sharing the target resource link, the maximum user total number corresponding to the target resource link shared by other users, the maximum user total number accessed based on the shared target resource link, the maximum resource transfer total number corresponding to resource acquisition based on the shared target resource link, and the maximum sharing propagation coefficient of the target resource link.

In one embodiment, the display unit 1201 is further configured to:

responding to query trigger operation of the user sets, and displaying the obtained set information of each user set in a set query interface;

In one embodiment, the set query interface further comprises a selection identifier for querying the users included in any user set;

the display unit 1201 is further configured to display, when a target selection identifier is triggered, user information of each user included in a target user set associated with the target selection identifier, where the user information includes one or more of: user identifications of corresponding users and feedback information generated after the target resource link is shared;

the processing unit 1203 is further configured to determine a key propagation user in the target user set according to the user information of each user.

In one embodiment, the collection query interface further comprises a download component;

the processing unit 1203 is further configured to detect a selection operation on the download component, and download the user identifier of the user included in the target user set to obtain a target identifier set;

the display unit 1201 is further configured to display a user management interface in response to a display trigger operation for user management analysis, where the user management interface includes a user identifier addition component;

the processing unit 1203 is further configured to detect a selection operation of the user identifier adding component, import the target identifier set, and display an analysis component for performing user portrait analysis on a user corresponding to each user identifier in the target identifier set;

the processing unit 1203 is further configured to, when the analysis component is selected, perform user portrait analysis on a user corresponding to the user identifier included in the target identifier set, and the display unit 1201 is further configured to display a corresponding user portrait analysis result.

According to an embodiment of the present application, the steps involved in the data processing methods shown in fig. 2 and fig. 7 may be performed by units in the data processing apparatus 120 shown in fig. 12. For example, step S201 shown in fig. 2 may be performed by the display unit 1201 in the data processing apparatus 120 shown in fig. 12, steps S202 to S203 and S206 may be performed by the acquisition unit 1202 in the data processing apparatus 120 shown in fig. 12, and steps S204 to S205 may be performed by the processing unit 1203 in the data processing apparatus 120 shown in fig. 12; for another example, steps S701 and S707 shown in fig. 7 may be executed by the display unit 1201 in the data processing apparatus 120 shown in fig. 12, steps S702 to S703 and S706 may be executed by the acquisition unit 1202 in the data processing apparatus 120 shown in fig. 12, and steps S704 to S705 may be executed by the processing unit 1203 in the data processing apparatus 120 shown in fig. 12.

According to another embodiment of the present application, the units in the data processing apparatus 120 shown in fig. 12 may be respectively or entirely combined into one or several other units to form one or several other units, or some unit(s) may be further split into multiple functionally smaller units to form one or several other units, which may achieve the same operation without affecting the achievement of the technical effect of the embodiment of the present application. The units are divided based on logic functions, and in practical application, the functions of one unit can be realized by a plurality of units, or the functions of a plurality of units can be realized by one unit. In other embodiments of the present application, the data processing apparatus 120 divided based on logical functions may also include other units, and in practical applications, the functions may also be implemented by being assisted by other units, and may be implemented by cooperation of a plurality of units.

According to another embodiment of the present application, the data processing apparatus 120 shown in fig. 12 may be constructed by running a computer program (including program codes) capable of executing the steps involved in the respective methods shown in fig. 2 and fig. 7 on a general-purpose computing device such as a computer including a processing element such as a Central Processing Unit (CPU), a random access storage medium (RAM), a read-only storage medium (ROM), and a storage element, and implementing the data processing method of the embodiment of the present application. The computer program may be embodied on a computer-readable storage medium, for example, and loaded into and executed by the above-described computing apparatus via the computer-readable storage medium.

In this embodiment of the application, the data processing apparatus 120 first obtains, on the analysis setting interface, a data identifier of source data of a target resource link, and an event identifier corresponding to a sharing operation performed on the target resource link; then, source data of the target resource link are obtained according to the data identification, data screening processing is carried out on the obtained source data according to the event identification, and analysis reference data of the target resource link are obtained, wherein the analysis reference data records a plurality of user identifications and sharing relations of different users about the target resource link; further, the data processing device 120 performs analysis processing on the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets, so as to obtain a plurality of user sets; then, the data processing apparatus 120 may obtain feedback information generated after each user sharing the target resource link shares the target resource link, where the feedback information is used to determine, from the multiple user sets, a target user set when sharing other resource links to be shared, where resource types indicated by the other resource links and the target resource link are the same; the analysis reference data of the target resource link can be further obtained by obtaining the source data of the target resource link, and the analysis reference data comprises a plurality of user identifications and sharing relations among different users about the target resource link; dividing users corresponding to the user identifications recorded in the analysis reference data according to the analysis reference data to obtain a plurality of user sets; finally, feedback information of the target resource link can be acquired, so that a user can know the propagation condition of the target resource link conveniently; meanwhile, the target user set can be obtained from the plurality of user sets based on the feedback information, so that other resource links of the same type needing to be quickly propagated can be quickly propagated through the target user set, and a good propaganda effect is achieved.

Based on the method embodiment and the device embodiment, the application also provides a data processing device. Fig. 13 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application. The data processing apparatus 130 shown in fig. 13 may include at least a processor 1301, an input interface 1302, an output interface 1303, and a computer storage medium 1304. The processor 1301, the input interface 1302, the output interface 1303, and the computer storage medium 1304 may be connected by a bus or other means.

A computer storage medium 1304 may be stored in the memory 1305 of the data processing device 130, the computer storage medium 1304 being for storing a computer program comprising program instructions, the processor 1301 being for executing the program instructions stored by the computer storage medium 1304. The processor 1301 (or CPU) is a computing core and a control core of the data Processing apparatus 130, and is adapted to implement one or more instructions, and specifically, adapted to load and execute the one or more instructions so as to implement the data Processing method flow or the corresponding functions.

An embodiment of the present application further provides a computer storage medium (Memory), which is a Memory device in the data processing device 130 and is used for storing programs and data. It is understood that the computer storage medium herein may include a built-in storage medium in the terminal, and may also include an extended storage medium supported by the terminal. The computer storage medium provides a storage space that stores an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), suitable for loading and execution by processor 1301. The computer storage medium may be a Random Access Memory (RAM) memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory; and optionally at least one computer storage medium located remotely from the processor.

In one embodiment, one or more instructions stored in a computer storage medium may be loaded and executed by the processor 1301 to implement the corresponding steps of the method in the data processing method embodiment described above with respect to fig. 2 and 7, and in particular, the one or more instructions stored in the computer storage medium may be loaded and executed by the processor 1301 to implement the following steps:

In one embodiment, the analysis reference data is a knowledge graph constructed by using a plurality of nodes, the knowledge graph comprises a node for recording a user identifier, and an edge of the knowledge graph is used for indicating a sharing relationship between users corresponding to the corresponding user identifiers; the processor 1301 performs analysis processing on the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets, and specifically performs the following operations when obtaining a plurality of user sets:

In an embodiment, when performing clustering operation on each node in the knowledge graph according to the node association degree, the processing unit 1301 specifically performs the following operations:

In one embodiment, the processor 1301 is further configured to:

In one embodiment, the set query interface further comprises a selection identifier for querying the users included in any user set; the processor 1301 is further configured to:

when a target selection identifier is triggered, displaying user information of each user included in a target user set associated with the target selection identifier, the user information including one or more of: user identifications of corresponding users and feedback information generated after the target resource link is shared;

and determining key propagation users in the target user set according to the user information of each user.

In one embodiment, the collection query interface further comprises a download component; the processor 1301 is further configured to:

detecting the selection operation of the downloading component, and downloading the user identification of the user in the target user set to obtain a target identification set;

in response to a display trigger operation for user management analysis, displaying a user management interface, the user management interface including a user identification addition component;

detecting the selection operation of the user identifier adding component, importing the target identifier set, and displaying an analysis component for carrying out user portrait analysis on the user corresponding to each user identifier in the target identifier set;

and when the analysis component is selected, performing user portrait analysis on a user corresponding to the user identification included in the target identification set, and displaying a corresponding user portrait analysis result.

Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method embodiments as shown in fig. 2 or fig. 7. The computer-readable storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A data processing method, comprising:

2. The method according to claim 1, wherein the analysis reference data is a knowledge graph constructed by using a plurality of nodes, the knowledge graph comprises one node for recording one user identifier, and the knowledge graph comprises edges for indicating a sharing relationship between users corresponding to the respective user identifiers; the analyzing the analysis reference data to divide users corresponding to the user identifiers recorded in the analysis reference data into different user sets to obtain a plurality of user sets, including:

3. The method according to claim 2, wherein the clustering operation on each node in the knowledge graph according to the node association degree comprises:

4. The method of claim 1, further comprising:

5. The method of claim 1, further comprising:

6. The method of claim 4, wherein the feedback information comprises one or more of: the total number of times of sharing the target resource link, the total number of users corresponding to other users who share the target resource link, the total number of users who visit based on the shared target resource link, the total amount of resource transfer generated by resource transfer based on the shared target resource link, and the sharing propagation coefficient of the target resource link;

7. The method of claim 1, further comprising:

8. The method of claim 7, wherein the set query interface further comprises a selection identifier for querying the user included in any user set; the method further comprises the following steps:

9. The method of claim 7, wherein the collection query interface further comprises a download component; the method further comprises the following steps:

10. A computer storage medium having computer program instructions stored therein, which when executed by a processor, are adapted to perform a data processing method according to any one of claims 1-9.