CN116541760A - User grouping processing method, electronic device and computer readable storage medium - Google Patents

User grouping processing method, electronic device and computer readable storage medium Download PDF

Info

Publication number
CN116541760A
CN116541760A CN202310504582.6A CN202310504582A CN116541760A CN 116541760 A CN116541760 A CN 116541760A CN 202310504582 A CN202310504582 A CN 202310504582A CN 116541760 A CN116541760 A CN 116541760A
Authority
CN
China
Prior art keywords
grouping
rule
user
intelligent
label
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310504582.6A
Other languages
Chinese (zh)
Inventor
谢成亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Music Entertainment Technology Shenzhen Co Ltd
Original Assignee
Tencent Music Entertainment Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Music Entertainment Technology Shenzhen Co Ltd filed Critical Tencent Music Entertainment Technology Shenzhen Co Ltd
Priority to CN202310504582.6A priority Critical patent/CN116541760A/en
Publication of CN116541760A publication Critical patent/CN116541760A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides a user grouping processing method, electronic equipment and a computer readable storage medium, wherein the user grouping processing method comprises the following steps: receiving a user grouping request message from a client, wherein the user grouping request message comprises at least one grouping description information; extracting information from at least one group description information to obtain at least one user tag; generating an intelligent rule format based on at least one user tag and a preset grouping rule relation; filtering a plurality of users to be clustered based on an intelligent rule format to obtain a clustered result, wherein the clustered result comprises a first clustered result, and one or more users to be clustered in the first clustered result meet a preset clustered rule relation; and sending a user grouping request response message to the client, wherein the user grouping request response message comprises a grouping result. The embodiment of the application can directly obtain the grouping result through the intelligent rule format, thereby improving the efficiency of obtaining the target user group.

Description

User grouping processing method, electronic device and computer readable storage medium
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a user grouping processing method, an electronic device, and a computer readable storage medium.
Background
User portrayal: the user portraits (Persona), also called user models, are proposed by alaan cooper, and are a method for depicting target users in marketing planning or business design, so that a planner can conveniently analyze and set strategies developed by the planner aiming at different user types by using the user portraits. The user representation is a virtual representation of a real user, is a user model built on top of a series of real data, and includes a plurality of labels.
Currently, in business decisions, it is necessary to specify the target user population through user portraits. In making a recommendation for goods or services, a particular user group may be selected based on the user representation to recommend goods or services to the user group. In the method, the target user group needs to be acquired and processed, and the process of acquiring the target user group is complex, so that the efficiency of acquiring the target user group is low.
Therefore, how to improve the efficiency of obtaining the target user group is a urgent problem to be solved.
Disclosure of Invention
In view of the above technical problems, the present application provides a user grouping processing method, an electronic device, and a computer readable storage medium, which can improve the efficiency of obtaining a target user group.
In one aspect, an embodiment of the present application provides a user grouping processing method, where the method includes: receiving a user grouping request message from a client, wherein the user grouping request message comprises at least one grouping description information; extracting information from at least one group description information to obtain at least one user tag; generating an intelligent rule format based on at least one user tag and a preset grouping rule relation; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logic operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between the labels and the label values; filtering a plurality of users to be clustered based on an intelligent rule format to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation; and sending a user grouping request response message to the client, wherein the user grouping request response message comprises the grouping result.
In an alternative embodiment, the method further comprises: acquiring recommended content to be displayed in a content recommendation interface based on the grouping result; when a content recommendation interface is displayed through a content platform, corresponding interaction controls are respectively generated based on a plurality of characteristic dimensions, the characteristic dimensions are related to the type of recommended content provided by the content platform and user preference, the characteristic dimensions respectively have display weights which influence the display sequence of the recommended content in the content recommendation interface, and the interaction controls are used for adjusting the weight influence degree of the display weights; updating the display weights of the plurality of feature dimensions in response to a weight adjustment operation of the display weights based on the interaction control; and rearranging the display positions of the recommended contents in the content recommendation interface according to the updated display weights.
In an alternative embodiment, the grouping result further includes a second grouping result, and none of one or more users to be grouped in the second grouping result satisfies a preset grouping rule relationship.
In an alternative embodiment, filtering a plurality of users to be clustered based on an intelligent rule format to obtain a clustered result, including: acquiring user marks of a plurality of users to be grouped and intelligent rule format marks for grouping the plurality of users to be grouped; based on the intelligent rule format label, acquiring an intelligent rule format corresponding to the intelligent rule format label; acquiring grouping rules based on intelligent rule formats corresponding to the intelligent rule format labels; acquiring labels of each user to be grouped based on user labels of a plurality of users to be grouped; and filtering the plurality of users to be clustered based on the clustering rules and the labels of each user to be clustered to obtain a clustering result.
In an alternative embodiment, the obtaining the grouping rule based on the intelligent rule format corresponding to the intelligent rule format label includes: based on the intelligent rule format corresponding to the intelligent rule format label, acquiring a label corresponding to the sub rule and metadata of the label, wherein the metadata of the label is used for indicating the position of a label value of the label; acquiring a tag value of the tag based on the metadata of the tag; and acquiring a preset grouping rule relation based on the intelligent rule format, the label and the label value of the label corresponding to the intelligent rule format label.
In an alternative embodiment, after generating the intelligent rule format based on at least one user tag and the preset grouping rule relationship, the method further includes: and storing the intelligent rule format and generating an intelligent rule format label corresponding to the intelligent rule format.
In an alternative embodiment, before storing the intelligent rule format and generating the intelligent rule format label corresponding to the intelligent rule format, the method further includes: based on a plurality of sub-rules in the intelligent rule format, the labels and the label values corresponding to the intelligent rule format are obtained and stored respectively.
In one aspect, an embodiment of the present application provides a user grouping processing method, where the method includes: transmitting a user grouping request message to a server, wherein the user grouping request message comprises at least one grouping description information; receiving a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more users to be grouped in the first grouping result meet a preset grouping rule relation, or the grouping result also comprises a second grouping result, and one or more users to be grouped in the second grouping result do not meet the preset grouping rule relation.
In one aspect, an embodiment of the present application provides a user grouping processing method, where the method includes: a user grouping request message is sent to a server, wherein the user grouping request message comprises user marks of a plurality of users to be grouped and grouping rule marks for grouping the plurality of users to be grouped; receiving a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more users to be grouped in the first grouping result meet the grouping rule, or the grouping result also comprises a second grouping result, and one or more users to be grouped in the second grouping result do not meet the grouping rule.
In one aspect, an embodiment of the present application provides a user grouping processing apparatus, where the apparatus includes:
the receiving module is used for receiving a user grouping request message from the client, wherein the user grouping request message comprises at least one grouping description information;
the processing module is used for extracting information of at least one grouping description information to obtain at least one user tag;
the processing module is also used for generating an intelligent rule format based on at least one user tag and a preset grouping rule relation; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logic operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between the labels and the label values;
The processing module is also used for filtering the plurality of users to be clustered based on the intelligent rule format to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation;
and the sending module is used for sending a user grouping request response message to the client, wherein the user grouping request response message comprises a grouping result.
In one aspect, an embodiment of the present application provides a user grouping processing apparatus, including:
the system comprises a sending module, a server and a receiving module, wherein the sending module is used for sending a user grouping request message to the server, and the user grouping request message comprises at least one grouping description information;
the receiving module is used for receiving a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more users to be grouped in the first grouping result meet a preset grouping rule relation, or the grouping result also comprises a second grouping result, and one or more users to be grouped in the second grouping result do not meet the preset grouping rule relation.
In one aspect, an embodiment of the present application provides an electronic device, including: the device comprises a processor, a user interface, a communication interface and a memory, wherein the processor, the user interface, the communication interface and the memory are connected with each other, the memory stores executable program codes, and the processor is used for calling the executable program codes and executing the method provided by the embodiment of the application.
Accordingly, the embodiment of the application further provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and the computer program includes program instructions, and when the program instructions are executed by a processor, the method provided by the embodiment of the application is implemented.
Accordingly, embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the method provided by the embodiment of the application.
In the embodiment of the application, a user grouping request message from a client is received, wherein the user grouping request message comprises at least one grouping description information; extracting information from at least one group description information to obtain at least one user tag; generating an intelligent rule format based on at least one user tag and a preset grouping rule relation; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logic operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between the labels and the label values; filtering a plurality of users to be clustered based on an intelligent rule format to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation; and sending a user grouping request response message to the client, wherein the user grouping request response message comprises the grouping result. In the method, various logic relations among a plurality of sub-rules in the intelligent rule format can be identified and calculated, and the grouping result is directly obtained by utilizing the intelligent rule format, so that the process of obtaining user groups corresponding to a plurality of rules and processing the user groups corresponding to the rules is avoided, and further, the efficiency of obtaining target user groups is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical methods in the prior art, the drawings that are required in the embodiments or the prior art description will be briefly described, it will be apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
Fig. 1 is a schematic structural diagram of a user grouping processing method system according to an embodiment of the present application;
fig. 2 is a flow chart of a user grouping processing method provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a grouping rule creation interface according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a tag search according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an operator selection provided in an embodiment of the present application;
FIG. 6 is a schematic diagram of a logical relationship selection provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of a smart rule format storage form provided in an embodiment of the present application;
fig. 8 is a schematic diagram of a user grouping process according to an embodiment of the present application;
FIG. 9 is a schematic diagram of another user grouping process according to an embodiment of the present application;
FIG. 10 is a schematic diagram of a user grouping device according to an embodiment of the present disclosure;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical methods in the embodiments of the present application will be clearly and fully described in the following description with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a user grouping processing method system provided in an embodiment of the present application, and as shown in fig. 1, the user grouping processing method system includes an operation end, a client and a server (a star painting management platform, an internal memory, an external real-time data service interface and star painting online service (unified online grouping service and unified portrait query service)), where the operation end, the client and the server are connected through a network. The operation end is used for making and reporting the intelligent rule format to a star painting management platform in the server, and the star painting management platform is used for analyzing and storing the intelligent rule format received from the operation end (namely meta information and rule storage), wherein the meta information is tag data and tag metadata. The client is used for sending a user grouping request message to a unified online grouping service in the star painting online service in the server, wherein the user grouping request message comprises at least one grouping description information. After receiving a user grouping request message from a client based on a unified online grouping service, a star painting online service in a server generates an intelligent rule format from an internal memory based on at least one user tag and a preset grouping rule relation by utilizing a unified portrait query service; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logical operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logical operation relations between the labels and the label values. After the star painting online service obtains the intelligent rule format, filtering a plurality of users to be clustered based on the intelligent rule format by utilizing the unified online clustering service to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation. The storage locations of the tag and the tag value may be in an internal memory or an external memory, when the storage locations are in the internal memory, the server directly obtains the tag (such as tag storage a, tag storage B, tag storage N, etc.) according to the storage locations, and when the storage locations are in the external memory, the server needs to obtain corresponding tag data (such as tag data of security, area code, etc.) by using an external real-time data service interface.
Currently, in business decisions, it is necessary to specify the target user population through user portraits. The method for defining the target user group through the user portrait comprises the following steps: determining a plurality of rules (e.g., rule 1, rule 2, rule 3, etc.) based on a plurality of labels in the user representation; screening the users to be clustered by using each rule respectively to obtain user groups corresponding to each rule; and screening the user group corresponding to each rule by utilizing the logic relation among the rules to obtain a target user group. In the method, the user groups corresponding to the rules are required to be acquired and processed, so that the process of acquiring the target user group is complex, and the efficiency of acquiring the user group is low. Accordingly, how to improve the efficiency of obtaining the target user group is a problem to be solved.
The embodiment of the application provides a user grouping processing method, which comprises the steps of receiving a user grouping request message from a client, wherein the user grouping request message comprises at least one grouping description information; extracting information from at least one group description information to obtain at least one user tag; generating an intelligent rule format based on at least one user tag and a preset grouping rule relation; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logic operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between the labels and the label values; filtering a plurality of users to be clustered based on an intelligent rule format to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation; and sending a user grouping request response message to the client, wherein the user grouping request response message comprises the grouping result. In the method, various logic relations among a plurality of sub-rules in the intelligent rule format can be identified and calculated, and the grouping result is directly obtained by utilizing the intelligent rule format, so that the process of obtaining user groups corresponding to a plurality of rules and processing the user groups corresponding to the rules is avoided, and further, the efficiency of obtaining target user groups is improved.
It should be noted that, in a specific implementation, the method may be executed based on the user grouping processing method system shown in fig. 1, where the execution body may be an electronic device, or may be a module of the electronic device, and the electronic device may be a terminal or a server; the terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch, an intelligent vehicle-mounted terminal, and the like. The server may be an independent physical server, a server cluster formed by a plurality of physical servers, a distributed system, or the like, but is not limited thereto. When the electronic equipment is a server, the method is processed through the background of the server, and the method has high processing efficiency and high running speed.
The user grouping processing method is described in detail below with reference to the accompanying drawings.
Referring to fig. 2, fig. 2 is a flow chart of a user grouping processing method according to an embodiment of the present application. As shown in fig. 2, the user grouping method may include, but is not limited to, the following steps:
s101, a server receives a user grouping request message from a client, wherein the user grouping request message comprises at least one piece of grouping description information.
Correspondingly, the client sends a user grouping request message to the server, wherein the user grouping request message comprises at least one grouping description information. Optionally, the grouping description information may be user labels of a plurality of users to be grouped and grouping rule labels for grouping the plurality of users to be grouped.
In an alternative embodiment, before the server receives the user grouping request message from the client, the server may further perform: receiving a preset grouping rule relation storage request message from an operation end, wherein the preset grouping rule relation storage request message comprises a preset grouping rule relation to be stored; and storing the preset grouping rule relation and generating a corresponding user label. Correspondingly, the operation end sends a preset grouping rule relation storage request message to the server, wherein the preset grouping rule relation storage request message comprises a preset grouping rule relation to be stored.
In an optional implementation manner, storing the preset grouping rule relation and generating a corresponding user tag, including: extracting a plurality of sub-rules in a preset grouping rule relation, wherein the sub-rules are used for indicating a logical operation relation between the label and the label value; extracting labels and label values in a preset grouping rule relation and respectively storing the labels and the label values; based on the logic operation among the plurality of sub-rules, the operators in the plurality of sub-rules and the rule labels, user labels corresponding to the preset grouping rule relation are generated.
It should be noted that, when the preset grouping rule relation is stored, the grouping rule is deleted without corresponding deletion processing or unexpected situation, and is permanently stored.
By way of example, the operators in embodiments of the present application may be a variety of operators. The operator names and corresponding samples of the various operators can be referred to in table 1:
TABLE 1
As can be derived from table 1, the operator names included in the numerical comparison operation are: greater than (>), less than (<), equal to (=), greater than or equal to (∈), and less than or equal to (+.. The operator names of the set operation are: inclusion (in) and non-inclusion (not in), for example, the aggregate operation may include a sound, a national style, and a rap for the search list preference. The operator names for null value judgment are as follows: for example, the null value determination may be for a paid package feature to be null or a paid package feature to be non-null. Operator name of the range operation: there is something between (betwen), for example, the range operation may be between 1 hour and 3 hours for the last 3 days of recording duration. The operator names of the specified value selection operation are: the character string designation value, for example, the designation value selection operation may designate the user sex as male or the user sex as female.
The above-described various operators are only for the purpose of explanation, and the operators are not limited thereto.
In an alternative embodiment, before the server receives the preset grouping rule relation storage request message from the operation end, the server may further: receiving a preset grouping rule relation creation operation from an operation end; responding to a preset grouping rule relation creation operation, sending a preset grouping rule relation creation response message to the operation terminal, and displaying a grouping rule creation interface, wherein the preset grouping rule relation creation response message is used for informing the operation terminal to create the grouping rule at the grouping rule creation interface. Correspondingly, the operation end performs: carrying out preset grouping rule relation creation operation on the server; receiving a preset grouping rule relation creation response message from the server, wherein the preset grouping rule relation creation response message is used for informing an operation end to create a preset grouping rule relation at a grouping rule creation interface; creating a plurality of sub-rules at a grouping rule creation interface, wherein the sub-rules are used for indicating a logical operation relation between the tag and the tag value; selecting logic operation among a plurality of sub-rules at a grouping rule creation interface; generating a preset grouping rule relation based on logic operation between the plurality of sub-rules and the plurality of sub-rules; and sending a preset grouping rule relation storage request message to the server, wherein the preset grouping rule relation storage request message comprises a preset grouping rule relation to be stored.
The tag data sources corresponding to the tags comprise fixed storage (such as MongoDB, HBase), a real-time external interface, real-time equipment information and the like, and meanwhile, the operation of accessing a new tag data source through a user interface (such as a grouping rule creation interface) is supported.
Take the creation of grouping rules (preset grouping rule relation) as an example. Referring to figure 3 of the drawings in which,fig. 3 is a schematic diagram of a grouping rule creation interface provided in an embodiment of the present application, where, as shown in fig. 3, the grouping rule creation interface includes a user tag (a tag corresponding to a sub-rule in the present application), a user grouping, a help document, and an option of applying permission, and the creation of a grouping rule is introduced by taking a rule circling (offline+online) sub-option in the user grouping option as an example. Selecting user grouping options, and displaying sub-options such as rule circling (offline+online), structured query language (structured query language, SQL) circling, crowd import, crowd combination, grouping record and the like under the user grouping options on the left side of the grouping rule creation interface. The option of selecting rule circlers (offline+online), the interface of basic information and rule creation will appear on the right side of the grouping rule creation interface. The basic information includes grouping type (offline crowd pack, online grouping interface), grouping name, label product line, maximum query rate per second (QPS) and buffering time, and an operator can set the basic information at the interface of the basic information. Rule creation includes user tag satisfaction and outer layer added options, selection of a user tag satisfaction option will reveal support of tag search, operators, tag values, Add and->Options for deletion. Selecting the option to support the tag search, as shown in fig. 4, the grouping rule creation interface may display a plurality of account attributes (e.g., average age of the user concerned (rounded), average age of the fan (rounded), average age of the person concerned (rounded), number of friends singing, etc.) based on the basic information, and may select the tag from the plurality of account attributes. The selection of the operators, as shown in fig. 5, the grouping rule creation interface may display a plurality of operators (e.g., equal to, not equal to, greater than, less than, equal to, less than, choose a range of values, etc.), and may select one operator from the plurality of operators. Selecting the option added at the outer layer may display logical operations (e.g., AND operations)Or operation, etc.), the logical operation between the sub-rules may be adjustable, as shown in fig. 6, the logical operation between rule 1 and rule 2 may be or operation, or may be and operation, which is not limited herein; meanwhile, the logic operations can also be nested, as shown in fig. 6, the logic operation between the sub-rule 1 and the sub-rule 2 can be performed with the sub-rule 3 (such as a parallel operation). The operator can create the grouping rules at the grouping rule creation interface and select to submit after the grouping rules are created. For example, sub-rule 1, sub-rule 2, sub-rule 3, sub-rule 4, and sub-rule 5 may be created when the user tag is selected to be satisfied; selecting an outer layer addition may create a logical relationship between the sub-rules. Wherein, the label in the sub-rule 1 can select the age, the operator can select more than the age, the label value can be set to 18 (the label value is set to the custom setting, that is, the label value can be set according to the actual situation), and the sub-rules 2 to 5 are all similar operations; the logical relation between the sub-rules is created by clicking the outer layer addition, selecting the sub-rules and the logical operators, for example, the logical operation between the sub-rule 2 and the sub-rule 3 is an AND operation, the logical operation between the sub-rule 4 and the sub-rule 5 is an OR operation, and the logical operation between the logical operation result between the sub-rule 4 and the sub-rule 5 and the logical operation between the sub-rule 1 is an OR operation. After the creation of the logic operation between the sub-rules is completed, clicking the submitting option of the grouping rule creation interface to generate a grouping rule, and calculating the target user group by using the grouping rule.
In this example, on the one hand, compared with the previous grouping rule which only includes a plurality of sub-rules to perform simple comparison operation and the sub-rules to perform simple combination filtering, the grouping rule in the embodiment of the present application may include a plurality of sub-rules to perform various logic operations and may further perform nesting operation between the logic operations, so as to improve diversity corresponding to the grouping rule, so that the grouping rule may accurately define a target user population under a specific decision, and further improve calculation efficiency and effectiveness of obtaining the target user population based on the grouping rule. On the one hand, compared with the offline operation of the grouping rule, the embodiment of the application can calculate the grouping rule immediately after the grouping rule is established, namely, the server can acquire the target user group in real time based on the generated grouping rule, so that the capability of real-time decision making in marketing operation is improved. On one hand, a group rule creation interface with visual programming is provided, so that operators can simply and conveniently get hands without mastering advanced programming capacity, thereby quickly making the group rule and putting the group rule into an on-line environment, and improving the efficiency of making the group rule.
Illustratively, the generation and storage of a preset grouping rule relationship is described taking a decision of a typical music service line as an example. The operation group of the music service line platform needs to make an operation strategy named as 'a national wind member user high activity ranking front 5 (top 5)', hopes to screen three types of user groups at one time, takes and collects the three types of user groups as screened target user groups, and the target user groups are used for representing the national wind type high activity member groups and putting corresponding song list recommendation to the target user groups.
Description of the first class of user population (description of sub-rule 1): genre preference top5 contains a strong wind and the user is a green drill or a luxury green drill.
Description of the second class of user population (description of sub-rule 2): genre preference top5 contains chinese winds, and the user does the act of listening to songs during 9 months, and the total number of listening to songs is 8 times or more.
Description of the third class of user population (description of sub-rule 3): genre preference top5 contains folk music, user takes a leap action during 9 months, and user is a member and the number of active days is greater than 1 day.
The generation process of the grouping rule comprises the following steps:
after obtaining descriptions of three types of user groups, creating a sub-rule 1 on a grouping rule creation interface: genre preference top5 contains antique, user is green diamond or luxury green diamond. Creating sub-rule 2: genre preference top5 contains chinese style, user's listening to songs during 9 months and total number of listening to songs is 8 or more. Creating sub-rule 3: genre preference top5 contains folk music, user's jump during 9 months, user is a member and the number of days active is greater than 1 day.
After obtaining the sub-rules, a logical relationship between the sub-rules is obtained, and the logical relationship between sub-rule 1, sub-rule 2, and sub-rule 3 is "and". The logical relationship is selected as "and" between sub-rule 1, sub-rule 2, and sub-rule 3 in the grouping rule creation interface.
And generating a preset grouping rule relation based on the created sub-rule and the logic relation selection between the sub-rules.
The storage process of the preset grouping rule relation comprises the following steps:
after the preset grouping rule relation is generated, the preset grouping rule relation is input into the server. The server analyzes according to the semantics of the preset grouping rule relation, and extracts all labels and label values in the preset grouping rule relation, such as genre preference, member users, song listening behaviors, total song listening times, active behaviors, whether members are active days and the like. The server parses according to the semantics of the grouping rules, recording the operations between the labels and the label values, such as "genre preference" including antique, "member users" and "green drill".
The server analyzes according to the semantics of the preset grouping rule relation and records the operation among the labels. And the server generates a storage form of a preset grouping rule relation and a corresponding user label according to the analysis result. The server stores the labels, the label values, the storage form (intelligent rule format) of the preset grouping rule relation and the corresponding user labels.
It should be noted that, the embodiment of the present application does not limit the format of the intelligent rule format.
S102, the server extracts information of at least one grouping description information to obtain at least one user tag.
The user tag may be various tag information of the user such as genre preference top5, old wind, whether the user is a green drill or a luxury green drill, etc. This is not limiting in the embodiments of the present application.
S103, the server generates an intelligent rule format based on at least one user tag and a preset grouping rule relation.
The preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logical operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logical operation relations between the labels and the label values.
Alternatively, the intelligent rule format is stored in a byte compression encoded form that has a low memory footprint, an average memory footprint of no more than 100 bytes, and an average computation load of the memory footprint of no more than 1 millisecond.
It will be appreciated that the server in the embodiments of the present application has the ability to support complex rule operations. In actual testing, the single 8-core 16G server of the pressure measurement data processes the user population corresponding to the online grouping rule, the highest query rate per second is 12000 times per second, the maximum concurrency user number is 470, and the load is 94%. The load of the whole central processing unit is normal, and the condition of continuous occupation does not occur.
In an alternative embodiment, after the server generates the intelligent rule format based on at least one user tag and the preset grouping rule relationship, the server further performs: and storing the intelligent rule format and generating an intelligent rule format label corresponding to the intelligent rule format. In an alternative embodiment, before the server stores the intelligent rule format and generates the intelligent rule format label corresponding to the intelligent rule format, the server further performs: based on a plurality of sub-rules in the intelligent rule format, the labels and the label values corresponding to the intelligent rule format are obtained and stored respectively.
In an alternative embodiment, the intelligent rule format is stored in a byte compression encoded form that identifies sub-rules in the form of each rule label and in combination with logical operators that identify logical operational relationships between each rule label. In this embodiment, the intelligent rule format is stored in a byte compression encoded form that has a low memory footprint, an average memory footprint of no more than 100 bytes, and an average computation takes no more than 1 millisecond to load the memory form.
For example, referring to fig. 7, fig. 7 is a schematic diagram of an intelligent rule format storage form according to an embodiment of the present application. As shown in fig. 7, a rule reference a in the circle under fig. 7 is used to identify a sub-rule 1, a rule reference B is used to identify a sub-rule 2, and a rule reference C is used to identify a sub-rule 3; the logical operators contained by the arrows between the logical operators in the circle above fig. 7 and the circle identify the logical operational relationship between the respective rule labels (rule label a, rule label B, and rule label C). Wherein, "U" identifies "logical OR operator", "U" identifies "logical AND operator", "|! "identify" logical not operator. That is, the logical relationship between rule 1 and rule 2 is "AND", the logical relationship between rule 3 itself is "NOT", and the logical relationship between the result of the logical OR operation between rule 1 and rule 2 and the result of the logical NOT operation between rule 3 is "OR". Such a storage form occupies little memory space and takes little time to load the storage form, which is essentially negligible.
S104, the server filters the plurality of users to be clustered based on the intelligent rule format to obtain a clustering result.
The grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation.
Optionally, the grouping result further includes a second grouping result, and none of one or more users to be grouped in the second grouping result satisfies a preset grouping rule relationship.
For example, there are 10 users to be grouped, wherein 8 users to be grouped in the first grouping result and 2 users to be grouped in the second grouping result. Then 8 persons in the first grouping result meet the preset grouping rule relation, and 2 persons in the second grouping result do not meet the preset grouping rule relation.
In an optional implementation manner, the server performs filtering processing on the multiple users to be clustered based on the intelligent rule format to obtain a clustering result, which may be: acquiring user marks of a plurality of users to be grouped and intelligent rule format marks for grouping the plurality of users to be grouped; based on the intelligent rule format label, acquiring an intelligent rule format corresponding to the intelligent rule format label; acquiring a preset grouping rule relation based on an intelligent rule format corresponding to the intelligent rule format label; acquiring labels of each user to be grouped based on user labels of a plurality of users to be grouped; and filtering the plurality of users to be clustered based on a preset clustering rule relation and labels of each user to be clustered to obtain a clustering result.
Optionally, the server performs filtering processing on the multiple users to be clustered based on the intelligent rule format to obtain a clustering result, and may be: filtering a plurality of users to be clustered based on a preset clustering rule relation and labels of each user to be clustered; judging whether all operations (such as logic operations and the like) included in the preset grouping rule relation are completed, and outputting a grouping result after all operations included in the preset grouping rule relation are completed; or, when all the operations included in the preset grouping rule relation are not completed, continuing to execute the filtering processing.
In an optional implementation manner, the server obtains the preset grouping rule relationship based on the intelligent rule format corresponding to the intelligent rule format label, which may be: based on the intelligent rule format corresponding to the intelligent rule format label, acquiring a label corresponding to the sub rule and metadata of the label, wherein the metadata of the label is used for indicating the position of a label value of the label; acquiring a tag value of the tag based on the metadata of the tag; and acquiring a preset grouping rule relation based on the intelligent rule format, the label and the label value of the label corresponding to the intelligent rule format label.
S105, the server sends a user grouping request response message to the client.
Correspondingly, the client receives a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more to-be-grouped users in the first grouping result meet a preset grouping rule relation, or the grouping result also comprises a second grouping result, and one or more to-be-grouped users in the second grouping result do not meet the preset grouping rule relation.
It can be seen that, compared with the previous user grouping, if the server wants to output the refined user grouping (target user group), the operator needs to formulate multiple simple rules, the client understands the logic relationship between the rules (that is, the client and the operator communicate the rules to obtain the self-quiet logic relationship of the rules), and after obtaining the logic relationship between the rules, the client requests the rules to the server multiple times to obtain the group corresponding to the rules, and performs multiple operations on the group corresponding to the rules to obtain the final refined grouping result. For example, the flow may be: the operation end formulates rule 1 and rule 2 … rule n; the client requests the server for a plurality of times to obtain a grouping result 1 and a result 2 … result n; after the client side understands the logical relation between the rules by the operation side, the clustering result 1 and the result 2 … result n are calculated for a plurality of times, and a final clustering result (target user crowd) is obtained. In the embodiment of the application, the operation end only needs to formulate a complex grouping rule (the grouping rule comprises a plurality of sub-rules), and the client only needs to make a request to the server for the grouping rule once, so that the target user group can be obtained, on one hand, the request amount is greatly reduced, the performance of the client for inquiring the target user group is improved, and the efficiency of obtaining the target user group is improved; on the other hand, the client does not need to communicate with the grouping rules of the operation end, and the server can directly identify and calculate the logic relationship among all the sub-rules in the grouping rules, so that the efficiency and the effectiveness of acquiring the target user group are improved.
In an alternative embodiment, after performing step S105, the server may further perform: acquiring recommended content to be displayed in a content recommendation interface based on the grouping result; when a content recommendation interface is displayed through a content platform, corresponding interaction controls are respectively generated based on a plurality of characteristic dimensions, the characteristic dimensions are related to the type of recommended content provided by the content platform and user preference, the characteristic dimensions respectively have display weights which influence the display sequence of the recommended content in the content recommendation interface, and the interaction controls are used for adjusting the weight influence degree of the display weights; updating the display weights of the plurality of feature dimensions in response to a weight adjustment operation of the display weights based on the interaction control; and rearranging the display positions of the recommended content in the content recommendation interface according to the updated display weights.
In example 1, taking an example that a server receives a user grouping request message of a client to the server and outputs a grouping result, please refer to fig. 8, fig. 8 is a schematic diagram of a scheme of user grouping processing according to an embodiment of the present application. As shown in fig. 8, the server may perform: receiving a user grouping request message, wherein the user grouping request message comprises user marks of a plurality of users to be grouped and grouping rule marks (grouping description information) for grouping the plurality of users to be grouped; based on the grouping rule label, a storage form (intelligent rule format) of the grouping rule is obtained, wherein the storage form of the grouping rule is the byte compression coding form; based on the rule labels, obtaining labels corresponding to the sub rules and metadata of the labels, wherein the metadata of the labels are used for indicating the positions of label values of the labels; acquiring a tag value of the tag based on the metadata of the tag; acquiring a grouping rule based on a storage form of the grouping rule, a label and a label value of the label; acquiring labels of each user to be grouped based on user labels of a plurality of users to be grouped; filtering a plurality of users to be clustered based on a clustering rule and labels of each user to be clustered; judging whether all operations (such as logic operations and the like) included in the grouping rules are completed, and outputting a grouping result after all operations included in the grouping rules are completed; or, when all the operations included in the grouping rule are not completed, the above filtering process is continued.
Wherein, the grouping rules (intelligent rule format) are stored in a byte compression coding form (storage form of the grouping rules), and the byte compression coding form is in a mode of combining each rule label and a logic operator for identifying a logic operation relation among each rule label, wherein the rule labels are used for identifying the sub-rules.
In example 2, taking interaction among a server, a client and an operator as an example, please refer to fig. 9, fig. 9 is a schematic diagram of another user grouping process scheme provided in an embodiment of the present application. As shown in fig. 9, the operation end performs a grouping rule (preset grouping rule relation) creation operation on the server; the server receives grouping rule creation operation from the operation end, responds to the grouping rule creation operation, sends grouping rule creation response information to the operation end and displays a grouping rule creation interface; the method comprises the steps that an operation end receives a grouping rule creation response message from a server, a plurality of sub-rules are created at a grouping rule creation interface, the sub-rules are used for indicating a logical operation relation between a label and a label value, logical operation among the plurality of sub-rules is selected at the grouping rule creation interface, a grouping rule is generated based on the logical operation among the plurality of sub-rules and the plurality of sub-rules, a grouping rule storage request message is sent to the server, and the grouping rule storage request message comprises the grouping rule; the server receives the grouping rule storage request message from the operation end, stores the grouping rule, and generates a storage form ((intelligent rule format)) and a grouping rule label (intelligent rule format label) of the corresponding grouping rule. The client sends a user grouping request message to the server; the method comprises the steps that a server receives user grouping request information from a client, the user grouping request information comprises user marks of a plurality of users to be grouped and grouping rule marks for grouping the plurality of users to be grouped, grouping rules are obtained based on the grouping rule marks, labels of each user to be grouped are obtained based on the user marks of the plurality of users to be grouped, filtering processing is carried out on the plurality of users to be grouped based on the grouping rules and the labels of each user to be grouped, grouping results are obtained, and user grouping response information is sent to the client; the client receives a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more to-be-grouped users in the first grouping result meet a grouping rule, or the grouping result also comprises a second grouping result, and one or more to-be-grouped users in the second grouping result do not meet the grouping rule.
Referring to fig. 10, fig. 10 is a schematic diagram of a user grouping processing apparatus according to an embodiment of the present application. As shown in fig. 10, when the execution subject is a server, the grouping rule processing means may include, but is not limited to:
a receiving module 1001, configured to receive a user grouping request message from a client, where the user grouping request message includes at least one grouping description information;
the processing module 1002 is configured to extract information from at least one group description information to obtain at least one user tag;
the processing module 1002 is further configured to generate an intelligent rule format based on at least one user tag and a preset grouping rule relationship; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logic operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between the labels and the label values;
the processing module 1002 is further configured to perform filtering processing on the plurality of users to be clustered based on the intelligent rule format, to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation;
A sending module 1003, configured to send a user grouping request response message to the client, where the user grouping request response message includes a grouping result.
In an optional implementation manner, the processing module 1002 is further configured to obtain, based on the grouping result, recommended content that needs to be displayed in the content recommendation interface; when a content recommendation interface is displayed through a content platform, corresponding interaction controls are respectively generated based on a plurality of characteristic dimensions, the characteristic dimensions are related to the type of recommended content provided by the content platform and user preference, the characteristic dimensions respectively have display weights which influence the display sequence of the recommended content in the content recommendation interface, and the interaction controls are used for adjusting the weight influence degree of the display weights; updating the display weights of the plurality of feature dimensions in response to a weight adjustment operation of the display weights based on the interaction control; and rearranging the display positions of the recommended contents in the content recommendation interface according to the updated display weights.
In an alternative embodiment, the grouping result further includes a second grouping result, and one or more users to be grouped in the second grouping result do not satisfy a preset grouping rule relationship.
In an alternative embodiment, the processing module 1002 performs filtering processing on a plurality of users to be clustered based on an intelligent rule format to obtain a clustering result, which is specifically configured to: acquiring user marks of a plurality of users to be grouped and intelligent rule format marks for grouping the plurality of users to be grouped; based on the intelligent rule format label, acquiring an intelligent rule format corresponding to the intelligent rule format label; acquiring grouping rules based on intelligent rule formats corresponding to the intelligent rule format labels; acquiring labels of each user to be grouped based on user labels of a plurality of users to be grouped; and filtering the plurality of users to be clustered based on the clustering rules and the labels of each user to be clustered to obtain a clustering result.
In an alternative embodiment, the processing module 1002 obtains the grouping rule based on the intelligent rule format corresponding to the intelligent rule format label, which is specifically configured to: based on the intelligent rule format corresponding to the intelligent rule format label, acquiring a label corresponding to the sub rule and metadata of the label, wherein the metadata of the label is used for indicating the position of a label value of the label; acquiring a tag value of the tag based on the metadata of the tag; acquiring grouping rules based on intelligent rule formats, labels and label values of labels corresponding to intelligent rule format labels
In an alternative embodiment, the processing module 1002 is further configured to, after generating the intelligent rule format based on at least one user tag and the preset grouping rule relation: and storing the intelligent rule format and generating an intelligent rule format label corresponding to the intelligent rule format.
In an alternative embodiment, before the processing module 1002 stores the intelligent rule format and generates the intelligent rule format label corresponding to the intelligent rule format, the processing module is further configured to: based on a plurality of sub-rules in the intelligent rule format, the labels and the label values corresponding to the intelligent rule format are obtained and stored respectively.
Alternatively, when the execution subject is a client, the user grouping processing apparatus may include, but is not limited to:
a sending module 1003, configured to send a user grouping request message to a server, where the user grouping request message includes at least one grouping description information;
the receiving module 1001 is configured to receive a user grouping request response message from the server, where the user grouping request response message includes a grouping result, the grouping result includes a first grouping result, one or more to-be-grouped users in the first grouping result satisfy a preset grouping rule relationship, or the grouping result also includes a second grouping result, and one or more to-be-grouped users in the second grouping result do not satisfy the preset grouping rule relationship.
Optionally, the embodiment of the present application further provides a grouping rule generating device, where the grouping rule generating device is configured to: receiving a grouping rule creation response message from the server; creating a plurality of sub-rules at a grouping rule creation interface, wherein the sub-rules are used for indicating a logical operation relation between the tag and the tag value; selecting logic operation among a plurality of sub-rules at a grouping rule creation interface; generating a grouping rule based on the plurality of sub-rules and the logical operation between the plurality of sub-rules; and sending a grouping rule storage request message to a server, wherein the grouping rule storage request message comprises the grouping rule to be stored.
It may be understood that the specific implementation and the beneficial effects that can be achieved of each module in the grouping rule processing apparatus described in the embodiments of the present application may refer to the description of the foregoing method embodiments, which is not repeated herein.
Referring to fig. 11, fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device described in the embodiment of the application includes: a processor 1101, a user interface 1102, a communication interface 1103 and a memory 1104. The processor 1101, the user interface 1102, the communication interface 1103 and the memory 1104 may be connected by a bus or other means, for example, in the embodiment of the present application.
Among them, the processor 1101 (or CPU (Central Processing Unit, central processing unit)) is a computing core and a control core of the electronic device, which can parse various instructions in the electronic device and process various data of the electronic device, for example: the CPU can be used for analyzing a startup and shutdown instruction sent by the object to the electronic equipment and controlling the electronic equipment to perform startup and shutdown operation; and the following steps: the CPU may transmit various types of interaction data between internal structures of the electronic device, and so on. The user interface 1102 is a medium for implementing interaction and information exchange between a user and the electronic device, and may specifically include a Display screen (Display) for output, a Keyboard (Keyboard) for input, and the like, where the Keyboard may be a physical Keyboard, a touch screen virtual Keyboard, or a Keyboard that combines a physical Keyboard and a touch screen virtual Keyboard. The communication interface 1103 may optionally include a standard wired interface, a wireless interface (e.g., wi-Fi, mobile communication interface, etc.), and is controlled by the processor 1101 to transmit and receive data. Memory 1104 (Memory) is a Memory device in an electronic device for storing programs and data. It will be appreciated that the memory 1104 herein may include both built-in memory of the electronic device and extended memory supported by the electronic device. Memory 1104 provides storage space that stores an operating system for the electronic device, which may include, but is not limited to: android systems, iOS systems, windows Phone systems, etc., which are not limiting in this application.
In the present embodiment, the processor 1101 performs the following operations by executing executable program code in the memory 1104:
receiving a user grouping request message from a client, wherein the user grouping request message comprises at least one grouping description information; extracting information from at least one group description information to obtain at least one user tag; generating an intelligent rule format based on at least one user tag and a preset grouping rule relation; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to the plurality of sub-rules and logic operation relations among the plurality of sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between the labels and the label values; filtering a plurality of users to be clustered based on an intelligent rule format to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet a preset grouping rule relation; and sending a user grouping request response message to the client, wherein the user grouping request response message comprises the grouping result.
In an alternative embodiment, the processor 1101 obtains recommended content that needs to be displayed in the content recommendation interface based on the grouping result; when a content recommendation interface is displayed through a content platform, corresponding interaction controls are respectively generated based on a plurality of characteristic dimensions, the characteristic dimensions are related to the type of recommended content provided by the content platform and user preference, the characteristic dimensions respectively have display weights which influence the display sequence of the recommended content in the content recommendation interface, and the interaction controls are used for adjusting the weight influence degree of the display weights; updating the display weights of the plurality of feature dimensions in response to a weight adjustment operation of the display weights based on the interaction control; and rearranging the display positions of the recommended contents in the content recommendation interface according to the updated display weights.
In an alternative embodiment, the grouping result further includes a second grouping result, and one or more users to be grouped in the second grouping result do not satisfy a preset grouping rule relationship.
In an alternative embodiment, the processor 1101 performs filtering processing on a plurality of users to be clustered based on an intelligent rule format to obtain a clustering result, including: acquiring user marks of a plurality of users to be grouped and intelligent rule format marks for grouping the plurality of users to be grouped; based on the intelligent rule format label, acquiring an intelligent rule format corresponding to the intelligent rule format label; acquiring grouping rules based on intelligent rule formats corresponding to the intelligent rule format labels; acquiring labels of each user to be grouped based on user labels of a plurality of users to be grouped; and filtering the plurality of users to be clustered based on the clustering rules and the labels of each user to be clustered to obtain a clustering result.
In an alternative embodiment, the processor 1101 obtains a grouping rule based on an intelligent rule format corresponding to an intelligent rule format label, including: based on the intelligent rule format corresponding to the intelligent rule format label, acquiring a label corresponding to the sub rule and metadata of the label, wherein the metadata of the label is used for indicating the position of a label value of the label; acquiring a tag value of the tag based on the metadata of the tag; and acquiring a preset grouping rule relation based on the intelligent rule format, the label and the label value of the label corresponding to the intelligent rule format label.
In an alternative embodiment, after the processor 1101 generates the intelligent rule format based on at least one user tag and the preset grouping rule relation, the method further comprises: and storing the intelligent rule format and generating an intelligent rule format label corresponding to the intelligent rule format.
In an alternative embodiment, before the processor 1101 stores the intelligent rule format and generates the intelligent rule format label corresponding to the intelligent rule format, the method further includes: based on a plurality of sub-rules in the intelligent rule format, the labels and the label values corresponding to the intelligent rule format are obtained and stored respectively.
In a specific implementation, the processor 1101, the user interface 1102, the communication interface 1103 and the memory 1104 described in the embodiments of the present application may execute an implementation manner of the electronic device described in the user grouping processing method provided in the embodiments of the present application, or may execute an implementation manner described in the user grouping processing apparatus provided in the embodiments of the present application, which is not described herein again.
In the present embodiment, the processor 1101 further performs the following operations by executing executable program code in the memory 1104:
a user grouping request message is sent to a server, wherein the user grouping request message comprises user marks of a plurality of users to be grouped and grouping rule marks for grouping the plurality of users to be grouped; receiving a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more users to be grouped in the first grouping result meet the grouping rule, or the grouping result also comprises a second grouping result, and one or more users to be grouped in the second grouping result do not meet the grouping rule.
In a specific implementation, the processor 1101, the user interface 1102, the communication interface 1103 and the memory 1104 described in the embodiments of the present application may execute an implementation manner of the electronic device described in the method for generating a grouping rule provided in the embodiments of the present application, or may execute an implementation manner described in the user grouping processing apparatus provided in the embodiments of the present application, which is not described herein again.
The embodiment of the application further provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program includes program instructions, and when the program instructions are executed by a processor, the method for user grouping provided in the embodiment of the application is implemented, and specifically, reference may be made to implementation manners provided by the foregoing steps, which are not described herein again.
Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the user grouping processing method provided in the embodiments of the present application, and specifically, the implementation manner provided by each step may be referred to, which is not described herein.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the described order of action, as some steps may take other order or be performed simultaneously according to the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
The foregoing disclosure is only illustrative of some of the embodiments of the present application and is not, of course, to be construed as limiting the scope of the appended claims, and therefore, all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

Claims (10)

1. A method for user grouping, the method comprising:
receiving a user grouping request message from a client, wherein the user grouping request message comprises at least one grouping description information;
extracting information from the at least one grouping description information to obtain at least one user tag;
generating an intelligent rule format based on the at least one user tag and a preset grouping rule relation; the preset grouping rule relation comprises a plurality of logic operation relations; the intelligent rule format comprises sub-rule labels corresponding to a plurality of sub-rules and logic operation relations among the sub-rule labels, wherein the sub-rules are used for indicating the logic operation relations between labels and label values;
filtering a plurality of users to be clustered based on the intelligent rule format to obtain a clustering result; the grouping result comprises a first grouping result, and one or more users to be grouped in the first grouping result meet the preset grouping rule relation;
and sending a user grouping request response message to the client, wherein the user grouping request response message comprises the grouping result.
2. The method according to claim 1, wherein the method further comprises:
Acquiring recommended content to be displayed in a content recommendation interface based on the grouping result;
when the content recommendation interface is displayed through a content platform, corresponding interaction controls are respectively generated based on a plurality of characteristic dimensions, wherein the characteristic dimensions are related to the type of recommended content and user preference provided by the content platform, the characteristic dimensions are respectively provided with display weights for influencing the display sequence of the recommended content in the content recommendation interface, and the interaction controls are used for adjusting the weight influence degree of the display weights;
updating the display weights of the plurality of feature dimensions in response to a weight adjustment operation of the display weights based on the interaction control;
and rearranging the display positions of the recommended contents in the content recommendation interface according to the updated display weights.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the grouping result also comprises a second grouping result, and one or more users to be grouped in the second grouping result do not meet the preset grouping rule relation.
4. A method according to any one of claims 1 to 3, wherein filtering a plurality of users to be clustered based on the intelligent rule format to obtain a clustered result comprises:
Acquiring user marks of a plurality of users to be clustered and intelligent rule format marks for clustering the plurality of users to be clustered;
based on the intelligent rule format label, acquiring an intelligent rule format corresponding to the intelligent rule format label;
acquiring a preset grouping rule relation based on an intelligent rule format corresponding to the intelligent rule format label;
acquiring labels of each user to be grouped based on the user numbers of the plurality of users to be grouped;
and filtering the plurality of users to be clustered based on the preset clustering rule relation and the labels of each user to be clustered to obtain a clustering result.
5. The method of claim 4, wherein the obtaining a preset grouping rule relationship based on the intelligent rule format corresponding to the intelligent rule format label comprises:
acquiring a label corresponding to the sub rule and metadata of the label based on an intelligent rule format corresponding to the intelligent rule format label, wherein the metadata of the label is used for indicating the position of a label value of the label;
acquiring a tag value of the tag based on the metadata of the tag;
and acquiring a preset grouping rule relation based on the intelligent rule format corresponding to the intelligent rule format label, the label and the label value of the label.
6. The method of claim 5, wherein after generating the intelligent rule format based on the at least one user tag and a preset grouping rule relationship, the method further comprises:
and storing the intelligent rule format and generating an intelligent rule format label corresponding to the intelligent rule format.
7. The method of claim 6, wherein before storing the intelligent rule format and generating the intelligent rule format label corresponding to the intelligent rule format, the method further comprises:
and acquiring and storing the label and the label value corresponding to the intelligent rule format respectively based on the plurality of sub-rules in the intelligent rule format.
8. A method for user grouping, the method comprising:
transmitting a user grouping request message to a server, wherein the user grouping request message comprises at least one grouping description information;
receiving a user grouping request response message from the server, wherein the user grouping request response message comprises a grouping result, the grouping result comprises a first grouping result, one or more users to be grouped in the first grouping result meet a preset grouping rule relation, or the grouping result also comprises a second grouping result, and one or more users to be grouped in the second grouping result do not meet the preset grouping rule relation.
9. An electronic device, comprising: a processor, a user interface, a communication interface and a memory, the processor, the user interface, the communication interface and the memory being interconnected, wherein the memory stores executable program code, the processor being configured to invoke the executable program code to perform the method according to any of claims 1-7 or to perform the method according to claim 8.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1-7 or to perform the method of claim 8.
CN202310504582.6A 2023-05-06 2023-05-06 User grouping processing method, electronic device and computer readable storage medium Pending CN116541760A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310504582.6A CN116541760A (en) 2023-05-06 2023-05-06 User grouping processing method, electronic device and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310504582.6A CN116541760A (en) 2023-05-06 2023-05-06 User grouping processing method, electronic device and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN116541760A true CN116541760A (en) 2023-08-04

Family

ID=87443009

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310504582.6A Pending CN116541760A (en) 2023-05-06 2023-05-06 User grouping processing method, electronic device and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN116541760A (en)

Similar Documents

Publication Publication Date Title
US11539809B2 (en) Push notification delivery system with feedback analysis
US10958748B2 (en) Resource push method and apparatus
US11216509B2 (en) Dynamic faceting for personalized search and discovery
US9282162B2 (en) Processing user profiles of users in an electronic community
WO2021174944A1 (en) Message push method based on target activity, and related device
US10607271B1 (en) Search platform with data driven search relevancy management
CN110264328A (en) Account checking method, device, equipment, system and computer readable storage medium
US20140074851A1 (en) Dynamic data acquisition method and system
CN110825956A (en) Information flow recommendation method and device, computer equipment and storage medium
CN110020002A (en) Querying method, device, equipment and the computer storage medium of event handling scheme
US9069880B2 (en) Prediction and isolation of patterns across datasets
US20230112576A1 (en) Techniques for data processing predictions
WO2022178192A1 (en) Reputation management and machine learning systems and processes
CN111522724A (en) Abnormal account determination method and device, server and storage medium
CN111598360A (en) Service policy determination method and device and electronic equipment
CN110348669B (en) Intelligent rule generation method, intelligent rule generation device, computer equipment and storage medium
US20140214826A1 (en) Ranking method and system
CN116450723A (en) Data extraction method, device, computer equipment and storage medium
CN116089490A (en) Data analysis method, device, terminal and storage medium
CN116541760A (en) User grouping processing method, electronic device and computer readable storage medium
CN113438374B (en) Intelligent outbound call processing method, device, equipment and storage medium
CN114925275A (en) Product recommendation method and device, computer equipment and storage medium
TW202006617A (en) Cloud self-service analysis platform and analysis method thereof
CN113934894A (en) Data display method based on index tree and terminal equipment
CN109325198B (en) Resource display method and device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination