CN114022177B

CN114022177B - Intelligent grouping method and device for client data and electronic equipment

Info

Publication number: CN114022177B
Application number: CN202111134408.4A
Authority: CN
Inventors: 宋碧莲; 李盛刚; 祁云峰
Original assignee: Shanghai Hualong Information Technology Co ltd
Current assignee: Shanghai Hualong Information Technology Co ltd
Priority date: 2021-09-27
Filing date: 2021-09-27
Publication date: 2023-08-18
Anticipated expiration: 2041-09-27
Also published as: CN114022177A

Abstract

The application relates to the technical field of computers, in particular to an intelligent grouping method, device and electronic equipment of client data, which comprise the following steps: reading resource data through a standardized data template; acquiring customer personality characteristics according to the resource data and generating a customer portrait; generating cold-start type unsupervised client clustering according to the client portrait and an unsupervised clustering algorithm; grouping analysis and grouping feature expansion are carried out on the grouping result, and grouping images are obtained; obtaining a model label according to the filtering condition, and generating a model corresponding to the model label according to the clustered portraits; and collecting and analyzing benefits according to the model corresponding to the model label and the grouping portraits, and recommending market activities suitable for clients according to analysis results. The application reduces the operation cost and consumes less time; the user can flexibly establish different customer grouping scores according to the needs; the operation effect can be obtained more effectively, and the functions of value measurement and operation cycle optimization are realized.

Description

Intelligent grouping method and device for client data and electronic equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to an intelligent grouping method and apparatus for client data, and an electronic device.

Background

Some products with similar functions are available on the market, but the types and the functional ranges of the data aimed at are essentially different. Similar products now include the following marketing software systems: SELLUTION, rayleigh systems, freshmarter, sharpSpring, friendship systems, etc., where some systems develop market customer activity by unsupervised classification of data, such as SELLUTION and freshmarter; some are more biased towards customer relationship management, such as a user friendly system; some favor non-standardized integrated solutions such as the rayleigh system. We now describe the feature points of these systems as follows:

(1) SELLUTION: the system analyzes and subdivides the crowd according to the basic information of the clients. The software user can further generate a feature intelligent list according to the characteristics of client grouping, namely, the stored search of the contact person is realized. In addition, the search may be dynamically updated based on conditions. Email marketing may then be performed using the system, i.e., subdividing the customer base via the sales system to use the underlying customer profile in generating intelligent email marketing campaigns, with the final goal of increasing the conversion rate of the value customers. But the system data is not for transaction type retail data, nor is there a data normalization process. The intelligent modeling type is relatively single, such as providing only unsupervised customer groupings. Finally, the sales channel is too monotonous, i.e. mostly depends on the email popularization channel.

(2) Rayleigh system: this system provides an analysis-data analysis integrated solution. Including systems similar to BI (Business Intelligent), such as custom views, reports, dashboards and 360 degree customer queries. The system also comprises a client relation management system for realizing client archive management. In addition, the system can also perform grouping according to BI analysis so as to realize the processes of post-marketing follow-up and the like of market activities. The digital marketing of the system is not performed by a specific intelligent model, but is performed based on a BI mode. Moreover, the entire flow is not based on standardized software products, and in essence, the rayleigh system is an integrated solution, with implementations that rely on custom customization rather than through standardized products.

(3) Freshmarks: the system has the biggest characteristics of providing a triggered marketing function and being high in real-time performance. In addition, the system provides a variety of sales service functions, such as custom rules that can be built using branching logic, and the logic can interpret each stage guest behavior and differences. Setting up triggered messaging to deliver customer behavior is accomplished through a heatmap tool that provides summaries of visitor clicks and mouse movements in real time based on buried points. At the same time, the user may also track revenue and measure the value generated per click. In addition, the system provides tools that allow a user to detect device types and can generate heatmaps for mobile devices, tablet computers, and desktop devices. Channel analysis tools may help users identify visitor churn on multiple pages of web sites, etc. The system also provides classical a/B testing and funnel analysis, etc. In terms of intelligence, its primary function relies on unsupervised learning to establish customer groupings, and to conduct marketing campaigns in the form of sub-email sales. The disadvantage of this system is that no supervised learning method is used to construct various marketing models and no predictive score for the customer is used to discover potential customers, nor is it of course capable of data normalization or building different target models. Finally, the sales channel is too monotonous, i.e. mostly depends on the email popularization channel.

(4) Friend utilization system: the system is a sales management tool based on the customer lifecycle. Its main functions include tracking sales leads, customer base information and behavior management, recording and searching business opportunities, contract management, payment, fee and payback management, etc. The system also realizes diversified management and optimization in the aspect of sales channels, such as realizing automatic engine triggering of clients through automatic short messages and mails, and can also be interconnected with WeChat and application programs to realize interaction with clients so as to promote sales. In addition, the friend using system has value and analysis function in profit, such as funnel and conversion rate analysis and other analysis tools. In general, the user friendly system is a customer relationship management tool that tracks sales flows and implements a visual sales process. The system has the defects of machine learning and intelligent modeling, so that the system is a management system based on historical information, namely adding, deleting, modifying, searching, trading and summarizing reports. Although the system manages the clients in a full life cycle, the whole process does not have the functions of prediction and client grouping portrayal.

Disclosure of Invention

The application provides an intelligent grouping method, device and electronic equipment for client data, which are used for reducing operation cost and consuming less time; the user can flexibly establish different customer grouping scores according to the needs, so that the operation effect can be obtained more effectively, and the functions of value measurement and operation cycle optimization are realized. .

The embodiment of the specification provides an intelligent grouping method of client data, which comprises the following steps:

reading resource data through a standardized data template, wherein the resource data comprises transaction data, client history data and operation reflux data;

acquiring customer personality characteristics according to the resource data and generating a customer portrait;

generating cold-start type unsupervised client clustering according to the client portrait and an unsupervised clustering algorithm;

the clustering result of the cold-start type unsupervised client clustering is subjected to clustering analysis and clustering feature expansion, and a clustering image is obtained;

obtaining a model label according to the filtering condition, and generating a model corresponding to the model label according to the clustered portraits;

and collecting and analyzing benefits according to the model corresponding to the model label and the grouping portraits, and recommending market activities suitable for clients according to analysis results.

Preferably, the step of obtaining the customer personality characteristics and generating the customer portrait according to the resource data includes:

generating the customer personality characteristics according to the resource data or the customer in an interactive mode and preferences;

performing feature maintenance on the customer personality characteristics through a customer interface to generate the customer representation, wherein the feature maintenance comprises: feature addition, feature deletion and feature query.

Preferably, the step of performing the grouping analysis and the grouping feature expansion on the grouping result of the cold-start type unsupervised client grouping includes:

checking and adjusting the grouping result to obtain a final grouping result;

and adopting a data analysis method to expand the grouping characteristics of the final grouping result.

Preferably, said checking and adjusting the grouping result includes:

checking grouping effect according to grouping result;

and adjusting the grouping result by adjusting the parameter of the unsupervised grouping algorithm and adjusting the observation method.

Preferably, the obtaining the model tag according to the filtering condition includes:

setting filtering conditions according to the requirements of users;

and filtering the customer personality characteristics according to the filtering conditions to generate model labels.

Preferably, the generating a model corresponding to the model tag according to the clustered image includes:

selecting a model label under the operation of a user;

constructing a model corresponding to the model tag according to the model tag;

training the model corresponding to the model tag according to the customer personality characteristics corresponding to the grouping portraits;

and performing parameter setting and adjustment on the model corresponding to the model label by adopting a classification algorithm and a regression algorithm to generate a final model corresponding to the model label.

Preferably, the collecting and analyzing the benefits according to the model corresponding to the model label and the grouping portraits includes:

performing benefit summarization on each grouping based on summarization historical data and summarization operation reflux data;

and comparing and analyzing the benefit summary of each group by an AB test method.

The embodiment of the specification also provides an intelligent grouping apparatus for client data, which is characterized by comprising:

the resource acquisition module is used for reading resource data through a standardized data template, wherein the resource data comprises transaction data, client history data and operation reflux data;

the portrait generation module acquires the individual characteristics of the client according to the resource data and generates a client portrait;

the grouping generation module is used for generating cold-start type unsupervised customer groupings according to the customer portraits and an unsupervised grouping algorithm;

the grouping image acquisition module is used for carrying out grouping analysis and grouping characteristic expansion on the grouping result of the cold-start type unsupervised client grouping to acquire a grouping image;

the model generation module acquires a model label according to the filtering condition and generates a model corresponding to the model label according to the grouping portraits;

and the benefit summarizing module is used for summarizing and analyzing the benefits according to the model corresponding to the model label and the grouping portraits and recommending the benefits to the market activity suitable for the clients according to the analysis result.

An electronic device, wherein the electronic device comprises:

a processor and a memory storing computer executable instructions that, when executed, cause the processor to perform the method of any of the above.

A computer readable storage medium storing one or more programs which, when executed by a processor, implement the method of any of the preceding claims.

The beneficial effects are that:

the application effectively expands the grouping portrait characteristics through cold start unsupervised grouping, and the digital operation mode has low operation cost and less time consumption; the user can flexibly establish different customer grouping scores according to the needs; the system platform adopts cold start and intelligent grouping to carry out market operation, so that the operation effect can be obtained more effectively, and the functions of value measurement and operation cycle optimization are realized.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

fig. 1 is a schematic diagram of an intelligent grouping method for client data according to an embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of an intelligent grouping apparatus for client data according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of a computer readable medium according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present application will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the application to those skilled in the art. The same reference numerals in the drawings denote the same or similar elements, components or portions, and thus a repetitive description thereof will be omitted.

The features, structures, characteristics or other details described in a particular embodiment do not exclude that may be combined in one or more other embodiments in a suitable manner, without departing from the technical idea of the application.

In the description of specific embodiments, features, structures, characteristics, or other details described in the present application are provided to enable one skilled in the art to fully understand the embodiments. However, it is not excluded that one skilled in the art may practice the present application without one or more of the specific features, structures, characteristics, or other details.

The drawings shown in the figures are merely exemplary and do not necessarily include all of the content and operations/steps nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The term "and/or" and/or "includes all combinations of any one or more of the associated listed items.

Referring to fig. 1, a schematic diagram of an intelligent grouping method for client data according to an embodiment of the present disclosure includes:

s101: reading resource data through a standardized data template, wherein the resource data comprises transaction data, client history data and operation reflux data;

in the preferred embodiment of the present application, standardized data templates are set prior to resource data reading, which is the preparation for initializing transactional data and embedding the system of the present application. The data template comprises a feature name comparison table, data feature type setting, attribute description, table names, classification feature value setting and the like. The classification characteristic value settings are based on pre-specified default options, but the user can flexibly change, such as settings for holidays to which the sales period belongs, etc., and these initial information can be stored in a permanent external file, while the present application can update these settings based on data and user requirements. And the resource data is read into the system based on these settings. Data initialization normalization: including data field names, standardization of data types, and augmentation field descriptions. The main process is to rename the data characteristic column, mark the data type and field description by using a computer program according to the initializing table information. And storing the read external data file into a memory through data analysis, and then changing the data structure according to the setting of the initialization table. By setting a standardized template, all transaction data are standardized in terms of names, data types, missing value processing and the like, and all transaction order data can be embedded into the system in a seamless manner in the processing process.

And meanwhile, the tree list control is adopted to place the original data column characteristics on the tree nodes. This saves space and facilitates operations such as expansion, contraction, etc.; the computer interactive programming is adopted, so that a user can select different features in the tree form table to observe respectively, and also can perform customized condition query to return a sub-data set or a sub-feature column.

S102: acquiring customer personality characteristics according to the resource data and generating a customer portrait;

in the preferred embodiment of the application, the customer personality characteristics are obtained through analysis and processing of the resource data, and the customer portrait is generated. For example, a series of customer behavior features are generated based on the customer number of the trade order, trade behavior, time period, quantified information, statistics, etc., while the user may autonomously generate custom customer personality features based on preferences in an interactive manner, such as in a credit card business, the amount of use and the credit card line are two separate features, but the user may set new features, such as: utilization = amount used/credit card amount, and then the average utilization of the credit card over the past three months is formed by aggregation. The basic dimensions used herein are exemplified by banking customer imaging systems, and reference may be made to the following basic dimensions:

service dimension: deposit, loan, financing, etc., where all business is included as a class;

product dimension: all levels of classified products in each business topic are referred to, wherein all products in the business topic are included as one type; '

Behavior dimension: holding, entering account, exiting account, buying, switching on and off, customer payment, bank payment, etc.;

money dimension: handling fees, premium, main service money, etc.;

metering dimension: times, transaction amount, balance, proportion, time distance, etc.;

time dimension: within one month, within three months, within one year, etc.;

statistics dimension: such as average, sum, increment, maximum, minimum, variance, etc.;

channel dimension: application programs, offline, weChat, SMS, lobby, holiday, etc.

The generated customer personality characteristics are then maintained through the user interface. Such as adding, deleting, modifying, checking, etc., permanently storing the generated customer personality traits and corresponding program code.

S103: generating cold-start type unsupervised client clustering according to the client portrait and an unsupervised clustering algorithm;

in a preferred embodiment of the application, the system performs unsupervised clustering based on previously generated personal representations. The algorithm adopts K-means to combine Linkage clustering, and the system provides a plurality of typical grouping templates in advance, wherein the grouping is based on a plurality of specific customer summarization characteristics; in particular, the user may select the features in a customized manner according to the needs, for example, after the user generates the utilization rate in the credit card service above, the utilization rate and the age group information are added into the feature group to participate in grouping.

After the unsupervised clients are clustered, the system provides a summary of the features of each cluster based on the summary of the information. These composite features will be normalized to an index to indicate the uniqueness of each cluster, such as an age-average index of 2 for the first cluster, 7 for the second cluster, 9 for the last purchase, 5 for the second cluster, etc.

S104: the clustering result of the cold-start type unsupervised client clustering is subjected to clustering analysis and clustering feature expansion, and a clustering image is obtained;

in a preferred embodiment of the present application, according to the grouping result in the previous step, the user can observe the grouping effect, such as the number of group samples and the separability performance index among the groups, and consult the separation index through data grouping summary, and the separation index is graphically and visually displayed, such as an unsupervised grouping model diagram. The user can then adjust and improve the grouping effect by adjusting the parameters of the unsupervised grouping algorithm and manually adjusting the observation. And after the grouping characteristic expansion function is established according to the last customer grouping result of the last step, adopting a data analysis method, namely, summarizing the grouping image through retrospective research. Unlike personalized customer portrayal features, these clustered portrayal features can be directly applied to intelligent marketing operations; while preserving the above useful information to the persistent file.

S105: obtaining a model label according to the filtering condition, and generating a model corresponding to the model label according to the clustered portraits;

in the preferred embodiment of the present application, the user can provide various conditions for model object generation through interactive operation of input conditions according to some key characteristics, and various logic operations are included. The system program may convert the above conditions into program code recognizable by the computer system, generate feature columns from the above program code access and operation data, and give names, for example: for example, the following rules are selected to determine a 0,1 model goal, a specific time period is selected as a past period of time, such as 3 years and the next year to set a model prediction, goal period time window; meanwhile, the user can establish a relatively complex market retention goal through the liveness option. Wherein the result feature column is the model target. And according to various established model targets, establishing a prediction model by utilizing an intelligent algorithm, realizing client scoring and grouping, performing grouping analysis, and verifying a trend summary model. Here, intelligent grouping can be performed using single or combined model scores, and the user can flexibly customize various groupings to the evidence intended effect.

Then, a corresponding model is established according to the information, and the model depends on two factors: model object definition and a particular grouping. Wherein model objects must be generated and saved to a persistent file immediately after definition and typed with specialized notations. The user may perform post-maintenance, such as naming, modification, etc., based on the meaning of each model object. Whereas each rule originates from a target definition rule base, such as rule 1 corresponds to a rule of "more than 1000 yuan for a future three month purchase. The rules may in turn be decomposed into computer-recognizable command statements based on semantics. For the second factor "a certain specific grouping", which is the sample data used for establishing the model, the use of a certain customer grouping depends on the choice of the user, which may be based on the result of previous customer unsupervised groupings or on the field choice of the user, for example, the user may establish a retention score model exclusively among the customer population with gender "female". The benefit of cluster modeling is flexibility such that the model is specific to the population of interest; the accuracy of the model tends to increase as the data range is narrowed, and of course, the system will automatically give an alarm such as an overfitting, and if the sample is too small, the system will prompt risk information such as an overfitting, because the system will have some default threshold or a threshold set by the user.

The user may model the data by classification according to certain classification rules. Several machine learning methods are provided herein including classification and regression, which also include parameter setting and adjustment. And (3) analyzing the result characteristic column through data verification to obtain information such as target rate, sample number, various statistical analysis patterns and the like, and then enabling a user to correspondingly adjust according to the information. The above result features are listed in a persistent file.

S106: and collecting and analyzing benefits according to the model corresponding to the model label and the grouping portraits, and recommending market activities suitable for clients according to analysis results.

In a preferred embodiment of the present application, the benefit summary and analysis is performed according to the various models generated in the previous step and the clusters generated by the previous cold-start unsupervised client cluster module by:

performing benefit value assessment based on historical data involves calculating cost, profit, equity or sales channel summaries generated by each cluster.

Based on the operation reflux data, such as customer response, purchase amount, expense and the like, the cost and profit generated by each grouping are calculated through analysis of an AB test method, and the rights and interests or sales channel profits are summarized and compared, and then valuable information is output according to the selection of a user and saved to a permanent file.

Further, the step of obtaining the customer personality characteristics and generating the customer portrait according to the resource data includes:

In a preferred embodiment of the present application, customer behavior features are formed as a series of customer behavior features based on the customer number, transaction behavior, time period, quantitative information, and statistics of the transaction order, while the user can automatically interactively generate custom customer personality features based on preferences. And then the client interface performs feature maintenance on the client personality characteristics to generate the client portrait, wherein the feature maintenance comprises: feature augmentation, feature deletion, feature query, etc.

Further, the classifying analysis and classifying feature expansion of the classifying result of the cold-start type unsupervised client classifying include:

checking and adjusting the grouping result to obtain a final grouping result;

In the preferred embodiment of the present application, according to the grouping result, the user can observe the grouping effect, such as the number of group samples and the separability index between the groups, and review the separation index through data grouping summary, and display the separation index graphically and visually, such as an unsupervised grouping model diagram. And after the grouping characteristic expansion function is established according to the last customer grouping result of the last step, adopting a data analysis method, namely, summarizing the grouping image through retrospective research. Unlike personalized customer portrayal features, these clustered portrayal features can be directly applied to intelligent marketing operations; while preserving the above useful information to the persistent file.

Further, the checking and adjusting the grouping result includes:

checking grouping effect according to grouping result;

In a preferred embodiment of the present application, the user may observe the grouping effect, such as the number of group samples, the separability index between groups, review of the separability index by data grouping summary, and visual display of graphics, such as an unsupervised grouping canonical chart. The user can adjust and improve the grouping effect by adjusting the parameter of the unsupervised grouping algorithm and manually adjusting the observation method.

Further, the obtaining the model tag according to the filtering condition includes:

setting filtering conditions according to the requirements of users;

In the preferred embodiment of the application, a user can set the filtering conditions according to the self requirements, so that a targeted model label is generated, model targets in different occasions can be flexibly designated according to the requirements, different customer grouping scores can be established, and the operation effect can be more effectively obtained.

Further, the generating a model corresponding to the model tag according to the clustered image includes:

selecting a model label under the operation of a user;

constructing a model corresponding to the model tag according to the model tag;

In the preferred embodiment of the application, a user selects a model label which needs to be operated according to the self requirement, then builds a model corresponding to the model label, trains the model according to sample data, and simultaneously adopts a classification algorithm and a regression algorithm to set and adjust parameters of the model corresponding to the model label so as to build the model. Wherein the sample data includes customer personality traits.

Further, the collecting and analyzing the benefits according to the model corresponding to the model label and the grouping portraits comprises the following steps:

In the preferred embodiment of the present application, the benefit summary and analysis is performed according to the generated models and the clusters generated by the cold-start unsupervised client cluster module, as follows:

In the preferred embodiment of the application, the system will capture and output any valuable information: such as high value customers during a time period, about to lose customers during a time period, equity response customers, weighted combinations of these scores, etc. And (5) utilizing the grouping generated by the model to carry out grouping summarization of sales, profits and cost, so that the user can clearly determine the effect of the model. The value is optimized through factors such as customer lists, channel positioning and the like so as to develop various market strategies.

The system is convenient to operate, can be used by data analysis and business personnel with less training, performs unified standardized management on data of each retail industry, and can be embedded into the system without seams; the system and the use interface can help the company to carry out pre-sale training, demonstration and guidance on clients and pre-sale personnel; the feature of the clustered portraits is effectively expanded through cold-starting unsupervised clustering, and the digital operation mode has low operation cost and less time consumption; the user can flexibly establish different customer grouping scores according to the needs; the system platform adopts cold start and intelligent grouping to carry out market operation, so that the operation effect can be obtained more effectively, and the functions of value measurement and operation cycle optimization are realized.

Fig. 2 is a schematic structural diagram of an intelligent grouping apparatus for client data according to an embodiment of the present disclosure, including:

a resource acquisition module 201, which reads resource data through a standardized data template, wherein the resource data comprises transaction data, customer history data and operation reflux data;

a portrait creation module 202 for obtaining the individual characteristics of the client based on the resource data and creating a portrait of the client;

a grouping generation module 203 for generating a cold-start type unsupervised customer grouping according to the customer representation and an unsupervised grouping algorithm;

a grouping image acquisition module 204 for performing grouping analysis and grouping feature expansion on the grouping result of the cold-start type unsupervised client grouping to acquire a grouping image;

a model generation module 205 that obtains a model tag according to the filtering condition and generates a model corresponding to the model tag according to the group representation;

and the benefit summarizing module 206 is used for summarizing and analyzing the benefits according to the model corresponding to the model label and the grouping portraits and recommending the benefits to the market activity suitable for the clients according to the analysis result.

Based on the same inventive concept, the embodiments of the present specification also provide an electronic device.

The following describes an embodiment of an electronic device according to the present application, which may be regarded as a specific physical implementation of the above-described embodiment of the method and apparatus according to the present application. Details described in relation to the embodiments of the electronic device of the present application should be considered as additions to the embodiments of the method or apparatus described above; for details not disclosed in the embodiments of the electronic device of the present application, reference may be made to the above-described method or apparatus embodiments.

Referring to fig. 3, a schematic structural diagram of an electronic device according to an embodiment of the present disclosure is provided. An electronic device 300 according to this embodiment of the present application is described below with reference to fig. 3. The electronic device 300 shown in fig. 3 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present application.

As shown in fig. 3, the electronic device 300 is embodied in the form of a general purpose computing device. Components of electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one memory unit 320, a bus 330 connecting the different device components (including the memory unit 320 and the processing unit 310), a display unit 340, and the like.

Wherein the storage unit stores program code that is executable by the processing unit 310 such that the processing unit 310 performs the steps according to various exemplary embodiments of the application described in the above processing method section of the present specification. For example, the processing unit 310 may perform the steps shown in fig. 1.

The memory unit 320 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 3201 and/or cache memory 3202, and may further include Read Only Memory (ROM) 3203.

The storage unit 320 may also include a program/utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including, but not limited to: operating devices, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

Bus 330 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 300, and/or any device (e.g., router, modem, etc.) that enables the electronic device 300 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 350. Also, electronic device 300 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 via the bus 330. It should be appreciated that although not shown in fig. 3, other hardware and/or software modules may be used in connection with electronic device 300, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID devices, tape drives, data backup storage devices, and the like.

From the above description of embodiments, those skilled in the art will readily appreciate that the exemplary embodiments described herein may be implemented in software, or may be implemented in software in combination with necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a computer readable storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, or a network device, etc.) to perform the above-mentioned method according to the present application. The computer program, when executed by a data processing device, enables the computer readable medium to carry out the above-described method of the present application, namely: such as the method shown in fig. 1.

Referring to fig. 4, a schematic diagram of a computer readable medium according to an embodiment of the present disclosure is provided.

A computer program implementing the method shown in fig. 1 may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an apparatus, device, or means for electronic, magnetic, optical, electromagnetic, infrared, or semiconductor, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution apparatus, device, or apparatus. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

In summary, the application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in accordance with embodiments of the present application may be implemented in practice using a general purpose data processing device such as a microprocessor or Digital Signal Processor (DSP). The present application can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

The above-described specific embodiments further describe the objects, technical solutions and advantageous effects of the present application in detail, and it should be understood that the present application is not inherently related to any particular computer, virtual device or electronic apparatus, and various general-purpose devices may also implement the present application. The foregoing description of the embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the application.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. An intelligent grouping method for client data, comprising:

2. The intelligent grouping method of client data as in claim 1, wherein said obtaining client personality traits from said resource data and generating client portraits comprises:

3. The intelligent grouping method of client data as set forth in claim 1, wherein said performing a grouping analysis and a grouping feature expansion on the grouping result of the cold-start unsupervised client grouping includes:

checking and adjusting the grouping result to obtain a final grouping result;

4. A method of intelligent grouping of customer data as in claim 3 wherein said verifying and adjusting said grouping result comprises:

checking grouping effect according to grouping result;

5. The intelligent grouping method of client data as set forth in claim 1, wherein the obtaining model tags based on filtering conditions comprises:

setting filtering conditions according to the requirements of users;

6. The intelligent grouping method of claim 1, wherein said generating a model corresponding to said model tag from said clustered representation comprises:

selecting a model label under the operation of a user;

constructing a model corresponding to the model tag according to the model tag;

7. The intelligent grouping method of client data as set forth in claim 1, wherein the performing benefit summarization and analysis according to the model corresponding to the model tag and the grouping portraits comprises:

8. An intelligent grouping apparatus for client data, comprising:

9. An electronic device, wherein the electronic device comprises:

a processor and a memory storing computer executable instructions that, when executed, cause the processor to perform the method of any of claims 1-7.

10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-7.