CN117709801A

CN117709801A - Client data processing method, device, computer equipment and storage medium

Info

Publication number: CN117709801A
Application number: CN202410028239.3A
Authority: CN
Inventors: 严杨扬
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2024-01-05
Filing date: 2024-01-05
Publication date: 2024-03-15

Abstract

The embodiment of the application belongs to the fields of artificial intelligence and financial science and technology, and relates to a client data processing method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: inputting customer data into a customer evaluation model to obtain conversion scores of target customers in the current evaluation, wherein the customer data comprises a plurality of characteristic categories, and each characteristic category comprises at least one customer characteristic; acquiring the feature contribution degree and the feature category of each client feature to calculate the covariance base of each client feature in the current evaluation; obtaining a conversion score of a target client in previous evaluation and covariance base of each client characteristic; based on the obtained covariance base, calculating covariance of the previous evaluation and the current evaluation on each characteristic category; and generating a client analysis result of the target client according to the conversion score in the current evaluation, the conversion score in the previous evaluation and the covariance of the previous evaluation and the current evaluation on each characteristic category. The method and the device improve the accuracy of customer analysis.

Description

Client data processing method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence and financial science and technology, and in particular, to a client data processing method, apparatus, computer device, and storage medium.

Background

The enterprises can accumulate and store a large amount of client data through production and living activities, and the enterprises can process the client data frequently so as to achieve the purposes of client analysis and the like. For example, in the financial insurance industry, an insurance company may obtain customer data from a questionnaire or an existing customer, input the customer data into a model to predict conversion rate of the customer, and the like. However, the current customer data processing technology only performs a single customer data processing and customer analysis after obtaining the customer data of a certain customer, and only outputs the result according to the whole of the customer data, belongs to a black box model, and lacks of interpretability, which reduces the accuracy of the customer analysis according to the customer data.

Disclosure of Invention

An embodiment of the application aims to provide a client data processing method, device, computer equipment and storage medium, so as to solve the problem of low accuracy when client analysis is performed according to client data.

In order to solve the above technical problems, the embodiments of the present application provide a client data processing method, which adopts the following technical schemes:

Acquiring current client data of a target client, wherein the client data comprises a plurality of feature categories, and each feature category comprises at least one client feature;

inputting the client data into a client evaluation model to obtain a conversion score of the target client in the current evaluation;

acquiring a characteristic contribution degree corresponding to each predetermined customer characteristic and a characteristic category to which each predetermined customer characteristic belongs;

calculating covariance base of each client feature in current evaluation according to the feature contribution degree, feature class and feature value of each client feature;

obtaining a conversion score of the target client in the previous evaluation and a covariance base of each client characteristic;

calculating covariance of the previous evaluation and the current evaluation on each characteristic category based on the obtained covariance base;

and generating a client analysis result of the target client according to the conversion score in the current evaluation, the conversion score in the previous evaluation and the covariance of the previous evaluation and the current evaluation on each characteristic category.

In order to solve the above technical problems, the embodiments of the present application further provide a client data processing apparatus, which adopts the following technical schemes:

The data acquisition module is used for acquiring current client data of a target client, wherein the client data comprises a plurality of feature categories, and each feature category comprises at least one client feature;

the current evaluation module is used for inputting the client data into a client evaluation model to obtain a conversion score of the target client in the current evaluation;

the acquisition module is used for acquiring the characteristic contribution degree and the characteristic category which are respectively corresponding to the predetermined client characteristics;

the current calculation module is used for calculating the covariance base of each client feature in the current evaluation according to the feature contribution degree, the feature class and the feature value of each client feature;

the previous acquisition module is used for acquiring conversion scores of the target clients in previous evaluation and covariance bases of the client features;

a covariance calculation module, configured to calculate covariance of the previous evaluation and the current evaluation on each feature class based on the obtained covariance base;

and the result generation module is used for generating a client analysis result of the target client according to the conversion score in the current evaluation, the conversion score in the previous evaluation and the covariance of the previous evaluation and the current evaluation on each characteristic category.

In order to solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the following technical schemes:

In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:

Compared with the prior art, the embodiment of the application has the following main beneficial effects: acquiring current client data of a target client, wherein the client data comprises a plurality of feature categories, and each feature category comprises at least one client feature; inputting the client data into a client evaluation model to obtain a conversion score of the target client in the current evaluation, wherein the conversion score represents the possibility of the target client to realize conversion; acquiring a characteristic contribution degree corresponding to each predetermined customer characteristic and a characteristic category to which each predetermined customer characteristic belongs; calculating covariance base of each client feature in current evaluation according to the feature contribution degree, feature class and feature value of each client feature; obtaining a conversion score of a target client in previous evaluation and covariance base of each client characteristic; taking the covariance base of each client feature in the previous evaluation of each feature class as the value of one variable, taking the covariance base of each client feature in the current evaluation as the value of another variable, calculating the covariance of the previous evaluation and the current evaluation on each feature class, wherein the covariance reflects the integral influence of each feature class on the conversion score in different evaluation periods, so that the model is not a black box model any more, and has interpretability, and the periodic evaluation can dynamically consider the conversion score fluctuation of a target client in different time nodes; according to the transformation scores in the current evaluation, the transformation scores in the previous evaluation and the covariance of the previous evaluation and the current evaluation on each characteristic category, a client analysis result of a target client is generated, and the accuracy, the comprehensiveness and the interpretability of client analysis according to client data can be greatly improved.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of a customer data processing method according to the present application;

FIG. 3 is a schematic diagram of one embodiment of a client data processing apparatus according to the present application;

FIG. 4 is a schematic structural diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.

It should be noted that, the client data processing method provided in the embodiments of the present application is generally executed by a server, and accordingly, the client data processing apparatus is generally disposed in the server.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of a customer data processing method according to the present application is shown. The client data processing method comprises the following steps:

In step S201, current client data of the target client is obtained, the client data includes a plurality of feature categories, and each feature category includes at least one client feature.

In this embodiment, the electronic device (e.g., the server shown in fig. 1) on which the client data processing method operates may communicate with the terminal device through a wired connection or a wireless connection. It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.

Specifically, the present application can perform the client data processing at regular intervals, and thus can acquire the client data of the target client at regular intervals. For example, with the week as the update frequency, the client data processing instruction is triggered at a fixed time of each week, and the latest client data of each target client is obtained according to the client data processing instruction.

The customer data comprises a plurality of feature categories, the feature categories being feature categories, each feature category comprising at least one customer feature. The feature class and the customer features contained in the feature class are predetermined. For example, in the field of financial insurance, customer data acquired by an insurance company is feature data of a customer of a vehicle insurance service before an underwriting period, and feature categories included in the customer data and customer features included in each feature category are as follows:

1. Customer base feature class: age, city, sex, age of vehicle, brand of vehicle, value of vehicle, etc.;

2. manual history contact characteristics class: contact duration, number of contacts, contact time period, customer intent, etc.;

3. AI (artificial intelligence) history contact feature class: contact duration, contact times, contact time period, interaction turn, customer intent, etc.; (insurance company can make contact with customer through AI)

4. Specify app operation class: designating app return number, price reporting number, interaction round, active days and the like;

5. online active class: app active data, web page active data, breakpoint data, etc.

Further, before the step S201, the method may further include: acquiring sample data of each sample client, wherein the sample data comprises conversion labels of the sample clients; training an initial customer evaluation model according to sample data of each sample customer to obtain a customer evaluation model, and obtaining feature contribution degree of each customer feature in the sample data after training is finished, wherein the initial customer evaluation model is a tree model.

Specifically, the application requires that a customer assessment model be obtained in advance through training. The customer assessment model is used for outputting a conversion score of the customer according to the customer data, wherein the conversion score represents the possibility of realizing conversion of the customer in the form of a score.

During training, sample data of each sample client is acquired, and client features contained in the sample data are the same as those contained in the client data. The sample data contains a conversion label of the sample customer, wherein the conversion label indicates whether the customer realizes conversion (namely, the customer purchases the product to realize conversion) under the time node of product recommendation or sales. With the above example, under the time node of the historical vehicle insurance sales, if the client has underwriting, the client is considered to implement conversion, the conversion label is 1, otherwise, it is 0.

The initial customer assessment model is trained from sample data for each sample customer, wherein the conversion tags will be the expected output of the initial customer assessment model for each sample data. After training is finished, a customer assessment model can be obtained.

In this application, the initial customer assessment model/customer assessment model is a tree model, such as random forest, lightGBM, etc. After the training is finished, the tree model can automatically obtain the feature contribution degree of each client feature, and the feature contribution degree represents the importance of the feature. The tree model considers the split point of each feature in the construction process to determine which features are most helpful for the prediction of the target variable. The feature contribution is used to measure the contribution of each feature to the model performance and can help identify which features play a key role in the prediction and which features have a greater impact on the accuracy of the model. Feature contribution is typically calculated based on the frequency of splitting of the features in the model and the degree of reduction in the degree of non-purity after splitting. Random forests and other integrated tree models can typically provide importance scores for each feature, which are calculated from the training process of the model and the splitting situation of the tree nodes. Random forests typically use Gini importance or keni importance to measure the contribution of each feature to the model; the importance score represents the effect of each feature in each decision tree of the model for segmenting the data, with higher Gini importance scores representing that the feature is more discriminative for segmentation of the data. If multiple decision trees are used to construct a random forest, the average importance of each feature can be calculated to comprehensively consider the contribution of each tree.

In this embodiment, sample data of each sample client is obtained, where the sample data includes a conversion tag of the sample client; training an initial customer evaluation model according to sample data of each sample customer to obtain a customer evaluation model; because the initial customer evaluation model is a tree model, the feature contribution degree of each customer feature in the sample data can be obtained after training is finished, so that model preparation and data preparation are performed for subsequent customer analysis.

Step S202, inputting the client data into a client evaluation model to obtain the conversion score of the target client in the current evaluation.

Specifically, the client data is input into a client assessment model to obtain a conversion score of the target client in the current assessment, wherein the value interval of the conversion score is [0,100].

Further, the step S202 may include: inputting the client data into a client evaluation model to obtain the conversion probability of the target client; and generating a conversion score of the target client in the current evaluation according to the conversion probability.

Specifically, the client data is input into a client assessment model, the client assessment model outputs the conversion probability of the target client, and the conversion probability represents the possibility of realizing conversion of the target client in assessment in a numerical value, wherein the value interval is [0,1]. In the foregoing example, the conversion probability is the underwriting probability of the target client.

The conversion probability of the target clients can be further integrated to score the target clients, the target clients are uniformly distributed with 100 shares in sequence from low conversion probability to high conversion probability, and the score with the value between 0 and 100 points is attached to serve as the conversion score of the target clients.

In the embodiment, the client data is input into the client evaluation model to obtain the conversion probability of the target client, and then the conversion probability is converted into the conversion score of the target client in the current evaluation, so that the possibility of representing the conversion of the client by the score is realized, the data standardization is realized, and the display and the understanding of the data are facilitated.

Step S203, the feature contribution degree and the feature category to which each predetermined client feature corresponds are obtained.

Specifically, before each evaluation, the feature contribution degree of each client feature and the feature class to which each client feature belongs are determined, and the feature contribution degree and the feature class can be obtained directly through table lookup. It will be appreciated that the feature class and the customer features contained by the feature class may be adjusted; if the customer assessment model is retrained, the feature contribution of the customer features will also need to be adjusted.

Step S204, calculating covariance base of each client feature in the current evaluation according to the feature contribution degree, the feature class and the feature value of each client feature.

Specifically, the present application incorporates covariance of two adjacent assessments on a feature class into an analysis. It will be appreciated that the feature class has at least one customer feature, and that prior to calculating the covariance, the covariance base of the customer feature in the evaluation needs to be calculated to calculate the covariance of the feature class to which the customer feature belongs based on the covariance base.

The feature contribution of each customer feature, the feature class to which it belongs, and the feature value in the current evaluation are now available from which the covariance base of that customer feature in the current evaluation can be calculated.

The customer characteristic has a characteristic value, for example, for gender, which includes "male" and "female"; the characteristic value may be different for some customer characteristics in the assessment at different points in time, for example, the characteristic may change for the number of days of activity. Thus, the covariance base may also be different in the evaluations at different time points, requiring binding to the time point or to some evaluation.

Further, the step S204 may include: for each feature class, calculating the average contribution of the feature classes according to the feature contribution of each client feature in the feature class; for each client feature, calculating the covariance base of the client feature in the current evaluation according to the feature value of the client feature and the average contribution degree of the feature class of the client feature.

Specifically, for each feature class, acquiring all customer features contained in the feature class, and acquiring feature contribution degrees of all customer features; and calculating the average value of the feature contribution degrees to obtain the average contribution degree of the feature class.

Then, for each client feature in the feature class, multiplying the feature value of the client feature by the average contribution of the feature class, and obtaining the covariance base of the client feature in the current evaluation. It will be appreciated that the multiplication here is weighting the eigenvalues, and the subsequent calculation is in fact a weighted covariance.

It will be appreciated that the feature values of the client features need to be digitally represented when participating in the calculation.

In this embodiment, for each feature class, calculating an average contribution of feature classes according to feature contribution of each client feature in the feature class; for each client feature, calculating the covariance base of the client feature in the current evaluation according to the feature value of the client feature and the average contribution degree of the feature class of the client feature, and preparing data for covariance calculation.

Step S205, the conversion score of the target client in the previous evaluation and the covariance base of each client feature are obtained.

In particular, as mentioned earlier, customer analysis may be timed, periodic. Thus, there is also a previous evaluation adjacent to the current evaluation. There is also a need to obtain the conversion score of the target customer in the previous evaluation and the covariance base of each customer feature.

Step S206, based on the obtained covariance base, calculating covariance of the previous evaluation and the current evaluation on each characteristic category.

Specifically, for each feature class, the covariance base of the client features in the feature class in the current evaluation, and the covariance base of the client features in the previous evaluation, have now been obtained. From these cardinalities, the covariance of the previous and current evaluations on the feature class may be calculated. It will be appreciated that one covariance is associated with two evaluations, and that covariance cannot be obtained based on one evaluation.

Further, the step S206 may include: for each feature class, generating a first variable value sequence according to covariance base of the client features contained in the feature class in the current evaluation; generating a second variable value sequence according to covariance base of the client features contained in the feature class in the previous evaluation; covariance over the feature class of the previous and current evaluations is calculated based on the first and second sequences of variable values.

Specifically, assuming an existing feature class 1, which contains customer features A, B, C, D whose covariance bases in the current evaluation are A1, B1, C1, D1, respectively, they can be regarded as respective values of the first variable X, resulting in a first variable value sequence { A1, B1, C1, D1}.

Assuming that the covariance bases of the client feature A, B, C, D in the previous evaluation are A0, B0, C0, D0, respectively, in the feature class 1, they can be regarded as the values of the second variable Y, and the second variable value sequence { A0, B0, C0, D0} is obtained.

Based on the first variable value sequence and the second variable value sequence, covariance of the previous evaluation and the current evaluation on the feature class can be calculated, wherein a covariance calculation formula is expressed as follows:

wherein X represents a first variable, Y represents a second variable, cov (X, Y) represents the covariance of the first variable X and the second variable Y, i.e., the covariance of the previous evaluation and the current evaluation on a certain feature class; x is X _i And Y _i Respectively representing the ith data point (namely value) in the first variable value sequence and the second variable value sequence, wherein i is used for counting the data points (values) in the variable value sequence; x and Y represent the mean of the first variable X and the second variable Y, respectively, and n represents the sample size when calculating the covariance.

In this embodiment, for each feature class, the covariance base of the client feature included in the feature class in the current evaluation is used as a first variable value sequence; taking the covariance base of the client features contained in the feature class in the previous evaluation as a second variable value sequence; based on the first variable value sequence and the second variable value sequence, covariance of the previous evaluation and the current evaluation on the characteristic category is calculated, and covariance calculation is achieved.

Step S207, generating a client analysis result of the target client according to the conversion score in the current evaluation, the conversion score in the previous evaluation and the covariance of the previous evaluation and the current evaluation on each characteristic category.

Specifically, according to the conversion score in the current evaluation and the conversion score in the previous evaluation, the score change condition of the target client in the two evaluations, namely the change condition of the conversion possibility of the target client in the two evaluations, can be obtained. The transition score fluctuations of the target client at different time nodes can be dynamically taken into account when making the timed, periodic assessment.

Covariance is a statistic that measures the relationship between two random variables. It represents the trend of two variables changing together, i.e. if one variable increases, the other also increases or decreases. Covariance can be used to learn the linear relationship between variables and how they change together.

The covariance of the previous evaluation and the current evaluation on each characteristic category is calculated, and the covariance reflects the influence of each characteristic category on the conversion score in different evaluation periods, so that the score model is not a black box model any more and has interpretability.

Therefore, the customer analysis result generated by the method and the device can contain the change condition of the conversion score, and each feature class has an important influence on the conversion score in the current evaluation and the change of the conversion score, so that a service person can know what feature classes play an important role besides knowing the conversion score and the change condition thereof, and the accuracy of customer analysis according to the customer data is ensured.

Further, the step S207 may include: respectively obtaining conversion states of a target client in the current evaluation and the previous evaluation; and generating a client analysis result of the target client according to the obtained conversion state, conversion score and covariance.

Specifically, the conversion states of the target client in the current evaluation and the previous evaluation can be obtained respectively, wherein the conversion states represent whether the target client realizes conversion or not under the time node (or in the evaluation period) of product recommendation or sales.

Under the condition that the conversion state is obtained, the influence of each characteristic category on the conversion state can be further obtained, and the richness and the accuracy of the analysis result of the client are improved. For example, table 1 shows calculated conversion scores for the current assessment of the target customer, conversion scores for the previous assessment, and covariance for 5 feature classes in one embodiment. Assuming that the transformation status of the target client is untransformed for both assessments, but the transformation score is increased from 82 to 98, the transformation probability is greatly increased, and the improvement is mainly from the feature class 5 according to covariance, while the feature class 2 has less contribution to the improvement; to further increase the transformation score, one may focus on feature class 2. If the conversion is not completed after the previous evaluation and the conversion is completed after the current evaluation, the influence of the feature class 5 on the conversion status of the target client can be considered to be large, and later, when the client similar to the target client is faced, the improvement of the feature class 5 can be focused to promote the client conversion.

TABLE 1

Customer ID	Current scoring	Previous scoring	Class 1 covariance	Class 2 covariance	Class 3 covariance	Class 4 covariance	Class 5 covariance
								0001	98	82	0.3	0.1	0.2	0.6	0.7

In the embodiment, conversion states of the target client in the current evaluation and the previous evaluation are respectively obtained; according to the obtained transformation state, transformation score and covariance, a client analysis result of the target client is generated, the influence of each characteristic category on the transformation state can be further obtained, and the richness and accuracy of the client analysis result are improved.

Further, the client analysis result includes a client service policy, and after the step of generating the client analysis result of the target client, the method may further include: and sending the customer analysis result to a salesman so that the salesman provides service for the target customer according to the customer service policy in the customer analysis result.

Specifically, the customer analysis result is sent to the salesman, where the customer analysis result includes the customer service policy, for example, the corresponding customer service policy obtained according to the feature class 5 has been enumerated above. The salesman can provide service for the target client according to the client service policy or other clients similar to the target client, so that the efficiency of client conversion is improved.

In this embodiment, the client analysis result is sent to the salesman, and the salesman provides services for the target client according to the client service policy in the client analysis result, so that the efficiency of client conversion can be improved.

In this embodiment, current client data of a target client is obtained, where the client data includes a plurality of feature classes, and each feature class includes at least one client feature; inputting the client data into a client evaluation model to obtain a conversion score of the target client in the current evaluation, wherein the conversion score represents the possibility of the target client to realize conversion; acquiring a characteristic contribution degree corresponding to each predetermined customer characteristic and a characteristic category to which each predetermined customer characteristic belongs; calculating covariance base of each client feature in current evaluation according to the feature contribution degree, feature class and feature value of each client feature; obtaining a conversion score of a target client in previous evaluation and covariance base of each client characteristic; taking the covariance base of each client feature in the previous evaluation of each feature class as the value of one variable, taking the covariance base of each client feature in the current evaluation as the value of another variable, calculating the covariance of the previous evaluation and the current evaluation on each feature class, wherein the covariance reflects the integral influence of each feature class on the conversion score in different evaluation periods, so that the model is not a black box model any more, and has interpretability, and the periodic evaluation can dynamically consider the conversion score fluctuation of a target client in different time nodes; according to the transformation scores in the current evaluation, the transformation scores in the previous evaluation and the covariance of the previous evaluation and the current evaluation on each characteristic category, a client analysis result of a target client is generated, and the accuracy, the comprehensiveness and the interpretability of client analysis according to client data can be greatly improved.

It is emphasized that to further ensure the privacy and security of the client data, the client data may also be stored in a blockchain node.

The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 3, as an implementation of the method shown in fig. 2 described above, the present application provides an embodiment of a client data processing apparatus, where an embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus is particularly applicable to various electronic devices.

As shown in fig. 3, the client data processing apparatus 300 according to the present embodiment includes: a data acquisition module 301, a current evaluation module 302, an acquisition module 303, a current calculation module 304, a previous acquisition module 305, a covariance calculation module 306, and a result generation module 307, wherein:

the data obtaining module 301 is configured to obtain current client data of a target client, where the client data includes a plurality of feature classes, and each feature class includes at least one client feature.

The current evaluation module 302 is configured to input the client data into the client evaluation model to obtain a conversion score of the target client in the current evaluation.

The obtaining module 303 is configured to obtain a feature contribution degree and a feature class to which each predetermined client feature corresponds.

The current calculation module 304 is configured to calculate a covariance base of each client feature in the current evaluation according to the feature contribution degree, the feature class and the feature value of each client feature.

A previous acquisition module 305 is configured to acquire the conversion score of the target client in the previous evaluation and the covariance base of each client feature.

Covariance calculation module 306 is configured to calculate covariance of previous and current evaluations on each feature class based on the obtained covariance base.

The result generating module 307 is configured to generate a client analysis result of the target client according to the conversion score in the current evaluation, the conversion score in the previous evaluation, and the covariance of the previous evaluation and the current evaluation on each feature class.

In some alternative implementations of the present embodiment, the client data processing apparatus 300 may further include: sample acquisition module and model training module, wherein:

the sample acquisition module is used for acquiring sample data of each sample client, wherein the sample data comprises conversion labels of the sample clients.

The model training module is used for training the initial customer evaluation model according to the sample data of each sample customer to obtain a customer evaluation model, and obtaining the characteristic contribution degree of each customer characteristic in the sample data after training is finished, wherein the initial customer evaluation model is a tree model.

In some alternative implementations of the present embodiment, the current assessment module 302 may include: the device comprises a data input sub-module and a probability conversion sub-module, wherein:

And the data input sub-module is used for inputting the client data into the client evaluation model to obtain the conversion probability of the target client.

And the probability conversion sub-module is used for generating a conversion score of the target client in the current evaluation according to the conversion probability.

In some alternative implementations of the present embodiment, the current computing module 304 may include: average calculation sub-module and radix calculation sub-module, wherein:

and the average calculation sub-module is used for calculating the average contribution degree of the feature categories according to the feature contribution degree of each client feature in the feature categories for each feature category.

And the base calculation sub-module is used for calculating the covariance base of the client feature in the current evaluation according to the feature value of the client feature and the average contribution degree of the feature class of the client feature for each client feature.

In some alternative implementations of the present embodiment, covariance calculation module 306 may include: the device comprises a first generation sub-module, a second generation sub-module and a covariance calculation sub-module, wherein:

and the first generation sub-module is used for generating a first variable value sequence according to the covariance base of the client features contained in the feature categories in the current evaluation for each feature category.

And the second generation sub-module is used for generating a second variable value sequence according to the covariance base of the client features contained in the feature class in the previous evaluation.

And the covariance calculation sub-module is used for calculating covariance of the previous evaluation and the current evaluation on the characteristic category based on the first variable value sequence and the second variable value sequence.

In some alternative implementations of the present embodiment, the result generation module 307 may include: the system comprises a state acquisition sub-module and a result generation sub-module, wherein:

and the state acquisition sub-module is used for respectively acquiring the conversion states of the target client in the current evaluation and the previous evaluation.

And the result generation sub-module is used for generating a client analysis result of the target client according to the obtained conversion state, the conversion score and the covariance.

In some alternative implementations of the present embodiment, the client data processing apparatus 300 may further include: and the result sending module is used for sending the customer analysis result to the salesman so that the salesman provides service for the target customer according to the customer service policy in the customer analysis result.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of a client data processing method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing the client data processing method.

The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.

The computer device provided in this embodiment may perform the above-described client data processing method. The client data processing method may be the client data processing method of each of the above embodiments.

The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of a client data processing method as described above.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. A method of processing customer data, comprising the steps of:

2. The client data processing method according to claim 1, further comprising, prior to the step of acquiring the current client data of the target client:

Acquiring sample data of each sample client, wherein the sample data comprises conversion labels of the sample clients;

training an initial client evaluation model according to the sample data of each sample client to obtain a client evaluation model, and obtaining the characteristic contribution degree of each client characteristic in the sample data after training is finished, wherein the initial client evaluation model is a tree model.

3. The customer data processing method as recited in claim 1, wherein the step of inputting the customer data into a customer assessment model to obtain a conversion score for the target customer in the current assessment comprises:

inputting the client data into a client evaluation model to obtain the conversion probability of the target client;

and generating a conversion score of the target client in the current evaluation according to the conversion probability.

4. The method of claim 1, wherein the step of calculating a covariance base of each of the client features in the current evaluation based on the feature contribution, feature class, and feature value of each of the client features comprises:

for each feature class, calculating the average contribution of the feature classes according to the feature contribution of each client feature in the feature class;

For each client feature, calculating the covariance base of the client feature in the current evaluation according to the feature value of the client feature and the average contribution degree of the feature class of the client feature.

5. The method of claim 1, wherein the step of calculating covariance of the previous and current evaluations on each feature class based on the obtained covariance base comprises:

for each feature class, generating a first variable value sequence according to covariance base of client features contained in the feature class in the current evaluation;

generating a second variable value sequence according to covariance base of the client features contained in the feature class in the previous evaluation;

covariance of the previous evaluation and the current evaluation on the feature class is calculated based on the first variable value sequence and the second variable value sequence.

6. The method of claim 1, wherein the step of generating the customer analysis result of the target customer based on the conversion score in the current assessment, the conversion score in the previous assessment, and the covariance of the previous assessment and the current assessment across the feature categories comprises:

Respectively acquiring conversion states of the target client in the current evaluation and the previous evaluation;

and generating a client analysis result of the target client according to the obtained conversion state, conversion score and covariance.

7. The method of claim 6, wherein the customer analysis result includes a customer service policy, and further comprising, after the step of generating the customer analysis result for the target customer:

and sending the customer analysis result to a salesman so that the salesman provides service for the target customer according to a customer service policy in the customer analysis result.

8. A client data processing apparatus, comprising:

9. A computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the customer data processing method of any of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the customer data processing method according to any of claims 1 to 7.