CN115587830A

CN115587830A - Work task excitation method and device, computer equipment and storage medium

Info

Publication number: CN115587830A
Application number: CN202211350776.7A
Authority: CN
Inventors: 卢显锋
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: 2022-10-31
Filing date: 2022-10-31
Publication date: 2023-01-10

Abstract

The embodiment of the application belongs to the fields of artificial intelligence and financial science and technology, is applied to the field of insurance sales application, and relates to a work task incentive method, a device, computer equipment and a storage medium, wherein the work task incentive method comprises the steps of obtaining customer characteristic information and sales characteristic information, inputting a classification model based on a logical regression algorithm, and training a customer intention classification model and a sales index classification model; acquiring characteristic information of a customer to be contacted, inputting the characteristic information into a customer intention classification model, and classifying the purchase intention of the customer; obtaining characteristic information of sales, inputting the characteristic information into a sales index classification model, and classifying sales capacity indexes; and selecting a corresponding bill rewarding formula according to the classification result, acquiring a bill rewarding value, and displaying the bill rewarding value on a preset billboard interface in real time. According to the method and the system, the sales seat and the characteristics of the client are integrated to evaluate the endorsement rewards, and reward evaluation results are displayed to the manual seat in real time, so that the staff in the sales service can be stimulated in real time.

Description

Work task excitation method and device, computer equipment and storage medium

Technical Field

The application relates to the technical field of artificial intelligence and financial science and technology, in particular to a work task incentive method and device, computer equipment and a storage medium.

Background

Due to market competition, for various industries, business companies have certain difficulties in carrying out new business promotion on customers, and some problems are solved without the help of manual seats.

Taking insurance business or credit card business as an example, aiming at the aspect of calculating sales prizes of human agents, the existing methods in the industry at present mainly calculate based on percentages, stage achievement incentives and the like, and generally adopt a fixed flow algorithm formula to obtain a prize drawing; most of the calculation modes are daily knot, monthly knot and the like; such a method is generally low in timeliness after being sold as a single, and therefore lacks incentive for sales personnel to sell.

Disclosure of Invention

The embodiment of the application aims to provide a work task incentive method, a work task incentive device, computer equipment and a storage medium, wherein a sales agent and the characteristics of a client are integrated to evaluate the reward of a sign-off form, and the reward evaluation result is displayed to an artificial agent in real time, so that real-time incentive is conveniently provided for workers in the sales service.

In order to solve the above technical problem, an embodiment of the present application provides a method for exciting a work task, which adopts the following technical solutions:

a method of job task incentive comprising the steps of:

performing data binning processing on the distinguishing identifications in a given list according to a preset binning proportion to obtain a training set and a testing set, wherein the given list is a related data list for performing classification model training;

acquiring characteristic information of all objects in the given list according to the distinguishing identification, and preprocessing the characteristic information;

inputting the preprocessed feature information into a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model;

acquiring the characteristic information of the customer to be contacted in a customer list to be contacted newly distributed by a sales agent, and inputting the characteristic information into the customer intention classification model to classify the purchasing intention of the customer;

acquiring characteristic information of the sales, and inputting the characteristic information into the sales index classification model to perform sales capability index classification;

and selecting a corresponding sign rewarding formula according to the purchasing intention classification result and the sales capability index classification result of the client, acquiring a sign rewarding value, and displaying the sign rewarding value on a preset billboard interface in real time.

Further, the given list includes a historical customer list and a sales seat list, and the step of performing data binning processing on the distinguished identifiers in the given list according to a preset binning ratio to obtain a training set and a test set specifically includes:

performing data binning processing on the client distinguishing identifications in the historical client list according to a preset binning ratio to obtain a client training set and a client testing set;

and carrying out data binning processing on the sales distinguishing identifications in the sales seat list according to a preset binning proportion to obtain a sales training set and a sales testing set.

Further, the step of obtaining the feature information of all the objects in the given list according to the distinguishing identifier and preprocessing the feature information specifically includes:

acquiring characteristic information of all clients in the historical client list according to the client distinguishing identification, and performing missing value processing, characteristic construction processing and discrete characteristic standardization processing on the characteristic information to acquire a numerical characteristic value, wherein the characteristic information comprises age, gender, education level, marital status, property level, income level, whether the client is a company member or not and member level;

and acquiring characteristic information of all sales in the sales seat list according to the sales distinguishing identification, and performing missing value processing, characteristic construction processing and discrete characteristic standardization processing on the characteristic information to acquire a numerical characteristic value, wherein the characteristic information comprises a sales capability index.

Further, the step of obtaining and inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, pre-training the classification model, and obtaining a pre-trained target classification model includes:

according to the customer distinguishing identification in the customer training set, screening out the characteristic information corresponding to all the customers in the customer training set from the characteristic information;

performing model training on the initialized classification model by taking the characteristic information as training data to obtain a first classification model;

screening out characteristic information corresponding to all customers in the customer test set from the characteristic information according to the customer distinguishing identifications in the customer test set;

performing model test on the first classification model by taking the characteristic information as test data;

and performing iterative tuning processing on the first classification model according to a model test result and a preset tuning mode until the model test result meets a certain preset condition, completing the iterative tuning, completing the pre-training of the classification model, and obtaining a pre-trained client intention classification model.

Further, the step of obtaining and inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, pre-training the classification model, and obtaining a pre-trained target classification model further includes:

screening out all characteristic information corresponding to sales in the sales training set from the characteristic information according to the sales distinguishing identification in the sales training set;

performing model training on the initialized classification model by taking the characteristic information as training data to obtain a second classification model;

screening out all characteristic information corresponding to sales in the sales test set from the characteristic information according to the sales distinguishing identification in the sales test set;

performing model test on the second classification model by taking the characteristic information as test data;

and performing iterative tuning processing on the second classification model according to a model test result and a preset tuning mode until the model test result meets a certain preset condition, completing the iterative tuning, completing the pre-training of the classification model, and obtaining a pre-trained sales index classification model.

Further, the step of obtaining the feature information of the customer to be contacted in the list of the customer to be contacted newly allocated by the sales agent specifically includes:

reading a list of clients to be contacted newly distributed by a sales agent, and acquiring a client distinguishing identifier according to the read content, wherein the list of the clients to be contacted comprises the client distinguishing identifier;

and acquiring the characteristic information of the client to be contacted in a characteristic cache library according to the client distinguishing identification, wherein the characteristic cache library comprises the characteristic information of the client to be contacted.

Further, before the step of selecting a corresponding endorsement award formula according to the customer purchase intention classification result and the sales capability index classification result to obtain the endorsement award value, the method further comprises:

respectively setting sign expectation levels for different customer purchase intention classification results and different sales capability index classification results in advance;

the method comprises the steps that an expectation algorithm formula is preset, and corresponding expected values of the signposts can be obtained according to the expectation algorithm formula and the signpost expectation levels, wherein the expectation algorithm formula is a proportional formula, the higher the signpost expectation level is, the higher the corresponding expected value of the signpost is, the lower the signpost expectation level is, and the lower the corresponding expected value of the signpost is;

the method comprises the steps that a bill rewarding formula is preset, and corresponding bill rewarding values can be obtained according to the bill rewarding formula and the bill expected values, wherein the bill rewarding formula is an inverse proportion formula, the higher the bill expected value is, the lower the corresponding bill rewarding value is, and the lower the bill expected value is, the higher the corresponding bill rewarding value is.

Further, the step of selecting a corresponding endorsement incentive formula according to the classification result of the purchasing intention and the classification result of the sales capability index of the customer to obtain the endorsement incentive value specifically comprises the following steps:

obtaining the corresponding sign expectation levels of the classification result of the purchasing intention of the customer and the classification result of the sales capability index;

inputting the expected levels of the signposts into the expected algorithm formula respectively, and calculating to obtain expected values of the signposts;

and inputting the expected value of the ticket into the ticket reward formula, calculating and obtaining the reward value of the ticket.

Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:

according to the work task excitation method, data binning processing is carried out on the distinguishing identifications in the given list according to a preset binning proportion, and a training set and a test set are obtained; acquiring characteristic information of all objects in a given list according to the distinguishing identification, and preprocessing the characteristic information; acquiring characteristic information, inputting a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model; acquiring the characteristic information of the customers to be contacted in a customer list to be contacted newly distributed by the sales seat, and inputting the characteristic information into a customer intention classification model to classify the purchase intention of the customers; acquiring characteristic information of sales, and inputting the characteristic information into a sales index classification model to perform sales capability index classification; and selecting a corresponding sign-in reward formula according to the purchasing intention classification result and the sales capacity index classification result of the client, acquiring a sign-in reward value, and displaying the sign-in reward value on a preset billboard interface in real time. According to the method and the system, the sales seat and the characteristics of the client are integrated to evaluate the endorsement rewards, and reward evaluation results are displayed to the manual seat in real time, so that the staff in the sales service can be stimulated in real time.

Drawings

In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.

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

FIG. 2 is a flow diagram of one embodiment of a work task incentive method according to the present application;

FIG. 3 is a flow diagram of one embodiment of step 201 of FIG. 2;

FIG. 4 is a flow diagram of one embodiment of step 203 shown in FIG. 2;

FIG. 5 is a flow diagram of one embodiment of step 401 shown in FIG. 4;

FIG. 6 is a flow diagram of one embodiment of step 505 of FIG. 5;

FIG. 7 is a flow diagram of one embodiment of step 402 of FIG. 4;

FIG. 8 is a flowchart of one embodiment of step 705 of FIG. 7;

FIG. 9 is a flowchart of one embodiment of step 206 shown in FIG. 2;

FIG. 10 is a schematic block diagram of one embodiment of a work task activation device according to the present application;

FIG. 11 is a schematic block 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 application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof in the description and claims of this application and the description of the figures above, are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the foregoing drawings are used for distinguishing between different objects and not for describing a particular sequential order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase 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. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, 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 work task incentive method provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the work task incentive device is generally disposed in the server/terminal device.

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 diagram of one embodiment of a work task incentive method according to the present application is shown. The work task exciting method comprises the following steps:

step 201, performing data binning processing on the distinguished identifiers in the given list according to a preset binning proportion to obtain a training set and a test set, wherein the given list is a related data list for performing classification model training.

In this embodiment, the given list includes a historical customer list and a sales agent list.

With continued reference to FIG. 3, FIG. 3 is a flowchart of one embodiment of step 201 shown in FIG. 2, including the steps of:

step 301, performing data binning processing on the customer difference identifications in the historical customer list according to a preset binning ratio to obtain a customer training set and a customer testing set;

and 302, performing data binning processing on the sales distinguishing identifications in the sales seat list according to a preset binning ratio to obtain a sales training set and a sales testing set.

Step 202, obtaining the characteristic information of all the objects in the given list according to the distinguishing mark, and preprocessing the characteristic information.

In this embodiment, the step of obtaining the feature information of all the objects in the given list according to the distinguishing identifier and preprocessing the feature information specifically includes: acquiring characteristic information of all clients in the historical client list according to the client distinguishing identification, and performing missing value processing, characteristic construction processing and discrete characteristic standardization processing on the characteristic information to acquire a numerical characteristic value, wherein the characteristic information comprises age, gender, education level, marital status, property level, income level, whether the information is a company member or not and member level; and acquiring characteristic information of all sales in the sales seat list according to the sales distinguishing identification, and performing missing value processing, characteristic construction processing and discrete characteristic standardization processing on the characteristic information to acquire a numerical characteristic value, wherein the characteristic information comprises a sales capability index.

In this embodiment, missing value processing, feature construction processing, and discrete feature standardization processing are performed on the feature information to obtain a digitized feature value, in this embodiment, a missing value completion mode is used as a missing value processing mode, specifically, when a certain feature information corresponding to a certain customer or a certain sale is retrieved and has no value, a mode corresponding to the feature information is directly obtained and used as a feature information corresponding to the customer or the sale, a mode completion mode is used to ensure sufficiency of the feature information, deletion of the missing value is not required, feature construction processing is performed on the feature information after the missing value processing to obtain a specific feature value corresponding to each individual in a customer group and a sale group, the specific feature value is processed through discrete feature standardization, the missing value processing, feature construction processing, and discrete feature standardization processing are performed on the feature information to obtain a digitized feature value, and a corresponding digitized feature value is generated for each individual in the customer and the sale, so as to facilitate later-stage data analysis.

And 203, inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model.

With continuing reference to FIG. 4, FIG. 4 is a flowchart of one embodiment of step 203 shown in FIG. 2, comprising the steps of:

step 401, obtaining the preprocessed feature information corresponding to the client, inputting a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a pre-trained client intention classification model;

with continued reference to FIG. 5, FIG. 5 is a flowchart of one embodiment of step 401 shown in FIG. 4, including the steps of:

step 501, according to the customer distinguishing identifications in the customer training set, screening out the characteristic information corresponding to all the customers in the customer training set from the characteristic information;

step 502, performing model training on the initialized classification model by taking the characteristic information as training data to obtain a first classification model;

step 503, according to the customer difference identification in the customer test set, screening out the characteristic information corresponding to all the customers in the customer test set from the characteristic information;

step 504, using the characteristic information as test data to perform model test on the first classification model;

and 505, performing iterative tuning processing on the first classification model according to a model test result and a preset tuning mode until the model test result meets a certain preset condition, completing iterative tuning, completing pre-training of the classification model, and obtaining a pre-trained client intention classification model.

And in the process of training the client intention classification model, optimizing the classification model by adopting a logistic regression algorithm iteration mode, and ensuring the classification accuracy of the client intention classification model.

Taking insurance sales as an example, obtaining customers in a telephone list dialed by a historical sales agent as a historical customer list, dividing the customers in the historical customer list into a customer training set and a customer testing set, obtaining characteristic information of the customers corresponding to the customer training set and the customer testing set, preprocessing the characteristic information, and then pre-training a customer intention classification model to obtain a trained customer intention classification model.

With continuing reference to FIG. 6, FIG. 6 is a flowchart of one embodiment of step 505 of FIG. 5, comprising the steps of:

601, calculating according to the model test result and a preset loss function to obtain a loss value of the first classification model;

step 602, comparing the loss value with a preset loss threshold value, and determining whether the loss value is smaller than the preset loss threshold value;

step 603, if the loss value is smaller than the loss threshold, the model test result does not need to be subjected to tuning processing, and the classification model is trained in advance;

step 604, if the loss value is not less than the loss threshold, continuing to use the logistic regression algorithm to perform iterative training on the first classification model until the loss value is less than the loss threshold, and completing the classification model pre-training without performing optimization processing on the model test result.

Specifically, the step of obtaining the preprocessed feature information corresponding to the client, inputting a classification model based on a logistic regression algorithm, and pre-training the classification model to obtain a pre-trained client intention classification model includes: acquiring a numerical characteristic value corresponding to each individual in the customer training set according to the customer distinguishing identification; taking the characteristic value as a characteristic data point set corresponding to the client training set, and constructing a linear regression equation to fit data in the characteristic data point set to obtain a linear regression equation expression; substituting the linear regression equation expression into a sigmoid function to construct and activate a client intention classification model; then obtaining the numerical eigenvalue corresponding to each individual in the customer test set according to the customer distinguishing mark; inputting the numerical characteristic value corresponding to each individual in the customer test set into the customer intention classification model for verification, and completing the pre-training of the customer intention classification model if the verification is successful.

In this embodiment, the step of using the feature values as the feature data point set corresponding to the client training set, and constructing a linear regression equation to fit the data in the feature data point set to obtain a linear regression equation expression further includes: obtaining a residual error square value of all data in the characteristic data point set as an error value of the characteristic data point set; traversing and sequencing all data in the characteristic data point set, and obtaining a linear regression graph by taking the number of elements in the characteristic data point set as an abscissa value and the sequencing result as an ordinate value; obtaining a slope value according to the linear regression graph; according to a preset algorithm formula: y = ax ± b, and obtaining a linear regression equation expression, wherein a is the slope value and b is the error value.

In this embodiment, the preset loss threshold may be understood as the error value.

In this embodiment, the step of inputting the digitized feature value corresponding to each individual in the customer test set into the customer intention classification model for verification, and if the verification is successful, completing the pre-training of the customer intention classification model specifically includes: and acquiring the number of successfully verified individuals in the client test set, if the number of successfully verified individuals reaches a certain proportional value, successfully verifying, otherwise, adjusting the binning proportion to perform data binning to obtain a client training set and a client test set after binning, and performing pre-training on the client intention classification model until the number of successfully verified individuals reaches the certain proportional value, so that the pre-training of the client intention classification model is completed.

In this embodiment, the adjusting of the binning ratio to perform data binning to obtain a client training set and a client testing set after binning, and then performing pre-training on the client intention classification model until the number of individuals successfully verified reaches a certain ratio, where the completion of the pre-training on the client intention classification model may be understood as a specific tuning processing manner in the step 505.

Step 402, obtaining the preprocessed feature information corresponding to the sales, inputting a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a sales index classification model after pre-training.

With continuing reference to FIG. 7, FIG. 7 is a flowchart of one embodiment of step 402 of FIG. 4, comprising the steps of:

701, screening out all characteristic information corresponding to sales in the sales training set from the characteristic information according to the sales distinguishing identification in the sales training set;

step 702, performing model training on the initialized classification model by taking the characteristic information as training data to obtain a second classification model;

703, screening out all characteristic information corresponding to all sales in the sales test set from the characteristic information according to the sales distinguishing identifications in the sales test set;

step 704, taking the characteristic information as test data, and performing model test on the second classification model;

step 705, performing iterative tuning processing on the second classification model according to a model test result and a preset tuning mode until the model test result meets a certain preset condition, completing the iterative tuning, completing the pre-training of the classification model, and obtaining a pre-trained sales index classification model.

With continued reference to FIG. 8, FIG. 8 is a flowchart of one embodiment of step 705 of FIG. 7, including the steps of:

step 801, calculating according to the model test result and a preset loss function to obtain a loss value of the second classification model;

step 802, comparing the loss value with a preset loss threshold value, and judging whether the loss value is smaller than the preset loss threshold value;

step 803, if the loss value is smaller than the loss threshold, the model test result does not need to be subjected to tuning and optimizing treatment, and the classification model is trained in advance;

and step 804, if the loss value is not less than the loss threshold, continuing to use the logistic regression algorithm to perform iterative training on the second classification model until the loss value is less than the loss threshold, and completing the classification model pre-training without performing optimization processing on the model test result.

Specifically, the step of obtaining the preprocessed feature information corresponding to the sales, inputting a classification model based on a logistic regression algorithm, pre-training the classification model, and obtaining a sales index classification model after pre-training includes: acquiring a numerical characteristic value corresponding to each individual in the sales training set according to the sales distinguishing mark; taking the characteristic value as a characteristic data point set corresponding to the sales training set, and constructing a linear regression equation to fit data in the characteristic data point set to obtain a linear regression equation expression; substituting the linear regression equation expression into a sigmoid function to construct and activate a sales index classification model; then obtaining the numerical characteristic value corresponding to each individual in the sales test set according to the sales distinguishing mark; inputting the numerical characteristic value corresponding to each individual in the sales test set into the sales index classification model for verification, and finishing the pre-training of the sales index classification model if the verification is successful.

In this embodiment, the step of using the feature value as the feature data point set corresponding to the sales training set, and constructing a linear regression equation to fit the data in the feature data point set to obtain a linear regression equation expression further includes: obtaining a residual error square value of all data in the characteristic data point set as an error value of the characteristic data point set; traversing and sequencing all data in the characteristic data point set, and obtaining a linear regression graph by taking the number of elements in the characteristic data set as an abscissa value and the sequencing result as an ordinate value; obtaining a slope value according to the linear regression graph; according to a preset algorithm formula: y = ax ± b, and obtaining a linear regression equation expression, wherein a is the slope value and b is the error value.

In this embodiment, the step of inputting the digitized feature value corresponding to each individual in the sales test set into the sales index classification model for verification, and if the verification is successful, the sales index classification model is pre-trained, specifically includes: and acquiring the number of successfully verified individuals in the sales test set, if the number of successfully verified individuals in the sales test set reaches a certain proportional value, successfully verifying, otherwise, adjusting the binning proportion to perform data binning to obtain a sales training set and a sales test set after binning, and performing sales index classification model pre-training until the number of successfully verified individuals reaches the certain proportional value, so that the sales index classification model pre-training is completed.

In this embodiment, the adjusting of the binning ratio is performed to perform data rebinning, obtain a sales training set and a sales test set after the rebinning, and perform pre-training on the sales index classification model until the number of individuals successfully verified reaches a certain ratio, and the completion of the pre-training on the sales index classification model may be understood as a specific tuning and optimizing processing manner in the step 705.

And in the process of training the sales index classification model, optimizing the classification model by adopting a logistic regression algorithm iteration mode and adjusting the data binning proportion, and ensuring the classification accuracy of the sales index classification model.

Taking insurance sales as an example, obtaining a sales agent list, dividing sales in the sales agent list into a sales training set and a sales testing set, obtaining characteristic information, namely sales capability indexes, of corresponding sales in the sales training set and the sales testing set, preprocessing the characteristic information, then pre-training a sales index classification model, and obtaining a trained sales index classification model.

And 204, acquiring the characteristic information of the customer to be contacted in a customer list to be contacted newly allocated by the sales seat, and inputting the characteristic information into the customer intention classification model to classify the purchase intention of the customer.

In this embodiment, the step of obtaining the feature information of the customer to be contacted in the list of customers to be contacted newly allocated by the sales agent specifically includes: reading a list of clients to be contacted newly distributed by a sales agent, and acquiring a client distinguishing identifier according to the read content, wherein the list of the clients to be contacted comprises the client distinguishing identifier; and acquiring characteristic information of the clients to be contacted in a characteristic cache library according to the client distinguishing identification, wherein the characteristic cache library comprises the characteristic information of the clients to be contacted, and the characteristic information comprises age, gender, education level, marital status, property level, income level, whether the clients are company members or not and member level.

Step 205, obtaining the characteristic information of the sales, and inputting the characteristic information into the sales index classification model to perform sales capability index classification.

And step 206, selecting a corresponding sign reward formula according to the classification result of the purchasing intention of the customer and the classification result of the sales capability index, acquiring a sign reward value, and displaying the sign reward value on a preset billboard interface in real time.

In this embodiment, before the step of selecting a corresponding endorsement award formula according to the customer purchase intention classification result and the sales capability index classification result to obtain the endorsement award value, the method further includes: respectively setting sign expectation levels for different customer purchase intention classification results and different sales capability index classification results in advance; the method comprises the steps that an expectation algorithm formula is preset, and corresponding expected values of the signposts can be obtained according to the expectation algorithm formula and the signpost expectation levels, wherein the expectation algorithm formula is a proportional formula, the higher the signpost expectation level is, the higher the corresponding expected value of the signpost is, the lower the signpost expectation level is, and the lower the corresponding expected value of the signpost is; the method comprises the steps that a bill rewarding formula is preset, and corresponding bill rewarding values can be obtained according to the bill rewarding formula and the bill expected values, wherein the bill rewarding formula is an inverse proportion formula, the higher the bill expected value is, the lower the corresponding bill rewarding value is, and the lower the bill expected value is, the higher the corresponding bill rewarding value is.

In this embodiment, the slip expectation level corresponding to the customer and the slip expectation level corresponding to the sale are input into the same expectation algorithm formula for multiplication, and finally, one slip expectation value is obtained from the two slip expectation levels.

For example: the sign expectation grade can be set to be 1-5 grades according to different classification results of the purchasing intentions of the customers, and the higher the sign expectation grade is, the stronger the purchasing intentions of the customers are; the order expectation grade can also be set to be 1-5 grades according to different sales capacity index classification results, and the higher the order expectation grade is, the higher the success probability of sales is indicated to be; the direct proportion formula corresponding to the expectation algorithm formula can be as follows: m = c × n1 × n2, where m is a ticket expectation value, n1 is a ticket expectation level corresponding to a customer, n2 is a ticket expectation level corresponding to a sale, and c is a numerical value greater than 0; the inverse proportion formula corresponding to the endorsement award formula can be as follows:

where m is the expected value of the ticket and l is the prize value of the ticket.

The method comprises the steps of obtaining a receipt expectation value by setting a receipt expectation level and an expectation algorithm formula, setting the expectation algorithm formula as a direct proportion formula to enable the receipt expectation level to be higher and the receipt expectation value to be higher, then setting a receipt reward formula, and setting the receipt reward formula as an inverse proportion formula to enable the receipt expectation value to be lower and the receipt reward value to be higher, so that sales staff are encouraged to stimulate staff when meeting clients with low receipt expectation values, and work power is improved for the higher receipt reward values.

With continued reference to FIG. 9, FIG. 9 is a flowchart of one embodiment of step 206 shown in FIG. 2, comprising the steps of:

step 901, obtaining the corresponding sign expectation levels of the classification result of the purchase intention of the customer and the classification result of the sales capability index;

step 902, inputting the expected levels of the signages into the expected algorithm formula respectively, calculating and obtaining expected values of the signages;

and 903, inputting the expected value of the ticket into the ticket reward formula, calculating and acquiring the reward value of the ticket.

According to the method, data binning is carried out on the distinguishing marks in the given list according to a preset binning proportion, and a training set and a test set are obtained; acquiring characteristic information of all objects in a given list according to the distinguishing identification, and preprocessing the characteristic information; acquiring characteristic information, inputting a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model; acquiring the characteristic information of customers to be contacted in a list of customers to be contacted newly allocated by a sales agent, and inputting the characteristic information into a customer intention classification model to classify the purchasing intention of the customers; acquiring characteristic information of sales, and inputting the characteristic information into a sales index classification model to perform sales capability index classification; and selecting a corresponding sign-in reward formula according to the purchasing intention classification result and the sales capacity index classification result of the client, acquiring a sign-in reward value, and displaying the sign-in reward value on a preset billboard interface in real time. According to the method and the system, the sales seat and the characteristics of the client are integrated to evaluate the endorsement rewards, and reward evaluation results are displayed to the manual seat in real time, so that the staff in the sales service can be stimulated in real time.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly 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 the like.

In the embodiment of the application, the customer intention classification model and the sales index classification model are trained into the intelligent classification model, new customer intention classification prediction and sales index classification prediction are automatically performed in the later period through the customer intention classification model and the sales index classification model, the automation and the intelligence are improved, meanwhile, in the training process of the customer intention classification model and the sales index classification model, a logistic regression algorithm iteration mode is adopted for optimizing the classification model, and the classification accuracy of the customer intention classification model and the sales index classification model is guaranteed.

With further reference to fig. 10, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a job task activation device, which corresponds to the embodiment of the method shown in fig. 2, and which is particularly applicable to various electronic devices.

As shown in fig. 10, the job task incentive device 10 according to the present embodiment includes: an object binning module 10a, a data processing module 10b, a model training module 10c, a customer intent recognition module 10d, a sales capability recognition module 10e, and a display incentive module 10f. Wherein:

the object binning module 10a is configured to perform data binning processing on the difference identifiers in a given list according to a preset binning ratio to obtain a training set and a test set, where the given list is a related data list for performing classification model training;

the data processing module 10b is configured to obtain feature information of all objects in the given list according to the distinguishing identifier, and preprocess the feature information;

the model training module 10c is used for acquiring and inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, and pre-training the classification model to acquire a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model;

the customer intention identification module 10d is used for acquiring the characteristic information of the customer to be contacted in a customer list to be contacted newly distributed by the sales seat, and inputting the characteristic information into the customer intention classification model to classify the purchase intention of the customer;

the sales capability identification module 10e is configured to obtain characteristic information of the sales, and input the characteristic information into the sales index classification model to perform sales capability index classification;

and the display incentive module 10f is used for selecting a corresponding sign reward formula according to the purchase intention classification result and the sales capability index classification result of the customer, acquiring a sign reward value and displaying the sign reward value on a preset billboard interface in real time.

According to the method, data binning is carried out on the distinguishing identifications in the given list according to a preset binning proportion, and a training set and a testing set are obtained; acquiring characteristic information of all objects in a given list according to the distinguishing identification, and preprocessing the characteristic information; acquiring characteristic information, inputting a classification model based on a logistic regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model; acquiring the characteristic information of customers to be contacted in a list of customers to be contacted newly allocated by a sales agent, and inputting the characteristic information into a customer intention classification model to classify the purchasing intention of the customers; acquiring characteristic information of sales, and inputting the characteristic information into a sales index classification model to classify sales capacity indexes; and selecting a corresponding sign rewarding formula according to the purchasing intention classification result and the sales capability index classification result of the client, acquiring a sign rewarding value, and displaying the sign rewarding value on a preset billboard interface in real time. According to the method and the system, the sales seat and the characteristics of the client are integrated to evaluate the endorsement rewards, and reward evaluation results are displayed to the manual seat in real time, so that the staff in the sales service can be stimulated in real time.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the programs can include the processes of the embodiments of the methods described above. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a 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, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 11, fig. 11 is a block diagram of a basic structure of a computer device according to the embodiment.

The computer device 11 includes a memory 11a, a processor 11b, and a network interface 11c, which are communicatively connected to each other via a system bus. It is noted that only a computer device 11 having components 11a-11c is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may alternatively be implemented. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

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

The memory 11a includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 11a may be an internal storage unit of the computer device 11, such as a hard disk or a memory of the computer device 11. In other embodiments, the memory 11a may also be an external storage device of the computer device 11, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 11. Of course, the memory 11a may also include both an internal storage unit and an external storage device of the computer device 11. In this embodiment, the memory 11a is generally used for storing an operating system and various application software installed on the computer device 11, such as computer readable instructions of a work task incentive method. Further, the memory 11a may also be used to temporarily store various types of data that have been output or are to be output.

The processor 11b may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data Processing chip in some embodiments. The processor 11b is typically used to control the overall operation of the computer device 11. In this embodiment, the processor 11b is configured to execute computer readable instructions stored in the memory 11a or process data, such as computer readable instructions for executing the job task incentive method.

The network interface 11c may comprise a wireless network interface or a wired network interface, and the network interface 11c is generally used for establishing communication connection between the computer device 11 and other electronic devices.

The computer equipment that this embodiment provided belongs to financial science and technology technical field. According to the method, data binning is carried out on the distinguishing marks in the given list according to a preset binning proportion, and a training set and a test set are obtained; acquiring characteristic information of all objects in a given list according to the distinguishing identification, and preprocessing the characteristic information; acquiring characteristic information, inputting a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model; acquiring the characteristic information of the customers to be contacted in a customer list to be contacted newly distributed by the sales seat, and inputting the characteristic information into a customer intention classification model to classify the purchase intention of the customers; acquiring characteristic information of sales, and inputting the characteristic information into a sales index classification model to classify sales capacity indexes; and selecting a corresponding sign rewarding formula according to the purchasing intention classification result and the sales capability index classification result of the client, acquiring a sign rewarding value, and displaying the sign rewarding value on a preset billboard interface in real time. According to the method and the system, the sales seat and the characteristics of the client are integrated to evaluate the bill reward, and the reward evaluation result is displayed to the manual seat in real time, so that real-time excitation is performed on the working staff in the sales business conveniently.

The present application further provides another embodiment, which is a computer readable storage medium storing computer readable instructions executable by a processor to cause the processor to perform the steps of the work task incentive method as described above.

The embodiment provides a computer-readable storage medium, and belongs to the technical field of financial technologies. According to the method, data binning is carried out on the distinguishing marks in the given list according to a preset binning proportion, and a training set and a test set are obtained; acquiring characteristic information of all objects in a given list according to the distinguishing identification, and preprocessing the characteristic information; acquiring characteristic information, inputting a classification model based on a logical regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model; acquiring the characteristic information of customers to be contacted in a list of customers to be contacted newly allocated by a sales agent, and inputting the characteristic information into a customer intention classification model to classify the purchasing intention of the customers; acquiring characteristic information of sales, and inputting the characteristic information into a sales index classification model to perform sales capability index classification; and selecting a corresponding sign-in reward formula according to the purchasing intention classification result and the sales capacity index classification result of the client, acquiring a sign-in reward value, and displaying the sign-in reward value on a preset billboard interface in real time. According to the method and the system, the sales seat and the characteristics of the client are integrated to evaluate the endorsement rewards, and reward evaluation results are displayed to the manual seat in real time, so that the staff in the sales service can be stimulated in real time.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (such as a ROM/RAM, a magnetic disk, and an optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that modifications can be made to the embodiments described in the foregoing detailed description, or equivalents can be substituted for some of the features described therein. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.

Claims

1. A method of job task motivation comprising the steps of:

inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model;

acquiring the characteristic information of the customer to be contacted in a customer list to be contacted newly distributed by a sales seat, and inputting the characteristic information into the customer intention classification model to classify the purchase intention of the customer;

acquiring the characteristic information of the sales, and inputting the characteristic information into the sales index classification model to classify the sales capacity index;

2. The job-task incentive method according to claim 1, wherein said given list comprises a historical customer list and a sales agent list; the step of performing data binning processing on the distinguished identifiers in the given list according to a preset binning proportion to obtain a training set and a test set specifically comprises the following steps:

performing data binning processing on the client distinguishing identifications in the historical client list according to a preset binning proportion to obtain a client training set and a client testing set;

3. The method for exciting work tasks according to claim 2, wherein the step of obtaining the feature information of all the objects in the given list according to the distinguishing identifiers and preprocessing the feature information specifically comprises:

acquiring characteristic information of all clients in the historical client list according to the client distinguishing identification, and performing missing value processing, characteristic construction processing and discrete characteristic standardization processing on the characteristic information to acquire a numerical characteristic value, wherein the characteristic information comprises age, gender, education level, marital status, property level, income level, whether the information is a company member or not and member level;

4. The method for exciting a work task according to claim 3, wherein the step of obtaining and inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model comprises:

5. The method for exciting a work task according to claim 3, wherein the step of obtaining and inputting the preprocessed feature information into a classification model based on a logistic regression algorithm, and pre-training the classification model to obtain a pre-trained target classification model further comprises:

6. The job task incentive method according to claim 1, wherein the step of obtaining the feature information of the customer to be contacted in the list of customers to be contacted newly allocated by the sales agent specifically comprises:

7. The work task incentive method of claim 1, wherein prior to the step of classifying the results according to customer buying intent and classifying the results according to sales capability index, selecting a corresponding endorsement incentive formula, and obtaining the endorsement incentive value, the method further comprises:

respectively setting sign expectation levels for different customer purchase intention classification results and different sales capacity index classification results in advance;

8. The work task incentive method according to claim 7, wherein the step of selecting a corresponding endorsement incentive formula according to the customer purchase intention classification result and the sales capability index classification result to obtain the endorsement incentive value comprises:

and inputting the expected value of the ticket into the ticket rewarding formula, and calculating to obtain the ticket rewarding value.

9. A work task incentive device, comprising:

the object binning module is used for performing data binning processing on the distinguishing identifications in the given list according to a preset binning proportion to obtain a training set and a testing set, wherein the given list is a related data list used for performing classification model training;

the data processing module is used for acquiring the characteristic information of all the objects in the given list according to the distinguishing identification and preprocessing the characteristic information;

the model training module is used for acquiring and inputting the preprocessed feature information into a classification model based on a logical regression algorithm, pre-training the classification model and acquiring a pre-trained target classification model, wherein the target classification model comprises a client intention classification model and a sales index classification model;

the customer intention identification module is used for acquiring the characteristic information of the customers to be contacted in a list of the customers to be contacted newly allocated by the sales agent and inputting the characteristic information into the customer intention classification model to classify the purchasing intention of the customers;

the sales capability identification module is used for acquiring the characteristic information of the sales and inputting the characteristic information into the sales index classification model to classify the sales capability indexes;

and the display incentive module is used for selecting a corresponding sign reward formula according to the purchase intention classification result and the sales capability index classification result of the customer, acquiring a sign reward value and displaying the sign reward value on a preset billboard interface in real time.

10. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of a work task incentive method according to any one of claims 1 to 8.

11. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of a work task incentive method according to any one of claims 1 to 8.