Method, system and device for intelligently formulating insurance agent sales performance plans

Abstract

A method for intelligently formulating a sales performance plan for an insurance agent comprises the following steps: constructing an insurance product classifier model; obtaining salesperson data and the salesperson's customer data, inputting the data into the insurance product classifier model, and predicting whether the requirements are met. If so, the product is allocated once, excluding the customer resource; continuing to input the next customer data until the maximum number of copies of the product that can be allocated to the salesperson is calculated; looping through the decision tree model for the next product, and continuing to allocate until a list of all salespersons' products that can be sold and the maximum number of copies of the product that can be sold are calculated; and matching sales plan indicators to output the insurance agent's sales performance plan.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method, system and device for intelligently formulating a sales performance plan for an insurance agent. Background Art

[0002] In recent years, artificial intelligence has seen rapid advancements in data, algorithms, and computing power, ushering in a new wave of growth against the backdrop of the global digital transformation of the economy. This wave of AI has a far greater impact than any previous one, most notably by expanding its influence beyond specialized fields into the broader public.

[0003] At present, the performance plan of an insurance company is a sales plan set after formulating an overall sales target based on the sales data of the previous year and the market development plan of this year. The plan includes the sales volume of various insurance products that each branch needs to complete. The branch then allocates the product sales plan to its subordinate units and finally to the sales staff. The allocation ratio at the department level is based on the sales ratio of the previous year, but the plan allocated to the sales staff is allocated manually based on the experience of the department manager and gradually allocated to each sales staff.

[0004] Insurance agents, or salespeople, are required to develop a full-year sales performance plan for each calendar year. This plan outlines the number of policies they must sell and the total sales amount. This plan requires consideration of many complex parameters, such as meeting renewal premiums for existing customers and securing new insurance plans. For new customers, the number of new policies and total insured amounts must be achieved. Insurance companies also have specific product promotion targets, such as annual targets for total policy volume and total premiums for a particular product.

[0005] Assigning salespeople's performance plans is currently a major challenge for insurance companies. Sales plan allocation is often arbitrary and haphazard. Once the annual plan is established, individual plans are assigned based on experience by sales department leaders. This often has no direct correlation between assigned tasks and salespeople's abilities or their success rate in achieving sales targets. Furthermore, allocation efficiency is low, prone to miscalculations, and can lead to increased operational risk and difficulty ensuring the achievement of assigned tasks. Therefore, an intelligent method is needed to rationally assign tasks to specific executors, ensuring smooth and reliable plan implementation. Therefore, a simpler and more intelligent approach to allocating performance plans is needed. Summary of the Invention

[0006] One of the purposes of the present invention is to provide a method, system and device for intelligently formulating sales performance plans for insurance agents, which can intelligently formulate sales performance plans for insurance agents based on computer learning algorithms and reasonably allocate sales tasks to specific executors, so that the implementation of the plan is more secure, the implementation of the plan is smoother, the allocation efficiency is improved, and the operating risk is reduced.

[0007] One of the purposes of the present invention is to provide a method, system and equipment for intelligently formulating sales performance plans for insurance agents, which can match the sales skills and customer resources of sales personnel with the insurance products to be sold, greatly improve sales opportunities, make sales plans easier to achieve, and also greatly improve the efficiency of allocation work. The algorithm calculation automatically executed by the computer improves a large amount of manually allocated work, thereby improving overall efficiency.

[0008] In order to achieve at least one of the above-mentioned invention objectives, the present invention provides a method for intelligently formulating a sales performance plan for an insurance agent, comprising the following steps:

[0009] Build an insurance product classifier model;

[0010] The salesperson's data and their customer data are input into the insurance product classifier model to predict whether the requirements are met. If so, the product is allocated once, excluding the customer resource. The next customer data input is continued until the maximum number of copies of the product that can be allocated to the salesperson is calculated.

[0011] The decision tree model for the next product is cycled through and the allocation continues until the list of products that can be sold by all sales personnel and the maximum number of copies that can be sold for each product are calculated; and

[0012] Match sales plan indicators and output insurance agent sales performance plans.

[0013] In some embodiments, the step of matching sales plan indicators also includes the following steps: accumulating the number of product copies allocated to each salesperson; and comparing the sales plan data of the sales organization. If the accumulated number of copies is less than the sales plan number of copies, the excess number of copies is redistributed. If it is greater than the sales plan number of copies, the number of copies allocated to each salesperson is reduced according to the proportion of the excess data to the total number of copies, until the accumulated number of copies after rounding is equal to the planned number of copies, and the allocation task is completed.

[0014] In some embodiments, in the step of constructing an insurance product classifier model, a decision tree ID3 algorithm is executed to construct a decision tree based on product sales rule factors; wherein, a classifier is designed for each product sold by an insurance company, and the average value range of each attribute of the sales rules used by the classifier is set to between 2 and 10.

[0015] In some embodiments, the method for intelligently formulating a sales performance plan for insurance agents further includes the steps of: training an insurance product classifier model; wherein the step of training an insurance product classifier model further includes the steps of: generating training data according to a conditional exhaustive method, and the training data range is preset to be between 100 and 100,000, so that the trained insurance product classifier model executes classification of products to sales personnel to obtain matching data of products to sales personnel.

[0016] 5. The method for intelligently formulating insurance agent sales performance plans as described in any one of claims 1 to 4, wherein when performing decision tree classification, the decision trees are divided into classification trees and regression trees, the classification trees are used to construct decision trees for discrete variables, and the regression trees are used to construct decision trees for continuous variables; wherein in the process of constructing the decision tree, based on the degree of determinism of the features, the feature with the greatest determinism is used as the root node, and then the next largest deterministic feature in the sub-datasets under each branch is recursively found until all data in the sub-datasets belong to the same category; wherein, in the insurance product classifier model, the decision tree algorithm based on information theory is selected from the ID3, CART, and C4.5 algorithms.

[0017] In some embodiments, the method further includes executing the decision tree generation step: performing feature selection; recursively generating child nodes from top to bottom according to the selected feature evaluation criteria until the data set becomes indivisible and the decision tree stops growing; and reducing the size of the tree structure based on pre-pruning and post-pruning pruning techniques.

[0018] According to another aspect of the present invention, a device for intelligently formulating a sales performance plan for an insurance agent is also provided, wherein the device for intelligently formulating a sales performance plan for an insurance agent comprises: a software application, a memory for storing the software application, and a processor for executing the software application, wherein each program of the software application correspondingly executes the steps in the method for intelligently formulating a sales performance plan for an insurance agent.

[0019] According to another aspect of the present invention, a system for intelligently formulating insurance agent sales performance plans is also provided, the system for intelligently formulating insurance agent sales performance plans comprising an insurance product classifier model unit, a product allocation unit, and an insurance agent sales performance plan output unit, wherein the insurance product classifier model unit is configured to: construct an insurance product classifier model, and construct a decision tree model based on product sales rule factors; wherein the product allocation unit is configured to: obtain salesperson data and the salesperson's customer data, input the data into the constructed decision tree model, and execute product allocation to the salesperson; wherein the insurance agent sales performance plan output unit matches the sales plan indicators and outputs the insurance agent sales performance plan; wherein the insurance agent sales performance plan output unit is further configured to: accumulate the number of product copies allocated to each salesperson, compare it with the sales plan data of the sales organization, if the accumulated number of copies is less than the sales plan number of copies, perform secondary allocation on the excess number of copies, and if the number of copies is greater than the sales plan number of copies, reduce the number of copies already allocated to each salesperson according to the proportion of the excess data to the total number of copies, until the accumulated number of copies after rounding is equal to the planned number of copies, and complete the allocation task.

[0020] In some embodiments, the product allocation unit is further configured to: after the acquired salesperson data and the salesperson's customer data are input into the constructed decision tree model, predict whether they are satisfied. If so, the product is allocated once, excluding the customer resources; continue with the input of the next customer until the maximum number of copies of the product that can be allocated to the salesperson is calculated; loop the decision tree model of the next product and continue allocating until the list of products that can be sold by all salespeople and the maximum number of copies that can be sold of the product are calculated.

[0021] In some embodiments, the insurance product classifier model unit further includes a decision tree construction module and an insurance product classifier model training module, the insurance product classifier model training module is used to train the insurance product classifier model, wherein training data is generated according to a conditional exhaustive method, and the training data range is preset to be between 100 and 100,000, so that the trained insurance product classifier model performs classification of products to sales personnel and obtains matching data from products to sales personnel; wherein the decision tree construction module executes a decision tree ID3 algorithm and constructs a decision tree based on product sales rule factors, wherein a classifier is designed for each product sold by an insurance company, and the average value range of each attribute of the sales rule used by the classifier is set to be between 2 and 10; wherein the system for intelligently formulating insurance agent sales performance plans also includes a decision tree classification module and a decision tree classification module. A decision tree generation module, wherein the decision tree classification module is configured to: perform decision tree classification, decision trees are divided into classification trees and regression trees, classification trees make decision trees for discrete variables, and regression trees make decision trees for continuous variables, wherein in the process of constructing the decision tree, according to the degree of decisiveness of the feature, the feature with the greatest decisive effect is used as the root node, and then the second largest decisive feature in the sub-dataset under each branch is recursively found until all data in the sub-dataset belong to the same category, wherein, in the insurance product classifier model, the decision tree algorithm based on information theory is selected from ID3, CART and C4.5 algorithms; wherein the decision tree generation module is configured to: perform feature selection; according to the selected feature evaluation criteria, recursively generate child nodes from top to bottom until the data set is indivisible and the decision tree stops growing; and reduce the size of the tree structure by pruning technology based on pre-pruning and post-pruning. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a table diagram of various attributes of an insurance product classifier in a specific implementation of a method for intelligently formulating a sales performance plan for an insurance agent according to an embodiment of the present invention.

[0023] Figure 2 It is a flowchart of the method for intelligently formulating insurance agent sales performance plans according to the above embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are for illustrative purposes only, and those skilled in the art will readily appreciate other obvious variations. The basic principles of the present invention defined in the following description may be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the present invention.

[0025] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the elements may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0026] The present invention is an invention related to a computer program. Figure 2 The flowchart of a method for intelligently formulating insurance agent sales performance plans based on the present invention is shown. This method describes a solution for solving the problems raised by the present invention, based on a computer program processing flow, by executing a computer program compiled according to the above flow to control or process external or internal objects of the computer. The method of intelligently formulating insurance agent sales performance plans of the present invention can utilize a computer system to improve analysis efficiency and accuracy based on the computer's machine learning results, intelligently formulate and output insurance agent sales performance plans, and rationally assign sales tasks to specific executors. This can match sales personnel's sales skills and customer resources with the insurance products to be sold, significantly increasing sales opportunities and making sales plans easier to implement. It also significantly improves the efficiency of assignment work, and the algorithm calculations automatically executed by the computer eliminate a large amount of manually assigned work, thereby improving overall efficiency. It should be understood that the "computer" referred to in the present invention not only refers to devices such as desktop computers, laptops, and tablets, but also includes other intelligent electronic devices that can run according to programs and process data.

[0027] Specifically, the method for intelligently formulating an insurance agent's sales performance plan includes the following steps:

[0028] Build an insurance product classifier model;

[0029] The salesperson's data and their customer data are input into the insurance product classifier model to predict whether the requirements are met. If so, the product is allocated once, excluding the customer resource. The next customer data input is continued until the maximum number of copies of the product that can be allocated to the salesperson is calculated.

[0030] The decision tree model for the next product is cycled through and the allocation continues until the list of products that can be sold by all sales personnel and the maximum number of copies that can be sold for each product are calculated; and

[0031] Match sales plan indicators and output insurance agent sales performance plans.

[0032] In the step of constructing an insurance product classifier model, a decision tree ID3 algorithm is executed to construct a decision tree based on product sales rule factors; a classifier is designed for each product sold by an insurance company, and the average value range of each attribute of the sales rule used by the classifier is set to between 2 and 10.

[0033] More specifically, the method for intelligently formulating a sales performance plan for an insurance agent further includes the step of training an insurance product classifier model.

[0034] More specifically, the step of training the insurance product classifier model also includes the following steps: generating training data according to a conditional exhaustive method, and the training data range is preset to be between 100 and 100,000, so that the trained insurance product classifier model executes the classification of products to sales personnel and obtains matching data between products and sales personnel.

[0035] More specifically, the step of matching sales plan indicators further includes the following steps:

[0036] Accumulate the number of products allocated to each salesperson;

[0037] Compare the sales organization's sales plan data. If the cumulative number of copies is less than the sales plan number, the excess number of copies will be redistributed. If it is greater than the sales plan number of copies, the number of copies already allocated to each salesperson will be reduced based on the proportion of the excess data to the total number of copies, until the cumulative number of copies after rounding is equal to the planned number of copies, and the allocation task is completed.

[0038] In a specific embodiment, decision tree classification is performed. A decision tree is a process for classifying data using a series of rules. It provides a rule-like approach that determines what value will be obtained under certain conditions. Decision trees are categorized into classification trees and regression trees. Classification trees are used for discrete variables, while regression trees are used for continuous variables.

[0039] If efficiency and other factors are ignored, the cascaded judgment of all sample features will ultimately assign a single sample to a single class. In reality, some features among all sample features play a decisive role in classification. The decision tree construction process involves identifying these decisive features and constructing an inverted tree based on their degree of decisiveness. The most decisive feature is used as the root node. The next most decisive feature in each sub-dataset is then recursively found, until all data in the sub-datasets belong to the same class. Therefore, the process of constructing a decision tree is essentially a recursive process of classifying a dataset based on its features. It is necessary to determine which feature in the current dataset plays a decisive role in classifying the data.

[0040] In a specific embodiment, a decision tree is generated. The decision tree is generated in the following three parts:

[0041] Feature selection: Feature selection refers to selecting a feature from the numerous features in the training data as the splitting criterion for the current node. There are many different quantitative evaluation criteria for how to select features, which leads to different decision tree algorithms.

[0042] Decision tree generation: Based on the selected feature evaluation criteria, child nodes are recursively generated from top to bottom until the data set is indivisible, at which point the decision tree stops growing;

[0043] Pruning: Decision trees are prone to overfitting and generally require pruning to reduce the size of the tree structure and alleviate overfitting. There are two types of pruning techniques: pre-pruning and post-pruning.

[0044] In a specific embodiment, in the insurance product classifier model, the decision tree algorithm based on information theory is selected from algorithms such as ID3, CART and C4.5, among which the C4.5 and CART algorithms are derived from the ID3 algorithm.

[0045] More specifically, the process of partitioning a dataset aims to bring order to the disordered data. When a training dataset contains 20 features, a quantitative approach is used to determine the basis for partitioning. The quantitative partitioning approach can be selected from information theory metrics and information classification.

[0046] CART and C4.5 support processing data with continuous distributions. They primarily use binary splitting to handle continuous variables. This involves finding a specific value—the splitting value—to determine the left or right subtree if the feature value is greater than the splitting value. This splitting value is chosen to minimize the level of disorder in the resulting subtrees, and is defined differently in C4.5 and CART algorithms.

[0047] The ID3 algorithm, invented by Ross Quinlan, is based on the principle of Occam's razor: smaller decision trees are superior to larger ones (be simple theory). The ID3 algorithm evaluates and selects features based on information gain from information theory, selecting the feature with the highest information gain as the decision module. The ID3 algorithm can be used to partition nominal datasets without pruning. To eliminate overmatching, adjacent leaf nodes that do not generate significant information gain can be trimmed and merged (for example, by setting an information gain threshold). The CART algorithm also supports continuously distributed data features.

[0048] C4.5 is an improved version of ID3, inheriting its advantages. It uses information gain to select attributes, overcoming the drawback of using information gain to favor attributes with many values. It also performs tree pruning during construction, discretizes continuous attributes, and handles incomplete data. The classification rules generated by the C4.5 algorithm are easy to understand and highly accurate.

[0049] The CART algorithm, short for Classification and Regression Tree, uses the Gini index (selecting the feature with the smallest Gini index) as the splitting criterion and also includes post-pruning. To simplify the size of decision trees and improve tree generation efficiency, the CART decision tree algorithm was developed, which selects test attributes based on the Gini coefficient.

[0050] The method of intelligently formulating insurance agent sales performance plans according to the present invention is based on a decision tree algorithm and can be easily understood and explained, and the structure of the tree can be visualized; basically no preprocessing is required, no normalization is required in advance, and no missing values ​​need to be processed; the cost of using a decision tree for prediction is O(log2m), where m is the number of samples; it can process numerical data and categorical data; it can handle classification problems with multi-dimensional outputs; and the model can be verified through numerical statistical tests, which makes it possible to explain and verify the reliability of the model.

[0051] The method for intelligently formulating insurance agent sales performance plans according to the present invention is based on a decision tree algorithm, and pruning and setting the minimum number of samples required for leaf nodes or setting the maximum depth of the number are used to avoid overfitting; the integration of decision trees can make the decision tree more stable and alleviate the generation of completely different trees that may be caused by slight changes in the data; the actual decision tree learning algorithm is based on a heuristic algorithm, such as an algorithm that makes a local optimal decision at each node; multiple decision trees are trained through integrated learning to ensure that the global optimal decision tree is returned, and multiple decision trees are generally generated by random sampling of features and samples with replacement; the data set is balanced before fitting to avoid bias in the created decision tree.

[0052] It is worth mentioning that the introduction of the decision tree algorithm based on machine learning and the consideration of actual conditions have supplemented the branch situations in actual business scenarios that pure algorithms cannot fully cover, which has greatly improved the accuracy of sales plan allocation and helped insurance companies improve the efficiency of allocating sales tasks.

[0053] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided in the form of methods, systems, or computer program products. Thus, the present invention may take the form of an all-hardware embodiment, an all-software embodiment, or a combination of software and hardware embodiments.

[0054] Those skilled in the art will appreciate that the method for intelligently developing insurance agent sales performance plans described herein can be implemented using hardware, software, or a combination of both. The present invention can be implemented in a centralized manner within at least one computer system, or in a decentralized manner across multiple interconnected computer systems. Any computer system or other device capable of implementing the method is applicable. A commonly used combination of hardware and software can include a general-purpose computer system with a computer program installed, which controls the computer system by installing and executing the program to execute the method.

[0055] The present invention may be embedded in a computer program product, which includes all the features that enable the method described herein to be implemented. The computer program product is contained in one or more computer-readable storage media, and the computer-readable storage medium has a computer-readable program code contained therein. According to another aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method of the present invention are performed. A computer storage medium is a medium in a computer memory for storing a certain discontinuous physical quantity. Computer storage media include but are not limited to semiconductors, disk memories, magnetic cores, magnetic drums, magnetic tapes, laser discs, etc. It will be understood by those skilled in the art that computer storage media are not limited to the aforementioned examples, which are merely examples and are not limited to the present invention.

[0056] According to another aspect of the present invention, a device for intelligently developing an insurance agent sales performance plan is provided. The device includes a software application, a memory for storing the software application, and a processor for executing the software application. Each program in the software application is capable of correspondingly executing the steps of the method for intelligently developing an insurance agent sales performance plan according to the present invention.

[0057] A typical combination of hardware and software may be a general-purpose computer system with a computer program, which, when loaded and executed, controls the computer system so as to execute the method of intelligently formulating insurance agent sales performance plans disclosed in the present invention.

[0058] It will be understood by those skilled in the art that the device for intelligently formulating insurance agent sales performance plans can be embodied as a desktop computer, notebook, mobile smart device, etc., but the foregoing is only for example and also includes other smart devices equipped with the software application of the present invention.

[0059] Corresponding to the embodiment of the method of the present invention, according to another aspect of the present invention, a system for intelligently formulating insurance agent sales performance plans is also provided. The system for intelligently formulating insurance agent sales performance plans is the application of the method of intelligently formulating insurance agent sales performance plans of the present invention in computer program improvement.

[0060] Specifically, the system for intelligently formulating insurance agent sales performance plans includes an insurance product classifier model unit, a product allocation unit, and an insurance agent sales performance plan output unit, wherein the insurance product classifier model unit is configured to: construct an insurance product classifier model, and construct a decision tree model based on product sales rule factors; wherein the product allocation unit is configured to: obtain salesperson data and the salesperson's customer data, input the data into the constructed decision tree model, and execute product allocation to the salesperson; wherein the insurance agent sales performance plan output unit matches the sales plan indicators and outputs the insurance agent sales performance plan; wherein the insurance agent sales performance plan output unit is further configured to: accumulate the number of product copies allocated to each salesperson, compare it with the sales plan data of the sales organization, if the accumulated number of copies is less than the sales plan number of copies, perform secondary allocation on the extra number of copies, and if it is greater than the sales plan number of copies, reduce the number of copies already allocated to each salesperson according to the proportion of the extra data to the total number of copies, until the accumulated number of copies after rounding is equal to the planned number of copies, and complete the allocation task.

[0061] Furthermore, the product allocation unit is also configured to: after the acquired salesperson data and the salesperson's customer data are input into the constructed decision tree model, predict whether they are met. If they are met, the product is allocated once and the customer resources are excluded; continue with the input of the next customer until the maximum number of copies of the product that can be allocated to the salesperson is calculated; loop the decision tree model of the next product and continue to allocate until the list of products that can be sold by all salespersons and the maximum number of copies that can be sold of the product are calculated.

[0062] Furthermore, the insurance product classifier model unit also includes a decision tree construction module and an insurance product classifier model training module. The insurance product classifier model training module is used to train the insurance product classifier model, wherein training data is generated according to a conditional exhaustive method, and the training data range is preset to between 100 and 100,000, so that the trained insurance product classifier model executes the classification of products to sales personnel and obtains matching data from products to sales personnel; wherein the decision tree construction module executes the decision tree ID3 algorithm and constructs a decision tree based on the product sales rule factor, wherein a classifier is designed for each product sold by an insurance company, and the average value range of each attribute of the sales rule used by the classifier is set to between 2 and 10.

[0063] Furthermore, the system for intelligently formulating insurance agent sales performance plans also includes a decision tree classification module and a decision tree generation module, wherein the decision tree classification module is configured to: perform decision tree classification, decision trees are divided into classification trees and regression trees, classification trees are used to make decision trees for discrete variables, and regression trees are used to make decision trees for continuous variables, wherein in the construction process of the decision tree, according to the degree of decisiveness of the feature, the feature with the greatest decisive effect is used as the root node, and then the second largest decisive feature in the sub-dataset under each branch is recursively found until all data in the sub-dataset belongs to the same category, wherein, in the insurance product classifier model, the decision tree algorithm based on information theory is selected from ID3, CART and C4.5 algorithms.

[0064] Furthermore, the decision tree generation module is configured to: perform feature selection; recursively generate child nodes from top to bottom according to the selected feature evaluation criteria until the data set is indivisible, at which point the decision tree stops growing; and reduce the size of the tree structure based on pre-pruning and post-pruning pruning techniques.

[0065] It will be appreciated by those skilled in the art that the present invention has been described with reference to the flowcharts and / or block diagrams of the methods, systems, and computer program products according to the present invention. Each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions (which are passed through the processor of the computer or other programmable data processing device) generate means for implementing the functions specified in one or more blocks in the flowcharts and / or block diagrams.

[0066] Those skilled in the art will appreciate that the embodiments of the present invention described above and shown in the accompanying drawings are intended to be illustrative only and are not intended to limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Any variations or modifications may be made to the embodiments of the present invention without departing from these principles.

Claims

1. A method for intelligently formulating a sales performance plan for an insurance agent, characterized in that: The following steps are involved: Build an insurance product classifier model; The salesperson's data and their customer data are input into the insurance product classifier model to predict whether the requirements are met. If so, the product is allocated once, excluding the customer resource. The next customer data input is continued until the maximum number of copies of the product that can be allocated to the salesperson is calculated. The decision tree model for the next product is looped and the allocation continues until the list of products that can be sold by all sales personnel and the maximum number of copies that can be sold for each product are calculated; as well as Match sales plan indicators and output insurance agent sales performance plans; The method for intelligently formulating insurance agent sales performance plans further comprises the steps of: training an insurance product classifier model; The step of training the insurance product classifier model further includes the following steps: generating training data according to a conditional exhaustive method, where the training data range is preset to be between 100 and 100,000, so that the trained insurance product classifier model is executed to classify products to sales personnel, thereby obtaining matching data between products and sales personnel; The matching sales plan indicator step further includes the following steps: accumulating the number of product copies allocated to each salesperson; and comparing the sales plan data of the sales organization. If the accumulated number of copies is less than the sales plan number of copies, the excess copies are redistributed; if it is greater than the sales plan number of copies, the number of copies allocated to each salesperson is reduced according to the proportion of the excess data to the total number of copies, until the accumulated number of copies after rounding is equal to the planned number of copies, thereby completing the allocation task; In the step of constructing an insurance product classifier model, a decision tree ID3 algorithm is executed to construct a decision tree based on product sales rule factors; wherein, a classifier is designed for each product sold by an insurance company, and the average value range of each attribute of the sales rule used by the classifier is set to between 2 and 10.

2. The method for intelligently formulating insurance agent sales performance plans as described in claim 1, wherein when performing decision tree classification, the decision trees are divided into classification trees and regression trees, the classification trees are used to form decision trees for discrete variables, and the regression trees are used to form decision trees for continuous variables; wherein during the construction of the decision tree, based on the degree of determinism of the features, the feature with the greatest determinism is used as the root node, and then the next most deterministic feature in the sub-datasets under each branch is recursively found until all data in the sub-datasets belong to the same category.

3. The method for intelligently formulating insurance agent sales performance plans as described in claim 1 further includes executing the decision tree generation step: performing feature selection; recursively generating child nodes from top to bottom based on the selected feature evaluation criteria until the data set becomes indivisible, at which point the decision tree stops growing; and reducing the size of the tree structure based on pre-pruning and post-pruning techniques.

4. A device for intelligently formulating insurance agent sales performance plans, characterized in that: The device for intelligently formulating insurance agent sales performance plans includes: a software application, a memory for storing the software application, and a processor for executing the software application, wherein each program of the software application correspondingly executes the steps in the method for intelligently formulating insurance agent sales performance plans as described in any one of claims 1 to 3.

5. A system for intelligently formulating insurance agent sales performance plans, applicable to the method for intelligently formulating insurance agent sales performance plans according to any one of claims 1 to 3, characterized in that: The system for intelligently formulating insurance agent sales performance plans includes an insurance product classifier model unit, a product allocation unit, and an insurance agent sales performance plan output unit, wherein the insurance product classifier model unit is configured to: construct an insurance product classifier model, and construct a decision tree model based on product sales rule factors; wherein the product allocation unit is configured to: obtain salesperson data and the salesperson's customer data, input the data into the constructed decision tree model, and execute product allocation to the salesperson; wherein the insurance agent sales performance plan output unit matches the sales plan indicators and outputs the insurance agent sales performance plan; wherein the insurance agent sales performance plan output unit is further configured to: accumulate the number of product copies allocated to each salesperson, compare it with the sales plan data of the sales organization, if the accumulated number of copies is less than the sales plan number of copies, perform secondary allocation on the excess number of copies, and if the number of copies is greater than the sales plan number of copies, reduce the number of copies already allocated to each salesperson according to the proportion of the excess data to the total number of copies, until the accumulated number of copies after rounding is equal to the planned number of copies, and complete the allocation task.

6. The system for intelligently formulating insurance agent sales performance plans as described in claim 5, wherein the product allocation unit is further configured to: after the acquired salesperson data and the salesperson's customer data are input into the constructed decision tree model, predict whether they are satisfied; if so, the product is allocated once, excluding the customer resources; continue with the input of the next customer until the maximum number of copies of the product that can be allocated to the salesperson is calculated; loop the decision tree model for the next product and continue allocation until the list of products that can be sold by all salespeople and the maximum number of copies that can be sold of the product are calculated.

7. The system for intelligently formulating insurance agent sales performance plans according to claim 5 or 6, wherein the insurance product classifier model unit further comprises a decision tree construction module and an insurance product classifier model training module, wherein the insurance product classifier model training module is used to train the insurance product classifier model, wherein training data is generated in a conditional exhaustive manner, and the training data range is preset to be between 100 and 100,000, so that the trained insurance product classifier model is used to classify products to sales personnel and obtain product-to-sales personnel matching data; wherein the decision tree construction module executes a decision tree ID3 algorithm to construct a decision tree based on product sales rule factors, wherein: A classifier is designed for each product sold by an insurance company, and the average value range of each attribute of the sales rules used by the classifier is set to between 2 and 10; the system for intelligently formulating insurance agent sales performance plans also includes a decision tree classification module and a decision tree generation module, wherein the decision tree classification module is configured to: perform decision tree classification, decision trees are divided into classification trees and regression trees, classification trees are used to make decision trees for discrete variables, and regression trees are used to make decision trees for continuous variables, wherein during the construction of the decision tree, according to the degree of decisiveness of the feature, the feature with the greatest decisive effect is used as the root node, and then the second largest decisive feature in the sub-dataset under each branch is recursively found until all data in the sub-dataset belongs to the same category; wherein the decision tree generation module is configured to: perform feature selection; recursively generate child nodes from top to bottom according to the selected feature evaluation criteria until the decision tree stops growing when the data set is indivisible; and reduce the size of the tree structure by pruning techniques based on pre-pruning and post-pruning.

Images