Method, system and device for allocating customer lists of insurance sales personnel based on clustering algorithm

Abstract

A method for allocating customer lists of insurance sales personnel based on a clustering algorithm comprises the following steps: obtaining information of customers and sales personnel, defining attribute lists of two dimensions of customers and sales personnel according to personal attributes and insurance attributes, sorting the attribute sub-tables of the two dimensions listed, and recording the sorting values; performing labeling processing on each attribute; the insurance sales personnel customer list allocation model performs customer attribute vector calculation to obtain a vector list of all users; performs sales personnel vector calculation to obtain a vector list of sales personnel; performs clustering algorithm steps; performs Euclidean distance calculation steps; and unallocated customers continue to remain in the list of users to be allocated, and the clustering algorithm steps and the Euclidean distance calculation steps are repeatedly performed to complete the allocation of customer lists for all insurance sales personnel, and the insurance sales personnel customer list allocation model outputs the allocation results.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method, system and device for allocating customer lists of insurance sales personnel based on a clustering algorithm. Background Art

[0002] In recent years, artificial intelligence has achieved rapid development in data, algorithms and computing power, ushering in a new wave of development under the background of the global economic digital transformation. The influence of this wave of artificial intelligence far exceeds that of the previous ones, and the most notable feature is that the influence has spread from professional fields to popular fields.

[0003] Regarding the problem of customer allocation for insurance sales personnel, insurance companies usually have up to millions of users, and large insurance companies have up to hundreds of millions of users. These users require a large number of insurance agents to support and serve them in terms of insurance product promotion, insurance customer relationship maintenance, and after-sales service. In the usual customer allocation rules, sales personnel allocate customers based on the principle of proximity to the user's contact address or historical service rules, but new customers and customers under the jurisdiction of resigned agents need to be reallocated. This allocation method is currently managed manually by managers within the insurance company, and there is currently no unified and fixed method for allocation.

[0004] The artificial intelligence classification algorithm can use machine learning to perform clustering according to customer characteristics and automatically group users. The algorithm is already very mature. Although it is usually used in recommendation systems, the algorithm is universal and can be used to group customers and adapt to the characteristics of insurance sales personnel. Customer allocation is theoretically feasible.

[0005] However, the current allocation rules rely on manual allocation by managers. The allocation work is cumbersome and there is no objective reference rule for the allocation logic. It is also difficult for managers to make reasonable allocations. Unbalanced allocation also poses certain risks to subsequent customer service and management risks to insurance companies. Summary of the invention

[0006] One of the purposes of the present invention is to provide a method, system and device for allocating customer lists of insurance sales personnel based on a clustering algorithm, which can calculate weighted dimensions of customers and then automatically classify them, adapt sales personnel feature data, perform two-way matching, and automatically allocate customers to insurance sales personnel.

[0007] One of the purposes of the present invention is to provide a method, system and device for allocating customer lists of insurance sales personnel based on a clustering algorithm, which can automatically allocate customers through an algorithm, thereby greatly improving the efficiency of allocation and also improving the accuracy of allocation.

[0008] One of the purposes of the present invention is to provide a method, system and device for allocating customer lists of insurance sales personnel based on a clustering algorithm, which can replace the manual customer allocation work of insurance company managers, reduce the risk of unreasonable allocation, and improve the operating efficiency of the insurance company.

[0009] In order to achieve at least one of the inventive purposes of the present invention, the present invention provides a method for allocating a client list of an insurance salesperson based on a clustering algorithm, the method for allocating a client list of an insurance salesperson based on a clustering algorithm comprising the following steps:

[0010] Obtain information about customers and salespeople, define attribute lists of two dimensions of customers and salespeople according to personal attributes and insurance attributes, sort the attribute sub-tables of the two dimensions, and record the sorting values;

[0011] Perform labeling on each attribute;

[0012] The insurance salesperson customer list allocation model performs customer attribute vector calculations to obtain a vector list of all users;

[0013] Perform salesperson vector calculation to obtain a salesperson vector list;

[0014] Execute the clustering algorithm steps, cluster the users into the corresponding number of groups according to the number of sales personnel, calculate the average of the vector sum of each group, and classify similar samples into one class;

[0015] Execute the Euclidean distance calculation step, take the minimum value of the obtained set, define the user group as the group of the current salesperson, and assign the users to the current salesperson according to the minimum Euclidean distance according to the quantity that the current salesperson needs to assign, thereby completing the assignment of the current salesperson; and

[0016] The unallocated customers are kept in the list of users to be allocated, and the clustering algorithm step and the Euclidean distance calculation step are repeatedly executed to complete the allocation of customer lists for all insurance sales personnel, and the insurance sales personnel customer list allocation model outputs the allocation results.

[0017] In some embodiments, the label value when performing labeling processing is an integer, and the range of each label value is limited to less than 10.

[0018] In some embodiments, the calculation formula in the step of calculating the customer attribute vector is:

[0019]

[0020]

[0021] Among them, X and Y are calculated respectively and recorded as a vector (X, Y) to form a vector list of all users.

[0022] In some embodiments, the calculation formula for performing the salesperson vector calculation is:

[0023]

[0024]

[0025] The sub-table calculates X, Y to form a (X, Y) vector list for the salesperson.

[0026] In some embodiments, in the step of executing the clustering algorithm, the users are clustered into n groups according to the number of sales personnel using the K-means algorithm, and the average value of the sum of the (X, Y) vectors of each group is calculated to obtain the (x1, y1) vector, and the calculation formula is:

[0027]

[0028]

[0029] Among them, k center points are set as representatives of each class, μ k is the center of k clusters, C ik Indicates whether the i-th sample belongs to the k-th class;

[0030] Among them, k center points are initialized and samples are assigned to the nearest center point. The center points of each cluster are recalculated in the new cluster, and the k center points are continuously updated until convergence.

[0031] In some embodiments, in the step of calculating the Euclidean distance, the (X, Y) vector value of the salesperson is recorded as (x2, y2) and the (x1, y1) of each customer after clustering is used to calculate the Euclidean distance, and the calculation formula is:

[0032]

[0033] Among them, the D set takes the minimum value, that is, the user group is the group of the current salesperson. When the number of people in the group is less than or equal to the number of people to be assigned to the salesperson, the group assignment is completed. Otherwise, the Euclidean distance from each person in the group to the salesperson is calculated, and they are assigned to the current salesperson in order of the minimum Euclidean distance to complete the salesperson assignment; unassigned customers continue to remain in the list of users to be assigned.

[0034] According to another aspect of the present invention, there is also provided a device for allocating a client list of an insurance salesperson based on a clustering algorithm, comprising:

[0035] Memory, for storing software applications,

[0036] The processor is used to execute the software application, and each program of the software application correspondingly executes the steps in the method of allocating a customer list of insurance sales personnel based on a clustering algorithm.

[0037] According to another aspect of the present invention, there is also provided a system for allocating customer lists of insurance sales personnel based on a clustering algorithm, the system for allocating customer lists of insurance sales personnel based on a clustering algorithm comprising an attribute list unit, an insurance sales personnel customer list allocation model unit and an allocation result output unit, the attribute list unit being configured to: obtain information about customers and sales personnel, define attribute lists of two dimensions of customers and sales personnel according to personal attributes and insurance attributes, sort the attribute sub-tables of the two dimensions listed, and record the sorting values; and perform labeling processing on each attribute and input it into the insurance sales personnel customer list allocation model unit; the insurance sales personnel customer list allocation model unit comprises a customer attribute vector calculation module, a sales personnel vector calculation module, a clustering algorithm module, a Euclidean distance calculation module and a reallocation module, wherein the customer attribute vector calculation module calculates the customer attribute vector; the sales personnel The vector calculation module calculates the vector of the salesperson; the clustering algorithm module clusters and groups user attributes through the K-means algorithm, groups similar users into the same user group, and executes an overall allocation from one group to the salesperson; the Euclidean distance calculation module is used to execute the allocation rule, takes the minimum value of the obtained set, defines the user group as the group of the current salesperson, and completes the group allocation when the number of people in the group is less than or equal to the number of people to be allocated for the salesperson, otherwise calculates the Euclidean distance from each person in the group to the salesperson, and allocates them to the current salesperson according to the number of people who need to be allocated to the current salesperson in order of the minimum Euclidean distance, thereby completing the allocation of the current salesperson; the reallocation module obtains the unallocated customer information in the list of users to be allocated, and puts the users with overflowed allocation back into the pool to be allocated for repeated allocation; the allocation result output unit outputs the allocation result of the insurance salesperson customer list allocation model unit.

[0038] In some embodiments, wherein

[0039] The calculation formula in the customer attribute vector calculation module is:

[0040]

[0041]

[0042] Among them, X and Y are calculated respectively and recorded as a vector (X, Y) to form a vector list of all users;

[0043] The calculation formula in the salesperson vector calculation module is:

[0044]

[0045]

[0046] Among them, the sub-table calculates X, Y to form the (X, Y) vector list of the salesperson;

[0047] The clustering algorithm module is configured as follows: according to the number of sales personnel, users are clustered into n groups by the K-means algorithm, and the average value of the sum of the (X, Y) vectors of each group is calculated to obtain the (x1, y1) vector, and the calculation formula is:

[0048]

[0049]

[0050] Among them, k center points are set as representatives of each class, μ_k is the center of k classes, and Cik represents whether the i-th sample belongs to the k-th class; among them, k center points are initialized and samples are assigned to the nearest center point, and the center points of each cluster are recalculated in the new cluster, and k center points are continuously updated until convergence;

[0051] The Euclidean distance calculation module is further configured to calculate the Euclidean distance using the (X, Y) vector value of the salesperson as (x2, y2) and the (x1, y1) of each customer after clustering, and the calculation formula is:

[0052]

[0053] Among them, the D set takes the minimum value, that is, the user group is the group of the current salesperson. When the number of people in the group is less than or equal to the number of people to be assigned to the salesperson, the group assignment is completed. Otherwise, the Euclidean distance from each person in the group to the salesperson is calculated, and they are assigned to the current salesperson in order of the minimum Euclidean distance to complete the salesperson assignment; unassigned customers continue to remain in the list of users to be assigned.

[0054] In some embodiments, the label value of the attribute list unit when performing labeling processing is an integer, and the range of each label value is limited to less than 10. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic diagram of a method, system and device method for allocating customer lists of insurance sales personnel based on a clustering algorithm in a specific embodiment according to an embodiment of the present invention.

[0056] Figure 2 It is a flowchart of the steps of the method, system and device method for allocating customer lists of insurance sales personnel based on clustering algorithm according to the above embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0058] 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 element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0059] The present invention is an invention related to computer programs. A flow chart of a method for allocating a customer list of insurance sales personnel based on a clustering algorithm according to the present invention is disclosed, and a solution for solving the problem proposed by the present invention is described, based on the computer program processing flow, by executing a computer program compiled according to the above flow, to control or process the external or internal objects of the computer. Through the intelligent analysis method of medical test data of the present invention, it is possible to use a computer system to automatically allocate based on a clustering algorithm, calculate the weighted dimension of the customer and then automatically classify it, and adapt the characteristic data of the salesperson to perform two-way matching, and automatically allocate the customer to the insurance salesperson; the customer is automatically allocated by an algorithm, thereby greatly improving the efficiency of allocation and the accuracy of allocation; replacing the customer allocation work of the insurance company manager, reducing the risk of unreasonable allocation, and improving the operating efficiency of the insurance company. It can be understood that the "computer" referred to in the present invention not only refers to desktop computers, laptops, tablets and other devices, but also includes other intelligent electronic devices that can run according to the program and process data.

[0060] Specifically, the method for allocating a customer list of insurance sales personnel based on a clustering algorithm comprises the following steps:

[0061] Obtain information about customers and salespeople, define attribute lists of two dimensions of customers and salespeople according to personal attributes and insurance attributes, sort the attribute sub-tables of the two dimensions, and record the sorting values;

[0062] Perform labeling on each attribute;

[0063] The insurance salesperson customer list allocation model performs customer attribute vector calculations to obtain a vector list of all users;

[0064] Perform salesperson vector calculation to obtain a salesperson vector list;

[0065] Execute the clustering algorithm steps, cluster the users into the corresponding number of groups according to the number of sales personnel, calculate the average of the vector sum of each group, and classify similar samples into one class;

[0066] Execute the Euclidean distance calculation step, take the minimum value of the obtained set, define the user group as the group of the current salesperson, and assign the users to the current salesperson according to the minimum Euclidean distance according to the number of users to be assigned to the current salesperson, thereby completing the assignment of the current salesperson; and

[0067] The unallocated customers are kept in the list of users to be allocated, and the clustering algorithm step and the Euclidean distance calculation step are repeatedly executed to complete the allocation of customer lists for all insurance sales personnel, and the insurance sales personnel customer list allocation model outputs the allocation results.

[0068] Specifically, the label value during labeling processing is an integer, and the value range of each label is limited to less than 10.

[0069] Specifically, the calculation formula in the step of calculating the customer attribute vector is:

[0070]

[0071]

[0072] Among them, X and Y are calculated respectively and recorded as a vector (X, Y) to form a vector list of all users.

[0073] Specifically, the calculation formula for performing salesperson vector calculation is:

[0074]

[0075]

[0076] The sub-table calculates X, Y to form a (X, Y) vector list for the salesperson.

[0077] Specifically, in the step of executing the clustering algorithm, users are clustered into n groups according to the number of sales personnel using the K-means algorithm, and the average value of the sum of the (X, Y) vectors of each group is calculated to obtain the (x1, y1) vector, and the calculation formula is:

[0078]

[0079]

[0080] Among them, k center points are set as representatives of each class, μ k is the center of k clusters, C ik Indicates whether the i-th sample belongs to the k-th class;

[0081] Among them, k center points are initialized and samples are assigned to the nearest center point. The center points of each cluster are recalculated in the new cluster, and the k center points are continuously updated until convergence.

[0082] Specifically, in the step of calculating the Euclidean distance, the (X, Y) vector value of the salesperson is recorded as (x2, y2) and the (x1, y1) of each customer after clustering is used to calculate the Euclidean distance. The calculation formula is:

[0083]

[0084] Among them, the D set takes the minimum value, that is, the user group is the group of the current salesperson. When the number of people in the group is less than or equal to the number of people to be assigned to the salesperson, the group assignment is completed. Otherwise, the Euclidean distance from each person in the group to the salesperson is calculated, and they are assigned to the current salesperson in order of the minimum Euclidean distance to complete the salesperson assignment; unassigned customers continue to remain in the list of users to be assigned.

[0085] In a specific embodiment, Figure 1 Table and Figure 2 As shown in the specific implementation process, the method of allocating the customer list of insurance sales personnel based on the clustering algorithm of the present invention is used. Define the attribute lists of the two dimensions of customers and sales personnel, such as Figure 1 shown.

[0086] Specifically, the listed two dimension attribute sub-tables are sorted, and the sorting values ​​are recorded.

[0087] Furthermore, each attribute is labeled, the label value is an integer, and the value range of each label is limited to less than 10.

[0088] Furthermore, the customer attribute vector is calculated according to the following formula:

[0089]

[0090]

[0091] Calculate X and Y respectively and record them as a vector (X, Y) to get a vector list of all users.

[0092] Furthermore, the salesperson's vector is calculated using the following formula:

[0093]

[0094]

[0095] Calculate X and Y in the separate tables to get a list of (X, Y) vectors for the salespersons.

[0096] Furthermore, the users are clustered into n groups (n is the number of salespeople) using the k-means algorithm:

[0097] Calculate the average of the sum of the (X, Y) vectors for each group to get the (x1, y1) vector.

[0098]

[0099]

[0100] It is understandable that the K-means algorithm is an unsupervised algorithm used to classify similar samples into one class. For a given dataset {x1, x2, …, xN} containing N samples, the goal of the K-means algorithm is to assign the samples to k classes. The K-means algorithm needs to assume that there are K center points as representatives of each class. In the objective function, μ k is the center of k clusters, C ik Indicates whether the i-th sample belongs to the k-th class. The K-means algorithm is a process of finding suitable center points and assigning samples to k center points. The K-means algorithm needs to initialize k center points and assign samples to the center point closest to it, and then recalculate the center points of each cluster in the new cluster, so that the k center points are continuously updated until convergence.

[0101] Furthermore, the Euclidean distance is calculated using the salesperson's (X, Y) vector value (x2, y2) and each customer's clustered group (x1, y1). The formula is as follows:

[0102]

[0103] Then get the D set, and then take the minimum value of the D set, that is, the user group is the group of the current salesperson. When the number of people in the group is less than or equal to the number of people to be assigned to the salesperson, the group assignment is completed. Otherwise, calculate the Euclidean distance from each person in the group to the salesperson, and assign the first n (n is the number of salespeople to be assigned) positions with the smallest distance to the salesperson to complete the salesperson assignment. Unassigned customers continue to remain in the list of users to be assigned.

[0104] Furthermore, the previous two steps are re-executed to complete the final allocation action.

[0105] It is worth mentioning that in this preferred embodiment of the present invention, in the work of assigning customers to sales personnel, since there are many customer attributes and sales personnel's assigned attributes, and the attribute values ​​cannot be directly compared and matched, an algorithm is needed to match them. The above algorithm uses a scheme of clustering and grouping user attributes to group similar users into the same user group, so that the overall assignment of a group to a salesperson can be completed, and the assignment rules are also converted into a method of calculating the Euclidean distance through a plane, which simplifies the assignment rules, effectively meets the assignment tasks, and can basically achieve the desired assignment effect.

[0106] It is worth mentioning that the method of allocating customer lists of insurance sales personnel based on clustering algorithm of the present invention, combined with the K-means algorithm and Euclidean distance formula of machine learning, can realize the automatic allocation of customer lists to sales personnel, and consider the actual situation to supplement the scheme of re-adding users with overflowing allocation to the pool to be allocated for repeated allocation, which greatly automates the allocation work and improves the allocation efficiency.

[0107] 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. Therefore, the present invention may take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware.

[0108] It will be appreciated by those skilled in the art that the method of allocating a client list of insurance sales personnel based on a clustering algorithm of the present invention can be implemented by hardware, software, or a combination of hardware and software. The present invention can be implemented in a centralized manner in at least one computer system, or in a decentralized manner by different parts distributed in several interconnected computer systems. Any computer system or other device that can implement the method is applicable. The combination of common hardware and software can be a general-purpose computer system with a computer program installed, and the computer system is controlled by installing and executing the program to make it run according to the method.

[0109] 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 can be performed. Computer storage media 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 storage, magnetic cores, magnetic drums, magnetic tapes, laser disks, etc. It can be understood by those skilled in the art that computer storage media are not limited to the aforementioned examples, and the aforementioned examples are merely examples and are not limited to the present invention.

[0110] According to another aspect of the present invention, there is also provided a device for allocating a client list of insurance sales personnel based on a clustering algorithm, the device comprising: a software application, a memory for storing the software application, and a processor for executing the software application. Each program of the software application can correspondingly execute the steps of the method for allocating a client list of insurance sales personnel based on a clustering algorithm of the present invention.

[0111] 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 to perform the method of allocating customer lists of insurance sales personnel based on clustering algorithms disclosed in the present invention.

[0112] It will be understood by those skilled in the art that the device may be embodied as a desktop computer, a notebook, a mobile smart device, etc., but the foregoing is only for example and also includes other smart analysis devices equipped with the software application of the present invention.

[0113] Corresponding to the embodiment of the method of the present invention, according to another aspect of the present invention, a method system for allocating customer lists of insurance sales personnel based on a clustering algorithm is also provided. The system for allocating customer lists of insurance sales personnel based on a clustering algorithm is the application of the method of allocating customer lists of insurance sales personnel based on a clustering algorithm of the present invention in the improvement of a computer program.

[0114] Specifically,

[0115] 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 box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram, can obviously 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 (the instructions are passed through the processor of the computer or other programmable data processing device) generate a device for implementing the functions specified in one or more boxes of the flowchart and / or block diagram.

[0116] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. A method for allocating customer lists of insurance sales personnel based on clustering algorithm, characterized in that: The method for allocating a customer list of insurance sales personnel based on a clustering algorithm comprises the following steps: Obtain information about customers and salespeople, define attribute lists of two dimensions of customers and salespeople according to personal attributes and insurance attributes, sort the attribute sub-tables of the two dimensions, and record the sorting values; Perform labeling on each attribute; The insurance salesperson customer list allocation model performs customer attribute vector calculations to obtain a vector list of all users; Perform salesperson vector calculation to obtain a salesperson vector list; Execute the clustering algorithm steps, cluster the users into the corresponding number of groups according to the number of sales personnel, calculate the average of the vector sum of each group, and classify similar samples into one class; Execute the Euclidean distance calculation step, take the minimum value of the obtained set, define the user group as the group of the current salesperson, and assign the users to the current salesperson according to the minimum Euclidean distance according to the quantity that the current salesperson needs to assign, thereby completing the assignment of the current salesperson; and The unallocated customers are kept in the list of users to be allocated, and the clustering algorithm step and the Euclidean distance calculation step are repeatedly executed to complete the allocation of customer lists for all insurance sales personnel, and the insurance sales personnel customer list allocation model outputs the allocation results.

2. The method for allocating customer lists of insurance sales personnel based on a clustering algorithm as described in claim 1, wherein the label value when performing labeling processing is an integer, and the range of each label value is limited to less than 10.

3. The method for allocating a customer list of insurance sales personnel based on a clustering algorithm as claimed in claim 1, wherein the calculation formula in the step of calculating the customer attribute vector is: in, X and Y are calculated respectively and recorded as a vector (X, Y) to form a vector list of all users.

4. The method for allocating a customer list of insurance sales personnel based on a clustering algorithm as claimed in claim 3, wherein the calculation formula for performing the sales personnel vector calculation is: in, The sub-table calculates X, Y to form a list of (X, Y) vectors for the salesperson.

5. The method for allocating a customer list of insurance sales personnel based on a clustering algorithm as claimed in claim 4, wherein: In the step of executing the clustering algorithm, users are clustered into n groups according to the number of sales personnel using the K-means algorithm, and the average value of the sum of the (X, Y) vectors of each group is calculated to obtain the (x1, y1) vector, and the calculation formula is: Among them, k center points are set as representatives of each class, μ k is the center of k clusters, C ik Indicates whether the i-th sample belongs to the k-th class; Among them, k center points are initialized and samples are assigned to the nearest center point. The center points of each cluster are recalculated in the new cluster, and the k center points are continuously updated until convergence.

6. The method for allocating a customer list of insurance sales personnel based on a clustering algorithm as claimed in claim 5, wherein: In the Euclidean distance calculation step, the (X, Y) vector value of the salesperson is recorded as (x2, y2) and the (x1, y1) of each customer after clustering is used to calculate the Euclidean distance. The calculation formula is: Among them, the D set takes the minimum value, that is, the user group is the group of the current salesperson. When the number of people in the group is less than or equal to the number of people to be assigned to the salesperson, the group assignment is completed. Otherwise, the Euclidean distance from each person in the group to the salesperson is calculated, and they are assigned to the current salesperson in order of the minimum Euclidean distance to complete the salesperson assignment; unassigned customers continue to remain in the list of users to be assigned.

7. A device for distributing customer lists of insurance sales personnel based on a clustering algorithm, characterized in that: include: Memory, for storing software applications, A processor is used to execute the software application, each program of the software application correspondingly executes the steps in the method for allocating a customer list of insurance sales personnel based on a clustering algorithm as described in claims 1 to 6.

8. A system for allocating customer lists of insurance sales personnel based on clustering algorithms, characterized in that: The system for allocating insurance salesperson customer lists based on clustering algorithms comprises an attribute list unit, an insurance salesperson customer list allocation model unit, and an allocation result output unit, wherein the attribute list unit is configured to: obtain information about customers and salespersons, define attribute lists of two dimensions of customers and salespersons according to personal attributes and insurance attributes, sort the attribute sub-tables of the two dimensions listed, and record the sorting values; and perform labeling processing on each attribute, and input the labeling to the insurance salesperson customer list allocation model unit; The insurance salesperson customer list allocation model unit includes a customer attribute vector calculation module, a salesperson vector calculation module, a clustering algorithm module, a Euclidean distance calculation module and a reallocation module, wherein the customer attribute vector calculation module calculates the customer attribute vector; the salesperson vector calculation module calculates the salesperson vector; the clustering algorithm module clusters and groups user attributes through the K-means algorithm, groups similar users into the same user group, and performs an overall allocation from one group to the salesperson; the Euclidean distance calculation module is used to execute the allocation rule, take the minimum value of the obtained set, define the user group as the group of the current salesperson, and complete the group allocation when the number of people in the group is less than or equal to the number of people to be allocated for the salesperson, otherwise calculate the Euclidean distance from each person in the group to the salesperson, and allocate them to the current salesperson according to the number of people to be allocated to the current salesperson in order of the minimum Euclidean distance, thereby completing the allocation of the current salesperson; the reallocation module obtains the unallocated customer information in the list of users to be allocated, and re-enters the users who have been allocated in the pool to be allocated for repeated allocation; the allocation result output unit outputs the allocation result of the insurance salesperson customer list allocation model unit.

9. The system for allocating insurance salesperson customer lists based on clustering algorithm as claimed in claim 8, wherein: The calculation formula in the customer attribute vector calculation module is: Among them, X and Y are calculated respectively and recorded as a vector (X, Y) to form a vector list of all users; The calculation formula in the salesperson vector calculation module is: Among them, the sub-table calculates X, Y to form the (X, Y) vector list of the salesperson; The clustering algorithm module is configured as follows: according to the number of sales personnel, users are clustered into n groups by the K-means algorithm, and the average value of the sum of the (X, Y) vectors of each group is calculated to obtain the (x1, y1) vector, and the calculation formula is: Among them, k center points are set as representatives of each class, μ_k is the center of k classes, and Cik represents whether the i-th sample belongs to the k-th class; among them, k center points are initialized and samples are assigned to the nearest center point, and the center points of each cluster are recalculated in the new cluster, and k center points are continuously updated until convergence; The Euclidean distance calculation module is further configured to calculate the Euclidean distance using the (X, Y) vector value of the salesperson as (x2, y2) and the (x1, y1) of each customer after clustering, and the calculation formula is: Among them, the D set takes the minimum value, that is, the user group is the group of the current salesperson. When the number of people in the group is less than or equal to the number of people to be assigned to the salesperson, the group assignment is completed. Otherwise, the Euclidean distance from each person in the group to the salesperson is calculated, and they are assigned to the current salesperson in order of the minimum Euclidean distance to complete the salesperson assignment; unassigned customers continue to remain in the list of users to be assigned.

10. The system for allocating insurance salesperson customer lists based on clustering algorithm as claimed in claim 8 or 9, wherein: When the attribute list unit performs labeling processing, the label value is an integer, and the range of each label value is limited to less than 10.

Images