Customer list allocation method, device, computer equipment and storage medium

Abstract

The embodiments of the present application belong to the fields of artificial intelligence and fintech, and are applied to the field of allocating customers to salespersons. It involves a method, device, computer equipment and storage medium for allocating customer lists, including obtaining the historical transaction data from a preset database, parsing the historical transaction data to obtain customer information and salesperson information, then constructing a bipartite graph between customers and salespersons, constructing a business type order matrix according to the bipartite graph, constructing a customer list allocation model according to the business type order matrix and a preset prediction iteration algorithm, directly using the customer list allocation model when there is new business, automatically allocating customer lists to salespersons, and performing incremental model updates, realizing intelligent and automated prediction using artificial intelligence, and realizing that the customer lists are handed over to more suitable salespersons for contact to ensure a relatively high completion rate for different business types.

Description

Technical Field

[0001] The present application relates to the technical fields of big data and fintech, and particularly to a method, device, computer device and storage medium for allocating customer lists. Background Art

[0002] In the large market environment, how to maximize the company's business revenue remains a common concern for all companies. Different from general company businesses, taking insurance companies as an example, insurance businesses rely more on manual policy issuance. That is, the sales level of salespersons and the quality of customers themselves largely determine the success or failure of insurance policies. Against this background, insurance companies need to hand over customer lists to more suitable salespersons for contact to ensure a high completion rate.

[0003] Taking insurance business as an example, the types of insurance business mainly include commercial insurance business, compulsory insurance business, health insurance business, accident insurance business, etc. How to hand over customer lists to more suitable salespersons for contact to ensure a high completion rate for different business types has become a technical problem urgently to be solved in the current insurance industry. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to propose a method, device, computer device and storage medium for allocating customer lists to achieve handing over customer lists to more suitable salespersons for contact to ensure a high completion rate for different business types.

[0005] To solve the above technical problems, the embodiments of the present application provide a method for allocating customer lists, which adopts the following technical solutions:

[0006] A method for allocating customer lists includes the following steps:

[0007] Read the business database, and search for historical transaction data of different business types of the company in the business database according to the business identifier;

[0008] Parse the historical transaction data, and extract customer information and salesperson information from the parsed content corresponding to the historical transaction data;

[0009] Construct a bipartite graph according to the customer information and the salesperson information;

[0010] Construct a business type order matrix according to the bipartite graph;

[0011] Construct a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm;

[0012] Receive a customer list allocation request, parse the allocation request, and obtain the request content. Among them, the request content includes the business type corresponding to the customers to be recommended for allocation and the customer information in the customer list.

[0013] Based on the business type, the customer information in the customer list, and the customer list allocation model, obtain the customer recommendation allocation result.

[0014] Further, the customer information includes a customer number, and the salesperson information includes the corresponding salesperson number when a business deal is closed. The step of extracting customer information and salesperson information from the corresponding parsed content of the historical transaction data specifically includes:

[0015] Traverse the parsed content to obtain the traversal result, and obtain all the customer numbers in the parsed content according to the traversal result.

[0016] Use the customer number as the retrieval field and the preset different business types as the restriction fields to find the corresponding salesperson numbers when all the customers in the parsed content close deals based on different business types.

[0017] Further, the step of constructing a bipartite graph according to the customer information and the salesperson information specifically includes:

[0018] Use all the obtained customer numbers as the elements in the first subset to construct the first subset.

[0019] Use the salesperson numbers as the elements in the second subset to construct the second subset.

[0020] Through a preset display interface, display the elements in the first subset and the elements in the second subset separately according to the differences in the corresponding sets.

[0021] According to the corresponding salesperson numbers when all the customers close deals based on different business types, obtain the deal closing relationships corresponding to different business types between the elements in the first subset and the elements in the second subset.

[0022] According to the deal closing relationships corresponding to different business types between the elements in the first subset and the elements in the second subset, on the display interface, perform a connection process on the column values in the display column corresponding to the first subset and the column values in the display column corresponding to the second subset.

[0023] Obtain the interface display diagram after the connection process, and thus complete the construction of the bipartite graph.

[0024] Further, the step of constructing a business type deal matrix according to the bipartite graph specifically includes:

[0025] Determine the number of column values in the display columns corresponding to the first subset by traversing, denoted as m;

[0026] Determine the number of column values in the display columns corresponding to the second subset by traversing, denoted as n;

[0027] Using the value corresponding to A (i,j) as the elements in the matrix, construct a business type order matrix of m×n, where i is the column value in the display columns corresponding to the first subset, and j is the column value in the display columns corresponding to the second subset;

[0028] The step of using the value corresponding to A (i,j) as the elements in the matrix to construct a business type order matrix of m×n specifically includes:

[0029] Based on the bipartite graph, identify whether there is a connection between the column value corresponding to i and the column value corresponding to j;

[0030] If there is a connection, the value corresponding to A (i,j) is 1, that is, the element in the matrix corresponding to A (i,j) is 1;

[0031] If there is no connection, the value corresponding to A (i,j) is 0, that is, the element in the matrix corresponding to A (i,j) is 0.

[0032] Further, the step of constructing a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm specifically includes:

[0033] Based on the business type order matrix, when the value of A (i,j) corresponding to each salesman is 1, screen out all customer numbers corresponding to the salesman number, and construct a set of customer numbers corresponding to the salesman number, denoted as in(j) using in(j);

[0034] Based on the prediction iteration algorithm: Obtain the recommendation probabilities of each of the said salespersons for different business types. Among them, PR(j) represents the output of the recommendation probabilities of each salesperson for different business types, alpha represents the probability of continuing to search for the next customer corresponding to the column value of the current salesperson, i∈in(j) is used to restrict that the next customer searched for starting from the column value corresponding to the current salesperson belongs to the customers with the customer numbers in its corresponding in(j) set, PR(i) represents the probability that the current salesperson recommended the same business type as customer number i to an uncertain new customer at the end of the previous iteration, out(i) represents the probability of selecting different salespersons starting from the column value corresponding to customer number i found by the current salesperson, that is, the out-degree of the customer, j = u means that after iteration starting from the initial salesperson u, the salesperson j selected by the customers in the set in(j) is still u, and j≠u means that after iteration starting from the initial salesperson u, the salesperson j selected by the customers in the set in(j) is not u;

[0035] Sort the recommendation probabilities of each of the said salespersons for different business types in descending order, take the descending order sorting result corresponding to each of the said salespersons as the recommendation form corresponding to the salesperson, and set an association relationship for the salesperson and the corresponding recommendation form to complete the construction of the customer list allocation model.

[0036] Further, the step of obtaining the customer recommendation allocation result based on the business type, the customer information in the customer list, and the customer list allocation model specifically includes:

[0037] Obtain the business type corresponding to the customer to be recommended and allocated and the customer information in the customer list;

[0038] Based on the business type and the recommendation form, screen out the recommendation form corresponding to the maximum value of the recommendation probability corresponding to the business type;

[0039] According to the association relationship between the recommendation form and the salespersons and the customer information, recommend and allocate customers to different salespersons to complete the customer recommendation allocation.

[0040] Further, after executing the step of obtaining the customer recommendation allocation result based on the business type, the customer information in the customer list, and the customer list allocation model, the method further includes:

[0041] Obtain the customer recommendation allocation result;

[0042] According to the customer recommendation allocation result, execute the customer list allocation model update step to perform incremental update on the customer list allocation model.

[0043] To solve the above technical problems, an embodiment of the present application further provides a customer list allocation device, which adopts the following technical solutions:

[0044] A customer list allocation device includes:

[0045] A historical transaction data acquisition module, configured to read a business database and search for historical transaction data of different business types of a company in the business database according to a business identifier;

[0046] A historical transaction data parsing module, configured to parse the historical transaction data and extract customer information and salesperson information from the corresponding parsing content of the historical transaction data;

[0047] A bipartite graph construction module, configured to construct a bipartite graph according to the customer information and the salesperson information;

[0048] A matrix construction module, configured to construct a business type order matrix according to the bipartite graph;

[0049] An allocation model construction module, configured to construct a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm;

[0050] A customer list allocation request module, configured to receive a customer list allocation request, parse the allocation request, and obtain request content, where the request content includes the business type corresponding to the customer to be recommended for allocation and the customer information in the customer list;

[0051] A customer list allocation processing module, configured to obtain a customer recommendation allocation result based on the business type, the customer information in the customer list, and the customer list allocation model.

[0052] To solve the above technical problems, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:

[0053] A computer device includes a memory and a processor. Computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, the steps of the above-mentioned customer list allocation method are implemented.

[0054] To solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:

[0055] A computer-readable storage medium has computer-readable instructions stored thereon, and when the computer-readable instructions are executed by a processor, the steps of the above-mentioned customer list allocation method are implemented.

[0056] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects:

[0057] In the customer list allocation method described in the embodiments of the present application, by reading a preset database, historical transaction data of different business types of a company is obtained according to the company identifier in the database; the historical transaction data is parsed to extract customer information and salesman information in the parsed content corresponding to the historical transaction data; a bipartite graph is constructed according to the customer information and the salesman information; a business type order matrix is constructed according to the bipartite graph; a customer list allocation model is constructed based on the business type order matrix and a preset prediction iteration algorithm; a customer list allocation request is received, the allocation request is parsed to obtain the request content; based on the request content and the customer list allocation model, customers are recommended and allocated to different salesmen. When there is a new business, the customer list allocation model is directly used to automatically allocate customer lists to salesmen, realizing intelligent and automated prediction using artificial intelligence, and ensuring that customer lists are handed over to more suitable salesmen for contact to guarantee a relatively high completion rate for different business types. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the solutions in the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1 It is an exemplary system architecture diagram to which the present application can be applied;

[0060] Figure 2 A flowchart of an embodiment of the customer list allocation method according to the present application;

[0061] Figure 3 is Figure 2 A flowchart of a specific embodiment of step 202 shown;

[0062] Figure 4 is Figure 2 A flowchart of a specific embodiment of step 203 shown;

[0063] Figure 5 is Figure 2 A schematic diagram of the result of a specific embodiment of step 203 shown;

[0064] Figure 6 is Figure 2 A schematic diagram of the result of a specific embodiment of step 204 shown;

[0065] Figure 7 is Figure 2Flowchart of a specific embodiment of step 207 shown;

[0066] Figure 8 Schematic structural diagram of an embodiment of a customer list allocation device according to the present application;

[0067] Figure 9 Schematic structural diagram of an embodiment of a computer device according to the present application. Detailed implementation manners

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0069] Referring to "embodiments" herein means that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0070] To enable those skilled in the technical field to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0071] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0072] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0073] The terminal devices 101, 102, and 103 can be various electronic devices with 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), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and so on.

[0074] The server 105 can be a server providing various services, such as a background server that supports the pages displayed on the terminal devices 101, 102, and 103.

[0075] It should be noted that the customer list allocation method provided by the embodiments of the present application is generally executed by the server / terminal device. Correspondingly, the customer list allocation device is generally set in the server / terminal device.

[0076] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in

[0077] Continuing to refer to Figure 2 , a flowchart of an embodiment of the customer list allocation method according to the present application is shown. The customer list allocation method includes the following steps:

[0078] Step 201, read the business database, and look up the historical transaction data of different business types of the company in the business database according to the business identifier, where the business database includes the types of the different business types, the business identifier, and the correspondence between the business identifier and the historical transaction data of the different business types.

[0079] In this embodiment, taking the insurance business as an example, the types of the different business types include commercial insurance business, compulsory insurance business, health insurance business, accident insurance business, and so on.

[0080] By obtaining the historical transaction data of the insurance business, it is convenient to construct an allocation model in combination with the historical transaction data of the company later, so that the allocation model can be directly used to automatically recommend the optimal salesperson for new customers or recommend new customers of the corresponding business type for the corresponding salesperson.

[0081] Step 202, parse the historical transaction data, and extract customer information and salesperson information from the parsed content corresponding to the historical transaction data.

[0082] In this embodiment, the customer information includes a customer number, and the salesperson information includes the corresponding salesperson number when a business deal is closed. The step of extracting customer information and salesperson information from the parsed content corresponding to the historical transaction data specifically includes: traversing the parsed content to obtain a traversal result, and obtaining all customer numbers in the parsed content according to the traversal result; using the customer numbers as retrieval fields and preset different business types as restriction fields, and searching for the corresponding salesperson numbers when all customers in the parsed content close deals based on different business types respectively.

[0083] Continue to refer to Figure 3 , Figure 3 Yes Figure 2 is a flowchart of a specific embodiment of step 202 shown in

[0084] Step 301: Traverse the parsed content to obtain a traversal result, and obtain all customer numbers in the parsed content according to the traversal result;

[0085] Step 302: Use the customer numbers as retrieval fields and preset different business types as restriction fields, and search for the corresponding salesperson numbers when all customers in the parsed content close deals based on different business types respectively.

[0086] By parsing the historical transaction data in the insurance business, obtaining customer numbers, using the customer numbers as retrieval fields and different business types as restriction fields, and searching for the corresponding salesperson numbers when customers close deals based on different business types respectively, so as to associate the customer numbers, business types, and salesperson numbers, and do the preliminary processing work for the construction of the bipartite graph, which is convenient for quickly constructing the bipartite graph between customers and salespersons according to the historical transaction data.

[0087] Step 203: Construct a bipartite graph according to the customer information and the salesperson information.

[0088] In this embodiment, the step of constructing a bipartite graph according to the customer information and the salesperson information specifically includes: taking all the obtained customer numbers as elements in the first subset to construct the first subset; taking the salesperson numbers as elements in the second subset to construct the second subset; through a preset display interface, displaying the elements in the first subset and the elements in the second subset separately according to the differences in the corresponding sets; obtaining the order placement relationships corresponding to different business types between the elements in the first subset and the elements in the second subset according to the salesperson numbers corresponding to all the customers when placing orders based on different business types; according to the order placement relationships corresponding to different business types between the elements in the first subset and the elements in the second subset, performing connection processing on the column values in the display column corresponding to the first subset and the column values in the display column corresponding to the second subset on the display interface; obtaining the interface display diagram after the connection processing, that is, completing the construction of the bipartite graph.

[0089] Continue to refer to Figure 4 , Figure 4 is Figure 2 a flowchart of a specific embodiment of step 203 shown in

[0090] Step 401, taking all the obtained customer numbers as elements in the first subset to construct the first subset;

[0091] Step 402, taking the salesperson numbers as elements in the second subset to construct the second subset;

[0092] Step 403, through a preset display interface, displaying the elements in the first subset and the elements in the second subset separately according to the differences in the corresponding sets;

[0093] Step 404, obtaining the order placement relationships corresponding to different business types between the elements in the first subset and the elements in the second subset according to the salesperson numbers corresponding to all the customers when placing orders based on different business types;

[0094] Step 405, according to the order placement relationships corresponding to different business types between the elements in the first subset and the elements in the second subset, performing connection processing on the column values in the display column corresponding to the first subset and the column values in the display column corresponding to the second subset on the display interface;

[0095] Step 406, obtaining the interface display diagram after the connection processing, that is, completing the construction of the bipartite graph.

[0096] Please refer to Figure 5 , Figure 5 is Figure 2Schematic diagram of the result of a specific embodiment of step 203 shown. Continuing with the above insurance business as an example, assume that in the historical transaction data, the customer numbers are 1 to 5 respectively, and the corresponding salesman numbers are 6 to 10. Assume that the salesman numbered 6 is only responsible for issuing commercial insurance policies, the salesman numbered 7 is only responsible for issuing compulsory traffic insurance policies, the salesman numbered 8 is only responsible for issuing health insurance policies, the salesman numbered 9 is responsible for issuing health insurance and accident insurance policies, and the salesman numbered 10 is responsible for issuing commercial insurance, accident insurance and health insurance policies. Customer No. 1 has completed a commercial insurance policy issued by the salesman numbered 6 and a compulsory traffic insurance policy issued by the salesman numbered 7. Customer No. 2 has completed a compulsory traffic insurance policy issued by the salesman numbered 7 and a health insurance policy issued by the salesman numbered 8. Customer No. 3 has completed commercial insurance and accident insurance policies issued by the salesman numbered 10. Customer No. 4 has completed an accident insurance policy issued by the salesman numbered 9. Customer No. 5 has completed commercial insurance, accident insurance and health insurance policies issued by the salesman numbered 10. A bipartite graph is constructed for the said customers and salesmen.

[0097] By adopting the method of bipartite graph construction, the transaction and policy issuance information between customers and salesmen is graphically represented, which can not only facilitate the intuitive review and statistics by the company's business statisticians, but also facilitate the secondary processing of data through the graph.

[0098] Step 204, construct a business type policy issuance matrix according to the said bipartite graph.

[0099] In this embodiment, the step of constructing a business type policy issuance matrix according to the said bipartite graph specifically includes: by traversing, determine the number of column values in the display column corresponding to the first subset, denoted as m; by traversing, determine the number of column values in the display column corresponding to the second subset, denoted as n; use the value corresponding to A (i,j) as the element in the matrix to construct an m×n business type policy issuance matrix, where i is the column value in the display column corresponding to the first subset and j is the column value in the display column corresponding to the second subset; the step of using the value corresponding to A (i,j) as the element in the matrix to construct an m×n business type policy issuance matrix specifically includes: based on the said bipartite graph, identify whether there is a connection between the column value corresponding to i and the column value corresponding to j; if there is a connection, then the value corresponding to A (i,j) is 1, that is, the element in the matrix corresponding to A (i,j) is 1; if there is no connection, then the value corresponding to A (i,j) is 0, that is, the element in the matrix corresponding to A (i,j) is 0.

[0100] Please refer to Figure 6 , Figure 6 which is Figure 2Schematic diagram of the result of a specific embodiment of step 204 shown above, continuing with the Figure 5 bipartite graph shown above as an example. By traversing, it can be known that the number of column values in the display columns of both the first subset and the second subset is 5. Then, a 5×5 matrix is constructed. The column values of the first subset include 1, 2, 3, 4, 5, and the column values of the second subset include 6, 7, 8, 9, 10. After matrix conversion, 25 matrix elements are generated. According to the connection relationship in the bipartite graph, the values of the 25 matrix elements are determined. If there is a connection, the corresponding value is 1; otherwise, the corresponding value is 0.

[0101] By converting the bipartite graph into a matrix, it is convenient for the computer to perform data processing according to the graphic characteristics and facilitate model construction.

[0102] Step 205, construct a customer list allocation model based on the order form matrix of the business type and a preset prediction iteration algorithm.

[0103] In this embodiment, the step of constructing a customer list allocation model based on the order form matrix of the business type and a preset prediction iteration algorithm specifically includes: based on the order form matrix of the business type, screen out all customer numbers corresponding to each salesman when the value of A (i,j) is 1, and construct a set of customer numbers corresponding to the salesman number, and use in(j) to represent the set; based on the prediction iteration algorithm: Obtain the recommendation probability of each salesman for different business types. Among them, PR(j) represents the output of the recommendation probability of each salesman for different business types, alpha represents the probability of continuing to find the next customer corresponding to the column value of the current salesman, i∈in(j) is used to limit that the next customer found starting from the column value of the current salesman belongs to the customer among the customer numbers in the corresponding in(j) set, PR(i) represents the probability that the current salesman recommended the same business type as customer number i to an uncertain new customer at the end of the previous iteration, out(i) represents the probability of selecting different salesmen starting from the column value corresponding to customer number i found by the current salesman, that is, the out-degree of the customer, j = u means that after iteration starting from the initial salesman u, the salesman j selected by the customer in the set in(j) is still u, and j≠u means that after iteration starting from the initial salesman u, the salesman j selected by the customer in the set in(j) is not u; sort the recommendation probabilities of each salesman for different business types in descending order, use the descending order sorting result corresponding to each salesman as the recommendation form of the salesman, and set an association relationship for the salesman and his corresponding recommendation form to complete the construction of the customer list allocation model.

[0104] Continuing with the above insurance business as an example, the issued order matrix corresponding to the business type is Figure 6 , and through data screening in the matrix, it can be seen that the customer number corresponding to the salesman numbered 6 is 1, that is, in(6) = {1}, and the customer numbers corresponding to the salesman numbered 7 are 1 and 2, that is, in(7) = {1, 2}. Similarly, the in(j) corresponding to the salesmen numbered 8, 9, and 10 are screened out. Assuming that the salesman numbered 6 is the initial salesman, obviously the corresponding customer number is only one, then the corresponding alpha value, that is, the probability of finding the next customer is 0. The customer number is 1. Starting from this customer to find the corresponding salesman numbers can be the salesman numbered 6 and the salesman numbered 7, that is, out(1) = 50%. Assuming that the salesman numbered 7 is the initial salesman, the first customer number he finds is 1. Obviously, the corresponding customer numbers are only two, then the corresponding alpha value, that is, the probability of finding the next customer is 50%. Assuming that the current customer he is looking for is the customer numbered 2, and there are also two salesmen corresponding to the customer numbered 2, that is, the salesman numbered 7 and the salesman numbered 8. Then, starting from the customer numbered 2 to find the corresponding salesman numbers can be the salesman numbered 6 and the salesman numbered 7, that is, out(2) = 50%. Similarly, starting from the customer numbered 3 to find the corresponding salesman number can only be 10, that is, out(3) = 100%.

[0105] Through the issued order matrix of the business type and the preset prediction iteration algorithm, obtain the recommended probabilities of each salesman for different business types, sort the recommended probabilities of each salesman for different business types in descending order, and use the descending order result corresponding to each salesman as the recommended form corresponding to the salesman. Set the association relationship for the salesman and the corresponding recommended form, and complete the construction of the customer list allocation model, which is convenient for directly making an automated recommendation to allocate customers to the salesman according to the allocation model when an old customer conducts a renewal business or a new customer conducts an insurance application business, making it more intelligent.

[0106] Step 206, receive a customer list allocation request, parse the allocation request, and obtain the request content. Among them, the request content includes the business type corresponding to the customer to be recommended and allocated and the customer information in the customer list.

[0107] Step 207, based on the business type, the customer information in the customer list, and the customer list allocation model, obtain the customer recommendation allocation result.

[0108] In this embodiment, the step of obtaining the customer recommendation allocation result based on the service type, the customer information in the customer list, and the customer list allocation model specifically includes: obtaining the service type corresponding to the customer to be recommended and allocated and the customer information in the customer list; filtering out the recommendation form corresponding to the maximum recommendation probability of the service type based on the service type and the recommendation form; and recommending and allocating customers to different salespersons according to the association relationship between the recommendation form and the salespersons and the customer information, thereby completing the customer recommendation and allocation.

[0109] Continue to refer to Figure 7 , Figure 7 Yes Figure 2 is a flowchart of a specific embodiment of step 207 shown in the figure, including the steps:

[0110] Step 701: Obtain the service type corresponding to the customer to be recommended and allocated and the customer information in the customer list;

[0111] Step 702: Filter out the recommendation form corresponding to the maximum recommendation probability of the service type based on the service type and the recommendation form;

[0112] Step 703: Recommend and allocate customers to different salespersons according to the association relationship between the recommendation form and the salespersons and the customer information, thereby completing the customer recommendation and allocation.

[0113] In this embodiment, after executing the step of obtaining the customer recommendation allocation result based on the service type, the customer information in the customer list, and the customer list allocation model, the method further includes: obtaining the customer recommendation allocation result; and according to the customer recommendation allocation result, re-executing steps 203 to 205 to perform incremental update on the customer list allocation model.

[0114] By using the request content and the customer list allocation model to recommend and allocate customers to different salespersons, and according to the recommendation and allocation result, re-executing steps 203 to 205 to perform incremental update on the customer list allocation model, it is ensured that the customer list allocation model is continuously updated, which is convenient for model reuse. Through incremental improvement, it is ensured that the business application scope of the model is becoming wider and wider.

[0115] This application reads a preset database, obtains historical transaction data of different business types of a company according to the company identifier in the database; parses the historical transaction data, and extracts customer information and salesman information in the parsed content corresponding to the historical transaction data; constructs a bipartite graph according to the customer information and the salesman information; constructs a business type order matrix according to the bipartite graph; constructs a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm; receives a customer list allocation request, parses the allocation request, and obtains the request content; based on the request content and the customer list allocation model, recommends and allocates customers to different salesmen. When there is new business, directly use the customer list allocation model to automatically allocate customer lists to salesmen, and use artificial intelligence to achieve intelligent and automated prediction, so as to ensure that the customer list is handed over to more suitable salesmen for contact to ensure a relatively high completion rate of different business types.

[0116] In the embodiment of this application, relevant data can be obtained and processed based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technology and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

[0117] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0118] In the embodiment of this application, the historical transaction data can be obtained from a preset database through big data processing technology, and then a customer list allocation prediction model can be constructed through a bipartite graph and a matrix. When there is new business, directly use the customer list allocation model to automatically allocate customer lists to salesmen, and perform incremental model updates. Using artificial intelligence realizes intelligent and automated prediction, and realizes that the customer list is handed over to more suitable salesmen for contact to ensure a relatively high completion rate of different business types.

[0119] For further reference Figure 8 As an implementation of the method shown above Figure 2 In an embodiment of a customer list allocation device provided by this application, this device embodiment corresponds to the method embodiment shown in Figure 2 This device can be specifically applied to various electronic devices.

[0120] Such as Figure 8As shown in the figure, the customer list allocation device 800 described in this embodiment includes: a historical transaction data acquisition module 801, a historical transaction data parsing module 802, a bipartite graph construction module 803, a matrix construction module 804, an allocation model construction module 805, a customer list allocation request module 806, and a customer list allocation processing module 807. Among them:

[0121] The historical transaction data acquisition module 801 is used to read the business database and find the historical transaction data of different business types of the company in the business database according to the business identifier;

[0122] The historical transaction data parsing module 802 is used to parse the historical transaction data and extract customer information and salesperson information from the corresponding parsed content of the historical transaction data;

[0123] The bipartite graph construction module 803 is used to construct a bipartite graph according to the customer information and the salesperson information;

[0124] The matrix construction module 804 is used to construct a business type order matrix according to the bipartite graph;

[0125] The allocation model construction module 805 is used to construct a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm;

[0126] The customer list allocation request module 806 is used to receive a customer list allocation request, parse the allocation request, and obtain the request content. Among them, the request content includes the business type corresponding to the customer to be recommended for allocation and the customer information in the customer list;

[0127] The customer list allocation processing module 807 is used to obtain a customer recommendation allocation result based on the business type, the customer information in the customer list, and the customer list allocation model.

[0128] This application reads a preset database, obtains historical transaction data of different business types of a company according to the company identifier in the database; parses the historical transaction data to extract customer information and salesperson information in the corresponding parsed content of the historical transaction data; constructs a bipartite graph according to the customer information and the salesperson information; constructs a business type order matrix according to the bipartite graph; constructs a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm; receives a customer list allocation request, parses the allocation request to obtain the request content; and recommends and allocates customers to different salespersons based on the request content and the customer list allocation model. When there is a new business, the customer list allocation model is directly used to automatically allocate customer lists to salespersons, realizing intelligent and automated prediction using artificial intelligence, and ensuring that the customer lists are handed over to more suitable salespersons for contact to guarantee a relatively high completion rate for different business types.

[0129] In some specific embodiments of this application, the customer list allocation device further includes an incremental update module 808. The incremental update module is used to obtain the recommended allocation result after the customer list allocation processing module performs allocation processing; and according to the recommended allocation result, sequentially enable the bipartite graph construction module, the matrix construction module, and the allocation model construction module again to perform incremental update on the customer list recommendation model.

[0130] This application performs incremental update on the customer list allocation model through the incremental update module, ensuring continuous update of the customer list allocation model, facilitating model reuse, and ensuring that the business application scope of the model becomes wider and wider through incremental improvement.

[0131] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the foregoing storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disc, a read-only memory (ROM), etc., or a random access memory (RAM), etc.

[0132] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0133] To solve the above technical problems, an embodiment of the present application further provides a computer device. Specifically, please refer to Figure 9 , Figure 9 which is the basic structural block diagram of the computer device of this embodiment.

[0134] The computer device 9 includes a memory 9a, a processor 9b, and a network interface 9c that are communicatively connected to each other through a system bus. It should be noted that only the computer device 9 with components 9a - 9c is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art of this technology can understand that a computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0135] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can perform human-computer interaction with users through means such as a keyboard, a mouse, a remote control, a touchpad, or a voice control device.

[0136] The memory 9a includes at least one type of readable storage medium, which includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 9a may be an internal storage unit of the computer device 9, such as the hard disk or memory of the computer device 9. In other embodiments, the memory 9a may also be an external storage device of the computer device 9, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc. equipped on the computer device 9. Of course, the memory 9a may also include both the internal storage unit and the external storage device of the computer device 9. In this embodiment, the memory 9a is generally used to store the operating system and various application software installed on the computer device 9, such as computer-readable instructions of the customer list distribution method, etc. In addition, the memory 9a may also be used to temporarily store various data that have been output or will be output.

[0137] In some embodiments, the processor 9b may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 9b is generally used to control the overall operation of the computer device 9. In this embodiment, the processor 9b is used to run the computer-readable instructions stored in the memory 9a or process data, such as running the computer-readable instructions of the customer list distribution method.

[0138] The network interface 9c may include a wireless network interface or a wired network interface, and the network interface 9c is generally used to establish a communication connection between the computer device 9 and other electronic devices.

[0139] The computer device proposed in this embodiment belongs to the field of artificial intelligence technology. In this application, by reading a preset database, historical transaction data of different business types of a company is obtained according to the company identifier in the database; the historical transaction data is parsed to extract customer information and salesman information in the parsed content corresponding to the historical transaction data; a bipartite graph is constructed according to the customer information and the salesman information; a business type order matrix is constructed according to the bipartite graph; based on the business type order matrix and a preset prediction iteration algorithm, a customer list allocation model is constructed; a customer list allocation request is received, the allocation request is parsed to obtain the request content; based on the request content and the customer list allocation model, customers are recommended and allocated to different salesmen. When there is a new business, the customer list allocation model is directly used to automatically allocate customer lists to salesmen, and artificial intelligence is used to achieve intelligent and automatic prediction, so as to ensure that the customer list is handed over to more suitable salesmen for contact to ensure a higher completion rate for different business types.

[0140] This application also provides another implementation manner, that is, to provide a computer-readable storage medium storing computer-readable instructions that can be executed by a processor to cause the processor to execute the steps of the customer list allocation method as described above.

[0141] The computer-readable storage medium proposed in this embodiment belongs to the field of artificial intelligence technology. In this application, by reading a preset database, historical transaction data of different business types of a company is obtained according to the company identifier in the database; the historical transaction data is parsed to extract customer information and salesman information in the parsed content corresponding to the historical transaction data; a bipartite graph is constructed according to the customer information and the salesman information; a business type order matrix is constructed according to the bipartite graph; based on the business type order matrix and a preset prediction iteration algorithm, a customer list allocation model is constructed; a customer list allocation request is received, the allocation request is parsed to obtain the request content; based on the request content and the customer list allocation model, customers are recommended and allocated to different salesmen. When there is a new business, the customer list allocation model is directly used to automatically allocate customer lists to salesmen, and artificial intelligence is used to achieve intelligent and automatic prediction, so as to ensure that the customer list is handed over to more suitable salesmen for contact to ensure a higher completion rate for different business types.

[0142] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0143] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The accompanying drawings show the preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields shall be equally within the scope of the patent protection of the present application.

Claims

1. A method for allocating customer lists, characterized in that, Including the following steps: Read the business database, and search for the historical transaction data of different business types of the company in the business database according to the business identifier; Parse the historical transaction data, and extract customer information and salesman information from the corresponding parsed content of the historical transaction data; Construct a bipartite graph according to the customer information and the salesman information. Among them, the customer information includes a customer number, and the salesman information includes the corresponding salesman number when the business transaction is completed. Specifically, the step of constructing a bipartite graph according to the customer information and the salesman information includes: Use all the obtained customer numbers as elements in the first subset to construct the first subset; Use the salesman numbers as elements in the second subset to construct the second subset; Through a preset display interface, display the elements in the first subset and the elements in the second subset separately according to the differences in the corresponding sets; According to the salesman numbers corresponding to all customers when they complete transactions for different business types, obtain the transaction completion relationships corresponding to different business types between the elements in the first subset and the elements in the second subset; According to the transaction completion relationships corresponding to different business types between the elements in the first subset and the elements in the second subset, on the display interface, perform connection processing on the column values in the display column corresponding to the first subset and the column values in the display column corresponding to the second subset; Obtain the interface display diagram after the connection processing, that is, complete the construction of the bipartite graph; Construct a business type order matrix according to the bipartite graph. Among them, the step of constructing a business type order matrix according to the bipartite graph specifically includes: Determine the number of column values in the display columns corresponding to the first subset by traversing, denoted as ; Determine the number of column values in the display columns corresponding to the second subset by traversing, denoted as ; Using the corresponding numerical values as elements in the matrix, construct the business type policy issuance matrix, where is the column value in the display column corresponding to the first subset, is the column value in the display column corresponding to the second subset; The step of using the corresponding numerical value as an element in the matrix to construct the underwriting matrix for the business type includes specifically: Based on the bipartite graph, identify the corresponding column values and whether there is a connection between the corresponding column values; If there is a connection, then the corresponding value is 1, that is, the element in the corresponding matrix is 1; If there is no connection, then the corresponding value is 0, that is, the element in the corresponding matrix is 0; Construct a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm; Receive a customer list allocation request, parse the allocation request, and obtain the request content. Among them, the request content includes the business type corresponding to the customer to be recommended and allocated and the customer information in the customer list; Based on the business type, the customer information in the customer list, and the customer list allocation model, obtain the customer recommendation and allocation result.

2. The customer list allocation method according to claim 1, characterized in that The step of extracting customer information and salesman information from the corresponding parsed content of the historical transaction data specifically includes: Traverse the parsed content to obtain a traversal result, and obtain all customer numbers in the parsed content according to the traversal result; Use the customer numbers as search fields and the preset different business types as restriction fields to search for the corresponding salesman numbers when all customers in the parsed content complete transactions for different business types.

3. The customer list allocation method according to claim 1, characterized in that The step of constructing a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm specifically includes: Based on the order-issuing matrix for the business type, filter out all customer numbers corresponding to each salesman when the value of is 1, and construct a set of customer numbers corresponding to the salesman number, using to represent the set; When it is 1, all customer numbers corresponding to the salesman number are filtered out, and a set of customer numbers corresponding to the salesman number is constructed, using to represent the set; Based on the above prediction iteration algorithm: , obtain the recommendation probability of each salesperson for different business types, where represents outputting the recommendation probability of each salesperson for different business types, represents the probability of continuing to search for the next customer corresponding to the column value of the current salesperson, is used to limit that the next customer searched starting from the column value corresponding to the current salesperson belongs to the customers with the customer numbers in the corresponding set, represents the probability that the current salesperson recommends the same business type as the customer number to an uncertain new customer when the previous iteration is completed, represents the probability of respectively selecting different salespersons starting from the column value corresponding to the customer number searched by the current salesperson, that is, the out-degree of the customer, represents that after iteration starting from the initial salesperson , the salesperson selected by the customers in the set is still , represents that after iteration starting from the initial salesperson , the salesperson selected by the customers in the set is not ;​ Sort the recommendation probabilities of each salesman for different business types in descending order, use the descending order sorting result corresponding to each salesman as the recommendation form corresponding to the salesman, and set an association relationship for the salesman and the corresponding recommendation form to complete the construction of the customer list allocation model.

4. The customer list allocation method according to claim 3, characterized in that, The step of obtaining the customer recommendation and allocation result based on the business type, the customer information in the customer list, and the customer list allocation model specifically includes: Obtain the business types corresponding to the customers to be recommended and allocated, and the customer information in the customer list; Based on the business type and the recommendation form, filter out the recommendation form corresponding to the maximum recommendation probability for the business type; According to the association relationship between the recommendation form and the salespersons, and the customer information, recommend and allocate customers to different salespersons to complete the customer recommendation and allocation.

5. The customer list allocation method according to claim 1, wherein After performing the step of obtaining the customer recommendation and allocation result based on the business type, the customer information in the customer list, and the customer list allocation model, the method further includes: Obtain the customer recommendation and allocation result; According to the customer recommendation and allocation result, perform the customer list allocation model update step to incrementally update the customer list allocation model.

6. A customer list allocation device, characterized in that, The customer list allocation device is used to implement the steps of the customer list allocation method according to any one of claims 1 to 5. The customer list allocation device includes: A historical transaction data acquisition module, configured to read the business database and find the historical transaction data of different business types of the company in the business database according to the business identifier; A historical transaction data parsing module, configured to parse the historical transaction data and extract customer information and salesperson information from the corresponding parsed content of the historical transaction data; A bipartite graph construction module, configured to construct a bipartite graph according to the customer information and the salesperson information; A matrix construction module, configured to construct a business type order matrix according to the bipartite graph; An allocation model construction module, configured to construct a customer list allocation model based on the business type order matrix and a preset prediction iteration algorithm; A customer list allocation request module, configured to receive a customer list allocation request, parse the allocation request, and obtain the request content, where the request content includes the business type corresponding to the customers to be recommended and allocated and the customer information in the customer list; A customer list allocation processing module, configured to obtain a customer recommendation and allocation result based on the business type, the customer information in the customer list, and the customer list allocation model.

7. A computer device, including a memory and a processor, where computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, the steps of the customer list allocation method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that, Computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by the processor, the steps of the customer list allocation method according to any one of claims 1 to 5 are implemented.

Images