Seat recommendation method, apparatus, device, and storage medium

Abstract

The application relates to the field of intelligent recommendation, and is used for recommending a seat to a user to improve the efficiency and accuracy of a recommendation process. Specifically, a seat recommendation method is provided. The method comprises the following steps: receiving a service request sent by a terminal device of a target user, obtaining user information of the target user in response to the service request; obtaining historical user information in a first preset time period and obtaining seat information of a seat; generating user score data according to the user information of the target user and the historical user information, and generating seat score data according to the seat information; generating a service allocation table according to the user score data and the seat score data, wherein the service allocation table comprises a corresponding relationship between each seat and the target user; determining a target seat corresponding to the target user according to the service allocation table, and sending a service access instruction to a terminal device of the target seat, so that the target seat can access the service request of the target user.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent recommendation, and in particular to a method and device for recommending a service representative, an apparatus, and a storage medium. BACKGROUND

[0002] With the development of e-commerce, the number of user groups has become large, and the needs of user groups have become more complex. In the field of non-physical product sales, such as insurance sales, the service level of a service representative is an important factor in transaction implementation. Mismatch between the service level of a service representative and the business needs of a user is a major cause of transaction failure. However, enterprises also need to consider cost factors and cannot only pursue high-quality services. How to achieve intelligent rating matching of service levels and business needs is an important problem that enterprises need to solve. SUMMARY

[0003] The present application provides a method and device for recommending a service representative, an apparatus, and a storage medium, which are used to assign a corresponding service representative to a user, thereby improving the efficiency and accuracy of the assignment process and thus improving the success rate of transactions.

[0004] In a first aspect, the present application provides a method for recommending a service representative, which includes receiving a service request sent by a terminal device of a target user, obtaining user information of the target user in response to the service request;

[0005] obtaining historical user information in a first preset time period and obtaining service representative information of a service representative;

[0006] generating user score data according to the user information of the target user and the historical user information, and generating service representative score data according to the service representative information;

[0007] generating a service assignment table according to the user score data and the service representative score data, the service assignment table including a corresponding relationship between each service representative and the target user;

[0008] determining a target service representative corresponding to the target user according to the service assignment table, and sending a service access instruction to a terminal device of the target service representative to enable the target service representative to access the service request of the target user.

[0009] In a second aspect, the present application provides a device for recommending a service representative, which includes a service response module, an information obtaining module, a data scoring module, a result assignment module, and a communication implementation module.

[0010] The service response module is configured to receive a service request sent by a terminal device of a target user, and obtain user information of the target user in response to the service request.

[0011] An information obtaining module is configured to obtain historical user information in a first preset time period and obtain agent information of an agent;

[0012] A data scoring module is configured to generate user scoring data according to the user information of the target user and the historical user information, and generate agent scoring data according to the agent information;

[0013] A result distribution module is configured to generate a service distribution table according to the user scoring data and the agent scoring data, the service distribution table including a corresponding relationship between each agent and the target user;

[0014] A communication implementation module is configured to determine a target agent corresponding to the target user according to the service distribution table, and send a service access instruction to a terminal device of the target agent, so that the target agent can access a service request of the target user.

[0015] In a third aspect, a computer device is provided, and the computer device includes a memory and a processor;

[0016] The memory is configured to store a computer program;

[0017] The processor is configured to execute the computer program and implement any one of the agent recommendation methods provided in the embodiments of the present application when the computer program is executed.

[0018] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, which, when executed by a processor, causes the processor to implement any one of the agent recommendation methods provided in the embodiments of the present application.

[0019] The application discloses a method for recommending a seat, which comprises the following steps: receiving a service request sent by a terminal device of a target user, obtaining user information of the target user in response to the service request, obtaining historical user information in a first preset time period, and obtaining seat information of a seat; generating user score data according to the user information and the historical user information, and generating seat score data according to the seat information; generating a service allocation table according to the user score data and the seat score data, wherein the service allocation table comprises a corresponding relationship between each seat and the target user; determining a target seat corresponding to the target user according to the service allocation table, and sending a service access instruction to a terminal device of the target seat, so that the target seat can access the service request of the target user. According to the method for recommending a seat provided in the application, the target user and the seat are scored to obtain user score data and seat score data, the target seat is determined according to the user score data and the seat score data, a communication link is built between the target user and the target seat, intelligent seat recommendation is realized, the efficiency and accuracy of the seat recommendation process are improved, and the success rate of transaction is improved. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is an application scenario diagram of a method provided by an embodiment of the present application;

[0022] Figure 2 is a schematic flowchart of a method provided by an embodiment of the present application;

[0023] Figure 3 is a schematic block diagram of an apparatus provided by an embodiment of the present application;

[0024] Figure 4 is a structural schematic block diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0026] The flowcharts shown in the drawings are merely illustrative and do not necessarily include all the contents and operations / steps, nor are they necessarily executed in the order described. For example, some operations / steps can be further broken down, combined or partially merged, so the actual execution order can be changed according to actual conditions.

[0027] It should be understood that the terms used in the specification of the present application are merely for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0029] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features in the embodiments can be combined with each other without conflict.

[0030] Please refer to Figure 1 , Figure 1 An application scenario diagram of a method for recommending a seat provided by an embodiment of the present application is shown. As Figure 1 shown, the method of the present embodiment can be applied in a server, specifically in a service end of an application program for recommending a seat, which runs in a server and is used to respond to a service request initiated by a first terminal on which a corresponding application program is installed, call stored user information and seat information, and further used to recommend a seat according to the user information and the seat information, and send a generated service access instruction to a second terminal where the seat is located. The first terminal and the second terminal can be connected to the server through a wireless network for communication.

[0031] The second terminal is installed with an application program responding to the service access instruction sent by the server, and the seat gets a service access window corresponding to the service access instruction through the application program, and realizes communication with the target user through a service access label in the service window. The application program includes a user end and a service end. The user end is installed in the first terminal device and the second terminal device to provide for the target user and the seat to use. The service end is installed in the server, and the terminal device is connected to the server through network communication.

[0032] When installing the application program for recommending a seat in the terminal device of the target user, the terminal device needs to authorize the corresponding permissions. For example, the permissions to obtain basic attribute information, device number, recording, call data and network information, etc.

[0033] The server can be a stand-alone server, a server cluster, a cloud server providing cloud services, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (CDN) and basic cloud computing services such as big data and artificial intelligence platform. The terminal can be a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant and a wearable device.

[0034] It should be further noted that the embodiments of the present application can acquire and process related data based on artificial intelligence technology, such as generating a service allocation table according to user score data and agent score data through artificial intelligence. Artificial intelligence (AI) is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0035] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. Artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology and machine learning / deep learning.

[0036] Please refer to Figure 2 , Figure 2 is a schematic flowchart of a method for recommending an agent provided by the embodiments of the present application. As Figure 2 indicated, the specific steps of the method for recommending an agent provided by the embodiments of the present application include S101-S105.

[0037] S101, receiving a service request sent by a terminal device of a target user, and in response to the service request, obtaining user information of the target user.

[0038] Illustratively, the target user can be a user with transaction cooperation intention, for example, a user of insurance renewal. The target user operates on the interface of the application program installed with the agent recommendation, the terminal device generates a service request in response to the operation, and sends the service request to the server through a wireless network. The server receives the service request and obtains the user information of the target user in response to the service request.

[0039] The user information of the target user includes the user's premium amount, renewal intention amount and renewal times.

[0040] S102, acquire historical user information in a first preset time period, and acquire agent information of the agent;

[0041] For example, in order to evaluate the possibility of reaching a transaction with the target user, the historical user information in the first preset time period is needed as a reference. Since it may be affected by various factors, the first preset time is a variable value. For example, the first preset time period can be the previous month of the current time node, or the previous two months of the current time node. After acquiring the historical user information, the agent information is also retrieved from the database, including the agent list, the agent ranking and the agent classification. The agent ranking and the agent classification are obtained according to the work situation of the agent, for example, the service level and the order success rate of the agent.

[0042] By acquiring the user information, the historical user information and the agent information, the analysis information required for agent allocation is collected, which is used to match the target user with the target agent in the subsequent allocation calculation framework without manual intervention, thereby improving the processing efficiency.

[0043] S103, generate user score data according to the user information and the historical user information of the target user, and generate agent score data according to the agent information.

[0044] For example, by comparing the user information of the target user with the historical user information, the transaction probability and the intended transaction amount of the target user are obtained. According to the transaction probability and the intended transaction amount, the ranking order of the target user in the historical user can be obtained, and thus the service level required by the target user can be obtained. The ranking order of the agent can be obtained through the agent information, and thus the service level of the agent can be obtained.

[0045] In some embodiments, the ranking order is generated according to the user information and the historical user information of the target user; the first weighted value is generated according to the ranking order and the number of users in the historical user information; and the user score data is generated according to the ranking order and the first weighted value. The calculation formula for calculating the user score data is:

[0046]

[0047]

[0048] wherein, P i is the first weighted value, R is the number of users in the historical user information, i is the ranking order of the target user, C i is the user score data, median(P) is the median of the ranking order, and std(P) is the standard deviation of the ranking order.

[0049] In some embodiments, a second weighted value is obtained according to the ranking of the agents and the number of agents; and the agent score data is obtained according to the second weighted value and the number of agents. The specific formula for calculating the agent score data in this step is:

[0050]

[0051]

[0052] wherein S j is the second weighted value, T is the number of agents, j is the ranking order of the agents, S j is the user score data, median(Q) is the median of the ranking order of the agents, and std(Q) is the standard deviation of the ranking order of the agents.

[0053] In some embodiments, a rating interval corresponding to each agent is obtained according to the ranking of the agents; interval data of the rating interval is obtained, the interval data including a preset third weighted value and the number of agents in the rating interval; and the agent score data is generated according to the third weighted value and the number of agents. The specific formula for calculating the agent score data in this step is:

[0054]

[0055]

[0056] wherein G y is the agent score data, F is the number of rating intervals, y is the third weighted value, for example, y = 1, 2, 3, …, S j is the user score data, median(D) is the median of the number of agents in the rating interval of the agents, and std(D) is the standard deviation of the number of agents in the rating interval.

[0057] In some embodiments, the user score data and the agent score data need to be normalized to convert the user score data and the agent score data into data in the interval (0, 1) to improve the efficiency of calculation.

[0058] S104, generating a service allocation table according to the user score data and the agent score data, the service allocation table including the corresponding relationship between each agent and the target user.

[0059] In some embodiments, an efficiency matrix is generated according to the user score data and the agent score data; the efficiency matrix is solved based on the Hungarian algorithm to obtain an independent zero element matrix; and the service allocation table is generated according to the independent zero element matrix.

[0060] Specifically, after obtaining the unified user score data and the unified agent score data, distribution calculation is performed based on a preset capacity model, and a formula of the preset capacity model is:

[0061]

[0062] wherein Price i is a premium amount of the target user, which is obtained in the user information; X ij = 1 when the target user is not assigned to the target agent; and X ij = 0 when the target user is assigned to the target agent.

[0063] In the above capacity model, C i S j Price i may be regarded as a calculation element related to the user score data and the agent score data, therefore, an efficiency matrix is generated according to the calculation element, and an independent zero element matrix is obtained by solving the efficiency matrix through the Hungarian algorithm, and a service distribution table is generated according to the independent zero elements in the row and column set of the independent zero element matrix.

[0064] In some embodiments, the specific steps of obtaining the independent zero element matrix by solving the efficiency matrix through the Hungarian algorithm include S201-S205.

[0065] S201, row and column transformation is performed, and the value of each row in the efficiency matrix is subtracted by the minimum value in the row, and the value of each column in the efficiency matrix is subtracted by the minimum value in the column.

[0066] S202, the value in the row and column not including the value 0 is subtracted by a first preset value, and the value at the coincidence point of the row and column including the value 0 is added by the first preset value, for example, the first preset value can be 100.

[0067] S203, the non-0 value in the row and column is subtracted by a second preset value, and the second preset value is the minimum value of the non-0 value in the row and column.

[0068] S204, the non-0 value in the row and column is replaced by 0, and the value 0 in the row and column is replaced by 1, to obtain the independent zero element matrix.

[0069] The relationship of the independent zero elements in the independent zero element matrix is the corresponding relationship between each agent and the target user, and the service distribution table is generated according to the corresponding relationship.

[0070] Through the above calculation process, the user score data and the agent score data are effectively combined, and the optimal list distribution scheme is obtained, which can adapt to various user score standards and agent score standards, and improves the overall compatibility.

[0071] S105, determining a target agent corresponding to the target user according to the service distribution table, and sending a service access instruction to a terminal device of the target agent, so that the target agent can access the service request of the target user.

[0072] In some embodiments, the service access instruction is sent to the terminal device of the target agent, and the terminal device of the target agent is controlled to generate a service access window, and the service access window includes a service access label; wherein when the target agent selects the service access label through the terminal device, a communication link is generated between the terminal device of the target user and the terminal device of the target agent.

[0073] For example, the server sends a service access instruction to the terminal device of the target agent, and the terminal device generates a service access window in response to the service access instruction, the service access window includes a service access label, and the service access window is displayed on the display screen. The target agent selects the operation through the input device of the terminal device, for example, the input device is a mouse, and the terminal device initiates a communication request to the server in response to the selection operation. The server generates a communication link between the terminal device of the target user and the terminal device of the target agent in response to the communication request, so that the target user can communicate with the target agent.

[0074] In some embodiments, a first service access instruction is sent to the terminal device of the first target agent, and the terminal device of the first target agent is controlled to generate a first service access window; if the terminal device of the first target agent does not respond to the first service access window within a second preset time period, the terminal device of the first target agent is controlled to close the first service access window, and a second service access instruction is sent to the terminal device of the second target agent, and the terminal device of the first target agent is controlled to generate a second service access window.

[0075] By setting the first target agent and the second target agent, when the first target agent is busy and cannot provide services to the target user in time, the user's use experience is improved.

[0076] The agent recommendation method provided by the embodiments of the present application scores the target user and the agent to obtain user score data and agent score data, determines the target agent according to the user score data and the agent score data, and builds a communication link between the target user and the target agent, which realizes intelligent agent recommendation and improves the efficiency and accuracy of the agent recommendation process, thereby improving the success rate of transactions.

[0077] Please refer to Figure 3 , Figure 3 The embodiments of the present application also provide a schematic block diagram of an agent recommendation device, which is used to execute the aforementioned agent recommendation method. The agent recommendation device can be configured in a server or a terminal.

[0078] The server can be a stand-alone server, a server cluster, a cloud server providing cloud services, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (CDN), and basic cloud computing services such as big data and artificial intelligence platform. The terminal can be a mobile phone, a tablet computer, a notebook computer, a desktop computer, a user digital assistant, and a wearable device.

[0079] As shown in Figure 3 The agent recommendation device 300 includes a service response module 301, an information acquisition module 302, a data scoring module 303, a result allocation module 304, and a communication implementation module 305.

[0080] The service response module 301 is configured to receive a service request sent by a terminal device of a target user, and acquire user information of the target user in response to the service request.

[0081] The information acquisition module 302 is configured to acquire historical user information in a first preset time period, and acquire agent information of an agent.

[0082] The data scoring module 303 is configured to generate user scoring data according to the user information of the target user and the historical user information, and generate agent scoring data according to the agent information.

[0083] In some embodiments, the data scoring module 303 is further configured to generate a ranking order according to the user information of the target user and the historical user information, generate a first weighted value according to the ranking order and a number of users in the historical user information, and generate the user scoring data according to the ranking order and the first weighted value.

[0084] In some embodiments, the data scoring module 303 is further configured to obtain a second weighted value according to a ranking of the agent and a number of agents, and obtain the agent scoring data according to the second weighted value and the number of agents.

[0085] In some embodiments, the data scoring module 303 is further configured to obtain a corresponding rating interval of each agent according to the ranking of the agent, acquire interval data of the rating interval, the interval data including a preset third weighted value and a number of agents in the rating interval, and generate the agent scoring data according to the third weighted value and the number of agents.

[0086] The result allocation module 304 is configured to generate a service allocation table according to the user scoring data and the agent scoring data, the service allocation table including a corresponding relationship between each agent and the target user.

[0087] In some embodiments, the result distribution module 304 is further configured to generate an efficiency matrix according to the user score data and the agent score data; solve the efficiency matrix based on a Hungarian algorithm to obtain an independent zero element matrix; and generate a service distribution table according to the independent zero element matrix.

[0088] The communication implementation module 305 is configured to determine a target agent corresponding to a target user according to the service distribution table, and send a service access instruction to a terminal device of the target agent, so that the target agent can access the service request of the target user.

[0089] In some embodiments, the communication implementation module 305 is further configured to send the service access instruction to the terminal device of the target agent, control the terminal device of the target agent to generate a service access window, and the service access window includes a service access label; wherein when the target agent selects the service access label through the terminal device, a communication link is generated between the terminal device of the target user and the terminal device of the target agent.

[0090] In some embodiments, the communication implementation module 305 is further configured to send a first service access instruction to the terminal device of the first target agent, control the terminal device of the first target agent to generate a first service access window; if the terminal device of the first target agent does not respond to the first service access window within a second preset time period, control the terminal device of the first target agent to close the first service access window, and send a second service access instruction to the terminal device of the second target agent, control the terminal device of the first target agent to generate a second service access window.

[0091] It should be noted that, for the convenience and brevity of description, the specific working process of the above-described agent recommendation device and each module can refer to the corresponding process in the foregoing agent recommendation method embodiments, and will not be described herein.

[0092] It should be noted that, for the convenience and brevity of description, the specific working process of the above-described model training device and each module can refer to the corresponding process in the foregoing agent recommendation method embodiments, and will not be described herein.

[0093] The above-described agent recommendation device can be implemented in the form of a computer program, which can run on a computer device as shown in Figure 4 .

[0094] Please refer to Figure 4 , Figure 4 is a structural schematic block diagram of a computer device provided by an embodiment of the present application. The computer device can be a server or a terminal.

[0095] Refer toFigure 4 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory can include a storage medium and an internal memory.

[0096] The storage medium can store an operating system and a computer program. The computer program includes program instructions which, when executed, can cause the processor to perform any one of the agent recommendation methods provided by the embodiments of the present application.

[0097] The processor is configured to provide computing and control capabilities to support the operation of the entire computer device.

[0098] The internal memory provides an environment for the execution of the computer program in the storage medium, and the computer program, when executed by the processor, can cause the processor to perform any one of the agent recommendation methods. The storage medium can be non-volatile or volatile.

[0099] The network interface is configured to perform network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that the network interface can be implemented by a network card, a network adapter, etc. Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] It should be understood that the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0101] Exemplarily, in one embodiment, the processor is configured to run a computer program stored in the memory to implement the following steps: receiving a service request sent by a terminal device of a target user, obtaining user information of the target user in response to the service request; obtaining historical user information in a first preset time period, and obtaining agent information of an agent; generating user score data according to the user information of the target user and the historical user information, and generating agent score data according to the agent information; generating a service allocation table according to the user score data and the agent score data, the service allocation table including a corresponding relationship between each agent and the target user; determining a target agent corresponding to the target user according to the service allocation table, and sending a service access instruction to a terminal device of the target agent to enable the target agent to access the service request of the target user.

[0102] In some embodiments, when the processor is configured to send the service access instruction to the terminal device of the target agent to enable the target agent to access the service request of the target user, the processor is further configured to: send the service access instruction to the terminal device of the target agent, control the terminal device of the target agent to generate a service access window, and the service access window includes a service access label; wherein when the target agent selects the service access label through the terminal device, a communication link is generated between the terminal device of the target user and the terminal device of the target agent.

[0103] In some embodiments, the processor is further configured to: send a first service access instruction to a terminal device of a first target agent, control the terminal device of the first target agent to generate a first service access window; if the terminal device of the first target agent does not respond to the first service access window within a second preset time period, control the terminal device of the first target agent to close the first service access window, and send a second service access instruction to a terminal device of a second target agent, control the terminal device of the first target agent to generate a second service access window.

[0104] In some embodiments, when the processor is configured to generate user score data according to the user information of the target user and the historical user information, the processor is further configured to: generate a ranking order according to the user information of the target user and the historical user information; generate a first weighted value according to the ranking order and the number of users in the historical user information; and generate the user score data according to the ranking order and the first weighted value.

[0105] In some embodiments, when the processor is configured to generate agent score data according to the agent information, the processor is further configured to: obtain a second weighted value according to the agent ranking and the number of agents; and obtain the agent score data according to the second weighted value and the number of agents.

[0106] In some embodiments, the processor is further configured to: obtain a corresponding rating interval of each agent according to the agent ranking; obtain interval data of the rating interval, the interval data comprising a preset third weighting value and a number of agents in the rating interval; and generate agent score data according to the third weighting value and the number of agents.

[0107] In some embodiments, when generating the service allocation table according to the user score data and the agent score data, the processor is further configured to: generate an efficiency matrix according to the user score data and the agent score data; solve the efficiency matrix based on a Hungarian algorithm to obtain an independent zero element matrix; and generate the service allocation table according to the independent zero element matrix.

[0108] The above merely describes specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements shall be encompassed within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of agent recommendation, characterized by, The method comprises: receiving a service request sent by a terminal device of a target user, and obtaining user information of the target user in response to the service request; the user information comprises at least one of a premium amount and a renewal intention amount of the target user and a renewal frequency; obtaining historical user information in a first preset time period and obtaining agent information of an agent; generating user score data according to the user information of the target user and the historical user information, and generating agent score data according to the agent information; generating a service allocation table according to the user score data and the agent score data, the service allocation table comprising a corresponding relationship between each agent and the target user; determining a target agent corresponding to the target user according to the service allocation table, and sending a service access instruction to a terminal device of the target agent to enable the target agent to access the service request of the target user; the generating of the user score data according to the user information of the target user and the historical user information comprises: comparing the user information of the target user with the historical user information to obtain a transaction probability and an intended transaction amount of the target user; determining a ranking order of the target user among historical users according to the transaction probability and the intended transaction amount; generating a first weighted value according to the ranking order and a user quantity in the historical user information; the first weighted value comprises a reciprocal of a sum of absolute values of the ranking order and the user quantity; generating the user score data according to the ranking order and the first weighted value; the user score data comprises a ratio between a target difference value and a standard deviation of the ranking order; the target difference value comprises a difference between the first weighted value and a median of the ranking order.

2. The method of claim 1, wherein, the sending of the service access instruction to the terminal device of the target agent to enable the target agent to access the service request of the target user comprises: sending a service access instruction to the terminal device of the target agent to control the terminal device of the target agent to generate a service access window, the service access window comprising a service access label; wherein, when the target agent selects the service access label through the terminal device, a communication link is generated between the terminal device of the target user and the terminal device of the target agent.

3. The method of claim 2, wherein, the target agent comprises a first target agent and a second target agent, and the method further comprises: sending a first service access instruction to a terminal device of the first target agent to control the terminal device of the first target agent to generate a first service access window; if the terminal device of the first target agent does not respond to the first service access window within a second preset time period, controlling the terminal device of the first target agent to close the first service access window, and sending a second service access instruction to a terminal device of the second target agent to control the terminal device of the first target agent to generate a second service access window.

4. The method of claim 1, wherein, the agent information comprises an agent ranking and an agent quantity; the generating of the agent score data according to the agent information comprises: obtaining a second weighted value according to the agent ranking and the agent quantity; The agent score data is obtained according to the second weighted value and the number of agents.

5. The method of claim 4, wherein, The method further comprises: obtaining a rating interval corresponding to each agent according to the agent ranking; obtaining interval data of the rating interval, the interval data comprising a preset third weighted value and the number of agents in the rating interval; generating the agent score data according to the third weighted value and the number of agents.

6. The method of claim 1, wherein, The generation of the service allocation table according to the user score data and the agent score data comprises: generating an efficiency matrix according to the user score data and the agent score data; solving the efficiency matrix based on the Hungarian algorithm to obtain an independent zero element matrix; generating the service allocation table according to the independent zero element matrix.

7. An agent recommendation apparatus characterized by comprising: comprise: a service response module, configured to receive a service request sent by a terminal device of a target user, and obtain user information of the target user in response to the service request; the user information comprising at least one of a premium amount, a renewal intention amount and a renewal frequency of the target user; an information obtaining module, configured to obtain historical user information in a first preset time period and obtain agent information of an agent; a data scoring module, configured to generate user score data according to the user information of the target user and the historical user information, and generate agent score data according to the agent information; a result allocation module, configured to generate a service allocation table according to the user score data and the agent score data, the service allocation table comprising a corresponding relationship between each agent and the target user; a communication implementation module, configured to determine a target agent corresponding to the target user according to the service allocation table, and send a service access instruction to a terminal device of the target agent, so that the target agent can access the service request of the target user; the generation of the user score data according to the user information of the target user and the historical user information comprises: comparing the user information of the target user and the historical user information to obtain a transaction probability and an intended transaction amount of the target user; determining a ranking order of the target user among historical users according to the transaction probability and the intended transaction amount; generating a first weighted value according to the ranking order and a number of users in the historical user information; the first weighted value comprising a reciprocal of a sum of absolute values of the ranking order and the number of users; generating the user score data according to the ranking order and the first weighted value; the user score data comprising a ratio between a target difference value and a standard deviation of the ranking order; the target difference value comprising a difference between the first weighted value and a median of the ranking order.

8. A computer device, comprising: The computer device comprises a memory and a processor; the memory is configured to store a computer program; the processor is configured to execute the computer program and implement the agent recommendation method as claimed in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program causes the processor to implement the agent recommendation method as claimed in any one of claims 1 to 6 when executed by the processor.

Images