Agent classification method, device, electronic device and storage medium

Abstract

The present application relates to the field of artificial intelligence technology, and discloses a method, device, electronic device, and storage medium for classifying agents, wherein the classification method includes: obtaining basic information of each agent among all agents; performing score conversion on the basic information of each agent to obtain a feature score corresponding to each agent; performing at least one clustering process on all agents based on the feature score corresponding to each agent to obtain a target processing result; generating a visual clustering diagram based on the target processing result; determining the business needs of the institutions to which all agents belong, and determining the number of categories of agents required by the institution based on the business needs; determining a classification method for agents based on the number of categories and the visual clustering diagram, and classifying all agents based on the classification method. In this way, agents with similar abilities can be allocated together as much as possible, and the allocation result can maximize the satisfaction of the institution's business needs.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device and storage medium for classifying seat personnel. Background Art

[0002] With the rapid development of the national economy, support from relevant policies, and a growing awareness of insurance among the public, domestic insurance demand is experiencing a significant growth trend. For example, on September 3, 2020, the China Banking and Insurance Regulatory Commission (CBIRC) issued comprehensive reform guidelines for auto insurance. These guidelines significantly increased the liability limits for compulsory motor vehicle insurance and lowered the floating rate coefficient to 50%. This will intensify competition among insurance companies, leading to different insurers developing their own strategies for reducing compulsory motor vehicle insurance premiums to enhance their market competitiveness. Furthermore, due to the increased liability limits, insurance companies' profits from compulsory motor vehicle insurance will further decline, making premium income from commercial insurance even more crucial to maintaining overall profitability.

[0003] Therefore, for major insurance companies, how to effectively develop business and retain customers has become a crucial metric. Currently, business development and customer retention rely primarily on communication between agents and customers. However, the current allocation of agents is completely random, resulting in some agents' abilities not being fully utilized, which in turn impacts insurance business development and customer retention. Therefore, there is an urgent need for a method to categorize agents based on their work ability, so that insurance agents can be appropriately assigned to groups that meet their respective ability levels. Summary of the Invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the embodiments of the present application provide a seat classification method, device, electronic device and storage medium, which can allocate seats with similar capabilities as much as possible, and the allocation results can maximize the satisfaction of the organization's business needs.

[0005] In a first aspect, an embodiment of the present application provides a method for classifying seat personnel, comprising:

[0006] Get the basic information of each agent among all agents;

[0007] Convert the basic information of each agent into a score to obtain the corresponding feature score of each agent;

[0008] According to the feature score corresponding to each agent, all agents are clustered at least once to obtain the target processing result;

[0009] Generate a visual clustering diagram based on the target processing results;

[0010] Determine the business needs of the organizations to which all agents belong, and determine the types and number of agents required by the organization based on the business needs;

[0011] Based on the number of categories and the visual cluster diagram, determine the classification method for the agents and classify all agents according to the classification method.

[0012] In a second aspect, an embodiment of the present application provides a seat classification device, comprising:

[0013] The collection module is used to obtain the basic information of each agent among all agents;

[0014] The conversion module is used to convert the basic information of each agent into a score to obtain the corresponding feature score of each agent;

[0015] The clustering module is used to perform at least one clustering process on all agents based on the feature score corresponding to each agent, obtain the target processing result, and generate a visual clustering diagram based on the target processing result;

[0016] The processing module is used to determine the business needs of the organizations to which all agents belong, and determine the number of categories of agents required by the organization based on the business needs, and determine the classification method of the agents based on the number of categories and the visual cluster diagram, and classify all agents according to the classification method.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, the processor being connected to a memory, the memory being used to store computer programs, and the processor being used to execute the computer programs stored in the memory, so that the electronic device performs the method of the first aspect.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a computer to execute the method of the first aspect.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and is computer-operable to enable the computer to execute the method of the first aspect.

[0020] The implementation of the present application has the following beneficial effects:

[0021] In the embodiments of the present application, the basic information of the agents is scored and used as the corresponding characteristic score of the agent. The distance between each agent is calculated based on the characteristic score of each agent, and the agents are clustered at least once. Then, a visual cluster diagram is generated based on the clustering results of multiple clusterings. The required number of agent categories is then determined based on the organization's business needs. Finally, based on the number of categories and the visual cluster diagram, a method for classifying the agents is determined, and all agents are classified according to the classification method. This allows agents with similar capabilities to be allocated together as much as possible, and the allocation results can maximize the satisfaction of the organization's business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A schematic diagram of the hardware structure of a seat classification device provided in an embodiment of the present application;

[0024] Figure 2 A flowchart of a method for classifying seat personnel provided in an embodiment of the present application;

[0025] Figure 3 A flowchart of a method for performing multiple clustering processes on all agents based on the feature scores corresponding to each agent to obtain a target processing result, provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of a visual cluster diagram provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of moving a line in a visual cluster diagram provided by an embodiment of the present application;

[0028] Figure 6 A block diagram of the functional modules of a seat classification device provided in an embodiment of the present application;

[0029] Figure 7 A schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] The terms "first," "second," "third," and "fourth," etc., in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, rather than to describe a specific order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0032] Reference herein to an "embodiment" means that a particular feature, result, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0033] First, see Figure 1 , Figure 1 The hardware structure diagram of a seat classification device provided in an embodiment of the present application is as follows: The seat classification device 100 includes at least one processor 101 , a communication line 102 , a memory 103 and at least one communication interface 104 .

[0034] In this embodiment, the processor 101 can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0035] The communication link 102 may include a path for transmitting information between the above components.

[0036] The communication interface 104 may be any transceiver-like device (eg, antenna, etc.) for communicating with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (WLAN), etc.

[0037] The memory 103 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0038] In this embodiment, the memory 103 can exist independently and be connected to the processor 101 via the communication line 102. The memory 103 can also be integrated with the processor 101. The memory 103 provided in the embodiments of the present application can generally be non-volatile. Among them, the memory 103 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 101. The processor 101 is used to execute the computer-executable instructions stored in the memory 103, thereby implementing the methods provided in the following embodiments of the present application.

[0039] In an optional implementation, the computer-executable instructions may also be referred to as application code, which is not specifically limited in this application.

[0040] In an optional embodiment, the processor 101 may include one or more CPUs, such as Figure 1 CPU0 and CPU1 in.

[0041] In an optional embodiment, the seat classification device 100 may include multiple processors, such as Figure 11 and 107. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0042] In an optional embodiment, if the agent classification device 100 is a server, for example, it can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The agent classification device 100 can also include an output device 105 and an input device 106. The output device 105 communicates with the processor 101 and can display information in various ways. For example, the output device 105 can be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 106 communicates with the processor 101 and can receive user input in various ways. For example, the input device 106 can be a mouse, keyboard, touch screen device, or sensor device.

[0043] The above-mentioned seat classification device 100 can be a general device or a dedicated device. The embodiment of the present application does not limit the type of the seat classification device 100.

[0044] Secondly, it should be noted that the embodiments disclosed in this application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0045] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0046] The following describes the seat classification method disclosed in this application:

[0047] See Figure 2 , Figure 2 This is a flow chart of a method for classifying seat personnel provided in an embodiment of the present application. The method for classifying seat personnel includes the following steps:

[0048] 201: Get the basic information of each agent among all agents.

[0049] In this embodiment, each agent's basic information can include at least one sub-item, such as: agent's age, gender, place of origin, and educational background, which represent identity; length of service, company length of service, total hours worked in the previous year, total bonuses in the previous year, and total overtime hours in the previous year, which represent work experience; and sub-items representing competence, such as the number of clients in the previous year, number of policies underwritten in the previous year, total premiums in the previous year, number of complaints received in the previous year, average consecutive policy issuance in the previous year, and policy issuance volume by various channels in the previous year. These sub-items can be obtained by querying the database of the agent's institution.

[0050] 202: Convert the basic information of each agent into a score to obtain a feature score corresponding to each agent.

[0051] In this embodiment, since each agent's basic information includes at least one sub-information, and these sub-information items are numerous and complex, and the data formats are also different, before analyzing this data, it is possible to convert the data into scores and unify the data format to simplify the subsequent analysis.

[0052] For example, by determining the value range corresponding to each sub-information in the at least one sub-information, each sub-information can be converted into a score based on the value range corresponding to each sub-information, thereby obtaining at least one score corresponding to the at least one sub-information. Finally, the at least one score is used as the feature score corresponding to each agent.

[0053] Specifically, for each sub-information, a mapping table corresponding to the sub-information can be pre-set, and the mapping table records the scores corresponding to different value ranges of the sub-information. Therefore, by determining the value range corresponding to each sub-information, the score corresponding to the sub-information can be determined through the mapping relationship in the mapping table. For example, for length of service, it can be set to 1 point for 1 to 3 years of length of service, 2 points for 4 to 6 years of length of service, 3 points for 7 to 9 years of length of service, and so on. When an agent's length of service is 4 years, its value falls within the value range of 4 to 6 years, so the score converted from the agent's length of service is 2. Therefore, after each agent's basic information, including at least one sub-information, is converted into scores one by one, these branches can be sorted according to the order of the preset sub-information to obtain a score sequence as the characteristic score of the agent.

[0054] 203: Perform at least one clustering process on all agents based on the feature score corresponding to each agent to obtain a target processing result.

[0055] In this embodiment, a method is provided for performing at least one clustering process on all agents according to the feature score corresponding to each agent to obtain a target processing result, such as Figure 3 As shown, the method includes:

[0056] 301: Determine a starting data group A for the i-th clustering process, calculate the distance between data B and data C in the starting data group A, and obtain n distances.

[0057] In this embodiment, data B and data C are any two different data in the initial data set. This can be understood as calculating the distance value between any two different data in the initial data set A. For example, when the initial data set A includes three data, data 1, data 2, and data 3, the distance between data 1 and data 2, the distance between data 2 and data 3, and the distance between data 1 and data 3 can be calculated respectively.

[0058] At the same time, in this embodiment, i is an integer greater than or equal to 1, and when i = 1, the initial data set A is a data set consisting of the feature scores corresponding to all agents. That is, when i = 1, each data in the initial data set A is the feature score of each agent. In this case, each data in the initial data set A can be understood as a single data, that is, each data only includes the feature score of one agent. To this end, this embodiment provides a method for calculating the distance between data B and data C in the initial data set A when i = 1. Specifically, the method is as follows:

[0059] First, determine the data B[x1,x2,x3,……,x s The average value of the elements in And the data C[y1,y2,y3,……,y e The average value of the elements in Then according to data B, the average value of the elements in data B Data C and the average of the elements in data C Determine the distance h between data B and data C AB , where data B and the average value of the elements in data B are Data C, the average value of the elements in data C and the distance h between data B and data C AB Satisfy formula ①:

[0060]

[0061] Among them, x j is the jth element in data B; y j is the j-th element in data C.

[0062] Furthermore, when i > 1, due to the clustering process, all data in the initial data set A are clustered data, i.e., composite data. Simply put, each data point in the initial data set A now includes the feature scores of at least two agents. Therefore, this embodiment also provides a method for calculating the distance between data B and data C in the initial data set A when i > 1. Specifically, the method is as follows:

[0063] First, determine the sub-data B included in data B k , and data C includes sub-data C f Then, according to the sub-data B included in data B k , and data C includes sub-data C f , determine the distance q between data B and data C AB , where data B includes sub-data B k , data C includes sub-data C f and the distance q between data B and data C AB Satisfy formula ②:

[0064]

[0065] in, is the kth sub-data B in data B k and the fth bit sub-data C in data C f The distance between them can be calculated by the method in formula ①; K is the number of sub-data included in data B, and F is the number of sub-data included in data C.

[0066] For example, assuming that data B includes sub-data of two agents, P and O, and data C includes sub-data of two agents, V and U, then the distance q between data B and data C is AB Satisfy formula ③:

[0067]

[0068] Among them, h PV The distance between seats P and V can be calculated using formula ①; h OV Indicates the distance between seat O and seat V; h PU Indicates the distance between seat P and seat U; h OU Indicates the distance between seats O and U.

[0069] 302: Cluster the data in the initial data group A according to n distances to obtain a clustered data group D, and add the processing result of this clustering process to the processing result of the i-1th clustering process to obtain the final processing result of the i-th clustering process.

[0070] In this embodiment, each cluster of data in cluster data set D includes at least two data items, and the distance between any two different data items in the at least two data items is less than or equal to a first threshold. Specifically, the actual value of the first threshold varies with each clustering. For example, it may gradually increase based on the number of clusterings. The specific value may be pre-set by the agent's organization.

[0071] At the same time, by adding the current processing result to the previous processing result to generate the corresponding final result, each final processing result can include the current processing result and the results of multiple processing times before this one. Based on this, when i = 1, the processing result of the i-1th clustering process can be an empty result. For example, the final processing result of the first clustering process is: G1 = g1 + 0, where g1 is the processing result of the first clustering process; the final processing result of the second clustering process is: G2 = g2 + G1 = g2 + g1, where g2 is the processing result of the second clustering process; the final processing result of the third clustering process is: G3 = g3 + G2 = g3 + g2 + g1, where g3 is the processing result of the third clustering process, and so on.

[0072] 303: When the number of clustered data in the clustered data group D is less than or equal to the second threshold, the final processing result of the i-th clustering processing is used as the target processing result.

[0073] In this embodiment, the second threshold value may be the minimum number of categories in the clustering result obtained by clustering. For example, when the second threshold value is 1, it means that clustering is stopped when all seats are clustered into one category after multiple clustering.

[0074] 304: When the number of clustered data in the clustered data group D is greater than the second threshold, the clustered data group D is used as the starting data group for the (i+1)th clustering process and the (i+1)th clustering process is performed until the target processing result is obtained after multiple clustering processes are performed.

[0075] 204: Generate a visual clustering diagram based on the target processing results.

[0076] In this embodiment, since the target processing result can include the clustering mode and clustering result of each clustering process in the multiple clustering processes, each agent can be used as the horizontal axis and the distance as the vertical axis. Based on the target processing result, the agents that are clustered together in each clustering process are connected, and the vertical axis value of the connection line is set to the distance between the two connected agents, thereby generating the following: Figure 4 The visual cluster diagram shown.

[0077] 205: Determine the business needs of the organizations to which all agents belong, and determine the types and number of agents required by the organization based on the business needs.

[0078] In this embodiment, the organization's services can be categorized by business type to obtain at least one business group. The characteristics of the customer groups within each of the at least one business group are then determined. Based on these characteristics, the customer groups within each business group are divided to determine the number of customer groups within each business group. Finally, based on the number of customer groups within each business group, the number of agent categories required by the organization is determined based on business needs, i.e., the number of agent categories into which the agents need to be divided.

[0079] Specifically, for organization L, it includes Business 1, Business 2, Business 3, and Business 4. Based on the business characteristics of each business, these four businesses are divided into two categories: Category 1 [Business 1, Business 4] and Category 2 [Business 2, Business 3]. Furthermore, by analyzing the business characteristics of Category 1 businesses, Category 1 customers are divided into three categories. Similarly, by analyzing the business characteristics of Category 2 businesses, Category 2 customers are divided into two categories. Therefore, the organization's customers can be divided into five categories, and therefore the number of agent categories required is five.

[0080] 206: Determine the classification method for the agents based on the number of categories and the visual cluster diagram, and classify all agents according to the classification method.

[0081] In this embodiment, after determining the number of categories required by the organization, a line parallel to the horizontal axis can be drawn on the visual cluster diagram, and the line is moved upward from the horizontal axis of the visual cluster diagram to determine the number of intersections between the line and the visual cluster diagram, such as Figure 5 When the number of intersections equals the required number of categories, the classification result at the position corresponding to the horizontal line is used as the final classification method, and all seats are classified accordingly.

[0082] In summary, the agent classification method provided by the present invention uses a scoring system to convert the agent's basic information into a score, which serves as the corresponding agent's characteristic score. The distance between each agent is calculated based on the characteristic score, and the agents are clustered at least once. Then, a visual cluster diagram is generated based on the clustering results of multiple clusterings. The required number of agent categories is then determined based on the organization's business needs. Finally, based on the number of categories and the visual cluster diagram, a method for classifying the agents is determined, and all agents are classified according to the classification method. This allows agents with similar capabilities to be grouped together as closely as possible, and the resulting allocations can maximize the satisfaction of the organization's business needs.

[0083] See Figure 6 , Figure 6 This is a functional module block diagram of a seat classification device provided by the embodiment of this application. Figure 6 As shown, the customer real-time conversation switching device 600 includes:

[0084] The collection module 601 is used to obtain basic information of each agent among all agents;

[0085] The conversion module 602 is used to convert the basic information of each agent into a score to obtain a feature score corresponding to each agent;

[0086] Clustering module 603, configured to perform at least one clustering process on all agents based on the feature score corresponding to each agent, obtain a target processing result, and generate a visual clustering diagram based on the target processing result;

[0087] Processing module 604 is used to determine the business needs of the organizations to which all agents belong, and determine the number of categories of agents required by the organization based on the business needs, and determine the classification method of the agents based on the number of categories and the visual cluster diagram, and classify all agents according to the classification method.

[0088] In the embodiment of the present invention, in performing at least one clustering process on all agents based on the feature score corresponding to each agent to obtain the target processing result, the clustering module 603 is specifically configured to:

[0089] Determine the starting data set A for the i-th clustering process, calculate the distance between data B and data C in the starting data set A, and obtain n distances, where data B and data C are any two different data in the starting data set, i is an integer greater than or equal to 1, and when i=1, the starting data set A is a data set consisting of the feature scores corresponding to all agents;

[0090] According to n distances, the data in the initial data group A are clustered to obtain a clustered data group D, and the processing result of this clustering processing is added to the processing result of the i-1th clustering processing to obtain the final processing result of the i-th clustering processing, wherein each cluster data in the clustered data group D includes at least two data, and the distance between any two different data in the at least two data is less than or equal to the first threshold. When i=1, the processing result of the i-1th clustering processing is an empty result;

[0091] When the number of clustered data in the clustered data group D is less than or equal to the second threshold, the final processing result of the i-th clustering processing is used as the target processing result;

[0092] When the number of clustered data in clustered data group D is greater than the second threshold, clustered data group D is used as the starting data group for the i+1th clustering process and clustered until the target processing result is obtained after multiple clustering processes.

[0093] In an embodiment of the present invention, when i=1, in calculating the distance between data B and data C in the initial data group A, the clustering module 603 is specifically configured to:

[0094] Determine the mean of the elements in data B and the average value of the elements in data C

[0095] According to data B, the average value of the elements in data B Data C and the average of the elements in data C Determine the distance h between data B and data C AB , where data B and the average value of the elements in data B are Data C, the average value of the elements in data C and the distance h between data B and data C AB Satisfy formula ④:

[0096]

[0097] Among them, x j is the jth element in data B, y jis the j-th element in data C.

[0098] In an embodiment of the present invention, when i>1, in calculating the distance between data B and data C in the starting data group A, the clustering module 603 is specifically configured to:

[0099] Determine sub-data B included in data B k , and data C includes sub-data C f ;

[0100] According to the sub-data B included in data B k , and data C includes sub-data C f , determine the distance q between data B and data C AB , where data B includes sub-data B k , data C includes sub-data C f and the distance q between data B and data C AB Satisfy formula ⑤:

[0101]

[0102] in, is the kth sub-data B in data B k and the fth bit sub-data C in data C f K is the number of sub-data included in data B, and F is the number of sub-data included in data C.

[0103] In the embodiment of the present invention, in terms of converting the basic information of each agent into a score to obtain the feature score corresponding to each agent, the conversion module 602 is specifically configured to:

[0104] The basic information of each agent includes at least one sub-information;

[0105] Determine a value range corresponding to each sub-information in the at least one sub-information;

[0106] Convert each sub-information into a score according to a value range corresponding to each sub-information to obtain at least one score, wherein the at least one score corresponds one-to-one to the at least one sub-information;

[0107] At least one score is used as a feature score corresponding to each agent.

[0108] In an embodiment of the present invention, in determining the business needs of the organizations to which all agents belong and determining the number of agent categories required by the organizations based on the business needs, the processing module 604 is specifically configured to:

[0109] Classifying the businesses included in the organization according to business types to obtain at least one business group;

[0110] determining characteristics of the customer base of each of the at least one business group;

[0111] Divide the customer groups of each business group according to their characteristics and determine the number of customer groups for each business group;

[0112] Based on the number of customer groups in each business group, determine the business needs and the number of categories of agents the organization needs.

[0113] See Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in the embodiment of this application. Figure 7 As shown, electronic device 700 includes transceiver 701, processor 702 and memory 703. They are connected via bus 704. Memory 703 is used to store computer programs and data, and can transmit data stored in memory 703 to processor 702.

[0114] The processor 702 is configured to read the computer program in the memory 703 and perform the following operations:

[0115] Get the basic information of each agent among all agents;

[0116] Convert the basic information of each agent into a score to obtain the corresponding feature score of each agent;

[0117] According to the feature score corresponding to each agent, all agents are clustered at least once to obtain the target processing result;

[0118] Generate a visual clustering diagram based on the target processing results;

[0119] Determine the business needs of the organizations to which all agents belong, and determine the types and number of agents required by the organization based on the business needs;

[0120] Based on the number of categories and the visual cluster diagram, determine the classification method for the agents and classify all agents according to the classification method.

[0121] In an embodiment of the present invention, in performing at least one clustering process on all agents based on the feature score corresponding to each agent to obtain a target processing result, the processor 702 is specifically configured to perform the following operations:

[0122] Determine the starting data set A for the i-th clustering process, calculate the distance between data B and data C in the starting data set A, and obtain n distances, where data B and data C are any two different data in the starting data set, i is an integer greater than or equal to 1, and when i=1, the starting data set A is a data set consisting of the feature scores corresponding to all agents;

[0123] According to n distances, the data in the initial data group A are clustered to obtain a clustered data group D, and the processing result of this clustering processing is added to the processing result of the i-1th clustering processing to obtain the final processing result of the i-th clustering processing, wherein each cluster data in the clustered data group D includes at least two data, and the distance between any two different data in the at least two data is less than or equal to the first threshold. When i=1, the processing result of the i-1th clustering processing is an empty result;

[0124] When the number of clustered data in the clustered data group D is less than or equal to the second threshold, the final processing result of the i-th clustering processing is used as the target processing result;

[0125] When the number of clustered data in clustered data group D is greater than the second threshold, clustered data group D is used as the starting data group for the i+1th clustering process and clustered until the target processing result is obtained after multiple clustering processes.

[0126] In an embodiment of the present invention, when i=1, in calculating the distance between data B and data C in the starting data group A, the processor 702 is specifically configured to perform the following operations:

[0127] Determine the mean of the elements in data B and the average value of the elements in data C

[0128] According to data B, the average value of the elements in data B Data C and the average of the elements in data C Determine the distance h between data B and data C AB , where data B and the average value of the elements in data B are Data C, the average value of the elements in data C and the distance h between data B and data C AB Satisfy formula ⑥:

[0129]

[0130] Among them, x j is the jth element in data B, y j is the j-th element in data C.

[0131] In an embodiment of the present invention, when i>1, in calculating the distance between data B and data C in the starting data group A, the processor 702 is specifically configured to perform the following operations:

[0132] Determine sub-data B included in data B k , and data C includes sub-data C f ;

[0133] According to the sub-data B included in data B k , and data C includes sub-data C f , determine the distance q between data B and data C AB , where data B includes sub-data B k , data C includes sub-data C f and the distance q between data B and data C AB Satisfy formula ⑦:

[0134]

[0135] in, is the kth sub-data B in data B k and the fth bit sub-data C in data C f K is the number of sub-data included in data B, and F is the number of sub-data included in data C.

[0136] In the embodiment of the present invention, in terms of converting the basic information of each agent into a score to obtain a feature score corresponding to each agent, the processor 702 is specifically configured to perform the following operations:

[0137] The basic information of each agent includes at least one sub-information;

[0138] Determine a value range corresponding to each sub-information in the at least one sub-information;

[0139] Convert each sub-information into a score according to a value range corresponding to each sub-information to obtain at least one score, wherein the at least one score corresponds one-to-one to the at least one sub-information;

[0140] At least one score is used as a feature score corresponding to each agent.

[0141] In an embodiment of the present invention, in determining the business requirements of the organizations to which all agents belong and determining the number of agent categories required by the organizations based on the business requirements, the processor 702 is specifically configured to perform the following operations:

[0142] Classifying the businesses included in the organization according to business types to obtain at least one business group;

[0143] determining characteristics of the customer base of each of the at least one business group;

[0144] Divide the customer groups of each business group according to their characteristics and determine the number of customer groups for each business group;

[0145] Based on the number of customer groups in each business group, determine the business needs and the number of categories of agents the organization needs.

[0146] It should be understood that the seat classification device in this application may include smartphones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptop computers, mobile Internet devices (MIDs), robots, or wearable devices. The above-mentioned seat classification devices are merely examples, not exhaustive, and include but are not limited to the above-mentioned seat classification devices. In actual applications, the above-mentioned seat classification devices may also include: smart vehicle terminals, computer equipment, etc.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by combining software with a hardware platform. Based on this understanding, all or part of the contribution of the technical solution of the present invention to the background art can be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention or certain parts of the embodiments.

[0148] Therefore, embodiments of the present application further provide a computer-readable storage medium storing a computer program, which is executed by a processor to implement some or all of the steps of any of the agent classification methods described in the above method embodiments. For example, the storage medium may include a hard disk, a floppy disk, an optical disk, a magnetic tape, a magnetic disk, a USB flash drive, a flash memory, or the like.

[0149] An embodiment of the present application further provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the agent classification methods described in the above method embodiments.

[0150] It should be noted that for the aforementioned method implementations, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required for this application.

[0151] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0153] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0154] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0155] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0156] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0157] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for classifying seat personnel, characterized in that: The method comprises: Obtaining basic information of each agent among all agents; the basic information of each agent includes at least one sub-information; The basic information of each agent, including at least one sub-information, is converted into a score one by one, and the converted scores are sorted according to a preset order of the sub-information to obtain a score sequence as the feature score corresponding to each agent; Performing at least one clustering process on all the agents based on the feature scores corresponding to each agent to obtain a target processing result; the target processing result includes a clustering method and a clustering result of each clustering process in the multiple clustering processes; Generate a visual cluster diagram based on the target processing result; wherein, each agent is used as the horizontal axis and the distance is used as the vertical axis, and the agents clustered together in each clustering process are connected by the target processing result, and the vertical axis value of the connection line is set to the distance between the two connected agents, thereby generating the visual cluster diagram; Determine the business needs of the organizations to which all the agents belong, and determine the types and quantities of agents required by the organizations based on the business needs; A classification method for the agents is determined based on the number of categories and the visual cluster diagram, and all agents are classified according to the classification method.

2. The method according to claim 1, characterized in that The step of performing at least one clustering process on all the agents based on the feature score corresponding to each agent to obtain a target processing result includes: Determine a starting data group A for the i-th clustering process, calculate the distance between data B and data C in the starting data group A, and obtain n distances, where the data B and the data C are any two different data in the starting data group, i is an integer greater than or equal to 1, and when i=1, the starting data group A is a data group consisting of the feature scores corresponding to all the agents; Clustering the data in the initial data group A according to the n distances to obtain a clustered data group D, and adding the processing result of this clustering processing to the processing result of the i-1th clustering processing to obtain the final processing result of the i-th clustering processing, wherein each cluster data in the clustered data group D includes at least two data, and the distance between any two different data in the at least two data is less than or equal to a first threshold, and when i=1, the processing result of the i-1th clustering processing is an empty result; When the number of clustered data in the clustered data group D is less than or equal to a second threshold, the final processing result of the i-th clustering processing is used as the target processing result; When the number of clustered data in the clustered data group D is greater than the second threshold, the clustered data group D is used as the starting data group for the i+1th clustering process and the i+1th clustering process is performed until the target processing result is obtained after multiple clustering processes.

3. The method according to claim 2, characterized in that When i=1, the calculating the distance between data B and data C in the starting data group A includes: Determine the average value of the elements in the data B and the average value of the elements in the data C According to the data B, the average value of the elements in the data B The data C and the average value of the elements in the data C Determine the distance h between the data B and the data C AB , wherein the data B, the average value of the elements in the data B The data C, the average value of the elements in the data C and the distance h between the data B and the data C AB Satisfies the following formula: Among them, x j is the jth element in data B, y j is the j-th element in data C.

4. The method according to claim 2 or 3, characterized in that When i>1, calculating the distance between data B and data C in the starting data group A includes: Determine the sub-data B included in the data B k , and the data C includes sub-data C f ; According to the sub-data B included in the data B k , and the data C includes sub-data C f , determine the distance q between the data B and the data C AB , wherein the data B includes sub-data B k , the data C includes sub-data C f and the distance q between the data B and the data C AB Satisfies the following formula: Among them, h BkCf is the kth sub-data B in data B k and the fth bit sub-data C in data C f K is the number of sub-data included in data B, and F is the number of sub-data included in data C.

5. The method according to claim 1, characterized in that Determining a value range corresponding to each item of sub-information in the at least one item of sub-information; Each item of sub-information is converted into a score according to a value range corresponding to each item of sub-information to obtain at least one score, wherein the at least one score corresponds one-to-one to the at least one item of sub-information.

6. The method according to claim 1, characterized in that Determining the business needs of the organizations to which all the agents belong, and determining the number and type of agents required by the organization based on the business needs, includes: Classifying the businesses included in the organization according to business types to obtain at least one business group; determining characteristics of a customer group of each business group in the at least one business group; Dividing the customer groups of each business group according to the characteristics of the customer groups of each business group, and determining the number of customer groups of each business group; The business needs are determined based on the number of customer groups in each business group to determine the number of categories of agents required by the organization.

7. A seat personnel classification device, characterized in that: The device comprises: A collection module, configured to obtain basic information of each of all agents; the basic information of each agent includes at least one sub-information; a conversion module, configured to convert the basic information of each agent, including at least one sub-information, into a score, and sort the converted scores according to a preset order of the sub-information to obtain a score sequence as a feature score corresponding to each agent; A clustering module is configured to perform at least one clustering process on all agents based on the feature scores corresponding to each agent, to obtain a target processing result, wherein the target processing result includes the clustering method and clustering result of each clustering process in the multiple clustering processes; and to generate a visual clustering diagram based on the target processing result; wherein each agent is used as the horizontal axis and the distance is used as the vertical axis, and the agents clustered together in each clustering process are connected by the target processing result, and the vertical axis value of the connected line is set to the distance between the two connected agents, thereby generating the visual clustering diagram; A processing module is used to determine the business needs of the organizations to which all the agents belong, and determine the number of categories of agents required by the organization based on the business needs, and determine the classification method of the agents based on the number of categories and the visual cluster diagram, and classify all the agents according to the classification method.

8. The device according to claim 7, characterized in that In the aspect of performing at least one clustering process on all the agents according to the feature score corresponding to each agent to obtain the target processing result, the clustering module is specifically configured to: Determine a starting data group A for the i-th clustering process, calculate the distance between data B and data C in the starting data group A, and obtain n distances, where the data B and the data C are any two different data in the starting data group, i is an integer greater than or equal to 1, and when i=1, the starting data group A is a data group consisting of the feature scores corresponding to all the agents; Clustering the data in the initial data group A according to the n distances to obtain a clustered data group D, and adding the processing result of this clustering processing to the processing result of the i-1th clustering processing to obtain the final processing result of the i-th clustering processing, wherein each cluster data in the clustered data group D includes at least two data, and the distance between any two different data in the at least two data is less than or equal to a first threshold, and when i=1, the processing result of the i-1th clustering processing is an empty result; When the number of clustered data in the clustered data group D is less than or equal to a second threshold, the final processing result of the i-th clustering processing is used as the target processing result; When the number of clustered data in the clustered data group D is greater than the second threshold, the clustered data group D is used as the starting data group for the i+1th clustering process and the i+1th clustering process is performed until the target processing result is obtained after multiple clustering processes.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the computer program is configured to be executed by the processor to perform the steps in any one of the methods of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

Images