Customer resource allocation method and device, equipment and medium

Abstract

The invention relates to the field of artificial intelligence, and discloses a customer resource allocation method and device, equipment and a medium, and the method comprises the steps: carrying out the capability scoring processing of seat data through a preset scoring card model, and obtaining the capability score of each to-be-evaluated seat; according to the historical customer behavior data, performing conversion rate analysis of cross transfer protection on the customer resources to obtain corresponding customer resource scores; acquiring historical performance data of each to-be-evaluated seat to perform conversion rate analysis in a plurality of preset fields to obtain a list of fields at which each to-be-evaluated seat is good; generating a corresponding seat preference list and a customer preference list according to the ability score, the skilled field list and the customer resource score of each to-be-evaluated seat; and matching is carried out according to the seat preference list and the customer preference list, and corresponding target customer resources are allocated to each to-be-evaluated seat according to a matching result. Resource allocation is carried out after efficient and quantitative accurate matching is carried out on the seat and the customer resources, and the accuracy of resource allocation is improved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence technology and financial technology, and in particular to a customer resource allocation method, device, equipment and medium. Background Art

[0002] Reasonable allocation of customer resources is one of the keys to ensuring the efficient operation of the sales team. A reasonable customer allocation strategy can optimize the processing efficiency of customer resources and improve customer conversion rate.

[0003] However, traditional insurance sales teams do not have fixed standards in terms of personnel selection and training. In terms of team operation application, the allocation of customer resources to the sales team basically relies on the offline operations of managers. It is difficult to allocate different types of customer resources to the most suitable sales personnel, resulting in inaccurate human resource matching, which in turn reduces operational efficiency and affects customer conversion rates. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a customer resource allocation method, device, equipment and medium that can be applied to financial technology or other related fields. Its main purpose is to improve the matching degree between customer resources and sales personnel, to achieve a higher quality and more efficient customer resource allocation plan, and to improve operational efficiency.

[0005] The technical solution of the present invention is as follows:

[0006] A first aspect of the present invention provides a method for allocating customer resources, comprising:

[0007] Collect seat data of each seat to be evaluated, and perform capability scoring on the seat data using a preset scoring card model to obtain a capability score for each seat to be evaluated;

[0008] Collect historical customer behavior data, analyze the conversion rate of cross-insurance transfer of customer resources based on the historical customer behavior data, and obtain corresponding customer resource scores;

[0009] Collect historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise of each seat to be evaluated;

[0010] Generate a corresponding agent preference list and customer preference list based on the ability score, list of areas of expertise and customer resource score of each agent to be evaluated;

[0011] The seats are matched with the customer resources according to the seat preference list and the customer preference list, and corresponding target customer resources are allocated to each seat to be evaluated according to the matching result.

[0012] A second aspect of the present invention provides a client resource allocation device, comprising:

[0013] The capability scoring module is used to collect the seat data of each seat to be evaluated, and perform capability scoring processing on the seat data through a preset scoring card model to obtain the capability score of each seat to be evaluated;

[0014] A resource scoring module is used to collect historical customer behavior data, analyze the conversion rate of cross-insurance transfer of customer resources based on the historical customer behavior data, and obtain corresponding customer resource scores;

[0015] A field determination module is used to collect historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise of each seat to be evaluated;

[0016] A preference generation module, for generating a corresponding agent preference list and a customer preference list according to the ability score, the list of areas of expertise and the customer resource score of each agent to be evaluated;

[0017] The resource allocation module is used to match seats with customer resources according to the seat preference list and the customer preference list, and allocate corresponding target customer resources to each seat to be evaluated according to the matching result.

[0018] A third aspect of the present invention provides a computer device, comprising at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned client resource allocation method.

[0021] A fourth aspect of the present invention provides a non-volatile computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by one or more processors, the one or more processors can execute the above-mentioned customer resource allocation method.

[0022] Beneficial effects: The present invention discloses a customer resource allocation method, device, equipment and medium. Compared with the prior art, the embodiments of the present invention collect the seat data of each seat to be evaluated, and perform capability scoring processing on the seat data through a preset scoring card model to obtain the capability score of each seat to be evaluated; collect historical customer behavior data, and perform cross-insurance conversion rate analysis on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score; collect historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise of each seat to be evaluated; generate a corresponding seat preference list and a customer preference list based on the capability score, the list of areas of expertise and the customer resource score of each seat to be evaluated; match seats with customer resources based on the seat preference list and the customer preference list, and allocate corresponding target customer resources to each seat to be evaluated based on the matching results. Through the collection of agent data and the application of scoring card models, a quantitative assessment of agent capabilities is achieved, and an agent preference list and a customer preference list are generated by integrating the agent's capabilities and areas of expertise as well as the quality of customer resources, thereby achieving precise matching between agents and customer resources for resource allocation, improving the accuracy of customer resource allocation, and thereby improving operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the scheme in the present invention, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A schematic diagram of an application environment of the client resource allocation method provided by an embodiment of the present invention;

[0025] Figure 2 A flow chart of a method for allocating customer resources provided by an embodiment of the present invention;

[0026] Figure 3 A flow chart of step S201 in the method for allocating customer resources provided by an embodiment of the present invention;

[0027] Figure 4 A flow chart of step S202 in the method for allocating customer resources provided by an embodiment of the present invention;

[0028] Figure 5 A flow chart of step S203 in the method for allocating customer resources provided by an embodiment of the present invention;

[0029] Figure 6A flow chart of step S204 in the method for allocating customer resources provided by an embodiment of the present invention;

[0030] Figure 7 A flow chart of step S205 in the method for allocating customer resources provided by an embodiment of the present invention;

[0031] Figure 8 A schematic diagram of the functional modules of a client resource allocation device provided by an embodiment of the present invention;

[0032] Fig. 9 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail below. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. The embodiments of the present invention are described below in conjunction with the accompanying drawings.

[0034] The client resource allocation method provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment of FIG. 1 , it includes a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0035] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0036] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0037] The server 105 may be a server that provides various services, such as a background server that provides support for the content browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (for example only). The background server may analyze and process the received data such as the user request, and feed back the processing results (such as web pages, information, or data obtained or generated according to the user request) to the terminal device. The server 105 may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server 105 may also be a server for a distributed system, or a server combined with a blockchain.

[0038] It should be noted that the client resource allocation method provided in the embodiment of the present application can generally be executed by the first terminal device 101, the second terminal device 102 or the third terminal device 103. Accordingly, the client resource allocation device provided in the embodiment of the present invention can also be set in the first terminal device 101, the second terminal device 102 or the third terminal device 103. Alternatively, the client resource allocation method provided in the embodiment of the present invention can also generally be executed by the server 105. Accordingly, the client resource allocation device provided in the embodiment of the present invention can generally be set in the server 105.

[0039] It should be understood that the numbers of the above terminal devices, networks and servers are only illustrative. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0040] like Figure 2 As shown, the client resource allocation method provided by the embodiment of the present invention specifically includes the following steps:

[0041] S201: Collect seat data of each seat to be evaluated, and perform capability scoring on the seat data using a preset scoring card model to obtain a capability score for each seat to be evaluated.

[0042] In this embodiment, in order to objectively and quantitatively distinguish the capabilities of each agent to be evaluated, the agent data of each agent to be evaluated is collected for evaluation. The agent data may include data of multiple dimensions, such as the agent's call duration, number of calls, deal rate, call connection rate, problem solving rate, customer satisfaction, customer evaluation, colleague evaluation, leader evaluation, etc., and may also include relevant data extracted from unstructured data, such as the frequency of occurrence of specific keywords (such as "quick response" and "professional knowledge") in customer feedback, etc. The collected agent data is scored using a preset scoring card model. The model can quantitatively analyze the agent data from multiple indicator dimensions, and then calculate the comprehensive ability score of each agent, thereby quantitatively evaluating the work performance of the agent, which can provide objective data support for the enterprise, help the enterprise understand the advantages and disadvantages of the agent, not only provide accurate data support for resource allocation, but also facilitate the adoption of corresponding training and improvement measures to improve work efficiency.

[0043] For example, in an insurance company, the agent data such as call records, customer interaction data, and sales performance of each agent to be evaluated are collected. Using the preset scorecard model, which may include indicators such as call connection rate, problem solving rate, and customer satisfaction, these data are quantitatively analyzed to calculate the ability score of each agent. For example, if agent A answered 100 calls in a month, solved 90 problems, and achieved 85% customer satisfaction, he may get a comprehensive score of 85 points according to the scorecard model.

[0044] S202: Collect historical customer behavior data, and perform a conversion rate analysis of cross-insurance transfers on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score.

[0045] In this embodiment, different customer resources are scored by collecting historical customer behavior data from the customer resource briefing, so as to facilitate the identification of high-quality resources among customer resources. Specifically, the collected historical customer behavior data includes the type, frequency, and claim records of insurance purchased by customers. These data are used in combination with machine learning algorithms to analyze the conversion rate of cross-insurance transfers of customer resources, that is, the analysis is the conversion rate of customer behavior from one insurance product to another. By statistically evaluating customer behavior patterns, the customer's demand for different insurance products and the possibility of conversion are evaluated, thereby achieving a quantitative evaluation of different customer resources. For example, through analysis, it is found that the customer group that has purchased health insurance has a higher conversion rate to life insurance, so this type of customer resource is given a higher score, etc., which facilitates more accurate human resource matching and product promotion, and improves marketing efficiency.

[0046] S203: Collect historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise of each seat to be evaluated.

[0047] In this embodiment, for each agent to be evaluated, on the basis of a comprehensive assessment of its ability score, the conversion rate of each agent to be evaluated in multiple preset fields is further analyzed by collecting historical performance data such as sales, customer feedback, conversion rate, etc. For example, the conversion rate of each agent to be evaluated in different fields such as health insurance, life insurance, property insurance, low-priced products, medium-priced products, and high-priced products is analyzed, so as to obtain a list of areas of expertise for each agent to be evaluated. For example, the conversion rate of agent A in the field of health insurance is particularly high, indicating that he is more proficient in sales operations in this field, so it is listed as an area of ​​expertise, thereby providing more auxiliary matching information for customer resource allocation. By analyzing the conversion rates of agents in different fields, the areas of expertise of each agent can be identified, and then the work allocation of the agents can be optimized to improve efficiency and conversion rate.

[0048] S204: Generate a corresponding agent preference list and a customer preference list according to the ability score, the list of areas of expertise and the customer resource score of each agent to be evaluated.

[0049] In this embodiment, based on the previous analysis results, i.e., the ability score, list of areas of expertise, and customer resource score of each agent to be evaluated, an agent preference list is generated for each agent to be evaluated, and the agent preference list lists the customer resources that the agent most wants and is best at matching, for example, agent B is better at and has strong abilities in the field of health insurance, etc.; a customer preference list is also generated, and the customer preference list lists the agents that each customer resource most wants to match, for example, customer resources that like to buy life insurance prefer agents with strong abilities and expertise in life insurance. The generated agent preference list and customer preference list help to achieve more personalized services and improve the matching degree between agents and customer resources.

[0050] S205 , matching seats with customer resources according to the seat preference list and the customer preference list, and allocating corresponding target customer resources to each seat to be evaluated according to the matching result.

[0051] In this embodiment, seats and customer resources are matched based on the generated seat preference list and customer preference list, and corresponding target customer resources are allocated. Specific matching strategies can be, for example, to give priority to high-quality resources to seats with strong capabilities, to give priority to resources in the areas where seats are good at, etc. For example, seat C who likes to sell health insurance is matched with customer resources with a high conversion rate for health insurance, and corresponding target customer resources are allocated to seat C according to the matching results, such as customers who frequently purchase or inquire about health insurance. In this way, the ability and areas of expertise of the seat and the quality of customer resources can be comprehensively considered, and the best customer matching can be achieved according to the ability of the seat. By accurately matching seats and customer resources, the accuracy of customer resource allocation can be improved, thereby improving work efficiency.

[0052] In the above embodiment, the present invention discloses a customer resource allocation method, which collects the seat data of each seat to be evaluated, performs capability scoring processing on the seat data through a preset scoring card model, and obtains the capability score of each seat to be evaluated; collects historical customer behavior data, and performs cross-insurance conversion rate analysis on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score; collects historical performance data of each seat to be evaluated, and performs conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise for each seat to be evaluated; generates a corresponding seat preference list and a customer preference list based on the capability score, the list of areas of expertise and the customer resource score of each seat to be evaluated; matches seats with customer resources based on the seat preference list and the customer preference list, and allocates corresponding target customer resources to each seat to be evaluated based on the matching results. Through the collection of agent data and the application of scoring card models, a quantitative assessment of agent capabilities is achieved, and an agent preference list and a customer preference list are generated by integrating the agent's capabilities and areas of expertise as well as the quality of customer resources, thereby achieving precise matching between agents and customer resources for resource allocation, improving the accuracy of customer resource allocation, and thereby improving operational efficiency.

[0053] In one embodiment, Figure 3 As shown, step S201 includes:

[0054] S301, collecting seat data of each seat to be evaluated, performing feature extraction on the seat data according to preset indicators, and obtaining feature variables of each seat to be evaluated under various preset indicators, wherein the preset indicators include capability evaluation indicators and key performance indicators;

[0055] S302: binning the characteristic variables, and performing capability scoring on the variable binning results of the characteristic variables in a preset scoring card model to obtain a capability score for each seat to be evaluated.

[0056] In this embodiment, when scoring the ability of the agents, the agent data of each agent to be evaluated is first collected. Since the agent data may involve multiple types and the data volume is huge, in order to improve the matching efficiency, feature extraction is performed on all the agent data based on preset indicators, namely, ability evaluation indicators and key performance indicators. The specific ability evaluation indicators may include qualitative indicators and quantitative indicators that are highly correlated with the ability evaluation. For example, quantitative indicators may be call duration, number of calls, transaction volume, customer satisfaction score, etc., and qualitative indicators may be emotional tendencies (positive, negative) in customer feedback, colleagues' evaluation of the agent's teamwork ability, etc.; and key performance indicators may be relevant indicators extracted from unstructured data, which can be used to identify specific factors or behaviors that affect agent performance, such as the frequency of occurrence of specific keywords (such as "quick response" and "professional knowledge") in customer feedback.

[0057] According to the preset capability evaluation indicators and key performance indicators, feature extraction is performed on the agent data. For example, the preset indicators include the number of calls, call duration, customer satisfaction, number of problems solved, sales, etc., and it is extracted that agent A answered 100 calls in a month, the average call duration was 5 minutes, 85 problems were solved, the sales success rate was 20%, and the customer satisfaction score was 4.5 points. Through these preset indicators, the characteristic variables of agent A under various indicators are extracted, the performance of the agent is quantified, and accurate data support is provided for subsequent scoring and analysis.

[0058] After that, the extracted feature variables are binned. According to the preset scoring card model, the feature variables can be binned by equal frequency binning, equal width binning, or binning methods based on decision trees, so as to discretize continuous variables such as call duration, or group categorical variables such as question types. For example, call duration may be divided into three bins: "short", "medium", and "long", while question types may be divided into three bins: "simple", "medium", and "complex". Then, these binning results are scored through the scoring card model, and each bin may be assigned a score based on historical data and logistic regression analysis, such as "short" call duration may correspond to a higher score, while "long" call duration may correspond to a lower score, and so on. By dividing the feature variables into limited bins, the generalization ability of the model can be enhanced, the complexity of the features can be reduced, and thus the stability of the model in evaluating the agent's ability score can be improved.

[0059] In one embodiment, step S302 includes:

[0060] According to the preset binning strategy, the characteristic variables under each preset indicator are binned and mapped, each characteristic variable is mapped to the corresponding variable bin and the binning characteristic value is calculated;

[0061] Input the variable binning and corresponding binning feature values ​​of each feature variable into the preset scorecard model, and predict and output the transaction success probability of each feature variable;

[0062] Calibrate and transform the transaction success probability of each characteristic variable to obtain the ability score of the ability evaluation dimension and the key performance dimension;

[0063] A capability profile of each agent to be evaluated is generated based on the capability evaluation dimensions and the capability scores of the key performance dimensions, and the total capability score is obtained by weighting.

[0064] In this embodiment, the characteristic variables under the key performance indicators and capability evaluation indicators of the agents are binned and mapped according to the preset binning strategy. For example, for the characteristic variable of call duration, it can be divided into three bins of "short", "medium" and "long" according to the preset binning strategy. If the average call duration of agent A is 5 minutes, according to the binning strategy, it is classified into the "short" call duration bin, etc., and the binning characteristic values ​​of each bin are calculated at the same time, such as the weight of evidence (WOE) value. The WOE value is a statistic used to measure the difference in the distribution of good customers and bad customers in a certain bin, which can be used for subsequent capability score calculations. The variable binning of each feature variable and the corresponding binning feature value are input into the preset scorecard model, and the transaction success probability of each feature variable is predicted and output. For example, for the feature variable of agent A, the binning result of call duration "short" is input into the preset scorecard model together with the binning results of other feature variables (number of calls, transaction rate, satisfaction score, etc.). The model predicts the transaction success probability of agent A under various indicators based on historical data and logistic regression analysis. For example, the model predicts that the success probability of agent A under the call duration indicator is 0.7, the success probability of the number of calls indicator is 0.6, the success probability under the transaction rate indicator is 0.5, and the success probability under the satisfaction score indicator is 0.8 in the next assessment cycle. The scorecard model is used to predict the transaction success probability of the variable binning results, and then the potential performance of the agent is identified to quantitatively evaluate the agent's ability.

[0065] After the model predicts and outputs the probability value, it is converted into the ability score of the ability evaluation dimension and the key performance dimension through calibration conversion methods, such as linear calibration or logistic regression calibration. For example, the probability of transaction success can be converted into a standardized ability score, such as 85 points, through the calibration conversion formula. The calibration conversion ensures the consistency and comparability of the scores, so that the scores between different agents can be compared fairly, providing a basis for the subsequent construction of agent ability portraits. Corresponding to the ability evaluation indicators and key performance indicators, the ability scores of the agents in the ability evaluation dimension and the key performance dimension can be obtained. The ability portrait of the agent is generated based on the multi-dimensional scores, which helps to understand the strengths and weaknesses of the agent, and then arrange more targeted training for performance. Finally, according to the scores of these dimensions and the preset weights, the total ability score of the agent is calculated to demonstrate the comprehensive ability of the agent and achieve comprehensive and integrated customer resource allocation.

[0066] In one embodiment, Figure 4 As shown, step S202 includes:

[0067] S401, collecting historical customer behavior data within a specified time period, and extracting customer insurance transfer behavior data related to insurance transfer behavior from the historical customer behavior data;

[0068] S402, grouping customer resources, and calculating the cross-insurance conversion rate of each group of customer resources according to the customer insurance transfer behavior data;

[0069] S403: Map the cross-insurance conversion rate into a preset resource score range to obtain a customer resource score for each group of customer resources.

[0070] In this embodiment, historical customer behavior data within a specified time period is collected, including customer purchase records, claims history, customer service interaction records, etc. From these data, customer transfer behavior data related to the transfer behavior is extracted. For example, if customer A transferred from car insurance to home insurance in the past year, the data of this transfer behavior will be recorded. By collecting and extracting the transfer behavior data, the changes in the customer's insurance needs can be understood more accurately, thereby providing data support for subsequent cross-selling and product recommendations.

[0071] The collected customer insurance transfer behavior data is grouped, for example, the customer can be grouped according to characteristics such as age, gender, and insurance type. Then, based on the insurance transfer behavior data of each group of customer resources, the cross-insurance transfer conversion rate of each group is calculated. For example, if 20% of customers in a customer group of an age group have transferred insurance, then this conversion rate will be used to evaluate the insurance transfer tendency of the group, and then identify which customer groups are more likely to transfer insurance as the basis for scoring customer resources. The calculated cross-insurance transfer conversion rate is mapped to the preset resource score range to obtain the customer resource score of each group of customer resources. For example, if the conversion rate is between 10%-20%, the corresponding customer resource score may be 60-70 points; if the conversion rate is higher than 20%, the customer resource score is higher. The resource quality of different customer groups is evaluated by quantitative customer resource scoring, which more intuitively reflects the insurance transfer potential of different customer groups, thereby conducting more targeted customer management and resource allocation.

[0072] In one embodiment, Figure 5 As shown, step S203 includes:

[0073] S501, obtaining a predefined tag set, wherein the tag set includes a plurality of domain tags;

[0074] S502, collecting historical performance data of each seat to be evaluated, wherein the historical performance data includes historical transaction records in different fields;

[0075] S503. Calculate the conversion rate of each seat to be evaluated under each field label according to the historical transaction records in the different fields;

[0076] S504: Arrange the conversion rates of each agent to be evaluated under each field label, and determine the list of areas of expertise of each agent to be evaluated according to the conversion rate ranking and a preset ranking threshold.

[0077] In this embodiment, a label set is predefined, and the label set includes multiple field labels such as "health insurance", "auto insurance", "life insurance", and "property insurance". The label set can be set according to the company's product line and market segmentation to ensure that all areas of the company's business can be fully covered. After that, the historical performance data of each seat to be evaluated is collected. These data include transaction records in different fields. For example, the number of transactions of seat A in the field of "health insurance" in the past year is 200 times, and the number of transactions in the field of "auto insurance" is 60 times. Based on the historical transaction records of the seats to be evaluated in different fields, the conversion rate of each seat to be evaluated under each field label is calculated. For example, if the total number of customers contacted by seat A in the field of "health insurance" is 500, the conversion rate is 40%; the total number of customers contacted in the field of "auto insurance" is 300, and the conversion rate is 20%.

[0078] Through the conversion rate of each agent to be evaluated under each field label, the sales efficiency and effect of the agent in each field can be intuitively obtained. The conversion rate of each agent to be evaluated under each field label is ranked, and the list of areas of expertise of each agent to be evaluated is determined from the ranking and the preset ranking threshold. For example, if the preset ranking threshold is 2, the first two areas are extracted from the conversion rate ranking of each agent to be evaluated as the list of areas of expertise. For example, the conversion rates of agent A in the fields of "health insurance", "life insurance", "auto insurance" are ranked, and it is found that the conversion rate in the fields of "health insurance" and "life insurance" is higher. According to the conversion rate ranking and the preset ranking threshold, the list of areas of expertise of agent A is determined to be "health insurance" and "life insurance". By arranging the conversion rate and determining the list of areas of expertise, the expertise and potential areas of each agent can be more clearly understood, thereby better optimizing the work allocation of the agents.

[0079] In one embodiment, Figure 6 As shown, step S204 includes:

[0080] S601, calculating the matching score between each pair of agents and customer resources according to the ability score, the list of areas of expertise and the customer resource score of each agent to be evaluated;

[0081] S602: Generate an agent preference list for each agent to be evaluated and a customer preference list for each customer resource according to the ranking of the matching scores between each pair of agents and customer resources.

[0082] In this embodiment, the matching score between each pair of agents and customer resources is calculated based on the ability score of each agent to be evaluated, the list of areas of expertise, and the customer resource score. Specifically, the agent ability score Score (s i ), that is, each seat to be evaluated s i The ability score of each customer resource rj; the customer resource score Score(rj), that is, the customer resource score of each customer resource rj; the proficiency score Proficiency(s i ,r j ), that is, if the agent s i Good at handling customer resources j For each pair of agent and resource, a matching score is calculated, which reflects the expected effect of the agent in handling the resource. The specific matching score can be Match_Score(s i ,r j )=α·Score(s i )+β·Score(r j )+γ·Proficiency(si ,r j ) Among them, α, β and γ are weight parameters, representing the relative importance of the agent ability score, resource score and expertise list score respectively.

[0083] According to the sorting of the matching scores between each pair of agents and customer resources, an agent preference list for each agent to be evaluated and a customer preference list for each customer resource are generated, that is, each agent is matched with each customer resource in pairs and sorted based on the matching scores. For example, agent A may have a high matching score with multiple customer resources. By sorting, it can be determined which customer resources agent A should serve first. Generate an agent preference list for agent A, listing the most matching customer resources, and a customer preference list for customer B, listing the most matching agents. For example, agent A's agent preference list may include customer B, customer C, and customer D, while customer B's customer preference list may include agent A, agent E, and agent F. By generating agent preference lists and customer preference lists, more refined customer resource management and agent work allocation can be achieved, resource utilization efficiency can be optimized, and overall business processing efficiency and effectiveness can be improved.

[0084] In one embodiment, Figure 7 As shown, step S205 includes:

[0085] S701, initializing the seat preference list and the customer preference list, so that the seat preference list and the customer preference list are arranged in order of preference;

[0086] S702, initiating a matching request to the most preferred customer resource according to the seat preference list for each unmatched seat to be evaluated;

[0087] S703, processing the received matching request according to the preference order in the customer preference list of the most preferred customer resource and the current matching status, and accepting or rejecting the matching request;

[0088] S704: When the matching request is accepted, the most preferred customer resource is allocated as a target customer resource to the agent to be evaluated who initiated the request, and the matching status of the most preferred customer resource is updated;

[0089] S705: When the matching request is rejected, the agent to be evaluated who initiated the request continues to initiate a matching request to the next preferred customer resource, and repeats the matching request initiation and customer resource response operations until all the agents to be evaluated and customer resources are allocated.

[0090] In this embodiment, the seats and customer resources are matched by a stable matching algorithm based on the generated seat preference list and customer preference list to achieve the optimal customer resource allocation. Specifically, the seat preference list and customer preference list are initialized first, and the seat preference list and customer preference list are arranged in the order of preference. At this time, all seats and customer resources are not matched. Then, each unmatched seat makes a matching request to the most preferred unmatched customer resource according to its preference list. At this time, for the matching request received by the most preferred customer resource, if it is not currently matched, the matching request is accepted, and the most preferred customer resource is allocated as the target customer resource to the seat to be evaluated that initiated the request, and the matching status of the most preferred customer resource is updated; if it is currently matched, the currently matched seat and the seat that newly initiated the matching request can be compared, and the seat with a lower customer preference order between the two seats is rejected, and the seat with a higher customer preference order is accepted. If the current most preferred customer resource rejects the matching request, the seat to be evaluated that initiated the request continues to initiate a matching request to the next preferred customer resource, and repeats the matching request initiation and customer resource response operations until all seats and resources enter the matching state.

[0091] Assume that there are currently 3 seats to be evaluated (S1, S2, S3) and 3 customer resources (R1, R2, R3). Each seat and resource has a preference list, where:

[0092] S1 preference: R1>R2>R3;

[0093] S2 preference: R2>R3>R1;

[0094] S3 preference: R3>R1>R2;

[0095] R1 preference: S1>S2>S3;

[0096] R2 preference: S2>S1>S3;

[0097] R3 preference: S3>S1>S2

[0098] According to the above matching process, S1 proposes a match to R1, and R1 accepts (because S1 is the highest in R1's preference list); S2 proposes a match to R2, and R2 accepts (because S2 is the highest in R2's preference list); S3 proposes a match to R3, and R3 accepts (because S3 is the highest in R3's preference list). By continuously trying to match until the right customer resources are found, the ability and expertise of the agents and the quality of customer resources can be combined to achieve the optimal allocation of customer resources, ensuring that customer resources are used most effectively and improving the work efficiency and conversion rate of the entire team.

[0099] It should be noted that there is not necessarily a certain order between the above-mentioned steps. A person skilled in the art can understand, based on the description of the embodiments of the present invention, that in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, may be executed interchangeably, and so on.

[0100] Further references Figure 8 , as a response to the above Figure 2 The present invention provides an embodiment of a client resource allocation device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0101] like Figure 8 As shown, the client resource allocation device 80 described in this embodiment includes:

[0102] The capability scoring module 801 is used to collect the seat data of each seat to be evaluated, and perform capability scoring processing on the seat data through a preset scoring card model to obtain the capability score of each seat to be evaluated;

[0103] The resource scoring module 802 is used to collect historical customer behavior data, and analyze the conversion rate of cross-insurance transfer of customer resources based on the historical customer behavior data to obtain a corresponding customer resource score;

[0104] The field determination module 803 is used to collect the historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields according to the historical performance data to obtain a list of areas of expertise of each seat to be evaluated;

[0105] The preference generation module 804 is used to generate a corresponding agent preference list and a customer preference list according to the ability score, the list of areas of expertise and the customer resource score of each agent to be evaluated;

[0106] The resource allocation module 805 is used to match seats with customer resources according to the seat preference list and the customer preference list, and allocate corresponding target customer resources to each seat to be evaluated according to the matching result.

[0107] The module referred to in the present invention refers to a series of computer program instruction segments that can complete specific functions, which are more suitable for describing the customer resource allocation execution process than programs. For the specific implementation of each module, please refer to the corresponding method embodiment above, which will not be repeated here.

[0108] In one embodiment, the capability scoring module 801 includes:

[0109] A collection and extraction unit, used to collect seat data of each seat to be evaluated, perform feature extraction on the seat data according to preset indicators, and obtain feature variables of each seat to be evaluated under various preset indicators, wherein the preset indicators include capability evaluation indicators and key performance indicators;

[0110] The capability scoring unit is used to perform variable binning processing on the characteristic variables, and perform capability scoring processing on the variable binning results of the characteristic variables in a preset scoring card model to obtain the capability score of each seat to be evaluated.

[0111] In one embodiment, the capability scoring unit comprises:

[0112] The binning unit is used to bin and map the characteristic variables under each preset indicator according to the preset binning strategy, map each characteristic variable to the corresponding variable bin and calculate the binning characteristic value;

[0113] The prediction unit is used to input the variable binning of each feature variable and the corresponding binning feature value into a preset scoring card model, and predict and output the transaction success probability of each feature variable;

[0114] The conversion unit is used to calibrate and convert the transaction success probability of each characteristic variable to obtain the capability evaluation dimension and the capability score of the key performance dimension;

[0115] The scoring unit is used to generate a capability profile of each seat to be evaluated based on the capability evaluation dimension and the capability score of the key performance dimension and to obtain a total capability score by weighting.

[0116] In one embodiment, the resource scoring module 802 includes:

[0117] A behavior data collection unit, used to collect historical customer behavior data within a specified time period, and extract customer insurance transfer behavior data related to insurance transfer behavior from the historical customer behavior data;

[0118] A grouping calculation unit, used to group customer resources and calculate the cross-insurance conversion rate of each group of customer resources according to the customer insurance transfer behavior data;

[0119] A mapping conversion unit is used to map the cross-insurance conversion rate into a preset resource score range to obtain a customer resource score for each group of customer resources.

[0120] In one embodiment, the domain determination module 803 includes:

[0121] A tag acquisition unit, used to acquire a predefined tag set, wherein the tag set includes a plurality of domain tags;

[0122] A performance data collection unit, used to collect historical performance data of each seat to be evaluated, wherein the historical performance data includes historical transaction records in different fields;

[0123] A label conversion rate unit, used to calculate the conversion rate of each seat to be evaluated under each field label according to the historical transaction records in the different fields;

[0124] The ranking determination unit is used to rank the seats to be evaluated according to their conversion rates under various field labels, and determine the list of areas of expertise of each seat to be evaluated according to the conversion rate ranking and a preset ranking threshold.

[0125] In one embodiment, the preference generation module 804 includes:

[0126] A matching calculation unit, used to calculate a matching score between each pair of agents and customer resources according to the ability score, the list of areas of expertise of each agent to be evaluated, and the customer resource score;

[0127] The preference generating unit is used to generate an agent preference list of each agent to be evaluated and a customer preference list of each customer resource according to the ranking of the matching scores between each pair of agents and customer resources.

[0128] In one embodiment, the resource allocation module 805 includes:

[0129] An initialization unit, used to initialize the seat preference list and the customer preference list, so that the seat preference list and the customer preference list are arranged in order of preference;

[0130] A request initiating unit, configured to initiate a matching request to the most preferred customer resource according to the agent preference list for each unmatched agent to be evaluated;

[0131] a request response unit, configured to process the received matching request and accept or reject the matching request according to the preference order in the customer preference list of the most preferred customer resource and the current matching status;

[0132] a matching processing unit, configured to, when accepting the matching request, allocate the most preferred customer resource as a target customer resource to the agent to be evaluated who initiated the request, and update the matching status of the most preferred customer resource;

[0133] The iterative unit is used for, when the matching request is rejected, the agent to be evaluated who initiated the request continues to initiate the matching request to the next preferred customer resource, and repeats the matching request initiation and customer resource response operations until all the agents to be evaluated and customer resources are allocated.

[0134] In the above embodiment, the present invention discloses a customer resource allocation device, which collects the seat data of each seat to be evaluated, performs capability scoring processing on the seat data through a preset scoring card model, and obtains the capability score of each seat to be evaluated; collects historical customer behavior data, and performs cross-insurance conversion rate analysis on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score; collects historical performance data of each seat to be evaluated, and performs conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise for each seat to be evaluated; generates a corresponding seat preference list and a customer preference list based on the capability score, the list of areas of expertise and the customer resource score of each seat to be evaluated; matches seats with customer resources based on the seat preference list and the customer preference list, and allocates corresponding target customer resources to each seat to be evaluated based on the matching results. Through the collection of agent data and the application of scoring card models, a quantitative assessment of agent capabilities is achieved, and an agent preference list and a customer preference list are generated by integrating the agent's capabilities and areas of expertise as well as the quality of customer resources, thereby achieving precise matching between agents and customer resources for resource allocation, improving the accuracy of customer resource allocation, and thereby improving operational efficiency.

[0135] Another embodiment of the present invention provides a computer device, such as Fig. 9 As shown, the computer device 90 includes:

[0136] One or more processors 901 and memory 902, Fig. 9 A processor 901 is used as an example for description. The processor 901 and the memory 902 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0137] Processor 901 is used to complete various control logics of computer device 90, which can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component or any combination of these components. In addition, processor 901 can also be any traditional processor, microprocessor or state machine. Processor 901 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP and / or any other such configuration.

[0138] The memory 902 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions corresponding to the customer resource allocation method in the embodiment of the present invention. The processor 901 executes various functional applications and data processing of the computer device 90 by running the non-volatile software programs, instructions and units stored in the memory 902, that is, implements the customer resource allocation method in the above method embodiment.

[0139] The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the computer device 90, etc. In addition, the memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 902 may optionally include a memory remotely arranged relative to the processor 901, and these remote memories may be connected to the computer device 90 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. One or more units are stored in the memory 902, and when executed by one or more processors 901, the steps of the customer resource allocation method in any of the above-mentioned method embodiments are executed.

[0140] In the above embodiment, the present invention discloses a computer device, which collects the seat data of each seat to be evaluated, performs capability scoring processing on the seat data through a preset scoring card model, and obtains the capability score of each seat to be evaluated; collects historical customer behavior data, and performs cross-insurance conversion rate analysis on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score; collects historical performance data of each seat to be evaluated, and performs conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise for each seat to be evaluated; generates a corresponding seat preference list and customer preference list based on the capability score, the list of areas of expertise and the customer resource score of each seat to be evaluated; matches seats with customer resources based on the seat preference list and the customer preference list, and allocates corresponding target customer resources to each seat to be evaluated based on the matching results. Through the collection of agent data and the application of scoring card models, a quantitative assessment of agent capabilities is achieved, and an agent preference list and a customer preference list are generated by integrating the agent's capabilities and areas of expertise as well as the quality of customer resources, thereby achieving precise matching between agents and customer resources for resource allocation, improving the accuracy of customer resource allocation, and thereby improving operational efficiency.

[0141] An embodiment of the present invention provides a non-volatile computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by one or more processors, the steps of the customer resource allocation method in any of the above method embodiments are executed.

[0142] In the above embodiment, the present invention discloses a non-volatile computer-readable storage medium, which collects the seat data of each seat to be evaluated, performs capability scoring processing on the seat data through a preset scoring card model, and obtains the capability score of each seat to be evaluated; collects historical customer behavior data, and performs cross-insurance conversion rate analysis on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score; collects historical performance data of each seat to be evaluated, and performs conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise for each seat to be evaluated; generates a corresponding seat preference list and a customer preference list based on the capability score, the list of areas of expertise and the customer resource score of each seat to be evaluated; matches seats with customer resources based on the seat preference list and the customer preference list, and allocates corresponding target customer resources to each seat to be evaluated based on the matching results. Through the collection of agent data and the application of scoring card models, a quantitative assessment of agent capabilities is achieved, and an agent preference list and a customer preference list are generated by integrating the agent's capabilities and areas of expertise as well as the quality of customer resources, thereby achieving precise matching between agents and customer resources for resource allocation, improving the accuracy of customer resource allocation, and thereby improving operational efficiency.

[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0144] The present invention can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present invention can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0145] In summary, the present invention discloses a method, device, equipment and medium for allocating customer resources, the method comprising: collecting the seat data of each seat to be evaluated, performing capability scoring processing on the seat data through a preset scoring card model, and obtaining a capability score for each seat to be evaluated; collecting historical customer behavior data, and performing a conversion rate analysis of cross-transfer of customer resources based on the historical customer behavior data to obtain a corresponding customer resource score; collecting historical performance data of each seat to be evaluated, and performing a conversion rate analysis of each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise for each seat to be evaluated; generating a corresponding seat preference list and a customer preference list based on the capability score, the list of areas of expertise and the customer resource score of each seat to be evaluated; matching seats with customer resources based on the seat preference list and the customer preference list, and allocating corresponding target customer resources to each seat to be evaluated based on the matching results. Through the collection of agent data and the application of scoring card models, a quantitative assessment of agent capabilities is achieved, and an agent preference list and a customer preference list are generated by integrating the agent's capabilities and areas of expertise as well as the quality of customer resources, thereby achieving precise matching between agents and customer resources for resource allocation, improving the accuracy of customer resource allocation, and thereby improving operational efficiency.

[0146] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium, and the computer program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, a floppy disk, a flash memory, an optical storage device, etc.

[0147] It should be noted that if any software tools or components other than those of the Company appear in the embodiments of the present application, they are merely used for illustration and do not represent actual use. It should be understood that the application of the present invention is not limited to the above examples, and that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes shall fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for allocating customer resources, characterized in that: include: Collect seat data of each seat to be evaluated, and perform capability scoring on the seat data using a preset scoring card model to obtain a capability score for each seat to be evaluated; Collect historical customer behavior data, analyze the conversion rate of cross-insurance transfer of customer resources based on the historical customer behavior data, and obtain corresponding customer resource scores; Collect historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise of each seat to be evaluated; Generate a corresponding agent preference list and customer preference list based on the ability score, list of areas of expertise and customer resource score of each agent to be evaluated; The seats are matched with the customer resources according to the seat preference list and the customer preference list, and corresponding target customer resources are allocated to each seat to be evaluated according to the matching result.

2. The method for allocating customer resources according to claim 1, characterized in that: The collecting of seat data of each seat to be evaluated and performing capability scoring processing on the seat data through a preset scoring card model to obtain the capability score of each seat to be evaluated includes: Collect seat data of each seat to be evaluated, perform feature extraction on the seat data according to preset indicators, and obtain feature variables of each seat to be evaluated under various preset indicators, wherein the preset indicators include capability evaluation indicators and key performance indicators; The characteristic variables are binned, and the variable binning results of the characteristic variables are binned in a preset scoring card model to perform capability scoring, so as to obtain the capability score of each seat to be evaluated.

3. The method for allocating customer resources according to claim 2, characterized in that: The variable binning process is performed on the feature variables, and the ability scoring process is performed on the variable binning results of the feature variables in a preset scoring card model to obtain the ability score of each seat to be evaluated, including: According to the preset binning strategy, the characteristic variables under each preset indicator are binned and mapped, each characteristic variable is mapped to the corresponding variable bin and the binning characteristic value is calculated; Input the variable binning and corresponding binning feature values ​​of each feature variable into the preset scorecard model, and predict and output the transaction success probability of each feature variable; Calibrate and transform the transaction success probability of each characteristic variable to obtain the ability score of the ability evaluation dimension and the key performance dimension; A capability profile of each agent to be evaluated is generated based on the capability evaluation dimensions and the capability scores of the key performance dimensions, and the total capability score is obtained by weighting.

4. The method for allocating customer resources according to claim 1, characterized in that: The collecting of historical customer behavior data, and performing a cross-insurance conversion rate analysis on customer resources based on the historical customer behavior data to obtain a corresponding customer resource score, include: Collecting historical customer behavior data within a specified time period, and extracting customer insurance transfer behavior data related to insurance transfer behavior from the historical customer behavior data; Grouping customer resources, and calculating the cross-insurance conversion rate of each group of customer resources based on the customer insurance transfer behavior data; The cross-insurance conversion rate is mapped into a preset resource score range to obtain a customer resource score for each group of customer resources.

5. The method for allocating customer resources according to claim 1, characterized in that: The historical performance data of each seat to be evaluated is collected, and the conversion rate of each seat to be evaluated is analyzed in multiple preset fields according to the historical performance data to obtain a list of areas of expertise of each seat to be evaluated, including: Obtain a predefined tag set, wherein the tag set includes a plurality of domain tags; Collect historical performance data of each agent to be evaluated, including historical transaction records in different fields; Based on the historical transaction records in the different fields, calculate the conversion rate of each agent to be evaluated under each field label; The seats to be evaluated are arranged according to their conversion rates under various field labels, and the list of areas of expertise of each seat to be evaluated is determined based on the conversion rate ranking and the preset ranking threshold.

6. The method for allocating customer resources according to claim 1, characterized in that: The corresponding agent preference list and customer preference list are generated according to the ability score, the list of areas of expertise and the customer resource score of each agent to be evaluated, including: Calculate the matching score between each pair of agents and customer resources based on the ability score, list of areas of expertise and the customer resource score of each agent to be evaluated; According to the ranking of the matching scores between each pair of agents and customer resources, an agent preference list of each agent to be evaluated and a customer preference list of each customer resource are generated.

7. The method for allocating customer resources according to claim 1, characterized in that: The matching of seats and customer resources according to the seat preference list and the customer preference list, and allocating corresponding target customer resources to each seat to be evaluated according to the matching result, includes: Initializing the seat preference list and the customer preference list, so that the seat preference list and the customer preference list are arranged in order of preference; According to the agent preference list, a matching request is initiated to the most preferred customer resource for each unmatched agent to be evaluated; Processing the received matching request according to the preference order in the customer preference list of the most preferred customer resource and the current matching status, and accepting or rejecting the matching request; When the matching request is accepted, the most preferred customer resource is allocated as a target customer resource to the agent to be evaluated who initiated the request, and the matching status of the most preferred customer resource is updated; When the matching request is rejected, the agent to be evaluated who initiated the request continues to initiate a matching request to the next preferred customer resource, and repeats the matching request initiation and customer resource response operations until all the agents to be evaluated and customer resources are allocated.

8. A client resource allocation device, characterized in that: include: The capability scoring module is used to collect the seat data of each seat to be evaluated, and perform capability scoring processing on the seat data through a preset scoring card model to obtain the capability score of each seat to be evaluated; A resource scoring module is used to collect historical customer behavior data, analyze the conversion rate of cross-insurance transfer of customer resources based on the historical customer behavior data, and obtain corresponding customer resource scores; A field determination module is used to collect historical performance data of each seat to be evaluated, and perform conversion rate analysis on each seat to be evaluated in multiple preset fields based on the historical performance data to obtain a list of areas of expertise of each seat to be evaluated; A preference generation module, for generating a corresponding agent preference list and a customer preference list according to the ability score, the list of areas of expertise and the customer resource score of each agent to be evaluated; The resource allocation module is used to match seats with customer resources according to the seat preference list and the customer preference list, and allocate corresponding target customer resources to each seat to be evaluated according to the matching result.

9. A computer device, characterized in that: comprising at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the customer resource allocation method according to any one of claims 1 to 7.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by one or more processors, enable the one or more processors to execute the customer resource allocation method according to any one of claims 1 to 7.

Images