Case allocation method and device, equipment and medium

Abstract

The invention belongs to the field of big data and the field of financial science and technology, and relates to a case allocation method, which comprises the steps of obtaining staff comprehensive information and historical case data of a collection staff, and constructing a collection staff database through preprocessing; and performing influence factor analysis on the historical cases in the database to obtain data analysis results of the collection personnel. Meanwhile, an initial weight factor representing the basic ability and experience of the collection person is obtained; and in combination with the initial weight and a data analysis result, calculating a weight factor of each collection person by using an analytic hierarchy process. The weight factor guides the distribution of new cases. And when a to-be-allocated case is received, the case is reasonably allocated to each collection person according to the case data and the weight factor. The invention further provides a device, equipment and a medium. In addition, the invention also relates to a block chain technology, and staff comprehensive information and historical case data can be stored in a block chain. Accurate case allocation can be realized, and then collection efficiency and success rate are improved.

Description

Technical Field

[0001] This application relates to the field of big data technology and fintech, and particularly to a case allocation method, device, equipment and medium. Background Art

[0002] In the debt collection work of the financial industry, the reasonable allocation of collection cases is crucial for improving the collection effect and efficiency. However, the existing collection case allocation methods are generally relatively simple and crude, and do not fully consider the comprehensive capabilities of collection personnel and the specific characteristics of cases, which directly leads to unsatisfactory collection effects and low efficiency of resource utilization.

[0003] Traditional collection case allocation models usually involve multi-level allocation, that is, first allocate cases to collection agencies, and then conduct secondary allocation within the collection agencies. This model not only has a cumbersome process, but also easily suffers from problems such as information transmission distortion and low allocation efficiency. The layer-by-layer transmission of information often leads to the loss or misunderstanding of key information, thus affecting the accuracy of collection decisions. In addition, the mismatch between the personal capabilities of collection personnel and the characteristics of cases is also an important factor affecting the collection effect. The existing allocation methods lack in-depth analysis and quantitative consideration of these factors.

[0004] In summary, the existing collection case allocation methods have defects such as cumbersome processes, information transmission distortion, low allocation efficiency, and mismatch between collection personnel and cases. Summary of the Invention

[0005] The purpose of the embodiments of this application is to propose a case allocation method, device, equipment and medium to solve the problems of cumbersome processes, information transmission distortion, low allocation efficiency, and mismatch between collection personnel and cases in the existing collection case allocation methods.

[0006] In the first aspect, a case allocation method is provided, which adopts the following technical solutions:

[0007] Obtain the comprehensive staff information of multiple collectors and the historical case data of multiple historical cases; preprocess the comprehensive staff information and historical case data to construct a collector database; perform an influencing factor analysis on the historical case data stored in the collector database to obtain the data analysis results of each collector; obtain the initial weight factor of each collector, where the initial weight factor represents the basic collection ability and experience level of each collector; according to the initial weight factor and the data analysis results, use the preset analytic hierarchy process to calculate the weight factor of each collector, and the weight factor is used to guide the allocation of new collection cases; when receiving the target case data of multiple cases to be allocated, allocate the multiple cases to be allocated to multiple collectors according to the target case data and the weight factor.

[0008] In a second aspect, a case allocation device is provided, which adopts the following technical solution:

[0009] A first acquisition module, configured to acquire the comprehensive employee information of multiple debt collectors and the historical case data of multiple historical cases;

[0010] A preprocessing module, configured to preprocess the comprehensive employee information and the historical case data to construct a debt collector database;

[0011] An analysis module, configured to perform an influencing factor analysis on the historical case data stored in the debt collector database to obtain the data analysis results of each debt collector;

[0012] A second acquisition module, configured to acquire the initial weight factor of each debt collector, where the initial weight factor characterizes the basic debt collection ability and experience level of each debt collector;

[0013] A calculation module, configured to calculate the weight factor of each debt collector according to the initial weight factor and the data analysis results by using a preset analytic hierarchy process, where the weight factor is used to guide the allocation of new debt collection cases;

[0014] An allocation module, configured to, when receiving the target case data of multiple cases to be allocated, allocate the multiple cases to be allocated to multiple debt collectors according to the target case data and the weight factor.

[0015] In a third aspect, a computer device is provided, including a memory and a processor, where computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, the steps of the above-mentioned case allocation method are implemented.

[0016] In a fourth aspect, a computer-readable storage medium is provided, where computer-readable instructions are stored in the computer-readable storage medium, and the computer-readable instructions can be executed by at least one processor to enable at least one processor to execute the steps of the above-mentioned case allocation method.

[0017] In the solution implemented by the above-mentioned case allocation method, device, equipment and medium, by comprehensively considering the comprehensive information of debt collectors and historical case data, in-depth mining of the capabilities of debt collectors and accurate tracing of historical performance are achieved. By preprocessing to construct a debt collector database, a solid data foundation is provided for subsequent analysis. Further, by analyzing the influencing factors of the historical case data stored in the database, the correlation between case characteristics and collection effects is quantified, solving the problem that existing allocation methods ignore case characteristics. Combining the initial weight factor of the debt collector, the weight factor calculated by the analytic hierarchy process not only reflects the basic capabilities and experience of the debt collector, but also incorporates the consideration of case characteristics, achieving an accurate match between the debt collector and the case. This innovative allocation model effectively avoids the hierarchical transmission of information and the loss of key information, significantly improving the allocation efficiency and decision-making accuracy. In summary, the technical solution of this application effectively solves the problems existing in the existing debt collection case allocation methods, such as cumbersome processes, distorted information transmission, low allocation efficiency, and mismatch between debt collectors and cases. Through the solution of this application, accurate case allocation can be achieved, thereby improving the collection efficiency and success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the solutions in this application, the following will briefly introduce the drawings required for the description of the embodiments of this application. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 is an exemplary system architecture diagram to which this application can be applied;

[0020] Figure 2 is a flowchart of a case allocation method provided by this application;

[0021] Figure 3 is a structural diagram of a case allocation device provided by this application;

[0022] Figure 4 is a structural diagram of a computer device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0024] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The phrase does not necessarily refer to the same embodiment at every occurrence in the specification, nor is it an independent or alternative embodiment mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0025] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0026] As Figure 1 shown, the system architecture 100 may include a terminal device 101, a network 102, and a server 103. The terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0027] Users may use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications may be installed on the terminal device 101, such as a web browser application, a shopping application, a search application, an instant messaging tool, an email client, a social platform software, etc.

[0028] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop 1011, the tablet computer 1012, or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop portable computer, a desktop computer, and the like.

[0029] The server 103 can be a server that provides various services. For example, it is a background server that provides support for the pages displayed on the terminal device 101.

[0030] It should be noted that the case allocation method provided by the embodiments of the present application is generally executed by the server. Correspondingly, the case allocation device is generally set in the server.

[0031] It should be understood that Figure 1 the numbers of the terminal devices, the network, and the server in

[0032] Continue to refer to Figure 2 , which shows a flowchart of an embodiment of the case allocation method according to the present application. The case allocation method includes the following steps:

[0033] Step S201, obtain the comprehensive staff information of multiple debt collectors and the historical case data of multiple historical cases.

[0034] Among them, the multiple debt collectors refer to multiple staff members participating in debt collection work, and they each have different debt collection capabilities and experiences. For example, ten members in a debt collection team constitute "multiple debt collectors".

[0035] Among them, the comprehensive staff information refers to multi-dimensional data covering the basic information, professional skills, past performance, training experience, etc. of the debt collectors, which comprehensively reflects the comprehensive capabilities of the debt collectors. These information are important sources for constructing the debt collector database and evaluating the capabilities of the debt collectors. For example, the education background, work experience, debt collection success rate, etc. of debt collector A constitute his "comprehensive staff information".

[0036] Among them, the multiple historical cases refer to the debt collection cases that have been processed in the past, and each case has unique characteristics and backgrounds. The data of these cases are used to analyze the relationship between the debt collection effect, the case characteristics, and the capabilities of the debt collectors.

[0037] Among them, historical case data refers to various information involved in historical cases, such as case amount, overdue time, debtor's credit status, collection process and results, etc. These data are the key basis for conducting factor analysis and optimizing collection strategies. For example, the overdue days, collection times, and final repayment situation of case B constitute its "historical case data".

[0038] Step S202: Preprocess the comprehensive information of employees and historical case data to construct a collector database.

[0039] Among them, preprocessing refers to cleaning, sorting, and standardizing the collected comprehensive information of employees and historical case data to ensure the quality and consistency of the data. Preprocessing is the prerequisite for constructing a collector database and conducting subsequent analysis. For example, filling in missing values and correcting outliers are the "preprocessing" processes.

[0040] Among them, the collector database refers to a system or platform that stores the preprocessed comprehensive information of collectors and historical case data. This database provides data support for factor analysis and weight factor calculation. For example, a spreadsheet or database system containing all collector information and historical case data is the "collector database".

[0041] Step S203: Conduct factor analysis on the historical case data stored in the collector database to obtain the data analysis results for each collector.

[0042] Among them, factor analysis refers to deeply analyzing the historical case data, identifying the key factors that affect the collection effect, and quantifying the influence degree of these factors on the collection effect of collectors. This process helps to understand the relationship between case characteristics and collector capabilities. For example, analyzing and finding that there is a negative correlation between the case amount and the collection success rate is a kind of "factor analysis".

[0043] Among them, the data analysis results refer to the conclusions or findings obtained after factor analysis, usually presented in the form of data or charts. These results are used to guide the calculation of weight factors and the allocation of collection cases. For example, the data analysis results show that collector A performs excellently in handling high-amount cases, which is a kind of "data analysis result".

[0044] Step S204: Obtain the initial weight factor for each collector, and the initial weight factor represents the basic collection ability and experience level of each collector.

[0045] Among them, the initial weight factor refers to the initial weight value set based on the basic collection ability and experience level of the collector, which is used to reflect the relative importance of the collector in the collection work. These weight factors will be adjusted and optimized in the subsequent calculation process. For example, the initial weight value set according to the evaluation scores corresponding to multiple evaluation dimensions of collector B, historical performance data, working years, average collection success rate, etc. is the "initial weight factor".

[0046] Step S205, according to the initial weight factor and the data analysis result, adopt the preset analytic hierarchy process to calculate the weight factor of each collector, and the weight factor is used to guide the allocation of new collection cases.

[0047] Among them, the analytic hierarchy process refers to a multi-criteria decision-making analysis method, which decomposes complex problems into several levels and factors for comprehensive evaluation combining qualitative and quantitative analysis. In the embodiment, the analytic hierarchy process is used to combine the initial weight factor and the data analysis result to calculate the weight factor of each collector. For example, the analytic hierarchy process is used to determine the relative importance of factors such as case amount and overdue time in the calculation of the weight factor.

[0048] Among them, the weight factor refers to the weight value of each collector calculated according to the analytic hierarchy process. These weight factors are the key basis for guiding the allocation of new collection cases. For example, collector C has a higher weight factor when dealing with specific types of cases, which means that this collector is more suitable for handling such cases.

[0049] Step S206, when receiving the target case data of multiple cases to be allocated, allocate the multiple cases to be allocated to multiple collectors according to the target case data and the weight factor.

[0050] Among them, the multiple cases to be allocated refer to the set of debt collection cases to be processed currently, and these cases need to be reasonably allocated according to the weight factor of the collector. For example, the thirty newly received debt collection cases are the "multiple cases to be allocated".

[0051] Among them, the target case data refers to the set of information describing the specific characteristics and background of the cases to be allocated, including case amount, overdue time, debtor's credit status, etc. These information are used to match with the weight factor of the collector to determine the best collector allocation plan. For example, the detailed information of case D (including amount, overdue days, etc.) is the "target case data".

[0052] Embodiments of the present application can achieve in-depth mining of the capabilities of debt collectors and accurate tracing of historical performance by comprehensively considering the comprehensive information of debt collectors and historical case data. By preprocessing to construct a debt collector database, a solid data foundation is provided for subsequent analysis. Further, by analyzing the influencing factors of the historical case data stored in the database, the correlation between case characteristics and collection effects is quantified, solving the problem that existing allocation methods ignore case characteristics. Combining the initial weight factors of debt collectors, the weight factors calculated using the analytic hierarchy process not only reflect the basic capabilities and experience of debt collectors but also incorporate considerations of case characteristics, achieving an accurate match between debt collectors and cases. This innovative allocation model effectively avoids the layer-by-layer transmission of information and the loss of key information, significantly improving the allocation efficiency and decision-making accuracy. In summary, the technical solution of the present application effectively solves the problems existing in the existing debt collection case allocation methods, such as cumbersome processes, distorted information transmission, low allocation efficiency, and mismatches between debt collection personnel and cases. Through the solution of the present application, accurate case allocation can be achieved, thereby improving the collection efficiency and success rate.

[0053] In some alternative implementation manners of this embodiment, in step 202, preprocessing the comprehensive information of the staff and the historical case data to construct a debt collector database specifically includes the following steps:

[0054] Normalize the numerical data in the comprehensive information of the staff and the numerical data in the historical case data respectively to obtain the standard numerical data corresponding to the comprehensive information of the staff and the standard case data corresponding to the historical case data; classify and encode the text data in the comprehensive information of the staff and the text data in the historical case data to obtain the category data corresponding to the comprehensive information of the staff and the category case data corresponding to the historical case data; obtain the preset database table structure and the preset data integration rules; store the standard numerical data, the standard case data, the category data, and the category case data in a relational database management system according to the database table structure and the data integration rules to obtain the debt collector database.

[0055] Among them, the standard numerical data refers to the result of normalizing the numerical data in the comprehensive information of the debt collector and the historical case data. Normalization is a data preprocessing technique aimed at converting numerical values of different magnitudes or ranges into numerical values under a unified scale for subsequent data analysis and processing.

[0056] Among them, the standard case data refers to the result of normalizing the numerical data in the historical case data. These numerical data may include the amount of the case, the overdue time, etc. Through normalization, these numerical values can be converted into standard values under a unified scale for subsequent influencing factor analysis and calculation of the weight factors of debt collectors.

[0057] Among them, the category data refers to the result of classifying and encoding the comprehensive information of the debt collectors and the text data in the historical case data. Classification and encoding is the process of converting text data into numerical or symbolic data that is easy for computers to process and analyze.

[0058] Among them, the category case data refers to the result of classifying and encoding the text data in the historical case data. Such text data may include the type of the case, the credit rating of the debtor, etc. Through classification and encoding, these text data can be converted into numerical or symbolic data that is easy to analyze and process.

[0059] Among them, the database table structure refers to the table framework or layout for storing data in the database, which defines the names, data types, lengths of the columns (fields) in the table, and the association relationships between the columns. It is used to guide the construction of the debt collector database to ensure that the data organization method meets the requirements of subsequent analysis and processing. For example, a table containing fields such as debt collector ID, name, age, education level, etc. is a possible database table structure.

[0060] Among them, the data integration rules refer to the principles and methods followed when integrating and uniformly processing data from different sources, formats, or structures. It is used to guide the storage process of standard numerical data, standard case data, category data, and category case data in a relational database management system to ensure that these data can be organized and accessed in the expected format and structure. For example, the data integration rules may stipulate that all information of the same debt collector is integrated into the same record and stored in a specific order.

[0061] Among them, the relational database management system is a database management system based on the relational model, which uses tables (relations) to store and manage data. It is used to store and process the comprehensive information of the debt collectors and the historical case data.

[0062] In one example, the comprehensive staff information of 100 debt collectors was obtained from the database of a financial institution. This information includes numerical data such as the age, work experience, educational background, and past debt collection success rate of the debt collectors, as well as text data such as the academic qualifications, departments, and professional skills of the debt collectors. At the same time, data on 500 historical cases corresponding to these 100 debt collectors was also obtained. This data includes numerical data such as the amount of the case, the overdue time, and the credit rating of the debtor, as well as text data such as the type of the case, the processing status, and the debt collection difficulty. Next, normalization processing was performed on these numerical data. For example, for the age of the debt collector, it was converted into a standard value between 0 and 1. The specific conversion method was to subtract the minimum age from the age and then divide by the age range (maximum age - minimum age). Similarly, for the amount and overdue time in historical cases, similar normalization processing was also performed. For the text data, classification and encoding were carried out. For example, for the academic qualifications of the debt collectors, they were divided into categories such as undergraduate, master, and doctor, and corresponding codes were assigned respectively. For the type of cases in historical cases, they were divided into categories such as personal loans, corporate loans, and credit card overdue, and corresponding codes were also assigned. Then, according to the preset database table structure and data integration rules, the processed data was stored in a relational database management system. The database table structure includes a debt collector information table and a case information table, which are used to store the comprehensive staff information of the debt collectors and historical case data respectively. The data integration rules stipulate how to integrate and uniformly process data from different sources, formats, or structures. Through the above steps, a debt collector database was successfully constructed. This database contains the preprocessed and integrated comprehensive staff information of the debt collectors and historical case data, providing a solid foundation for subsequent data analysis and debt collection case allocation.

[0063] The embodiment of the present application can effectively eliminate the dimensional difference of numerical data in the comprehensive staff information and historical case data through normalization processing, enabling data from different sources and different ranges to be compared and analyzed on the same scale, and improving the comparability and accuracy of the data. At the same time, classification and encoding of the text data are carried out to achieve the standardization and normalization of the data, providing convenience for subsequent data processing and analysis. Through the preset database table structure and data integration rules, the processed data is successfully stored in a relational database management system, constructing a complete debt collector database. This database not only contains the comprehensive staff information of the debt collectors but also covers historical case data, providing rich data support for subsequent factor analysis and debt collection case allocation. In addition, the construction of the debt collector database also realizes the centralized management and efficient access of the data, avoiding the layer-by-layer transmission of information and the loss or misunderstanding of key information, and improving the accuracy of information transmission and allocation efficiency.

[0064] In some alternative implementation manners of this embodiment, in step S203, perform an impact factor analysis on the historical case data stored in the debt collector database to obtain the data analysis result of each debt collector, which specifically includes the following steps:

[0065] Extract features from the historical case data in the debt collector database to obtain multiple historical case feature information; obtain the collection effect indicators of each debt collector in the corresponding historical collection cases; use the pre-trained data analysis model to perform feature impact analysis on the multiple historical case feature information and collection effect indicators to obtain the data analysis result of each debt collector.

[0066] Among them, the multiple historical case feature information refers to a key data set extracted from multiple historical collection cases that can reflect the characteristics of the cases. This data comes from the historical case database and includes, but is not limited to, the amount of the case, the overdue duration, the credit score of the debtor, the type of the case, etc. It is used to characterize the different dimensional characteristics of the historical cases.

[0067] Among them, the collection effect indicator is a quantitative standard used to measure the performance of the debt collector in the corresponding historical collection case. These indicators usually include the collection success rate, the collection cycle, the amount of money recovered, the customer satisfaction, etc., which directly reflect the work efficiency and achievements of the debt collector. It is used to characterize the basic collection ability and experience level of the debt collector.

[0068] Among them, the data analysis model reveals the internal relationship between the case characteristics and the collection effect by analyzing the historical case data and collection effect indicators of the debt collector.

[0069] Among them, the feature impact analysis is a method of performing correlation analysis on multiple historical case feature information and collection effect indicators by using a pre-trained data analysis model. This analysis aims to reveal the specific impact degree of different features on the collection effect, so as to help identify the key factors affecting the collection effect. For example, the feature impact analysis may reveal that the amount of the case has a significant positive impact on the collection success rate, while the credit score of the debtor has a negative impact on the collection cycle.

[0070] In one example, in the debt collector database, feature extraction is performed on historical case data. For example, the urgency and severity features of a case can be extracted from the amount of the case and the overdue time; the repayment willingness and repayment ability features of the debtor can be extracted from the debtor's credit record. These features together constitute multiple historical case feature information. At the same time, obtain the collection effect indicators of each debt collector in the corresponding historical collection cases, such as collection success rate, collection cycle, recovered amount, etc. These indicators can reflect the actual collection ability and effect of the debt collector. Use a pre-trained data analysis model, such as a random forest model in machine learning or a neural network model in deep learning, to perform feature impact analysis on the extracted multiple historical case feature information and collection effect indicators. Through the training and learning of the model, the influence degree of each feature on the collection effect can be obtained, so as to obtain the data analysis result of each debt collector.

[0071] The embodiment of the present application can successfully obtain multiple key historical case feature information by performing feature extraction on the historical case data in the debt collector database. These information comprehensively reflect the type, difficulty and complexity of the case. At the same time, combined with the collection effect indicators of each debt collector in the corresponding historical cases, such as the recovery rate, collection cycle, etc., the accurate evaluation of the actual collection ability of the debt collector is realized. Use a pre-trained data analysis model to perform in-depth feature impact analysis on these feature information and collection effect indicators, further excavate the potential relationship between the case features and the collection effect, and provide a scientific basis for the calculation of the weight factor of the debt collector. This process not only enhances the accuracy and objectivity of data analysis, but also effectively avoids the interference of human factors in the traditional allocation method, so as to ensure that new collection cases can be reasonably allocated based on the actual ability of the debt collector and the characteristics of the case, greatly improving the collection efficiency and effect.

[0072] In some optional implementation manners of this embodiment, step S204 of obtaining the initial weight factor of each debt collector specifically includes the following steps:

[0073] Obtain the evaluation scores corresponding to multiple evaluation dimensions of each debt collector; obtain the historical performance data of each debt collector, and use a pre-trained regression model to perform performance evaluation on the historical performance data to obtain the performance scores of each debt collector; obtain the first weight coefficient of the evaluation scores and the second weight coefficient of the performance scores; based on the evaluation scores, the first weight coefficient, the performance scores and the second weight coefficient, determine the initial weight factor of each debt collector.

[0074] Among them, the multiple evaluation dimensions refer to comprehensively considering from multiple different perspectives or aspects when evaluating a debt collector. These dimensions may include but are not limited to the work experience, professional skills, communication ability, psychological quality, historical collection success rate, etc. of the debt collector.

[0075] Among them, the evaluation score refers to the result obtained by quantitatively scoring the performance of debt collectors in each evaluation dimension according to preset evaluation criteria and methods. These scores are usually obtained through methods such as expert review, questionnaire survey, and data analysis, and are important bases for evaluating the comprehensive ability of debt collectors.

[0076] Among them, historical performance data refers to the relevant data of the achievements and performances of debt collectors in handling cases over a past period of time. These data may include, but are not limited to, collection success rate, recovered amount, collection cycle, customer satisfaction, etc.

[0077] Among them, the regression model is a statistical model used to predict numerical output results.

[0078] Among them, the performance score refers to the quantitative score obtained after predicting and analyzing the historical performance data of debt collectors according to the regression model.

[0079] Among them, the first weight coefficient refers to the relative importance or influence degree given to the evaluation score when calculating the initial weight factor of a debt collector. This coefficient can be determined according to factors such as the importance and relevance of the evaluation dimension and expert opinions.

[0080] Among them, the second weight coefficient refers to the relative importance or influence degree given to the performance score when calculating the initial weight factor of a debt collector. Similar to the first weight coefficient, the second weight coefficient is also determined according to factors such as the importance and relevance of the performance score and expert opinions.

[0081] In an example, the corresponding evaluation scores can be obtained from multiple evaluation dimensions. For example, through methods such as expert review and questionnaire survey, evaluate the professional skills, communication ability, and psychological quality of debt collectors and give corresponding scores. At the same time, obtain the historical performance data of each debt collector, such as collection success rate, recovered amount, etc. Use a pre-trained regression model to conduct performance evaluation on the historical performance data to obtain the performance scores of each debt collector. In this embodiment, the regression model uses a machine learning algorithm based on historical performance data, which can automatically learn the laws and trends in the data, so as to accurately predict the future performance of debt collectors. In order to comprehensively consider the influence of evaluation scores and performance scores on the weight factor of debt collectors, obtain the first weight coefficient of the evaluation score and the second weight coefficient of the performance score. These weight coefficients are set according to expert opinions and actual needs to balance the contributions of different evaluation dimensions and historical performances in the calculation of the weight factor. Finally, based on the evaluation score, the first weight coefficient, the performance score, and the second weight coefficient, determine the initial weight factor of each debt collector. The initial weight factor characterizes the basic collection ability and experience level of debt collectors, and provides a basis for calculating the weight factor using the analytic hierarchy process subsequently.

[0082] In the embodiments of the present application, by comprehensively considering multiple evaluation dimensions and historical performance data of debt collectors, the accurate quantification of the capabilities of debt collectors is achieved. Specifically, first, debt collectors are comprehensively evaluated from multiple dimensions such as professional skills, communication skills, and psychological qualities to obtain evaluation scores, which helps to deeply explore the potential advantages of debt collectors. Secondly, the historical performance data is deeply analyzed using a pre-trained regression model to obtain performance scores, which objectively reflects the actual work effectiveness of debt collectors. At the same time, by reasonably setting the weight coefficients of the evaluation scores and performance scores, the contributions of different evaluation dimensions and historical performance in the calculation of the weight factors are further balanced. Finally, based on these data and coefficients, the initial weight factor of each debt collector is calculated. This factor not only represents the basic debt collection ability and experience level of the debt collector, but also provides a solid foundation for calculating the weight factor using the analytic hierarchy process in the follow-up.

[0083] In some alternative implementation manners of this embodiment, in step S205, according to the initial weight factor and the data analysis result, the preset analytic hierarchy process is used to calculate the weight factor of each debt collector, which specifically includes the following steps:

[0084] Based on the initial weight factor, the analytic hierarchy process is used to construct the first judgment matrix for each debt collector; based on the data analysis result, the analytic hierarchy process is used to construct the second judgment matrix for each debt collector; the preset weight vector calculation method is used to calculate the first weight vector corresponding to the first judgment matrix and the second weight vector corresponding to the second judgment matrix respectively; the first weight vector and the second weight vector are synthesized to obtain the weight factor of each debt collector.

[0085] Among them, the first judgment matrix is a matrix constructed using the analytic hierarchy process (AHP) based on the initial weight factor of the debt collector. This matrix is used to quantify the relative importance of debt collectors in terms of basic debt collection ability and experience level.

[0086] Among them, the second judgment matrix is a matrix constructed using the analytic hierarchy process based on the analysis result of the influence of historical case data stored in the debt collector database. This matrix is used to quantify the relative advantages of debt collectors when handling different types of cases.

[0087] Among them, the weight vector calculation method may include methods such as the eigenvector method, the geometric mean method, or the arithmetic mean method. These methods can calculate the relative weights of each element in the overall based on the element values in the judgment matrix, so as to be used for subsequent decision-making analysis.

[0088] Among them, the first weight vector is the weight vector calculated based on the first judgment matrix. It represents the relative importance ranking of debt collectors in terms of basic debt collection ability and experience level. The larger the element value of the first weight vector, the more advantageous the corresponding debt collector is in terms of basic debt collection ability and experience level.

[0089] Among them, the second weight vector is a weight vector calculated based on the second judgment matrix. It characterizes the relative advantage ranking of the debt collectors when dealing with different types of cases. The larger the element value of the second weight vector, the more specialized the corresponding debt collector is in dealing with specific types of cases.

[0090] In one example, based on the initial weight factor of each debt collector, the analytic hierarchy process was used to construct the first judgment matrix. At the same time, based on the data analysis results, a second judgment matrix was constructed, which reflects the relative advantages of debt collectors when dealing with different types of cases. When constructing the judgment matrix, the 1-9 scale method can be used to represent the relative importance between elements. For example, in the first judgment matrix, if the initial weight factor of debt collector A is significantly higher than that of debt collector B, then the relative importance of A to B in the matrix is assigned as 7 or 9. Next, the eigenvector method was used to calculate the weight vectors corresponding to the first judgment matrix and the second judgment matrix. During the calculation process, the eigenvalues and eigenvectors of the judgment matrix were first obtained, and then the eigenvector corresponding to the largest eigenvalue was selected as the weight vector. Finally, the first weight vector and the second weight vector were synthesized to obtain the weight factor of each debt collector. This weight factor comprehensively considers the basic debt collection ability of the debt collector and their relative advantages when dealing with different types of cases.

[0091] The embodiment of the present application can construct the first judgment matrix based on the initial weight factor of the debt collector, quantify the basic debt collection ability and experience level of the debt collector, and ensure the objectivity and accuracy of the evaluation. At the same time, by combining the data analysis results of historical cases to construct the second judgment matrix, the expertise and adaptability of the debt collector when dealing with different case types are further considered, thus achieving an accurate match between the debt collector and the case characteristics. The preset weight vector calculation method ensures the scientific quantification of the relative importance of elements in the judgment matrix, providing a reliable basis for synthesizing the weight factor. By synthesizing the first weight vector and the second weight vector, a weight factor that comprehensively reflects the comprehensive ability of the debt collector is obtained. This factor not only considers the basic qualities of the debt collector but also incorporates their performance when dealing with specific cases. Therefore, the technical solution of this embodiment can guide the more reasonable and efficient allocation of debt collection cases to suitable debt collectors, effectively avoiding the problems of information transmission distortion and low allocation efficiency, and significantly improving the debt collection effect and resource utilization efficiency.

[0092] In some optional implementation manners of this embodiment, in step S206, according to the target case data and the weight factor, multiple cases to be assigned are assigned to multiple debt collectors, which specifically includes the following steps:

[0093] Compare the target case data with the weight factor to obtain a comparison result; according to the comparison result, assign multiple cases to be assigned to multiple debt collectors.

[0094] In one example, when receiving the target case data of multiple cases to be assigned, the overdue amount of the target case data can be determined first, and the multiple cases to be assigned are sorted in descending order to obtain a sequence of cases to be assigned. At the same time, based on the value of the weight factor, the multiple debt collectors are sorted in descending order to obtain a sequence of debt collectors. Subsequently, the sequence of cases to be assigned and the sequence of debt collectors are compared to obtain a comparison result. Based on the comparison result, according to the arrangement order of the cases to be assigned in the sequence of cases to be assigned and the arrangement order of the debt collectors in the sequence of debt collectors, the multiple cases to be assigned are sequentially assigned to the corresponding debt collectors in the sequence of debt collectors.

[0095] In the embodiment of the present application during case assignment, according to the comparison result between the weight factor and the target case data, the case is preferentially assigned to the most suitable debt collector, thereby improving the collection efficiency and reducing resource waste. At the same time, the technical solution of this embodiment also simplifies the case assignment process, reduces the levels of information transmission, reduces the risk of information distortion, and ensures the accuracy of the collection decision.

[0096] In some alternative implementation manners of this embodiment, the steps of "comparing the target case data with the weight factor to obtain a comparison result" and "assigning multiple cases to be assigned to multiple debt collectors according to the comparison result" specifically include the following steps:

[0097] Based on the overdue amount of the target case data, the multiple cases to be assigned are sorted in descending order to obtain a sequence of cases to be assigned; based on the value of the weight factor, the multiple debt collectors are sorted in descending order to obtain a sequence of debt collectors; the sequence of cases to be assigned and the sequence of debt collectors are compared to obtain a comparison result; based on the comparison result, according to the arrangement order of the cases to be assigned in the sequence of cases to be assigned and the arrangement order of the debt collectors in the sequence of debt collectors, the multiple cases to be assigned are sequentially assigned to the corresponding debt collectors in the sequence of debt collectors.

[0098] Among them, the sequence of cases to be assigned refers to the case list obtained by sorting according to the target case data (such as the overdue amount) of these cases after receiving the target case data of multiple collection cases.

[0099] Among them, the sequence of debt collectors is the debt collector list obtained by sorting according to the value of the weight factor of the debt collectors. For example, when there are 20 debt collectors in a collection team, sorting them from high to low according to their weight factors can obtain a sequence of debt collectors.

[0100] Among them, the comparison result refers to the matching situation obtained after comparing the sequence of cases to be assigned with the sequence of debt collectors. The comparison result is used to guide how to assign the cases to be assigned to the most suitable debt collector.

[0101] In one example, when receiving the target case data of 20 new collection cases (cases to be assigned), first, the overdue amounts of the cases are sorted in descending order to obtain a sequence of cases to be assigned. At the same time, the weight factors of the collectors are sorted in descending order to obtain a sequence of collectors. Subsequently, the sequence of cases to be assigned is compared with the sequence of collectors to obtain a comparison result. According to the comparison result, the cases are assigned to the most suitable collector one by one in the order of the cases in the sequence of cases to be assigned and the order of the collectors in the sequence of collectors. For example, the case with the highest overdue amount is assigned to the collector with the highest weight factor, and so on.

[0102] In the embodiment of the present application, by sorting the cases to be assigned in descending order based on the overdue amount to construct a sequence of cases to be assigned, the urgency and potential risks of the cases can be clearly identified, ensuring that high-amount and high-risk cases are given priority. At the same time, by sorting the weight factors of the collectors in descending order to form a sequence of collectors, the comprehensive collection ability and experience level of the collectors can be intuitively reflected. By comparing the sequence of cases to be assigned with the sequence of collectors, accurate matching of cases and collectors is achieved, ensuring that each case can be handled by the most suitable collector. This allocation method based on data analysis and quantitative evaluation not only simplifies the cumbersome process of traditional multi-level allocation but also avoids problems such as information transmission distortion and low allocation efficiency, effectively improving the collection efficiency and success rate, and realizing the optimal allocation of collection resources and case requirements.

[0103] It should be emphasized that to further ensure the above-mentioned comprehensive information of employees, historical case data, data analysis results, initial weight factors, weight factors, and target case data, the above-mentioned comprehensive information of employees, historical case data, data analysis results, initial weight factors, weight factors, and target case data can also be stored in a node of a blockchain.

[0104] The blockchain referred to in the present application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. Blockchain, in essence, is a decentralized database, a string of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0105] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM), etc.

[0106] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or alternately with at least some of the sub-steps or stages of other steps or other steps.

[0107] Further reference Figure 3 to Figure 2 As an implementation of the method shown above, an embodiment of a case allocation device is provided in this application. This device embodiment corresponds to the method embodiment shown Figure 2 above, and this device can be specifically applied to various electronic devices.

[0108] As Figure 3 shown, the case allocation device 400 of this embodiment includes: a first acquisition module 401, a preprocessing module 402, an analysis module 403, a second acquisition module 404, a calculation module 405, and an allocation module 406. Among them:

[0109] The first acquisition module 401 is used to acquire the comprehensive employee information of multiple debt collectors and the historical case data of multiple historical cases;

[0110] The preprocessing module 402 is used to preprocess the comprehensive employee information and the historical case data to construct a debt collector database;

[0111] The analysis module 403 is used to analyze the influencing factors of the historical case data stored in the debt collector database to obtain the data analysis results of each debt collector;

[0112] The second acquisition module 404 is used to acquire the initial weight factor of each debt collector, and the initial weight factor represents the basic debt collection ability and experience level of each debt collector;

[0113] A calculation module 405, configured to calculate a weight factor for each debt collector according to an initial weight factor and data analysis results by using a preset analytic hierarchy process, where the weight factor is used to guide the allocation of new debt collection cases.

[0114] An allocation module 406, configured to, when receiving target case data of multiple cases to be allocated, allocate the multiple cases to be allocated to multiple debt collectors according to the target case data and the weight factor.

[0115] The embodiment of the present application can realize in-depth mining of the capabilities of debt collectors and accurate tracing of historical performance by comprehensively considering the comprehensive information of debt collectors and historical case data. By performing preprocessing to construct a debt collector database, a solid data foundation is provided for subsequent analysis. Further, by analyzing the influencing factors of the historical case data stored in the database, the correlation between case characteristics and debt collection effects is quantified, solving the problem that the existing allocation method ignores case characteristics. Combining the initial weight factor of debt collectors, the weight factor calculated by using the analytic hierarchy process not only reflects the basic capabilities and experience of debt collectors, but also incorporates the consideration of case characteristics, realizing an accurate match between debt collectors and cases. This innovative allocation mode effectively avoids the hierarchical transmission of information and the loss of key information, significantly improving the allocation efficiency and decision-making accuracy. In summary, the technical solution of the present application effectively solves the problems existing in the existing debt collection case allocation method, such as cumbersome processes, distorted information transmission, low allocation efficiency, and mismatch between debt collection personnel and cases. Through the solution of the present application, accurate case allocation can be achieved, thereby improving the debt collection efficiency and success rate.

[0116] In one embodiment, the preprocessing module 402 includes:

[0117] A normalization sub-module, configured to perform normalization processing on the numerical data in the comprehensive information of employees and the numerical data in the historical case data respectively to obtain standard numerical data corresponding to the comprehensive information of employees and standard case data corresponding to the historical case data.

[0118] A classification and coding sub-module, configured to classify and code the text data in the comprehensive information of employees and the text data in the historical case data to obtain category data corresponding to the comprehensive information of employees and category case data corresponding to the historical case data.

[0119] A first acquisition sub-module, configured to acquire a preset database table structure and a preset data integration rule.

[0120] A storage sub-module, configured to store the standard numerical data, the standard case data, the category data, and the category case data in a relational database management system according to the database table structure and the data integration rule to obtain a debt collector database.

[0121] In the embodiments of the present application, through normalization processing, the dimensional differences of numerical data in the comprehensive information of employees and historical case data are effectively eliminated, enabling data from different sources and different scopes to be compared and analyzed on the same scale, improving the comparability and accuracy of the data. At the same time, text data is classified and coded, realizing the standardization and normalization of the data, which provides convenience for subsequent data processing and analysis. Through the preset database table structure and data integration rules, the processed data is successfully stored in a relational database management system, constructing a complete debt collector database. This database not only contains the comprehensive information of employees of debt collectors, but also covers historical case data, providing rich data support for subsequent analysis of influencing factors and distribution of debt collection cases. In addition, the construction of the debt collector database also realizes the centralized management and efficient access of data, avoiding the layer-by-layer transmission of information and the loss or misunderstanding of key information, and improving the accuracy of information transmission and distribution efficiency.

[0122] In one embodiment, the analysis module 403 includes:

[0123] An extraction sub-module, configured to extract feature information of multiple historical cases from the historical case data in the debt collector database;

[0124] A second acquisition sub-module, configured to acquire the debt collection effect indicators of each debt collector in the corresponding historical debt collection cases;

[0125] An analysis sub-module, configured to perform feature influence analysis on the multiple historical case feature information and debt collection effect indicators by using a pre-trained data analysis model, and obtain the data analysis results of each debt collector.

[0126] In the embodiments of the present application, by extracting feature information of historical case data in the debt collector database, multiple key historical case feature information is successfully obtained, which comprehensively reflects the type, difficulty and complexity of the cases. At the same time, combined with the debt collection effect indicators of each debt collector in the corresponding historical cases, such as the collection rate, debt collection cycle, etc., the actual debt collection ability of the debt collector is accurately evaluated. Using a pre-trained data analysis model to conduct in-depth feature influence analysis on these feature information and debt collection effect indicators, further exploring the potential relationship between case features and debt collection effects, provides a scientific basis for calculating the weight factors of debt collectors. This process not only enhances the accuracy and objectivity of data analysis, but also effectively avoids the interference of human factors in traditional distribution methods, thus ensuring that new debt collection cases can be reasonably distributed based on the actual capabilities of debt collectors and case characteristics, greatly improving the debt collection efficiency and effect.

[0127] In one embodiment, the second acquisition module 404 includes:

[0128] The third acquisition sub-module is used to acquire the evaluation scores corresponding to multiple evaluation dimensions of each debt collector;

[0129] The fourth acquisition sub-module is used to acquire the historical performance data of each debt collector, and use a pre-trained regression model to perform performance evaluation on the historical performance data to obtain the performance scores of each debt collector;

[0130] The fifth acquisition sub-module is used to acquire the first weight coefficient of the evaluation scores and the second weight coefficient of the performance scores;

[0131] The determination sub-module is used to determine the initial weight factor of each debt collector based on the evaluation scores, the first weight coefficient, the performance scores, and the second weight coefficient.

[0132] In the embodiment of the present application, by comprehensively considering the multiple evaluation dimensions and historical performance data of debt collectors, the accurate quantification of debt collectors' capabilities is realized. Specifically, first, debt collectors are comprehensively evaluated from multiple dimensions such as professional skills, communication skills, and psychological qualities to obtain evaluation scores, which helps to deeply explore the potential advantages of debt collectors. Secondly, a pre-trained regression model is used to deeply analyze the historical performance data to obtain performance scores, which objectively reflect the actual work effectiveness of debt collectors. At the same time, by reasonably setting the weight coefficients of the evaluation scores and performance scores, the contributions of different evaluation dimensions and historical performance in the calculation of the weight factor are further balanced. Finally, based on these data and coefficients, the initial weight factor of each debt collector is calculated. This factor not only characterizes the basic debt collection ability and experience level of debt collectors, but also provides a solid foundation for calculating the weight factor using the analytic hierarchy process in the follow-up.

[0133] In one embodiment, the calculation module 405 includes:

[0134] The first construction sub-module is used to construct the first judgment matrix of each debt collector based on the initial weight factor by using the analytic hierarchy process;

[0135] The second construction sub-module is used to construct the second judgment matrix of each debt collector based on the data analysis results by using the analytic hierarchy process;

[0136] The calculation sub-module is used to calculate the first weight vector corresponding to the first judgment matrix and the second weight vector corresponding to the second judgment matrix respectively by using a preset weight vector calculation method;

[0137] The synthesis sub-module is used to synthesize the first weight vector and the second weight vector to obtain the weight factor of each debt collector.

[0138] In the embodiments of the present application, a first judgment matrix can be constructed based on the initial weight factors of debt collectors, quantifying the basic debt collection capabilities and experience levels of debt collectors, ensuring the objectivity and accuracy of the evaluation. At the same time, a second judgment matrix is constructed in combination with the analysis results of historical case data, further considering the expertise and adaptability of debt collectors in handling different case types, thereby achieving an accurate match between debt collectors and case characteristics. The preset weight vector calculation method ensures the scientific quantification of the relative importance of elements in the judgment matrix, providing a reliable basis for synthesizing weight factors. By synthesizing the first weight vector and the second weight vector, a weight factor that comprehensively reflects the comprehensive capabilities of debt collectors is obtained. This factor not only considers the basic qualities of debt collectors but also incorporates their performance in handling specific cases. Therefore, the technical solution of this embodiment can guide the more reasonable and efficient allocation of debt collection cases to suitable debt collectors, effectively avoiding the problems of information transmission distortion and low allocation efficiency, and significantly improving the debt collection effect and resource utilization efficiency.

[0139] In one embodiment, the allocation module 406 includes:

[0140] A comparison sub-module, configured to compare the target case data with the weight factor to obtain a comparison result;

[0141] An allocation sub-module, configured to allocate a plurality of cases to be allocated to a plurality of debt collectors according to the comparison result.

[0142] In the embodiments of the present application, when allocating cases, according to the comparison result of the weight factor and the target case data, the cases are preferentially allocated to the most suitable debt collectors, thereby improving the debt collection efficiency and reducing resource waste. At the same time, the technical solution of this embodiment also simplifies the case allocation process, reduces the levels of information transmission, reduces the risk of information distortion, and ensures the accuracy of debt collection decisions.

[0143] In one embodiment, the comparison sub-module is further configured to perform a descending order sorting on a plurality of cases to be allocated based on the overdue amount of the target case data to obtain a sequence of cases to be allocated; perform a descending order sorting on a plurality of debt collectors based on the value of the weight factor to obtain a sequence of debt collectors; and compare the sequence of cases to be allocated with the sequence of debt collectors to obtain a comparison result;

[0144] The allocation sub-module is further configured to, based on the comparison result, sequentially allocate a plurality of cases to be allocated to the corresponding debt collectors in the sequence of debt collectors according to the arrangement order of the cases to be allocated in the sequence of cases to be allocated and the arrangement order of the debt collectors in the sequence of debt collectors.

[0145] In the embodiments of the present application, the cases to be assigned can be sorted in descending order based on the overdue amount to construct a sequence of cases to be assigned, which can clearly identify the urgency and potential risks of the cases and ensure that high-amount and high-risk cases are given priority for processing. At the same time, sorting in descending order according to the weight factors of the debt collectors forms a sequence of debt collectors, which intuitively reflects the comprehensive debt collection ability and experience level of the debt collectors. By comparing the sequence of cases to be assigned with the sequence of debt collectors, accurate matching of cases and debt collectors is achieved, ensuring that each case can be handled by the most suitable debt collector. This allocation method based on data analysis and quantitative evaluation not only simplifies the cumbersome process of traditional multi-level allocation but also avoids problems such as information transmission distortion and low allocation efficiency, effectively improving the debt collection efficiency and success rate, and realizing the optimal allocation of debt collection resources and case requirements.

[0146] To solve the above technical problems, the embodiments of the present application also provide a computer device. For details, please refer to Figure 4 , Figure 4 which is the basic structural block diagram of the computer device in this embodiment.

[0147] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are communicatively connected to each other through a system bus. It should be noted that only the computer device 6 with the memory 61, the processor 62, and the network interface 63 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Among them, those skilled in the art of the present technology can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0148] The computer device can be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touchpad, a voice control device, or other means.

[0149] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 6. Of course, the memory 61 may also include both the internal storage unit and the external storage device of the computer device 6. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the case allocation method, etc. In addition, the memory 61 can also be used to temporarily store various data that have been output or will be output.

[0150] In some embodiments, the processor 62 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run the computer-readable instructions stored in the memory 61 or process data, such as running the computer-readable instructions of the case allocation method.

[0151] The network interface 63 may include a wireless network interface or a wired network interface, and the network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0152] Embodiments of the present application can achieve in-depth exploration of the capabilities of debt collectors and accurate tracing of historical performance by comprehensively considering the comprehensive information of debt collectors and historical case data. By preprocessing to construct a debt collector database, a solid data foundation is provided for subsequent analysis. Further, by analyzing the influencing factors of the historical case data stored in the database, the correlation between case characteristics and collection effects is quantified, solving the problem that existing allocation methods ignore case characteristics. Combining the initial weight factors of debt collectors, the weight factors calculated using the analytic hierarchy process not only reflect the basic capabilities and experience of debt collectors but also incorporate considerations of case characteristics, achieving an accurate match between debt collectors and cases. This innovative allocation model effectively avoids the hierarchical transmission of information and the loss of key information, significantly improving the allocation efficiency and decision-making accuracy. In summary, the technical solution of the present application effectively solves the problems existing in the existing debt collection case allocation method, such as cumbersome processes, distorted information transmission, low allocation efficiency, and mismatch between debt collectors and cases. Through the solution of the present application, accurate case allocation can be achieved, thereby improving the collection efficiency and success rate.

[0153] The present application also provides another implementation manner, that is, to provide a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor, so that at least one processor executes the steps of the case allocation method as described above.

[0154] Embodiments of the present application can achieve in-depth exploration of the capabilities of debt collectors and accurate tracing of historical performance by comprehensively considering the comprehensive information of debt collectors and historical case data. By preprocessing to construct a debt collector database, a solid data foundation is provided for subsequent analysis. Further, by analyzing the influencing factors of the historical case data stored in the database, the correlation between case characteristics and collection effects is quantified, solving the problem that existing allocation methods ignore case characteristics. Combining the initial weight factors of debt collectors, the weight factors calculated using the analytic hierarchy process not only reflect the basic capabilities and experience of debt collectors but also incorporate considerations of case characteristics, achieving an accurate match between debt collectors and cases. This innovative allocation model effectively avoids the hierarchical transmission of information and the loss of key information, significantly improving the allocation efficiency and decision-making accuracy. In summary, the technical solution of the present application effectively solves the problems existing in the existing debt collection case allocation method, such as cumbersome processes, distorted information transmission, low allocation efficiency, and mismatch between debt collectors and cases. Through the solution of the present application, accurate case allocation can be achieved, thereby improving the collection efficiency and success rate.

[0155] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of the present application.

[0156] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The accompanying drawings show the preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields is similarly within the scope of the patent protection of the present application. The non-company enterprise software tools or components that appear in the embodiments of the present application are only introduced by way of example and do not represent actual use.

Claims

1. A case allocation method, characterized in that: The steps include: Obtain comprehensive employee information of multiple debt collectors and historical case data of multiple historical cases; Pre-processing the comprehensive information of the staff and the historical case data to build a debt collector database; Performing an influencing factor analysis on the historical case data stored in the debt collector database to obtain data analysis results for each debt collector; Obtaining an initial weight factor of each debt collector, wherein the initial weight factor represents the basic debt collection ability and experience level of each debt collector; According to the initial weight factor and the data analysis result, a preset hierarchical analysis method is used to calculate the weight factor of each debt collector, and the weight factor is used to guide the allocation of new debt collection cases; When target case data of a plurality of cases to be assigned are received, the plurality of cases to be assigned are assigned to the plurality of debt collectors according to the target case data and the weight factors.

2. The method according to claim 1, characterized in that The step of preprocessing the comprehensive information of the staff and the historical case data to construct a database of debt collectors specifically includes: Normalizing the numerical data in the employee comprehensive information and the numerical data in the historical case data respectively to obtain standard numerical data corresponding to the employee comprehensive information and standard case data corresponding to the historical case data; Classifying and encoding the text data in the employee comprehensive information and the text data in the historical case data to obtain category data corresponding to the employee comprehensive information and category case data corresponding to the historical case data; Obtain the preset database table structure and preset data integration rules; The standard numerical data, the standard case data, the category data and the category case data are stored in a relational database management system according to the database table structure and the data integration rules to obtain a debt collector database.

3. The method according to claim 2, characterized in that The step of analyzing the influencing factors of the historical case data stored in the debt collector database to obtain the data analysis results of each debt collector specifically includes: Extracting features from the historical case data in the debt collector database to obtain multiple historical case feature information; Obtaining the collection effect index of each debt collector in the corresponding historical collection cases; A pre-trained data analysis model is used to perform feature impact analysis on the feature information of the multiple historical cases and the collection effect indicators to obtain data analysis results for each collection officer.

4. The method according to claim 1, characterized in that: The step of obtaining the initial weight factor of each debt collector specifically includes: Obtaining evaluation scores corresponding to multiple evaluation dimensions of each debt collector; Obtaining historical performance data of each debt collector, using a pre-trained regression model to perform performance evaluation on the historical performance data, and obtaining a performance score of each debt collector; Obtaining a first weight coefficient of the evaluation score and a second weight coefficient of the performance score; An initial weight factor for each debt collector is determined based on the evaluation score, the first weight coefficient, the performance score, and the second weight coefficient.

5. The method according to claim 4, characterized in that The step of calculating the weight factor of each debt collector by using a preset hierarchical analysis method according to the initial weight factor and the data analysis result specifically includes: Based on the initial weight factors, a first judgment matrix of each debt collector is constructed by using a hierarchical analysis method; Based on the data analysis results, the hierarchical analysis method is used to construct the second judgment matrix of each debt collector; Using a preset weight vector calculation method, respectively calculate a first weight vector corresponding to the first judgment matrix and a second weight vector corresponding to the second judgment matrix; The first weight vector and the second weight vector are synthesized to obtain a weight factor of each debt collector.

6. The method according to claim 1, characterized in that The step of allocating the multiple cases to be allocated to the multiple debt collectors according to the target case data and the weight factor specifically includes: Comparing the target case data with the weight factor to obtain a comparison result; According to the comparison result, the multiple cases to be assigned are assigned to the multiple debt collectors.

7. The method according to claim 6, characterized in that The step of comparing the target case data with the weight factor to obtain a comparison result specifically includes: Based on the overdue amount of the target case data, the multiple cases to be assigned are sorted in descending order to obtain a sequence of cases to be assigned; Based on the values ​​of the weight factors, the plurality of debt collectors are sorted in descending order to obtain a debt collector sequence; Comparing the sequence of cases to be assigned with the sequence of debt collectors to obtain a comparison result; The step of assigning the plurality of cases to be assigned to the plurality of debt collectors according to the comparison result specifically includes: Based on the comparison result, the multiple cases to be assigned are sequentially assigned to the corresponding collectors in the collection sequence according to the arrangement order of the cases to be assigned in the case to be assigned sequence and the arrangement order of the collectors in the collection sequence.

8. A case allocation device, characterized in that: include: A first acquisition module is used to acquire comprehensive employee information of multiple debt collectors and historical case data of multiple historical cases; A preprocessing module, used to preprocess the comprehensive information of the staff and the historical case data to build a debt collector database; An analysis module, used to analyze the influencing factors of the historical case data stored in the debt collector database to obtain data analysis results for each debt collector; A second acquisition module is used to acquire an initial weight factor of each debt collector, wherein the initial weight factor represents the basic debt collection ability and experience level of each debt collector; A calculation module, used to calculate the weight factor of each debt collector according to the initial weight factor and the data analysis result by using a preset hierarchical analysis method, wherein the weight factor is used to guide the allocation of new debt collection cases; The allocation module is used to allocate the multiple cases to be allocated to the multiple debt collectors according to the target case data and the weight factors when receiving the target case data of the multiple cases to be allocated.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the case allocation method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the case allocation method according to any one of claims 1 to 7 are implemented.

Images