Credit customer complaint processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a credit customer complaint processing method and device, electronic equipment and a storage medium, and relates to the intelligent customer service technology, and the method comprises the steps: determining a target customer complaint type according to customer complaint information of a user; obtaining a credit record and a credit behavior related to the target customer complaint type, and determining a credit score of the user in the target customer complaint type based on the credit record and the credit behavior; and generating a target customer complaint scheme according to the credit score, so as to process customer complaints of the user through the target customer complaint scheme. According to the method, the credit condition of the user can be accurately judged through the current credit score in a mode of performing credit scoring on the user in the target customer complaint type by acquiring the multi-dimensional data related to the credit record and the credit behavior; therefore, the customer complaint problem of the user is effectively solved in time according to the corresponding target customer complaint scheme under the current credit score, and the beneficial effects of improving the customer complaint processing efficiency and improving the service experience of the user are achieved.

Description

Technical Field

[0001] The present application relates to the field of intelligent customer service technology, and in particular to a credit customer complaint processing method, device, electronic device and storage medium. Background Art

[0002] As people's pace of life accelerates, users increasingly expect that questions or demands raised about products or services can be quickly resolved. Based on this, the emergence of intelligent customer service has improved the efficiency of handling some customer complaints in various industries. The processing method of intelligent customer service is generally to handle the user's current customer complaint based on a preset reply or a reply generated by artificial intelligence.

[0003] In the financial field, existing intelligent customer service can only solve some simple customer complaints, such as contract issues, credit impact issues, etc. When it comes to complex customer complaints related to the amount of money (such as collection issues involving large amounts or credit limit issues, etc.), manual customer service is required to create a customer complaint ticket according to the corresponding customer complaint type, and then assign the customer complaint ticket to the corresponding business personnel for processing. After the business personnel handle the ticket, they will return the processing results to the manual customer service node, and the manual customer service will reply to the user with the customer complaint processing results.

[0004] However, when handling the above-mentioned complex customer complaints, the processing process is long and requires human participation at multiple nodes. The case processing time is long, which affects the user experience. Summary of the invention

[0005] The present application provides a credit customer complaint handling method, device, electronic device and storage medium, which can improve the efficiency of credit customer complaint handling and enhance the user service experience.

[0006] In a first aspect, the present application provides a method for handling credit customer complaints, comprising: determining a target customer complaint type based on a user's customer complaint information; obtaining a credit record and credit behavior related to the target customer complaint type, and determining a credit score of the user in the target customer complaint type based on the credit record and the credit behavior; generating a target customer complaint plan based on the credit score, so as to handle the user's customer complaint through the target customer complaint plan.

[0007] In a second aspect, the present application provides a credit customer complaint processing device, the device comprising:

[0008] A type determination module is used to determine the target customer complaint type based on the user's customer complaint information;

[0009] A score determination module, used to obtain the credit record and credit behavior related to the target customer complaint type, and determine the credit score of the user in the target customer complaint type based on the credit record and the credit behavior;

[0010] A solution generation module is used to generate a target customer complaint solution according to the credit score, so as to handle the customer complaint of the user according to the target customer complaint solution.

[0011] In a third aspect, the present application further provides an electronic device, the electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the credit customer complaint handling method described in any embodiment of the present application.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the credit customer complaint handling method described in any embodiment of the present application when executed.

[0016] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the credit customer complaint handling method described in any embodiment of the present application.

[0017] The credit customer complaint handling solution provided in the embodiment of the present application first determines the target customer complaint type based on the user's customer complaint information, and by classifying the credit customer complaints, when handling customer complaints of different credit types, the credit records and credit behaviors required to be obtained are different. By obtaining the credit records and credit behaviors related to the target credit type, a foundation is laid for improving the efficiency of customer complaint handling; further based on the obtained credit records and credit behaviors, the credit score of the user in the target customer complaint type is determined, so as to generate the relevant target customer complaint solution based on the credit score. The solution provided in this embodiment, by obtaining multi-dimensional data related to credit records and credit behaviors to score the user's credit in the target customer complaint type, the current credit score can accurately judge the user's credit situation, and then timely and effectively solve the user's customer complaint problem according to the corresponding target customer complaint solution under the current credit score, thereby achieving the beneficial effects of improving the efficiency of customer complaint handling and improving the user's service experience.

[0018] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the credit customer complaint processing device, or may be packaged separately from the processor of the credit customer complaint processing device, and this application does not limit this.

[0019] The description of the second, third, fourth and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the second, third, fourth and fifth aspects described in this application can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description.

[0021] It is understandable that before using the technical solutions disclosed in the embodiments of this application, the type, scope of use, and usage scenarios of the personal information involved in this application should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a flowchart of a method for handling credit customer complaints provided by an embodiment of the present application;

[0024] Figure 2 is another flowchart of the credit customer complaint handling method provided in the embodiment of the present application;

[0025] Figure 3 It is a structural schematic diagram of a credit customer complaint processing device provided in an embodiment of the present application;

[0026] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the present application will be clearly and completely described below in conjunction with the drawings in the present embodiment. Obviously, the described embodiment is only a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0030] Figure 1 This is a flow chart of a method for handling customer complaints about credit provided by an embodiment of the present application. This embodiment can be applied to customer complaints about credit involving amounts in the financial field. This method can be executed by a customer complaint handling device for credit, which can be implemented in the form of hardware and / or software and integrated in an electronic device that executes this method. Preferably, the electronic device in the embodiment of the present application can be a server, or a computer device, etc.

[0031] refer to Figure 1 The credit customer complaint handling method of this embodiment includes but is not limited to the following steps:

[0032] S110. Determine a target customer complaint type according to the user's customer complaint information.

[0033] Credit customer complaints indicate demands made by users to financial institutions. The current demands can be complaints (i.e., complaints about customer service visits or product usage, such as complaints about customer service's collection attitude, etc.), or demands (i.e., demands for improvements to related functions or other aspects of a product, such as demands for lowering credit interest rates or increasing credit limits, etc.). The specific credit types indicated in this embodiment are not limited here.

[0034] Among them, the above-mentioned customer complaint information can be generated by the user calling the fixed-line phone of the financial institution, or by the user submitting text, pictures, and / or recordings on the fixed customer complaint interface. The specific method of obtaining customer complaint information is not limited here.

[0035] For the currently received customer complaint information, the customer complaint system will identify the customer complaint voice or customer complaint text to identify and classify the current customer complaint information, and identify different types of credit customer complaints, such as the current customer complaint type can include loan amount type, loan interest rate type, collection type, or consultation type. For the customer complaint type generated through the customer complaint interface, the customer complaint system will generate a customer complaint work order based on the customer complaint content, customer complaint type, required call back time, call back phone number and other information that can be identified by user information, so as to facilitate the subsequent customer service specialist to follow up according to the customer complaint work order; for the customer complaint generated by the customer through the incoming call, it can be processed in real time, such as real-time analysis and processing of the customer complaint voice through voice recognition technology, and using natural language processing algorithms to identify and determine the target customer complaint type of the user's complaint, such as overdue repayment, interest rate dispute, service dissatisfaction, etc. It should be noted that whether the customer complaint information is generated by the user through an incoming call or by submitting the customer complaint information on the relevant customer complaint interface, the credit customer complaint processing solution provided in this embodiment can be used to improve the efficiency of handling user customer complaints.

[0036] S120: Obtain credit records and credit behaviors related to the target customer complaint type, and determine the user's credit score in the target customer complaint type based on the credit records and credit behaviors.

[0037] This embodiment specifically refers to the situation of handling customer complaints involving amounts and other related types in financial institutions, such as collection types and loan types, where loan types can include loan interest rates and loan amounts, etc. For collection-type customer complaints, it may involve complaints about the customer service staff's collection attitude or collection methods, and may also involve demands for caching, suspension of collection, or reduction of interest and fees; for loan interest rates, it may involve demands for lowering loan interest rates; for loan amounts, it may involve demands for increasing loan amounts, etc. Based on this, the improved solution of this embodiment obtains credit records and credit behaviors related to the target customer complaint type when the customer complaint type is different. The purpose of this is to obtain corresponding credit records and credit behaviors according to the corresponding data system by linking with the data system related to the target customer complaint type, thereby improving data acquisition efficiency and laying a foundation for improving customer complaint handling efficiency.

[0038] Exemplarily, taking the collection type as an example, the credit records corresponding to the collection type at least include arrears records (recording the user's current arrears amount, arrears time, etc.), overdue records (recording the number of overdue repayments, overdue days, and other detailed information) and collection records (recording the user's response during the collection process, including whether to cooperate with the collection, the collection results, etc.); the credit behavior corresponding to the collection type may at least include post-loan consumption behavior (in the case of arrears records and overdue records, the user's post-loan consumption behavior, whether it includes large-amount consumption, etc.), post-loan income behavior (used to evaluate the user's repayment ability, etc.). Specifically in the collection type, the specific content contained in the corresponding credit records and credit behaviors is not limited here.

[0039] When determining the credit score of a user in the target customer complaint type based on credit records and credit behaviors, a credit scoring model can be trained by using data mining and machine learning algorithms to evaluate the credit risk of the user in the target customer complaint type through the credit scoring model; the evaluation result is presented in the form of a credit score, which comprehensively considers factors such as the user's credit status, repayment ability, and borrowing behavior. Among them, the current machine learning algorithm can be a support vector machine algorithm, a neural network algorithm, a decision tree algorithm, or a gradient boosting algorithm, etc., and the specific algorithm type of the machine learning algorithm is not limited here.

[0040] Specifically, taking the collection type as an example, the method for determining the credit score of the user in the target customer complaint type based on the credit record and credit behavior can be, according to the overdue record and the collection record, the first weight corresponding to the credit record is determined; then the second weight corresponding to the credit behavior is determined according to the post-loan consumption behavior and the post-loan income behavior; the credit scoring model parameters are adjusted by the first weight and the second weight to obtain an updated credit scoring model; finally, the overdue record, the collection record, the post-loan consumption behavior and the post-loan income behavior are input into the updated credit scoring model to obtain the credit score of the user in the target customer complaint type; optionally, the method for determining the credit score of the user in the target customer complaint type based on the credit record and the credit behavior can also be, first, according to the user's arrears record, the first sub-parameter is determined, and the parameter comprehensively considers the amount of arrears and the length of arrears; secondly, according to the overdue record, the second sub-parameter is determined, and the parameter reflects the frequency of the user's overdue repayment and the length of time the overdue payment lasts. On this basis, the first weight about the credit record is obtained by combining the first sub-parameter with the second sub-parameter; the user's post-loan income behavior and post-loan consumption behavior are further analyzed to determine the second weight, and the second weight reveals the user's consumption habits and financial status. In addition, variable factors can be determined based on the user's collection records during the collection process, and the variable factors can reflect the user's reaction to the collection and willingness to repay; the first weight and the second weight are then dynamically adjusted through the variable factors to obtain the first updated weight and the second updated weight, so as to adjust the credit scoring model parameters according to the first updated weight and the second updated weight to obtain an updated credit scoring model; finally, the arrears record, overdue record, collection record, post-loan consumption behavior and post-loan income behavior are input into the updated credit scoring model, and the user's credit score in the collection type is obtained through precise calculation of the model.

[0041] The credit score in this embodiment can be expressed in a specific scoring form, or in the form of excellent [100, 90], good (90, 80], medium (80, 70], and unsatisfactory (<70). The expression form of the credit score result is not limited here.

[0042] The solution provided in this embodiment integrates the credit records and credit behaviors corresponding to different credit types to achieve real-time updates of the user's credit score in the target credit type, thereby more accurately reflecting the user's credit status in different credit types, helping financial institutions to better manage credit risks, and also providing users with more fair and reasonable credit services. This process not only ensures the accuracy and timeliness of credit scores, but also provides financial institutions with more refined and personalized credit risk assessment methods, which helps to optimize credit management and improve service quality.

[0043] S130. Generate a target customer complaint solution according to the credit score to handle the user's customer complaint through the target customer complaint solution.

[0044] According to different credit types and credit scores, this embodiment combines the pre-set customer complaint handling rules to automatically generate corresponding customer complaint solutions for the user. Taking the customer complaint type as the collection type as an example, the corresponding customer complaint solution includes but is not limited to adjusting the repayment plan, reducing interest and fees, stopping or delaying collection; for the loan type, the corresponding customer complaint solution includes but is not limited to providing interest rate discounts, increasing loan amounts or improving service measures.

[0045] Exemplarily, this embodiment provides a specific embodiment, taking the customer complaint information received from user A as an example, by processing and analyzing the customer complaint information and identifying keywords such as "arrears" and "overdue", it can be clarified that the target customer complaint type of user A is the collection type; further, it is obtained that the amount of arrears of user A is 50,000 yuan, and the number of overdue days of user A is 7 days. During the overdue process, the customer service staff carried out two collections, and the collection records show that the user's attitude is to cooperate with the collection; further evaluate the user's post-loan income and post-loan consumption, and determine that the user is overdue for the first time, and the post-loan consumption of this amount of arrears focuses on hospitals, or mortgages, etc.; based on this, after evaluation by the credit scoring model, the corresponding credit score is 82 points, indicating that the historical credit situation is good and has a better repayment ability. The target customer complaint solution generated for this type of user can be to generate a processing solution for interest reduction and exemption based on the current loan interest rate, so that user A can repay the loan as soon as possible.

[0046] The credit customer complaint handling method provided in this embodiment first determines the target customer complaint type based on the customer complaint information of the user, and by classifying the credit customer complaints, when handling customer complaints of different credit types, the credit records and credit behaviors required to be obtained are different. By obtaining the credit records and credit behaviors related to the target credit type, a foundation is laid for improving the efficiency of customer complaint handling; further based on the obtained credit records and credit behaviors, the credit score of the user in the target customer complaint type is determined, so as to generate the relevant target customer complaint solution according to the credit score. The solution provided in this embodiment, by obtaining multi-dimensional data related to credit records and credit behaviors to score the user in the target customer complaint type, the current credit score can accurately judge the user's credit situation, and then timely and effectively solve the user's customer complaint problem according to the corresponding target customer complaint solution under the current credit score, thereby achieving the beneficial effect of improving the efficiency of customer complaint handling and improving the user service experience.

[0047] Figure 2It is another flow chart of the credit customer complaint handling method provided by an embodiment of the present application. The embodiment of the present application is optimized on the basis of the above embodiments. The specific optimization is as follows: This embodiment explains in detail the relevant implementation process of "determining the target customer complaint type according to the user's customer complaint information" in the above embodiments, the relevant implementation process of "determining the credit score of the user in the target customer complaint type based on the credit record and the credit behavior", and the relevant implementation process of "generating a target customer complaint solution according to the credit score".

[0048] See also Figure 2 The credit customer complaint handling method of this embodiment includes but is not limited to the following steps:

[0049] S210: Perform text processing on the customer complaint information to obtain multiple test segments.

[0050] When the received customer complaint information is a customer complaint voice, semantic conversion is first performed to obtain the customer complaint text, and further text processing is performed to obtain multiple test segments; when the customer complaint information is submitted text information, text processing is directly performed on the text information to obtain the test segments.

[0051] In this embodiment, the text processing method includes at least text conversion, word segmentation, stop word removal, keyword extraction and other processing operations. The multiple test segments obtained can be "collection", "service attitude", "very dissatisfied", "increase credit limit", etc., so as to quickly and accurately determine the user's customer complaint type through text processing, providing a basis for subsequent data acquisition.

[0052] S211 , extracting the word feature to be tested corresponding to each word segment to be tested, and sequentially comparing each word feature to be tested with a plurality of preset word features in a standard database.

[0053] The features of the words to be tested corresponding to each word segment to be tested may include word frequency, part of speech, contextual relationship, etc. The method of extracting the features of the words to be tested corresponding to each word segment to be tested may be implemented by a word vector model applied in the credit field.

[0054] The standard database indicates a database storing standard word features corresponding to multiple types of customer complaints; wherein one customer complaint type corresponds to multiple preset word features; taking the collection customer complaint type as an example, the corresponding multiple preset word features may include word features corresponding to "service", "attitude", "grace period", "number of days", "collection" and "interest and fees" respectively; taking the credit customer complaint type as an example, the corresponding multiple preset word features may include word features corresponding to "reduction", "interest rate", "limit" and "increase" respectively. The specific content of the preset word features corresponding to each customer complaint type in the standard database is not limited here.

[0055] In this embodiment, the method of sequentially comparing each feature of the word to be tested with multiple preset word features in the standard database can be by performing a string comparison between each feature of the word to be tested and multiple preset word features; or, converting each feature of the word to be tested into a word vector to be tested, converting multiple preset word features into preset word vectors, and then calculating the similarity between each word vector to be tested and multiple preset word vectors, etc.

[0056] S212: When the feature of the current word to be tested is consistent with the feature of the current preset word, determine the customer complaint type corresponding to the feature of the current preset word as the target customer complaint type.

[0057] In this embodiment, if the feature of the word to be tested, "customer service collection attitude", is consistent with the preset feature of the word "collection attitude" in the standard database, the target customer complaint type is determined to be the collection customer complaint type.

[0058] Another optional method, in order to improve the accuracy of determining the customer complaint type, the method for determining the target customer complaint type in this embodiment can also be to compare the test word features corresponding to multiple test word segments with multiple preset word features corresponding to each customer complaint type in turn, to obtain the similarity results between the current customer complaint information and each customer complaint type, and determine the customer complaint type with the highest similarity result as the target customer complaint type.

[0059] S220. Retrieve the user's collection records, and determine whether the collection actions are compliant based on the collection records.

[0060] Taking the target customer complaint type as the collection type as an example, before obtaining the user's corresponding credit record and credit behavior under the collection type, first retrieve the user's collection record. The current collection record includes the collection timing, collection method, collection result, collection recording or collection SMS sent by the customer service when collecting from the user. First, based on the collection record, check whether the customer service's collection action is compliant. Current compliance may include that when the customer first collects, according to regulatory requirements, the customer has a three-day grace period. If collection is carried out within the three-day grace period, it is not in compliance with the regulations, and the third-party contact information left by the customer can only be notified to collect when the number of overdue days meets the conditions and the customer himself cannot be contacted continuously.

[0061] If it is determined according to the collection record that the collection action is not compliant, that is, no, then execute step S221; if it is determined according to the collection record that the collection action is compliant, that is, yes, then execute step S230.

[0062] S221. Processing user complaints based on preset strategies.

[0063] The current preset strategy is to automatically generate a plan to stop or postpone collection when the collection action is not compliant. For example, if the user is collecting debts for the first time, but the customer service calls or sends text messages to collect debts within three days, after receiving the user's customer complaint, the preset strategy can be determined to stop collection; if the user is not collecting debts for the first time, but the customer service's collection action is not compliant, after receiving the user's customer complaint, the preset strategy can be determined to postpone collection; specifically, when the preset strategy is cache, the number of days for postponement can be further generated. The current specific number of days for postponement is related to the number of times the user has been collected. For example, if the user has been collected once in history, the preset strategy can be postponed for seven days; if the user has been collected 2-3 times in history, the preset strategy can be postponed for five days; if the user has been collected 3 times or more in history, the preset strategy can be postponed for three days, etc.; the specific way to handle user complaints based on the preset strategy is not limited here.

[0064] This embodiment sets a standardized collection process so that when the customer complaint type is determined to be a collection type, the compliance of the collection action can be automatically verified. When it is determined that the customer service's collection action is not compliant, it can automatically trigger the generation of a plan to stop or delay collection, so as to improve the efficiency of customer complaint handling.

[0065] S230. Determine a first weight corresponding to the credit record according to the user's debt record, overdue record, and collection record within the first time period.

[0066] In this embodiment, the credit records corresponding to the collection type include arrears records, overdue records and collection records. Arrears records indicate the current amount of a user's arrears and the length of time the arrears last, etc.; overdue records refer to situations where the user fails to repay the loan in a timely manner as agreed in the contract within the first time period, which can be used to evaluate the customer's historical creditworthiness; collection records refer to relevant records of collection measures taken by financial institutions due to the user's overdue loan repayment, which can be used to evaluate the customer's cooperation; among them, the current first time period can be from the current time period to the time when the customer first generates a credit record, so as to better grasp the user's creditworthiness; optionally, if the first time period is longer, such as more than 5 years, priority is given to selecting records from the current time period to the past three years, etc., or records within one year, etc., so as to better characterize the user's recent historical creditworthiness, etc., and the selection of the specific first time period is not restricted here.

[0067] In this embodiment, the credit score of the user in the collection type is calculated more accurately by dynamically allocating weights. The specific method can be: quantify the arrears records, overdue records and collection records in the first time period respectively; determine the first weight corresponding to the credit record according to the quantified data. Optionally, before determining the first weight, the arrears weight of the arrears record in the credit record, the overdue weight of the overdue record in the credit record, and the collection weight of the collection record in the credit record can be determined in advance, and the sum of the arrears weight, overdue weight and collection weight is 1. The specific method can be: quantify the arrears record according to the amount of arrears and the duration of arrears to obtain the arrears quantification value; quantify the overdue record according to the number of overdue times and the duration of overdue times to obtain the overdue quantification value; quantify the collection record according to the number of collections and the collection success situation to obtain the collection quantification value; and the arrears quantification value is proportional to the arrears weight; the overdue weight is proportional to the overdue quantification value; the collection weight is proportional to the collection quantification value. Specifically, the weight of arrears, the weight of overdue payments and the weight of collection can be obtained by optimizing the allocation through machine learning algorithms.

[0068] Furthermore, when determining the first weight based on the debt weight associated with the debt record, the overdue weight associated with the overdue record, and the collection weight associated with the collection record, a time decay factor can be introduced, that is, recent overdue and collection events have a greater impact on the score, while early events have a smaller impact on the score, thereby determining the first weight through a machine learning algorithm.

[0069] S231. Determine a second weight corresponding to the credit behavior based on the user's post-loan consumption behavior and post-loan income behavior in the second time period.

[0070] In this embodiment, the credit behaviors corresponding to the collection type include post-loan consumption behaviors and post-loan income behaviors. Post-loan consumption behaviors refer to consumption activities performed by users after obtaining loans, such as shopping and paying bills, which can be used to evaluate the consumption of users; post-loan income behaviors refer to the income generated by users after obtaining loans, such as salary income and investment income, which can be used to evaluate the loan repayment ability of users. The current second time period can be from the time period corresponding to the overdue to the current time period, or from the time when the overdue consumption occurs to the current time period, etc.; the selection of the specific second time period is not limited here.

[0071] Optionally, when determining the second weight, the corresponding consumption type weight can be determined by analyzing the post-loan consumption behavior, that is, different types of consumption have different impacts on the score, such as luxury consumption has a greater impact on the score, and daily consumption has a smaller impact on the score; thereby, based on the machine learning algorithm, the consumption behavior corresponding to the post-loan consumption type and the post-loan income behavior are comprehensively calculated to determine the second weight.

[0072] In this embodiment, the sum of the first weight and the second weight is 1.

[0073] S232. Adjust the credit scoring model parameters according to the first weight and the second weight to obtain an updated credit scoring model.

[0074] In this embodiment, the credit scoring model is obtained by a gradient descent algorithm or a genetic algorithm to achieve accurate adjustment of the parameters corresponding to the first weight and the second weight. In this embodiment, by dynamically adjusting the weights corresponding to the credit record and the credit behavior to update the credit scoring model, the accuracy and reliability of the credit score can be improved, and the accurate prediction of the user's credit score can be achieved.

[0075] S233. Input the arrears record, overdue record, collection record, post-loan consumption behavior and post-loan income behavior into the updated credit scoring model to obtain the user's credit score.

[0076] Furthermore, after obtaining an updated credit scoring model, the current user's corresponding debt records, overdue records, collection records, post-loan consumption behaviors and post-loan income behaviors are input into the updated credit scoring model. Optionally, before inputting into the updated credit scoring model, the debt records, overdue records, collection records, post-loan consumption behaviors and post-loan income behaviors may be extracted in advance through features to obtain corresponding feature values, so as to output the user's credit score after inputting the feature values ​​corresponding to the debt records, overdue records, collection records, post-loan consumption behaviors and post-loan income behaviors into the updated credit scoring model.

[0077] S240. Retrieve the collection scoring rule library.

[0078] In this embodiment, the collection scoring rule library can be retrieved through a preset interface, and the rule library contains multiple scoring intervals, each of which corresponds to a specific customer complaint solution. For example, the rule library may contain the following correspondence between scoring intervals and customer complaint solutions: scoring interval 1 [100, 90]: customer complaint solution A, interest reduction and exemption; scoring interval 2 (90, 80]: customer complaint solution B, stop collection; scoring interval 3 (80, 70]: customer complaint solution C, delay collection; scoring interval 4 (<70): customer complaint solution D, maintain the original collection method, etc.

[0079] Optionally, the collection scoring rule base provided in this embodiment can also be dynamically updated. For example, during the collection process, the system can dynamically adjust the correspondence between the scoring interval and the customer complaint solution according to the actual effect. For example, if it is found that the customer complaint solution for a certain scoring interval is not effective, the system can adjust the customer complaint solution corresponding to the scoring interval, so that each time the collection scoring rule base is retrieved, the latest correspondence between the scoring interval and the customer complaint solution will be obtained.

[0080] S241. Determine a target score range from a collection score rule library based on the credit score.

[0081] For example, if the credit score is 72 points, the target score interval is (80, 70]. Optionally, for the current user's credit score, the target score interval can also be determined from multiple score intervals corresponding to the latest updated collection score rule library.

[0082] S242. Determine the customer complaint solution corresponding to the target scoring range as the target customer complaint solution.

[0083] Based on the above example, when the target score interval is (80, 70], the corresponding target customer complaint solution is to delay the collection.

[0084] S243. Handle user complaints through targeted customer complaint solutions.

[0085] When handling user complaints according to the target customer complaint plan, if the target customer complaint plan is to defer collection, a further output handling plan is to defer collection for N days. The specific value of N is based on the model output result, so as to remind customer service personnel to follow up again after the preset number of days, and then update the corresponding overdue records and collection records according to the follow-up results.

[0086] In another implementation, the solution provided in this embodiment can also predict future collection results based on the customer's historical collection records, for example, by analyzing the customer's transaction habits, predicting the customer's likely response to collection, and thus adjusting the timing and method of collection. By formulating strategies for stopping, delaying, or reducing interest and fees in advance, it helps to reduce unnecessary collection behavior and improve collection efficiency.

[0087] When the customer complaint type is determined to be a collection type, this embodiment can assist financial institutions in predicting the borrower's default risk through credit scoring, which helps financial institutions take timely measures to reduce bad debt risks. Based on the borrower's default probability, the credit score can be used to obtain different collection strategies. For high-risk customers, more aggressive collection measures can be taken, while for low-risk customers, a more gentle approach can be taken to improve collection efficiency. For high-risk customers, the credit limit and interest rate can be adjusted, or collection measures can be taken in advance to reduce risks. For low-risk customers, more credit limits and more favorable interest rates can also be given to increase business development.

[0088] Another preferred embodiment, the credit customer complaint handling solution provided in this embodiment, when the target customer complaint type is a credit limit type or an interest rate type, the credit record includes loan records, consumption records and personal credit information; the credit behavior includes pre-loan customer behavior, mid-loan customer behavior and post-loan customer behavior. Then the solution provided by this embodiment, when the target customer complaint type is determined to be a loan type in the above S210~S212, further, in this embodiment, the loan type includes a credit limit type or an interest rate type; then the implementation method of "obtaining the credit record and credit behavior related to the target customer complaint type, and determining the credit score of the user in the target customer complaint type based on the credit record and the credit behavior" provided by the above embodiment can be: determining a third weight about the user's repayment ability according to the loan record, consumption record and personal credit information; determining a fourth weight about the user's creditworthiness according to the pre-loan customer behavior, the mid-loan customer behavior and the post-loan customer behavior, and the sum of the third weight and the fourth weight is 1; adjusting the credit scoring model parameters according to the third weight and the fourth weight to obtain an updated credit scoring model; inputting the loan record, consumption record, personal credit information, the pre-loan customer behavior, the mid-loan customer behavior and the post-loan customer behavior into the updated credit scoring model to obtain the user's credit score.

[0089] In this embodiment, the loan record includes the user's loan type, amount, term, repayment status, etc. in the past period of time; the consumption record is used to reflect the user's consumption habits and consumption capacity over a period of time, including at least credit card consumption, shopping consumption, and third-party payment platform consumption; personal credit information includes the user's credit history, credit limit, overdue status, and may also include credit status, etc.

[0090] When determining the third weight based on loan records, consumption records and personal credit information, the third weight is set higher for users with good repayment and credit, and lower otherwise, according to the user's repayment situation.

[0091] Pre-loan customer behavior includes the activity of the mobile terminal before the user applies for a loan (such as IP address, used to determine whether it is a fixed customer with normal activities), contact information (the number of contacts can reflect whether the user is a normal user), mobile application list records (by querying whether other software is included, it can be determined whether the user is a high-quality customer), GPS location change records, etc. Pre-loan customer behavior can be used to preliminarily screen whether the current user is a malicious borrower. If so, the current customer complaint will be rejected. It can also include the number of loan applications and the purpose of the loan; the customer behavior during the loan includes the repayment progress, loan usage, repayment method and loan adjustment of the user during the loan process on the basis of the pre-loan customer behavior; the customer behavior after the loan includes the post-loan web browsing information, post-loan consumption behavior, number of loan delinquencies and amount of loan delinquencies on the basis of the pre-loan customer behavior.

[0092] In this embodiment, when determining the fourth weight regarding the user's creditworthiness based on pre-loan customer behavior, mid-loan customer behavior, and post-loan customer behavior, the fourth weight can be set higher for users with fewer overdue payments, and lower otherwise, based on the user's post-loan customer behavior.

[0093] Furthermore, when the target customer complaint type is a credit limit type or an interest rate type, this embodiment can improve the accuracy and reliability of the credit score by dynamically adjusting the weights corresponding to the credit record and credit behavior corresponding to the credit limit type or interest rate type to update the credit scoring model, thereby achieving accurate prediction of the user's credit score, so that the obtained credit score can more accurately represent the user's credit status.

[0094] Furthermore, when the target loan type is a credit limit type or an interest rate type, the specific implementation method of "generating a target customer complaint solution based on a credit score" in the above embodiment may be: determining the user's target credit limit based on the credit score and the current credit limit; or, determining the user's target credit interest rate based on the credit score and the current credit interest rate.

[0095] When the credit score is good, when the customer complaint information is of the credit limit type, the corresponding credit limit increase operation can be performed on the basis of the current credit limit to obtain the target credit limit. Specifically, the corresponding credit limit increase percentage can be set for different credit score intervals, so as to determine the target credit limit according to the target increase percentage corresponding to the target score interval where the current credit score is located. Or, when the credit score is good, when the customer complaint information is of the interest rate type, the corresponding interest rate reduction operation can be performed on the basis of the current credit interest rate to obtain the target credit interest rate, etc.

[0096] Optionally, when the target loan type is a credit limit type or an interest rate type, the solution provided in this embodiment may further include: obtaining the customer's historical loan application information before determining the third weight of the user's repayment ability based on the loan record, consumption record and personal credit information. When the application information corresponding to the application information is incomplete, the current target customer complaint solution may be a suggestion for supplementing the information. This is to remind the user to supplement the information according to the relevant suggestions, so as to facilitate the subsequent evaluation operation.

[0097] This embodiment determines the credit score of the user, which helps financial institutions to more accurately judge the credit risk of the applicant, thereby expanding the scope of credit business while reducing the risk. It can also assist financial institutions to quickly process a large number of credit applications, improve the efficiency of credit review, reduce the subjectivity of human judgment, and thus reduce credit risk.

[0098] Figure 3is a structural diagram of a credit customer complaint processing device provided in an embodiment of the present application, and the device is suitable for executing a credit customer complaint processing method provided in an embodiment of the present application. Figure 3 As shown, the device may specifically include: a type determination module 310, a score determination module 320 and a solution generation module 330, wherein:

[0099] A type determination module 310 is used to determine a target customer complaint type according to the user's customer complaint information;

[0100] A score determination module 320, configured to obtain a credit record and a credit behavior related to the target customer complaint type, and determine a credit score of the user in the target customer complaint type based on the credit record and the credit behavior;

[0101] The solution generation module 330 is used to generate a target customer complaint solution according to the credit score, so as to handle the customer complaint of the user according to the target customer complaint solution.

[0102] The credit customer complaint processing device provided in this embodiment first determines the target customer complaint type based on the customer complaint information of the user, and by classifying the credit customer complaints, when handling customer complaints of different credit types, the credit records and credit behaviors required to be obtained are different. By obtaining the credit records and credit behaviors related to the target credit type, a foundation is laid for improving the efficiency of customer complaint processing; further based on the obtained credit records and credit behaviors, the credit score of the user in the target customer complaint type is determined, so as to generate the relevant target customer complaint solution according to the credit score. The solution provided in this embodiment, by obtaining multi-dimensional data related to credit records and credit behaviors to score the user in the target customer complaint type, the current credit score can accurately judge the credit status of the user, and then timely and effectively solve the user's customer complaint problem according to the corresponding target customer complaint solution under the current credit score, thereby achieving the beneficial effect of improving the efficiency of customer complaint processing and improving the user service experience.

[0103] In one embodiment, when the target customer complaint type is a collection type, the credit record includes arrears records, overdue records and collection records; the credit behavior includes post-loan consumption behavior and post-loan income behavior.

[0104] The score determination module 320 includes a weight determination unit, a parameter updating unit and a score obtaining unit, wherein:

[0105] A weight determination unit, configured to determine a first weight corresponding to the credit record according to the arrears record, the overdue record and the collection record of the user within a first time period;

[0106] The weight determination unit is further used to determine a second weight corresponding to the credit behavior according to the post-loan consumption behavior and the post-loan income behavior of the user in a second time period, wherein the sum of the first weight and the second weight is 1;

[0107] a parameter updating unit, configured to adjust a credit scoring model parameter according to the first weight and the second weight to obtain an updated credit scoring model;

[0108] The score obtaining unit is used to input the arrears record, the overdue record, the collection record, the post-loan consumption behavior and the post-loan income behavior into the updated credit score model to obtain the credit score of the user.

[0109] In one embodiment, the solution generation module 330 includes a rule base retrieval unit, a target interval determination unit, and a target solution determination unit, wherein:

[0110] A rule library retrieval unit, used to retrieve a collection scoring rule library, in which a scoring interval corresponds to a customer complaint solution;

[0111] A target interval determination unit, configured to determine a target score interval from the collection score rule base according to the credit score;

[0112] The target solution determination unit is used to determine the customer complaint solution corresponding to the target scoring interval as the target customer complaint solution.

[0113] In one embodiment, the device further includes a record retrieval module and an action determination module, wherein:

[0114] A record retrieval module, used to retrieve the user's collection records and determine whether the collection action is compliant based on the collection records;

[0115] The action judgment module is used to execute the operation of obtaining the user's credit record and credit behavior if the collection action is compliant; if the collection action is not compliant, execute the operation of handling the user's customer complaint based on a preset strategy.

[0116] In one embodiment, when the target customer complaint type is a credit limit type or an interest rate type, the credit record includes a loan record, a consumption record, and personal credit information; the credit behavior includes pre-loan customer behavior, mid-loan customer behavior, and post-loan customer behavior.

[0117] The weight determination unit is further configured to determine a third weight regarding the repayment ability of the user according to the loan record, the consumption record and the personal credit information; determine a fourth weight regarding the creditworthiness of the user according to the pre-loan customer behavior, the mid-loan customer behavior and the post-loan customer behavior, wherein the sum of the third weight and the fourth weight is 1;

[0118] a parameter updating unit, further configured to adjust the credit scoring model parameters according to the third weight and the fourth weight to obtain an updated credit scoring model;

[0119] The score obtaining unit is further specifically used to input the loan record, the consumption record, the personal credit information, the pre-loan customer behavior, the mid-loan customer behavior and the post-loan customer behavior into the updated credit scoring model to obtain the credit score of the user.

[0120] In one embodiment, the solution generation module 330 is specifically configured to determine the target credit limit of the user according to the credit score and the current credit limit; or, determine the target credit interest rate of the user according to the credit score and the current credit interest rate.

[0121] In one embodiment, the type determination module 310 includes a text processing unit, a feature comparison unit, and a type determination unit, wherein:

[0122] A text processing unit, specifically used to perform text processing on the customer complaint information to obtain a plurality of test segments;

[0123] A feature comparison unit, specifically used to extract the feature of the word to be tested corresponding to each of the word segments to be tested, and sequentially compare each of the feature of the word to be tested with a plurality of preset word features in the standard database;

[0124] The type determination unit is specifically configured to determine that the customer complaint type corresponding to the current preset word feature is the target customer complaint type when the current to-be-tested word feature is consistent with the current preset word feature.

[0125] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0126] An embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the credit customer complaint handling method described in any embodiment of the present application.

[0127] An embodiment of the present application further provides a computer-readable medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the credit customer complaint handling method described in any embodiment of the present application when executed.

[0128] Reference below Figure 4 , Figure 4 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, and shows a schematic diagram of the structure of a computer system 500 suitable for implementing the electronic device in an embodiment of the present application. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0129] like Figure 4 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0130] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0131] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present application are executed.

[0132] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, etc., or any suitable combination of the above.

[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0134] The modules and / or units involved in the embodiments described in the present application may be implemented by software or hardware. The modules and / or units described may also be set in a processor, for example, it may be described as: a processor includes a type determination module, a score determination module, and a solution generation module. The names of these modules do not, in some cases, constitute limitations on the modules themselves.

[0135] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: determining a target customer complaint type according to the customer complaint information of the user; obtaining a credit record and credit behavior related to the target customer complaint type, and determining the credit score of the user in the target customer complaint type based on the credit record and the credit behavior; generating a target customer complaint solution according to the credit score, so as to handle the customer complaint of the user through the target customer complaint solution.

[0136] According to the technical solution of this embodiment, the target customer complaint type is first determined based on the customer complaint information of the user, and by classifying the credit customer complaints, when handling customer complaints of different credit types, the credit records and credit behaviors required to be obtained are different. By obtaining the credit records and credit behaviors related to the target credit type, the foundation is laid for improving the efficiency of customer complaint handling; further based on the obtained credit records and credit behaviors, the credit score of the user in the target customer complaint type is determined, so as to generate the relevant target customer complaint solution according to the credit score. The solution provided by this embodiment, by obtaining multi-dimensional data related to credit records and credit behaviors to score the user in the target customer complaint type, the current credit score can accurately judge the user's credit situation, and then timely and effectively solve the user's customer complaint problem according to the corresponding target customer complaint solution under the current credit score, and achieve the beneficial effect of improving the efficiency of customer complaint handling and improving the user service experience.

[0137] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for handling credit customer complaints, characterized in that: include: Determine the target customer complaint type based on the user’s customer complaint information; Acquire the credit record and credit behavior related to the target customer complaint type, and determine the credit score of the user in the target customer complaint type based on the credit record and the credit behavior; A target customer complaint solution is generated according to the credit score, so as to handle the customer complaint of the user through the target customer complaint solution.

2. The method for handling customer complaints of credit according to claim 1, characterized in that: When the target customer complaint type is a collection type, the credit record includes arrears records, overdue records and collection records; the credit behavior includes post-loan consumption behavior and post-loan income behavior; The determining the credit score of the user in the target customer complaint type based on the credit record and the credit behavior includes: Determine a first weight corresponding to the credit record according to the arrears record, the overdue record and the collection record of the user in a first time period; Determine a second weight corresponding to the credit behavior according to the post-loan consumption behavior and the post-loan income behavior of the user in a second time period, wherein the sum of the first weight and the second weight is 1; Adjust the credit scoring model parameters according to the first weight and the second weight to obtain an updated credit scoring model; The arrears record, the overdue record, the collection record, the post-loan consumption behavior and the post-loan income behavior are input into the updated credit scoring model to obtain the credit score of the user.

3. The method for handling customer complaints regarding credit according to claim 2, characterized in that: The generating of a target customer complaint solution according to the credit score comprises: Retrieving a collection scoring rule library, in which a scoring interval corresponds to a customer complaint solution; Determining a target score range from the collection score rule base according to the credit score; The customer complaint solution corresponding to the target scoring interval is determined as the target customer complaint solution.

4. The method for handling customer complaints regarding credit according to claim 2, characterized in that: Before obtaining the credit records and credit behaviors related to the target customer complaint type, it also includes: Retrieving the collection records of the user, and judging whether the collection actions are in compliance with regulations based on the collection records; If the collection action is in compliance with regulations, the operation of obtaining the user's credit record and credit behavior is performed; If the collection action is not in compliance with regulations, an operation of handling the user's complaint based on a preset strategy is executed.

5. The method for handling customer complaints regarding credit according to claim 1, characterized in that: When the target customer complaint type is a credit limit type or an interest rate type, the credit record includes loan records, consumption records and personal credit information; the credit behavior includes pre-loan customer behavior, during-loan customer behavior and post-loan customer behavior; The determining the credit score of the user in the target customer complaint type based on the credit record and the credit behavior includes: determining a third weight regarding the user's repayment ability based on the loan record, consumption record, and personal credit information; determining a fourth weight on the creditworthiness of the user according to the pre-loan customer behavior, the mid-loan customer behavior, and the post-loan customer behavior, wherein the sum of the third weight and the fourth weight is 1; Adjust the credit scoring model parameters according to the third weight and the fourth weight to obtain an updated credit scoring model; The loan record, the consumption record, the personal credit information, the pre-loan customer behavior, the mid-loan customer behavior and the post-loan customer behavior are input into the updated credit scoring model to obtain the credit score of the user.

6. The method for handling customer complaints regarding credit according to claim 5, characterized in that: The target customer complaint plan includes a target credit limit or a target credit interest rate; The generating of a target customer complaint solution according to the credit score comprises: Determining a target credit limit for the user based on the credit score and the current credit limit; Or, determine the user's target credit rate based on the credit score and the current credit rate.

7. The method for handling customer complaints regarding credit according to claim 1, characterized in that: Determining the target customer complaint type according to the user's customer complaint information includes: Performing text processing on the customer complaint information to obtain multiple word segments to be tested; Extracting the word feature corresponding to each of the word segments to be tested, and sequentially comparing each of the word features to be tested with a plurality of preset word features in the standard database; When the feature of the current word to be tested is consistent with the feature of the current preset word, the customer complaint type corresponding to the feature of the current preset word is determined to be the target customer complaint type.

8. A credit customer complaint processing device, characterized in that: include: A type determination module, used to determine the target customer complaint type based on the user's customer complaint information; A score determination module, used to obtain the credit record and credit behavior related to the target customer complaint type, and determine the credit score of the user in the target customer complaint type based on the credit record and the credit behavior; A solution generation module is used to generate a target customer complaint solution according to the credit score, so as to handle the customer complaint of the user according to the target customer complaint solution.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the credit customer complaint handling method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the credit customer complaint handling method as described in any one of claims 1 to 7 is implemented.

Images