Personal credit comprehensive evaluation method and device, equipment and medium

Abstract

The invention provides a comprehensive evaluation method and device for personal credit, equipment and a medium, and relates to the technical field of credit evaluation, and the method comprises the steps: obtaining debt data, repayment data and negotiation data of a target user; taking the scoring result as a first repayment willingness score of the target user; performing text conversion on the call recording to obtain a call recording text; analyzing the call recording text to obtain a second repayment willingness score of the target user; based on the first repayment willingness score and the second repayment willingness score, obtaining a total repayment willingness score of the target user; and calculating a personal credit score of the target user according to the debt data, the repayment data, the call parameters and the total repayment willingness score. According to the method and the device, the debt data, the repayment data and the negotiation data are combined to comprehensively and comprehensively evaluate the personal credit, so that an accurate, comprehensive and reliable personal credit score can be obtained.

Description

Technical Field

[0001] The present application relates to the technical field of credit assessment, and in particular to a method, device, equipment and medium for comprehensive assessment of personal credit. Background Art

[0002] Existing personal credit scoring methods are determined based on the user's current and historical debt situations. First, the assessment relies solely on current or historical debt data, without considering the user's debt negotiation data. The data basis is single, resulting in inaccurate assessment results. Second, existing methods directly set the personal credit score of users who have debt negotiations to failing or negative, without comprehensively and comprehensively considering the user's situation. The setting of the personal credit score is not only unreasonable, but also has a great impact on the user. Finally, some users may face a major economic crisis due to sudden illness or accidents, so they need to negotiate repayment, but the user's willingness to repay is relatively strong. At this time, the user's personal credit should not be greatly affected by the sudden situation, but the existing technology does not take this into account. Therefore, the personal credit scoring system is imperfect, unreasonable and unreliable.

[0003] Financial risk assessment based on unreasonable, inaccurate and unreliable personal credit scores is bound to be inaccurate and unreliable, and its results are not sufficient to provide a reference for financial risk assessment. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a comprehensive personal credit assessment method, device, equipment and medium to solve the above-mentioned problems existing in the prior art, and to conduct a comprehensive and comprehensive personal credit assessment by combining the debt data, repayment data and negotiation data to obtain an accurate, comprehensive and reliable personal credit score.

[0005] In a first aspect, a comprehensive evaluation method for personal credit is provided, which may include:

[0006] Obtaining the target user's debt data, repayment data, and negotiation data; wherein the negotiation data includes the call parameters and call recordings between the negotiator and the target user regarding the debt, and the negotiator's scoring results on the target user's willingness to repay;

[0007] The scoring result is used as the first repayment willingness score of the target user;

[0008] Convert the call recording into text to obtain a call recording text;

[0009] Analyze the call recording text to obtain the target user's second repayment willingness score;

[0010] Based on the first repayment willingness score and the second repayment willingness score, obtaining a total repayment willingness score of the target user;

[0011] The personal credit score of the target user is calculated based on the debt data, the repayment data, the call parameters and the total repayment willingness score.

[0012] In an optional implementation, the call recording text is analyzed to obtain the second repayment willingness score of the target user, including:

[0013] Inputting the call recording text into multiple trained repayment willingness scoring models to obtain multiple initial second repayment willingness scores;

[0014] The average of the multiple initial second repayment willingness scores is used as the second repayment willingness score of the target user.

[0015] In an optional implementation, obtaining the total repayment willingness score of the target user based on the first repayment willingness score and the second repayment willingness score includes:

[0016] Obtain the first repayment willingness score weight coefficient and the second repayment willingness score weight coefficient;

[0017] Multiplying the first repayment willingness score by the first repayment willingness score weight coefficient to obtain a first repayment willingness weight score;

[0018] Multiplying the second repayment willingness score by the second repayment willingness score weight coefficient to obtain a second repayment willingness weight score;

[0019] The first repayment willingness weighted score and the second repayment willingness weighted score are added together to obtain the target user's total repayment willingness score.

[0020] In an optional implementation, the debt data includes: a total debt amount and a total debt duration;

[0021] The call parameters include: number of calls, total call duration and average call duration;

[0022] The repayment data includes: repayment result data and repayment execution data; wherein, the repayment result data includes: whether the repayment plan is completed; the repayment execution data includes: whether all debts are paid off, the total repayment amount, the number of fulfillment times, and the distance between the last repayment time and the current time.

[0023] In an optional implementation, before calculating the personal credit score of the target user based on the debt data, the repayment data and the total repayment willingness score, the method includes:

[0024] using the call parameters and the total repayment willingness score as repayment negotiation process data;

[0025] Respectively using the repayment negotiation process data, the arrears data, the repayment result data and the repayment execution data as first evaluation data, second evaluation data, third evaluation data and fourth evaluation data;

[0026] Obtaining preset weight coefficients of the second evaluation data, the third evaluation data, and the fourth evaluation data, as well as financial environment analysis data; wherein the financial environment analysis data is obtained by analyzing the average amount of arrears and the average duration of arrears of all users in a preset historical period;

[0027] Based on the financial environment analysis data, a weight coefficient of the first evaluation data is calculated.

[0028] In an optional implementation, calculating the personal credit score of the target user includes:

[0029] Multiply different evaluation data by corresponding weight coefficients to obtain scoring results corresponding to different evaluation data;

[0030] The scoring results corresponding to different evaluation data are added together to obtain the personal credit score of the target user.

[0031] In an optional implementation, the calculation formula of the weight coefficient of the first evaluation data is as follows:

[0032]

[0033] Wherein, s1 represents the weight coefficient of the first evaluation data; q0 represents the preset adjustment coefficient; r w represents the average amount of debt owed by all users in arrears up to the wth historical period; t w represents the average arrears duration of all users in arrears up to the wth historical period; r1 represents the average arrears amount of all users in arrears up to the 1st historical period; t1 represents the average arrears duration of all users in arrears up to the 1st historical period.

[0034] In a second aspect, a comprehensive evaluation device for personal credit is provided, which may include:

[0035] An acquisition unit, used to acquire the target user's debt data, repayment data and negotiation data; wherein the negotiation data includes the call parameters and call recordings between the negotiator and the target user regarding the debt, and the negotiator's scoring result on the target user's willingness to repay;

[0036] A conversion unit, used for converting the call recording into text to obtain a call recording text;

[0037] A determination unit is configured to use the scoring result as a first repayment willingness score of the target user; analyze the call recording text to obtain a second repayment willingness score of the target user; and obtain a total repayment willingness score of the target user based on the first repayment willingness score and the second repayment willingness score;

[0038] An evaluation unit is used to calculate the personal credit score of the target user based on the debt data, the repayment data, the call parameters and the total repayment willingness score.

[0039] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0040] Memory, used to store computer programs;

[0041] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0042] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0043] When conducting personal credit assessment, this application not only takes into account the debt data, but also the debt negotiation data. The data basis is broader and more comprehensive, which effectively improves the accuracy of the assessment. This application determines the user's repayment willingness based on the negotiator's subjective scoring of the user's repayment willingness and the objective scoring of the user's repayment willingness based on call recording analysis, and can obtain true and reliable user repayment willingness. At the same time, incorporating debt negotiation data into credit assessment can eliminate the unreasonable and inaccurate situation caused by relying solely on debt for credit assessment, so that when the user encounters an economic crisis due to sudden accidents, the personal credit will not be greatly affected, thereby helping the user to carry out economic activities without major interference, helping to quickly eliminate economic crises, pay off debts, and avoid triggering a vicious cycle.

[0044] This application conducts a comprehensive assessment of personal credit by combining multiple types of data covering the entire process of user's arrears and repayment, such as repayment willingness, negotiation process data, debt data, repayment result data and repayment execution data. It not only comprehensively and comprehensively considers the user's situation, making the data basis for the assessment comprehensive, rich and reasonable, but also greatly improves the accuracy and reliability of the assessment; it can provide a more objective and reliable reference or data support for financial risk assessment or financial decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application 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.

[0046] Figure 1 A flowchart of a comprehensive evaluation method for personal credit provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the structure of a comprehensive evaluation device for personal credit provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The comprehensive evaluation method of personal credit provided in the embodiment of the present application can be applied in a server or in a terminal with strong computing power. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a user equipment (User Equipment, UE) such as a mobile phone, a smart phone, a laptop, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing equipment connected to a wireless modem, a mobile station (Mobile Station, MS), a mobile terminal (Mobile Terminal), etc. The terminal and the server can be directly or indirectly connected by wired or wireless communication, which is not limited in this application.

[0051] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0052] Figure 1 The following is a flow chart of a comprehensive evaluation method for personal credit provided by the embodiment of the present application. Figure 1 As shown, the method may include:

[0053] Step S110, obtaining the target user's outstanding data, repayment data and negotiation data; using the score of the target user's repayment willingness given by the negotiator in the negotiation data as the first repayment willingness score of the target user.

[0054] In the embodiment of the present application, the debt data includes: the total debt amount and the total debt duration; the call parameters include: the number of calls, the total call duration and the average call duration; the repayment data includes: the repayment result data and the repayment execution data; the repayment result data includes: whether the repayment plan is completed; the repayment execution data includes: whether all debts are paid off, the total repayment amount, the number of fulfillment times, and the distance between the last repayment time and the current time; the negotiation data includes the call parameters between the negotiator and the target user regarding the debt, the call recording and the negotiator's scoring of the target user's willingness to repay; the scoring result range is [0, 10]; the number of fulfillment times is the number of times the repayment plan is executed on time and in amount.

[0055] In the embodiment of the present application, the total call duration is the total duration of all calls between the negotiator and the target user regarding the negotiation of the outstanding debt; average call duration = total call duration / number of calls.

[0056] In the embodiment of the present application, the negotiation call is a call between a bank negotiator or a third-party negotiator commissioned by the bank and the user in arrears regarding the repayment of the debt when the user has outstanding debt.

[0057] In an embodiment of the present application, the target user's personal name, ID type, ID number, contact information, and debt institution can also be obtained. After obtaining the target user's personal credit score, the above data can be combined with the user's debt data, repayment data, negotiation data, and personal credit score to generate the target user's personal credit file.

[0058] In an embodiment of the present application, after each conversation between the negotiator and the target user, it is necessary to score the repayment willingness expressed by the target user during the conversation, and save the recording of the conversation and the scoring results; if the target user does not answer the call or does not reply to the call, the default score given by the negotiator to the target user's repayment willingness is 0 points.

[0059] Step S120: convert the call recording into text to obtain the call recording text; analyze the call recording text to obtain the second repayment willingness score of the target user.

[0060] In the embodiment of the present application, the call recording text includes the negotiator's call text and the target user's negotiation text.

[0061] In the embodiment of the present application, the call recording is converted into text to obtain the call recording text, including:

[0062] Obtain the time of the call recording; input the call recording into a pre-built recording parsing model to obtain the number of interlocutors and the audio of each interlocutor; convert the audio of each interlocutor into text to obtain the call text of each interlocutor; based on the time period to which the call recording belongs, match the negotiation speech corresponding to the time period from the pre-built negotiator speech library to obtain the target negotiation speech; compare the similarity of each interlocutor's call text with the target negotiation speech; the call text whose similarity with the target negotiation speech exceeds a preset threshold is the negotiator's call text; the call text of the interlocutor who is not the negotiator is the target user's call text; the call text of each interlocutor is obtained based on the negotiator's call text and the target user's call text.

[0063] In an embodiment of the present application, the negotiator's script library includes multiple sets of negotiation scripts and time periods for applying the sets of negotiation scripts; the preset threshold may be 99%.

[0064] For example, the acquired call recording is a call recording between negotiator A and target user B, and the recording time is January 2015; the call recording is input into the pre-built recording parsing model, and it is obtained that there are two interlocutors and the sentences spoken by the two interlocutors respectively; the sentences spoken by the two interlocutors are converted into text, and the call text of interlocutor 1 and the call text of interlocutor 2 are obtained;

[0065] Based on the recording time of January 2015, the negotiation script used in 2015 stored in the negotiator script library is determined to obtain the target negotiation script; the call text of interlocutor 1 is compared with the target negotiation script for similarity. If the similarity between the call text of interlocutor 1 and the target negotiation script is 99%, interlocutor 1 is negotiator A and interlocutor 2 is target user B; otherwise, interlocutor 1 is target user B and interlocutor 2 is negotiator A.

[0066] In another embodiment of the present application, the call recording is converted into text to obtain the call recording text, including:

[0067] Analyze the call recordings and divide the sentences of different interlocutors according to the sound features; for any interlocutor, select the longest sentence from all the sentences of the interlocutor as the target sentence of the interlocutor; extract the voiceprint features of the interlocutor based on the target sentence of the interlocutor; determine whether there is a voiceprint feature identical to the extracted voiceprint feature of the interlocutor in a pre-built negotiator voiceprint feature library, if so, the interlocutor is the negotiator; if not, the interlocutor is the target user; convert all the sentences of the negotiator and the target user into call text respectively, and obtain the call text of the negotiator and the call text of the target user; obtain the call text of each interlocutor based on the call text of the negotiator and the call text of the target user.

[0068] In the embodiment of the present application, the sound features include male voice, female voice, female high voice and male low voice, etc.

[0069] In an embodiment of the present application, a method for constructing a voiceprint library of a negotiator may include the following steps:

[0070] First, a negotiation script containing at least 50 characters is randomly selected from the pre-built negotiation script library as the initial negotiation script; 8 random numbers are added to the end of the initial negotiation script to obtain the target negotiation script;

[0071] Secondly, for any negotiator, check whether the current recording environment of the negotiator meets the preset standards; the preset standards include that the microphone is normal and the current environmental noise is less than 30 decibels;

[0072] Furthermore, if the current recording environment of the negotiator meets the preset standard, the audio of the negotiator reciting the target negotiation words is obtained; the voiceprint feature of the obtained audio of the negotiator is extracted and analyzed to obtain the voiceprint feature of the negotiator;

[0073] Finally, the identity ID of the negotiator is obtained, and the identity ID of the negotiator is bound to the voiceprint feature; based on the identity ID of each negotiator and the corresponding voiceprint feature, the voiceprint library of the negotiator is obtained.

[0074] For example, a preliminary analysis is performed on the call recording, and the audio of interlocutor 1 and the audio of interlocutor 2 are divided according to the sound characteristics; the longest sentence is selected from the audio of interlocutor 1 to obtain the target sentence of interlocutor 1; the voiceprint features of the target sentence of interlocutor 1 are extracted to obtain the voiceprint features of interlocutor 1; it is determined whether there are voiceprint features identical to those of interlocutor 1 in the pre-constructed negotiator voiceprint feature library. If so, interlocutor 1 is the negotiator and interlocutor 2 is the target user; otherwise, interlocutor 2 is the negotiator and interlocutor 1 is the target user.

[0075] In the embodiment of the present application, the call recording text is analyzed to obtain the second repayment willingness score of the target user, including:

[0076] The call recording text is input into multiple trained repayment willingness scoring models to obtain multiple initial second repayment willingness scores; the average value of the multiple initial second repayment willingness scores is used as the second repayment willingness score of the target user.

[0077] In the embodiment of the present application, the repayment willingness scoring model may be a Transformer model or an open source large model Qwen-7B or other models.

[0078] In an embodiment of the present application, multiple repayment willingness scoring models may be the same model or different models; for example, multiple Transformer models trained by different basic data are used as multiple preliminary trained Transformer models; then, the call text records corresponding to the cases with repayments in the past year and the corresponding repayment willingness scoring results (manual scoring) are used as training data, and the training data is used to retrain the multiple preliminary trained Transformer models to obtain a repayment willingness scoring model.

[0079] In the embodiment of the present application, the rules for manual scoring are set as follows: carefully read the content of the conversation to understand the attitude and expression of the debtor; analyze the debtor's willingness to repay, including whether there is a clear repayment plan, repayment time, repayment method, etc.; consider factors such as the debtor's tone and attitude, and whether there is any behavior of evading repayment.

[0080] In the embodiment of the present application, detailed manual scoring rules can also be set according to actual conditions, for example, 1 point is given when the debtor has a clear repayment plan, 0 point is given when there is no repayment plan, or 2 points is given when the debtor has a strong willingness to repay; the final scoring result is obtained based on the sum of all scores.

[0081] In an embodiment of the present application, when there are multiple call recordings for the target user, the multiple call recordings are converted into call recording texts respectively, and after integrating all the call recording texts of the target user, a comprehensive call recording text is obtained, and the comprehensive call recording text is input into multiple repayment willingness scoring models to obtain multiple initial second repayment willingness scores, and the multiple initial second repayment willingness scores are added together to obtain the second repayment willingness score.

[0082] In another embodiment of the present application, after converting multiple call recordings into call recording texts, each call recording text is input into multiple repayment willingness scoring models to obtain multiple initial second repayment willingness scores corresponding to each call recording text;

[0083] For any call recording corresponding to a call recording text, the call recording is input into a trained emotion recognition model to obtain the call emotion state of the target user corresponding to the call recording and the corresponding call recording text; the call emotion state of the corresponding target user is sorted according to the recording time sequence of different call recordings to obtain the call emotion state sequence of the target user; the call emotion state sequence of the target user is analyzed using a time series analysis method (for example) such as an ARIMA model, seasonal decomposition, etc. to obtain the call emotion state change trend of the target user; based on multiple initial second repayment willingness scores, the call emotion states of multiple target users and the call emotion state change trend, the second repayment willingness score of the target user is obtained.

[0084] In the embodiment of the present application, the emotion quantization value may be a continuous value ranging from -1 to +1; wherein, an emotion quantization value of -1 indicates an extremely negative emotion; and an emotion quantization value of +1 indicates an extremely positive emotion.

[0085] In the embodiment of the present application, the calculation formula of the second repayment willingness score of the target user includes the following:

[0086] (Emotional Impact Coefficient p ×Emotional Quantification p × Emotional change contribution p + Rating Weight p × Initial Second Repayment Willingness Score p );

[0087] Where L represents the number of call recordings with the target user; p represents the pth call recording, and p is a positive integer; the emotion impact coefficient and scoring weight can be set by the negotiator who calls the target user, or based on big data analysis, or adjusted according to actual conditions; the emotion change contribution value p Indicates the target user's emotional change contribution value during the pth call; emotional change contribution value p = emotional quantification value p -Emotional Quantification p-1 .

[0088] In an embodiment of the present application, the emotional state recognition model may be a CNN-based recognition model.

[0089] In an embodiment of the present application, the call parameters can also be analyzed to obtain a third willingness to repay score, specifically including: obtaining the number of times the target user rejects the negotiation calls made by the negotiator and the number of negotiation calls with a call duration of less than 10 seconds; based on the number of rejections and the number of calls less than 10 seconds, obtaining the third willingness to repay score.

[0090] Step S130: obtaining a total repayment willingness score of the target user based on the first repayment willingness score and the second repayment willingness score; and calculating a personal credit score of the target user based on the arrears data, repayment data, call parameters and the total repayment willingness score.

[0091] In another embodiment of the present application, the total repayment willingness score of the target user is obtained based on the first repayment willingness score, the second repayment willingness score and the third repayment willingness score.

[0092] In the embodiment of the present application, based on the first repayment willingness score and the second repayment willingness score, the total repayment willingness score of the target user is obtained, including:

[0093] Obtain a first repayment willingness score weight coefficient and a second repayment willingness score weight coefficient; multiply the first repayment willingness score and the first repayment willingness score weight coefficient to obtain a first repayment willingness weight score; multiply the second repayment willingness score and the second repayment willingness score weight coefficient to obtain a second repayment willingness weight score; add the first repayment willingness weight score and the second repayment willingness weight score to obtain a total repayment willingness score of the target user.

[0094] In the embodiment of the present application, the first repayment willingness score weight coefficient and the second repayment willingness score weight coefficient are pre-set.

[0095] In the embodiment of the present application, the total repayment willingness score calculation formula of the target user is as follows:

[0096] f = n1 × f1 + n2 × f2;

[0097] Among them, f represents the total repayment willingness score of the target user; f1 represents the first repayment willingness score; f2 represents the second repayment willingness score; n1 represents the first repayment willingness score weight coefficient; n2 represents the first repayment willingness score weight coefficient; specifically, the first repayment willingness score weight coefficient n1 can be set to 0.1; the second repayment willingness score weight coefficient n2 can be set to 0.9.

[0098] In the embodiment of the present application, before calculating the personal credit score of the target user based on the arrears data, the repayment data and the total repayment willingness score, the method includes:

[0099] Use call parameters and total repayment willingness score as repayment negotiation process data; use repayment negotiation process data, arrears data, repayment result data and repayment execution data as first evaluation data, second evaluation data, third evaluation data and fourth evaluation data respectively; obtain predetermined weight coefficients of the first evaluation data, second evaluation data, third evaluation data and fourth evaluation data.

[0100] In the embodiment of the present application, calculating the personal credit score of the target user includes:

[0101] Multiply different evaluation data with corresponding weight coefficients to obtain scoring results corresponding to different evaluation data; add up the scoring results corresponding to different evaluation data to obtain the personal credit score of the target user.

[0102] In the embodiment of the present application, the calculation formula of the personal credit score m of the target user is as follows:

[0103]

[0104] Among them, a represents the total amount of debt, in yuan; b represents the total duration of debt, in days; c represents the number of calls; d represents the total duration of calls, in minutes; e represents the average duration of calls, in minutes; f represents the total repayment willingness score; g represents whether the repayment plan has been completed, if completed, the value is 1, if not completed, the value is 0; h represents whether all debts have been paid off, if so, the value is 1, if not, the value is 0; i represents the number of fulfillment times; k represents the distance between the last repayment time and the current time; s1 represents the weight coefficient of the first evaluation data; s2 represents the weight coefficient of the second evaluation data; s3 represents the weight coefficient of the third evaluation data; s4 represents the weight coefficient of the fourth evaluation data.

[0105] In an embodiment of the present application, the values ​​of s2, s3 and s4 are preset values ​​and can be adjusted according to actual needs; in one embodiment of the present application, the values ​​of s2, s3 and s4 are preset values ​​and can be set to s2=0.3, s3=0.2, s4=1.

[0106] In the embodiment of the present application, s1 can be dynamically adjusted: the calculation formula of s1 is as follows:

[0107]

[0108] Wherein, s1 represents the weight coefficient of the first evaluation data; q0 represents the preset adjustment coefficient; r w represents the average amount of debt owed by all users in arrears up to the wth historical period; t w represents the average arrears duration of all users in arrears up to the wth historical period; r1 represents the average arrears amount of all users in arrears up to the 1st historical period; t1 represents the average arrears duration of all users in arrears up to the 1st historical period.

[0109] In the embodiment of the present application, the historical period can be set to one natural month as a historical period, or it can be set to three natural months as a historical period; the user sets it according to their actual situation; at the same time, the end date and start date of the historical period and the first historical period can also be determined by the customer according to their actual situation, which can be the beginning of each year or other dates.

[0110] In practical applications, the wth historical cycle can be the previous historical cycle of the user's current historical cycle, or the current historical cycle ending at the current date. For example, if one natural month is the historical cycle, and the first natural month of each year is the first historical cycle, then when s1 is calculated on March 15, r1×t1 represents the product of the average arrears duration and the corresponding average arrears amount of all users in arrears as of January 31; r w ×t w It can represent the product of the average duration of arrears and the corresponding average amount of arrears for all users in arrears as of February 28 or 29, or it can represent the product of the average duration of arrears and the corresponding average amount of arrears for all users in arrears as of March 15.

[0111] In an embodiment of the present application, when a bank user owes money or takes out a loan or conducts other banking business, a bank needs to evaluate the user's credit in order to conduct a financial risk assessment, or assist the bank in making financial decisions, such as conducting a loan risk assessment or whether financial litigation is needed against the user in arrears.

[0112] Corresponding to the above method, the embodiment of the present application also provides a comprehensive evaluation device for personal credit, such as Figure 2 As shown, the comprehensive evaluation device for personal credit includes:

[0113] The acquisition unit 210 is used to acquire the target user's debt data, repayment data and negotiation data; wherein the negotiation data includes the call parameters and call recordings between the negotiator and the target user regarding the debt, and the negotiator's scoring result on the target user's willingness to repay;

[0114] The conversion unit 220 converts the call recording into text to obtain the call recording text;

[0115] The determination unit 230 is used to use the scoring result as the first repayment willingness score of the target user; analyze the call recording text to obtain the second repayment willingness score of the target user; and obtain the total repayment willingness score of the target user based on the first repayment willingness score and the second repayment willingness score;

[0116] The evaluation unit 240 is used to calculate the personal credit score of the target user based on the debt data, repayment data, call parameters and total repayment willingness score.

[0117] The functions of the various functional units of the comprehensive evaluation device for personal credit provided in the above-mentioned embodiments of the present application can be realized through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the comprehensive evaluation device for personal credit provided in the embodiments of the present application are not repeated here.

[0118] The present application also provides an electronic device, such as Figure 3 As shown, it includes a processor 310 , a communication interface 320 , a memory 330 and a communication bus 340 , wherein the processor 310 , the communication interface 320 , and the memory 330 communicate with each other via the communication bus 340 .

[0119] Memory 330, for storing computer programs;

[0120] The processor 310 is used to execute the program stored in the memory 330 to implement the following steps:

[0121] Obtaining the target user's outstanding debt data, repayment data, and negotiation data; wherein the negotiation data includes the call parameters and call recordings between the negotiator and the target user regarding the outstanding debt, and the negotiator's scoring results on the target user's willingness to repay;

[0122] Convert the call recording into text to obtain the call recording text;

[0123] The scoring result is used as the first repayment willingness score of the target user; the call recording text is analyzed to obtain the second repayment willingness score of the target user; based on the first repayment willingness score and the second repayment willingness score, the total repayment willingness score of the target user is obtained;

[0124] The target user's personal credit score is calculated based on the debt data, repayment data, call parameters and total repayment willingness score.

[0125] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0126] The communication interface is used for communication between the above electronic device and other devices.

[0127] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0128] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0129] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 1 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0130] In another embodiment provided by the present application, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is executed on a computer, the computer executes any one of the comprehensive evaluation methods for personal credit in the above embodiments.

[0131] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any one of the comprehensive evaluation methods for personal credit in the above embodiments.

[0132] It should be understood by those skilled in the art that the embodiments in the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0136] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0137] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application fall within the scope of the claims and their equivalents in the embodiments of the present application, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A comprehensive evaluation method for personal credit, characterized in that: The method comprises: Obtaining the target user's debt data, repayment data, and negotiation data; wherein the negotiation data includes the call parameters and call recordings between the negotiator and the target user regarding the debt, and the negotiator's scoring results on the target user's willingness to repay; The scoring result is used as the first repayment willingness score of the target user; Convert the call recording into text to obtain a call recording text; Analyze the call recording text to obtain the target user's second repayment willingness score; Based on the first repayment willingness score and the second repayment willingness score, obtaining a total repayment willingness score of the target user; The personal credit score of the target user is calculated based on the debt data, the repayment data, the call parameters and the total repayment willingness score.

2. The method according to claim 1, characterized in that The call recording text is analyzed to obtain the target user's second repayment willingness score, including: Inputting the call recording text into multiple trained repayment willingness scoring models to obtain multiple initial second repayment willingness scores; The average of the multiple initial second repayment willingness scores is used as the second repayment willingness score of the target user.

3. The method according to claim 1, characterized in that Based on the first repayment willingness score and the second repayment willingness score, a total repayment willingness score of the target user is obtained, including: Obtain the first repayment willingness score weight coefficient and the second repayment willingness score weight coefficient; Multiplying the first repayment willingness score by the first repayment willingness score weight coefficient to obtain a first repayment willingness weight score; Multiplying the second repayment willingness score by the second repayment willingness score weight coefficient to obtain a second repayment willingness weight score; The first repayment willingness weighted score and the second repayment willingness weighted score are added together to obtain the target user's total repayment willingness score.

4. The method according to claim 1, characterized in that The debt data includes: the total debt amount and the total debt duration; The call parameters include: number of calls, total call duration and average call duration; The repayment data includes: repayment result data and repayment execution data; wherein, the repayment result data includes: whether the repayment plan is completed; the repayment execution data includes: whether all debts are paid off, the total repayment amount, the number of fulfillment times, and the distance between the last repayment time and the current time.

5. The method according to claim 4, characterized in that Before calculating the personal credit score of the target user based on the debt data, the repayment data and the total repayment willingness score, the method includes: using the call parameters and the total repayment willingness score as repayment negotiation process data; Respectively using the repayment negotiation process data, the arrears data, the repayment result data and the repayment execution data as first evaluation data, second evaluation data, third evaluation data and fourth evaluation data; Obtaining preset weight coefficients of the second evaluation data, the third evaluation data, and the fourth evaluation data, as well as financial environment analysis data; wherein the financial environment analysis data is obtained by analyzing the average amount of arrears and the average duration of arrears of all users in a preset historical period; Based on the financial environment analysis data, a weight coefficient of the first evaluation data is calculated.

6. The method according to claim 5, characterized in that Calculate the target user's personal credit score, including: Multiply different evaluation data by corresponding weight coefficients to obtain scoring results corresponding to different evaluation data; The scoring results corresponding to different evaluation data are added together to obtain the personal credit score of the target user.

7. The method according to claim 5, characterized in that The calculation formula of the weight coefficient of the first evaluation data is as follows: Wherein, s1 represents the weight coefficient of the first evaluation data; q0 represents the preset adjustment coefficient; r w represents the average amount of debt owed by all users in arrears up to the wth historical period; t w represents the average arrears duration of all users in arrears up to the wth historical period; r1 represents the average arrears amount of all users in arrears up to the 1st historical period; t1 represents the average arrears duration of all users in arrears up to the 1st historical period.

8. A comprehensive evaluation device for personal credit, characterized in that: The device comprises: An acquisition unit, used to acquire the target user's debt data, repayment data and negotiation data; wherein the negotiation data includes the call parameters and call recordings between the negotiator and the target user regarding the debt, and the negotiator's scoring result on the target user's willingness to repay; A conversion unit, used for converting the call recording into text to obtain a call recording text; A determination unit is configured to use the scoring result as a first repayment willingness score of the target user; analyze the call recording text to obtain a second repayment willingness score of the target user; and obtain a total repayment willingness score of the target user based on the first repayment willingness score and the second repayment willingness score; An evaluation unit is used to calculate the personal credit score of the target user based on the debt data, the repayment data, the call parameters and the total repayment willingness score.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, used to implement the method described in any one of claims 1 to 7 when executing a program stored in a memory.

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

Images