Customer rating method and device, equipment, storage medium and product

Abstract

The invention relates to the technical field of risk analysis, and discloses a customer rating method and device, equipment, a storage medium and a product, and the method comprises the steps: obtaining the end call information corresponding to a to-be-rated customer; constructing rating index data according to the exhaustion information; risk prediction is carried out based on the rating index data, and a risk assessment score is generated; and determining a risk level label corresponding to the to-be-rated customer according to the risk assessment score. Due to the fact that the machine processes the collected end-of-sale information, constructs the rating index data needed for client rating, then scores the rating index data, and determines the risk level label corresponding to the rating client according to the scoring result, the whole process is automatically processed, excessive manual intervention is not needed, the machine processing efficiency is high, and the processing efficiency of the machine is greatly improved. According to the invention, the duration required by rating can be greatly shortened, the disjunction of the business process caused by the duration is avoided, and the smooth handling of the business is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of risk analysis, and in particular to a customer rating method, device, equipment, storage medium and product. Background Art

[0002] At present, when enterprises need to conduct high-risk businesses such as foreign exchange (referred to as business development), in order to ensure that the enterprises can operate normally, they generally need to conduct corresponding risk ratings on the customers. However, the manual sorting and calculation of various business development risk indicator data of customers is cumbersome and labor-intensive, which will lead to extremely long customer rating time and prone to errors. Due to the long customer rating time, the large time span will lead to disconnection between the due diligence, rating, business handling and other processes of business development data, making it difficult to handle the business smoothly. Summary of the invention

[0003] The main purpose of this application is to provide a customer rating method, device, equipment, storage medium and product, aiming to solve the technical problem that it takes too long to rate customer risks in the process of business development in the existing technology.

[0004] To achieve the above objectives, the present application proposes a customer rating method, which is applied to a customer rating device. The customer rating method includes:

[0005] Obtain due diligence information corresponding to the customers to be rated;

[0006] Construct rating index data based on the due diligence information;

[0007] Perform risk prediction based on the rating indicator data to generate a risk assessment score;

[0008] The risk level label corresponding to the customer to be rated is determined according to the risk assessment score.

[0009] Optionally, the step of constructing rating index data according to the due diligence information includes:

[0010] Obtain the customer classification category corresponding to the customer to be rated;

[0011] Find the rating indicator corresponding to the customer classification category;

[0012] Rating indicator data is constructed based on the rating indicator and the due diligence information.

[0013] Optionally, the step of performing risk prediction based on the rating indicator data and generating a risk assessment score includes:

[0014] Determine the indicator weight and scoring rules corresponding to each rating indicator according to the customer classification category;

[0015] Scoring the rating indicator data according to the scoring rules to obtain an indicator score corresponding to each rating indicator;

[0016] The risk assessment score is generated based on the indicator weight and indicator score corresponding to each rating indicator.

[0017] Optionally, the step of scoring the rating indicator data according to the scoring rule to obtain an indicator score corresponding to each rating indicator includes:

[0018] Performing integrity check on the rating indicator data based on the rating indicator;

[0019] If it is detected that the rating indicator data is missing, obtaining the missing indicator;

[0020] Determine, according to the customer classification category, an approximate customer corresponding to the customer to be rated;

[0021] Generate reference data corresponding to the missing indicator according to the due diligence information of the similar customers;

[0022] Completing the missing parts of the rating indicator data according to the reference data;

[0023] After completion, the completed rating indicator data is scored according to the scoring rules to obtain the indicator score corresponding to each rating indicator.

[0024] Optionally, the step of generating a risk assessment score according to the indicator weight and indicator score corresponding to each rating indicator includes:

[0025] Obtaining a correlation index corresponding to the missing index;

[0026] Correcting the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators to obtain corrected indicator weights;

[0027] Generate risk assessment scores based on modified weight indicators and indicator scores.

[0028] Optionally, the step of correcting the missing indicator and the indicator weight corresponding to the correlation indicator in the indicator weight corresponding to each rating indicator to obtain the corrected indicator weight includes:

[0029] Obtaining the missing type and missing magnitude corresponding to the missing indicator;

[0030] Determine the weight correction ratio according to the missing type and the missing magnitude;

[0031] Based on the weight correction ratio, the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators are corrected to obtain the corrected indicator weights.

[0032] In addition, to achieve the above purpose, the present application also proposes a customer rating device, the device comprising:

[0033] The acquisition module is used to obtain the due diligence information corresponding to the customer to be rated;

[0034] A construction module, used to construct rating index data based on the due diligence information;

[0035] A scoring module, used to perform risk prediction based on the rating indicator data and generate a risk assessment score;

[0036] The rating module is used to determine the risk level label corresponding to the customer to be rated according to the risk assessment score.

[0037] In addition, to achieve the above objectives, the present application also proposes a customer rating device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the customer rating method described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the customer rating method described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the customer rating method described above are implemented.

[0040] One or more technical solutions proposed in this application have at least the following technical effects:

[0041] Since the collected due diligence information is processed by machines, the rating index data required for customer rating is constructed, and then the rating is performed, and the risk level label corresponding to the loan rating customer is determined based on the scoring results. The entire process is automated and does not require excessive human intervention. The machine processing efficiency is high, which can greatly shorten the time required for rating, avoid business process disconnection caused by time, and ensure that the business can be handled smoothly. In the evaluation process, some missing data will be supplemented with similar customer data, and the confidence of the supplemented data will be appropriately adjusted to ensure that in the rating process, the rating will not fail or be abnormal due to some defective data, and the supplemented data will not have too much impact on the overall score, so as to avoid too much supplemented data affecting the final rating results. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flowchart of the first embodiment of the customer rating method of this application is provided;

[0045] Figure 2 A flowchart of the second embodiment of the customer rating method of this application is provided;

[0046] Figure 3 A flowchart of the third embodiment of the customer rating method of this application is provided;

[0047] Figure 4 A schematic diagram of a system implementation process provided in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of optional indicators and scoring rules within the risk prediction model provided in one embodiment of the present application;

[0049] Figure 6 A schematic diagram of a combined use process of a system provided in an embodiment of the present application;

[0050] Figure 7 This is a schematic diagram of the module structure of the customer rating device according to an embodiment of the present application;

[0051] Figure 8 Schematic diagram of the device structure of the hardware operating environment involved in the customer rating method in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: obtaining due diligence information corresponding to the customer to be rated; constructing rating index data based on the due diligence information; performing risk prediction based on the rating index data to generate a risk assessment score; determining the risk level label corresponding to the customer to be rated based on the risk assessment score

[0056] In this embodiment, for the convenience of description, the following description is made with the customer rating device as the execution subject.

[0057] Due to the existing technology, when enterprises need to conduct high-risk businesses such as foreign exchange (referred to as business development), in order to ensure that the enterprises can operate normally, they generally need to conduct corresponding risk ratings on the customers. However, the manual sorting and calculation of various business development risk indicator data of customers is cumbersome and labor-intensive, which will result in extremely long customer rating time and prone to errors. Due to the long customer rating time, the large time span will lead to disconnection between the due diligence, rating, business handling and other processes of business development data, making it difficult to handle the business smoothly.

[0058] This application provides a solution, which processes the collected due diligence information through a machine, constructs the rating index data required for customer rating, and then scores, and determines the risk level label corresponding to the loan rating customer based on the scoring results. The entire process is automated, without the need for excessive human intervention, and the machine processing efficiency is high, which can greatly shorten the time required for rating, avoid business process disconnection caused by time, and ensure that the business can be handled smoothly.

[0059] Based on this, the present application embodiment provides a customer rating method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the customer rating method of the present application.

[0060] In this embodiment, the customer rating method is applied to a customer rating device, including steps S10 to S40:

[0061] Step S10, obtaining due diligence information corresponding to the customer to be rated.

[0062] It should be noted that the execution subject of this embodiment may be the customer rating device, or a platform or system composed of at least one customer rating device, and the customer rating device may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes the customer rating device as an example to illustrate this embodiment and the following embodiments.

[0063] It should be noted that the client to be rated may be an enterprise or individual that is about to cooperate or may cooperate when conducting high-risk business, which leads to the need for risk rating. Due diligence data may be data related to the client to be rated collected during the due diligence process when investigating or analyzing the client to be rated. Due diligence data may include external data, credit data, anti-money laundering data and other data. Among them, external data may be data related to the external debts of an enterprise or individual (such as debts or external loans), credit data may be data related to the credit loans of an enterprise or individual (such as credit loans from banks), and anti-money laundering data may include customer information, business transaction data, customer location, account information and other data that conducts commercial business with the enterprise or individual.

[0064] In actual use, due diligence data can be submitted to the customer rating device by business personnel after conducting due diligence on the customer to be rated by inputting or uploading. Of course, the customer rating device can also be connected with other devices or systems (such as bank systems, corporate data analysis systems, etc.) and then read the due diligence data from the connected devices or systems.

[0065] Step S20: construct rating index data based on the due diligence information.

[0066] It should be noted that the rating indicator data may be the relevant data required for risk rating of the client to be rated. The rating indicator data may be generated by analyzing, counting, and summarizing the due diligence information to generate the data required for risk rating, thereby obtaining the rating indicator data.

[0067] Step S30: Perform risk prediction based on the rating indicator data to generate a risk assessment score.

[0068] Step S40: determining the risk level label corresponding to the customer to be rated according to the risk assessment score.

[0069] It should be noted that the risk assessment score can be a quantitative score used to characterize whether there is a risk in conducting related business (such as foreign exchange business) with the customer to be rated. For example, the higher the risk assessment score, the lower the possibility that there is a risk in conducting related business with the customer to be rated; or the lower the risk assessment score, the lower the possibility that there is a risk in conducting related business with the customer to be rated.

[0070] In actual use, risk prediction is performed based on rating indicator data, and the risk assessment score is generated by matching the rating indicator data with a preset scoring rule, or analyzing and predicting the rating indicator data through a pre-trained risk prediction model, so as to determine the risk assessment score. The scoring rule can be pre-set by the manager of the customer rating device. For example, assuming that the rating indicator data is the asset scale, and the scoring rule is set to the value of the asset scale / 5 million*100%, with a cap of 100%, if the asset scale of the customer to be rated is 3 million, then its risk assessment score can be 60%. Among them, the rating indicator data can include multiple types of data, and different scoring rules can be set for each type of data, which is not limited in this embodiment.

[0071] In specific implementation, determining the risk level label corresponding to the customer to be rated based on the risk assessment score can be done by matching the risk assessment score with the score range corresponding to each preset level, determining the target score range to which the risk assessment score belongs, and then using the preset level corresponding to the target score range as the risk level label corresponding to the customer to be rated.

[0072] This embodiment provides a customer rating method, which processes the collected due diligence information through a machine, constructs the rating index data required for customer rating, and then scores the customer, and determines the risk level label corresponding to the loan rating customer based on the scoring result. The entire process is automated and does not require excessive human intervention. The machine processing efficiency is high, which can greatly shorten the time required for rating, avoid business process disconnection caused by time, and ensure that the business can be handled smoothly.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S20 includes steps S201 to S203:

[0074] Step S201: Obtain the customer classification category corresponding to the customer to be rated.

[0075] It should be noted that the customer classification category can be data used to characterize the characteristics of the customer to be rated, such as the establishment time, business field, and enterprise scale. For example, the main business of a customer to be rated is vehicle manufacturing, the enterprise scale is a medium-sized enterprise, and the establishment time is one year. At this time, the customer classification category of the customer to be rated can be an emerging medium-sized vehicle manufacturing type.

[0076] In actual use, the customer classification category of the customer to be rated can be determined and set by the due diligence executor during the due diligence process. At this time, obtaining the customer classification category corresponding to the customer to be rated can be extracting the customer classification category corresponding to the customer to be rated from the due diligence information.

[0077] However, due to the unreliability of manual operations (such as fraud or analysis errors by due diligence personnel), errors may occur in the setting of customer classification categories. Customer classification categories can be determined through relevant analysis algorithms or category analysis models, for example: feature extraction is performed on data related to the length of establishment, business field, and enterprise size in the due diligence information, and then the extracted features are matched with the feature data in each classification category in the category classification library for similarity, and the customer classification category corresponding to the customer to be rated is determined based on the matching results; or, feature extraction is performed on data related to the length of establishment, business field, and enterprise size in the due diligence information, and then the extracted features are analyzed through a pre-trained category analysis model to determine the customer classification category corresponding to the customer to be rated.

[0078] Among them, since the algorithm analysis or model analysis may also make mistakes, the due diligence personnel can set the customer classification category during the due diligence, and compare it with the customer classification category obtained by the algorithm analysis or model analysis. If the two are consistent, the customer classification category is directly used as the customer classification category corresponding to the customer to be rated;

[0079] If the two are inconsistent, determine the difference between the two customer classification categories. If the difference is small, then one of the two customer classification categories can be extracted as the customer classification category corresponding to the customer to be rated. If the difference is large, then the extracted features, due diligence data and the two customer classification categories can be submitted to relevant analysts for further confirmation, and then the corresponding customer classification category can be set for the customer to be rated based on the analyst's confirmation results.

[0080] Step S202: Find the rating index corresponding to the customer classification category.

[0081] It should be noted that different customer classification categories correspond to customers with different enterprise sizes and business fields. Therefore, the rating indicators used may also be different. In order to ensure that various types of customers can be rated as accurately as possible, the managers of the customer rating equipment can pre-set the correspondence between customer classification categories and rating indicators, and store them through a category indicator mapping table. At this time, the execution process of finding the rating indicator corresponding to the customer classification category can be to find the rating indicator corresponding to the customer classification category in the category indicator mapping table.

[0082] Among them, the rating indicators that may be used can be divided into six categories according to specific circumstances, including basic information, foreign exchange business, related parties, credit reputation, operating conditions, and capital conditions;

[0083] The rating indicators included in each major category can be as follows:

[0084] Basic information may include: rating indicators such as enterprise type, economic type, industry type, etc.;

[0085] Foreign exchange business may include: annual settlement scale, proportion of large-value business, proportion of foreign exchange refund business, proportion of pre-collected business and other rating indicators;

[0086] Related parties may include rating indicators such as restrictions on high consumption, legal person judicial sanctions, corporate judicial sanctions, and sanctions status;

[0087] Credit reputation may include rating indicators such as credit rating, administrative penalty risk level, operational anomalies, and whether sanctions have been imposed;

[0088] The operating conditions may include: annual revenue scale, annual expenditure scale, monthly revenue and expenditure frequency, monthly revenue and expenditure amount and other rating indicators;

[0089] Capital status may include rating indicators such as asset size, paid-in capital, and registered capital.

[0090] It should be noted that the above-mentioned rating indicator categories are merely illustrative descriptions and are not specifically limited. If necessary, more or fewer rating indicators may be included, and this embodiment does not impose any limitation on this.

[0091] Step S203: construct rating index data based on the rating index and the due diligence information.

[0092] It should be noted that after the rating indicators are determined, the due diligence information can be analyzed, counted, summarized, etc. based on the rating indicators to obtain rating indicator data. The rating indicator data may include indicator data corresponding to each rating indicator.

[0093] It is understandable that the customer classification category corresponding to the customer to be rated is first obtained, and then the rating indicators to be used are determined based on the customer classification category, and then the rating indicator data for rating the customer to be rated is constructed based on the rating indicators. This can ensure that when rating, the corporate particularities of the customer to be rated are taken into account, and a reasonable rating is performed based on its establishment time, corporate field and corporate scale, to ensure that the final rating result is more in line with practical applications.

[0094] In this embodiment, the step S30 may include:

[0095] Step S301: Determine the indicator weight and scoring rules corresponding to each rating indicator according to the customer classification category.

[0096] It should be noted that the indicator weight corresponding to the rating indicator can be the weight ratio of the score corresponding to the rating indicator in the overall risk assessment score. The scoring rule corresponding to the rating indicator can be the rule for scoring the indicator data corresponding to the rating indicator, and the scoring rule can include the numerical range used in scoring and the score corresponding to each numerical range;

[0097] For example, taking the rating indicator monthly frequency of revenue and expenditure as an example, the corresponding scoring rule may be "a full score of 100% for a frequency of revenue and expenditure of n times or more; a score of 70% for a frequency of revenue and expenditure of less than or equal to n times and greater than or equal to m times; a score of 0 for a frequency of revenue and expenditure of less than m times", where n and m may be pre-set by the manager of the customer rating device, both of which are positive integers, and n>m, such as setting n to 5 and m to 3.

[0098] Step S302: Score the rating indicator data according to the scoring rules to obtain an indicator score corresponding to each rating indicator.

[0099] Step S303: Generate a risk assessment score based on the indicator weight and indicator score corresponding to each rating indicator.

[0100] It should be noted that the indicator data corresponding to each rating indicator contained in the rating indicator data can be scored respectively according to the scoring rules corresponding to each rating indicator, so as to obtain the indicator score corresponding to each rating indicator.

[0101] In actual use, generating a risk assessment score based on the indicator weights and indicator scores corresponding to each rating indicator can be performed by weighted summing up the indicator scores corresponding to each rating indicator based on the indicator weights corresponding to each rating indicator, thereby obtaining a risk assessment score.

[0102] This embodiment provides a customer rating method, which ensures that appropriate rating indicators can be selected according to the customer classification category of the customer, and scoring can be performed according to the indicator weights and scoring rules corresponding to the rating indicators. The rationality scoring can be performed by comprehensively considering factors such as the customer's establishment time, business field and enterprise scale, to ensure that the generated risk assessment score is more reasonable and more in line with the actual situation of the customer to be rated.

[0103] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first or second embodiment can be referred to the above description, and will not be described in detail later. Figure 3 , step S302 includes steps S3021 to S3026:

[0104] Step S3021: Perform integrity check on the rating indicator data based on the rating indicator.

[0105] It should be noted that due to data privacy or due diligence channel issues, some data may not be available during the due diligence process (such as the sales or revenue data of a company in a certain month cannot be obtained), which will lead to the lack of indicator data corresponding to some rating indicators. Such data loss will affect the accuracy of customer ratings. In order to minimize such impacts, before rating, the rating indicator data can be checked for integrity based on the rating indicators to determine whether there is any missing indicator data corresponding to some rating indicators.

[0106] Step S3022: If it is detected that the rating index data is missing, the missing index is obtained.

[0107] It should be noted that the missing indicator may be a rating indicator for which the corresponding indicator data is missing in the rating indicator data. If it is detected that the rating indicator data is missing, it means that the rating indicator data is missing the indicator data corresponding to some rating indicators, and the scoring may not be performed normally. Therefore, it is necessary to complete it. In order to complete it reasonably, the missing indicator can be obtained; if it is detected that the rating indicator data does not have missing data, it means that no completion processing is required. Therefore, the rating indicator data can be directly scored according to the scoring rules to obtain the indicator scores corresponding to each rating indicator.

[0108] Step S3023: Determine the approximate customer corresponding to the customer to be rated according to the customer classification category.

[0109] It should be noted that the approximate customers corresponding to the customer to be rated may be other customers whose establishment time, business field, and enterprise scale are the same or similar to those of the customer to be rated, and the customer classification category is used to characterize the establishment time, business field, and enterprise scale. Therefore, determining the approximate customers corresponding to the customer to be rated based on the customer classification category may be to find other customers whose corresponding customer classification category is consistent with the customer classification category corresponding to the customer to be rated, and use the found customers as approximate customers.

[0110] Step S3024: Generate reference data corresponding to the missing indicators based on the due diligence information of the similar customers.

[0111] It should be noted that the due diligence information on similar customers may be relevant data collected when conducting due diligence on similar customers, and generating reference data corresponding to missing indicators based on the due diligence information on similar customers may be performing corresponding processing (such as analysis, statistics, aggregation, etc.) on the due diligence information on similar customers to generate indicator data, and using the generated indicator data as reference data corresponding to the missing indicators.

[0112] Step S3025: completing the missing parts of the rating index data according to the reference data.

[0113] It should be noted that the missing data of the rating index data can be supplemented by using the reference data as the index data corresponding to the missing index, and added to the rating index data.

[0114] Step S3026: After completion, the completed rating indicator data is scored according to the scoring rules to obtain the indicator score corresponding to each rating indicator.

[0115] It is understandable that after the missing parts of the rating indicator data are completed, the data in the rating indicator data is complete and scoring can be performed normally. Therefore, the completed rating indicator data can be scored according to the scoring rules to obtain the indicator score corresponding to each rating indicator.

[0116] In a possible implementation of this embodiment, in order to ensure the rationality of the scoring as much as possible, in this embodiment, step S303 may include steps S3031-3033:

[0117] Obtaining a correlation index corresponding to the missing index;

[0118] Correcting the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators to obtain corrected indicator weights;

[0119] Generate risk assessment scores based on modified weight indicators and indicator scores.

[0120] It should be noted that when completing the rating indicator data, the due diligence data of other customers is used to complete it. In fact, the data of other customers will be different from the data of the customers to be rated, and the credibility of their data will be reduced accordingly. Therefore, it is necessary to correct the indicator weights of the missing indicators. Since the rating indicators may not be single indicators, multiple rating indicators may have certain correlations. If only the indicator weights corresponding to the missing indicators are corrected, the upper and lower limits of the final score may change, which will reduce the practicality of the score. In order to avoid this situation, the correlation indicators corresponding to the missing indicators can be obtained first, and then the indicator weights corresponding to the missing indicators and the correlation indicators in the indicator weights corresponding to each rating indicator can be corrected together, and the indicator weights corresponding to each rating indicator after correction can be used as the corrected indicator weights.

[0121] Among them, the correlation indicator corresponding to the missing indicator can be other rating indicators that are correlated with the missing indicator, such as rating indicators that belong to the same category as the missing indicator. For example, taking the evaluation indicator asset scale as an example, the asset scale, paid-in capital and registered capital belong to the same category of capital situation. If the asset scale is a missing indicator, then the correlation indicators can include the two rating indicators of paid-in capital and registered capital.

[0122] In actual use, the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to each rating indicator are corrected. The corrected indicator weights can be obtained by reducing the indicator weights of the missing indicators in the indicator weights corresponding to each rating indicator, and adding the reduced indicator weight values ​​to the indicator weights of the correlation indicators on average. For example, assuming that the rating indicators include asset size, paid-in capital and registered capital, and the corresponding indicator weights are 50%, 30% and 20% respectively, at this time, the asset size is the missing indicator, and the paid-in capital and registered capital are correlation indicators. At this time, the indicator weight corresponding to the asset size can be reduced by 20%, and the reduced 20% can be added on average to the indicator weights corresponding to the paid-in capital and registered capital. The corrected indicator weights obtained at this time are 30%, 40% and 30%.

[0123] The adjustment values ​​of the above-mentioned indicator weights are only used as examples but not as specific limitations. The specific reduction extent of the indicator weights of the missing indicators can be set in advance by the managers of the customer rating equipment.

[0124] It can be understood that by generating risk assessment scores based on modified weight indicators and indicator scores, it can be ensured that in the process of generating risk assessment scores, the problem of reduced data credibility due to data completion is fully considered, ensuring that the generated risk assessment scores are more in line with the actual situation of the customer and maximizing the accuracy of the risk assessment scores.

[0125] In a specific implementation, in order to ensure the rationality of the coefficient correction, the step of correcting the missing indicator and the indicator weight corresponding to the correlation indicator in the indicator weight corresponding to each rating indicator in this embodiment to obtain the corrected indicator weight may include:

[0126] Obtaining the missing type and missing magnitude corresponding to the missing indicator;

[0127] Determine the weight correction ratio according to the missing type and the missing magnitude;

[0128] Based on the weight correction ratio, the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators are corrected to obtain the corrected indicator weights.

[0129] It should be noted that the missing types may include missing values, missing fields, missing values ​​and fields, etc. The missing range may be a quantitative score used to represent the proportion of missing data. For example, if the missing range is 100%, it means that the indicator data corresponding to the missing indicator is completely missing; if the missing range is 50%, it means that half of the indicator data corresponding to the missing indicator is missing.

[0130] In actual use, determining the weight correction ratio according to the missing type and the missing range can be to search for the corresponding weight correction ratio in a preset ratio missing mapping table according to the missing type and the missing range. The preset ratio missing mapping table stores the mapping relationship between the missing type and the missing range and the weight correction ratio, and the preset ratio missing mapping table can be pre-set by the administrator of the customer rating device.

[0131] In actual application, based on the weight correction ratio, the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to each rating indicator are corrected. The specific implementation process for obtaining the corrected indicator weights can be:

[0132] The indicator weights corresponding to the missing indicators in the indicator weights corresponding to each rating indicator are reduced by the weight correction ratio, and the reduced indicator weights are added to the indicator weights corresponding to the correlation indicators, so as to obtain the corrected indicator weights.

[0133] For example: assuming that the weight correction ratio is 50%, the rating indicators include annual income scale, asset scale, paid-in capital and registered capital, and the corresponding indicator weights are 10%, 40%, 30% and 20% respectively. At this time, the asset scale is a missing indicator, and the paid-in capital and registered capital are related indicators. At this time, the indicator weight corresponding to the asset scale can be reduced by 40%*50%=20%, and the reduced 20% can be added evenly to the indicator weights corresponding to the paid-in capital and registered capital. The corrected indicator weights obtained at this time are 10%, 20%, 40%, and 30%.

[0134] This embodiment provides a customer rating method, which ensures that when rating indicator data is missing, the rating indicator data can be supplemented by relevant data of similar customers corresponding to the customer to be rated, ensuring that even if some data is missing, the risk rating of the customer to be rated can still be performed normally.

[0135] For example, to help understand the implementation process of the customer rating method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 4 , Figure 4 A schematic diagram of the system implementation process of a customer rating method is provided, specifically:

[0136] The process of customer rating may involve the foreign exchange business development system, the credit system and the account manager. The foreign exchange business development system can initiate the relevant tasks of the first due diligence, which requires updating the foreign exchange data, credit data, anti-money laundering data, etc. After that, the first due diligence task will be sent to the credit system. After receiving the first due diligence task, the credit system will notify the account manager, who will conduct customer due diligence (i.e., due diligence on the customer) and enter the collected due diligence information related to the customer into the credit system. The credit system will send the entered due diligence information to the foreign exchange business development system. The foreign exchange business development system will construct the rating index data based on the due diligence data and verify the integrity. If the data is complete, it will be scored directly based on the rating index data (the scoring can be performed by the risk prediction model, and the risk prediction model will select the corresponding rating index and scoring rules); if it is incomplete, it will be scored after completion;

[0137] After that, the scoring result (i.e. risk level label) is determined based on the scoring. After that, the rating result can be sent to the handler for review (i.e. due diligence rating handler), and then reviewed by the reviewer (i.e. due diligence rating review). After the review is passed, the foreign exchange business development system can also make further rating authorization determination based on the scoring results (i.e. determine whether it is Class I, whether to adjust the classification, whether to do business in Class II, etc.). If the authorization determination is passed, the due diligence rating authorization will be carried out based on the authorization determination, and a due diligence form will be generated. The account manager (or relevant business personnel) can view / download the due diligence form to determine the rating authorization, etc.; if the authorization determination fails, a due diligence form will be directly generated, and the account manager (or relevant business personnel) can view / download the due diligence form to determine the results such as the authorization determination failure.

[0138] in, Figure 5 The following is a schematic diagram of the optional indicators and scoring rules within the risk prediction model. The optional rating indicators and scoring rules within the risk prediction model can be as follows: Figure 5 As shown, the rating indicators that can be selected include six categories: basic information, foreign exchange business, related parties, credit reputation, operating conditions, and capital conditions;

[0139] The rating indicators included in each major category can be as follows:

[0140] Basic information may include: rating indicators such as enterprise type, economic type, industry type, etc.;

[0141] Foreign exchange business may include: annual settlement scale, proportion of large-value business, proportion of foreign exchange refund business, proportion of pre-collected business and other rating indicators;

[0142] Related parties may include rating indicators such as restrictions on high consumption, legal person judicial sanctions, corporate judicial sanctions, and sanctions status;

[0143] Credit reputation may include rating indicators such as credit rating, administrative penalty risk level, operational anomalies, and whether sanctions have been imposed;

[0144] The operating conditions may include: annual revenue scale, annual expenditure scale, monthly revenue and expenditure frequency, monthly revenue and expenditure amount and other rating indicators;

[0145] Capital status may include rating indicators such as asset size, paid-in capital, and registered capital.

[0146] Figure 5 In the , you can set different category weights for each category, and according to the rating indicators under the category, you can set the corresponding weight coefficient under the category. The category weight and the weight coefficient are multiplied to get the indicator weight corresponding to the rating indicator. For example: Figure 5 In the above table, the weight coefficient corresponding to asset size is 50%, and the category weight corresponding to the capital situation is 10%. At this time, the indicator weight corresponding to asset size is 50%*10%=5%.

[0147] It should be noted that Figure 5 The scoring rules corresponding to the scores of each indicator (e.g., for asset size, the scoring rule is "value / 5 million*100%, the highest does not exceed 100%) and the weights (e.g., capital situation weight 10%, asset size weight 50%) are only for illustrative purposes and are not specifically limited. Figure 5 It is only used to indicate the rating indicators, indicator weights, and scoring rules that may be selected for the risk prediction model. The rating indicators, indicator weights, and scoring rules used in the scoring process can be freely selected according to actual needs, and this embodiment does not impose any restrictions on this.

[0148] In specific implementation, the rating results can also be used in combination with relevant data from other systems. Figure 6 To explain, Figure 6 The system of this embodiment is used in combination with the flow chart, as shown in FIG. Figure 6 As shown, the foreign exchange business development system can also be used in conjunction with the national settlement system. When handling foreign exchange business, the business operator can enter customer information in the national settlement system and click to query. At this time, the national settlement system will query the foreign exchange business development system for the risk level label of the customer corresponding to the customer information. If the foreign exchange business development system finds the corresponding data (that is, the risk level label corresponding to the customer), it can also feedback the customer's risk level label together with the customer label, portrait data, etc. to the national settlement system. The national settlement system can display the query results, and the business operator can perform subsequent business processing based on the displayed query results; if the corresponding data is not found, the foreign exchange business development system will notify the national settlement system. At this time, the national settlement system can prompt the business operator that the data has not been found, and the business operator can perform subsequent processing.

[0149] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the customer rating method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0150] This application also provides a customer rating device, please refer to Figure 7 , the customer rating device comprises:

[0151] An acquisition module 10 is used to acquire due diligence information corresponding to the customer to be rated;

[0152] A construction module 20, configured to construct rating index data according to the due diligence information;

[0153] A scoring module 30, configured to perform risk prediction based on the rating indicator data and generate a risk assessment score;

[0154] The rating module 40 is used to determine the risk level label corresponding to the customer to be rated according to the risk assessment score.

[0155] The customer rating device provided by the present application adopts the customer rating method in the above embodiment, which can solve the technical problem that it takes too long to rate the risk of customers during business development. Compared with the prior art, the beneficial effects of the customer rating device provided by the present application are the same as the beneficial effects of the customer rating method provided by the above embodiment, and other technical features in the customer rating device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0156] The present application provides a customer rating device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the customer rating method in the above-mentioned embodiment one.

[0157] Reference below Figure 8 , which shows a schematic diagram of the structure of a customer rating device suitable for implementing the embodiment of the present application. The customer rating device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8The customer rating device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0158] like Figure 8 As shown, the customer rating device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the customer rating device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the customer rating device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a customer rating device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0159] 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 a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0160] The customer rating device provided by the present application adopts the customer rating method in the above embodiment, which can solve the technical problem that it takes too long to rate the risk of customers during business development. Compared with the prior art, the beneficial effects of the customer rating device provided by the present application are the same as the beneficial effects of the customer rating method provided by the above embodiment, and the other technical features in the customer rating device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0161] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0162] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0163] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the customer rating method in the above-mentioned embodiment.

[0164] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, 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 this embodiment, the 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, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0165] The computer-readable storage medium may be included in the customer rating device; or may exist independently without being assembled into the customer rating device.

[0166] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the customer rating device, the customer rating device: obtains due diligence information corresponding to the customer to be rated; constructs rating indicator data based on the due diligence information; performs risk prediction based on the rating indicator data and generates a risk assessment score; and determines the risk level label corresponding to the customer to be rated based on the risk assessment score.

[0167] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0168] 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 square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the 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 square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / 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.

[0169] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0170] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned customer rating method, and can solve the technical problem of customer rating. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the customer rating method provided in the above-mentioned embodiment, and will not be repeated here.

[0171] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned customer rating method when executed by a processor.

[0172] The computer program product provided by this application can solve the technical problem that it takes too long to rate the risk of customers during business development. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the customer rating method provided by the above embodiment, which will not be repeated here.

[0173] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A customer rating method, characterized in that: Applied to a customer rating device, the customer rating method includes: Obtain due diligence information corresponding to the customers to be rated; Construct rating index data based on the due diligence information; Perform risk prediction based on the rating indicator data to generate a risk assessment score; The risk level label corresponding to the customer to be rated is determined according to the risk assessment score.

2. The customer rating method according to claim 1, characterized in that: The step of constructing rating index data according to the due diligence information includes: Obtain the customer classification category corresponding to the customer to be rated; Find the rating indicator corresponding to the customer classification category; Rating indicator data is constructed based on the rating indicator and the due diligence information.

3. The customer rating method according to claim 2, characterized in that: The step of performing risk prediction based on the rating indicator data and generating a risk assessment score comprises: Determine the indicator weight and scoring rules corresponding to each rating indicator according to the customer classification category; Scoring the rating indicator data according to the scoring rules to obtain an indicator score corresponding to each rating indicator; The risk assessment score is generated based on the indicator weight and indicator score corresponding to each rating indicator.

4. The customer rating method according to claim 3, characterized in that: The step of scoring the rating indicator data according to the scoring rule to obtain the indicator score corresponding to each rating indicator includes: Performing integrity check on the rating indicator data based on the rating indicator; If it is detected that the rating indicator data is missing, obtaining the missing indicator; Determine, according to the customer classification category, an approximate customer corresponding to the customer to be rated; Generate reference data corresponding to the missing indicator according to the due diligence information of the similar customers; Completing the missing parts of the rating indicator data according to the reference data; After completion, the completed rating indicator data is scored according to the scoring rules to obtain the indicator score corresponding to each rating indicator.

5. The customer rating method according to claim 4, characterized in that: The step of generating a risk assessment score based on the indicator weight and indicator score corresponding to each rating indicator includes: Obtaining a correlation index corresponding to the missing index; Correcting the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators to obtain corrected indicator weights; Generate risk assessment scores based on modified weight indicators and indicator scores.

6. The customer rating method according to claim 5, characterized in that: The step of correcting the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators to obtain the corrected indicator weights includes: Obtaining the missing type and missing magnitude corresponding to the missing indicator; Determine the weight correction ratio according to the missing type and the missing magnitude; Based on the weight correction ratio, the missing indicators and the indicator weights corresponding to the correlation indicators in the indicator weights corresponding to the rating indicators are corrected to obtain the corrected indicator weights.

7. A customer rating device, characterized in that: The device comprises: The acquisition module is used to obtain the due diligence information corresponding to the customer to be rated; A construction module, used to construct rating index data based on the due diligence information; A scoring module, used to perform risk prediction based on the rating indicator data and generate a risk assessment score; The rating module is used to determine the risk level label corresponding to the customer to be rated according to the risk assessment score.

8. A customer rating device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the customer rating method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the customer rating method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the customer rating method according to any one of claims 1 to 6 are implemented.

Images