Credit granting processing method and device, equipment, medium and product

Abstract

The invention provides a credit granting processing method, device and equipment, a medium and a product, is applied to a credit granting scheme decision platform, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: determining an evaluation index of a credit extension scheme according to a service type; the evaluation indexes comprise credit indexes and current market economic indexes; establishing an index weight matrix according to the evaluation indexes; the index weight matrix represents the relative importance degree of any two evaluation indexes in the evaluation indexes; establishing a scheme weight matrix, wherein each element of the scheme weight matrix represents index data of the evaluation index under each to-be-decided scheme; and multiplying the index weight matrix and the scheme weight matrix to obtain a scheme decision matrix, and obtaining a credit extension scheme according to the relative proximity between each to-be-decided scheme and an ideal solution of the scheme decision matrix. According to the invention, the accuracy of the credit evaluation result can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a credit granting method, device, equipment, medium and product. Background Art

[0002] In the current increasingly complex and volatile financial market environment, credit assessment is a key link in the risk management of financial institutions. Its accuracy and efficiency are directly related to the quality of credit assets and the sound operation of financial institutions. Therefore, it is necessary to establish a credit processing method to evaluate the credit plan.

[0003] Some credit processing methods conduct credit assessment based on the credit-related data of users or enterprises; however, this method results in inaccurate credit assessment results due to incomplete assessment. Summary of the invention

[0004] The present application provides a credit processing method, device, equipment, medium and product to improve the accuracy of credit assessment results.

[0005] In the first aspect, the present application provides a credit processing method, which is applied to a credit scheme decision-making platform, including: determining the evaluation indicators of the credit scheme according to the business type; the evaluation indicators include credit indicators and current market economic indicators; establishing an indicator weight matrix according to the evaluation indicators; the indicator weight matrix represents the relative importance of any two evaluation indicators in the evaluation indicators; establishing a scheme weight matrix, and each element of the scheme weight matrix represents the indicator data of the evaluation indicator under each scheme to be decided; multiplying the indicator weight matrix and the scheme weight matrix to obtain a scheme decision matrix, and obtaining the credit scheme according to the relative proximity of each scheme to be decided to the ideal solution of the scheme decision matrix.

[0006] In the second aspect, the present application provides a credit processing device, which is applied to a credit scheme decision platform, including: an acquisition module, which is used to determine the evaluation indicators of the credit scheme according to the business type; the evaluation indicators include credit indicators and current market economic indicators; an establishment module, which is used to establish an indicator weight matrix according to the evaluation indicators; the indicator weight matrix represents the relative importance of any two evaluation indicators in the evaluation indicators; the establishment module is also used to establish a scheme weight matrix, and each element of the scheme weight matrix represents the indicator data of the evaluation indicator under each scheme to be decided; a processing module, which multiplies the indicator weight matrix and the scheme weight matrix to obtain a scheme decision matrix, and obtains the credit scheme according to the relative proximity of each scheme to be decided to the ideal solution of the scheme decision matrix.

[0007] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the above method.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above method.

[0009] In a fifth aspect, the present application provides a computer program product, including a computer program, which is used to implement the above method when executed by a processor.

[0010] In the credit processing method, device, equipment, medium and product provided by the present application, the evaluation index of the credit scheme is determined according to the business type; and based on the evaluation index, an index weight matrix is ​​established, wherein the index weight matrix represents the relative importance of any two evaluation indexes in the evaluation index. Then, a scheme weight matrix is ​​established according to the index data of the evaluation index under each scheme to be decided; the index weight matrix and the scheme weight matrix are multiplied to obtain the scheme decision matrix, and the credit scheme is obtained according to the relative proximity of each scheme to be decided and the ideal solution in the scheme decision matrix. The scheme of the present application determines the credit scheme by establishing a scheme decision matrix and calculating the relative proximity of each scheme to be decided and the ideal solution in the decision scheme matrix, thereby achieving accurate evaluation of the credit scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] 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.

[0012] Figure 1 A flowchart of a credit processing method is exemplarily shown;

[0013] Figure 2 A schematic diagram of a credit scheme decision platform for an example of this application;

[0014] Figure 3 A flowchart of a credit processing method is exemplarily shown;

[0015] Figure 4 A flowchart of a credit processing method is exemplarily shown;

[0016] Figure 5 A flowchart of a credit processing method is exemplarily shown;

[0017] Figure 6 Schematic diagram of the process of data storage for this application;

[0018] Figure 7 A structural diagram of a credit processing device is exemplarily shown in FIG.

[0019] Figure 8A structural schematic diagram of an electronic device is exemplarily shown in FIG.

[0020] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0021] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0022] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0023] In addition, this application involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and the use of artificial intelligence technology for automated decision-making, and a technical solution for making decisions that have a significant impact on personal rights and interests based on the results of automated decision-making. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decision-making; if the user chooses to reject, the expert decision-making process will be entered.

[0024] It should be noted that the brief description of the terms in this application is only for the convenience of understanding the implementation methods described below, and is not intended to limit the implementation methods of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings. The terms "first", "second", etc. in the specification and claims and the above-mentioned drawings in this application are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise indicated. It should be understood that the terms used in this way can be interchangeable where appropriate, for example, they can be implemented in an order other than those given in the diagram or description of the embodiment of this application. The terms "including" and "having" in the specification and claims and the above-mentioned drawings in this application and any of their variations are intended to cover but not exclusively include, for example, a product or device containing a series of components is not necessarily limited to those components clearly listed, but may include other components that are not clearly listed or inherent to these products or devices. The term "module" used in this application refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic or a combination of hardware or / and software code that can perform functions related to the element.

[0025] It should be noted that the credit processing methods, devices, equipment, media and products provided in this application can be used in the field of financial technology, and can also be used in any field other than financial technology. The application field of the credit processing methods, devices, equipment, media and products in this application is not limited.

[0026] In recent years, the state has continued to support and encourage the development of small and micro enterprises, and has actively introduced powerful credit policies to guide financial institutions to increase the first loan, renewal loan, credit loan, and medium- and long-term loan to small and micro enterprises. With the vigorous development of credit business and the upward momentum of economic development, the domestic small and micro enterprise credit business is also facing a series of problems. The lack of transparency of corporate customer information leads to the lack of credit information, making it difficult for banks to make accurate judgments on their credit status. Secondly, the efficiency of credit business processing is low, and the credit method is not scientific enough. In the current increasingly complex and changing financial market environment, credit assessment is a key link in the risk management of financial institutions. Its accuracy and efficiency are directly related to the quality of credit assets and the sound operation of financial institutions. Therefore, it is necessary to establish a credit processing method to evaluate credit.

[0027] In some credit processing methods, credit is assessed based on the credit-related data of users or enterprises; however, this solution leads to inaccurate credit assessment results due to incomplete assessment.

[0028] The technical content provided by the present application is intended to solve the above technical problems of the prior art. In the credit processing method, device, equipment, medium and product provided by the present application, the evaluation index of the credit scheme is determined according to the business type; and based on the evaluation index, an index weight matrix is ​​established, wherein the index weight matrix represents the relative importance of any two evaluation indicators in the evaluation index. Then, a scheme weight matrix is ​​established according to the indicator data of the evaluation index under each scheme to be decided; the indicator weight matrix and the scheme weight matrix are multiplied to obtain the scheme decision matrix, and the credit scheme is obtained according to the relative proximity of each scheme to be decided and the ideal solution in the scheme decision matrix. The scheme of the present application determines the credit scheme by establishing a scheme decision matrix and calculating the relative proximity of each scheme to be decided and the ideal solution in the decision scheme matrix, thereby achieving accurate evaluation of the credit scheme.

[0029] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0030] Embodiment 1

[0031] Figure 1 A flow chart of a credit processing method is shown in FIG. Figure 1 As shown, the method is applied to a credit scheme decision platform, including:

[0032] Step 102: Determine the evaluation index of the credit scheme according to the business type; the evaluation index includes credit index and current market economic index;

[0033] Step 102: Establish an indicator weight matrix based on the evaluation indicators; the indicator weight matrix represents the relative importance of any two evaluation indicators in the evaluation indicators;

[0034] Step 103: Establish a scheme weight matrix, wherein each element of the scheme weight matrix represents the index data of the evaluation index under each scheme to be decided;

[0035] Step 104: Multiply the indicator weight matrix and the solution weight matrix to obtain a solution decision matrix, and obtain a credit granting solution based on the relative proximity between each solution to be decided and the ideal solution of the solution decision matrix.

[0036] The credit processing method of the present application is applied to the credit scheme decision platform; in practical applications, the credit scheme decision platform provides comprehensive decision support for financial institutions by collecting, integrating and analyzing a large amount of financial data. Figure 2 This is a schematic diagram of a credit scheme decision platform for an example of this application; Figure 2As shown, the platform includes: a data collection and storage module and a credit processing module; when credit processing is required, the data collection and storage module obtains business data based on the front-end business interaction, the credit processing module obtains the business data in the data collection and storage module, and performs credit processing based on the business data to obtain a credit plan.

[0037] Specifically, the number and type of each evaluation index shall be determined according to the actual business type for which credit assessment is required; as an example, when credit assessment is required for multiple enterprises, the financial indicators of enterprises, such as cash ratio, return on net assets, operating profit margin, etc., need to be considered; operating indicators, such as market share, customer satisfaction, employee performance supply chain management, etc.; risk assessment, such as economic risk, legal risk, operational risk, etc. When credit assessment is conducted for multiple individuals, basic information of individuals, such as age, gender, occupation, marital status, etc., income and assets, such as salary income, investment income, real estate, vehicles and other assets, credit records, such as credit card usage, loan records, overdue records, etc. in the credit report, liabilities, such as credit card arrears, loan balances and other liabilities, stability, such as job stability, residential stability, etc. In addition, the evaluation indexes shall also consider the current market economic indicators, such as the current market supply, market demand, economic development level, etc.

[0038] After determining the type and number of evaluation indicators, establish a matrix of evaluation indicators and calculate the weight matrix corresponding to the matrix; establish the corresponding indicator weight matrix, which represents the relative importance of any two evaluation indicators; specifically, the indicator weight matrix can be expressed as:

[0039]

[0040] Among them, X1 represents the indicator weight matrix, A matrix consisting of element values ​​representing the relative importance of each evaluation index, where each element value in the matrix represents a relative importance value.

[0041] Next, establish a solution weight matrix; the element values ​​in the solution weight matrix are the actual indicator data under the evaluation indicators in the indicator weight matrix. For example, when doing a credit assessment for an individual, the element values ​​in the solution weight matrix are the individual's basic information data, property-related data, and credit-related data. It should be noted that the order of the element values ​​in the indicator weight matrix corresponds to the element values ​​in the solution weight matrix based on the evaluation indicators. Exemplarily, the solution weight matrix can be expressed as:

[0042]

[0043] Among them, A represents the scheme weight matrix, represents the corresponding weight matrix of the scheme weight matrix, It represents a data matrix composed of actual indicator data under each evaluation indicator, and the element values ​​in the matrix represent the indicator data corresponding to each evaluation indicator under each decision-making scheme.

[0044] Furthermore, the established indicator weight matrix is ​​multiplied with the solution weight matrix to obtain the solution decision matrix, which is expressed as:

[0045]

[0046] Among them, V represents the solution decision matrix, A is the aforementioned solution weight matrix, X1 represents the aforementioned indicator weight matrix, represents the weight vector corresponding to the aforementioned scheme weight matrix, A matrix representing the result of multiplying the element values ​​in the aforementioned indicator weight matrix by the element values ​​of the actual indicator data in the scenario weight matrix.

[0047] Next, the relative closeness of each solution to be decided, that is, the solution corresponding to each row in the solution decision matrix, and the ideal solution of the solution decision matrix is ​​calculated to obtain the credit plan. In this example, by establishing an indicator weight matrix and a solution weight matrix according to the business type, and multiplying the two matrices to obtain the solution decision matrix; further, the relative closeness of each solution to be decided and the ideal solution in the solution decision matrix is ​​calculated to obtain the credit plan, thereby improving the accuracy of the credit processing results.

[0048] Furthermore, it is necessary to establish an indicator weight matrix for the evaluation indicators; accordingly, as an example, Figure 3 A flowchart of a credit processing method is exemplified; based on any example, an indicator weight matrix is ​​obtained according to the evaluation indicators, including:

[0049] Step 201: construct a pairwise comparison matrix of the evaluation indicators according to the evaluation indicators;

[0050] Step 202: obtaining a first weight matrix by normalizing the element values ​​in the pairwise comparison matrix;

[0051] Step 203: multiply the pairwise comparison matrix by the first weight matrix to obtain an indicator weight matrix.

[0052] Specifically, first, according to the determined evaluation index types and quantities, a pairwise comparison matrix of evaluation indicators is established; in one example, the importance of each evaluation indicator can be scored by experts; according to the scoring results, the indicators are compared two by two to construct a pairwise comparison matrix after the two-by-two comparison. It should be noted that this example does not make specific restrictions on the scoring method for each evaluation indicator, as long as the relative importance of any two evaluation indicators can be obtained after comparison. The element values ​​in the pairwise comparison matrix are normalized to obtain the corresponding first weight matrix; this example does not limit the specific calculation method of the weight matrix. In one example, the first weight matrix corresponding to the pairwise comparison matrix can be calculated by the square root method; first, for each row in the matrix, the product of all element values ​​in each row is calculated; a vector is obtained based on the product value of the elements of all rows, the vector is raised to the nth power, and the calculation result is normalized to obtain the corresponding first weight matrix; in another example, the first weight matrix corresponding to the pairwise comparison matrix can be calculated by the summation method; first, for each row in the matrix, the sum of all element values ​​in each row is calculated; a vector is obtained based on the value of the sum of the elements of all rows, and the vector is normalized to obtain the corresponding first weight matrix. After obtaining the first weight matrix, the indicator weight matrix can be obtained by multiplying the pairwise comparison matrix and the first weight matrix. The matrix after multiplication can be expressed as:

[0053]

[0054] Where X represents the multiplication of the first weight matrix and the pairwise comparison matrix, represents the first weight matrix, represents the paired comparison matrix; the result obtained by multiplying the first weight matrix with the paired comparison matrix is ​​the aforementioned X1 indicator weight matrix. In this example, by constructing a paired comparison matrix and calculating the first weight matrix of the paired comparison matrix, the indicator weight matrix is ​​obtained by multiplying the two; the credit result obtained by subsequent credit processing based on the indicator weight matrix is ​​more accurate.

[0055] Furthermore, after constructing the indicator weight matrix, it is also necessary to perform a data consistency check on the indicator weight matrix to ensure the correctness of the establishment of the indicator weight matrix; accordingly, as an example, the method also includes:

[0056] Conduct consistency check on the indicator weight matrix;

[0057] If the verification fails, the indicator weight matrix is ​​modified; the modification process includes at least one of the following: modifying element values, changing the number of elements, and changing the indicator weight matrix.

[0058] Specifically, after the indicator weight matrix is ​​constructed, it is necessary to perform a consistency check on the indicator weight matrix; in practical applications, performing a consistency check on the matrix can ensure logical rationality. For example, if element A in the matrix is ​​more important than element B, and element B is more important than element C, then logically, element A should be more important than element C; if the elements in the matrix violate this logical law, that is, the result that element C is more important than element A appears, then the matrix violates the consistency principle and is logically unreasonable. In addition, the consistency check also ensures the accuracy of subsequent decisions. If the elements in the matrix are inconsistent, the decision results based on the matrix may be seriously affected, and even lead to wrong decisions. Exemplarily, if the indicator weight matrix fails the consistency check, it is necessary to correct the indicator weight matrix; the correction process includes modifying the values ​​of the elements in the matrix, such as re-scoring the scoring criteria of each indicator, thereby changing the element values ​​in the matrix; the number of elements in the matrix can also be changed, such as increasing or decreasing the number of some evaluation indicators; it can also be re-established by the method of re-establishing an indicator weight matrix to make it pass the consistency check. In this example, by performing consistency check on the pairwise comparison matrix, inconsistencies in the indicator weight matrix can be discovered and corrected in a timely manner, thereby improving the accuracy of credit processing.

[0059] Furthermore, the consistency check process of the evaluation index weight matrix is ​​performed, including:

[0060] Calculate the maximum eigenvalue of the indicator weight matrix;

[0061] According to the maximum eigenvalue, the consistency index of the index weight matrix is ​​calculated;

[0062] Query the random consistency indicator table to obtain the random consistency indicator;

[0063] Calculate the ratio of the consistency index to the random consistency index to obtain the consistency ratio;

[0064] If the consistency ratio is less than the preset value, the indicator weight matrix test is judged to have passed; if the consistency ratio is not less than the preset value, the indicator weight matrix test is judged to have failed.

[0065] Specifically, the consistency test of the indicator weight matrix is ​​performed by calculating the consistency ratio; firstly, the maximum eigenvalue of the indicator weight matrix is ​​calculated, and then the consistency index of the indicator weight matrix is ​​calculated according to the maximum eigenvalue. The calculation formula is:

[0066]

[0067] Among them, CI represents the consistency index, λ maxRepresents the maximum eigenvalue, and n represents the order of the indicator weight matrix. In practical applications, the consistency index of a matrix is ​​related to the maximum eigenvalue of the matrix and the order of the matrix. Next, the random consistency index corresponding to the indicator weight matrix is ​​queried by looking up the random consistency index table; in practical applications, the random consistency index is obtained by the average consistency index of multiple randomly generated judgment matrices, and its value is related to the order of the matrix. The value of the random consistency index can be obtained by looking up the corresponding table. Then calculate the consistency ratio, and the calculation formula is:

[0068] CR=CI / RI

[0069] Among them, CR represents the consistency ratio, CI represents the consistency index calculated above, and RI represents the random consistency index. If the value of the consistency ratio is less than the preset value, it is considered that the consistency check of the indicator weight matrix has passed; otherwise, the consistency check of the indicator weight matrix has failed, and the indicator weight matrix needs to be corrected as above. In this example, the consistency of the indicator weight matrix is ​​judged by calculating the consistency ratio, which improves the accuracy of establishing the indicator weight matrix.

[0070] Furthermore, it is necessary to establish a scheme weight matrix corresponding to the actual indicator data. As an example, Figure 4 The example shows a flowchart of a credit processing method; based on any example, a scheme weight matrix is ​​established, including:

[0071] Step 301, establishing an indicator data matrix according to the indicator data of the evaluation indicators under each decision-making scheme;

[0072] Step 302: Establish a second weight matrix, where the second weight matrix includes the weights of each decision-making solution;

[0073] Step 303: Calculate the product of the indicator data matrix and the second weight matrix to obtain the solution weight matrix.

[0074] Specifically, according to the indicator data of each evaluation indicator corresponding to each decision-making scheme under each decision-making scheme, an indicator data matrix is ​​established; the indicator data matrix contains the actual data of each scheme under each indicator, such as the actual consumption record data of individuals, the actual data of repayment date, the relevant data of the enterprise's operating status, etc.; then, according to each decision-making scheme, a second weight matrix is ​​established, and the second weight matrix represents the weight of each decision-making scheme. In practical applications, the second weight matrix is ​​established based on some other evaluation indicators of the decision-making scheme, such as the company's industry status, brand influence, strategic planning, etc.; personal education, social security payment, provident fund payment, etc.; it should be noted that these influencing factors are used as adjustment items of the scheme weight matrix, so that the scheme weight is established more accurately. Further, the indicator data matrix is ​​multiplied by the second weight matrix to obtain the scheme weight matrix. In this example, the scheme weight matrix obtained by calculating the product of the indicator data matrix and the second weight makes the scheme weight matrix more accurate, further improving the accuracy of subsequent credit processing.

[0075] Furthermore, it is necessary to obtain the target credit scheme based on the scheme decision matrix obtained above and conduct credit assessment; accordingly, as an example, Figure 5 A flow chart of a credit processing method is exemplarily shown; the ideal solution includes a positive ideal solution and a negative ideal solution; according to the relative proximity between each decision-making scheme and the ideal solution of the scheme decision matrix, a credit scheme is obtained, including:

[0076] Step 401, calculating the positive ideal solution and the negative ideal solution of the solution decision matrix;

[0077] Step 402, calculating the distance between each decision-making solution and the positive ideal solution and the negative ideal solution;

[0078] Step 403, obtaining the relative proximity of each decision-making solution according to the distance between each decision-making solution and the positive ideal solution and the negative ideal solution;

[0079] Step 404: The decision-making plan whose relative proximity meets the predetermined requirement is used as the credit granting plan.

[0080] Specifically, first calculate the positive ideal solution and negative ideal solution of the solution decision matrix; the formula is expressed as:

[0081]

[0082] Among them, A * represents a positive ideal solution, A - represents a negative ideal solution; It represents the matrix formed by taking the maximum value of each column in the matrix, that is, the positive ideal solution; represents the matrix formed by taking the minimum value of each column in the matrix, that is, the negative ideal solution; {A11 ,A 21 ,…A n1}, {A 12 ,A 22 ,…A n2}, {A 1m ,A 2m ,…A nm} represents the element value of each column in the matrix, n represents the row of the matrix, and m represents the column of the matrix; in practical applications, the positive ideal solution represents the best solution in all evaluation indicators, and the negative ideal solution represents the worst solution in all evaluation indicators. Furthermore, after obtaining the positive ideal solution and the negative ideal solution, the distance between each decision-making solution and the positive ideal solution, as well as the distance between each decision-making solution and the negative ideal solution are calculated. The calculation formula is:

[0083]

[0084] in, Indicates the distance between each decision-making plan and the ideal solution, v ij Represents any decision-making plan in the plan decision matrix, represents the positive ideal solution obtained above, represents the negative ideal solution obtained above; Represents the distance between any one of the schemes to be decided in the scheme decision matrix and the negative ideal solution, n represents the total number of columns in the matrix, i and j represent the current row and current column of the position of a specific element respectively; after obtaining the distance between each scheme to be decided and the positive ideal solution and the distance between each scheme to be decided and the negative ideal solution according to the aforementioned calculation formula, calculate the similarity between the scheme to be decided and the ideal solution, and take the scheme to be decided whose similarity meets the predetermined requirements as the credit scheme. Exemplarily, the schemes can be sorted from high to low according to the relative proximity, and the credit schemes can be selected in order. In this example, the credit scheme is obtained by calculating the relative proximity between each scheme to be decided and the ideal solution, thereby improving the accuracy of the credit assessment.

[0085] Furthermore, according to the distance between each decision-making scheme and the positive ideal solution and the negative ideal solution, the relative proximity of each decision-making scheme is obtained, including:

[0086] For each decision-making solution, the distance between the decision-making solution and the positive ideal solution and the distance between the decision-making solution and the negative ideal solution are summed to obtain a first result;

[0087] The ratio of the distance between the solution to be decided and the negative ideal solution to the first result is calculated to obtain the relative proximity of the solution to be decided.

[0088] Specifically, after obtaining the distance between the solution to be decided and the positive ideal solution, and the distance between the solution to be decided and the negative ideal solution, the distance between the solution to be decided and the positive ideal solution and the distance between the solution to be decided and the negative ideal solution are summed to obtain a first result; then, the ratio of the distance between the solution to be decided and the negative ideal solution to the first result is calculated to obtain a relative closeness, and the calculation formula is:

[0089]

[0090] Among them, C represents the relative proximity, Indicates the distance between the decision-making plan and the negative understanding. Indicates the distance between the solution to be decided and the correct ideal solution; the smaller the distance between the solution to be decided and the correct ideal solution, the larger the value of relative proximity C, indicating that the solution to be decided is closer to the correct ideal solution, which indicates that the solution is closer to the ideal solution; on the contrary, the larger the distance between the solution to be decided and the correct ideal solution, the smaller the value of relative proximity C, indicating that the solution to be decided is further away from the correct ideal solution, which indicates that the solution is less ideal. In this example, by calculating the relative proximity, the credit scheme is determined, which improves the accuracy of credit assessment.

[0091] Furthermore, in actual credit processing, it is necessary to obtain actual business data and current market conditions for evaluation; accordingly, as an example, the credit scheme decision platform of the present application includes a database management system and a business server; the method also includes:

[0092] Obtain business data based on front-end interaction;

[0093] Input the business data into the business server and perform data format conversion to obtain indicator data;

[0094] Store indicator data into database management system;

[0095] Obtain indicator data from the database management system.

[0096] Specifically, the credit decision platform of the present application includes a database management system for storing business data and corresponding result data; based on the actual business needs, based on the front-end business interaction, business data is obtained, and the business data includes data generated by the actual business and some current market economic environment data; further, the business data is input into the business server, and the business server converts the received business data into a data format so that the business data conforms to the format of the database management system, and stores the business data after the conversion into the data format into the database management system; afterwards, the required indicator data can be obtained from the database management system; in actual applications, the business server receives data requests from the client or other services, and verifies, converts, calculates and processes the received data; according to the processing results, the database is updated or other services are called; at the same time, the business server has high security, such as identity authentication, authorization and data encryption can be implemented to protect applications and data from unauthorized access. In this example, the business server performs a series of processing on the business data obtained based on the front-end interaction, and stores the processed data into the database management system. When credit processing is required, the required data is directly obtained from the database management system, which improves the efficiency of credit processing.

[0097] Furthermore, it is necessary to perform load balancing on the data processing flow. Accordingly, as an example, the business data is input to the business server, including:

[0098] Use load balancing to input business data to the business server.

[0099] Specifically, when using a business server for business processing, its performance needs to be optimized; exemplary, the performance of business processing is optimized through technologies such as caching, load balancing, and asynchronous processing. The business server in this example is a highly scalable business server so that functions or performance can be added as business needs change. A load balancer is used to balance the business servers so that when the business servers perform corresponding data processing, the amount of data processed by each server is relatively balanced; this example does not limit the type of load balancer, which can be any load balancer that implements load balancing or related technologies that can implement load balancing. In this example, load balancing is used to balance multiple business servers, so that when the business servers perform data processing, the performance of the business servers is optimized, the data processing efficiency is improved, and the efficiency of credit processing is further improved.

[0100] Furthermore, the indicator data includes fixed data and changed data; storing the indicator data in a database management system includes:

[0101] Synchronize all fixed data to the database management system;

[0102] Synchronize the changed data to the database management system incrementally.

[0103] Specifically, the indicator data in this example includes some fixed data and data that changes based on actual business interactions; among them, the changed data includes data generated by data query, addition and deletion operations based on specific business. This example uses full synchronization to the database management system for fixed data; and uses corresponding incremental synchronization to the database management system for changed data. In actual applications, full synchronization means that the system will transmit all data each time a synchronization operation is performed; incremental synchronization means that only the data that has changed since the last synchronization is synchronized, not all data. In actual applications, incremental synchronization and full synchronization can be used in combination. For example, full synchronization is used to establish baseline data during the initial synchronization, and then incremental synchronization is used for daily data updates and change tracking. This hybrid method can balance data consistency, synchronization efficiency and resource consumption. In this example, the data is processed by combining full synchronization and incremental synchronization, which improves the efficiency of data processing, while ensuring the integrity of the data, and further improves the accuracy and efficiency of credit processing.

[0104] Furthermore, the changed data is incrementally synchronized to the database management system, including:

[0105] Synchronize the changed data to the message queue and transmit it to the data management system through the message queue.

[0106] Specifically, for the changed data, incremental synchronization technology is used to synchronize the data to the message queue, and then the data is transmitted to the data management system through the message queue. As an example, the changed data is encapsulated into a corresponding string and then synchronized to the message queue; in actual applications, transferring data to the message queue and then to the database management system is a common data processing architecture; this process means that when the producer receives the data, the data to be processed is sent to the message queue as a message, and then the message is taken out of the message queue and stored in the database management system. In this example, transferring the changed data to the message queue and then to the database management system can effectively improve the performance, reliability and flexibility of the system.

[0107] Furthermore, the credit scheme decision platform also includes a data temporary storage system; before transmitting to the data management system through the message queue, the method also includes:

[0108] Store the changed data in the data staging system.

[0109] Specifically, the credit decision-making platform for this application also includes a data temporary storage system. After the changed data is transmitted to the message queue, the data will be stored in the corresponding data temporary storage system to realize data caching and improve the efficiency of data processing. When it is necessary to obtain actual data, you can first query whether there is relevant data from the temporary storage system, which further improves the efficiency of data processing and data acquisition.

[0110] Furthermore, the credit scheme decision platform of the present application also includes a visualization module, and the method also includes:

[0111] The indicator data is visualized through the visualization module.

[0112] Specifically, the credit scheme decision platform of the present application also includes a visualization module; when the data is stored in the database management system, the credit scheme decision platform of the present application will further hierarchically process the business data, dividing the business data into the original layer, the detail layer, and the application layer of the data, and can subsequently obtain the required data from different layers, further improving the efficiency of obtaining data. Relevant business data can be displayed through the visualization module, and users can query the corresponding indicator data through the visualization module. In this example, the corresponding data can be queried through the visualization module, which improves the efficiency of obtaining data.

[0113] Combining the above examples, Figure 6 A schematic diagram of the process of storing data for this application; Figure 6 As shown, in the data collection and storage module, based on the front-end interaction, load balancing is used at the front end of the business server to perform load balancing on multiple business servers; each business server processes the business data obtained through the front-end interaction, and then transmits it to subsequent modules through full synchronization and incremental synchronization. After a series of data layering processing, the data is stored in the database management system, and then the data is visualized through the visualization module.

[0114] In the credit processing method provided in this embodiment, the evaluation index of the credit scheme is determined according to the business type; and based on the evaluation index, an index weight matrix is ​​established, wherein the index weight matrix represents the relative importance of any two evaluation indexes in the evaluation index. Then, a scheme weight matrix is ​​established according to the index data of the evaluation index under each scheme to be decided; the index weight matrix and the scheme weight matrix are multiplied to obtain the scheme decision matrix, and the credit scheme is obtained according to the relative proximity of each scheme to be decided to the ideal solution in the scheme decision matrix. The scheme of the present application determines the credit scheme by establishing a scheme decision matrix and calculating the relative proximity of each scheme to be decided to the ideal solution in the decision scheme matrix, thereby achieving accurate evaluation of the credit scheme.

[0115] Embodiment 2

[0116] Figure 7 The schematic diagram of the structure of a credit processing device is shown as an example; the device is applied to a credit scheme decision platform, such as Figure 7 As shown, the device comprises:

[0117] The acquisition module 21 determines the evaluation index of the credit scheme according to the business type; the evaluation index includes the credit index and the current market economic index;

[0118] Establishing module 22, establishing an indicator weight matrix according to the evaluation indicators; the indicator weight matrix represents the relative importance of any two evaluation indicators in the evaluation indicators;

[0119] The establishment module 22 is also used to establish a scheme weight matrix, and each element of the scheme weight matrix represents the indicator data of the evaluation indicator under each decision-making scheme;

[0120] The processing module 23 is used to multiply the indicator weight matrix and the solution weight matrix to obtain a solution decision matrix, and obtain a credit scheme according to the relative proximity between each solution to be decided and the ideal solution of the solution decision matrix.

[0121] The credit processing method of the present application is applied to a credit scheme decision platform; in practical applications, the credit scheme decision platform provides comprehensive decision support for financial institutions by collecting, integrating and analyzing a large amount of financial data.

[0122] Specifically, the number and type of each evaluation index shall be determined according to the actual business type for which credit assessment is required; as an example, when credit assessment is required for multiple enterprises, the financial indicators of enterprises, such as cash ratio, return on net assets, operating profit margin, etc., need to be considered; operating indicators, such as market share, customer satisfaction, employee performance supply chain management, etc.; risk assessment, such as economic risk, legal risk, operational risk, etc. When credit assessment is conducted for multiple individuals, basic information of individuals, such as age, gender, occupation, marital status, etc., income and assets, such as salary income, investment income, real estate, vehicles and other assets, credit records, such as credit card usage, loan records, overdue records, etc. in the credit report, liabilities, such as credit card arrears, loan balances and other liabilities, stability, such as job stability, residential stability, etc. In addition, the evaluation indexes shall also consider the current market economic indicators, such as the current market supply, market demand, economic development level, etc.

[0123] After determining the type and number of evaluation indicators, establish a matrix of evaluation indicators and calculate the weight matrix corresponding to the matrix; establish the corresponding indicator weight matrix, which represents the relative importance of any two evaluation indicators; specifically, the indicator weight matrix can be expressed as:

[0124]

[0125] Among them, X1 represents the indicator weight matrix, A matrix consisting of element values ​​representing the relative importance of each evaluation index, where each element value in the matrix represents a relative importance value.

[0126] Next, establish a solution weight matrix; the element values ​​in the solution weight matrix are the actual indicator data under the evaluation indicators in the indicator weight matrix. For example, when doing a credit assessment for an individual, the element values ​​in the solution weight matrix are the individual's basic information data, property-related data, and credit-related data. It should be noted that the order of the element values ​​in the indicator weight matrix corresponds to the element values ​​in the solution weight matrix based on the evaluation indicators. Exemplarily, the solution weight matrix can be expressed as:

[0127]

[0128] Among them, A represents the scheme weight matrix, Represents the weight matrix corresponding to the scheme weight matrix, It represents a data matrix composed of actual indicator data under each evaluation indicator, and the element values ​​in the matrix represent the indicator data corresponding to each evaluation indicator under each decision-making scheme.

[0129] Furthermore, the established indicator weight matrix is ​​multiplied with the solution weight matrix to obtain the solution decision matrix, which is expressed as:

[0130]

[0131] Among them, V represents the solution decision matrix, A is the aforementioned solution weight matrix, X1 represents the aforementioned indicator weight matrix, represents the weight vector corresponding to the aforementioned scheme weight matrix, A matrix representing the result of multiplying the element values ​​in the aforementioned indicator weight matrix by the element values ​​of the actual indicator data in the scenario weight matrix.

[0132] Next, the relative closeness of each solution to be decided, that is, the solution corresponding to each row in the solution decision matrix, and the ideal solution of the solution decision matrix is ​​calculated to obtain the credit plan. In this example, by establishing an indicator weight matrix and a solution weight matrix according to the business type, and multiplying the two matrices to obtain the solution decision matrix; further, the relative closeness of each solution to be decided and the ideal solution in the solution decision matrix is ​​calculated to obtain the credit plan, thereby improving the accuracy of the credit processing results.

[0133] Furthermore, it is necessary to establish an indicator weight matrix of the evaluation indicators; based on any example, the indicator weight matrix is ​​obtained according to the evaluation indicators, and the establishment module 22 is specifically used for:

[0134] According to the evaluation indicators, a pairwise comparison matrix of the evaluation indicators is constructed;

[0135] According to the element values ​​in the pairwise comparison matrix, a first weight matrix is ​​obtained by normalization processing;

[0136] Multiply the pairwise comparison matrix by the first weight matrix to obtain the indicator weight matrix.

[0137] Specifically, first, according to the determined evaluation index types and quantities, a pairwise comparison matrix of evaluation indicators is established; in one example, the importance of each evaluation indicator can be scored by experts; according to the scoring results, the indicators are compared two by two to construct a pairwise comparison matrix after the two-by-two comparison. It should be noted that this example does not make specific restrictions on the scoring method for each evaluation indicator, as long as the relative importance of any two evaluation indicators can be obtained after comparison. The element values ​​in the pairwise comparison matrix are normalized to obtain the corresponding first weight matrix; this example does not limit the specific calculation method of the weight matrix. In one example, the first weight matrix corresponding to the pairwise comparison matrix can be calculated by the square root method; first, for each row in the matrix, the product of all element values ​​in each row is calculated; a vector is obtained based on the product value of the elements of all rows, the vector is raised to the nth power, and the calculation result is normalized to obtain the corresponding first weight matrix; in another example, the first weight matrix corresponding to the pairwise comparison matrix can be calculated by the summation method; first, for each row in the matrix, the sum of all element values ​​in each row is calculated; a vector is obtained based on the value of the sum of the elements of all rows, and the vector is normalized to obtain the corresponding first weight matrix. After obtaining the first weight matrix, the indicator weight matrix can be obtained by multiplying the pairwise comparison matrix and the first weight matrix. The matrix after multiplication can be expressed as:

[0138]

[0139] Where X represents the multiplication of the first weight matrix and the pairwise comparison matrix, represents the first weight matrix, represents the paired comparison matrix; the result obtained by multiplying the first weight matrix with the paired comparison matrix is ​​the aforementioned X1 indicator weight matrix. In this example, by constructing a paired comparison matrix and calculating the first weight matrix of the paired comparison matrix, the indicator weight matrix is ​​obtained by multiplying the two; the credit result obtained by subsequent credit processing based on the indicator weight matrix is ​​more accurate.

[0140] Furthermore, after constructing the indicator weight matrix, it is also necessary to perform a data consistency check on the indicator weight matrix to ensure the correctness of the establishment of the indicator weight matrix; accordingly, as an example, the device further includes: a checking module 24, which is used to:

[0141] Conduct consistency check on the indicator weight matrix;

[0142] If the verification fails, the indicator weight matrix is ​​modified; the modification process includes at least one of the following: modifying element values, changing the number of elements, and changing the indicator weight matrix.

[0143] Specifically, after the indicator weight matrix is ​​constructed, it is necessary to perform a consistency check on the indicator weight matrix; in practical applications, performing a consistency check on the matrix can ensure logical rationality. For example, if element A in the matrix is ​​more important than element B, and element B is more important than element C, then logically, element A should be more important than element C; if the elements in the matrix violate this logical law, that is, the result that element C is more important than element A appears, then the matrix violates the consistency principle and is logically unreasonable. In addition, the consistency check also ensures the accuracy of subsequent decisions. If the elements in the matrix are inconsistent, the decision results based on the matrix may be seriously affected, and even lead to wrong decisions. Exemplarily, if the indicator weight matrix fails the consistency check, it is necessary to correct the indicator weight matrix; the correction process includes modifying the values ​​of the elements in the matrix, such as re-scoring the scoring criteria of each indicator, thereby changing the element values ​​in the matrix; the number of elements in the matrix can also be changed, such as increasing or decreasing the number of some evaluation indicators; it can also be re-established by the method of re-establishing an indicator weight matrix to make it pass the consistency check. In this example, by performing consistency check on the pairwise comparison matrix, inconsistencies in the indicator weight matrix can be discovered and corrected in a timely manner, thereby improving the accuracy of credit processing.

[0144] Furthermore, the consistency check process of the evaluation index weight matrix is ​​performed, including:

[0145] Calculate the maximum eigenvalue of the indicator weight matrix;

[0146] According to the maximum eigenvalue, the consistency index of the index weight matrix is ​​calculated;

[0147] Query the random consistency indicator table to obtain the random consistency indicator;

[0148] Calculate the ratio of the consistency index to the random consistency index to obtain the consistency ratio;

[0149] If the consistency ratio is less than the preset value, the indicator weight matrix test is judged to have passed; if the consistency ratio is not less than the preset value, the indicator weight matrix test is judged to have failed.

[0150] Specifically, the consistency test of the indicator weight matrix is ​​performed by calculating the consistency ratio; firstly, the maximum eigenvalue of the indicator weight matrix is ​​calculated, and then the consistency index of the indicator weight matrix is ​​calculated according to the maximum eigenvalue. The calculation formula is:

[0151]

[0152] Among them, CI represents the consistency index, λ max Represents the maximum eigenvalue, and n represents the order of the indicator weight matrix. In practical applications, the consistency index of a matrix is ​​related to the maximum eigenvalue of the matrix and the order of the matrix. Next, the random consistency index corresponding to the indicator weight matrix is ​​queried by looking up the random consistency index table; in practical applications, the random consistency index is obtained by the average consistency index of multiple randomly generated judgment matrices, and its value is related to the order of the matrix. The value of the random consistency index can be obtained by looking up the corresponding table. Then calculate the consistency ratio, and the calculation formula is:

[0153] CR=CI / RI

[0154] Among them, CR represents the consistency ratio, CI represents the consistency index calculated above, and RI represents the random consistency index. If the value of the consistency ratio is less than the preset value, it is considered that the consistency check of the indicator weight matrix has passed; otherwise, the consistency check of the indicator weight matrix has failed, and the indicator weight matrix needs to be corrected as above. In this example, the consistency of the indicator weight matrix is ​​judged by calculating the consistency ratio, which improves the accuracy of establishing the indicator weight matrix.

[0155] Furthermore, it is necessary to establish a solution weight matrix corresponding to the actual indicator data; the establishment module 22 is also specifically used for:

[0156] According to the indicator data of the evaluation indicators under each decision-making plan, establish an indicator data matrix;

[0157] Establishing a second weight matrix, the second weight matrix includes the weights of each decision-making solution;

[0158] The product of the indicator data matrix and the second weight matrix is ​​calculated to obtain the solution weight matrix.

[0159] Specifically, according to the indicator data of each evaluation indicator corresponding to each decision-making scheme under each decision-making scheme, an indicator data matrix is ​​established; the indicator data matrix contains the actual data of each scheme under each indicator, such as the actual consumption record data of individuals, the actual data of repayment date, the relevant data of the enterprise's operating status, etc.; then, according to each decision-making scheme, a second weight matrix is ​​established, and the second weight matrix represents the weight of each decision-making scheme. In practical applications, the second weight matrix is ​​established based on some other evaluation indicators of the decision-making scheme, such as the company's industry status, brand influence, strategic planning, etc.; personal education, social security payment, provident fund payment, etc.; it should be noted that these influencing factors are used as adjustment items of the scheme weight matrix, so that the scheme weight is established more accurately. Further, the indicator data matrix is ​​multiplied by the second weight matrix to obtain the scheme weight matrix. In this example, the scheme weight matrix obtained by calculating the product of the indicator data matrix and the second weight makes the scheme weight matrix more accurate, further improving the accuracy of subsequent credit processing.

[0160] Furthermore, it is necessary to obtain a target credit scheme according to the scheme decision matrix obtained above and perform credit assessment; accordingly, as an example, the ideal solution includes a positive ideal solution and a negative ideal solution; according to the relative proximity between each scheme to be decided and the ideal solution of the scheme decision matrix, a credit scheme is obtained, and the processing module 23 is used to:

[0161] Calculate the positive and negative ideal solutions of the alternative decision matrix;

[0162] Calculate the distance between each decision-making plan and the positive ideal solution and the negative ideal solution;

[0163] According to the distance between each decision-making scheme and the positive ideal solution and the negative ideal solution, the relative closeness of each decision-making scheme is obtained;

[0164] Step 404: The decision-making plan whose relative proximity meets the predetermined requirement is used as the credit granting plan.

[0165] Specifically, first calculate the positive ideal solution and negative ideal solution of the solution decision matrix; the formula is expressed as:

[0166]

[0167] Among them, A * represents a positive ideal solution, A - represents a negative ideal solution; It represents the matrix formed by taking the maximum value of each column in the matrix, that is, the positive ideal solution; represents the matrix formed by taking the minimum value of each column in the matrix, that is, the negative ideal solution; {A 11 ,A 21 ,…A n1}, {A 12 ,A 22 ,…A n2}, {A 1m ,A 2m ,…A nm} represents the element value of each column in the matrix, n represents the row of the matrix, and m represents the column of the matrix; in practical applications, the positive ideal solution represents the best solution in all evaluation indicators, and the negative ideal solution represents the worst solution in all evaluation indicators. Furthermore, after obtaining the positive ideal solution and the negative ideal solution, the distance between each decision-making solution and the positive ideal solution, as well as the distance between each decision-making solution and the negative ideal solution are calculated. The calculation formula is:

[0168]

[0169] in, Indicates the distance between each decision-making plan and the ideal solution, v ij Represents any decision-making plan in the plan decision matrix, represents the positive ideal solution obtained above, represents the negative ideal solution obtained above; Represents the distance between any one of the schemes to be decided in the scheme decision matrix and the negative ideal solution, n represents the total number of columns in the matrix, i and j represent the current row and current column of the position of a specific element respectively; after obtaining the distance between each scheme to be decided and the positive ideal solution and the distance between each scheme to be decided and the negative ideal solution according to the aforementioned calculation formula, calculate the similarity between the scheme to be decided and the ideal solution, and take the scheme to be decided whose similarity meets the predetermined requirements as the credit scheme. Exemplarily, the schemes can be sorted from high to low according to the relative proximity, and the credit schemes can be selected in order. In this example, the credit scheme is obtained by calculating the relative proximity between each scheme to be decided and the ideal solution, thereby improving the accuracy of the credit assessment.

[0170] Furthermore, according to the distance between each decision-making scheme and the positive ideal solution and the negative ideal solution, the relative proximity of each decision-making scheme is obtained, including:

[0171] For each decision-making solution, the distance between the decision-making solution and the positive ideal solution and the distance between the decision-making solution and the negative ideal solution are summed to obtain a first result;

[0172] The ratio of the distance between the solution to be decided and the negative ideal solution to the first result is calculated to obtain the relative proximity of the solution to be decided.

[0173] Specifically, after obtaining the distance between the solution to be decided and the positive ideal solution, and the distance between the solution to be decided and the negative ideal solution, the distance between the solution to be decided and the positive ideal solution and the distance between the solution to be decided and the negative ideal solution are summed to obtain a first result; then, the ratio of the distance between the solution to be decided and the negative ideal solution to the first result is calculated to obtain a relative closeness, and the calculation formula is:

[0174]

[0175] Among them, C represents the relative proximity, Indicates the distance between the decision-making plan and the negative understanding. Indicates the distance between the solution to be decided and the correct ideal solution; the smaller the distance between the solution to be decided and the correct ideal solution, the larger the value of relative proximity C, indicating that the solution to be decided is closer to the correct ideal solution, which indicates that the solution is closer to the ideal solution; on the contrary, the larger the distance between the solution to be decided and the correct ideal solution, the smaller the value of relative proximity C, indicating that the solution to be decided is further away from the correct ideal solution, which indicates that the solution is less ideal. In this example, by calculating the relative proximity, the credit scheme is determined, which improves the accuracy of credit assessment.

[0176] Furthermore, in actual credit processing, it is necessary to obtain actual business data and current market conditions for evaluation; the credit scheme decision platform of this application includes a database management system and a business server; an acquisition module 21 is used to:

[0177] Obtain business data based on front-end interaction;

[0178] Input the business data into the business server and perform data format conversion to obtain indicator data;

[0179] Store indicator data into database management system;

[0180] Obtain indicator data from the database management system.

[0181] Specifically, the credit decision platform of the present application includes a database management system for storing business data and corresponding result data; based on the actual business needs, based on the front-end business interaction, business data is obtained, and the business data includes data generated by the actual business and some current market economic environment data; further, the business data is input into the business server, and the business server converts the received business data into a data format so that the business data conforms to the format of the database management system, and stores the business data after the conversion into the data format into the database management system; afterwards, the required indicator data can be obtained from the database management system; in actual applications, the business server receives data requests from the client or other services, and verifies, converts, calculates and processes the received data; according to the processing results, the database is updated or other services are called; at the same time, the business server has high security, such as identity authentication, authorization and data encryption can be implemented to protect applications and data from unauthorized access. In this example, the business server performs a series of processing on the business data obtained based on the front-end interaction, and stores the processed data into the database management system. When credit processing is required, the required data is directly obtained from the database management system, which improves the efficiency of credit processing.

[0182] Furthermore, it is necessary to perform load balancing on the data processing flow. Accordingly, as an example, the business data is input to the business server, including:

[0183] Use load balancing to input business data to the business server.

[0184] Specifically, when using a business server for business processing, its performance needs to be optimized; exemplary, the performance of business processing is optimized through technologies such as caching, load balancing, and asynchronous processing. The business server in this example is a highly scalable business server so that functions or performance can be added as business needs change. A load balancer is used to balance the business servers so that when the business servers perform corresponding data processing, the amount of data processed by each server is relatively balanced; this example does not limit the type of load balancer, which can be any load balancer that implements load balancing or related technologies that can implement load balancing. In this example, load balancing is used to balance multiple business servers, so that when the business servers perform data processing, the performance of the business servers is optimized, the data processing efficiency is improved, and the efficiency of credit processing is further improved.

[0185] Furthermore, the indicator data includes fixed data and changed data; storing the indicator data in a database management system includes:

[0186] Synchronize all fixed data to the database management system;

[0187] Synchronize the changed data to the database management system incrementally.

[0188] Specifically, the indicator data in this example includes some fixed data and data that changes based on actual business interactions; among them, the changed data includes data generated by data query, addition and deletion operations based on specific business. This example uses full synchronization to the database management system for fixed data; and uses corresponding incremental synchronization to the database management system for changed data. In actual applications, full synchronization means that the system will transmit all data each time a synchronization operation is performed; incremental synchronization means that only the data that has changed since the last synchronization is synchronized, not all data. In actual applications, incremental synchronization and full synchronization can be used in combination. For example, full synchronization is used to establish baseline data during the initial synchronization, and then incremental synchronization is used for daily data updates and change tracking. This hybrid method can balance data consistency, synchronization efficiency and resource consumption. In this example, the data is processed by combining full synchronization and incremental synchronization, which improves the efficiency of data processing, while ensuring the integrity of the data, and further improves the accuracy and efficiency of credit processing.

[0189] Furthermore, the changed data is incrementally synchronized to the database management system, including:

[0190] Synchronize the changed data to the message queue and transmit it to the data management system through the message queue.

[0191] Specifically, for the changed data, incremental synchronization technology is used to synchronize the data to the message queue, and then the data is transmitted to the data management system through the message queue. As an example, the changed data is encapsulated into a corresponding string and then synchronized to the message queue; in actual applications, transferring data to the message queue and then to the database management system is a common data processing architecture; this process means that when the producer receives the data, the data to be processed is sent to the message queue as a message, and then the message is taken out of the message queue and stored in the database management system. In this example, transferring the changed data to the message queue and then to the database management system can effectively improve the performance, reliability and flexibility of the system.

[0192] Furthermore, the credit scheme decision platform also includes a data temporary storage system; before being transmitted to the data management system through the message queue, it includes:

[0193] Store the changed data in the data staging system.

[0194] Specifically, the credit decision-making platform for this application also includes a data temporary storage system. After the changed data is transmitted to the message queue, the data will be stored in the corresponding data temporary storage system to realize data caching and improve the efficiency of data processing. When it is necessary to obtain actual data, you can first query whether there is relevant data from the temporary storage system, which further improves the efficiency of data processing and data acquisition.

[0195] Furthermore, the credit scheme decision platform of the present application also includes a visualization module, an acquisition module 21, which is also used for:

[0196] The indicator data is visualized through the visualization module.

[0197] Specifically, the credit scheme decision platform of the present application also includes a visualization module; when the data is stored in the database management system, the credit scheme decision platform of the present application will further hierarchically process the business data, dividing the business data into the original layer, the detail layer, and the application layer of the data, and can subsequently obtain the required data from different layers, further improving the efficiency of obtaining data. Relevant business data can be displayed through the visualization module, and users can query the corresponding indicator data through the visualization module. In this example, the corresponding data can be queried through the visualization module, which improves the efficiency of obtaining data.

[0198] The credit processing device provided in this embodiment determines the evaluation index of the credit scheme according to the business type; and establishes an index weight matrix based on the evaluation index, wherein the index weight matrix represents the relative importance of any two evaluation indexes in the evaluation index. Then, a scheme weight matrix is ​​established according to the index data of each scheme to be decided under the evaluation index; the index weight matrix and the scheme weight matrix are multiplied to obtain the scheme decision matrix, and the credit scheme is obtained according to the relative proximity between each scheme to be decided and the ideal solution in the scheme decision matrix. The scheme of the present application determines the credit scheme by establishing a scheme decision matrix and calculating the relative proximity between each scheme to be decided and the ideal solution in the decision scheme matrix, thereby achieving accurate evaluation of the credit scheme.

[0199] Embodiment 3

[0200] Figure 8 exemplarily shows a structural schematic diagram of an electronic device, the device comprising:

[0201] The device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, the memory 292, and the communication interface 293 may communicate with each other through the bus 294. The communication interface 293 may be used for information transmission. The processor 291 may call the logic instructions in the memory 292 to execute the above-mentioned example method.

[0202] In addition, the logic instructions in the above-mentioned memory 292 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0203] The memory 292 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, that is, implementing the methods in the above method examples.

[0204] The memory 292 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 292 may include a high-speed random access memory and may also include a non-volatile memory.

[0205] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method in any embodiment.

[0206] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the method in any embodiment when executed by a processor.

[0207] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0208] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0209] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0210] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0211] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0212] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0213] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0214] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0215] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A credit processing method, characterized in that: Applied to a credit scheme decision platform, the method includes: Determine the evaluation indicators of the credit scheme according to the business type; the evaluation indicators include credit indicators and current market economic indicators; According to the evaluation indicators, an indicator weight matrix is ​​established; the indicator weight matrix represents the relative importance of any two evaluation indicators among the evaluation indicators; Establishing a scheme weight matrix, wherein each element of the scheme weight matrix represents the indicator data of the evaluation indicator under each scheme to be decided; The indicator weight matrix and the solution weight matrix are multiplied to obtain a solution decision matrix, and the credit scheme is obtained according to the relative proximity between each of the solutions to be decided and the ideal solution of the solution decision matrix.

2. The method according to claim 1, characterized in that The indicator weight matrix is ​​obtained according to the evaluation indicators, including: According to the evaluation indicators, construct a pairwise comparison matrix of the evaluation indicators; According to the element values ​​in the pairwise comparison matrix, a first weight matrix is ​​obtained by normalization processing; The pairwise comparison matrix is ​​multiplied by the first weight matrix to obtain the indicator weight matrix.

3. The method according to claim 1, characterized in that: The method further comprises: Performing consistency check on the indicator weight matrix; If the verification fails, the indicator weight matrix is ​​modified; the modification process includes at least one of the following: modifying element values, changing the number of elements, and changing the evaluation indicator weight matrix.

4. The method according to claim 3, characterized in that The consistency check process of the evaluation index weight matrix includes: Calculate the maximum eigenvalue of the indicator weight matrix; Calculating the consistency index of the index weight matrix according to the maximum eigenvalue; Query the random consistency indicator table to obtain the random consistency indicator; Calculating the ratio of the consistency index to the random consistency index to obtain a consistency ratio; If the consistency ratio is less than a preset value, it is determined that the indicator weight matrix test has passed; if the consistency ratio is not less than the preset value, it is determined that the indicator weight matrix test has failed.

5. The method according to claim 1, characterized in that The step of establishing a scheme weight matrix includes: Establishing an indicator data matrix according to the indicator data of the evaluation indicator under each decision-making scheme; Establishing a second weight matrix, wherein the second weight matrix includes weights of the solutions to be decided; The product of the indicator data matrix and the second weight matrix is ​​calculated to obtain the scheme weight matrix.

6. The method according to claim 1, characterized in that The ideal solution includes a positive ideal solution and a negative ideal solution; the credit scheme is obtained according to the relative proximity between each decision-making scheme and the ideal solution of the scheme decision matrix, including: Calculating positive ideal solutions and negative ideal solutions of the decision matrix of the scheme; Calculating the distances between each of the to-be-decided solutions and the positive ideal solution and the negative ideal solution; Obtaining the relative proximity of each of the to-be-decided solutions according to the distances between each of the to-be-decided solutions and the positive ideal solution and the negative ideal solution; The decision-making plan whose relative proximity meets the predetermined requirements is used as the credit granting plan.

7. The method according to claim 6, characterized in that The obtaining the relative proximity of each of the solutions to be decided according to the distances between each of the solutions to be decided and the positive ideal solution and the negative ideal solution includes: For each solution to be decided, summing up the distance between the solution to be decided and the positive ideal solution, and the distance between the solution to be decided and the negative ideal solution, to obtain a first result; The ratio of the distance between the solution to be decided and the negative ideal solution to the first result is calculated to obtain the relative proximity of the solution to be decided.

8. The method according to claim 5, characterized in that The credit scheme decision platform includes a database management system and a business server; the method also includes: Obtain business data based on front-end interaction; Inputting the business data into the business server, performing data format conversion processing to obtain the indicator data; storing the indicator data in the database management system; The indicator data is obtained from the database management system.

9. The method according to claim 8, characterized in that The step of inputting the business data into the business server comprises: The service data is input to the service server using load balancing.

10. The method according to claim 8, characterized in that The indicator data includes fixed data and changed data; storing the indicator data in the database management system includes: Synchronizing the fixed data in full to the database management system; The changed data is synchronized to the database management system in increments.

11. The method according to claim 10, characterized in that The step of synchronizing the changed data to the database management system in increments includes: The changed data is synchronized to a message queue, and transmitted to the data management system via the message queue.

12. The method according to claim 11, characterized in that The credit scheme decision platform also includes a data temporary storage system; before the message is transmitted to the data management system through the message queue, the method also includes: The changed data is stored in the data temporary storage system.

13. The method according to any one of claims 1 to 12, characterized in that: The credit scheme decision platform further includes a visualization module, and the method further includes: The indicator data is visualized through the visualization module.

14. A credit processing device, characterized in that: Applied to a credit scheme decision platform, the device comprises: An acquisition module is used to determine evaluation indicators of the credit scheme according to the business type; the evaluation indicators include credit indicators and current market economic indicators; An establishment module is used to establish an indicator weight matrix according to the evaluation indicators; the indicator weight matrix represents the relative importance of any two evaluation indicators among the evaluation indicators; The establishment module is also used to establish a scheme weight matrix, wherein each element of the scheme weight matrix represents the index data of the evaluation index under each scheme to be decided; The processing module multiplies the indicator weight matrix and the solution weight matrix to obtain a solution decision matrix, and obtains a credit granting solution according to the relative proximity between each of the solutions to be decided and the ideal solution of the solution decision matrix.

15. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 13 when executed by a processor.

17. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 13 when being executed by a processor.

Images