Credit rating determination method and device based on government affair data, equipment and medium

Abstract

The invention provides a credit rating determination method and device based on government affair data, equipment and a medium. Comprising the steps of obtaining government affair data of a target object from a front database through ETL, determining information dimensions included in the government affair data, and classifying the government affair data under each information dimension to obtain index data table items of the government affair data; determining an index reference value of each type of index in the index data table item; determining the index weight of each index, and determining a dimension reference value corresponding to each information dimension according to the index reference value of the index and the corresponding index weight; determining a credit reference value of the target object according to each dimension reference value and the corresponding dimension weight; comparing the credit reference value with the credit threshold interval, and determining the credit level of the target object; therefore, the data dimension is perfected, the accuracy of enterprise evaluation is improved, and the credit status of the enterprise is evaluated more comprehensively.

Description

Technical Field

[0001] This application relates to the field of data analysis, and in particular, to a method, device, equipment, and medium for determining credit ratings based on government affairs data. Background Art

[0002] In recent years, fintech technologies have developed rapidly. Among them, the specific applications of big data and large models in the fintech field have become increasingly widespread. This provides a basis for realizing financial services between enterprises and financial institutions through fintech technologies. Typical application scenarios in the fintech field include: financial risk and credit assessment of enterprises, and its technical essence involves related technologies of data collection and data analysis.

[0003] In the prior art, to conduct credit assessment on an enterprise, a large amount of original data needs to be collected, including credit investigation data and in-house account transaction data as the data source basis for data analysis and data processing.

[0004] However, the prior art has the problem that the data analysis results are inaccurate. Summary of the Invention

[0005] This application provides a method, device, equipment, and medium for determining credit ratings based on government affairs data to solve the problem that the data analysis results in the prior art are inaccurate.

[0006] In a first aspect, this application provides a method for determining a credit rating based on government affairs data, including:

[0007] Obtain the government affairs data of the target object from the front-end database through ETL, determine the information dimensions included in the government affairs data, and classify the government affairs data under each information dimension to obtain the index data table items of the government affairs data;

[0008] Determine the index reference values of various types of indexes in the index data table items;

[0009] Determine the index weights of each index, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight;

[0010] Determine the credit reference value of the target object according to each dimension reference value and its corresponding dimension weight;

[0011] Compare the credit reference value with the credit threshold interval to determine the credit rating of the target object.

[0012] In the embodiments of this application, each index type includes discrete data or continuous data; determining the index reference values of various types of indexes in the index data table items includes:

[0013] If the data of the indicator is discrete, determine the indicator value and the indicator score in the indicator data table entry;

[0014] Determine the indicator reference value of the discrete indicator according to the indicator value and the indicator score;

[0015] If the data type of the indicator is continuous, determine the value range critical value of the indicator value in the indicator data table and the indicator score;

[0016] Determine the indicator reference value of the continuous indicator according to the value range critical value of the indicator value and the indicator score.

[0017] In the embodiment of the present application, determine the indicator weight of each indicator, and determine the dimension reference value corresponding to each information dimension according to the indicator reference value of the indicator and its corresponding indicator weight, including:

[0018] Based on the indicator data table entry, determine the effective indicators under the information dimension and their corresponding indicator weights;

[0019] According to the indicator weights of the effective indicators, determine the sum of the effective weights of all the effective indicators;

[0020] According to the indicator weights of the effective indicators and the sum of the effective weights, determine the effective weights of the effective indicators;

[0021] According to the effective weight of each effective indicator and its corresponding indicator reference value, determine the dimension reference value corresponding to the information dimension.

[0022] In the embodiment of the present application, based on the indicator data table entry, determine the effective indicators under the information dimension and their corresponding indicator weights, including:

[0023] Based on the indicator data table entry, determine the variable values and missing values of each indicator under the information dimension;

[0024] According to the variable values and missing values of each indicator, determine the effective indicators.

[0025] In the embodiment of the present application, according to the indicator weights of the effective indicators, determine the sum of the effective weights of all the effective indicators, including:

[0026] According to the indicator weights of the effective indicators, determine the sum of the weights of all the effective indicators;

[0027] Compare the sum of the weights with a preset effective weight threshold;

[0028] If the sum of the weights is lower than the effective weight threshold, determine that the dimension reference value of the information dimension is a null value;

[0029] If the sum of the weights is not lower than the effective weight threshold, determine that the sum of the weights is the sum of the effective weights.

[0030] In an embodiment of the present application, after comparing the credit reference value with the credit threshold range to determine the credit level of the target object, the method further includes:

[0031] Determine the rule indicators of the target object according to the index data table items;

[0032] Compare the rule indicators with the rule level range to obtain the rule level corresponding to the rule indicators;

[0033] Compare the credit level with the rule level, and determine the target credit level of the target object according to the comparison result.

[0034] In an embodiment of the present application, comparing the credit level with the rule level, and determining the target credit level of the target object according to the comparison result includes:

[0035] Compare the credit level with the rule level;

[0036] If the comparison result is that the credit level is the same as the rule level, determine that the target credit level is the same level;

[0037] If the comparison result is that the credit level is different from the rule level, determine that the target credit level is the lower level of the credit level and the rule level.

[0038] In an embodiment of the present application, after comparing the credit reference value with the credit threshold range to determine the credit level of the target object, the method further includes:

[0039] Send the target credit level of the target object to the credit level application system, so that the credit level application system determines the credit of the target object according to the target credit level.

[0040] In a second aspect, the present application provides a credit level determination device based on government affairs data. The device includes:

[0041] A data acquisition module, configured to obtain the government affairs data of the target object from the front-end database through ETL, determine the information dimensions included in the government affairs data, and classify the government affairs data under each information dimension to obtain the index data table items of the government affairs data;

[0042] An index reference value determination module, configured to determine the index reference values of various types of indexes in the index data table items;

[0043] A dimension reference value determination module, configured to determine the index weights of each index, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight;

[0044] A credit reference value determination module, configured to determine the credit reference value of the target object according to each dimension reference value and its corresponding dimension weight;

[0045] A credit rating determination module, configured to compare a credit reference value with a credit threshold range to determine the credit rating of a target object.

[0046] Thirdly, the present application provides a device, including: a processor, and a memory communicatively connected to the processor;

[0047] The memory stores computer-executable instructions;

[0048] The processor executes the computer-executable instructions stored in the memory to implement the method of the present application.

[0049] Fourthly, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the method of the present application.

[0050] The credit rating determination method, device, equipment and medium based on government affairs data provided by the present application obtain the government affairs data of the target object from the front-end database through ETL, determine the information dimensions included in the government affairs data and classify the government affairs data under each information dimension to obtain the index data table items of the government affairs data; determine the index reference values of various types of indexes in the index data table items; determine the index weights of each index, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight; determine the credit reference value of the target object according to each dimension reference value and its corresponding dimension weight; compare the credit reference value with the credit threshold range to determine the credit rating of the target object.

[0051] In this way, by obtaining government affairs data and separately constructing a database, the dimension source of the data is improved, the timed automatic batch update of the enterprise credit data analysis result is realized, and the rating indexes more reflect the business conditions and credit history of the enterprise, so as to more accurately evaluate the credit status of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings here are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0053] Figure 1 It is a system schematic diagram of a method for determining a credit rating based on government affairs data provided by an embodiment of the present application;

[0054] Figure 2 It is a flowchart schematic diagram of a method for determining a credit rating based on government affairs data provided by an embodiment of the present application;

[0055] Figure 3 It is a structural schematic diagram of a device for determining a credit rating based on government affairs data provided by an embodiment of the present application;

[0056] Figure 4 This is a structural block diagram of a device for implementing the method for determining a credit rating based on government affairs data according to an embodiment of the present application.

[0057] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter; these drawings and textual descriptions are not intended to limit the scope of the concept 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 implementation manners

[0058] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0059] ETL (Extract-Transform-Load) is a tool for extracting, transforming, and loading data from a source end to a destination end, and is used to process the received data into the data required by an enterprise credit scoring and credit rating classification system and save it to an application database.

[0060] The pre-database is a repository for storing data provided by a data provider, so that the ETL tool can obtain the government affairs data of an enterprise from the pre-database and perform data processing.

[0061] In the prior art, the data source dimension of enterprise credit evaluation is less, and the modeling samples are not fully covered. Only a small amount of online data can be used as the rating basis. This part of the data cannot fully represent the advantages and disadvantages of an enterprise's operation status; at the same time, the quality of some data is poor, most fields are vacant, and the data application scenarios are missing, resulting in inaccurate data analysis results of the credit rating.

[0062] To solve the above problems, an embodiment of the present application proposes a method for determining a credit rating based on government affairs data, which improves the data source dimension of enterprise data. Based on the government affairs data samples of an enterprise, through data modeling, the enterprise rating analysis results are automatically updated in batches at regular intervals. Compared with traditional credit ratings, the rating indicators of the present application reflect more different data dimensions of an enterprise, so as to analyze the government affairs data of an enterprise more comprehensively and improve the accuracy of obtaining the credit rating analysis of an enterprise.

[0063] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be elaborated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0064] Figure 1 It is a schematic diagram of a system for a method of determining credit levels based on government affairs data provided by an embodiment of this application. The credit level determination system may include devices such as a pre-exchange database, an ETL tool, an application database, an enterprise credit scoring and credit level classification system, and a result application system.

[0065] Among them, the pre-exchange database is used to store the enterprise government affairs data provided by the data provider, so that the ETL tool can obtain the enterprise government affairs data from the pre-exchange database. The government affairs data is collected by the service platforms of each administrative agency, and after preprocessing such as data cleaning and filtering, it is stored through the constructed pre-exchange database. It may include data related to enterprise government affairs such as the shareholder information, industrial and commercial market information, litigation information, business tax payment information, etc. of each subject object, which more reflects the business conditions and credit history of the enterprise and helps to more comprehensively evaluate the credit status of the enterprise. It should be noted that the data involved in this application are all data that can be publicly queried or obtained by administrative agencies, and do not involve the privacy information of the subject object. The query or acquisition channels are authorized or certified by administrative agencies, and the query or acquisition behavior is legal and compliant.

[0066] The ETL tool is used to obtain the government affairs data from the pre-exchange database and process the received government affairs data, so as to obtain the data required by the enterprise credit scoring and credit level classification system and save it to the application database.

[0067] The application database is used to store the government affairs data processed by the ETL tool, so that the enterprise credit scoring and credit level classification system can read the processed data.

[0068] The enterprise credit scoring and credit level classification system is used to process the data in the application database, so as to generate the information credit score and level classification data of the enterprise and save it to the application database for the result application system to read.

[0069] The result application system is used to read the enterprise credit score and credit level classification data in the application database.

[0070] Based on this, through the credit rating determination system, the data provider regularly synchronizes data to the pre-exchange database; uses the ETL tool to load, transform, and load the data on the pre-exchange database into the application database; the enterprise credit scoring and credit rating classification system processes the data, and after the processing is completed, it is saved to the application database; the result application system uses the enterprise credit scoring and classification data.

[0071] Figure 2 It is a schematic flowchart of a method for determining credit rating based on government affairs data provided by an embodiment of this application. As Figure 2 shown, the execution entity can be a credit rating determination system. The method for determining credit rating based on government affairs data may include the following steps:

[0072] S210. Obtain the government affairs data of the target object from the pre-database through ETL, determine the information dimensions included in the government affairs data, and classify the government affairs data under each information dimension to obtain the index data table items of the government affairs data.

[0073] Among them, the target object can be the target enterprise that needs to determine the credit rating.

[0074] The information dimension can be understood as a certain type of information data of the enterprise. Each information dimension can include multiple categories of government affairs data. For example, the information dimension can be the enterprise basic information dimension, and the enterprise basic information dimension can include data such as the establishment years of the enterprise and the subscribed registered capital.

[0075] The index data table item is the government affairs data index table obtained by classifying the government affairs data according to the data index, including the government affairs data under different information dimensions, so as to determine the credit reference value and credit rating of the enterprise according to the data in the index data table item later. Among them, the data index includes multiple indexes such as index type, index value, index score value, and index missing value.

[0076] Based on this, the ETL tool determines the government affairs data related to the enterprise in the pre-database, such as shareholder information, industrial and commercial market information, business tax payment information, etc. data, determines the data extraction priority level and abnormal data processing measures according to the data quality and update frequency of each data source, so as to integrate the information with the same meaning together, and finally generates a unique primary key ID with the enterprise social credit code to concatenate all field information, forming a data wide table under different dimensions, so as to determine the credit reference value and credit rating of the enterprise according to the generated index data table items later.

[0077] S220. Determine the index reference values of each type of index in the index data table item.

[0078] Among them, the index reference value is the reference value of the enterprise for this index, which is used to determine the credit reference value of the enterprise subsequently. The completion degree of this index of the enterprise can be evaluated according to the index reference value.

[0079] Based on this, by determining the index reference values of each index in the index data table item, the credit reference value and credit rating of the enterprise can be determined subsequently according to the index reference values.

[0080] S230. Determine the index weights of each index, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight.

[0081] Among them, the index weight is the weight value of each index under the information dimension.

[0082] The dimension reference value is the reference value of the information dimension corresponding to the index, which is used to determine the credit reference value of the enterprise subsequently. The completion degree of the enterprise in this dimension can be evaluated according to the dimension reference value.

[0083] Based on this, through the index weights and index reference values of each index under the information dimension, the dimension reference value corresponding to this information dimension is determined, so that the credit reference value and credit rating of the enterprise can be determined subsequently according to the dimension reference value of the information dimension.

[0084] S240. Determine the credit reference value of the target object according to each dimension reference value and its corresponding dimension weight.

[0085] Among them, the credit reference value represents the credit value of the enterprise, and the credit rating of the enterprise can be determined according to the credit reference value.

[0086] Based on this, through the dimension reference value and dimension weight of the information dimension, the credit reference value of the enterprise is determined, so that the credit rating of the enterprise can be determined subsequently according to the credit reference value.

[0087] S250. Compare the credit reference value with the credit threshold interval to determine the credit rating of the target object.

[0088] Among them, the credit threshold interval is used to represent the corresponding relationship between the credit reference value and credit rating of the enterprise. For example, if the credit reference value of the enterprise is [100, 64.5), the corresponding credit rating can be AAA.

[0089] Based on this, by comparing the credit reference value with the credit threshold interval, the credit rating corresponding to the credit reference value of the enterprise is determined.

[0090] On the basis of the above embodiments, the present application further provides a feasible implementation manner for S220 to determine the index reference value, including:

[0091] If the data of the indicator is discrete, determine the indicator value and the indicator score in the indicator data table item;

[0092] Determine the indicator reference value of the discrete indicator according to the indicator value and the indicator score;

[0093] If the data type of the indicator is continuous, determine the value range critical value of the indicator value in the indicator data table and the indicator score;

[0094] Determine the indicator reference value of the continuous indicator according to the value range critical value of the indicator value and the indicator score.

[0095] Among them, the indicator value is a preset indicator numerical value, representing the preset score of this indicator, and is used to calculate the indicator reference value of the indicator.

[0096] The indicator score represents the score situation corresponding to each indicator under this information dimension. The indicator value and the indicator score are used to determine the indicator reference value of the discrete indicator.

[0097] The value range critical value is the value range critical value of the continuous indicator, including the upper critical value and the lower critical value. According to the value range critical value, the value range interval corresponding to the indicator can be determined, and the reference value of the indicator can be determined within this value range.

[0098] Based on this, by determining the data type of the indicator, the method for determining the corresponding reference value of the indicator is determined, and then the indicator reference value of this indicator is obtained; for example, if the indicator is a discrete indicator, the indicator reference value can be calculated according to the corresponding relationship between the indicator value and the indicator score. If the indicator is a continuous indicator, it can be based on

[0099] Obtain the reference value of the indicator.

[0100] On the basis of the above embodiments, the present application further provides a feasible implementation manner for S230 to determine the dimension reference value, including:

[0101] Based on the indicator data table item, determine the valid indicators under the information dimension and their corresponding indicator weights;

[0102] According to the indicator weights of the valid indicators, determine the sum of the valid weights of all valid indicators;

[0103] According to the indicator weights of the valid indicators and the sum of the valid weights, determine the valid weights of the valid indicators;

[0104] According to the valid weight of each valid indicator and its corresponding indicator reference value, determine the dimension reference value corresponding to the information dimension.

[0105] Among them, the valid indicators include the indicators with non-null variable values and the indicators with missing values assigned scores; the valid weights of the valid indicators represent the proportion of the valid indicators to all valid indicators, and can be obtained based on the indicator weights and valid weights of the valid indicators. For example, if the indicator weight of a valid indicator is A and the sum of the valid weights of all valid indicators is B, then the valid weight of this valid indicator is A / B.

[0106] Based on this, by determining the valid indicators and their sum of valid indicator weights under the information dimension, and according to the indicator weights of each valid indicator and the sum of valid weights of the information dimension, the valid weights of each valid indicator are obtained. Then, based on the indicator reference values and valid weights of the valid indicators, the dimension reference value of the information dimension is determined. For example, ∑(valid weight of each valid indicator * indicator reference value) = dimension reference value;

[0107] On the basis of the feasible implementation manner of the above S230, the present application further provides a process for determining valid indicators:

[0108] Based on the indicator data table items, determine the variable values and missing values of each indicator under the information dimension;

[0109] According to the variable values and missing values of each indicator, determine the valid indicators.

[0110] Based on this, by determining the variable values and missing values of each indicator under the information dimension, the indicators with non-null variable values and the indicators with missing values assigned scores are determined, that is, the valid indicators under this information dimension.

[0111] On the basis of the feasible implementation manner of the above S230, the present application further provides a process for determining the sum of valid weights:

[0112] According to the indicator weights of the valid indicators, determine the sum of the weights of all valid indicators;

[0113] Compare the sum of weights with a preset valid weight threshold;

[0114] If the sum of weights is lower than the valid weight threshold, determine that the dimension reference value of the information dimension is a null value;

[0115] If the sum of weights is not lower than the valid weight threshold, determine that the sum of weights is the sum of valid weights.

[0116] Among them, the preset valid weight threshold is the preset threshold of the sum of valid weights under this information dimension, which is used to compare with the sum of valid weights of the valid indicators, so as to determine whether the dimension reference value of the information dimension is a null value according to the comparison result.

[0117] Based on this, by comparing the sum of valid weights and the preset valid weight threshold, the dimension reference value of this information dimension is determined to be a null value or the sum of valid weights according to the comparison result.

[0118] Based on the feasible implementation of the above S240, the present application further provides a process of determining the target credit rating of the target object according to the credit rating and the rule rating after comparing the credit reference value with the credit threshold range:

[0119] Determine the rule indicators of the target object according to the index data table item;

[0120] Compare the rule indicators with the rule rating range to obtain the rule rating corresponding to the rule indicators;

[0121] Compare the credit rating with the rule rating, and determine the target credit rating of the target object according to the comparison result.

[0122] Among them, the rule indicator is an indicator representing the result of the enterprise touching the rules. According to the rule indicator, the result of the enterprise touching the rules can be determined. For example, if the rule indicator is 1, it can represent that the enterprise has touched the first-level rules, and the upper limit of the enterprise's credit rating does not exceed the first level.

[0123] The rule rating range is an interval representing the rating result corresponding to the rule indicator. For example, if the rule indicator is 1, the highest rating of the enterprise corresponds to the first level.

[0124] Based on this, by comparing the rule indicators of the target object with the rule rating range, the rule rating of the target object is obtained, and the credit rating is compared with the rule rating, so as to determine the target credit rating of the target object according to the comparison result.

[0125] In some embodiments, comparing the credit rating with the rule rating, and determining the target credit rating of the target object according to the comparison result includes:

[0126] Compare the credit rating with the rule rating;

[0127] If the comparison result is that the credit rating is the same as the rule rating, determine that the target credit rating is the same rating;

[0128] If the comparison result is that the credit rating is different from the rule rating, determine that the target credit rating is the lower rating of the credit rating and the rule rating.

[0129] Based on this, by comparing the credit rating with the rule rating, the lower of the two is determined as the target credit rating of the target object. For example, if the credit rating is the first level and the rule rating is the second level, the target credit rating of the target object is the second level.

[0130] Based on the feasible implementation of the above S240, the present application further provides a process of sending the target credit rating to the credit rating application system after comparing the credit reference value with the credit threshold range and determining the credit rating of the target object:

[0131] Send the target credit rating of the target object to the credit rating application system, so that the credit rating application system determines the credit of the target object according to the target credit rating.

[0132] Based on this, after determining the target credit rating by comparing the credit rating and the rule rating, the target credit rating is sent to the credit rating application system, so that the credit rating application system determines the credit of the target object according to the target credit rating. In this way, by combining the rule touch result based on the scoring credit rating result, the accuracy of the target credit rating is improved.

[0133] In this embodiment, in order to achieve the effect of accurately analyzing enterprise government affairs data to obtain the target credit rating of the enterprise, the ETL tool is used to obtain the government affairs data of the target object from the front-end database, and classify the government affairs data under each information dimension, so as to obtain the index data table items of the government affairs data and store them in the application database. Then, the enterprise credit scoring and credit rating classification system processes the index data in the index data table items to obtain the credit reference value and target credit rating of the target object, and saves them to the application database, so that the result application system can read the target credit rating of the target object to determine the credit of the target object; the rating indexes in the index data table items reflect different data dimensions of the enterprise, so as to analyze the government affairs data more comprehensively.

[0134] Figure 3 The following is a schematic structural diagram of a credit rating determination device 300 based on government affairs data provided by an embodiment of the present application. As Figure 3 shown, the credit rating determination device 300 based on government affairs data includes: a data acquisition module 310, an index reference value determination module 320, a dimension reference value determination module 330, a credit reference value determination module 340, and a credit rating determination module 350.

[0135] The data acquisition module 310 is used to obtain the government affairs data of the target object from the front-end database through ETL, determine the information dimensions included in the government affairs data, and classify the government affairs data under each information dimension to obtain the index data table items of the government affairs data;

[0136] The index reference value determination module 320 is used to determine the index reference values of various types of indexes in the index data table items;

[0137] The dimension reference value determination module 330 is used to determine the index weights of each index, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight;

[0138] A credit reference value determination module 340, configured to determine a credit reference value of a target object according to each dimension reference value and its corresponding dimension weight;

[0139] A credit rating determination module 350, configured to compare the credit reference value with a credit threshold range to determine the credit rating of the target object.

[0140] In an embodiment of the present application, the index reference value determination module 320 may further be specifically configured to:

[0141] If the data of the index is discrete, determine the index value and index score in the index data table entry;

[0142] Determine the index reference value of the discrete index according to the index value and index score;

[0143] If the data type of the index is continuous, determine the value range critical value and index score of the index value in the index data table;

[0144] Determine the index reference value of the continuous index according to the value range critical value and index score of the index value.

[0145] In an embodiment of the present application, the dimension reference value determination module 330 may further be specifically configured to:

[0146] Based on the index data table entry, determine the valid indexes and their corresponding index weights under the information dimension;

[0147] According to the index weights of the valid indexes, determine the sum of the valid weights of all the valid indexes;

[0148] According to the index weights and the sum of the valid weights of the valid indexes, determine the valid weights of the valid indexes;

[0149] According to the valid weight of each valid index and its corresponding index reference value, determine the dimension reference value corresponding to the information dimension.

[0150] In an embodiment of the present application, the dimension reference value determination module 330 may further be specifically configured to:

[0151] Based on the index data table entry, determine the variable values and missing values of each index under the information dimension;

[0152] Determine the valid indexes according to the variable values and missing values of each index.

[0153] In an embodiment of the present application, the dimension reference value determination module 330 may further be specifically configured to:

[0154] According to the index weights of the valid indexes, determine the sum of the weights of all the valid indexes;

[0155] Compare the sum of the weights with a preset valid weight threshold;

[0156] If the weight sum is lower than the effective weight threshold, determine that the dimension reference value of the information dimension is a null value;

[0157] If the weight sum is not lower than the effective weight threshold, determine that the weight sum is the effective weight sum.

[0158] In the embodiment of the present application, the credit rating determination device 300 based on government affairs data may also be specifically used for:

[0159] Determine the rule indicators of the target object according to the index data table items;

[0160] Compare the rule indicators with the rule level intervals to obtain the rule levels corresponding to the rule indicators;

[0161] Compare the credit rating with the rule level, and determine the target credit rating of the target object according to the comparison result.

[0162] In the embodiment of the present application, the credit rating determination device 300 based on government affairs data may also be specifically used for:

[0163] Compare the credit rating with the rule level;

[0164] If the comparison result is that the credit rating and the rule level are the same, determine that the target credit rating is the same level;

[0165] If the comparison result is that the credit rating and the rule level are different, determine that the target credit rating is the lower level of the credit rating and the rule level.

[0166] In the embodiment of the present application, the credit rating determination device 300 based on government affairs data may also be specifically used for:

[0167] Send the target credit rating of the target object to the credit rating application system, so that the credit rating application system determines the credit of the target object according to the target credit rating.

[0168] Figure 4 It is a schematic structural diagram of the device provided in the embodiment of the present application. As Figure 4 shown, the device 400 includes:

[0169] The device 400 may include a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a communication component 403 and other components. Among them, the processor 401, the memory 402 and the communication component 403 are connected through a bus 404.

[0170] In the specific implementation process, at least one processor 401 executes the computer execution instructions stored in the memory 402, so that at least one processor 401 executes the message processing method as described above.

[0171] For the specific implementation process of the processor 401, reference may be made to the above method embodiments. Their implementation principles and technical effects are similar, and thus will not be elaborated herein.

[0172] In the above Figure 4 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU for short), or may also be other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0173] The memory may include a random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0174] The bus may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0175] In some embodiments, a computer program product is also proposed, including a computer program or instruction. When the computer program or instruction is executed by a processor, the steps in any of the above methods for determining a credit rating based on government affairs data are implemented.

[0176] For the specific implementation of each of the above operations, reference may be made to the previous embodiments and will not be elaborated herein.

[0177] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0178] To this end, an embodiment of the present application provides a computer-readable storage medium, which stores multiple computer-executable instructions that can be loaded by a processor to execute the steps in any one of the credit rating determination methods based on government affairs data provided by the embodiments of the present application.

[0179] Among them, the storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0180] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.

[0181] Since the instructions stored in the storage medium can execute the steps in any one of the credit rating determination methods based on government affairs data provided by the embodiments of the present application, the beneficial effects that can be achieved by any one of the credit rating determination methods based on government affairs data provided by the embodiments of the present application can be realized. For details, see the previous embodiments and will not be elaborated here.

[0182] Those skilled in the art will readily think of other implementation manners of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0183] It should be understood that the present application is not limited to the exact structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A method for determining credit rating based on government affairs data, characterized in that, the method includes: Obtain the government affairs data of the target object from the front-end database through ETL, determine the information dimensions included in the government affairs data, and classify the government affairs data under each information dimension to obtain the index data items of the government affairs data; Determine the index reference values of various types of indexes in the index data items; Determine the index weights of each of the indexes, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight; Determine the credit reference value of the target object according to each dimension reference value and its corresponding dimension weight; Compare the credit reference value with the credit threshold interval to determine the credit rating of the target object.

2. The method according to claim 1, characterized in that, each of the index types includes discrete data or continuous data; the determination of the index reference values of various types of indexes in the index data items includes: If the data of the index is discrete, determine the index value and index score in the index data item; Determine the index reference value of the discrete index according to the index value and index score; If the data type of the index is continuous, determine the value range critical value and index score of the index value in the index data table; Determine the index reference value of the continuous index according to the value range critical value of the index value and the index score.

3. The method according to claim 1, characterized in that, the determination of the index weights of each of the indexes, and the determination of the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight, includes: Based on the index data items, determine the valid indexes and their corresponding index weights under the information dimension; According to the index weights of the valid indexes, determine the sum of the valid weights of all the valid indexes; According to the index weights of the valid indexes and the sum of the valid weights, determine the valid weights of the valid indexes; Determine the dimension reference value corresponding to the information dimension according to the valid weight of each valid index and its corresponding index reference value.

4. The method according to claim 3, characterized in that, the determination based on the index data items of the valid indexes and their corresponding index weights under the information dimension includes: Based on the index data items, determine the variable values and missing values of each index under the information dimension; Determine the valid indexes according to the variable values and missing values of each index.

5. The method according to claim 3, characterized in that, the determination of the sum of the valid weights of all the valid indexes according to the index weights of the valid indexes includes: According to the index weights of the valid indexes, determine the sum of the weights of all the valid indexes; Compare the sum of the weights with a preset valid weight threshold; If the sum of the weights is lower than the valid weight threshold, determine that the dimension reference value of the information dimension is a null value; If the sum of the weights is not lower than the valid weight threshold, determine that the sum of the weights is the sum of the valid weights.

6. The method according to claim 1, wherein, after comparing the credit reference value with the credit threshold range to determine the credit rating of the target object, the method further includes: determining the rule indicators of the target object according to the index data table entries; comparing the rule indicators with the rule rating range to obtain the rule rating corresponding to the rule indicators; comparing the credit rating with the rule rating, and determining the target credit rating of the target object according to the comparison result.

7. The method according to claim 6, wherein, the comparing the credit rating with the rule rating, and determining the target credit rating of the target object according to the comparison result includes: comparing the credit rating with the rule rating; if the comparison result is that the credit rating is the same as the rule rating, determining that the target credit rating is the same rating; if the comparison result is that the credit rating is different from the rule rating, determining that the target credit rating is the lower rating of the credit rating and the rule rating.

8. The method according to claim 1, wherein, after comparing the credit reference value with the credit threshold range to determine the credit rating of the target object, the method further includes: sending the target credit rating of the target object to a credit rating application system, so that the credit rating application system determines the credit of the target object according to the target credit rating.

9. A credit rating determination device based on government affairs data, wherein, the device includes: a data acquisition module, configured to obtain the government affairs data of the target object from a front-end database through ETL, determine the information dimensions included in the government affairs data, and classify the government affairs data under each information dimension to obtain the index data table entries of the government affairs data; an index reference value determination module, configured to determine the index reference values of various types of indexes in the index data table entries; a dimension reference value determination module, configured to determine the index weights of each of the indexes, and determine the dimension reference value corresponding to each information dimension according to the index reference value of the index and its corresponding index weight; a credit reference value determination module, configured to determine the credit reference value of the target object according to each dimension reference value and its corresponding dimension weight; a credit rating determination module, configured to compare the credit reference value with the credit threshold range to determine the credit rating of the target object.

10. A device, wherein, includes: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, wherein, computer-executable instructions are stored in the computer-readable storage medium, and the computer-executable instructions can be called by a processor to execute the method according to any one of claims 1 to 8.

Images