Market subject credit rating evaluation method and system, electronic equipment and storage medium

Abstract

The invention discloses a market subject credit rating assessment method and system, an electronic device and a storage medium, and relates to the technical field of credit rating assessment. Operation feature data of a target market subject is acquired and matched with preset standard transaction behavior acquisition frequency data; accurately matching transaction behavior acquisition frequency data of the target market subject; according to the transaction behavior acquisition frequency data, transaction behavior feature data of the target market subject is acquired, unnecessary resource waste caused by excessive data acquisition amount is avoided, and the efficiency of an evaluation process is improved while the accuracy of an evaluation result is ensured; setting a corresponding cost value for the transaction behavior feature data and calculating a credit value of the target market subject, thereby providing a data basis for analyzing the target market subject; and performing numerical value matching according to the credit value and the credit rating interval data, accurately searching the credit rating data of the target market subject, and realizing scientific evaluation of the credit rating of the market subject.

Description

Technical Field

[0001] The present application relates to the technical field of credit rating assessment, and in particular to a method, system, electronic device and storage medium for assessing the credit rating of a market entity. Background Art

[0002] In today's digital, globalized market economy, market transactions are becoming increasingly frequent and complex. Trust mechanisms between market participants have become a key factor in ensuring smooth transactions and maintaining stable market development. As a key means of measuring the creditworthiness of market participants, the accuracy and effectiveness of credit rating assessments are crucial.

[0003] Among the relevant technologies, the credit rating assessment model currently mainly adopts a fixed indicator system and traditional statistical analysis methods. However, the applicant recognizes that the existing credit rating assessment technology cannot adaptively adjust the data collection volume according to changes in market entities, and it is difficult to simultaneously ensure the efficiency and accuracy of the credit rating assessment process. At the same time, in the process of credit rating assessment, only a single data is often analyzed, resulting in poor quality of credit rating assessment operations. Summary of the Invention

[0004] In view of this, the present application provides a method, system, electronic device and storage medium for evaluating the credit rating of market entities. The main purpose is to solve the problem that the existing credit rating evaluation technology cannot adaptively adjust the data collection volume according to the changes of market entities, and it is difficult to simultaneously ensure the efficiency and accuracy of the credit rating evaluation process. At the same time, in the process of credit rating evaluation, it is often only through analysis of single data, resulting in poor quality of credit rating evaluation operations.

[0005] According to the first aspect of the present application, a method for evaluating the credit rating of a market entity is provided, the method comprising:

[0006] Acquire a target market entity's business characteristic data set, and match the business characteristic data set with a standard transaction behavior acquisition frequency data set to obtain transaction behavior acquisition frequency data of the target market entity;

[0007] Collecting a transaction behavior feature dataset of the target market entity based on the transaction behavior acquisition frequency data, setting a corresponding cost value for the transaction behavior feature dataset, and generating a transaction behavior cost value dataset of the target market entity;

[0008] Calculating the credit value of the target market entity based on the transaction behavior cost value dataset, numerically matching the credit value with the credit rating interval data, and generating the credit rating data of the target market entity;

[0009] Credit rating assessment data of the target market entity is constructed based on the transaction behavior feature data set and the credit rating data, and the credit rating assessment data is pushed to a market entity credit rating assessment platform via a wireless communication network.

[0010] Optionally, the step of acquiring an operating characteristic dataset of a target market entity and matching the operating characteristic dataset with standard transaction behavior acquisition frequency data to obtain the transaction behavior acquisition frequency data of the target market entity includes:

[0011] Obtaining the business type characteristic data and business scale characteristic data of the target market entity through the Internet of Things platform, and using the business type characteristic data and the business scale characteristic data as the business characteristic data set of the target market entity;

[0012] The business characteristic data set is matched with the standard transaction behavior acquisition frequency data set by character feature matching through the BM matching algorithm to obtain the transaction behavior acquisition frequency data of the target market entity, wherein the standard transaction behavior acquisition frequency data set includes standard transaction behavior acquisition frequency data corresponding to multiple business characteristic data, and the standard transaction behavior acquisition frequency data represents the standard number of transaction behavior characteristic data required to obtain when performing a credit rating assessment operation on the market entity corresponding to the business characteristic data.

[0013] Optionally, the step of collecting a transaction behavior feature dataset of the target market entity based on the transaction behavior acquisition frequency data, setting a corresponding cost value for the transaction behavior feature dataset, and generating a transaction behavior cost value dataset of the target market entity includes:

[0014] According to the number of transaction data obtained, the transaction behavior feature data matrix of the target market entity is obtained through the Internet of Things platform.

[0015]

[0016] Where C represents the transaction behavior characteristic data matrix of the target market entity, c ij Represents the characteristic data of the jth type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, and l represents the total number of categories of transaction behavior feature data;

[0017] Using the transaction behavior characteristic data matrix of the target market subject as the transaction behavior characteristic data set of the target market subject;

[0018] Determine the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set through an intelligent optimization algorithm, and generate a transaction behavior cost value data matrix of the target market entity.

[0019]

[0020] in, Represents the transaction behavior cost data matrix of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, and l represents the total number of categories of transaction behavior feature data;

[0021] The transaction behavior cost value data matrix of the target market subject is used as the transaction behavior cost value data set of the target market subject.

[0022] Optionally, determining the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set by an intelligent optimization algorithm to generate a transaction behavior cost value data matrix of the target market entity includes:

[0023] Based on the water wave optimization algorithm, set the population size, maximum number of iterations, current number of iterations, and the transaction behavior cost data search space dimension;

[0024] Initializing a transaction cost value data search space, randomly generating multiple groups of transaction cost value data in the transaction cost value data search space according to the population size, to obtain a cost value search wave population, wherein each group of transaction cost value data corresponds to a cost value search wave individual in the cost value search wave population, and each cost value search wave individual in the cost value search wave population has an initial wavelength and an initial wave height;

[0025] Calculating the fitness value of each cost value search water wave individual in the cost value search water wave population,

[0026]

[0027] Among them, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population, x i represents the accuracy of the transaction behavior cost data corresponding to the i-th cost search wave individual in the cost search wave population in measuring the credit rating of the market entity, and φ represents the correction value;

[0028] Sorting the plurality of cost value search wave individuals in the cost value search wave population in descending order of fitness values, and selecting the cost value search wave individual that ranks first in the sorting result as the current optimal individual corresponding to the first iteration number;

[0029] Iteratively calculating the cost value search water wave population based on the maximum number of iterations;

[0030] In the current iteration, a propagation strategy is used to update the positions and wavelengths of the multiple cost value search wave individuals in the transaction behavior cost value data search space.

[0031]

[0032] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand1 represents a random number uniformly distributed in the interval [-1,1], represents the wavelength of the i-th cost value search wave individual in the cost value search wave population before the position is updated, α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for transaction value data in the j-th dimension, represents the wavelength of the i-th cost value search wave individual in the cost value search wave population after the position is updated, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population before the position is updated, t represents the current number of iterations, t max represents the maximum number of iterations, f max represents the maximum fitness function of the cost-value search wave individual in the cost-value search wave population, f min represents the minimum value of the fitness function of the cost-value search wave individual in the cost-value search wave population, and χ represents the adjustment coefficient;

[0033] Calculating the fitness value of each cost value search wave individual in the cost value search wave population after the position is updated, and determining the current optimal individual corresponding to the current number of iterations according to the fitness value of each cost value search wave individual after the position is updated;

[0034] For each of the cost value search wave individuals, if the fitness value of the cost value search wave individual after the position update is greater than the fitness value of the cost value search wave individual before the position update, the fitness value of the cost value search wave individual after the position update is used as the fitness value of the cost value search wave at the current iteration number;

[0035] When the fitness value of the cost value search wave individual after the position update is greater than the fitness value of the current optimal individual corresponding to the current iteration number, the cost value search wave individual is updated by performing a wave breaking operation, and the position of the cost value search wave individual after the wave breaking operation is set as the position of the cost value search wave at the current iteration number.

[0036]

[0037] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand2 represents a Gaussian random number in the interval (0, 1), α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for the transaction value data of the j-th dimension, and δ represents the breaking wave coefficient;

[0038] When it is detected that the current number of iterations is greater than or equal to the maximum number of iterations, the cost value search wave individual with the highest fitness value in the cost value search wave population is taken as the global optimal solution;

[0039] Data identification is performed on the transaction behavior cost value data corresponding to the global optimal solution to generate a transaction behavior cost value data matrix of the target market entity.

[0040] Optionally, after determining the current optimal individual corresponding to the current number of iterations based on the fitness value of each cost value search water wave individual after position update, the method further includes:

[0041] If the fitness value of the cost value search water wave individual after the position update is less than or equal to the fitness value of the cost value search water wave individual before the position update, the fitness value of the cost value search water wave individual before the position update is used as the fitness value of the cost value search water wave at the current number of iterations, and the wave height value of the cost value search water wave individual is reduced by 1.

[0042] Optionally, the method further includes:

[0043] When it is determined that the wave height value of the cost value search water wave individual is 0, performing a refraction operation on the cost value search water wave individual;

[0044] The average position is calculated based on the position of the current optimal individual corresponding to the current iteration number and the position of the cost value search water wave individual before the position update, and the average position is used as the position of the cost value search water wave at the current iteration number, and the wavelength and wave height of the cost value search water wave individual are initialized after the refraction operation is performed.

[0045] Optionally, calculating the credit value of the target market entity based on the transaction behavior cost value dataset, numerically matching the credit value with credit rating interval data, and generating the credit rating data of the target market entity includes:

[0046] The transaction behavior cost value dataset is calculated using the market entity credit value calculation formula to obtain the credit value of the target market entity.

[0047]

[0048] Among them, λ represents the credit value of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, l represents the total number of categories of transaction behavior feature data, ω j Represents the weight factor of the characteristic data of the j-th type of transaction behavior;

[0049] Performing numerical matching processing on the credit value and a credit grade interval data set using a bidirectional search algorithm, wherein the credit grade interval data set includes credit value interval data corresponding to multiple credit grades;

[0050] The credit value interval data matching the credit value in the credit grade interval data set is used as the target credit value interval data, and the credit grade corresponding to the target credit value interval data is used to generate the credit grade data of the target market entity.

[0051] According to a second aspect of the present application, a market entity credit rating assessment system is provided, the system comprising an operating characteristic data collection module, a transaction behavior acquisition number matching module, a transaction behavior characteristic data collection module, a transaction behavior cost value setting module, a target market entity credit value calculation module, a credit rating data search module, and a credit rating assessment data construction module;

[0052] The business characteristic data collection module is used to obtain the business characteristic data set of the target market entity;

[0053] The transaction behavior acquisition frequency matching module is used to match the business characteristic data set with the standard transaction behavior acquisition frequency data set to obtain the transaction behavior acquisition frequency data of the target market entity;

[0054] The transaction behavior feature data collection module is configured to collect transaction behavior feature data sets of the target market subject based on the transaction behavior acquisition frequency data;

[0055] The transaction behavior value setting module is configured to set corresponding transaction behavior values for the transaction behavior feature data sets, and generate transaction behavior value data sets of the target market subject;

[0056] The target market subject credit value calculation module is configured to calculate the credit value of the target market subject according to the transaction behavior value data sets;

[0057] The credit level data search module is configured to perform numerical matching of the credit value and credit level interval data, and generate credit level data of the target market subject;

[0058] The credit level evaluation data construction module is configured to construct credit level evaluation data of the target market subject based on the transaction behavior feature data sets and the credit level data, and push the credit level evaluation data to a market subject credit level evaluation platform through a wireless communication network.

[0059] Optionally, the business feature data collection module is configured to acquire business type feature data and business scale feature data of the target market subject through an Internet of Things platform, and take the business type feature data and the business scale feature data as business feature data sets of the target market subject.

[0060] Optionally, the transaction behavior acquisition frequency matching module is configured to perform character feature matching of the business feature data sets and the standard transaction behavior acquisition frequency data sets through a BM matching algorithm to obtain transaction behavior acquisition frequency data of the target market subject, wherein the standard transaction behavior acquisition frequency data sets include standard transaction behavior acquisition frequency data corresponding to a plurality of business feature data, and the standard transaction behavior acquisition frequency data represents a standard number of times of acquiring transaction behavior feature data required when performing a credit level evaluation operation on a market subject corresponding to the business feature data.

[0061] Optionally, the transaction behavior feature data collection module is configured to acquire a transaction behavior feature data matrix of the target market subject through an Internet of Things platform according to the transaction behavior acquisition frequency data,

[0062]

[0063] wherein C represents the transaction behavior feature data matrix of the target market subject, c ijRepresents the characteristic data of the jth type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, l represents the total number of categories of transaction behavior feature data; the transaction behavior feature data matrix of the target market entity is used as the transaction behavior feature data set of the target market entity.

[0064] Optionally, the transaction behavior cost value setting module is used to determine the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set through an intelligent optimization algorithm, and generate a transaction behavior cost value data matrix of the target market entity.

[0065]

[0066] in, Represents the transaction behavior cost data matrix of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of transaction behavior acquisition data, l represents the total number of categories of transaction behavior feature data; the transaction behavior cost value data matrix of the target market entity is used as the transaction behavior cost value data set of the target market entity.

[0067] Optionally, the transaction behavior cost value setting module is used to set the population size, the maximum number of iterations, the current number of iterations, and the dimension of the transaction behavior cost value data search space based on the water wave optimization algorithm; initialize the transaction behavior cost value data search space, randomly generate multiple groups of transaction behavior cost value data in the transaction behavior cost value data search space according to the population size, and obtain a cost value search water wave population, wherein each group of the transaction behavior cost value data corresponds to a cost value search water wave individual in the cost value search water wave population, and each cost value search water wave individual in the cost value search water wave population has an initial wavelength and an initial wave height; calculate the fitness value of each cost value search water wave individual in the cost value search water wave population,

[0068]

[0069] Among them, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population, x irepresents the accuracy of the transaction behavior cost value data corresponding to the i-th cost value search wave individual in the cost value search wave population in measuring the credit rating of the market entity, and φ represents the correction value; multiple cost value search wave individuals in the cost value search wave population are sorted in descending order of fitness value, and the cost value search wave individual ranked first in the sorting result is selected as the current optimal individual corresponding to the first iteration number; the cost value search wave population is iteratively calculated based on the maximum iteration number; in the current iteration number, the propagation strategy is used to update the positions and wavelengths of the multiple cost value search wave individuals in the transaction behavior cost value data search space,

[0070]

[0071] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand1 represents a random number uniformly distributed in the interval [-1,1], represents the wavelength of the i-th cost value search wave individual in the cost value search wave population before the position is updated, α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for transaction value data in the j-th dimension, represents the wavelength of the i-th cost value search wave individual in the cost value search wave population after the position is updated, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population before the position is updated, t represents the current number of iterations, t max represents the maximum number of iterations, f max represents the maximum fitness function of the cost-value search wave individual in the cost-value search wave population, f minrepresents the minimum value of the fitness function of the cost value search wave individual in the cost value search wave population, and χ represents the adjustment coefficient; calculates the fitness value of each cost value search wave individual in the cost value search wave population after the position is updated, and determines the current optimal individual corresponding to the current iteration number according to the fitness value of each cost value search wave individual after the position is updated; for each cost value search wave individual, if the fitness value of the cost value search wave individual after the position is updated is greater than the fitness value of the cost value search wave individual before the position is updated, then the fitness value of the cost value search wave individual after the position is updated is used as the fitness value of the cost value search wave at the current iteration number; when the fitness value of the cost value search wave individual after the position is updated is greater than the fitness value of the current optimal individual corresponding to the current iteration number, performs a breaking wave operation on the cost value search wave individual to update its position, and uses the position of the cost value search wave individual after the breaking wave operation as the position of the cost value search wave at the current iteration number.

[0072]

[0073] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand2 represents a Gaussian random number in the interval (0, 1), α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the search lower limit of the j-th dimension transaction cost value data search space, and δ represents the breaking wave coefficient; when it is detected that the current number of iterations is greater than or equal to the maximum number of iterations, the cost value search wave individual with the highest fitness value in the cost value search wave population is taken as the global optimal solution; the transaction cost value data corresponding to the global optimal solution are data identified to generate the transaction cost value data matrix of the target market entity.

[0074] Optionally, the transaction behavior cost value setting module is used to, if the fitness value of the cost value search wave individual after the position update is less than or equal to the fitness value of the cost value search wave individual before the position update, use the fitness value of the cost value search wave individual before the position update as the fitness value of the cost value search wave at the current iteration number, and subtract 1 from the wave height value of the cost value search wave individual.

[0075] Optionally, the transaction behavior generation value setting module is configured to perform a refraction operation on the generation value search water wave individual when it is determined that the wave height value of the generation value search water wave individual is 0; calculate an average position based on the position of the current optimal individual corresponding to the current iteration number and the position of the generation value search water wave individual before position updating, take the average position as the position of the generation value search water wave at the current iteration number, and initialize the wavelength and wave height of the generation value search water wave individual after the refraction operation.

[0076] Optionally, the target market subject credit value calculation module is configured to calculate the transaction behavior generation value data set by using a market subject credit value calculation formula to obtain the credit value of the target market subject.

[0077]

[0078] wherein λ represents the credit value of the target market subject, represents the generation value corresponding to the jth type of transaction behavior feature data in the ith transaction behavior of the target market subject, represents the transaction behavior acquisition number data, l represents the total number of types of transaction behavior feature data, and ω j represents the weight factor of the jth type of transaction behavior feature data.

[0079] Optionally, the credit level data search module is configured to perform numerical matching processing on the credit value and a credit level interval data set by using a bidirectional search algorithm, wherein the credit level interval data set includes credit value interval data corresponding to a plurality of credit levels; take the credit value interval data in the credit level interval data set that matches the credit value as target credit value interval data, and generate the credit level data of the target market subject by using the credit level corresponding to the target credit value interval data.

[0080] According to the third aspect of the present application, an electronic device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of the first aspect when executing the computer program.

[0081] According to the fourth aspect of the present application, a storage medium is provided, which stores a computer program, and the computer program implements the steps of the method according to any one of the first aspect when executed by a processor.

[0082] By means of the above technical solutions, the technical solutions provided by the embodiments of the present application have at least the following advantages:

[0083] The present application provides a method, system, electronic device and storage medium for evaluating the credit rating of a market entity. The present application obtains the operating characteristic data of the target market entity and matches it with the preset standard transaction behavior acquisition frequency data to accurately match the target market entity's transaction behavior acquisition frequency data; collects the target market entity's transaction behavior characteristic data based on the transaction behavior acquisition frequency data to avoid excessive data collection and unnecessary waste of resources, thereby improving the efficiency of the evaluation process while ensuring the accuracy of the evaluation results; sets a corresponding cost value for the transaction behavior characteristic data and calculates the credit value of the target market entity, providing a data basis for analyzing the target market entity; performs numerical matching based on the credit value and credit rating interval data to accurately search for the target market entity's credit rating data, thereby realizing a scientific evaluation of the market entity's credit rating.

[0084] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0086] Figure 1 A schematic diagram of a method flow for evaluating the credit rating of a market entity provided in an embodiment of the present application is shown;

[0087] Figure 2A A schematic diagram of another method for evaluating the credit rating of a market entity provided in an embodiment of the present application is shown;

[0088] Figure 2B A flow chart of a method for evaluating the credit rating of a market entity based on transaction behavior data provided by an embodiment of the present application is shown;

[0089] Figure 3 A schematic diagram of a system architecture for evaluating the credit rating of a market entity provided by an embodiment of the present application is shown;

[0090] Figure 4 A schematic diagram of the device structure of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0091] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0092] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0093] Existing credit rating assessment technology cannot adaptively adjust the amount of data collected according to changes in market entities, and it is difficult to simultaneously ensure the efficiency and accuracy of the credit rating assessment process. At the same time, in the process of credit rating assessment, it is often only through analysis of single data, and it is impossible to set reasonable values ​​for each transaction behavior and further conduct comprehensive analysis, resulting in poor quality of credit rating assessment operations.

[0094] To solve this problem, the present application proposes a method for evaluating the credit rating of a market entity. The method obtains the target market entity's operating characteristic data and matches it with the preset standard transaction behavior acquisition frequency data to accurately match the target market entity's transaction behavior acquisition frequency data; collects the target market entity's transaction behavior characteristic data based on the transaction behavior acquisition frequency data to avoid excessive data collection and unnecessary resource waste, thereby improving the efficiency of the evaluation process while ensuring the accuracy of the evaluation results; sets a corresponding cost value for the transaction behavior characteristic data and calculates the target market entity's credit value, providing a data basis for analyzing the target market entity; and numerically matches the credit value with the credit rating interval data to accurately search for the target market entity's credit rating data, thereby achieving a scientific evaluation of the market entity's credit rating. The execution subject of the present application can be a market entity credit rating evaluation system. The market entity credit rating evaluation system relies on the computing power of the server to provide services to users. The server can be an independent server or a server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0095] This application embodiment provides a method for evaluating the credit rating of a market entity, such as Figure 1As shown, the method includes:

[0096] 101. Obtain an operating characteristic data set of the target market entity, match the operating characteristic data set with a standard transaction behavior acquisition frequency data set, and obtain transaction behavior acquisition frequency data of the target market entity.

[0097] In the embodiment of the present application, by matching operating characteristics (such as business type and scale) with the number of standard transaction behaviors obtained, the number of transaction data collection times required for each market entity can be accurately determined, and the standard transaction behavior acquisition number data set can be dynamically updated according to market changes (such as adding new industry types and adjusting scale classification standards), so that the evaluation model always fits the actual business needs.

[0098] 102. Collect a target market entity's transaction behavior feature dataset based on the transaction behavior acquisition frequency data, set a corresponding cost value for the transaction behavior feature dataset, and generate a target market entity's transaction behavior cost value dataset.

[0099] In an embodiment of the present application, based on the number of transaction data obtained (such as the 20 matched transactions), the core transaction characteristics of the target market entity (such as transaction amount, return rate, settlement cycle, etc.) are collected in a targeted manner. In this way, only necessary data that matches the operating characteristics is collected, and redundant fields (such as transaction types that are not related to the main business) are eliminated, which can reduce the interference of data noise on the evaluation results.

[0100] 103. Calculate the credit value of the target market entity based on the transaction behavior value dataset, numerically match the credit value with the credit rating interval data, and generate the credit rating data of the target market entity.

[0101] In an embodiment of the present application, various features in the transaction behavior value data set (such as transaction amount, return rate, settlement period, etc.) are weighted and summed according to the credit value calculation formula to form a single credit value, which can avoid one-sided evaluation of a single feature, and the weight setting can highlight key risk points in line with the evaluation focus of different industries.

[0102] 104. Construct credit rating assessment data of target market entities based on transaction behavior feature datasets and credit rating data, and push the credit rating assessment data to the market entity credit rating assessment platform via a wireless communication network.

[0103] In an embodiment of the present application, the transaction behavior feature data set (such as specific transaction amount, return record) and credit rating data (such as grade A) are integrated into a unified assessment report, forming a two-layer structure of "detailed data + conclusive grade", which can not only quickly determine the risk level through the credit grade, but also trace the cause of the grade through the transaction feature data.

[0104] The embodiment of the application provides a market subject credit rating evaluation method, compared with the prior art, the embodiment of the application obtains the operation characteristic data of the target market subject, and matches the preset standard transaction behavior acquisition frequency data, and the transaction behavior acquisition frequency data of the target market subject is accurately matched; according to the transaction behavior acquisition frequency data, the transaction behavior characteristic data of the target market subject is collected, the data collection amount is avoided to be too much, unnecessary resource waste is caused, the efficiency of the evaluation process is improved while ensuring the accuracy of the evaluation result; the corresponding value of the transaction behavior characteristic data is set, and the credit value of the target market subject is calculated, which provides a data basis for analyzing the target market subject; according to the credit value and the credit rating interval data, the credit rating data of the target market subject is accurately searched, and the scientific evaluation of the market subject credit rating is realized.

[0105] Further, as a refinement and expansion of the above embodiment, in order to completely describe the specific implementation process of the embodiment, the embodiment of the application provides another market subject credit rating evaluation method, as shown in Figure 2A The method comprises the following steps:

[0106] 201, obtaining the operation characteristic data set of the target market subject.

[0107] In the embodiment of the application, the business type characteristic data a1 and the operation scale characteristic data a2 of the target market subject are obtained through the Internet of Things platform, and the business type characteristic data and the operation scale characteristic data are taken as the operation characteristic data set A={a1, a2} of the target market subject.

[0108] 202, matching the operation characteristic data set with the standard transaction behavior acquisition frequency data set to obtain the transaction behavior acquisition frequency data of the target market subject.

[0109] In the embodiment of the application, the operation characteristic data set and the standard transaction behavior acquisition frequency data set are matched by the BM matching algorithm, and the transaction behavior acquisition frequency data of the target market subject is obtained Wherein, the standard transaction behavior acquisition frequency data set B={b1, b2,..., b i ,...,b k} includes a plurality of standard transaction behavior acquisition frequency data corresponding to the operation characteristic data, b i represents the standard transaction behavior acquisition frequency data corresponding to the i-th operation characteristic data, k represents the total number of standard transaction behavior acquisition frequency data, and the standard transaction behavior acquisition frequency data represents the standard number of transaction behavior characteristic data required to be acquired when the credit rating evaluation operation of the market subject corresponding to the operation characteristic data is performed.

[0110] By matching the operating characteristic data of the target market entities with the preset standard transaction behavior acquisition frequency data through character feature matching, the number of times the target market entity's transaction behavior characteristic data is collected is determined, thereby avoiding excessive data collection and unnecessary waste of resources. While ensuring the accuracy of the evaluation results, the efficiency of the evaluation process is improved.

[0111] 203. Based on the transaction behavior acquisition frequency data, a transaction behavior feature dataset of the target market entities is collected.

[0112] In the embodiment of the present application, according to the number of transaction behavior acquisition data, the transaction behavior characteristic data matrix of the target market entity is obtained through the Internet of Things platform, and the calculation formula is the following formula 1:

[0113]

[0114] Among them, C represents the transaction behavior characteristic data matrix of the target market players, c ij Represents the characteristic data of the jth type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of transaction behavior acquisitions, and l represents the total number of categories of transaction behavior feature data. The target market entity's transaction behavior feature data matrix is ​​used as the target market entity's transaction behavior feature dataset. Transaction behavior feature data includes but is not limited to transaction amount, transaction object, transaction method, service type, settlement cycle, return rate, complaint rate, and transaction completion time.

[0115] 204. Determine the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set through an intelligent optimization algorithm, and generate a transaction behavior cost value data set of the target market entity.

[0116] In the embodiment of the present application, the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set is determined by an intelligent optimization algorithm to generate a transaction behavior cost value data matrix of the target market entity. The calculation formula is the following formula 2:

[0117]

[0118] in, Represents the transaction behavior cost data matrix of the target market entity, It represents the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, The transaction behavior acquisition times data is represented by l, and the total number of categories of transaction behavior feature data is represented by l. The transaction behavior cost value data matrix of the target market entity is used as the transaction behavior cost value data set of the target market entity.

[0119] In an optional implementation scheme, the intelligent optimization algorithm may select a water wave optimization algorithm, and the specific process is as follows:

[0120] Based on the water wave optimization algorithm, set the population size N and the maximum number of iterations t max , the current number of iterations t, and the dimension P of the transaction behavior cost value data search space. Initialize the transaction behavior cost value data search space, randomly generate N groups of transaction behavior cost value data in the transaction behavior cost value data search space according to the population size, and obtain a cost value search wave population. Each group of transaction behavior cost value data corresponds to a cost value search wave individual in the cost value search wave population, and each cost value search wave individual in the cost value search wave population has an initial wavelength and initial wave height.

[0121] The fitness value of each cost-value search wave individual in the cost-value search wave population is calculated using the following formula 3:

[0122]

[0123] Among them, f i represents the fitness value of the i-th cost-value search water wave individual in the cost-value search water wave population, x i The transaction value data corresponding to the i-th cost-value search wave individual in the cost-value search wave population is used to measure the accuracy of the credit rating of market entities, and φ represents the correction value. The cost-value search wave individuals in the cost-value search wave population are sorted in descending fitness order. The top-ranked cost-value search wave individual is selected as the current optimal individual corresponding to the first iteration.

[0124] The cost value search water wave population is iteratively calculated based on the maximum number of iterations.

[0125] In the propagation phase of the current iteration, a propagation strategy is used to update the positions and wavelengths of multiple cost value search wave individuals in the transaction cost value data search space. The calculation formula is as follows:

[0126]

[0127]

[0128] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position update in the j-th dimension transaction behavior cost value data search space, X ijrepresents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand1 represents a random number uniformly distributed in the interval [-1,1], represents the wavelength of the i-th cost-value search wave individual in the cost-value search wave population before the position is updated, α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for transaction value data in the j-th dimension, represents the wavelength after the position of the i-th cost-value search wave individual in the cost-value search wave population is updated, f i It represents the fitness value of the i-th cost value search wave individual in the cost value search wave population before the position is updated, t represents the current number of iterations, t max Indicates the maximum number of iterations, f max represents the maximum fitness function of the cost-value search water wave individual in the cost-value search water wave population, f min represents the minimum value of the fitness function of the cost-value search wave individual in the cost-value search wave population, and χ represents the adjustment coefficient.

[0129] In the refraction stage, the fitness value of each cost-value search wave individual in the cost-value search wave population after the position is updated is calculated, and the current optimal individual corresponding to the current number of iterations is determined according to the fitness value of each cost-value search wave individual after the position is updated.

[0130] For each cost value search wave individual, if the fitness value of the cost value search wave individual after the position update is greater than the fitness value of the cost value search wave individual before the position update, then the fitness value of the cost value search wave individual after the position update is used as the fitness value of the cost value search wave at the current iteration number;

[0131] If the fitness value of the cost value search water wave individual after the position update is less than or equal to the fitness value of the cost value search water wave individual before the position update, the fitness value of the cost value search water wave individual before the position update is used as the fitness value of the cost value search water wave in the current iteration number, and the wave height value of the cost value search water wave individual is reduced by 1.

[0132] When it is determined that the wave height value of the cost value search water wave individual is 0, a refraction operation is performed on the cost value search water wave individual, and the average position is calculated based on the position of the current optimal individual corresponding to the current iteration number and the position of the cost value search water wave individual before the position update. The average position is used as the position of the cost value search water wave at the current iteration number, and the wavelength and wave height of the cost value search water wave individual after performing the refraction operation are initialized.

[0133] Then, in the wave-breaking stage, when the fitness value of the current value search wave individual after the position update is greater than the fitness value of the current optimal individual corresponding to the current iteration number, the wave-breaking operation is performed on the cost value search wave individual to update the position. The position of the cost value search wave individual after the wave-breaking operation is set to the position of the cost value search wave at the current iteration number. The calculation formula is the following formula 5:

[0134]

[0135] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position update in the j-th dimension transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand2 represents a Gaussian random number in the interval (0, 1), α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j It represents the lower limit of the search space of the transaction value data of the j-th dimension, and δ represents the breaking wave coefficient.

[0136] When it is detected that the current number of iterations is greater than or equal to the maximum number of iterations, the cost value search wave individual with the highest fitness value in the cost value search wave population is taken as the global optimal solution, and the transaction behavior cost value data corresponding to the global optimal solution is data-identified to generate the transaction behavior cost value data matrix of the target market entity.

[0137] By performing multiple iterative optimizations using the water wave optimization algorithm, reasonable cost values ​​are set for the transaction behavior characteristic data, thereby improving the speed and efficiency of the optimization process and ensuring the stability and accuracy of the optimization results. At the same time, the wavelength parameters in the optimization algorithm are updated according to the fitness value and the number of iterations to ensure that the search range remains at a position with high fitness. At the same time, the search range is gradually narrowed as the number of iterations increases, thereby improving the optimization performance of the algorithm.

[0138] 205. Calculate the credit value of the target market entity based on the transaction behavior value data set.

[0139] In the embodiment of the present application, the transaction behavior cost value dataset is calculated using the market entity credit value calculation formula to obtain the credit value of the target market entity. The calculation formula is the following formula 6:

[0140]

[0141] Among them, λ represents the credit value of the target market entity, It represents the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of transaction behavior acquisition data, l represents the total number of categories of transaction behavior feature data, ω j Represents the weight factor of the j-th type of transaction behavior characteristic data.

[0142] 206. Numerically match the credit value with the credit rating interval data to generate the credit rating data of the target market entity.

[0143] In the embodiment of the present application, a credit rating interval data set D={d1, d2, ..., d i ,...,d p}, where d i represents the credit value interval corresponding to the i-th credit grade, p represents the total number of credit grade interval data, and the credit grade interval data represents the credit value intervals corresponding to different credit grades of market entities. A bidirectional search algorithm is then used to numerically match the credit value with the credit grade interval dataset, where the credit grade interval dataset includes credit value interval data corresponding to multiple credit grades.

[0144] The credit value interval data that matches the credit value in the credit grade interval data set is used as the target credit value interval data, and the credit grade corresponding to the target credit value interval data is used to generate the credit grade data of the target market entity.

[0145] Specifically, the credit value λ is sequentially matched with each credit grade interval data in the credit grade interval data set through a bidirectional search algorithm;

[0146] If λ∈d i , it means that the credit value λ is successfully matched with the i-th credit rating interval data, the credit rating corresponding to the i-th credit rating interval data is data identified, and the credit rating data E of the target market entity is generated;

[0147] like It means that the credit value λ is not successfully matched with the i-th credit grade interval data, and the credit value λ is continued to be numerically matched with the remaining credit grade interval data in the credit grade interval data set until the credit value λ is successfully matched with any credit grade interval data in the credit grade interval data set.

[0148] By scientifically calculating the credit value of the target market entity and combining it with an intelligent search algorithm to accurately match the credit rating data of the target market entity from the credit rating interval data, a scientific assessment of the credit rating of the market entity is achieved.

[0149] 207. Construct credit rating assessment data of target market entities based on transaction behavior feature datasets and credit rating data, and push the credit rating assessment data to the market entity credit rating assessment platform via a wireless communication network.

[0150] In this embodiment of the present application, the transaction behavior feature data matrix C and the credit rating data E are combined to generate credit rating assessment data F = (C, E). The credit rating assessment data is pushed to the market entity credit rating assessment platform via a wireless communication network, and the credit rating assessment operation is completed.

[0151] In summary, this application proposes a method for evaluating the credit rating of market entities based on transaction behavior data. The flowchart is as follows:

[0152] like Figure 2B As shown, the target market entity's operating characteristic data is first obtained and matched against the standard transaction acquisition frequency data using character feature matching to obtain transaction acquisition frequency data. Next, transaction characteristic data is collected by combining data from water supply areas of varying water quality levels. These characteristics are then assigned corresponding cost values ​​using an intelligent optimization algorithm to generate transaction cost value data. The target market entity's credit value is then calculated based on the transaction cost value data. This credit value is numerically matched against a credit rating interval dataset to determine whether the credit value successfully matches any credit rating interval in the credit rating interval set. If unsuccessful, matching is continued; if successful, credit rating data is obtained. Credit rating assessment data is then constructed based on this credit rating data and pushed to the market entity credit rating assessment platform via a wireless communication network.

[0153] The embodiment of the present application provides a method for evaluating the credit rating of a market entity. Compared with the prior art, the embodiment of the present application obtains the operating characteristic data of the target market entity and matches it with the preset standard transaction behavior acquisition frequency data, thereby accurately matching the transaction behavior acquisition frequency data of the target market entity; collecting the transaction behavior characteristic data of the target market entity based on the transaction behavior acquisition frequency data, thereby avoiding excessive data collection and unnecessary waste of resources, thereby improving the efficiency of the evaluation process while ensuring the accuracy of the evaluation results; setting a corresponding cost value for the transaction behavior characteristic data and calculating the credit value of the target market entity, thereby providing a data basis for analyzing the target market entity; performing numerical matching based on the credit value and credit rating interval data, accurately searching for the credit rating data of the target market entity, thereby realizing a scientific evaluation of the credit rating of the market entity.

[0154] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a market subject credit rating assessment system, such as Figure 3As shown, the device comprises: business characteristic data acquisition module 301, transaction behavior acquisition times matching module 302, transaction behavior characteristic data acquisition module 303, transaction behavior value setting module 304, target market subject credit value calculation module 305, credit level data search module 306 and credit level evaluation data construction module 307.

[0155] The business characteristic data acquisition module 301 is used to acquire the business characteristic data set of the target market subject.

[0156] The transaction behavior acquisition times matching module 302 is used to match the business characteristic data set with the standard transaction behavior acquisition times data set, so as to obtain the transaction behavior acquisition times data of the target market subject.

[0157] The transaction behavior characteristic data acquisition module 303 is used to acquire the transaction behavior characteristic data set of the target market subject based on the transaction behavior acquisition times data.

[0158] The transaction behavior value setting module 304 is used to set the corresponding value for the transaction behavior characteristic data set, and generate the transaction behavior value data set of the target market subject.

[0159] The target market subject credit value calculation module 305 is used to calculate the credit value of the target market subject according to the transaction behavior value data set.

[0160] The credit level data search module 306 is used to value match the credit value with the credit level interval data, and generate the credit level data of the target market subject.

[0161] The credit level evaluation data construction module 307 is used to construct the credit level evaluation data of the target market subject based on the transaction behavior characteristic data set and the credit level data, and push the credit level evaluation data to the market subject credit level evaluation platform through the wireless communication network.

[0162] In a specific application scenario, the business characteristic data acquisition module 301 is used to acquire the business type characteristic data and the business scale characteristic data of the target market subject through the Internet of Things platform, and take the business type characteristic data and the business scale characteristic data as the business characteristic data set of the target market subject.

[0163] In a specific application scenario, the transaction behavior acquisition times matching module 302 is used to perform character feature matching on the business characteristic data set with the standard transaction behavior acquisition times data set through the BM matching algorithm to obtain the transaction behavior acquisition times data of the target market entity, wherein the standard transaction behavior acquisition times data set includes standard transaction behavior acquisition times data corresponding to multiple business characteristic data, and the standard transaction behavior acquisition times data represents the standard number of times the transaction behavior characteristic data needs to be obtained when performing a credit rating assessment operation on the market entity corresponding to the business characteristic data.

[0164] In a specific application scenario, the transaction behavior characteristic data collection module 303 is used to obtain the frequency data according to the transaction behavior, and obtain the transaction behavior characteristic data matrix of the target market entity through the Internet of Things platform.

[0165]

[0166] Where C represents the transaction behavior characteristic data matrix of the target market entity, c ij Represents the characteristic data of the jth type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, l represents the total number of categories of transaction behavior feature data; the transaction behavior feature data matrix of the target market entity is used as the transaction behavior feature data set of the target market entity.

[0167] In a specific application scenario, the transaction behavior cost value setting module 304 is used to determine the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set through an intelligent optimization algorithm, and generate a transaction behavior cost value data matrix of the target market entity.

[0168]

[0169] in, Represents the transaction behavior cost data matrix of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of transaction behavior acquisition data, l represents the total number of categories of transaction behavior feature data; the transaction behavior cost value data matrix of the target market entity is used as the transaction behavior cost value data set of the target market entity.

[0170] In a specific application scenario, the transaction behavior cost value setting module 304 is used to set the population size, the maximum number of iterations, the current number of iterations, and the transaction behavior cost value data search space dimension based on the water wave optimization algorithm; initialize the transaction behavior cost value data search space, randomly generate multiple groups of transaction behavior cost value data in the transaction behavior cost value data search space according to the population size, and obtain a cost value search water wave population, wherein each group of the transaction behavior cost value data corresponds to a cost value search water wave individual in the cost value search water wave population, and each cost value search water wave individual in the cost value search water wave population has an initial wavelength and an initial wave height; calculate the fitness value of each cost value search water wave individual in the cost value search water wave population,

[0171]

[0172] Among them, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population, x i represents the accuracy of the transaction behavior cost value data corresponding to the i-th cost value search wave individual in the cost value search wave population in measuring the credit rating of the market entity, and φ represents the correction value; multiple cost value search wave individuals in the cost value search wave population are sorted in descending order of fitness value, and the cost value search wave individual ranked first in the sorting result is selected as the current optimal individual corresponding to the first iteration number; the cost value search wave population is iteratively calculated based on the maximum iteration number; in the current iteration number, the propagation strategy is used to update the positions and wavelengths of the multiple cost value search wave individuals in the transaction behavior cost value data search space,

[0173]

[0174] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand1 represents a random number uniformly distributed in the interval [-1,1], represents the wavelength of the i-th cost value search wave individual in the cost value search wave population before the position is updated, α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for transaction value data in the j-th dimension, represents the wavelength of the i-th cost value search wave individual in the cost value search wave population after the position is updated, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population before the position is updated, t represents the current number of iterations, t max represents the maximum number of iterations, f max represents the maximum fitness function of the cost-value search wave individual in the cost-value search wave population, f min represents the minimum value of the fitness function of the cost value search wave individual in the cost value search wave population, and χ represents the adjustment coefficient; calculates the fitness value of each cost value search wave individual in the cost value search wave population after the position is updated, and determines the current optimal individual corresponding to the current iteration number according to the fitness value of each cost value search wave individual after the position is updated; for each cost value search wave individual, if the fitness value of the cost value search wave individual after the position is updated is greater than the fitness value of the cost value search wave individual before the position is updated, then the fitness value of the cost value search wave individual after the position is updated is used as the fitness value of the cost value search wave at the current iteration number; when the fitness value of the cost value search wave individual after the position is updated is greater than the fitness value of the current optimal individual corresponding to the current iteration number, performs a breaking wave operation on the cost value search wave individual to update its position, and uses the position of the cost value search wave individual after the breaking wave operation as the position of the cost value search wave at the current iteration number.

[0175]

[0176] in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand2 represents a Gaussian random number in the interval (0, 1), α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the search lower limit of the j-th dimension transaction cost value data search space, and δ represents the breaking wave coefficient; when it is detected that the current number of iterations is greater than or equal to the maximum number of iterations, the cost value search wave individual with the highest fitness value in the cost value search wave population is taken as the global optimal solution; the transaction cost value data corresponding to the global optimal solution are data identified to generate the transaction cost value data matrix of the target market entity.

[0177] In a specific application scenario, the transaction behavior cost value setting module 304 is used to use the fitness value of the cost value search wave individual before the position update as the fitness value of the cost value search wave individual at the current iteration number if the fitness value of the cost value search wave individual after the position update is less than or equal to the fitness value of the cost value search wave individual before the position update, and reduce the wave height value of the cost value search wave individual by 1.

[0178] In a specific application scenario, the transaction behavior cost value setting module 304 is used to perform a refraction operation on the cost value search water wave individual when it is determined that the wave height value of the cost value search water wave individual is 0; calculate the average position based on the position of the current optimal individual corresponding to the current iteration number and the position of the cost value search water wave individual before the position update, use the average position as the position of the cost value search water wave at the current iteration number, and initialize the wavelength and wave height of the cost value search water wave individual after performing the refraction operation.

[0179] In a specific application scenario, the target market entity credit value calculation module 305 is used to calculate the transaction behavior cost value data set using the market entity credit value calculation formula to obtain the credit value of the target market entity.

[0180]

[0181] Among them, λ represents the credit value of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, l represents the total number of categories of transaction behavior feature data, ω j Represents the weight factor of the j-th type of transaction behavior characteristic data.

[0182] In a specific application scenario, the credit rating data search module 306 is used to perform numerical matching processing on the credit value and the credit rating interval data set through a bidirectional search algorithm, where the credit rating interval data set includes credit value interval data corresponding to multiple credit ratings; the credit value interval data in the credit rating interval data set that matches the credit value is used as the target credit value interval data, and the credit rating data of the target market entity is generated using the credit rating corresponding to the target credit value interval data.

[0183] The embodiment of the present application provides a system. Compared with the existing technology, the embodiment of the present application obtains the operating characteristic data of the target market entity and matches it with the preset standard transaction behavior acquisition frequency data, thereby accurately matching the transaction behavior acquisition frequency data of the target market entity; collects the transaction behavior characteristic data of the target market entity based on the transaction behavior acquisition frequency data, thereby avoiding excessive data collection and unnecessary waste of resources, thereby improving the efficiency of the evaluation process while ensuring the accuracy of the evaluation results; sets a corresponding cost value for the transaction behavior characteristic data and calculates the credit value of the target market entity, thereby providing a data basis for analyzing the target market entity; performs numerical matching based on the credit value and credit grade interval data, accurately searches for the credit grade data of the target market entity, and realizes a scientific evaluation of the credit grade of the market entity.

[0184] It should be noted that for other corresponding descriptions of the various functional units involved in the market entity credit rating assessment system provided in the embodiment of this application, please refer to Figure 1 and Figures 2A to 2B The corresponding description in will not be repeated here.

[0185] 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.

[0186] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are 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.

[0187] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

[0188] In an exemplary embodiment, see Figure 4 A computer device is also provided, comprising a bus, a processor, a memory, and a communication interface. The computer device may also include an input / output interface and a display device, wherein the various functional units can communicate with each other via the bus. The memory stores a computer program, and the processor is configured to execute the program stored in the memory and perform the market entity credit rating assessment method described in the above embodiment.

[0189] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the market entity credit rating assessment method.

[0190] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0191] Those skilled in the art will understand that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required to implement the present application.

[0192] Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the implementation scenario description, or can be modified accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module or further split into multiple submodules.

[0193] The above application serial numbers are for description only and do not represent the advantages or disadvantages of the implementation scenarios.

[0194] The above disclosure only describes several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the scope of protection of the present application.

Claims

1. A method for evaluating the credit rating of a market entity, characterized in that: include: Acquire a target market entity's business characteristic data set, and match the business characteristic data set with a standard transaction behavior acquisition frequency data set to obtain transaction behavior acquisition frequency data of the target market entity; Collecting a transaction behavior feature dataset of the target market entity based on the transaction behavior acquisition frequency data, setting a corresponding cost value for the transaction behavior feature dataset, and generating a transaction behavior cost value dataset of the target market entity; Calculating the credit value of the target market entity based on the transaction behavior cost value dataset, numerically matching the credit value with the credit rating interval data, and generating the credit rating data of the target market entity; Credit rating assessment data of the target market entity is constructed based on the transaction behavior feature data set and the credit rating data, and the credit rating assessment data is pushed to a market entity credit rating assessment platform via a wireless communication network.

2. The method according to claim 1, characterized in that The step of obtaining the target market entity's business characteristic data set and matching the business characteristic data set with the standard transaction behavior acquisition frequency data to obtain the target market entity's transaction behavior acquisition frequency data includes: Obtaining the business type characteristic data and business scale characteristic data of the target market entity through the Internet of Things platform, and using the business type characteristic data and the business scale characteristic data as the business characteristic data set of the target market entity; The business characteristic data set is matched with the standard transaction behavior acquisition frequency data set by character feature matching through the BM matching algorithm to obtain the transaction behavior acquisition frequency data of the target market entity, wherein the standard transaction behavior acquisition frequency data set includes standard transaction behavior acquisition frequency data corresponding to multiple business characteristic data, and the standard transaction behavior acquisition frequency data represents the standard number of transaction behavior characteristic data required to obtain when performing a credit rating assessment operation on the market entity corresponding to the business characteristic data.

3. The method according to claim 1, characterized in that The step of collecting a transaction behavior feature dataset of the target market entity based on the transaction behavior acquisition frequency data, setting a corresponding cost value for the transaction behavior feature dataset, and generating a transaction behavior cost value dataset of the target market entity includes: According to the number of transaction data obtained, the transaction behavior feature data matrix of the target market entity is obtained through the Internet of Things platform. Where C represents the transaction behavior characteristic data matrix of the target market entity, c ij Represents the characteristic data of the jth type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, and l represents the total number of categories of transaction behavior feature data; Using the transaction behavior characteristic data matrix of the target market subject as the transaction behavior characteristic data set of the target market subject; Determine the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set through an intelligent optimization algorithm, and generate a transaction behavior cost value data matrix of the target market entity. in, Represents the transaction behavior cost data matrix of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, and l represents the total number of categories of transaction behavior feature data; The transaction behavior cost value data matrix of the target market subject is used as the transaction behavior cost value data set of the target market subject.

4. The method according to claim 3, characterized in that The step of determining the cost value corresponding to each transaction behavior feature data in the transaction behavior feature data set by using an intelligent optimization algorithm to generate a transaction behavior cost value data matrix of the target market entity includes: Based on the water wave optimization algorithm, set the population size, maximum number of iterations, current number of iterations, and the transaction behavior cost data search space dimension; Initializing a transaction cost value data search space, randomly generating multiple groups of transaction cost value data in the transaction cost value data search space according to the population size, to obtain a cost value search wave population, wherein each group of transaction cost value data corresponds to a cost value search wave individual in the cost value search wave population, and each cost value search wave individual in the cost value search wave population has an initial wavelength and an initial wave height; Calculating the fitness value of each cost value search water wave individual in the cost value search water wave population, Among them, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population, x i represents the accuracy of the transaction behavior cost data corresponding to the i-th cost search wave individual in the cost search wave population in measuring the credit rating of the market entity, and φ represents the correction value; Sorting the plurality of cost value search wave individuals in the cost value search wave population in descending order of fitness values, and selecting the cost value search wave individual that ranks first in the sorting result as the current optimal individual corresponding to the first iteration number; Iteratively calculating the cost value search water wave population based on the maximum number of iterations; In the current iteration, a propagation strategy is used to update the positions and wavelengths of the multiple cost value search wave individuals in the transaction behavior cost value data search space. in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand1 represents a random number uniformly distributed in the interval [-1,1], represents the wavelength of the i-th cost value search wave individual in the cost value search wave population before the position is updated, α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for transaction value data in the j-th dimension, represents the wavelength of the i-th cost value search wave individual in the cost value search wave population after the position is updated, f i represents the fitness value of the i-th cost value search wave individual in the cost value search wave population before the position is updated, t represents the current number of iterations, t max represents the maximum number of iterations, f max represents the maximum fitness function of the cost-value search wave individual in the cost-value search wave population, f min represents the minimum value of the fitness function of the cost-value search wave individual in the cost-value search wave population, and χ represents the adjustment coefficient; Calculating the fitness value of each cost value search wave individual in the cost value search wave population after the position is updated, and determining the current optimal individual corresponding to the current number of iterations according to the fitness value of each cost value search wave individual after the position is updated; For each of the cost value search wave individuals, if the fitness value of the cost value search wave individual after the position update is greater than the fitness value of the cost value search wave individual before the position update, the fitness value of the cost value search wave individual after the position update is used as the fitness value of the cost value search wave at the current iteration number; When the fitness value of the cost value search wave individual after the position update is greater than the fitness value of the current optimal individual corresponding to the current iteration number, the cost value search wave individual is updated by performing a wave breaking operation, and the position of the cost value search wave individual after the wave breaking operation is set as the position of the cost value search wave at the current iteration number. in, represents the position of the i-th cost value search wave individual in the cost value search wave population after the position is updated in the j-dimensional transaction behavior cost value data search space, X ij represents the position of the i-th cost value search wave individual in the cost value search wave population before the position update in the j-th dimension transaction behavior cost value data search space, rand2 represents a Gaussian random number in the interval (0, 1), α j represents the search upper limit of the transaction value data search space of the j-th dimension, β j represents the lower limit of the search space for the transaction value data of the j-th dimension, and δ represents the breaking wave coefficient; When it is detected that the current number of iterations is greater than or equal to the maximum number of iterations, the cost value search wave individual with the highest fitness value in the cost value search wave population is taken as the global optimal solution; Data identification is performed on the transaction behavior cost value data corresponding to the global optimal solution to generate a transaction behavior cost value data matrix of the target market entity.

5. The method according to claim 4, characterized in that After determining the current optimal individual corresponding to the current number of iterations based on the fitness value of each cost value search water wave individual after position update, the method further includes: If the fitness value of the cost value search water wave individual after the position update is less than or equal to the fitness value of the cost value search water wave individual before the position update, the fitness value of the cost value search water wave individual before the position update is used as the fitness value of the cost value search water wave at the current number of iterations, and the wave height value of the cost value search water wave individual is reduced by 1.

6. The method according to claim 5, characterized in that The method further comprises: When it is determined that the wave height value of the cost value search water wave individual is 0, performing a refraction operation on the cost value search water wave individual; The average position is calculated based on the position of the current optimal individual corresponding to the current iteration number and the position of the cost value search water wave individual before the position update, and the average position is used as the position of the cost value search water wave at the current iteration number, and the wavelength and wave height of the cost value search water wave individual are initialized after the refraction operation is performed.

7. The method according to claim 1, characterized in that The step of calculating the credit value of the target market entity based on the transaction behavior cost value dataset, numerically matching the credit value with the credit rating interval data, and generating the credit rating data of the target market entity includes: The transaction behavior cost value dataset is calculated using the market entity credit value calculation formula to obtain the credit value of the target market entity. Among them, λ represents the credit value of the target market entity, Indicates the cost value corresponding to the characteristic data of the j-th type of transaction behavior in the i-th transaction behavior of the target market entity, represents the number of times the transaction behavior is obtained, l represents the total number of categories of transaction behavior feature data, ω j Represents the weight factor of the characteristic data of the j-th type of transaction behavior; Performing numerical matching processing on the credit value and a credit grade interval data set using a bidirectional search algorithm, wherein the credit grade interval data set includes credit value interval data corresponding to multiple credit grades; The credit value interval data matching the credit value in the credit grade interval data set is used as the target credit value interval data, and the credit grade corresponding to the target credit value interval data is used to generate the credit grade data of the target market entity.

8. A market entity credit rating assessment system, characterized by: It includes an operating characteristic data collection module, a transaction behavior acquisition frequency matching module, a transaction behavior characteristic data collection module, a transaction behavior cost value setting module, a target market entity credit value calculation module, a credit rating data search module, and a credit rating assessment data construction module; The business characteristic data collection module is used to obtain the business characteristic data set of the target market entity; The transaction behavior acquisition frequency matching module is used to match the business characteristic data set with the standard transaction behavior acquisition frequency data set to obtain the transaction behavior acquisition frequency data of the target market entity; The transaction behavior feature data collection module is used to collect the transaction behavior feature data set of the target market entity based on the transaction behavior acquisition frequency data; The transaction behavior cost value setting module is used to set a corresponding cost value for the transaction behavior feature data set to generate a transaction behavior cost value data set of the target market entity; The target market entity credit value calculation module is used to calculate the credit value of the target market entity based on the transaction behavior cost value dataset; The credit rating data search module is used to perform numerical matching between the credit value and the credit rating interval data to generate the credit rating data of the target market entity; The credit rating assessment data construction module is used to construct the credit rating assessment data of the target market entity based on the transaction behavior feature data set and the credit rating data, and push the credit rating assessment data to the market entity credit rating assessment platform through a wireless communication network.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images