Risk monitoring method and system for virtual account receivable in factoring business

Abstract

The invention provides a risk monitoring method and system for virtual account receivable in factoring business, and relates to the technical field of risk monitoring, and the method comprises the steps: constructing a distributed account book of a target factoring user set based on a block chain technology principle, and extracting a first factoring user which has a corresponding relation with the first account book; extracting a first transaction, and obtaining a first archiving record; acquiring a first transaction characteristic parameter set based on the multi-dimensional transaction characteristics; introducing a transaction risk assessment function to obtain a first risk index; obtaining a first account book feature parameter set based on the multi-dimensional account book features; obtaining a transaction risk mean value, and obtaining an account book risk total value; and activating a predetermined smart contract of the distributed account book, and executing a factoring protocol on the first factoring user. By introducing multi-dimensional transaction features and account book features, feature extraction and analysis are performed on transaction records of factoring users, so that credit risks and operation risks of the factoring users are evaluated more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of risk monitoring, and in particular to a risk monitoring method and system for fictitious accounts receivable in factoring business. Background Art

[0002] With the development of financial technology, the application of blockchain technology in the financial field is becoming more and more extensive. Blockchain technology has the characteristics of decentralization, immutability, high transparency and strong security, which makes it have broad application prospects in financial transactions, supply chain finance, factoring business and other aspects. Factoring business is a financial business that provides financing services to enterprises, and its main purpose is to help enterprises solve capital turnover problems. In traditional factoring business, due to information asymmetry and credit assessment difficulties, factoring companies face high credit risks and operational risks. In order to reduce risks, factoring companies need to conduct strict credit assessment and risk assessment on enterprises applying for factoring. However, traditional credit assessment and risk assessment methods have certain limitations. On the one hand, traditional credit assessment methods mainly rely on information such as the company's financial statements and credit records, but this information may be distorted and incomplete; on the other hand, traditional risk assessment methods mainly rely on manual experience and historical data, which is difficult to cope with the complex and changing financial market environment.

[0003] In summary, there are technical problems in the existing technology that make it impossible to scientifically and accurately assess the risk of factoring users, and thus fail to timely monitor the risk of fictitious accounts receivable in factoring business, which ultimately leads to high operational risks in factoring business and is not conducive to the healthy development of the factoring industry. Summary of the invention

[0004] The purpose of this application is to provide a risk monitoring method and system for fictitious accounts receivable in factoring business, so as to solve the technical problems in the prior art that the risk situation of factoring users cannot be scientifically and accurately assessed, and the risk of fictitious accounts receivable in factoring business cannot be monitored in time, which ultimately leads to high operational risks of factoring business and is not conducive to the healthy development of the factoring industry.

[0005] In view of the above problems, the present application provides a method and system for monitoring the risk of fictitious accounts receivable in factoring business.

[0006] In a first aspect, the present application provides a method for monitoring the risk of fictitious accounts receivable in factoring business, and the method is implemented by a risk monitoring system for fictitious accounts receivable in factoring business, wherein the risk monitoring method comprises: constructing a distributed ledger of a target factoring user set based on the principle of blockchain technology, and extracting a first factoring user from the target factoring user set, wherein the first factoring user has a corresponding relationship with a first ledger in the distributed ledger; randomly extracting a first transaction in the first ledger, and obtaining a first archived record of the first transaction; reading multi-dimensional transaction features, and collecting features of the first archived record based on the multi-dimensional transaction features to obtain a first transaction feature. parameter set; introducing a transaction risk assessment function to analyze the first transaction feature parameter set to obtain a first risk index for the first transaction; when the first risk index meets the first risk limit, reading the multidimensional ledger feature, and collecting features of the first ledger based on the multidimensional ledger feature to obtain a first ledger feature parameter set; obtaining a transaction risk average according to the first risk index, and obtaining a total ledger risk value of the first ledger by combining the transaction risk average with the first ledger feature parameter set; when the total ledger risk value meets the second risk limit, activating a predetermined smart contract of the distributed ledger, and executing a factoring agreement on the first factoring user according to the predetermined smart contract.

[0007] In the second aspect, the present application also provides a risk monitoring system for fictitious accounts receivable in factoring business, which is used to execute a risk monitoring method for fictitious accounts receivable in factoring business as described in the first aspect, wherein the risk monitoring system includes: a user acquisition module, the user acquisition module is used to construct a distributed ledger of a target factoring user set based on the principle of blockchain technology, and extract the first factoring user in the target factoring user set, wherein the first factoring user has a corresponding relationship with the first ledger in the distributed ledger; a matching acquisition module, the matching acquisition module is used to randomly extract a first transaction in the first ledger, and obtain a first archived record of the first transaction; a first feature collection module, the first feature collection module is used to read multi-dimensional transaction features, and collect features of the first archived record based on the multi-dimensional transaction features to obtain a first transaction feature parameter set; a first risk assessment module Module, the first risk assessment module is used to introduce a transaction risk assessment function to analyze the first transaction feature parameter set to obtain a first risk index for the first transaction; a second feature collection module, the second feature collection module is used to read the multi-dimensional ledger feature when the first risk index meets the first risk limit, and collect features of the first ledger based on the multi-dimensional ledger feature to obtain a first ledger feature parameter set; a second risk assessment module, the second risk assessment module is used to obtain a transaction risk average according to the first risk index, and the transaction risk average is combined with the first ledger feature parameter set to obtain a total ledger risk value of the first ledger; a factoring execution module, the factoring execution module is used to activate a predetermined smart contract of the distributed ledger when the total ledger risk value meets the second risk limit, and execute a factoring agreement on the first factoring user according to the predetermined smart contract.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: 1. First, a distributed ledger of the target factoring user set is constructed based on the principle of blockchain technology, and a first factoring user is extracted from it, and the user has a corresponding relationship with the first ledger in the distributed ledger. Next, the first transaction in the first ledger is randomly extracted, and the first archived record of the transaction is obtained. Then, the multi-dimensional transaction features are read, and the features of the first archived record are collected based on these features to obtain the first transaction feature parameter set. Next, a transaction risk assessment function is introduced to analyze the first transaction feature parameter set to obtain the first risk index of the first transaction. In addition, when the first risk index meets the first risk limit, the multi-dimensional ledger features are read, and the features of the first ledger are collected based on these features to obtain the first ledger feature parameter set. According to the first risk index, the transaction risk mean is obtained, and the total account risk value of the first account is obtained in combination with the first account feature parameter set. Finally, when the total account risk value meets the second risk limit, the predetermined smart contract of the distributed ledger is activated, and the factoring agreement is executed on the first factoring user according to the smart contract. In other words, by constructing a distributed ledger, the transaction data, credit records and other information of the factoring user are stored on the chain to achieve the authenticity and integrity of the data. At the same time, by introducing multi-dimensional transaction features and ledger features, the transaction records of factoring users are extracted and analyzed, so as to more accurately assess the credit risk and operational risk of factoring users, and achieve the goal of timely and accurate identification of fictitious accounts receivable, thereby achieving the technical effect of reducing the risk of factoring business and ensuring the healthy development of factoring business.

[0009] 2. By introducing multi-dimensional transaction features and ledger features, feature extraction and analysis are performed on the transaction records of factoring users, thereby improving the accuracy of risk assessment.

[0010] 3. Combining the transaction risk assessment function and the total risk value of the ledger, the risk assessment of factoring users is realized, and when the risk is controllable, the intelligent execution goal of the factoring agreement is achieved, effectively improving the intelligence level of factoring business.

[0011] 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 according to the contents of the specification, and 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 specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A flowchart of a risk monitoring method for fictitious accounts receivable in factoring business is provided for this application; Figure 2 This is a schematic diagram of the structure of a risk monitoring system for fictitious accounts receivable in factoring business.

[0014] Description of reference numerals: User acquisition module 11, matching acquisition module 12, first feature collection module 13, first risk assessment module 14, second feature collection module 15, second risk assessment module 16, factoring execution module 17. DETAILED DESCRIPTION

[0015] This application provides a risk monitoring method and system for fictitious accounts receivable in factoring business, which solves the technical problem that the existing technology cannot scientifically and accurately assess the risk of factoring users, and thus cannot timely monitor the risk of fictitious accounts receivable in factoring business, which ultimately leads to high operational risk of factoring business and is not conducive to the healthy development of the factoring industry. It provides a more efficient and accurate method for factoring user risk assessment, which effectively reduces the risk of factoring business.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them. Example

[0017] Please see attached Figure 1 The present application provides a method for monitoring the risk of fictitious accounts receivable in factoring business, wherein the method is applied to a risk monitoring system for fictitious accounts receivable in factoring business, and the risk monitoring method specifically comprises the following steps: Step 1: construct a distributed ledger of a target factoring user set based on the principle of blockchain technology, and extract a first factoring user from the target factoring user set, wherein the first factoring user has a corresponding relationship with the first ledger in the distributed ledger.

[0018] Specifically, blockchain technology is first used to build a distributed ledger specifically for the target factoring user set. The main technical goal is to achieve a secure, transparent and efficient factoring user information management platform, in which the information of each factoring user corresponds to a ledger in the distributed ledger, ensuring the consistency and traceability of the information.

[0019] Specifically, first, based on the principle of blockchain technology, a distributed ledger system is constructed. This system has the characteristics of decentralization, immutability and data transparency. Then, the information of the target factoring user set is recorded on this distributed ledger to ensure that the information of each user is securely stored. Next, the first factoring user in the target factoring user set is extracted. This extraction process involves technical operations such as data retrieval and data correspondence. In addition, it is ensured that the first factoring user has a corresponding relationship with the first ledger in the distributed ledger, which means that there is a one-to-one correspondence between user information and ledger records, which enhances the accuracy and reliability of the data. Finally, through such a technical solution, factoring user information can be effectively managed and queried, and the efficiency and security of factoring business can be improved.

[0020] In summary, building a distributed ledger of the target factoring user set based on the principles of blockchain technology not only achieves the secure storage and efficient management of user information, but also enhances the reliability and transparency of the entire system by ensuring the one-to-one correspondence between users and ledgers. This provides a powerful technical support platform for factoring business and helps promote the development and innovation of the factoring industry.

[0021] Step 2: randomly extracting a first transaction from the first account book, and obtaining a first archived record of the first transaction.

[0022] Specifically, first, a transaction is randomly extracted from a specific ledger and the archived record corresponding to the transaction is obtained. The main technical goal is to achieve random retrieval of transaction records and efficient extraction of related information to ensure the integrity and traceability of transaction data.

[0023] Specifically, first, determine the ledger to be retrieved, i.e., the first ledger. Then, randomly select a transaction from this ledger, i.e., the first transaction. This process involves a data random selection algorithm. Next, obtain the first archived record of the selected transaction. This usually involves data matching and data extraction techniques to ensure that the extracted records fully correspond to the randomly selected transactions. In addition, through such operations, the transaction records in the ledger can be effectively reviewed and queried, improving the transparency and credibility of the data. Finally, ensure the accuracy and security of the entire extraction process to protect the transaction data from illegal access or tampering.

[0024] In summary, by randomly extracting transactions from the ledger and obtaining their archived records, we can not only effectively retrieve and extract transaction data, but also ensure the integrity and security of transaction records. This provides technical support for the review, query and analysis of transaction data, and helps improve the efficiency and reliability of data management.

[0025] Step three: Read the multi-dimensional transaction features, and collect features of the first archived record based on the multi-dimensional transaction features to obtain a first transaction feature parameter set.

[0026] Specifically, first, multi-dimensional transaction features are read and analyzed, and then features of specific archived records are collected based on these features, and finally a transaction feature parameter set is obtained. The main technical goal is to extract representative and valuable information through in-depth analysis of transaction features, providing a basis for subsequent data processing and analysis.

[0027] Specifically, first, read the multi-dimensional transaction features. These features may include multiple dimensions such as transaction amount, time, location, participants, etc. Then, based on these multi-dimensional transaction features, collect features for the first archived record. This process involves data analysis and feature extraction technology. Next, generate the first transaction feature parameter set through the collected feature data. This parameter set is a set containing key feature information, which can be used for further data analysis and model building. In addition, this process may also include data cleaning and preprocessing steps to ensure the accuracy and reliability of feature parameters. Finally, through such feature collection and parameter set generation, the transaction data can be understood and analyzed more deeply to provide support for decision-making.

[0028] In summary, by reading multi-dimensional transaction features and collecting features from archived records, we can obtain a set of transaction feature parameters, which not only enables a deep understanding and analysis of transaction data, but also provides an important foundation for subsequent data processing and application. This helps improve the accuracy and efficiency of data analysis and promotes data-driven decision-making and strategy formulation.

[0029] Step 4: Introduce a transaction risk assessment function to analyze the first transaction feature parameter set to obtain a first risk index for the first transaction.

[0030] Specifically, first, a transaction risk assessment function is introduced to analyze the transaction feature parameter set to obtain the transaction risk index. The main technical goal is to evaluate the risk level of the transaction through quantitative analysis of transaction characteristics and provide a quantitative basis for risk management and decision-making.

[0031] Specifically, first, a transaction risk assessment function is introduced. This function can output a risk index based on the input of the transaction feature parameter set. Then, the first transaction feature parameter set is input into this risk assessment function. This process involves data analysis and the application of risk assessment models. Next, the risk index of the first transaction is obtained through the calculation and analysis of the function. This index is a quantitative representation of the transaction risk level and can be used for risk control and decision support. In addition, this process may also include the optimization and adjustment of the risk assessment function to improve the accuracy and adaptability of the assessment. Finally, through such risk assessment, transaction risks can be effectively identified and managed, providing an important reference for transaction decisions.

[0032] In summary, by introducing the transaction risk assessment function to analyze the transaction feature parameter set and obtain the transaction risk index, we can not only achieve the quantitative assessment of transaction risk, but also provide an important basis for risk management and decision-making. This helps to improve the efficiency and effectiveness of risk control and promote the security and stability of transactions.

[0033] Step 5: When the first risk index meets the first risk limit, read the multi-dimensional ledger feature, and collect features of the first ledger based on the multi-dimensional ledger feature to obtain a first ledger feature parameter set.

[0034] Specifically, first, under specific conditions, that is, when the first risk index meets the preset first risk limit, the multi-dimensional ledger characteristics are read, and based on these characteristics, the characteristics of the first ledger are collected, and finally a ledger characteristic parameter set is obtained. The main technical goal is to extract the key information of the ledger through in-depth analysis of the ledger characteristics, while ensuring that the risks are controllable, to provide a basis for subsequent data processing and analysis.

[0035] Specifically, first, a first risk limit is set as a standard for risk control. Then, when the first risk index meets this limit, the risk is considered to be within an acceptable range, and the next step is performed. Next, the multidimensional ledger features are read. These features may include multiple dimensions such as the size of the ledger, transaction frequency, and number of participants. Based on these multidimensional ledger features, features are collected for the first ledger. This process involves data analysis and feature extraction techniques. Then, the first ledger feature parameter set is generated based on the collected feature data. This parameter set is a set of key feature information that can be used for further data analysis and model building. In addition, this process may also include data cleaning and preprocessing steps to ensure the accuracy and reliability of the feature parameters. Finally, through such feature collection and parameter set generation, the ledger data can be more deeply understood and analyzed to provide support for decision-making.

[0036] In summary, under the condition that the risk index meets the specific limit, by reading the multi-dimensional ledger characteristics and collecting the characteristics of the ledger, the ledger characteristic parameter set is obtained, which not only realizes the in-depth understanding and analysis of the ledger data, but also provides an important basis for subsequent data processing and application. This helps to improve the accuracy and efficiency of data analysis and promote data-driven decision-making and strategy formulation.

[0037] Step 6: Obtain a transaction risk average according to the first risk index, and obtain a total account risk value of the first account book by combining the transaction risk average with the first account book characteristic parameter set.

[0038] Specifically, first, the transaction risk mean is calculated according to the first risk index, and the mean is combined with the first ledger characteristic parameter set to obtain the total ledger risk value of the first ledger. The main technical goal is to achieve a quantitative assessment of the overall risk level of the ledger through a comprehensive assessment of transaction risks and an in-depth analysis of ledger characteristics.

[0039] Specifically, first, the transaction risk mean is calculated based on the first risk index. This process involves data statistics and computational analysis. The transaction risk mean is the statistical average of a series of transaction risk indices, reflecting the average risk level of the transaction. Then, the calculated transaction risk mean is combined with the first ledger feature parameter set. This process involves data fusion and comprehensive analysis technology. The first ledger feature parameter set contains multi-dimensional feature information of the ledger. Next, by combining the transaction risk mean and the ledger feature parameter set, the total ledger risk value of the first ledger is calculated. This total value is a quantitative representation of the overall risk level of the ledger, which can be used for risk assessment and decision support. In addition, this process may also include the optimization and adjustment of the risk assessment model to improve the accuracy and adaptability of the assessment. Finally, through such risk assessment, the ledger data can be more comprehensively understood and analyzed, providing an important basis for risk management and decision-making.

[0040] In summary, by calculating the transaction risk mean according to the first risk index and combining it with the first account book characteristic parameter set, the total account book risk value is obtained, which not only realizes the quantitative assessment of the overall risk level of the account book, but also provides an important basis for risk management and decision-making. This helps to improve the efficiency and effectiveness of risk control and promote the security and stability management of account book data.

[0041] Step 7: When the total risk value of the ledger meets the second risk limit, activate the predetermined smart contract of the distributed ledger, and execute the factoring agreement on the first factoring user according to the predetermined smart contract.

[0042] Specifically, first, under specific conditions, that is, when the total value of the ledger risk meets the preset second risk limit, the predetermined smart contract of the distributed ledger is activated, and the factoring agreement is executed on the first factoring user according to the smart contract. The main technical goal is to realize an automated and intelligent factoring agreement execution mechanism to ensure that the factoring business is executed efficiently and securely under the premise of controllable risks.

[0043] Specifically, first, a second risk limit is set as a condition for activating the smart contract and executing the factoring agreement. Then, when the total risk value of the ledger is calculated, it is determined whether it meets this second risk limit. If it does, it is considered that the risk is within an acceptable range, and the predetermined smart contract of the distributed ledger is activated. Next, according to the terms and logic of the predetermined smart contract, the factoring agreement is executed for the first factoring user. This process involves the execution of smart contracts and factoring business operations. A smart contract is a program that automatically executes contract terms and can automatically perform corresponding operations when specific conditions are met. In addition, this process may also include verification and monitoring of smart contracts to ensure the accuracy and security of contract execution. Finally, through such smart contract activation and factoring agreement execution, factoring business risks can be effectively managed and the efficiency and reliability of business execution can be improved.

[0044] In summary, under the condition that the total risk value of the ledger meets the specific limit, by activating the predetermined smart contract of the distributed ledger and executing the factoring agreement for the first factoring user according to the smart contract, not only the automation and intelligent execution of factoring business is realized, but also an important guarantee for risk control. This helps to improve the management efficiency and service quality of factoring business and promote the innovation and development of the factoring industry.

[0045] Furthermore, the present application includes: When the total account book risk value does not meet the second risk limit, a fictitious risk warning is issued, and the factoring qualifications of the first factoring user are reviewed based on the fictitious risk warning.

[0046] Specifically, first, under certain conditions, that is, when the total risk value of the ledger does not meet the preset second risk limit, a fictitious risk warning is issued, and the factoring qualification of the first factoring user is reviewed based on the warning. The main technical goal is to implement a risk warning and qualification review mechanism to ensure that when the risk exceeds the preset range, it can be discovered in time and corresponding measures can be taken to ensure the security and compliance of the factoring business.

[0047] Specifically, first, a second risk limit is set as a benchmark for judging the total value of the book risk. Then, when the total value of the book risk is calculated, it is determined whether it meets this second risk limit. If it does not meet the limit, it is considered that the risk exceeds the acceptable range, and a fictitious risk warning is issued. Next, based on the fictitious risk warning issued, the factoring qualification of the first factoring user is reviewed. This process involves risk assessment and qualification review operations. The fictitious risk warning is a warning of potential risks, indicating that a more stringent qualification review of the relevant users is required. In addition, this process may also include the optimization and adjustment of the risk warning system to improve the accuracy and response speed of the warning. Finally, through such risk warnings and qualification reviews, potential risks can be discovered and responded to in a timely manner to ensure the security and compliance of factoring business.

[0048] In summary, under the condition that the total book risk value does not meet the specific limit, by issuing a fictitious risk warning and re-examining the factoring qualifications of the first factoring user based on the warning, not only can the potential risks be discovered and responded to in a timely manner, but also an important guarantee for the risk management and compliance of the factoring business is provided. This helps to improve the security and reliability of the factoring business and promote the healthy development of the factoring industry.

[0049] Furthermore, the present application includes: The multi-dimensional transaction characteristics include customer type, transaction amount, payment mode, data integrity, data rationality, document support and report consistency.

[0050] Specifically, we first defined multi-dimensional transaction characteristics, which include customer type, transaction amount, payment mode, data integrity, data rationality, file support and report consistency. The main technical goal is to achieve a comprehensive understanding and risk assessment of transaction behavior through in-depth analysis of these multi-dimensional transaction characteristics, so as to provide support for transaction management and decision-making.

[0051] Specifically, first, identify and define multidimensional transaction features. Customer type refers to the type of customer involved in the transaction, such as individuals or enterprises. Transaction amount involves the monetary value of the transaction. Payment mode describes the way funds flow in the transaction, such as electronic payment or cash payment. Data integrity refers to whether the transaction data is complete and intact. Data rationality involves whether the transaction data is reasonable and logical. Document support describes the support of transaction-related documents. Report consistency refers to the consistency and accuracy of transaction reports. Then, based on these multidimensional transaction features, transaction behavior analysis and risk assessment can be carried out. This process involves the application of data analysis and risk assessment models. Next, by analyzing these features, transaction behavior can be understood and evaluated more deeply to provide support for decision-making. In addition, this process may also include the optimization and adjustment of feature analysis and assessment models to improve the accuracy and adaptability of the analysis. Finally, through such multidimensional transaction feature analysis, transaction risks can be effectively identified and managed, providing important reference for transaction decisions.

[0052] In summary, by analyzing multi-dimensional transaction characteristics including customer type, transaction amount, payment mode, data integrity, data rationality, document support and report consistency, we can not only achieve a comprehensive understanding of transaction behavior and risk assessment, but also provide an important basis for transaction management and decision-making. This helps to improve the accuracy and efficiency of transaction analysis and promote the security and stability of transactions.

[0053] Furthermore, the present application includes: The expression of the transaction risk assessment function is as follows: ;in, The first transaction The first risk index, The first transaction The first fictional likelihood and the first risk index The first correlation coefficient of The first transaction The first fictional possibility, Refers to the first transaction feature parameter set Parameters With the said The parameter The absolute value of the deviation of the predetermined parameters, refers to the Parameters The corresponding The weight coefficients of the features, and .

[0054] Specifically, the expression of the transaction risk assessment function is as follows: ;in, The first transaction The first risk index, The first transaction The first fictional likelihood and the first risk index The first correlation coefficient of The first transaction The first fictional possibility is proportional to the first risk index. Refers to the first transaction feature parameter set Parameters With the said The parameter The absolute value of the deviation of the predetermined parameters, refers to the Parameters The corresponding The weight coefficients of the features, and That is, the multi-dimensional transaction characteristics include customer type, transaction amount, payment mode, data integrity, data rationality, file support and report consistency, a total of 7 characteristics.

[0055] Furthermore, the present application includes: Based on the support vector machine principle, supervised learning is performed on the training data set to obtain a risk classifier; the first transaction feature parameter set is input into the risk classifier to obtain a first classification result; and the first risk index is verified according to the first classification result.

[0056] Specifically, first, supervised learning is performed on the training data set using the support vector machine principle to obtain a risk classifier. Then, the first transaction feature parameter set is input into the classifier to obtain the first classification result, and the first risk index is verified accordingly. The main technical goal is to achieve an accurate risk assessment model, and improve the efficiency and accuracy of risk management by analyzing and classifying transaction features.

[0057] Specifically, first, supervised learning is performed on the training data set based on the principle of support vector machine. This process involves the application of machine learning algorithms and model training. Support vector machine is a commonly used classification algorithm suitable for binary classification problems. Through training, a risk or no risk classifier is obtained. Then, the first transaction feature parameter set is input into this classifier. This process involves data input and model application. Next, the first classification result is obtained through the processing of the classifier. This result is a judgment on whether the transaction is risky or not. In addition, based on this first classification result, the first risk index is verified. This process involves result analysis and adjustment of the risk index. Through verification, the accuracy and reliability of the risk index can be improved. Finally, through such risk classification and verification, transaction risks can be more accurately evaluated and managed to provide support for decision-making.

[0058] In summary, by conducting supervised learning on the training data set based on the support vector machine principle, a risk classifier is obtained, and the first transaction feature parameter set is input into the classifier to obtain a first classification result, and then the first risk index is verified according to the classification result, which not only achieves an accurate assessment of transaction risk, but also provides an important basis for risk management and decision-making. This helps to improve the efficiency and effectiveness of risk control and promote the security and stability of transactions.

[0059] Furthermore, the present application includes: Acquire historical transaction data records, wherein the historical transaction data records include a first historical record and a second historical record, wherein the first historical record has an identifier of a first normal accounts receivable, and the second historical record has an identifier of a first fictitious accounts receivable; extract a first historical transaction feature parameter set from the first historical record, and form a first training data group with the first normal accounts receivable; extract a second historical transaction feature parameter set from the second historical record, and form a second training data group with the first fictitious accounts receivable; the first training data group and the second training data group together form the training data set.

[0060] Specifically, historical transaction data records are first obtained, and a training data set is created based on these records. The training data set includes a first training data group and a second training data group, which are respectively composed of historical transaction feature parameter sets of normal and fictitious accounts receivable. The main technical goal is to build a training data set for risk assessment and classification, providing a data basis for subsequent machine learning models.

[0061] Specifically, first, historical transaction data records are obtained. These records include a first historical record and a second historical record. The first historical record has the identification of a first normal account receivable, and the second historical record has the identification of a first fictitious account receivable. Then, a first historical transaction feature parameter set is extracted from the first historical record, and it is combined with the first normal account receivable to form a first training data group. Next, a second historical transaction feature parameter set is extracted from the second historical record, and it is combined with the first fictitious account receivable to form a second training data group. These two data groups represent the transaction characteristics of normal and fictitious accounts receivable, respectively. Next, the first training data group and the second training data group are combined together to form a training data set. This data set contains the transaction characteristics of normal and fictitious accounts receivable, which can be used to train a risk assessment model. In addition, this process may also include data cleaning and preprocessing steps to ensure the quality and accuracy of the training data. Finally, through such data extraction and combination, a training data set for risk assessment and classification is constructed, which provides important data support for subsequent machine learning models.

[0062] In summary, by obtaining historical transaction data records, extracting historical transaction feature parameter sets of normal and fictitious accounts receivable, and forming a training data set, we can not only achieve in-depth analysis and utilization of historical transaction data, but also provide an important basis for the training and application of risk assessment models. This helps to improve the accuracy and efficiency of risk assessment and promote the development and innovation of risk management.

[0063] Furthermore, the present application includes: The multi-dimensional account book features include transaction frequency and business variation, including: obtaining a predetermined transaction frequency, and calculating a first deviation index between the transaction frequency and the predetermined transaction frequency; reading a variation factor, wherein the variation factor includes an actual business activity time series and a market transaction frequency time series; performing trend analysis on the actual business activity time series and the market transaction frequency time series in turn, and obtaining an actual business variation and a market transaction frequency variation respectively; weighting the actual business variation and the market transaction frequency variation to obtain a predetermined business variation; obtaining a second deviation index between the business variation and the predetermined business variation, and obtaining a first account book risk adjustment coefficient in combination with the first deviation index; and recording the product of the first account book risk adjustment coefficient and the transaction risk mean as the total account book risk value.

[0064] Specifically, the total value of ledger risk is calculated first, which involves multi-dimensional ledger characteristics, including transaction frequency and business variation. The main technical goal is to calculate a ledger risk adjustment coefficient through analysis of transaction frequency and business variation, and then combine it with the average transaction risk to obtain the total value of ledger risk, so as to achieve a quantitative assessment of ledger risk.

[0065] Specifically, first, the scheduled transaction frequency is obtained, and the first deviation index between the actual transaction frequency and the scheduled transaction frequency is calculated. This process involves data comparison and statistical analysis. Then, the variation factors are read, which include the actual business activity time series and the market transaction frequency time series. Next, the actual business activity time series and the market transaction frequency time series are trend analyzed. This process involves trend analysis and data interpretation. Through analysis, the actual business variation and the market transaction frequency variation are obtained respectively. Then, these two variations are weighted to obtain the scheduled business variation. In addition, the second deviation index between the business variation and the scheduled business variation is calculated. Finally, the first deviation index and the second deviation index are combined to obtain the first account book risk adjustment coefficient. This coefficient is multiplied by the transaction risk mean to obtain the total account book risk value. This process involves risk adjustment and calculation analysis. The total account book risk value is a quantitative representation of the overall risk level of the account book, which can be used for risk assessment and decision support.

[0066] In summary, by calculating the deviation index between the transaction frequency and the scheduled transaction frequency, trend analysis is performed on the actual business activity time series and the market transaction frequency time series, weighting is used to obtain the scheduled business range, and the deviation index between the business range and the scheduled business range is calculated. These indexes are combined to obtain the account book risk adjustment coefficient, which is then multiplied by the transaction risk mean to obtain the total account book risk value. This not only achieves a quantitative assessment of the account book risk, but also provides an important basis for risk management and decision-making. This helps to improve the efficiency and effectiveness of risk control and promote the security and stability management of account book data.

[0067] In summary, the risk monitoring method for fictitious accounts receivable in factoring business provided by this application has the following technical effects: 1. First, a distributed ledger of the target factoring user set is constructed based on the principle of blockchain technology, and a first factoring user is extracted from it, and the user has a corresponding relationship with the first ledger in the distributed ledger. Next, the first transaction in the first ledger is randomly extracted, and the first archived record of the transaction is obtained. Then, the multi-dimensional transaction features are read, and the features of the first archived record are collected based on these features to obtain the first transaction feature parameter set. Next, a transaction risk assessment function is introduced to analyze the first transaction feature parameter set to obtain the first risk index of the first transaction. In addition, when the first risk index meets the first risk limit, the multi-dimensional ledger features are read, and the features of the first ledger are collected based on these features to obtain the first ledger feature parameter set. According to the first risk index, the transaction risk mean is obtained, and the total account risk value of the first account is obtained in combination with the first account feature parameter set. Finally, when the total account risk value meets the second risk limit, the predetermined smart contract of the distributed ledger is activated, and the factoring agreement is executed on the first factoring user according to the smart contract. In other words, by constructing a distributed ledger, the transaction data, credit records and other information of the factoring user are stored on the chain to achieve the authenticity and integrity of the data. At the same time, by introducing multi-dimensional transaction features and ledger features, the transaction records of factoring users are extracted and analyzed, so as to more accurately assess the credit risk and operational risk of factoring users, and achieve the goal of timely and accurate identification of fictitious accounts receivable, thereby achieving the technical effect of reducing the risk of factoring business and ensuring the healthy development of factoring business.

[0068] 2. By introducing multi-dimensional transaction features and ledger features, feature extraction and analysis are performed on the transaction records of factoring users, thereby improving the accuracy of risk assessment.

[0069] 3. Combining the transaction risk assessment function and the total risk value of the ledger, the risk assessment of factoring users is realized, and when the risk is controllable, the intelligent execution goal of the factoring agreement is achieved, effectively improving the intelligence level of factoring business. Example

[0070] Based on the same inventive concept as the risk monitoring method for fictitious accounts receivable in factoring business in the aforementioned embodiment, the present application also provides a risk monitoring system for fictitious accounts receivable in factoring business, please refer to the attached Figure 2 , the risk monitoring system comprises: A user acquisition module 11, the user acquisition module 11 is used to construct a distributed ledger of a target factoring user set based on the principle of blockchain technology, and extract a first factoring user from the target factoring user set, wherein the first factoring user has a corresponding relationship with a first ledger in the distributed ledger; a matching acquisition module 12, the matching acquisition module 12 is used to randomly extract a first transaction in the first ledger, and obtain a first archived record of the first transaction; a first feature collection module 13, the first feature collection module 13 is used to read multi-dimensional transaction features, and based on the multi-dimensional transaction features, perform feature collection on the first archived record to obtain a first transaction feature parameter set; a first risk assessment module 14, the first risk assessment module 14 is used to introduce a transaction risk assessment function to perform feature collection on the first transaction feature parameter set The first transaction is analyzed to obtain a first risk index of the first transaction; a second feature collection module 15, the second feature collection module 15 is used to read the multi-dimensional ledger feature when the first risk index meets the first risk limit, and collect features of the first ledger based on the multi-dimensional ledger feature to obtain a first ledger feature parameter set; a second risk assessment module 16, the second risk assessment module 16 is used to obtain a transaction risk average according to the first risk index, and the transaction risk average is combined with the first ledger feature parameter set to obtain a total ledger risk value of the first ledger; a factoring execution module 17, the factoring execution module 17 is used to activate a predetermined smart contract of the distributed ledger when the total ledger risk value meets the second risk limit, and execute a factoring agreement on the first factoring user according to the predetermined smart contract.

[0071] Furthermore, the risk monitoring system also includes a factoring warning module, which is used to issue a fictitious risk warning when the total book risk value does not meet the second risk limit, and review the factoring qualifications of the first factoring user based on the fictitious risk warning.

[0072] Furthermore, the first feature collection module 13 in the risk monitoring system is also used for the multi-dimensional transaction features including customer type, transaction amount, payment mode, data integrity, data rationality, file support and report consistency.

[0073] Furthermore, the first risk assessment module 14 in the risk monitoring system is also used for the expression of the transaction risk assessment function to be as follows: ;in, The first transaction The first risk index, The first transaction The first fictional likelihood and the first risk index The first correlation coefficient of The first transaction The first fictional possibility, Refers to the first transaction feature parameter set Parameters With the said The parameter The absolute value of the deviation of the predetermined parameters, refers to the Parameters The corresponding The weight coefficients of the features, and .

[0074] Furthermore, the risk monitoring system also includes a risk verification module, which is used to: perform supervised learning on the training data set based on the support vector machine principle to obtain a risk classifier; input the first transaction feature parameter set into the risk classifier to obtain a first classification result; and verify the first risk index based on the first classification result.

[0075] Furthermore, the risk verification module in the risk monitoring system is also used to: obtain historical transaction data records, the historical transaction data records include a first historical record and a second historical record, the first historical record has an identifier of a first normal accounts receivable, and the second historical record has an identifier of a first fictitious accounts receivable; extract a first historical transaction feature parameter set from the first historical record, and form a first training data group with the first normal accounts receivable; extract a second historical transaction feature parameter set from the second historical record, and form a second training data group with the first fictitious accounts receivable; the first training data group and the second training data group together constitute the training data set.

[0076] Furthermore, the second risk assessment module 16 in the risk monitoring system is also used for: the multidimensional account book features include transaction frequency and business variation, obtaining a predetermined transaction frequency, and calculating a first deviation index between the transaction frequency and the predetermined transaction frequency; reading a variation factor, the variation factor including an actual business activity time series and a market transaction frequency time series; performing trend analysis on the actual business activity time series and the market transaction frequency time series in turn, and obtaining an actual business variation and a market transaction frequency variation respectively; weighting the actual business variation and the market transaction frequency variation to obtain a predetermined business variation; obtaining a second deviation index between the business variation and the predetermined business variation, and combining the first deviation index to obtain a first account book risk adjustment coefficient; and recording the product of the first account book risk adjustment coefficient and the transaction risk mean as the total account book risk value.

[0077] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The risk monitoring method and specific examples of fictitious accounts receivable in a factoring business in Example 1 are also applicable to the risk monitoring system of fictitious accounts receivable in a factoring business in this embodiment. Through the detailed description of the risk monitoring method of fictitious accounts receivable in a factoring business, those skilled in the art can clearly know the risk monitoring system of fictitious accounts receivable in a factoring business in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0078] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0079] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring the risk of fictitious accounts receivable in factoring business, characterized in that: include: Constructing a distributed ledger of a target factoring user set based on the principle of blockchain technology, and extracting a first factoring user from the target factoring user set, wherein the first factoring user has a corresponding relationship with a first ledger in the distributed ledger; Randomly extracting a first transaction in the first account book, and obtaining a first archived record of the first transaction; Reading multi-dimensional transaction features, and collecting features of the first archived record based on the multi-dimensional transaction features to obtain a first transaction feature parameter set; Introducing a transaction risk assessment function to analyze the first transaction feature parameter set to obtain a first risk index for the first transaction; When the first risk index meets the first risk limit, reading the multi-dimensional account book feature, and collecting features of the first account book based on the multi-dimensional account book feature to obtain a first account book feature parameter set; Obtaining a transaction risk average according to the first risk index, and combining the transaction risk average with the first account book characteristic parameter set to obtain a total account book risk value of the first account book; When the total risk value of the ledger meets the second risk limit, a predetermined smart contract of the distributed ledger is activated, and a factoring agreement is executed on the first factoring user according to the predetermined smart contract.

2. The risk monitoring method according to claim 1, characterized in that: When the total account book risk value does not meet the second risk limit, a fictitious risk warning is issued, and the factoring qualifications of the first factoring user are reviewed based on the fictitious risk warning.

3. The risk monitoring method according to claim 1, characterized in that: The multi-dimensional transaction characteristics include customer type, transaction amount, payment mode, data integrity, data rationality, document support and report consistency.

4. The risk monitoring method according to claim 3, characterized in that: The expression of the transaction risk assessment function is as follows: ； in, The first transaction The first risk index, The first transaction The first fictional likelihood and the first risk index The first correlation coefficient of The first transaction The first fictional possibility, Refers to the first transaction feature parameter set Parameters With the said The parameter The absolute value of the deviation of the predetermined parameters, refers to the Parameters The corresponding The weight coefficients of the features, and .

5. The risk monitoring method according to claim 1, characterized in that: include: Based on the principle of support vector machine, supervised learning is performed on the training data set to obtain a risk classifier; Inputting the first transaction feature parameter set into the risk classifier to obtain a first classification result; The first risk index is verified according to the first classification result.

6. The risk monitoring method according to claim 5, characterized in that: include: Acquire a historical transaction data record, wherein the historical transaction data record includes a first historical record and a second historical record, wherein the first historical record has an identifier of a first normal account receivable, and the second historical record has an identifier of a first fictitious account receivable; Extracting a first historical transaction feature parameter set from the first historical record and forming a first training data group with the first normal accounts receivable; Extracting a second historical transaction feature parameter set from the second historical record and forming a second training data group with the first fictitious accounts receivable; The first training data set and the second training data set together constitute the training data set.

7. The risk monitoring method according to claim 1, characterized in that: The multi-dimensional ledger features include transaction frequency and business variation, including: Obtaining a predetermined transaction frequency, and calculating a first deviation index between the transaction frequency and the predetermined transaction frequency; Reading a variation factor, wherein the variation factor includes an actual business activity timing and a market transaction frequency timing; Performing trend analysis on the actual business activity time series and the market transaction frequency time series in turn, and obtaining actual business variation and market transaction frequency variation respectively; Weighting the actual business variation and the market transaction frequency variation to obtain a predetermined business variation; Obtaining a second deviation index between the business variation range and the predetermined business variation range, and obtaining a first account book risk adjustment coefficient in combination with the first deviation index; The product of the first account book risk adjustment coefficient and the transaction risk average is recorded as the total account book risk value.

8. A risk monitoring system for fictitious accounts receivable in factoring business, characterized in that: For implementing the steps of the risk monitoring method according to any one of claims 1 to 7, the risk monitoring system comprises: A user acquisition module, the user acquisition module is used to construct a distributed ledger of a target factoring user set based on the principle of blockchain technology, and extract a first factoring user from the target factoring user set, wherein the first factoring user has a corresponding relationship with the first ledger in the distributed ledger; a matching acquisition module, the matching acquisition module being used to randomly extract a first transaction in the first account book and acquire a first archived record of the first transaction; A first feature collection module, the first feature collection module is used to read the multi-dimensional transaction feature, and collect features of the first archived record based on the multi-dimensional transaction feature to obtain a first transaction feature parameter set; A first risk assessment module, the first risk assessment module is used to introduce a transaction risk assessment function to analyze the first transaction feature parameter set to obtain a first risk index of the first transaction; a second feature collection module, wherein the second feature collection module is configured to read a multi-dimensional ledger feature when the first risk index meets a first risk limit, and perform feature collection on the first ledger based on the multi-dimensional ledger feature to obtain a first ledger feature parameter set; A second risk assessment module, the second risk assessment module is used to obtain a transaction risk average according to the first risk index, and the transaction risk average is combined with the first account book characteristic parameter set to obtain a total account book risk value of the first account book; A factoring execution module, wherein the factoring execution module is used to activate a predetermined smart contract of the distributed ledger when the total risk value of the ledger meets a second risk limit, and execute a factoring agreement on the first factoring user according to the predetermined smart contract.

Images