Financial enterprise credit evaluation system and method based on block chain

Abstract

The invention discloses a financial enterprise credit evaluation system and method based on a block chain. The system comprises a data acquisition module, a data chaining module and a data evaluation module. Wherein the data acquisition module is used for acquiring enterprise financial data of a to-be-evaluated enterprise, and the enterprise financial data at least comprises a public financial statement, bank flow data and supply chain cooperation information; the data uplink module is used for encrypting enterprise financial data to obtain financial ciphertext data, and transmitting the financial ciphertext data to the block chain node; and the data evaluation module is used for analyzing and evaluating the financial ciphertext data based on an intelligent contract in a preset evaluation model, obtaining a credit evaluation result of the to-be-evaluated enterprise and storing the credit evaluation result in the block chain node. According to the invention, accurate, efficient and safe credit assessment of the financial enterprise is realized.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a blockchain-based financial enterprise credit assessment method and system. Background Art

[0002] Financial enterprises are mainly engaged in deposits and loans, financing and mergers and acquisitions, insurance, securities and funds, etc. Their credit is the "credit card" of financial enterprises in market economic activities and the basis for engaging in financial business. Therefore, accurate assessment of the credit of financial enterprises is crucial to financial enterprises.

[0003] At present, the evaluation of financial enterprise credit information usually relies on credit rating agencies to collect information for analysis and evaluation. This evaluation method is not only time-consuming and labor-intensive, but also prone to inaccurate evaluation due to information asymmetry and insufficient analysis. At the same time, it is also prone to data security issues. Therefore, how to accurately, efficiently and safely evaluate the credit of financial enterprises is one of the technical problems that need to be solved at present. Summary of the invention

[0004] The main purpose of the present invention is to provide a financial enterprise credit assessment system and method based on blockchain, aiming to solve the technical problem of how to accurately, efficiently and securely conduct credit assessment on financial enterprises in the prior art.

[0005] To achieve the above-mentioned purpose, the present invention provides a financial enterprise credit evaluation system based on blockchain, wherein the financial enterprise credit evaluation system based on blockchain includes a data acquisition module, a data chain module and a data evaluation module; wherein:

[0006] The data collection module is used to collect corporate financial data of the enterprise to be evaluated, and the corporate financial data at least includes public financial statements, bank flow data and supply chain cooperation information;

[0007] The data on-chain module is used to encrypt the enterprise financial data, obtain financial ciphertext data, and transmit the financial ciphertext data to the blockchain node;

[0008] The data evaluation module is used to analyze and evaluate the financial ciphertext data based on the smart contract in the preset evaluation model, and obtain the credit evaluation result of the enterprise to be evaluated and store it in the blockchain node.

[0009] Preferably, the data evaluation module comprises:

[0010] A screening unit, configured to screen out current asset value, current liability value, total asset value, retained earnings value, earnings before interest and taxes value, stock market value, total number of stocks, total liabilities value and sales from the financial ciphertext data based on the smart contract in the preset evaluation model;

[0011] a calculation unit, configured to calculate a first parameter according to the current asset value, the current liability value and the total asset value, calculate a second parameter according to the retained earnings value and the total asset value, calculate a third parameter according to the EBIT value and the total asset value, calculate a fourth parameter according to the stock market value, the total number of stocks and the total liability value, and calculate a fifth parameter according to the sales and the total asset value;

[0012] An evaluation unit, configured to analyze and evaluate the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter based on a preset evaluation model, calculate a bankruptcy risk coefficient, and generate the evaluation result based on the bankruptcy risk coefficient;

[0013] The calculation formula of the bankruptcy risk coefficient is:

[0014] Z=k1*X1+k2*X2+k3*X3+k4*X4+k5*X5;

[0015] Among them, Z represents the bankruptcy risk coefficient, K1, K2, K3, K4, K5 represent the reference coefficients of the preset evaluation model respectively, and X1, X2, X3, X4, X5 represent the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter respectively.

[0016] Preferably, the financial enterprise credit assessment system further includes:

[0017] A sample processing module, used to obtain financial sample data, and process the financial sample data according to preset risk characteristics to obtain multiple groups of risk characteristic samples corresponding to each of the preset risk characteristics;

[0018] The model training module is used to train the initial risk model based on multiple groups of risk feature samples, and obtain the risk score value calculated by the initial risk model for each group of risk feature samples. The calculation formula of the risk score value is:

[0019] Si==ln(Pi / (1-Pi));

[0020] Among them, Si represents the risk score value corresponding to the risk characteristic sample of the i-th group, and Pi represents the probability value predicted by the initial risk model that the risk characteristic sample of the i-th group exists at risk;

[0021] A calibration module is used to calibrate the initial risk model according to the score difference between the reference score value corresponding to each group of risk feature samples and the risk score value, so as to generate the initial risk model as a preset evaluation model based on the calibration of the initial risk model.

[0022] Preferably, the data uplink module further includes:

[0023] A block division unit, used for dividing the enterprise financial data into blocks to obtain a plurality of data blocks, and determining whether the last data block obtained through division has a preset data length;

[0024] A padding unit, used for padding the last data block based on preset padding data to obtain a padding data block when the last data block does not have a preset data length;

[0025] An encryption unit is used to generate a public key and a private key based on a preset algorithm, and to encrypt the padding data block and other data blocks among the multiple data blocks except the padding data block based on the public key to obtain multiple ciphertext data, and to jointly generate the multiple ciphertext data and the private key into the financial ciphertext data.

[0026] Preferably, the financial enterprise credit assessment system further includes:

[0027] The data updating module is used to collect the enterprise financial data updated by the enterprise to be evaluated within the preset period at intervals of the preset period, so as to update the credit evaluation result based on the updated enterprise financial data.

[0028] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a financial enterprise credit assessment method based on blockchain, the financial enterprise credit assessment method comprising:

[0029] Collecting corporate financial data of the enterprise to be evaluated, the corporate financial data at least includes public financial statements, bank flow data and supply chain cooperation information;

[0030] Encrypting the enterprise financial data to obtain financial ciphertext data, and transmitting the financial ciphertext data to the blockchain node;

[0031] The financial ciphertext data is analyzed and evaluated based on the smart contract in the preset evaluation model to obtain the credit evaluation result of the enterprise to be evaluated, and the credit evaluation result is stored in the blockchain node.

[0032] Preferably, the step of analyzing and evaluating the financial ciphertext data based on the smart contract in the preset evaluation model to obtain the credit evaluation result of the enterprise to be evaluated includes:

[0033] Based on the smart contract in the preset evaluation model, the current asset value, current liability value, total asset value, retained earnings value, earnings before interest and taxes value, stock market value, total number of stocks, total liabilities value and sales are screened out from the financial ciphertext data;

[0034] Calculating a first parameter based on the current asset value, current liability value and total asset value, calculating a second parameter based on the retained earnings value and total asset value, calculating a third parameter based on the EBIT value and total asset value, calculating a fourth parameter based on the stock market value, total number of stocks and total liabilities value, and calculating a fifth parameter based on sales and total asset value;

[0035] The preset evaluation model analyzes and evaluates the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter, calculates the bankruptcy risk coefficient, and generates the evaluation result based on the bankruptcy risk coefficient;

[0036] The calculation formula of the bankruptcy risk coefficient is:

[0037] Z=k1*X1+k2*X2+k3*X3+k4*X4+k5*X5;

[0038] Among them, Z represents the bankruptcy risk coefficient, K1, K2, K3, K4, K5 represent the reference coefficients of the preset evaluation model respectively, and X1, X2, X3, X4, X5 represent the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter respectively.

[0039] Preferably, the step of performing credit assessment on the enterprise to be assessed based on the smart contract in the preset assessment model includes:

[0040] Obtain financial sample data, and process the financial sample data according to preset risk characteristics to obtain multiple groups of risk characteristic samples corresponding to each of the preset risk characteristics; (processing as events)

[0041] The initial risk model is trained based on multiple groups of risk feature samples, and the risk score value calculated by the initial risk model for each group of risk feature samples is obtained. The calculation formula of the risk score value is:

[0042] Si==ln(Pi / (1-Pi));

[0043] Among them, Si represents the risk score value corresponding to the risk characteristic sample of the i-th group, and Pi represents the probability value predicted by the initial risk model that the risk characteristic sample of the i-th group exists at risk;

[0044] The initial risk model is calibrated according to the score difference between the reference score value corresponding to each group of risk feature samples and the risk score value, so as to generate the initial risk model as a preset assessment model based on the calibration of the initial risk model.

[0045] Preferably, the step of encrypting the enterprise financial data to obtain financial ciphertext data includes:

[0046] Divide the enterprise financial data into blocks to obtain a plurality of data blocks, and determine whether the last data block obtained through the division has a preset data length;

[0047] When the last data block does not have a preset data length, padding the last data block based on preset padding data to obtain a padding data block;

[0048] A public key and a private key are generated based on a preset algorithm, and the padding data block and other data blocks among the multiple data blocks except the padding data block are encrypted respectively based on the public key to obtain multiple ciphertext data, and the multiple ciphertext data and the private key are jointly generated into the financial ciphertext data.

[0049] Preferably, after the step of transmitting the credit assessment result to the blockchain node for storage, the step further includes:

[0050] At every preset period, the enterprise financial data of the enterprise to be evaluated updated within the preset period is collected, and the credit evaluation result is updated based on the updated enterprise financial data.

[0051] The present invention is based on the blockchain-based financial enterprise credit evaluation system and method, the system includes a data acquisition module, a data chain module and a data evaluation module; wherein the data acquisition module is used to collect the enterprise financial data of the enterprise to be evaluated, and the collected enterprise financial data at least includes public financial statements, bank flow data and supply chain cooperation information; the data chain module is used to encrypt the collected enterprise financial data, obtain financial ciphertext data, and transmit the financial ciphertext data to the block node; the data evaluation module is used to analyze and evaluate the financial ciphertext data based on the smart contract in the preset evaluation model, and obtain the credit evaluation result of the enterprise to be evaluated and store it in the blockchain node. In this way, various financial data related to financial enterprises are collected by crawler technology, so that the collected data is more efficient and comprehensive, and at the same time, various financial data are encrypted and transmitted to the blockchain node, and the preset evaluation model is analyzed and evaluated according to the smart contract, and the credit evaluation result of the enterprise to be evaluated is obtained and stored in the blockchain node, and the security of various financial data and evaluation results is ensured by the immutability of the blockchain, and the preset evaluation model formed by a large number of financial data samples is analyzed and evaluated, so that the generated evaluation result is more accurate, and the credit evaluation of financial enterprises is realized accurately, efficiently and safely. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a module diagram of the first embodiment of the financial enterprise credit assessment system based on blockchain of the present invention;

[0053] Figure 2This is a module diagram of the second embodiment of the financial enterprise credit assessment system based on blockchain of the present invention;

[0054] Figure 3 This is a flowchart of the first embodiment of the financial enterprise credit assessment method based on blockchain of the present invention;

[0055] Figure 4 This is a flow chart of the second embodiment of the financial enterprise credit assessment method based on blockchain of the present invention.

[0056] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0057] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0058] The present invention provides a financial enterprise credit assessment system based on blockchain, please refer to Figure 1 , Figure 1 This is a module diagram of the first embodiment of the financial enterprise credit assessment system based on blockchain of the present invention.

[0059] Specifically, the blockchain-based financial enterprise credit assessment system in this embodiment includes a data collection module 10, a data uploading module 20 and a data assessment module 30, wherein:

[0060] The data collection module 10 is used to collect the enterprise financial data of the enterprise to be evaluated, and the enterprise financial data at least includes public financial statements, bank flow data and supply chain cooperation information;

[0061] Furthermore, when a financial enterprise needs to undergo a credit assessment, it initiates an assessment request to the blockchain-based financial enterprise credit assessment system of this embodiment. After receiving the assessment request, the system reads the enterprise ID (Identification) carried therein, determines the specific financial enterprise that needs to undergo a credit assessment by the enterprise ID, and uses the financial enterprise that needs to undergo a credit assessment as the enterprise to be assessed.

[0062] Furthermore, the financial enterprise credit assessment system based on blockchain initiates a credit assessment of the enterprise to be assessed, and the data collection module in the system collects various public information related to the enterprise to be assessed from various official websites, news websites, social platforms and other channels by calling API (Application Programming Interface), web crawlers and other technologies. At the same time, a prompt message is sent to the enterprise to be assessed, prompting the enterprise to be assessed to upload the enterprise financial data. The enterprise to be assessed uploads the corresponding enterprise financial data according to the type of financial data contained in the prompt message, and the uploaded enterprise financial data type at least includes public financial statements, bank flow data and supply chain cooperation information. The financial enterprise credit assessment system based on blockchain combines the collected public information with the received enterprise financial data to verify each enterprise financial data. If the public information is consistent with the enterprise financial data, the enterprise financial data is marked as accurate, and if the public information is inconsistent with the enterprise financial data, the enterprise financial data is marked as pending. Then feedback information is sent to the enterprise to be assessed, and the enterprise to be assessed sends explanation information to the system based on the feedback information to explain the inconsistency. The system evaluates the rationality of the explanation information, and if the evaluation passes, the corresponding enterprise financial data is marked as accurate. If the assessment fails, the corresponding corporate financial data will be removed to ensure the accuracy of the corporate financial data. After all corporate financial data are verified, the final corporate financial data used for credit assessment of the assessed enterprise is generated.

[0063] The data uplink module 20 is used to encrypt the enterprise financial data, obtain financial ciphertext data, and transmit the financial ciphertext data to the blockchain node;

[0064] Furthermore, in order to ensure the security of corporate financial data, the data on the chain module in the system is encrypted to obtain the corresponding financial ciphertext data and transmit it to the blockchain node. Among them, encryption can adopt any one of the hash encryption algorithm, asymmetric encryption algorithm, elliptic curve encryption algorithm and digital signature encryption algorithm. This embodiment preferably adopts an asymmetric encryption algorithm.

[0065] Specifically, the data uplink module 20 includes:

[0066] A block division unit 21 is used to divide the enterprise financial data into blocks to obtain multiple data blocks, and determine whether the last data block obtained after division has a preset data length;

[0067] A padding unit 22, configured to pad the last data block based on preset padding data to obtain a padding data block when the last data block does not have a preset data length;

[0068] The encryption unit 23 is used to generate a public key and a private key based on a preset algorithm, and to encrypt the padding data block and other data blocks among the multiple data blocks except the padding data block based on the public key to obtain multiple ciphertext data, and to jointly generate the multiple ciphertext data and the private key into the financial ciphertext data.

[0069] Furthermore, in order to realize the encryption of enterprise financial data, the data uplink module is set to include a block unit, a padding unit and an encryption unit. The enterprise financial data is processed by the block module and divided into data blocks with the same data format and fixed data size. Among them, the data format and the data size can be preset. Among the multiple data blocks obtained by division, the data size of the last divided data block may not be a fixed data size. The fixed data size corresponds to a fixed data length, and the data length is used as the preset data length. After the block module divides and obtains multiple databases, the data length of the last data block obtained by division is judged, and its data length is compared with the preset data length. Through the comparison, it is judged whether the last data block obtained by division has the preset data length. If the comparison determines that the data length is consistent with the preset data length, it is judged that the last data block has the preset data length. On the contrary, if it is inconsistent, it is judged that it does not have the preset data length.

[0070] Furthermore, if the last data block is determined not to have a preset data length, the last data block is filled with preset filling data by the filling unit in the data on-chain module. The preset filling data is pre-set meaningless data, such as 1000..., or 0111..., etc. After the filling, the last data block has a preset data length, which is used as a filling data block. Then the encryption unit generates a public key and a private key by a preset algorithm, and the preset algorithm can be an RSA encryption algorithm. According to the generated public key, the filling data block and the other data blocks except the filling data block, that is, the last data block, in the multiple data blocks initially divided are encrypted respectively to obtain the corresponding ciphertext data. Then, each ciphertext data and private key are jointly generated as the amount ciphertext data and transmitted to the blockchain node for the blockchain members to obtain and view. Among them, the blockchain members are different according to the type of blockchain. For the public chain, its members are all people, for the alliance chain, the members are limited to members within the alliance, and for the private chain, its members are limited to company members.

[0071] The data evaluation module 30 is used to analyze and evaluate the financial ciphertext data based on the smart contract in the preset evaluation model, and obtain the credit evaluation result of the enterprise to be evaluated and store it in the blockchain node.

[0072] Furthermore, a preset evaluation model is pre-formed through training in the system. The data evaluation module analyzes and evaluates the financial ciphertext data through the smart contract in the preset recognition model, determines the credit evaluation result of the enterprise to be evaluated, and stores the generated credit evaluation result in the blockchain node for relevant blockchain members to obtain and view.

[0073] Understandably, the financial data of the enterprise to be evaluated will be updated over time, so that the credit evaluation results of the enterprise to be evaluated will change. In order to reflect the changes in the credit evaluation results, the financial enterprise credit evaluation system of this embodiment also includes:

[0074] The data updating module a1 is used to collect the enterprise financial data updated by the enterprise to be evaluated within the preset period at intervals of a preset period, so as to update the credit evaluation result based on the updated enterprise financial data.

[0075] Furthermore, a preset period is set in advance based on the average update period of the financial data of financial enterprises. Every time the preset period is reached, the enterprise financial data updated by the enterprise to be evaluated within the preset period is collected through the data update module. The collection method also includes crawling through public channels and obtaining from the enterprise to be evaluated, and combining the two for verification to obtain the enterprise financial data finally updated in the preset period. Then, the updated enterprise financial data is encrypted and transmitted to the blockchain node, and the updated and encrypted enterprise financial data and the original financial ciphertext data are analyzed and evaluated according to the smart contract in the preset evaluation model, and the updated credit evaluation results are obtained and stored in the blockchain node.

[0076] In addition, considering the timeliness of the original financial ciphertext data, a chronological elimination mechanism can be set up. That is, while obtaining updated corporate financial data at each preset period, the corporate financial data generated within the earliest preset period in the original corporate financial data is eliminated. Then, the eliminated corporate financial data and the updated corporate financial data are combined and encrypted to obtain updated financial ciphertext data, which is transmitted to the blockchain node, analyzed and evaluated by the preset evaluation model, and the new credit evaluation results of the enterprise to be evaluated are obtained and stored in the blockchain node. In this way, the credit evaluation results are more correlated with the latest corporate financial data of the enterprise to be evaluated, and the evaluation is more accurate.

[0077] The financial enterprise credit evaluation system based on blockchain implemented in this embodiment includes a data collection module, a data chain module and a data evaluation module; wherein the data collection module is used to collect the enterprise financial data of the enterprise to be evaluated, and the collected enterprise financial data at least includes public financial statements, bank flow data and supply chain cooperation information; the data chain module is used to encrypt the collected enterprise financial data, obtain financial ciphertext data, and transmit the financial ciphertext data to the block node; the data evaluation module is used to analyze and evaluate the financial ciphertext data based on the smart contract in the preset evaluation model, and obtain the credit evaluation results of the enterprise to be evaluated and store them in the blockchain node. In this way, various financial data related to financial enterprises are collected with the help of crawler technology, making the collected data more efficient and comprehensive. At the same time, by encrypting various financial data and transmitting them to the blockchain node, the preset evaluation model analyzes and evaluates them according to the smart contract, and obtains the credit evaluation results of the enterprise to be evaluated and stores them in the blockchain node. The security of various financial data and evaluation results is ensured by the immutability of the blockchain, and the preset evaluation model formed by a large number of financial data samples is analyzed and evaluated, so that the generated evaluation results are more accurate, and accurate, efficient and safe credit evaluation of financial enterprises is achieved.

[0078] For further information, please refer to Figure 2 Based on the first embodiment of the financial enterprise credit evaluation system based on blockchain of the present invention, a second embodiment of the financial enterprise credit evaluation system based on blockchain of the present invention is proposed.

[0079] The difference between the second embodiment of the financial enterprise credit assessment system based on blockchain and the first embodiment of the financial enterprise credit assessment system based on blockchain is that the financial enterprise credit assessment system based on blockchain further includes:

[0080] The sample processing module 40 is used to obtain financial sample data and process the financial sample data according to the preset risk characteristics to obtain multiple groups of risk characteristic samples corresponding to the preset risk characteristics;

[0081] A model training module 50 is used to train an initial risk model based on multiple groups of risk feature samples, and obtain a risk score value calculated by the initial risk model for each group of risk feature samples;

[0082] The calibration module 60 is used to calibrate the initial risk model according to the score difference between the reference score value corresponding to each group of risk feature samples and the risk score value, so as to generate the initial risk model as a preset evaluation model based on the calibration of the initial risk model.

[0083] Further, the preset evaluation model is formed by training a large number of financial sample data of financial enterprises in advance. Specifically, the system is also provided with a sample processing module, a model training module and a calibration module. The sample processing module obtains the financial sample data of a large number of financial enterprises, and processes the financial sample data according to the preset risk characteristics, and obtains multiple groups of risk feature samples corresponding to each of the preset risk characteristics. Among them, the preset risk characteristics are characteristic events and corresponding characteristic factors indicating that the financial enterprise may have risks. For example, bankruptcy risk events and their corresponding characteristic factors such as assets and debts, and liquidity risk events and their corresponding characteristic factors such as funds and debts. Different characteristic events are reflected by different characteristic factors. Through the preset risk characteristics, the financial sample data are grouped, and the data of the characteristic factors belonging to the same characteristic event are divided into the same group class, and then according to the way in which each characteristic factor reflects the characteristic event, the data of the same group class is analyzed and processed to obtain the risk sample characteristics. For example, for bankruptcy risk events, the ratio between the total debt and the total assets can be used as one of the reflection methods, and the data corresponding to the total debt and the data corresponding to the total assets are processed by ratio, and the ratio result is obtained as a risk feature sample of the bankruptcy risk event.

[0084] Furthermore, after obtaining the risk feature samples corresponding to each preset risk feature, the model training module in the system can train the initial risk model through the risk feature samples. It should be noted that a preset risk feature often corresponds to a group of risk feature samples, and a group of risk feature samples contains multiple risk feature values ​​to reflect risk events from multiple aspects. The initial risk model combines the risk feature values ​​contained in each group of risk feature samples to calculate the risk score value of each group of risk feature samples. The calculation formula can be seen in the following formula (1).

[0085] Si = = ln(Pi / (1-Pi)) (1);

[0086] Among them, Si represents the risk score value corresponding to the i-th group of risk feature samples, and Pi represents the probability value predicted by the initial risk model that the i-th group of risk feature samples has risk.

[0087] Further, in order to reflect the accuracy of the initial risk model in calculating the risk score value, the calibration module in the system performs a difference operation between the reference score value corresponding to each group of risk feature samples and the calculated risk score value, and generates a score difference corresponding to each group of risk feature samples. Then, the score difference is compared with the preset threshold value to determine whether the score difference is greater than the preset threshold value. If it is greater, it means that the difference between the reference score value and the risk score value is large, and the accuracy of the risk score value calculated by the preset initial risk model is low, so as to calibrate the initial risk model. Through calibration, the parameters of the initial risk model predicting the probability of risk of the risk feature sample are adjusted, so that the predicted probability value is more accurate, so that the risk score value obtained by the probability value calculation is more accurate. When the accuracy reaches the point where the score difference is not greater than the preset threshold, the initial risk model is generated as a preset evaluation model, and the initial risk model is generated as a preset evaluation model according to the calibration of the initial risk model. On the contrary, if it can be directly determined by comparison that the score difference is not greater than the preset threshold, it means that the difference between the reference score value and the risk score value is not large, and the accuracy of the risk score value calculated by the preset initial risk model is high. At this time, the initial risk model is generated as a preset evaluation model.

[0088] Furthermore, the preset evaluation model generated through training can evaluate the bankruptcy risk of financial enterprises. Specifically, the data evaluation module includes:

[0089] A screening unit 31 is used to screen out current asset value, current liability value, total asset value, retained earnings value, earnings before interest and taxes value, stock market value, total number of stocks, total liabilities value and sales from the financial ciphertext data based on the smart contract in the preset evaluation model;

[0090] a calculation unit 32, configured to calculate a first parameter according to the current asset value, the current liability value and the total asset value, calculate a second parameter according to the retained earnings value and the total asset value, calculate a third parameter according to the EBIT value and the total asset value, calculate a fourth parameter according to the stock market value, the total number of stocks and the total liabilities value, and calculate a fifth parameter according to the sales and the total asset value;

[0091] The evaluation unit 33 is used to analyze and evaluate the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter based on a preset evaluation model, calculate the bankruptcy risk coefficient, and generate the evaluation result based on the bankruptcy risk coefficient.

[0092] Furthermore, characteristic factors corresponding to the bankruptcy risk of financial enterprises are pre-set, and such characteristic factors at least include current asset value, current liability value, total asset value, retained earnings value, earnings before interest and tax value, stock market value, total number of stocks, total liabilities value and sales. For the enterprise to be evaluated, such characteristic factors are set in the smart contract of the preset evaluation model, and the screening unit in the data evaluation module screens the financial ciphertext data according to such smart contracts, and screens out the current asset value, current liability value, total asset value, retained earnings value, earnings before interest and tax value, stock market value, total number of stocks, total liabilities value and sales.

[0093] Furthermore, the calculation unit in the data evaluation module calculates the first parameter according to the current asset value, the current liability value and the total asset value, and the calculation method is to perform a difference operation on the current asset value and the current liability value, and the obtained calculation result is compared with the total asset value, and the obtained calculation result is the first parameter. In addition, the calculation unit also calculates the second parameter according to the retained earnings value and the total asset value, and the calculation method is to perform a ratio operation on the retained earnings value and the total asset value, and the calculation result is obtained as the second parameter. At the same time, the calculation unit also calculates the third parameter according to the EBIT value and the total asset value, and the calculation method is to perform a ratio operation on the EBIT value and the total asset value, and the calculation result is obtained as the third parameter. And, the calculation unit also calculates the fourth parameter according to the stock market value, the total number of stocks and the total liabilities value, and the calculation method is to perform a product operation on the stock market value and the total number of stocks, and the obtained calculation result is compared with the total liabilities value, and the calculation result is obtained as the fourth parameter. And, the calculation unit calculates the fifth parameter according to the sales and total assets value, and the calculation method is to perform a ratio operation between the sales and the total assets value, and the calculation result is obtained as the fifth parameter.

[0094] Furthermore, the evaluation unit in the data evaluation module analyzes and evaluates the calculated first parameter, second parameter, third parameter, fourth parameter and fifth parameter according to a preset evaluation model, and calculates the bankruptcy risk coefficient. The calculation formula can be seen in the following formula (2).

[0095] Z=k1*X1+k2*X2+k3*X3+k4*X4+k5*X5 (2);

[0096] Among them, Z represents the bankruptcy coefficient, K1, K2, K3, K4, K5 represent the reference coefficients of the preset evaluation model, for example, they are set to 1.2, 1.4, 3.3, 0.6, 0.999, or other parameters formed through training; X1, X2, X3, X4, X5 represent the first parameter, second parameter, third parameter, fourth parameter and fifth parameter obtained by calculation. After the bankruptcy risk coefficient is obtained by calculation, it can be generated as an evaluation result together with the risk coefficients of the enterprise to be evaluated in other aspects, reflecting the credit risk situation of the enterprise to be evaluated in various aspects.

[0097] This embodiment forms a preset evaluation model by training financial sample data of a large number of financial enterprises, so that the preset evaluation model can be used to accurately evaluate and analyze the financial ciphertext data, thereby improving the accuracy of the credit evaluation of the enterprise to be evaluated.

[0098] In addition, the present invention provides a financial enterprise credit assessment method based on blockchain, please refer to Figure 3 , Figure 3 This is a flowchart of the first embodiment of the financial enterprise credit assessment method based on blockchain of the present invention. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.

[0099] Specifically, the blockchain-based financial enterprise credit assessment method in this embodiment includes:

[0100] Step S10, collecting the enterprise financial data of the enterprise to be evaluated, wherein the enterprise financial data at least includes public financial statements, bank flow data and supply chain cooperation information;

[0101] Furthermore, when a financial enterprise needs to undergo a credit assessment, it initiates an assessment request to the blockchain-based financial enterprise credit assessment system of this embodiment. After receiving the assessment request, the system reads the enterprise ID (Identification) carried therein, determines the specific financial enterprise that needs to undergo a credit assessment by the enterprise ID, and uses the financial enterprise that needs to undergo a credit assessment as the enterprise to be assessed.

[0102] Furthermore, the financial enterprise credit assessment system based on blockchain initiates a credit assessment of the enterprise to be assessed, and collects various public information related to the enterprise to be assessed from various official websites, news websites, social platforms and other channels by calling API (Application Programming Interface), web crawlers and other technologies. At the same time, a prompt message is sent to the enterprise to be assessed, prompting the enterprise to be assessed to upload the enterprise financial data. The enterprise to be assessed uploads the corresponding enterprise financial data according to the type of financial data contained in the prompt message, and the uploaded enterprise financial data type at least includes public financial statements, bank flow data and supply chain cooperation information. The financial enterprise credit assessment system based on blockchain combines the collected public information with the received enterprise financial data to verify the various enterprise financial data. If the public information is consistent with the enterprise financial data, the enterprise financial data is marked as accurate, and if the public information is inconsistent with the enterprise financial data, the enterprise financial data is marked as pending. Then feedback information is sent to the enterprise to be assessed, and the enterprise to be assessed sends explanation information to the system based on the feedback information to explain the inconsistency. The system evaluates the rationality of the explanation information, and if the evaluation passes, the corresponding enterprise financial data is marked as accurate. If the assessment fails, the corresponding corporate financial data will be removed to ensure the accuracy of the corporate financial data. After all corporate financial data are verified, the final corporate financial data used for credit assessment of the assessed enterprise is generated.

[0103] Step S20, encrypting the enterprise financial data to obtain financial ciphertext data, and transmitting the financial ciphertext data to the blockchain node;

[0104] Furthermore, in order to ensure the security of the enterprise financial data, the enterprise financial data is encrypted to obtain the corresponding financial ciphertext data and transmit it to the blockchain node. The encryption can adopt any one of the hash encryption algorithm, asymmetric encryption algorithm, elliptic curve encryption algorithm and digital signature encryption algorithm. This embodiment preferably adopts an asymmetric encryption algorithm. Specifically, the step of encrypting the enterprise financial data to obtain the financial ciphertext data includes:

[0105] Step S21, dividing the enterprise financial data into blocks to obtain multiple data blocks, and determining whether the last data block obtained through division has a preset data length;

[0106] Step S22, when the last data block does not have a preset data length, padding the last data block based on preset padding data to obtain a padding data block;

[0107] Step S23, generating a public key and a private key based on a preset algorithm, and encrypting the padding data block and other data blocks among the multiple data blocks except the padding data block based on the public key, respectively, to obtain multiple ciphertext data, and jointly generating the multiple ciphertext data and the private key into the financial ciphertext data.

[0108] Furthermore, for the security of enterprise financial data encryption, the enterprise financial data is divided into blocks and divided into data blocks with the same data format and fixed data size. The data format and data size can be preset. Among the multiple data blocks obtained by division, the data size of the last divided data block may not be a fixed data size. The fixed data size corresponds to a fixed data length, and the data length is used as the preset data length. After the block module divides and obtains multiple databases, it determines the data length of the last data block obtained by division, compares its data length with the preset data length, and determines whether the last data block obtained by division has the preset data length through comparison. If the comparison determines that the data length is consistent with the preset data length, it is determined that the last data block has the preset data length. On the contrary, if it is inconsistent, it is determined that it does not have the preset data length.

[0109] Furthermore, if the last data block is determined not to have a preset data length, the last data block is padded according to the preset padding data. The preset padding data is pre-set meaningless data, such as 1000..., or 0111..., etc. After being padded, the last data block has a preset data length, and it is used as a padding data block. Then, a public key and a private key are generated by a preset algorithm, and the preset algorithm can be an RSA encryption algorithm. According to the generated public key, the padding data block and the other data blocks except the padding data block, that is, the last data block, in the multiple data blocks initially divided are encrypted respectively to obtain the corresponding ciphertext data. Then, each ciphertext data and private key are jointly generated as the amount ciphertext data and transmitted to the blockchain node for the blockchain members to obtain and view. Among them, the blockchain members are different according to the type of blockchain. For the public chain, its members are all people, for the alliance chain, the members are limited to members within the alliance, and for the private chain, its members are limited to company members.

[0110] Step S30, analyzing and evaluating the financial ciphertext data based on the smart contract in the preset evaluation model, obtaining the credit evaluation result of the enterprise to be evaluated and storing it in the blockchain node.

[0111] Furthermore, a preset evaluation model is pre-formed through training in the system. The financial ciphertext data is analyzed and evaluated through the smart contract in the preset recognition model to determine the credit evaluation result of the enterprise to be evaluated, and the generated credit evaluation result is stored in the blockchain node for relevant blockchain members to obtain and view.

[0112] Understandably, the financial data of the enterprise to be evaluated will be updated over time, so that the credit evaluation results of the enterprise to be evaluated will change. In order to reflect the changes in the credit evaluation results, after the step of transmitting the credit evaluation results to the blockchain node for storage, the embodiment also includes:

[0113] Step b1: collecting the enterprise financial data updated by the enterprise to be evaluated within the preset period at intervals of a preset period, so as to update the credit evaluation result based on the updated enterprise financial data.

[0114] Furthermore, a preset period is set in advance based on the average update period of the financial data of financial enterprises. Every time the preset period is reached, the enterprise financial data updated by the enterprise to be evaluated within the preset period is collected. The collection method also includes crawling through public channels and obtaining from the enterprise to be evaluated, and combining the two for verification to obtain the enterprise financial data that is finally updated in the preset period. Then, the updated enterprise financial data is encrypted and transmitted to the blockchain node, and the updated and encrypted enterprise financial data and the original financial ciphertext data are analyzed and evaluated based on the smart contract in the preset evaluation model, and the updated credit evaluation results are obtained and stored in the blockchain node.

[0115] In addition, considering the timeliness of the original financial ciphertext data, a chronological elimination mechanism can be set up. That is, while obtaining updated corporate financial data at each preset period, the corporate financial data generated within the earliest preset period in the original corporate financial data is eliminated. Then, the eliminated corporate financial data and the updated corporate financial data are combined and encrypted to obtain updated financial ciphertext data, which is transmitted to the blockchain node, analyzed and evaluated by the preset evaluation model, and the new credit evaluation results of the enterprise to be evaluated are obtained and stored in the blockchain node. In this way, the credit evaluation results are more correlated with the latest corporate financial data of the enterprise to be evaluated, and the evaluation is more accurate.

[0116] The implementation of the blockchain-based financial enterprise credit assessment method first collects the enterprise financial data of the enterprise to be assessed, and the collected enterprise financial data at least includes public financial statements, bank flow data and supply chain cooperation information; then encrypts the collected enterprise financial data to obtain financial ciphertext data, and transmits the financial ciphertext data to the block node; then analyzes and evaluates the financial ciphertext data based on the smart contract in the preset assessment model, and obtains the credit assessment results of the enterprise to be assessed and stores them in the blockchain node. In this way, various financial data related to financial enterprises are collected with the help of crawler technology, making the collected data more efficient and comprehensive. At the same time, by encrypting various financial data and transmitting them to the blockchain node, the preset assessment model analyzes and evaluates them according to the smart contract, and obtains the credit assessment results of the enterprise to be assessed and stores them in the blockchain node. The immutability of the blockchain ensures the security of various financial data and assessment results, and the preset assessment model formed by a large number of financial data samples is used for analysis and evaluation, so that the generated assessment results are more accurate, and accurate, efficient and safe credit assessment of financial enterprises is achieved.

[0117] For further information, please refer to Figure 4 Based on the first embodiment of the financial enterprise credit assessment method based on blockchain of the present invention, a second embodiment of the financial enterprise credit assessment method based on blockchain of the present invention is proposed.

[0118] The difference between the second embodiment of the financial enterprise credit assessment method based on blockchain and the first embodiment of the financial enterprise credit assessment method based on blockchain is that the step of performing credit assessment on the enterprise to be assessed based on the smart contract in the preset assessment model includes:

[0119] Step S40, acquiring financial sample data, and processing the financial sample data according to preset risk characteristics to obtain multiple groups of risk characteristic samples corresponding to the preset risk characteristics;

[0120] Step S50, training the initial risk model based on the multiple groups of risk feature samples, and obtaining the risk score value calculated by the initial risk model for each group of risk feature samples;

[0121] Step S60, calibrating the initial risk model according to the score difference between the reference score value corresponding to each group of risk feature samples and the risk score value, so as to generate the initial risk model as a preset assessment model based on the calibration of the initial risk model.

[0122] Furthermore, the preset assessment model is formed by training a large number of financial sample data of financial enterprises in advance. Specifically, the financial sample data of a large number of financial enterprises are obtained, and the financial sample data are processed according to the preset risk characteristics, and multiple groups of risk feature samples corresponding to each of the preset risk characteristics are obtained. Among them, the preset risk characteristics are characteristic events and corresponding characteristic factors indicating that the financial enterprise may have risks. For example, bankruptcy risk events and their corresponding characteristic factors such as assets and debts, and liquidity risk events and their corresponding characteristic factors such as funds and debts. Different characteristic events are reflected by different characteristic factors. Through the preset risk characteristics, the financial sample data are grouped, and the data of the characteristic factors belonging to the same characteristic event are divided into the same group class, and then according to the way each characteristic factor reflects the characteristic event, the data of the same group class is analyzed and processed to obtain the risk sample characteristics. For example, for bankruptcy risk events, the ratio between the total debt and the total assets can be used as one of the reflection methods, and the data corresponding to the total debt and the data corresponding to the total assets are processed by ratio, and the ratio result is obtained as a risk feature sample of the bankruptcy risk event.

[0123] Furthermore, after obtaining the risk feature samples corresponding to each preset risk feature, the initial risk model can be trained through the risk feature samples. It should be noted that a preset risk feature often corresponds to a group of risk feature samples, and a group of risk feature samples contains multiple risk feature values ​​to reflect risk events from multiple aspects. The initial risk model combines the risk feature values ​​contained in each group of risk feature samples to calculate the risk score value of each group of risk feature samples. The calculation formula can be seen in the following formula (1).

[0124] Si = = ln(Pi / (1-Pi)) (1);

[0125] Among them, Si represents the risk score value corresponding to the i-th group of risk feature samples, and Pi represents the probability value predicted by the initial risk model that the i-th group of risk feature samples has risk.

[0126] Furthermore, in order to reflect the accuracy of the initial risk model in calculating the risk score value, the reference score value corresponding to each group of risk feature samples is subjected to a difference operation with the calculated risk score value to generate a score difference corresponding to each group of risk feature samples. Then, the score difference is compared with a preset threshold to determine whether the score difference is greater than the preset threshold. If it is greater, it means that the difference between the reference score value and the risk score value is large, and the accuracy of the risk score value calculated by the preset initial risk model is low, thereby calibrating the initial risk model. The parameters of the initial risk model predicting the probability of risk of the risk feature sample are adjusted by calibration, so that the predicted probability value is more accurate, thereby making the risk score value obtained by the probability value calculation more accurate. When the accuracy reaches the point where the score difference is not greater than the preset threshold, the initial risk model is generated as a preset evaluation model, and the initial risk model is generated as a preset evaluation model based on the calibration of the initial risk model. On the contrary, if it can be directly determined by comparison that the score difference is not greater than the preset threshold, it means that the difference between the reference score value and the risk score value is not large, and the accuracy of the risk score value calculated by the preset initial risk model is high. At this time, the initial risk model is generated as a preset evaluation model.

[0127] Furthermore, the preset evaluation model generated by training can evaluate the bankruptcy risk of financial enterprises. Specifically, the steps of analyzing and evaluating the financial ciphertext data based on the smart contract in the preset evaluation model to obtain the credit evaluation result of the enterprise to be evaluated include:

[0128] Step S31, based on the smart contract in the preset evaluation model, filter out the current asset value, current liability value, total asset value, retained earnings value, earnings before interest and taxes value, stock market value, total number of stocks, total liabilities value and sales from the financial ciphertext data;

[0129] Step S32, calculating a first parameter according to the current asset value, the current liability value and the total asset value, calculating a second parameter according to the retained earnings value and the total asset value, calculating a third parameter according to the EBIT value and the total asset value, calculating a fourth parameter according to the stock market value, the total number of stocks and the total liabilities value, and calculating a fifth parameter according to the sales and the total asset value;

[0130] Step S33, analyzing and evaluating the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter based on a preset evaluation model, calculating the bankruptcy risk coefficient, and generating the evaluation result based on the bankruptcy risk coefficient.

[0131] Furthermore, characteristic factors corresponding to the bankruptcy risk of financial enterprises are pre-set, and such characteristic factors at least include current asset value, current liability value, total asset value, retained earnings value, earnings before interest and tax value, stock market value, total number of stocks, total liabilities value and sales. For the enterprise to be evaluated, such characteristic factors are set in the smart contract of the preset evaluation model, and the financial ciphertext data is screened according to such smart contract, and the current asset value, current liability value, total asset value, retained earnings value, earnings before interest and tax value, stock market value, total number of stocks, total liabilities value and sales are screened out.

[0132] Furthermore, the first parameter is calculated according to the current asset value, the current liability value and the total asset value, and the calculation method is to perform a difference operation on the current asset value and the current liability value, and the obtained calculation result is compared with the total asset value, and the obtained calculation result is the first parameter. In addition, the calculation unit also calculates the second parameter according to the retained earnings value and the total asset value, and the calculation method is to perform a ratio operation on the retained earnings value and the total asset value, and the calculation result is obtained as the second parameter. At the same time, the calculation unit also calculates the third parameter according to the EBIT value and the total asset value, and the calculation method is to perform a ratio operation on the EBIT value and the total asset value, and the calculation result is obtained as the third parameter. And, the calculation unit also calculates the fourth parameter according to the stock market value, the total number of stocks and the total liabilities value, and the calculation method is to perform a product operation on the stock market value and the total number of stocks, and the obtained calculation result is compared with the total liabilities value, and the calculation result is obtained as the fourth parameter. And, the calculation unit calculates the fifth parameter according to the sales and total assets value, and the calculation method is to perform a ratio operation between the sales and the total assets value, and the calculation result is obtained as the fifth parameter.

[0133] Furthermore, the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter calculated are analyzed and evaluated according to the preset evaluation model to calculate the bankruptcy risk coefficient. The calculation formula can be seen in the following formula (2).

[0134] Z=k1*X1+k2*X2+k3*X3+k4*X4+k5*X5 (2);

[0135] Among them, Z represents the bankruptcy coefficient, K1, K2, K3, K4, K5 represent the reference coefficients of the preset evaluation model, for example, they are set to 1.2, 1.4, 3.3, 0.6, 0.999, or other parameters formed through training; X1, X2, X3, X4, X5 represent the first parameter, second parameter, third parameter, fourth parameter and fifth parameter obtained by calculation. After the bankruptcy risk coefficient is obtained by calculation, it can be generated as an evaluation result together with the risk coefficients of the enterprise to be evaluated in other aspects, reflecting the credit risk situation of the enterprise to be evaluated in various aspects.

[0136] This embodiment forms a preset evaluation model by training financial sample data of a large number of financial enterprises, so that the preset evaluation model can be used to accurately evaluate and analyze the financial ciphertext data, thereby improving the accuracy of the credit evaluation of the enterprise to be evaluated.

[0137] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims. All equivalent structures or equivalent process changes made using the contents of the specification and drawings of the present invention, or directly or indirectly used in other related technical fields, are protected by the present invention.

Claims

1. A financial enterprise credit assessment system based on blockchain, characterized in that: It includes data acquisition module, data uploading module and data evaluation module; among them, The data collection module is used to collect corporate financial data of the enterprise to be evaluated, and the corporate financial data at least includes public financial statements, bank flow data and supply chain cooperation information; The data on-chain module is used to encrypt the enterprise financial data, obtain financial ciphertext data, and transmit the financial ciphertext data to the blockchain node; The data evaluation module is used to analyze and evaluate the financial ciphertext data based on the smart contract in the preset evaluation model, and obtain the credit evaluation result of the enterprise to be evaluated and store it in the blockchain node.

2. The financial enterprise credit evaluation system according to claim 1, characterized in that: The data evaluation module includes: A screening unit, configured to screen out current asset value, current liability value, total asset value, retained earnings value, earnings before interest and taxes value, stock market value, total number of stocks, total liabilities value and sales from the financial ciphertext data based on the smart contract in the preset evaluation model; a calculation unit, configured to calculate a first parameter according to the current asset value, the current liability value and the total asset value, calculate a second parameter according to the retained earnings value and the total asset value, calculate a third parameter according to the EBIT value and the total asset value, calculate a fourth parameter according to the stock market value, the total number of stocks and the total liability value, and calculate a fifth parameter according to the sales and the total asset value; An evaluation unit, configured to analyze and evaluate the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter based on a preset evaluation model, calculate a bankruptcy risk coefficient, and generate the evaluation result based on the bankruptcy risk coefficient; The calculation formula of the bankruptcy risk coefficient is: Z=k1*X1+k2*X2+k3*X3+k4*X4+k5*X5; Among them, Z represents the bankruptcy risk coefficient, K1, K2, K3, K4, K5 represent the reference coefficients of the preset evaluation model respectively, and X1, X2, X3, X4, X5 represent the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter respectively.

3. The financial enterprise credit evaluation system according to claim 1, characterized in that: The financial enterprise credit evaluation system also includes: A sample processing module, used to obtain financial sample data, and process the financial sample data according to preset risk characteristics to obtain multiple groups of risk characteristic samples corresponding to each of the preset risk characteristics; The model training module is used to train the initial risk model based on multiple groups of risk feature samples, and obtain the risk score value calculated by the initial risk model for each group of risk feature samples. The calculation formula of the risk score value is: Si==ln(Pi / (1-Pi)); Among them, Si represents the risk score value corresponding to the risk characteristic sample of the i-th group, and Pi represents the probability value predicted by the initial risk model that the risk characteristic sample of the i-th group exists at risk; A calibration module is used to calibrate the initial risk model according to the score difference between the reference score value corresponding to each group of risk feature samples and the risk score value, so as to generate the initial risk model as a preset evaluation model based on the calibration of the initial risk model.

4. The financial enterprise credit evaluation system according to any one of claims 1 to 3, characterized in that: The data uplink module also includes: A block division unit, used for dividing the enterprise financial data into blocks to obtain a plurality of data blocks, and determining whether the last data block obtained through division has a preset data length; A padding unit, used for padding the last data block based on preset padding data to obtain a padding data block when the last data block does not have a preset data length; An encryption unit is used to generate a public key and a private key based on a preset algorithm, and to encrypt the padding data block and other data blocks among the multiple data blocks except the padding data block based on the public key to obtain multiple ciphertext data, and to jointly generate the multiple ciphertext data and the private key into the financial ciphertext data.

5. The financial enterprise credit evaluation system according to any one of claims 1 to 3, characterized in that: The financial enterprise credit evaluation system also includes: The data updating module is used to collect the enterprise financial data updated by the enterprise to be evaluated within the preset period at intervals of the preset period, so as to update the credit evaluation result based on the updated enterprise financial data.

6. A blockchain-based financial enterprise credit assessment method, characterized in that: The financial enterprise credit assessment method comprises: Collecting corporate financial data of the enterprise to be evaluated, the corporate financial data at least includes public financial statements, bank flow data and supply chain cooperation information; Encrypting the enterprise financial data to obtain financial ciphertext data, and transmitting the financial ciphertext data to the blockchain node; The financial ciphertext data is analyzed and evaluated based on the smart contract in the preset evaluation model to obtain the credit evaluation result of the enterprise to be evaluated, and the credit evaluation result is stored in the blockchain node.

7. The financial enterprise credit assessment method according to claim 1, characterized in that: The step of analyzing and evaluating the financial ciphertext data based on the smart contract in the preset evaluation model to obtain the credit evaluation result of the enterprise to be evaluated includes: Based on the smart contract in the preset evaluation model, the current asset value, current liability value, total asset value, retained earnings value, earnings before interest and taxes value, stock market value, total number of stocks, total liabilities value and sales are screened out from the financial ciphertext data; Calculating a first parameter based on the current asset value, current liability value and total asset value, calculating a second parameter based on the retained earnings value and total asset value, calculating a third parameter based on the EBIT value and total asset value, calculating a fourth parameter based on the stock market value, total number of stocks and total liabilities value, and calculating a fifth parameter based on sales and total asset value; Analyzing and evaluating the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter based on a preset evaluation model, calculating a bankruptcy risk coefficient, and generating the evaluation result based on the bankruptcy risk coefficient; The calculation formula of the bankruptcy risk coefficient is: Z=k1*X1+k2*X2+k3*X3+k4*X4+k5*X5; Among them, Z represents the bankruptcy risk coefficient, K1, K2, K3, K4, K5 represent the reference coefficients of the preset evaluation model respectively, and X1, X2, X3, X4, X5 represent the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter respectively.

8. The financial enterprise credit assessment method according to claim 1, characterized in that: The step of performing credit assessment on the enterprise to be assessed based on the smart contract in the preset assessment model includes: Obtain financial sample data, and process the financial sample data according to preset risk characteristics to obtain multiple groups of risk characteristic samples corresponding to each of the preset risk characteristics; (processing as events) The initial risk model is trained based on multiple groups of risk feature samples, and the risk score value calculated by the initial risk model for each group of risk feature samples is obtained. The calculation formula of the risk score value is: Si==ln(Pi / (1-Pi)); Among them, Si represents the risk score value corresponding to the risk characteristic sample of the i-th group, and Pi represents the probability value predicted by the initial risk model that the risk characteristic sample of the i-th group exists at risk; The initial risk model is calibrated according to the score difference between the reference score value corresponding to each group of risk feature samples and the risk score value, so as to generate the initial risk model as a preset assessment model based on the calibration of the initial risk model.

9. The financial enterprise credit assessment method according to any one of claims 6 to 8, characterized in that: The step of encrypting the enterprise financial data to obtain financial ciphertext data comprises: Divide the enterprise financial data into blocks to obtain a plurality of data blocks, and determine whether the last data block obtained through the division has a preset data length; When the last data block does not have a preset data length, padding the last data block based on preset padding data to obtain a padding data block; A public key and a private key are generated based on a preset algorithm, and the padding data block and other data blocks among the multiple data blocks except the padding data block are encrypted respectively based on the public key to obtain multiple ciphertext data, and the multiple ciphertext data and the private key are jointly generated into the financial ciphertext data.

10. The financial enterprise credit assessment method according to any one of claims 6 to 8, characterized in that: After the step of transmitting the credit assessment result to the blockchain node for storage, the following step is further included: At every preset period, the enterprise financial data of the enterprise to be evaluated updated within the preset period is collected, and the credit evaluation result is updated based on the updated enterprise financial data.

Images