A financial asset evaluation method and system based on big data

Abstract

The present invention discloses a financial asset evaluation method and system based on big data, which specifically relates to the financial field, including a data collection timing planning step, a financial data collection step, a financial data analysis step, a financial asset evaluation step, and a risk judgment step. The present invention realizes a comprehensive and accurate evaluation of financial asset risks through systematic data collection, multi-dimensional data analysis, and comprehensive evaluation. The beneficial effect is that the timeliness and accuracy of the evaluation are improved, and a scientific decision-making basis is provided for enterprises and investors, which helps to reduce investment risks and increase asset value. At the same time, the regular evaluation function of the system can timely discover risk changes and support the continuous improvement and risk management of enterprises.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and more specifically, to a financial asset evaluation method and system based on big data. Background Art

[0002] With the rapid development of big data technology, the accuracy and efficiency of financial asset valuation have become the focus of industry attention. As an important part of the financial market, financial asset valuation is of great significance to corporate risk management, investment decisions and the healthy development of the capital market.

[0003] Existing technologies usually follow a set of established operating procedures when conducting financial asset valuation. This process includes steps such as data collection, preliminary analysis, risk assessment, and result reporting. The data collection stage mainly relies on traditional data sources such as financial statements and market data; preliminary analysis focuses on simple processing and interpretation of data; risk assessment makes a preliminary judgment on the potential risks of financial assets based on these analysis results; finally, the evaluation results are presented to companies and investors in the form of a report.

[0004] However, there are still some shortcomings in its actual use. First, the data sources relied on by existing technologies are relatively limited, and it is difficult to fully reflect the actual situation of financial assets; second, the analysis method is relatively single, and lacks a multi-dimensional and in-depth evaluation mechanism; finally, the accuracy and timeliness of the evaluation results need to be improved, and it is difficult to meet the rapidly changing needs of the financial market. Therefore, a more advanced and comprehensive financial asset evaluation method and system is urgently needed to overcome these shortcomings. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a financial asset evaluation method and system based on big data, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above purpose, the present invention provides the following technical solution: a financial asset evaluation method based on big data, the specific steps include:

[0007] S1: Data collection timing planning: used to plan the timing of financial data collection of the target enterprise, arrange the data collection moments according to the same preset time intervals, and number these moments sequentially;

[0008] S2: Financial data collection: used to collect the target company's amount data and transmit it to S3;

[0009] S3: Financial data analysis: used to analyze the data transmitted by S2 and transmit the analysis results to S4;

[0010] S4: Financial asset evaluation: used to conduct a comprehensive evaluation of the data transmitted by S3, calculate the comprehensive risk assessment value of the target enterprise, and transmit it to S5;

[0011] S5: Risk judgment: used to determine the risk status of the target enterprise’s financial assets based on the comprehensive risk assessment value transmitted by S4.

[0012] Preferably, S1 sets a financial data collection cycle according to the business characteristics and market environment of the target enterprise, the specific cycle depends on the volatility of the data and the analysis requirements, and then determines the start time and end time of data collection.

[0013] Preferably, S2 is used to collect high-frequency trading behavior and market structure data, credit risk and capital structure optimization data, operational efficiency and technological innovation potential data, and market linkage and macroeconomic data of the target enterprise at each time series.

[0014] Preferably, the high-frequency trading behavior and market structure data include the dynamic slope of the limit order book, the distribution entropy of transaction duration, the cancellation and relisting ratio and the price shock elasticity coefficient, which are marked as Lo, Lt, Lc and Lp respectively; the credit risk and capital structure optimization data include the implied default rate of credit derivatives, the debt maturity structure deviation, the capital structure adjustment cost and the contingent liability reserve adequacy ratio, which are marked as Cd, Cs, Cm and Cl respectively; the operational efficiency and technological innovation potential data include the digital input-output efficiency ratio, the intellectual property asset turnover rate, the customer feedback cycle time and the intelligent system fault recovery time, which are marked as Do, Dp, Dc and Ds respectively; the market linkage and macroeconomic data include the economic cycle synchronization index, the correlation of commodity price fluctuations, the trade flow change rate and the enterprise market share change rate, which are marked as Ge, Gc, Gt and Gm respectively.

[0015] Preferably, the S2 obtains the limit order book data in real time through the high-frequency trading data interface, calculates the rate of change of order volume at different price levels to collect the dynamic slope of the limit order book, records the time from the order placement time to the transaction time of each transaction, and calculates its entropy to collect the entropy of the transaction duration distribution, monitors the order cancellation and re-order behavior of traders, calculates the proportion of re-orders immediately after cancellation, and collects the cancellation and re-order ratio, and executes large transactions, observes changes in market prices, calculates the speed at which prices recover to the pre-transaction level, and collects the price impact elasticity coefficient.

[0016] Preferably, S2 obtains relevant data through the credit derivatives market, uses the market pricing model to reversely deduce the implied default rate to collect the implied default rate of credit derivatives, collects the debt term structure deviation by collecting the company's debt term structure data and actual capital demand cycle data, calculates the deviation, and collects the capital structure adjustment cost by calculating the cost required for capital structure adjustment through corporate announcements, financial reports and market research, and collects the contingent liability reserve adequacy ratio by directly consulting the contingent liabilities and reserve data in the company's financial statements.

[0017] Preferably, S2 collects the enterprise's input data and efficiency improvement data on digital transformation, calculates the input-output ratio to collect the digital input-output efficiency ratio, collects the intellectual property asset turnover rate by counting the commercialization ratio of the enterprise's intellectual property assets through patent database and trademark database, collects the customer feedback cycle time by recording the time from feedback to the enterprise's response and implementation of improvements through the customer feedback system, and collects the intelligent system fault recovery time by recording the time from the occurrence of system failure to restoration of normal through the monitoring log of the intelligent system.

[0018] Preferably, S2 calculates the synchronization index through economic cycle data of different regions and collects the economic cycle synchronization index, obtains price data of major commodities through commodity exchanges, calculates price fluctuation correlation and collects commodity price fluctuation correlation, obtains import and export flow data through international trade statistics database, calculates the change rate and collects the trade flow change rate, calculates the target enterprise's share change rate in the main market and collects the enterprise's market share change rate by collecting the target enterprise's sales data, market share data and competitor data.

[0019] Preferably, S3 includes high-frequency trading behavior and market structure analysis methods, credit risk and capital structure optimization analysis methods, operational efficiency and technological innovation potential assessment methods, and market linkage and macroeconomic risk assessment methods, which are used to establish corresponding mathematical models to analyze the data transmitted by S2.

[0020] Preferably, the high-frequency trading behavior and market structure analysis method is used to establish a high-frequency trading behavior and market structure analysis model, import the high-frequency trading behavior and market structure data transmitted by S2 into the high-frequency trading behavior and market structure analysis model, and calculate the high-frequency trading market dynamic evaluation value of each time series, which is specifically expressed as:

[0021] ,

[0022] ML i represents the dynamic evaluation value of the high-frequency trading market at the i-th time series, Lo i represents the dynamic slope of the limit order book at the i-th time series, Lt irepresents the transaction duration distribution entropy of the i-th time series, Lc i Indicates the cancellation and re-hang ratio of the i-th sequence, Lp i represents the price shock elasticity coefficient of the i-th time series, and n represents the number of time series.

[0023] Preferably, the credit risk and capital structure optimization analysis method is used to establish a credit risk and capital structure optimization analysis model, import the credit risk and capital structure optimization data transmitted by S2 into the credit risk and capital structure optimization analysis model, and calculate the credit risk and capital structure evaluation value of each time series, which is specifically expressed as:

[0024] ,

[0025] MC i represents the credit risk and capital structure assessment value of the i-th time series, Cd i represents the implied default rate of credit derivatives at the i-th time series, Cs i represents the debt maturity structure deviation of the i-th time series, Cm i represents the capital structure adjustment cost at the i-th time series, Cl i It represents the contingent liability reserve ratio at the i-th time series, and n represents the number of time series.

[0026] Preferably, the operation efficiency and technology innovation potential evaluation method is used to establish an operation efficiency and technology innovation potential evaluation model, import the operation efficiency and technology innovation potential data transmitted by S2 into the operation efficiency and technology innovation potential evaluation model, and calculate the operation optimization and technology potential evaluation value of each time series, which is specifically expressed as:

[0027] ,

[0028] MD i represents the operational optimization and technical potential evaluation value of the i-th time series, Do i Denotes the digital input-output efficiency ratio of the i-th time series, Dp i represents the intellectual property asset turnover rate at the i-th time series, Dc i Denotes the customer feedback cycle time of the i-th time sequence, Ds i It represents the intelligent system fault recovery time of the i-th time sequence, and n represents the number of time sequences.

[0029] Preferably, the market linkage and macroeconomic risk assessment method is used to establish a market linkage and macroeconomic risk assessment model, import the market linkage and macroeconomic data transmitted by S2 into the market linkage and macroeconomic risk assessment model, and calculate the macroeconomic and market interaction risk assessment value of each time series, which is specifically expressed as:

[0030] ,

[0031] MG i represents the risk assessment value of macroeconomic and market interaction at the i-th time series, Ge i Gc represents the economic cycle synchronization index of the i-th time series. i Gt represents the correlation of commodity price fluctuations in the i-th time series. i Gm represents the rate of change of trade flow at the i-th time series. i represents the change rate of the enterprise market share in the i-th time series, and n represents the number of time series.

[0032] Preferably, the specific steps of S4 performing comprehensive evaluation on the data transmitted by S3 are:

[0033] A1: Standardization: for ML i , MC i ,MD i and MG i After standardization, we get ML i ′、MC i ′、MD i ' and MG i ′, the standardized formula is:

[0034] ,

[0035] where min(x i ) represents the minimum value of all time series, max(x i ) represents the maximum value among all time series;

[0036] A2: Improved Euclidean distance calculation: Determine the target value as O = (ML0, MC0, MD0, MG0), the weights are W1, W2, W3 and W4, and W1+W2+W3+W4=1, then the improved Euclidean distance D is specifically expressed as:

[0037] ;

[0038] ML0 represents the dynamic target assessment value of the high-frequency trading market, MC0 represents the target assessment value of credit risk and capital structure, MD0 represents the target assessment value of operation optimization and technological potential, and MG0 represents the target assessment value of macroeconomic and market interaction risk;

[0039] A3: Fuzzy logic conversion: Let the comprehensive risk assessment value be R, and R∈[0,1], where 0 represents the lowest risk and 1 represents the highest risk. Define a membership function f(D) to map the distance value D to the risk assessment value R, which can be expressed as follows:

[0040] ,

[0041] max(D) represents the maximum value that the distance value D can take in all possible cases.

[0042] Preferably, the W1, W2, W3, and W4 are obtained by fitting experimental data.

[0043] Preferably, when R ≤ 0.3, it indicates that the financial assets of the target enterprise are in a low-risk state; when 0.3 < R ≤ 0.6, it indicates that the financial assets of the target enterprise are in a medium-risk state; when R > 0.6, it indicates that the financial assets of the target enterprise are in a high-risk state.

[0044] Preferably, a financial asset evaluation system based on big data includes a system operation database, a system central processing module, and a user information terminal, and further includes a data acquisition timing planning module, a financial data acquisition module, a financial data analysis module, a financial asset evaluation module, and a risk judgment module.

[0045] Preferably, the data acquisition timing planning module is used to plan the financial data acquisition timing of the target enterprise, arrange the data acquisition moments at the same preset time interval, and sequentially number these moments;

[0046] The financial data acquisition module is used to acquire the high-frequency trading behavior and market structure data, credit risk and capital structure optimization data, operation efficiency and technological innovation potential data, and market linkage and macroeconomic data of the target enterprise at each timing, and transmit them to the financial data analysis module;

[0047] The financial data analysis module includes a high-frequency trading behavior and market structure analysis unit, a credit risk and capital structure optimization analysis unit, an operation efficiency and technological innovation potential evaluation unit, and a market linkage and macroeconomic risk evaluation unit, and is used to establish corresponding mathematical models to analyze the data transmitted by the financial data acquisition module, and transmit the analysis results to the financial asset evaluation module;

[0048] The financial asset evaluation module is used to comprehensively evaluate the data transmitted by the financial data analysis module, calculate the comprehensive risk evaluation value of the target enterprise, and transmit it to the risk judgment module;

[0049] The risk judgment module is used to determine the financial asset risk state of the target enterprise according to the comprehensive risk evaluation value transmitted by the financial asset evaluation module.

[0050] The technical effects and advantages of the present invention:

[0051] The present invention plans the data collection moments by presetting the same time intervals through the data collection timing planning step, and numbers these moments sequentially, so as to systematically collect the financial data of the target enterprise, which not only ensures the time sequence of the data, but also avoids the deviation caused by inconsistent data collection time, and lays a solid foundation for subsequent analysis; through the financial data collection step, the detailed data of the target enterprise is collected from multiple dimensions, and the collected data is comprehensive and accurate through multiple channels such as real-time interface, market data, financial reports and intelligent system, which provides a rich source of information for subsequent in-depth analysis and evaluation; through the financial data analysis step, the collected data is converted into the core step of valuable information, and the collected data is professionally analyzed by establishing multiple mathematical models of high-frequency trading behavior, credit risk, operational efficiency, technological innovation potential, market linkage and macroeconomics, so as to quantitatively evaluate the target enterprise in different aspects. The performance of the overall situation can provide a scientific basis for comprehensive evaluation; through the financial asset evaluation step, the analysis results of multiple dimensions are integrated to form a comprehensive evaluation of the financial asset risks of the target enterprise. First, the evaluation values ​​of each dimension are standardized to eliminate dimensional differences. Then, the improved Euclidean distance calculation method is used, combined with the weights of each dimension, to calculate the comprehensive risk assessment value. Finally, through fuzzy logic conversion, the distance value is mapped to an intuitive risk assessment value, which is easy for enterprises and investors to understand and apply; through the risk judgment step, according to the comprehensive risk assessment value, the financial asset risk status of the target enterprise is divided into low risk, medium risk or high risk, which provides a clear decision-making basis for enterprises and investors, and helps them to formulate corresponding risk management strategies and investment decisions. At the same time, regular financial asset evaluation can also help enterprises discover risk changes in a timely manner, providing strong support for continuous improvement and risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the structure of the method of the present invention.

[0053] Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] refer to Figure 1 A financial asset evaluation method based on big data is shown, and the specific steps include:

[0056] S1: Data collection timing planning: used to plan the timing of financial data collection of the target enterprise, arrange the data collection moments according to the same preset time intervals, and number these moments sequentially.

[0057] The S1 sets the financial data collection cycle according to the business characteristics and market environment of the target enterprise. The specific cycle depends on the volatility of the data and the analysis requirements, and then determines the start time and end time of data collection.

[0058] It should be specifically explained in this embodiment that the financial data in the first time series specifically represents the initial financial data of the target enterprise and does not involve actual risks.

[0059] S2: Financial data collection: used to collect the target company's monetary data and transmit it to S3.

[0060] The S2 is used to collect the target enterprise's high-frequency trading behavior and market structure data at each time series, credit risk and capital structure optimization data, operational efficiency and technological innovation potential data, and market linkage and macroeconomic data.

[0061] The high-frequency trading behavior and market structure data include the dynamic slope of the limit order book, the distribution entropy of transaction duration, the cancellation and relisting ratio, and the price shock elasticity coefficient, which are marked as Lo, Lt, Lc, and Lp respectively. The credit risk and capital structure optimization data include the implied default rate of credit derivatives, the debt maturity structure deviation, the capital structure adjustment cost, and the contingent liability reserve adequacy ratio, which are marked as Cd, Cs, Cm, and Cl respectively. The operational efficiency and technological innovation potential data include the digital input-output efficiency ratio, the intellectual property asset turnover rate, the customer feedback cycle time, and the intelligent system fault recovery time, which are marked as Do, Dp, Dc, and Ds respectively. The market linkage and macroeconomic data include the economic cycle synchronization index, the correlation between commodity price fluctuations, the trade flow change rate, and the enterprise market share change rate, which are marked as Ge, Gc, Gt, and Gm respectively.

[0062] The S2 obtains the limit order book data in real time through the high-frequency trading data interface, calculates the order volume change rate at different price levels to collect the dynamic slope of the limit order book, records the order placement time to the transaction time of each transaction, and calculates its entropy value to collect the transaction duration distribution entropy, monitors the order cancellation and re-order behavior of traders, calculates the proportion of re-orders immediately after cancellation, and collects the cancellation and re-order ratio, and executes large transactions, observes the changes in market prices, calculates the speed at which prices recover to the pre-transaction level, and collects the price impact elasticity coefficient.

[0063] The S2 obtains relevant data through the credit derivatives market, uses the market pricing model to reversely deduce the implied default rate to collect the implied default rate of credit derivatives, collects the debt term structure deviation by collecting the company's debt term structure data and actual capital demand cycle data, calculates the deviation, and collects the capital structure adjustment cost by calculating the cost required for capital structure adjustment through corporate announcements, financial reports and market research, and collects the contingent liability reserve adequacy ratio by directly consulting the contingent liabilities and reserve data in the company's financial statements.

[0064] The S2 collects the company's investment data and efficiency improvement data on digital transformation, calculates the input-output ratio to collect the digital input-output efficiency ratio, collects the intellectual property asset turnover rate by counting the company's intellectual property asset commercialization ratio through the patent database and trademark database, collects the customer feedback cycle time by recording the time from feedback to the company's response and implementation of improvements through the customer feedback system, and collects the intelligent system failure recovery time by recording the time from system failure to restoration to normal through the intelligent system's monitoring log.

[0065] The S2 calculates the synchronization index through economic cycle data from different regions and collects the economic cycle synchronization index, obtains price data of major commodities through commodity exchanges, calculates price fluctuation correlation and collects commodity price fluctuation correlation, obtains import and export flow data through the international trade statistics database, calculates the change rate and collects the trade flow change rate, and calculates the target enterprise's share change rate in the main market and collects the enterprise's market share change rate by collecting the target enterprise's sales data, market share data and competitor data.

[0066] S3: Financial data analysis: used to analyze the data transmitted by S2 and transmit the analysis results to S4.

[0067] The S3 includes high-frequency trading behavior and market structure analysis methods, credit risk and capital structure optimization analysis methods, operational efficiency and technological innovation potential assessment methods, and market linkage and macroeconomic risk assessment methods, which are used to establish corresponding mathematical models to analyze the data transmitted by S2.

[0068] The high-frequency trading behavior and market structure analysis method is used to establish a high-frequency trading behavior and market structure analysis model, import the high-frequency trading behavior and market structure data transmitted by S2 into the high-frequency trading behavior and market structure analysis model, and calculate the dynamic evaluation value of the high-frequency trading market at each time series, which is specifically expressed as:

[0069] ,

[0070] ML i represents the dynamic evaluation value of the high-frequency trading market at the i-th time series, Loi represents the dynamic slope of the limit order book at the i-th time series, Lt i represents the transaction duration distribution entropy of the i-th time series, Lc i Indicates the cancellation and re-hang ratio of the i-th sequence, Lp i represents the price shock elasticity coefficient of the i-th time series, and n represents the number of time series.

[0071] The credit risk and capital structure optimization analysis method is used to establish a credit risk and capital structure optimization analysis model, import the credit risk and capital structure optimization data transmitted by S2 into the credit risk and capital structure optimization analysis model, and calculate the credit risk and capital structure evaluation value of each time series, which is specifically expressed as:

[0072] ,

[0073] MC i represents the credit risk and capital structure assessment value of the i-th time series, Cd i represents the implied default rate of credit derivatives at the i-th time series, Cs i represents the debt maturity structure deviation of the i-th time series, Cm i represents the capital structure adjustment cost at the i-th time series, Cl i It represents the contingent liability reserve ratio at the i-th time series, and n represents the number of time series.

[0074] The operation efficiency and technology innovation potential evaluation method is used to establish an operation efficiency and technology innovation potential evaluation model, import the operation efficiency and technology innovation potential data transmitted by S2 into the operation efficiency and technology innovation potential evaluation model, and calculate the operation optimization and technology potential evaluation value of each time series, which is specifically expressed as:

[0075] ,

[0076] MD i represents the operational optimization and technical potential evaluation value of the i-th time series, Do i Denotes the digital input-output efficiency ratio of the i-th time series, Dp i represents the intellectual property asset turnover rate at the i-th time series, Dc i Denotes the customer feedback cycle time of the i-th time sequence, Ds i It represents the intelligent system fault recovery time of the i-th time sequence, and n represents the number of time sequences.

[0077] The market linkage and macroeconomic risk assessment method is used to establish a market linkage and macroeconomic risk assessment model, import the market linkage and macroeconomic data transmitted by S2 into the market linkage and macroeconomic risk assessment model, and calculate the macroeconomic and market interaction risk assessment value of each time series, which is specifically expressed as:

[0078] ,

[0079] MG i represents the risk assessment value of macroeconomic and market interaction at the i-th time series, Ge i Gc represents the economic cycle synchronization index of the i-th time series. i Gt represents the correlation of commodity price fluctuations in the i-th time series. i Gm represents the rate of change of trade flow at the i-th time series. i represents the change rate of the enterprise market share in the i-th time series, and n represents the number of time series.

[0080] S4: Financial asset evaluation: used to conduct a comprehensive evaluation of the data transmitted by S3, calculate the comprehensive risk assessment value of the target enterprise, and transmit it to S5.

[0081] The specific steps of S4 performing comprehensive evaluation on the data transmitted by S3 are as follows:

[0082] A1: Standardization: for ML i , MC i ,MD i and MG i After standardization, we get ML i ′、MC i ′、MD i ' and MG i ′, the standardized formula is:

[0083] ,

[0084] where min(x i ) represents the minimum value of all time series, max(x i ) represents the maximum value among all time series;

[0085] A2: Improved Euclidean distance calculation: Determine the target value as O = (ML0, MC0, MD0, MG0), the weights are W1, W2, W3 and W4, and W1+W2+W3+W4=1, then the improved Euclidean distance D is specifically expressed as:

[0086] ;

[0087] ML0 represents the dynamic target assessment value of the high-frequency trading market, MC0 represents the target assessment value of credit risk and capital structure, MD0 represents the target assessment value of operation optimization and technological potential, and MG0 represents the target assessment value of macroeconomic and market interaction risk;

[0088] A3: Fuzzy Logic Transformation: Let the comprehensive risk assessment value be R, and R ∈ [0, 1], where 0 represents the lowest risk and 1 represents the highest risk. Define a membership function f(D) to map the distance value D to the risk assessment value R, specifically expressed as:

[0089] ,

[0090] max(D) represents the maximum value that the distance value D can take in all possible cases.

[0091] It should be specifically noted in this embodiment that the W1, W2, W3, and W4 are obtained by fitting experimental data.

[0092] S5: Risk Judgment: Used to determine the financial asset risk status of the target enterprise according to the comprehensive risk assessment value transmitted in S4.

[0093] When R ≤ 0.3, it indicates that the financial assets of the target enterprise are in a low-risk state; when 0.3 < R ≤ 0.6, it indicates that the financial assets of the target enterprise are in a medium-risk state; when R > 0.6, it indicates that the financial assets of the target enterprise are in a high-risk state.

[0094] Reference Figure 2 , A financial asset evaluation system based on big data includes a system operation database, a system central processing module, and a user information terminal, and also includes a data collection timing planning module, a financial data collection module, a financial data analysis module, a financial asset evaluation module, and a risk judgment module.

[0095] The data collection timing planning module is used to plan the financial data collection timing of the target enterprise, arrange the data collection moments at preset equal time intervals, and sequentially number these moments;

[0096] The financial data collection module is used to collect high-frequency trading behavior and market structure data, credit risk and capital structure optimization data, operation efficiency and technological innovation potential data, and market linkage and macroeconomic data of the target enterprise at each timing, and transmit them to the financial data analysis module;

[0097] The financial data analysis module includes a high-frequency trading behavior and market structure analysis unit, a credit risk and capital structure optimization analysis unit, an operation efficiency and technological innovation potential evaluation unit, and a market linkage and macroeconomic risk evaluation unit, and is used to establish corresponding mathematical models to analyze the data transmitted by the financial data collection module, and transmit the analysis results to the financial asset evaluation module;

[0098] The financial asset evaluation module is used to comprehensively evaluate the data transmitted by the financial data analysis module, calculate the comprehensive risk assessment value of the target enterprise, and transmit it to the risk judgment module;

[0099] The risk judgment module is used to determine the financial asset risk status of the target enterprise according to the comprehensive risk assessment value transmitted by the financial asset assessment module.

[0100] The present invention plans the data collection moments by presetting the same time intervals through the data collection timing planning step, and numbers these moments sequentially, so as to systematically collect the financial data of the target enterprise, which not only ensures the time sequence of the data, but also avoids the deviation caused by inconsistent data collection time, and lays a solid foundation for subsequent analysis; through the financial data collection step, the detailed data of the target enterprise is collected from multiple dimensions, and the collected data is comprehensive and accurate through multiple channels such as real-time interface, market data, financial reports and intelligent system, which provides a rich source of information for subsequent in-depth analysis and evaluation; through the financial data analysis step, the collected data is converted into the core step of valuable information, and the collected data is professionally analyzed by establishing multiple mathematical models of high-frequency trading behavior, credit risk, operational efficiency, technological innovation potential, market linkage and macroeconomics, so as to quantitatively evaluate the target enterprise in different aspects. The performance of the overall situation can provide a scientific basis for comprehensive evaluation; through the financial asset evaluation step, the analysis results of multiple dimensions are integrated to form a comprehensive evaluation of the financial asset risks of the target enterprise. First, the evaluation values ​​of each dimension are standardized to eliminate dimensional differences. Then, the improved Euclidean distance calculation method is used, combined with the weights of each dimension, to calculate the comprehensive risk assessment value. Finally, through fuzzy logic conversion, the distance value is mapped to an intuitive risk assessment value, which is easy for enterprises and investors to understand and apply; through the risk judgment step, according to the comprehensive risk assessment value, the financial asset risk status of the target enterprise is divided into low risk, medium risk or high risk, which provides a clear decision-making basis for enterprises and investors, and helps them to formulate corresponding risk management strategies and investment decisions. At the same time, regular financial asset evaluation can also help enterprises discover risk changes in a timely manner, providing strong support for continuous improvement and risk management.

[0101] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0102] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A financial asset evaluation method based on big data, characterized in that: include: S1: Data collection timing planning: used to plan the timing of financial data collection of the target enterprise, arrange the data collection moments according to the same preset time intervals, and number these moments sequentially; S1 sets the financial data collection cycle according to the business characteristics and market environment of the target enterprise. The specific cycle depends on the volatility of the data and the analysis requirements, and then determines the start and end time of data collection; S2: Financial data collection: used to collect the target company's amount data and transmit it to S3; The S2 is used to collect the target enterprise's high-frequency trading behavior and market structure data, credit risk and capital structure optimization data, operational efficiency and technological innovation potential data, and market linkage and macroeconomic data at each time series; S3: Financial data analysis: used to analyze the data transmitted by S2 and transmit the analysis results to S4; The S3 includes a high-frequency trading behavior and market structure analysis method, a credit risk and capital structure optimization analysis method, an operational efficiency and technological innovation potential assessment method, and a market linkage and macroeconomic risk assessment method, which are used to establish a corresponding mathematical model to analyze the data transmitted by S2; The high-frequency trading behavior and market structure analysis method is used to establish a high-frequency trading behavior and market structure analysis model, import the high-frequency trading behavior and market structure data transmitted by S2 into the high-frequency trading behavior and market structure analysis model, and calculate the dynamic evaluation value of the high-frequency trading market at each time series, which is specifically expressed as: ， ML i represents the dynamic evaluation value of the high-frequency trading market at the i-th time series, Lo i represents the dynamic slope of the limit order book at the i-th time series, Lt i represents the transaction duration distribution entropy of the i-th time series, Lc i Indicates the cancellation and re-hang ratio of the i-th sequence, Lp i represents the price shock elasticity coefficient of the i-th time series, and n represents the number of time series; The credit risk and capital structure optimization analysis method is used to establish a credit risk and capital structure optimization analysis model, import the credit risk and capital structure optimization data transmitted by S2 into the credit risk and capital structure optimization analysis model, and calculate the credit risk and capital structure evaluation value of each time series, which is specifically expressed as: ， MC i represents the credit risk and capital structure assessment value of the i-th time series, Cd i represents the implied default rate of credit derivatives at the i-th time series, Cs i represents the debt maturity structure deviation of the i-th time series, Cm i represents the capital structure adjustment cost at the i-th time series, Cl i represents the contingent liability reserve ratio at the i-th time series, and n represents the number of time series; The operation efficiency and technology innovation potential evaluation method is used to establish an operation efficiency and technology innovation potential evaluation model, import the operation efficiency and technology innovation potential data transmitted by S2 into the operation efficiency and technology innovation potential evaluation model, and calculate the operation optimization and technology potential evaluation value of each time series, which is specifically expressed as: ， MD i represents the operational optimization and technical potential evaluation value of the i-th time series, Do i Denotes the digital input-output efficiency ratio of the i-th time series, Dp i represents the intellectual property asset turnover rate at the i-th time series, Dc i Denotes the customer feedback cycle time of the i-th time sequence, Ds i represents the intelligent system fault recovery time of the i-th time series, and n represents the number of time series; The market linkage and macroeconomic risk assessment method is used to establish a market linkage and macroeconomic risk assessment model, import the market linkage and macroeconomic data transmitted by S2 into the market linkage and macroeconomic risk assessment model, and calculate the macroeconomic and market interaction risk assessment value of each time series, which is specifically expressed as: ， MG i represents the risk assessment value of macroeconomic and market interaction at the i-th time series, Ge i Gc represents the economic cycle synchronization index of the i-th time series. i Gt represents the correlation of commodity price fluctuations in the i-th time series. i Gm represents the rate of change of trade flow at the i-th time series. i represents the change rate of the enterprise market share in the i-th time series, and n represents the number of time series; S4: Financial asset evaluation: used to conduct a comprehensive evaluation of the data transmitted by S3, calculate the comprehensive risk assessment value of the target enterprise, and transmit it to S5; S5: Risk judgment: used to determine the risk status of the target enterprise’s financial assets based on the comprehensive risk assessment value transmitted by S4.

2. The financial asset evaluation method based on big data according to claim 1, characterized in that: The high-frequency trading behavior and market structure data include the dynamic slope of the limit order book, the distribution entropy of transaction duration, the cancellation and relisting ratio, and the price shock elasticity coefficient, which are marked as Lo, Lt, Lc, and Lp respectively. The credit risk and capital structure optimization data include the implied default rate of credit derivatives, the debt maturity structure deviation, the capital structure adjustment cost, and the contingent liability reserve adequacy ratio, which are marked as Cd, Cs, Cm, and Cl respectively. The operational efficiency and technological innovation potential data include the digital input-output efficiency ratio, the intellectual property asset turnover rate, the customer feedback cycle time, and the intelligent system fault recovery time, which are marked as Do, Dp, Dc, and Ds respectively. The market linkage and macroeconomic data include the economic cycle synchronization index, the correlation between commodity price fluctuations, the trade flow change rate, and the enterprise market share change rate, which are marked as Ge, Gc, Gt, and Gm respectively.

3. The financial asset evaluation method based on big data according to claim 1, characterized in that: The specific steps of S4 performing comprehensive evaluation on the data transmitted by S3 are as follows: A1: Standardization: for ML i , MC i ,MD i and MG i After standardization, we get ML i ′、MC i ′、MD i ' and MG i ′, the standardized formula is: ， where min(x i ) represents the minimum value of all time series, max(x i ) represents the maximum value among all time series; A2: Improved Euclidean distance calculation: Determine the target value as O = (ML0, MC0, MD0, MG0), the weights are W1, W2, W3 and W4, and W1+W2+W3+W4=1, then the improved Euclidean distance D is specifically expressed as: ； ML0 represents the dynamic target assessment value of the high-frequency trading market, MC0 represents the target assessment value of credit risk and capital structure, MD0 represents the target assessment value of operation optimization and technological potential, and MG0 represents the target assessment value of macroeconomic and market interaction risk; A3: Fuzzy logic conversion: Let the comprehensive risk assessment value be R, and R∈[0,1], where 0 represents the lowest risk and 1 represents the highest risk. Define a membership function f(D) to map the distance value D to the risk assessment value R, which can be expressed as follows: ， max(D) represents the maximum value that the distance value D can take in all possible cases.

4. A financial asset evaluation system based on big data, used to implement a financial asset evaluation method based on big data as described in any one of claims 1 to 3, comprising a system operation database, a system central processing module and a user information terminal, characterized in that: It also includes a data collection timing planning module, a financial data collection module, a financial data analysis module, a financial asset evaluation module and a risk judgment module.

5. A financial asset evaluation system based on big data according to claim 4, characterized in that: The financial data analysis module includes a high-frequency trading behavior and market structure analysis unit, a credit risk and capital structure optimization analysis unit, an operational efficiency and technological innovation potential assessment unit, and a market linkage and macroeconomic risk assessment unit, which are used to establish a corresponding mathematical model to analyze the data transmitted by the financial data acquisition module and transmit the analysis results to the financial asset assessment module.

Images