Enterprise risk assessment method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of risk assessment, and relates to an enterprise risk assessment method, which comprises the steps of extracting key indexes from enterprise operation data of an enterprise; calculating a first weight of each key index based on an entropy method; calculating a correlation coefficient between the key indexes, and adjusting the first weight of each key index based on the obtained correlation coefficient to obtain a second weight of each key index; for each key index, based on a preset time attenuation algorithm and the second weight of the key index, decomposing the key index to each preset time interval to obtain a sub-index weight of the key index in each time interval; according to the sub-index weight of the key index in each time interval and the corresponding sub-index value, calculating the index score of the key index, and calculating the comprehensive score of the enterprise according to the index score of each key index; and generating an enterprise risk assessment result of the enterprise according to the comprehensive score. According to the invention, the accuracy and efficiency of enterprise risk assessment are improved.

Description

Technical Field

[0001] The present application relates to the technical field of risk assessment, and in particular to an enterprise risk assessment method, apparatus, computer equipment and storage medium. Background Art

[0002] In the field of supply chain finance, the accounts receivable management and financing risk assessment for small and micro enterprises mainly rely on expert experience to screen indicators and assign weights. This method is highly subjective and easily influenced by the personal judgment of experts, resulting in insufficient objectivity, accuracy and comprehensiveness of enterprise risk assessment, making it difficult to meet the efficient and accurate risk management needs of modern finance. At the same time, manual processing and analysis of large amounts of data is inefficient and difficult to quickly respond to market changes and corporate financing needs. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an enterprise risk assessment method, apparatus, computer equipment and storage medium to solve the problem of low accuracy and efficiency in enterprise risk assessment.

[0004] In order to solve the above technical problems, the present application embodiment provides an enterprise risk assessment method, which adopts the following technical solution:

[0005] Acquire the enterprise's business operation data, and extract key indicators from the enterprise's business operation data according to preset indicator dimensions;

[0006] Calculate the first weight of each key indicator based on the entropy method;

[0007] Calculating the correlation coefficients between the key indicators, and adjusting the first weights of the key indicators based on the obtained correlation coefficients to obtain the second weights of the key indicators;

[0008] For each key indicator, based on a preset time decay algorithm and a second weight of the key indicator, the key indicator is decomposed into preset time intervals to obtain sub-indicator weights of the key indicator in each time interval;

[0009] Calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator scores of each key indicator;

[0010] An enterprise risk assessment result of the enterprise is generated according to the comprehensive score.

[0011] In order to solve the above technical problems, the embodiment of the present application also provides an enterprise risk assessment device, which adopts the following technical solution:

[0012] A data acquisition module, used to acquire the enterprise's business data and extract key indicators from the enterprise's business data according to preset indicator dimensions;

[0013] A first calculation module, used for calculating a first weight of each key indicator based on an entropy method;

[0014] A first adjustment module, used for calculating the correlation coefficient between the key indicators, and adjusting the first weight of the key indicators based on the obtained correlation coefficient to obtain the second weight of the key indicators;

[0015] An indicator decomposition module, for decomposing each key indicator into preset time intervals based on a preset time decay algorithm and a second weight of the key indicator, and obtaining sub-indicator weights of the key indicator in each time interval;

[0016] A scoring calculation module, used to calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator scores of each key indicator;

[0017] A risk assessment module is used to generate an enterprise risk assessment result of the enterprise based on the comprehensive score.

[0018] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0019] Acquire the enterprise's business operation data, and extract key indicators from the enterprise's business operation data according to preset indicator dimensions;

[0020] Calculate the first weight of each key indicator based on the entropy method;

[0021] Calculating the correlation coefficients between the key indicators, and adjusting the first weights of the key indicators based on the obtained correlation coefficients to obtain the second weights of the key indicators;

[0022] For each key indicator, based on a preset time decay algorithm and a second weight of the key indicator, the key indicator is decomposed into preset time intervals to obtain sub-indicator weights of the key indicator in each time interval;

[0023] Calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator scores of each key indicator;

[0024] An enterprise risk assessment result of the enterprise is generated according to the comprehensive score.

[0025] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0026] Acquire the enterprise's business operation data, and extract key indicators from the enterprise's business operation data according to preset indicator dimensions;

[0027] Calculate the first weight of each key indicator based on the entropy method;

[0028] Calculating the correlation coefficients between the key indicators, and adjusting the first weights of the key indicators based on the obtained correlation coefficients to obtain the second weights of the key indicators;

[0029] For each key indicator, based on a preset time decay algorithm and a second weight of the key indicator, the key indicator is decomposed into preset time intervals to obtain sub-indicator weights of the key indicator in each time interval;

[0030] Calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator scores of each key indicator;

[0031] An enterprise risk assessment result of the enterprise is generated according to the comprehensive score.

[0032] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: extracting key indicators from the business operation data of the enterprise, and weighting the key indicators through the entropy method, eliminating the subjectivity of relying on expert experience in traditional risk assessment, and ensuring the objectivity and rationality of weight distribution; through correlation adjustment, the weights are further optimized, so that the mutual relationship between key indicators can be fully considered, and the accuracy of the assessment is improved; introducing a time decay algorithm, decomposing key indicators into multiple time intervals, emphasizing the different impacts of data in different periods, so that the risk assessment results can better reflect the latest risk status of the enterprise; according to the sub-indicator weights and sub-indicator values ​​of the key indicators in each time interval, the indicator score of the key indicator is calculated, and the comprehensive score of the enterprise is calculated according to the indicator score of each key indicator, and the enterprise risk assessment result of the enterprise is generated according to the comprehensive score, which can reflect the changes in the business conditions of the enterprise in real time and improve the accuracy and efficiency of enterprise risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0035] Figure 2 is a flow chart of an embodiment of an enterprise risk assessment method according to the present application;

[0036] Figure 3 is a structural schematic diagram of an embodiment of an enterprise risk assessment device according to the present application;

[0037] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0039] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0041] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0042] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0043] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0044] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0045] It should be noted that the enterprise risk assessment method provided in the embodiment of the present application is generally executed by a server, and accordingly, the enterprise risk assessment device is generally set in the server.

[0046] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0047] Continue to refer Figure 2 , shows a flow chart of an embodiment of the enterprise risk assessment method according to the present application. The enterprise risk assessment method comprises the following steps:

[0048] Step S201, obtaining the business operation data of the enterprise, and extracting key indicators from the business operation data according to preset indicator dimensions.

[0049] In this embodiment, the electronic device (eg, Figure 1 The server shown in the figure) can communicate with the terminal device through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0050] Specifically, key indicators are extracted from the enterprise's business data according to the preset indicator dimensions. The enterprise business data may include business data from different aspects of the enterprise. The key indicator extraction process relies on the preset rules of specific indicator dimensions to ensure that the extracted key indicators are relevant to the enterprise risk assessment.

[0051] Furthermore, the above step S201 may include: obtaining the enterprise's business data, which includes the enterprise's cash flow data, credit data and supply chain data; preprocessing the enterprise's business data; and extracting a preset number of indicators from the enterprise's business data as key indicators according to preset indicator dimensions.

[0052] Specifically, business operating data may include multiple sources, such as the company's cash flow data, credit data, and supply chain data. These data provide information about the company's daily operations, loan credit status, and relationships with upstream and downstream companies in the supply chain.

[0053] After obtaining the business operation data of the enterprise, it is still necessary to perform preprocessing. For example, it may be necessary to clean the data (remove noise or incomplete data), standardize (unify the dimensions to ensure that different data dimensions are comparable), filter out irrelevant information, fill in the median of the outliers in the data, and fill in the missing values ​​with constants, etc.

[0054] Next, according to the preset indicator dimensions, a certain number of indicators are extracted from the pre-processed business data as key indicators for enterprise risk assessment. Usually, key indicators are extracted from flow data, credit data, and supply chain data. These key indicators can effectively reflect the comprehensive operating conditions of the enterprise and provide basic data support for subsequent risk assessment.

[0055] In this embodiment, multidimensional data sources from the enterprise are obtained and preprocessed to ensure the comprehensiveness and consistency of the data, providing a reliable data basis for enterprise risk assessment; preprocessing can eliminate outliers and noise, reduce the impact of data inconsistency on the assessment, and improve the accuracy of the assessment; key indicators are extracted based on preset indicator dimensions, and the most representative operating characteristics of the enterprise are directly extracted, which facilitates subsequent more accurate weight calculation and risk assessment.

[0056] Step S202, calculating the first weight of each key indicator based on the entropy method.

[0057] Specifically, the entropy method is used to calculate the first weight W of each key indicator: orig The entropy method is an objective weighting method that measures the degree of dispersion of each indicator and gives higher weights to indicators with greater fluctuations. The entropy method can reduce subjective interference and improve the objectivity of weights.

[0058] The entropy method is a method used for multi-objective decision analysis. It determines the degree of dispersion of indicators by calculating the information entropy of indicators, and then determines the weight of each indicator. In information theory, entropy is a measure of uncertainty. The greater the amount of information, the smaller the uncertainty and the smaller the entropy; the smaller the amount of information, the greater the uncertainty and the greater the entropy. According to the characteristics of entropy, the randomness and disorder of an event can be judged by calculating the entropy value. Similarly, the entropy value can also be used to judge the degree of dispersion of an indicator. The greater the degree of dispersion of an indicator, the greater the influence of the indicator on the comprehensive evaluation. Therefore, according to the degree of variation of each indicator, the information entropy can be used to calculate the weight of each indicator, providing a basis for the comprehensive evaluation of multiple indicators.

[0059] The application steps of the entropy method usually include the following aspects:

[0060] Data standardization: In order to eliminate the influence of dimension and unit on the evaluation results, the original data is standardized.

[0061] Calculate the proportion: form a weight matrix of the data, that is, calculate the proportion of each indicator in all samples.

[0062] Calculate the entropy value: According to the weight matrix, calculate the entropy value of each indicator to reflect the discrete degree of the indicator data.

[0063] Calculate the variation index: The variation index is an indicator that reflects the importance of the indicator and can be obtained by subtracting the entropy value from 1.

[0064] Calculate entropy weight: According to the variation index, calculate the weight of each indicator, namely the entropy weight, to reflect the influence of the indicator on the comprehensive evaluation.

[0065] Comprehensive score: Calculate the comprehensive evaluation value of the evaluation object based on the weight and proportion of each indicator.

[0066] In this embodiment, the existing entropy method can be used to calculate the first weight of each key indicator, including calculating the weight value of each key indicator, calculating information entropy, calculating entropy redundancy, and calculating the objective weight (first weight). The detailed calculation process will not be repeated here.

[0067] Step S203, calculating the correlation coefficient between the key indicators, and adjusting the first weight of each key indicator based on the obtained correlation coefficient to obtain the second weight of each key indicator.

[0068] Specifically, the correlation coefficients between the key indicators, such as the Pearson correlation coefficient, are calculated to evaluate the mutual relationship between the key indicators. On this basis, the first weight of each key indicator is adjusted to obtain the adjusted second weight W norm Key indicators with higher correlation coefficients may have a more direct impact on corporate risk, so the assessment accuracy is improved by adjusting the correlation.

[0069] Furthermore, the above step S203 may include: calculating the correlation coefficient between each key indicator; calculating the correlation adjustment coefficient between each key indicator based on the obtained correlation coefficient; constructing an adjustment coefficient matrix according to each correlation adjustment coefficient; adjusting the first weight of each key indicator according to the adjustment coefficient matrix, and normalizing the adjusted weight to obtain the second weight of each key indicator.

[0070] Specifically, the correlation coefficients between key indicators are calculated to obtain the correlation between different indicators. Through the correlation coefficient, it can be found that there may be a high correlation between certain key indicators, thereby avoiding repeated consideration of the influence of the same type of information in the weight calculation.

[0071] In one embodiment, the Pearson correlation coefficient formula is used to calculate the Pearson correlation coefficient between different key indicators. This application can use the existing Pearson correlation coefficient calculation method for calculation, and needs to use the observation values ​​of each key indicator at multiple time points. The specific calculation process is not repeated here.

[0072] Based on these correlation coefficients, the correlation adjustment coefficients between key indicators are calculated as follows: ij =1-|r ij |, where i and j represent key indicators, r ij represents the correlation coefficient between key indicators i and j, |r ij | is r ij The absolute value of a ij It represents the correlation adjustment coefficient between key indicators i and j. The correlation adjustment coefficient reflects the relative importance of key indicators in the overall evaluation, especially when there is a strong correlation, some key indicators may be affected by other key indicators.

[0073] Construct an adjustment coefficient matrix based on each associated adjustment coefficient. Assume that there is a key indicator X 1 , X 2 , X 3 .X 1 With X2 The correlation coefficient between 12 =0.9,X 1 With X 3 The correlation coefficient between 13 =0.8,X 2 With X 3 The correlation coefficient between 23 =0.9. Then the adjustment coefficient matrix A is as follows:

[0074]

[0075] The weights of each key indicator are adjusted by constructing a correlation adjustment coefficient matrix. This matrix comprehensively considers the interrelationships among key indicators to ensure that the weight distribution is more reasonable and objective.

[0076] The adjustment formula is as follows:

[0077]

[0078] in, Represents the weight obtained after adjustment of key indicator i; ω j represents the first weight of key indicator j, ω i Indicates the first weight of key indicator i; a ij Indicates the correlation adjustment coefficient between key indicators i and j; a kl is an element in the correlation adjustment coefficient matrix, indicating the correlation adjustment coefficient between key indicators k and l; ω l represents the first weight of the key indicator l. In formula 1, the numerator Σ(a ij ·ω j ) represents the correlation adjustment coefficient a for key indicator i combined with other key indicators ij To adjust its weight, the denominator ∑∑(a kl ·ω l ) is a normalization factor used to ensure that the adjusted weights remain within a reasonable range.

[0079] The adjusted weights are then normalized to eliminate the deviation in the sum of weights caused by the weight adjustment, ensuring that the weights of each key indicator have a uniform standardized range in the overall evaluation and that the sum of the second weights of each key indicator is 1. After these adjustments and normalization processes, the second weight of key indicator i is obtained. Used for subsequent risk assessment calculations.

[0080] In this embodiment, by calculating the correlation coefficients between key indicators, the correlation between indicators can be effectively identified and repeated calculation of redundant information can be avoided; the correlation adjustment coefficient is calculated based on the correlation coefficient to ensure that the relative importance of each indicator can be reasonably considered; the adjustment coefficient matrix is ​​constructed to comprehensively handle the complex correlation relationship between multiple indicators and achieve a more reasonable weight distribution; the normalization process ensures that the adjusted weights have consistent standards during the calculation process and avoids deviation problems caused by unbalanced weights.

[0081] Step S204: for each key indicator, based on a preset time decay algorithm and a second weight of the key indicator, the key indicator is decomposed into preset time intervals to obtain sub-indicator weights of the key indicator in each time interval.

[0082] Specifically, the key indicators are decomposed according to multiple preset time intervals, and each key indicator is decomposed into multiple sub-indicators. A time decay algorithm, such as an exponential decay function, is used to ensure that newer data occupies a larger proportion. The sub-indicator weight of each time interval is obtained by time decaying the second weight according to the time decay algorithm, reflecting the impact of dynamic changes on risk assessment.

[0083] Furthermore, the above step S204 may include: obtaining each preset time interval and obtaining the time interval between each time interval and the target time; calculating the time weight corresponding to each time interval based on the preset time decay algorithm and the obtained time interval; for each key indicator, multiplying the second weight of the key indicator by the time weight of each time interval respectively to decompose the key indicator into each time interval, and obtain the sub-indicator weight of the key indicator in each time interval.

[0084] Specifically, a preset time interval is obtained, for example, each month can be regarded as a time interval, and the time interval from each time interval to the target time is calculated. For example, assuming that there are four months of data (month t = 1, 2, 3, 4, 1 represents the latest month), each of which can be regarded as a time interval, assuming that the current time is the target time, then the time intervals are 1, 2, 3, 4. This operation is to reflect the importance of each time interval relative to the current time point in the overall assessment. According to the time interval, a time weight can be assigned to each time interval. The closer the time interval is to the current time, the greater its time weight may be. This also meets the actual assessment needs, that is, recent operating data may be better able to reflect the current risk status of the enterprise than earlier data.

[0085] The time decay algorithm can be reflected by a time decay function, which can be an exponential decay function and can be expressed as ωt = e -λt, where ωt represents the time weight, λ is the attenuation coefficient, which can be set to 0.1, for example, and t is the time interval between the time interval and the target time. The t value is smaller in newer months and larger in older months.

[0086] After obtaining the time weight of each time interval, the second weight of the key indicator is multiplied by the time weight of each time interval, so that the second weight of the key indicator is dynamically decomposed according to time, so that the data of the key indicator in different periods can be evaluated and considered separately, and the continuity and dynamism of the evaluation are maintained in the time dimension. After dynamic decomposition, the sub-indicator weights of each key indicator in each time interval are obtained, and these sub-indicator weights will be used to calculate the indicator scores in each time interval in the subsequent steps.

[0087] In this embodiment, the key indicators are decomposed into different time intervals, which can make a more detailed and dynamic assessment of the enterprise's operating data, making the enterprise risk assessment results more time-continuous and timely; the time weight is assigned by the time decay algorithm, which can reasonably reduce the impact of historical data on the assessment results, focus on recent data that has a greater impact on the current risk situation, and improve the real-time and accuracy of the assessment results; after multiplying the second weight of the key indicator by the time weight, the relative importance of each key indicator in each time interval is reflected, avoiding the excessive impact of long-term or expired data on the risk assessment results; a more flexible assessment method enables the assessment results to be dynamically adjusted to adapt to changes in the business conditions of the enterprise.

[0088] Step S205, calculating the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculating the comprehensive score of the enterprise according to the indicator score of each key indicator.

[0089] Specifically, indicator score and comprehensive score are two key calculation results in the enterprise risk assessment process, which correspond to risk assessment data at different levels.

[0090] The indicator score is the score result for each key indicator. In the previous step, the key indicator is decomposed by time interval, and the indicator score of the key indicator is calculated based on the sub-indicator weights of the key indicator in each time interval and its corresponding sub-indicator value. It reflects the performance of the key indicator in each time interval and measures the contribution or risk of the key indicator to the overall business status of the enterprise.

[0091] For example, a key indicator may be the cash flow data of a company, which will perform differently in different time periods. Through the time decay algorithm and sub-indicator weights, the cash flow performance of different periods is accumulated to obtain a comprehensive score of the company's cash flow status.

[0092] The comprehensive score is a summary of the scores of all key indicators. The comprehensive score of the enterprise is calculated based on the indicator scores of each key indicator to obtain the final comprehensive score. It is a comprehensive reflection of the entire enterprise's operating risk or status. It not only takes into account the independent performance of each key indicator, but also takes into account the weight distribution between them, making the enterprise's risk assessment more global and objective.

[0093] Furthermore, the above step S205 may include: multiplying the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values ​​respectively to obtain the sub-indicator score in each time interval; accumulating the sub-indicator scores of the key indicator to obtain the indicator score of the key indicator; accumulating the indicator scores of the key indicators to obtain the comprehensive score of the enterprise.

[0094] Specifically, key indicators are counted according to time intervals, and their sub-indicator values ​​in each time interval are recorded in the business data. The sub-indicator weights of the key indicators in each time interval are multiplied by the corresponding sub-indicator values ​​to obtain the sub-indicator scores for each time interval, ensuring that each sub-indicator is properly reflected in the overall evaluation, so that the evaluation takes into account both the importance (weight) of the indicator and the actual performance (sub-indicator value).

[0095] In one embodiment, since the sub-indicator values ​​of the key indicator in some time intervals are relatively large, the sub-indicator values ​​of the key indicator in each time interval may be normalized first, and then the sub-indicator score of each time interval may be calculated.

[0096] The scores of all sub-indicators of the key indicator are accumulated to obtain the overall indicator score of the key indicator. This process enables the sub-indicator scores of different time intervals to be combined to form a comprehensive evaluation of the indicator, which helps to reflect the performance of the key indicator within a certain time range. Finally, the indicator scores of all key indicators are accumulated to generate the comprehensive score of the enterprise. The comprehensive score intuitively shows the performance of the enterprise in the overall risk assessment, and can also provide a quantitative basis for decision-making, supporting the formulation and implementation of relevant risk management measures.

[0097] In this embodiment, a comprehensive perspective is provided for enterprise risk assessment through a refined scoring mechanism; the sub-indicator weights of the key indicators are multiplied by the sub-indicator values ​​to ensure that the assessment results can reflect the importance and actual performance of each sub-indicator, thereby improving the accuracy of the scoring; when calculating the key indicator scores, the accumulation of sub-indicator scores for each time interval enables the assessment to dynamically adapt to changes in the business operations of the enterprise and better capture the risk status of the enterprise in different time periods; the comprehensive score provides the enterprise with a clear risk portrait, helps with risk warning and decision-making, optimizes the enterprise's risk management strategy, and improves the accuracy and timeliness of risk assessment.

[0098] Step S206, generating an enterprise risk assessment result of the enterprise based on the comprehensive score.

[0099] Specifically, the comprehensive score is the overall performance of the enterprise in multiple key dimensions. It is a comprehensive risk assessment result that can reflect the overall health of the enterprise and the potential risk level. Based on the comprehensive score, the enterprise's risk assessment results can be generated to reflect the enterprise's operating stability and potential risks in a specific period of time.

[0100] In this embodiment, key indicators are extracted from the business operating data of the enterprise, and the key indicators are weighted by the entropy method, which eliminates the subjectivity of traditional risk assessment that relies on expert experience and ensures the objectivity and rationality of weight allocation; the weights are further optimized through correlation adjustment, so that the mutual relationship between key indicators can be fully considered, thereby improving the accuracy of the assessment; a time decay algorithm is introduced to decompose the key indicators into multiple time intervals, emphasizing the different impacts of data in different periods, so that the risk assessment results can better reflect the latest risk status of the enterprise; the indicator scores of the key indicators are calculated according to the sub-indicator weights and their sub-indicator values ​​of the key indicators in each time interval, and the comprehensive score of the enterprise is calculated according to the indicator scores of each key indicator, and the enterprise risk assessment results of the enterprise are generated according to the comprehensive score, which can reflect the changes in the business conditions of the enterprise in real time and improve the accuracy and efficiency of enterprise risk assessment.

[0101] Furthermore, the above-mentioned enterprise risk assessment method may also include: accumulating the sub-indicator weights of each key indicator in each time interval to obtain the final weight of each key indicator; and adding the final weight of each key indicator to the enterprise risk assessment result.

[0102] Specifically, the sub-indicator weights of each key indicator in each time interval are accumulated to obtain the final weight of each key indicator, and the performance of the key indicators in each time interval is integrated to ensure that the key indicators can be reflected with their most real weights when conducting a comprehensive risk assessment of the enterprise.

[0103] After accumulating the weights of the sub-indicators of each key indicator, a more representative final weight value is obtained, which reflects the overall importance and stability of the key indicator. The final weight can be added to the risk assessment results of the enterprise, providing the enterprise with a comprehensive risk assessment perspective, so that the risk assessment results not only show the current risk status of the enterprise, but also provide a basis for subsequent risk management strategies. According to the final weight, high-risk areas can be identified and corresponding preventive measures can be formulated to reduce risks in the enterprise's operations.

[0104] In this embodiment, the sub-indicator weights of each time interval are accumulated, and the final weight obtained can more truly reflect the overall importance of the key indicators, thereby enhancing the comprehensiveness of the risk assessment results. The final weight is incorporated into the enterprise risk assessment results, so that managers can more intuitively identify the risk status of the enterprise, clarify the impact of each key indicator on the overall risk, and provide data support for the daily operational decisions of the enterprise.

[0105] Furthermore, after the above step S206, it may also include: generating enterprise management information according to the enterprise risk assessment results of each enterprise, the enterprise management information including a list of safe enterprises and a list of risky enterprises; and sending the enterprise management information to the terminal logged in by the target account.

[0106] Specifically, enterprise management information is generated based on the enterprise risk assessment results of each enterprise. It may include a list of safe enterprises and a list of risky enterprises, converting the risk assessment results into actionable information, providing effective decision-making basis for enterprise management.

[0107] According to the results of enterprise risk assessment, enterprises with higher assessment scores can be sorted into the "safe enterprise list", which is usually called the white list; while enterprises with lower assessment scores and higher risks can be put into the "risk enterprise list", which is usually called the black list. This helps managers quickly identify and pay attention to risky enterprises and take timely measures to reduce potential losses. The safe enterprise list can also serve as an important basis for enterprise assessment and certification.

[0108] The generated enterprise management information is sent to the terminal logged in by the target account to ensure that relevant decision makers can receive the latest information in real time, improve the company's response speed to risk changes, enable the company's management to quickly adjust strategies to deal with risks, and improve the practicality and timeliness of risk management.

[0109] In this embodiment, the enterprise risk assessment results are effectively converted into enterprise management information, providing the enterprise with a dual perspective of security and risk, enabling the enterprise to clearly understand the risk status of itself and other enterprises in the same industry, which is conducive to the formulation of more accurate risk management strategies; by generating a list of safe enterprises and a list of risky enterprises, enterprises can quickly identify high-risk objects, thereby giving priority to risk management and reducing potential losses.

[0110] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0111] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0112] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of an enterprise risk assessment device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0113] like Figure 3 As shown, the enterprise risk assessment device 300 described in this embodiment includes: a data acquisition module 301, a first calculation module 302, a first adjustment module 303, an indicator decomposition module 304, a score calculation module 305 and a risk assessment module 306, wherein:

[0114] The data acquisition module 301 is used to acquire the business operation data of the enterprise and extract key indicators from the business operation data according to preset indicator dimensions.

[0115] The first calculation module 302 is used to calculate the first weight of each key indicator based on the entropy method.

[0116] The first adjustment module 303 is used to calculate the correlation coefficient between the key indicators, and adjust the first weight of each key indicator based on the obtained correlation coefficient to obtain the second weight of each key indicator.

[0117] The indicator decomposition module 304 is used to decompose each key indicator into preset time intervals based on a preset time decay algorithm and a second weight of the key indicator, and obtain sub-indicator weights of the key indicator in each time interval.

[0118] The score calculation module 305 is used to calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator score of each key indicator.

[0119] The risk assessment module 306 is used to generate an enterprise risk assessment result of the enterprise based on the comprehensive score.

[0120] In this embodiment, key indicators are extracted from the business operating data of the enterprise, and the key indicators are weighted by the entropy method, which eliminates the subjectivity of traditional risk assessment that relies on expert experience and ensures the objectivity and rationality of weight allocation; the weights are further optimized through correlation adjustment, so that the mutual relationship between key indicators can be fully considered, thereby improving the accuracy of the assessment; a time decay algorithm is introduced to decompose the key indicators into multiple time intervals, emphasizing the different impacts of data in different periods, so that the risk assessment results can better reflect the latest risk status of the enterprise; the indicator scores of the key indicators are calculated according to the sub-indicator weights and their sub-indicator values ​​of the key indicators in each time interval, and the comprehensive score of the enterprise is calculated according to the indicator scores of each key indicator, and the enterprise risk assessment results of the enterprise are generated according to the comprehensive score, which can reflect the changes in the business conditions of the enterprise in real time and improve the accuracy and efficiency of enterprise risk assessment.

[0121] In some optional implementations of this embodiment, the data acquisition module 301 may include:

[0122] The data acquisition submodule is used to obtain the enterprise's business data, which includes the enterprise's cash flow data, credit data and supply chain data.

[0123] The preprocessing submodule is used to preprocess the business operation data of the enterprise.

[0124] The indicator extraction submodule is used to extract a preset number of indicators from the enterprise operation data as key indicators according to the preset indicator dimensions.

[0125] In some optional implementations of this embodiment, the first adjustment module 303 may include:

[0126] The coefficient calculation submodule is used to calculate the correlation coefficients between key indicators.

[0127] The correlation calculation submodule is used to calculate the correlation adjustment coefficient between the key indicators based on the obtained correlation coefficient.

[0128] The matrix construction submodule is used to construct an adjustment coefficient matrix according to each associated adjustment coefficient.

[0129] The weight adjustment submodule is used to adjust the first weight of each key indicator according to the adjustment coefficient matrix, and normalize the adjusted weight to obtain the second weight of each key indicator.

[0130] In some optional implementations of this embodiment, the indicator decomposition module 304 may include:

[0131] The interval acquisition submodule is used to acquire each preset time interval and acquire the time interval between each time interval and the target time.

[0132] The weight calculation submodule is used to calculate the time weight corresponding to each time interval based on a preset time decay algorithm and the obtained time interval.

[0133] The indicator decomposition submodule is used to multiply the second weight of the key indicator by the time weight of each time interval for each key indicator, so as to decompose the key indicator into each time interval and obtain the sub-indicator weight of the key indicator in each time interval.

[0134] In some optional implementations of this embodiment, the score calculation module 305 may include:

[0135] The calculation submodule is used to multiply the sub-indicator weights of the key indicators in each time interval and their corresponding sub-indicator values ​​respectively to obtain the sub-indicator scores in each time interval.

[0136] The score calculation submodule is used to accumulate the scores of each sub-indicator of the key indicator to obtain the indicator score of the key indicator.

[0137] The comprehensive calculation submodule is used to accumulate the indicator scores of each key indicator to obtain the comprehensive score of the enterprise.

[0138] In some optional implementations of this embodiment, the enterprise risk assessment device 300 may further include:

[0139] The weight accumulation module is used to accumulate the sub-indicator weights of each key indicator in each time interval to obtain the final weight of each key indicator.

[0140] The weight adding module is used to add the final weight of each key indicator to the enterprise risk assessment results.

[0141] In some optional implementations of this embodiment, the enterprise risk assessment device 300 may further include:

[0142] The information generation module is used to generate enterprise management information based on the enterprise risk assessment results of each enterprise. The enterprise management information includes a list of safe enterprises and a list of risky enterprises.

[0143] The information sending module is used to send enterprise management information to the terminal logged in by the target account.

[0144] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0145] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0146] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0147] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the enterprise risk assessment method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0148] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the enterprise risk assessment method.

[0149] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0150] The computer device provided in this embodiment can execute the above-mentioned enterprise risk assessment method. Here, the enterprise risk assessment method can be the enterprise risk assessment method of each of the above-mentioned embodiments.

[0151] In this embodiment, key indicators are extracted from the business operating data of the enterprise, and the key indicators are weighted by the entropy method, which eliminates the subjectivity of traditional risk assessment that relies on expert experience and ensures the objectivity and rationality of weight allocation; the weights are further optimized through correlation adjustment, so that the mutual relationship between key indicators can be fully considered, thereby improving the accuracy of the assessment; a time decay algorithm is introduced to decompose the key indicators into multiple time intervals, emphasizing the different impacts of data in different periods, so that the risk assessment results can better reflect the latest risk status of the enterprise; the indicator scores of the key indicators are calculated according to the sub-indicator weights and their sub-indicator values ​​of the key indicators in each time interval, and the comprehensive score of the enterprise is calculated according to the indicator scores of each key indicator, and the enterprise risk assessment results of the enterprise are generated according to the comprehensive score, which can reflect the changes in the business conditions of the enterprise in real time and improve the accuracy and efficiency of enterprise risk assessment.

[0152] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the enterprise risk assessment method as described above.

[0153] In this embodiment, key indicators are extracted from the business operating data of the enterprise, and the key indicators are weighted by the entropy method, which eliminates the subjectivity of traditional risk assessment that relies on expert experience and ensures the objectivity and rationality of weight allocation; the weights are further optimized through correlation adjustment, so that the mutual relationship between key indicators can be fully considered, thereby improving the accuracy of the assessment; a time decay algorithm is introduced to decompose the key indicators into multiple time intervals, emphasizing the different impacts of data in different periods, so that the risk assessment results can better reflect the latest risk status of the enterprise; the indicator scores of the key indicators are calculated according to the sub-indicator weights and their sub-indicator values ​​of the key indicators in each time interval, and the comprehensive score of the enterprise is calculated according to the indicator scores of each key indicator, and the enterprise risk assessment results of the enterprise are generated according to the comprehensive score, which can reflect the changes in the business conditions of the enterprise in real time and improve the accuracy and efficiency of enterprise risk assessment.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0155] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for enterprise risk assessment, characterized in that: The steps include: Acquire the enterprise's business operation data, and extract key indicators from the enterprise's business operation data according to preset indicator dimensions; Calculate the first weight of each key indicator based on the entropy method; Calculating the correlation coefficients between the key indicators, and adjusting the first weights of the key indicators based on the obtained correlation coefficients to obtain the second weights of the key indicators; For each key indicator, based on a preset time decay algorithm and a second weight of the key indicator, the key indicator is decomposed into preset time intervals to obtain sub-indicator weights of the key indicator in each time interval; Calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator scores of each key indicator; An enterprise risk assessment result of the enterprise is generated according to the comprehensive score.

2. The enterprise risk assessment method according to claim 1, characterized in that: The step of obtaining the enterprise's business data and extracting key indicators from the enterprise's business data according to preset indicator dimensions includes: Acquire the business operation data of the enterprise, wherein the business operation data includes the flow data, credit data and supply chain data of the enterprise; Preprocessing the business operation data of the enterprise; According to the preset indicator dimensions, a preset number of indicators are extracted from the business operation data as key indicators.

3. The enterprise risk assessment method according to claim 1, characterized in that: The step of calculating the correlation coefficient between the key indicators and adjusting the first weight of the key indicators based on the obtained correlation coefficient to obtain the second weight of the key indicators includes: Calculate the correlation coefficients between the key indicators; Calculate the correlation adjustment coefficient between the key indicators based on the obtained correlation coefficient; Constructing an adjustment coefficient matrix according to each associated adjustment coefficient; The first weights of the key indicators are adjusted according to the adjustment coefficient matrix, and the adjusted weights are normalized to obtain the second weights of the key indicators.

4. The enterprise risk assessment method according to claim 1, characterized in that: The step of decomposing each key indicator into preset time intervals based on a preset time decay algorithm and the second weight of the key indicator to obtain the sub-indicator weights of the key indicator in each time interval includes: Obtaining each preset time interval, and obtaining the time interval between each time interval and the target time; Based on a preset time decay algorithm and the obtained time interval, calculating the time weight corresponding to each time interval; For each key indicator, the second weight of the key indicator is multiplied by the time weight of each time interval respectively to decompose the key indicator into each time interval and obtain the sub-indicator weights of the key indicator in each time interval.

5. The enterprise risk assessment method according to claim 1, characterized in that: The step of calculating the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and the corresponding sub-indicator values, and calculating the comprehensive score of the enterprise according to the indicator scores of each key indicator includes: Multiply the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values ​​respectively to obtain the sub-indicator scores in each time interval; Accumulate the scores of each sub-indicator of the key indicator to obtain the indicator score of the key indicator; The indicator scores of the key indicators are accumulated to obtain a comprehensive score of the enterprise.

6. The enterprise risk assessment method according to claim 1, characterized in that: The method further comprises: Accumulating the sub-indicator weights of each key indicator in each time interval to obtain the final weight of each key indicator; The final weight of each key indicator is added to the enterprise risk assessment result.

7. The enterprise risk assessment method according to claim 1, characterized in that: After the step of generating the enterprise risk assessment result of the enterprise according to the comprehensive score, the step further includes: Generating enterprise management information according to the enterprise risk assessment results of each enterprise, wherein the enterprise management information includes a list of safe enterprises and a list of risky enterprises; The enterprise management information is sent to the terminal logged in by the target account.

8. An enterprise risk assessment device, characterized in that: include: A data acquisition module, used to acquire the enterprise's business data and extract key indicators from the enterprise's business data according to preset indicator dimensions; A first calculation module, used for calculating a first weight of each key indicator based on an entropy method; A first adjustment module, used for calculating the correlation coefficient between the key indicators, and adjusting the first weight of the key indicators based on the obtained correlation coefficient to obtain the second weight of the key indicators; An indicator decomposition module, for decomposing each key indicator into preset time intervals based on a preset time decay algorithm and a second weight of the key indicator, and obtaining sub-indicator weights of the key indicator in each time interval; A scoring calculation module, used to calculate the indicator score of the key indicator according to the sub-indicator weights of the key indicator in each time interval and their corresponding sub-indicator values, and calculate the comprehensive score of the enterprise according to the indicator scores of each key indicator; A risk assessment module is used to generate an enterprise risk assessment result of the enterprise based on the comprehensive score.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the enterprise risk assessment method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the enterprise risk assessment method according to any one of claims 1 to 7 are implemented.

Images