CN114707733A - Risk indicator prediction method and device, electronic equipment and storage medium - Google Patents

Abstract

The application is applicable to the technical field of computers, and provides a risk indicator prediction method, a risk indicator prediction device, electronic equipment and a storage medium. The risk indicator prediction method comprises the following steps: acquiring the industry type of an enterprise, change information of macroscopic economic data of a first preset time period and operation indexes of the enterprise in the first preset time period, wherein the operation indexes comprise asset information and revenue change information, and the asset information comprises asset composition information and asset change information; inputting the industry category, the change information of the macroscopic economic data of the first preset time period and the operation indexes of the enterprises in the first preset time period into the data analysis model to obtain the grade of the operation condition output by the data analysis model; and determining the index which is most relevant to the level of the operation condition in the operation indexes according to the level of the operation condition, and taking the most relevant index as a risk index, thereby determining the risk index which has the greatest influence on the operation condition of the enterprise.

Description

Prediction method, device, electronic device and storage medium of risk index

technical field

The present application belongs to the field of computer technology, and in particular relates to a method, device, electronic device and storage medium for predicting risk indicators.

Background technique

There are many kinds of indicators that reflect the operating conditions of an enterprise. Among these indicators, some indicators have obvious change trends, and it can be determined whether they are risk indicators by counting the change trends. There are also some indicators whose change trend is not obvious. It is impossible to determine whether they are risk indicators through the change trend, and the operation indicators that have the greatest impact on the operating conditions of the enterprise may be risk indicators with insignificant change trends. If these risk indicators cannot be found in time, will seriously affect the development of enterprises.

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present application provide a method, device, electronic device, and storage medium for predicting risk indicators, which can solve the problem in the prior art that the risk indicators that have the greatest impact on the business operation of an enterprise cannot be determined.

A first aspect of the embodiments of the present application provides a method for predicting a risk indicator, including:

Obtain the industry category to which the enterprise belongs, the change information of macroeconomic data in the first preset period, and the business indicators of the enterprise in the first preset period, where the business indicators include asset information and revenue change information, and the Asset information includes asset composition information and asset change information;

Inputting the industry category, the change information of the macroeconomic data in the first preset time period, and the business indicators of the enterprise in the first preset time period into a data analysis model, to obtain the business status output by the data analysis model level;

According to the level of the business condition, the most relevant index among the business indicators is determined, and the most relevant index is used as a risk index.

In a possible implementation manner, the data analysis model is based on the operating indicators of multiple listed companies in the historical period, the change information of macroeconomic data in the historical period, the industry category to which each listed company belongs, and the information of each firm. The grades of the listed companies' operating conditions in the historical period are the training samples, which are obtained by training the classification model.

In a possible implementation manner, the determining, according to the level of the business condition, the most relevant indicator of the business index that is most relevant to the level of the business condition includes:

Fitting a relationship function between the level of the business condition and the business index according to the level of the business condition and the business index;

According to the relationship function, the most relevant index among the business indexes that is most relevant to the level of the business condition is determined.

In a possible implementation manner, the fitting of the relationship function between the level of the business condition and the business index according to the level of the business condition and the business index includes:

Determine the fitted value of the level of the business condition according to the initial function and the business index;

According to the fitted value of the level of the business condition and the level of the business condition, optimize the parameters of the initial function until the optimal parameters are obtained;

The relationship function is determined according to the optimal parameters.

In a possible implementation manner, in the fitting of the relationship function between the level of the business condition and the business index according to the level of the business condition and the business index, the function includes:

Normalize the business indicators;

According to the level of the business condition and the normalized business index, a relationship function between the level of the business condition and the business index is fitted.

In a possible implementation, the method further includes:

The influence weight of each of the business indicators on the business status is determined according to the relationship function.

In a possible implementation manner, the determining, according to the level of the business condition, the most relevant indicator of the business index that is most relevant to the level of the business condition includes:

Determine the first level according to the preset index in the business index and the first relational expression;

Determine the level of the target business condition according to the first level, the level of the business condition and the preset weight distribution method;

According to the level of the target business condition, the most relevant index among the business indicators that is most relevant to the level of the business condition is determined.

A second aspect of the embodiments of the present application provides a device for predicting risk indicators, including:

The acquisition module is used to acquire the industry category to which the enterprise belongs, the change information of the macroeconomic data in the first preset period, and the operation indicators of the enterprise in the first preset period, and the operation indicators include asset information and revenue Change information, the asset information includes asset composition information and asset change information;

An analysis module, configured to input the industry category, the change information of the macroeconomic data in the first preset period, and the business indicators of the enterprise in the first preset period into a data analysis model to obtain the data analysis The level of operating conditions output by the model;

The output module is configured to determine, according to the level of the business condition, the most relevant index among the business indicators that is most relevant to the level of the business condition, and use the most relevant index as a risk index.

A third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program The method for predicting the risk index as described in the first aspect above is implemented.

A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the risk indicator described in the first aspect above forecasting method.

A fifth aspect of the embodiments of the present application provides a computer program product that, when the computer program product runs on an electronic device, enables the electronic device to execute the method for predicting a risk indicator described in any one of the first aspects above.

Compared with the prior art, the beneficial effects of the embodiments of the present application are: input data by inputting the industry category to which the enterprise belongs, the change information of macroeconomic data in the first preset period, and the business indicators of the enterprise in the first preset period. Analyze the model to obtain the level of business conditions, so that a more accurate level of business conditions can be obtained based on industry conditions and macroeconomic conditions, and then the most relevant business indicators are determined according to the level of business conditions, and the most relevant business indicators are used as risk indicators. Since the most relevant business indicators have the greatest impact on the business status of the enterprise, the risk indicators that have the greatest impact on the business status of the enterprise can be determined.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that are required to be used in the description of the embodiments or the prior art.

Fig. 1 is the realization flow schematic diagram of the prediction method of the risk index provided by an embodiment of the present application;

2 is a schematic diagram of a prediction device for a risk index provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to illustrate the technical solutions described in the present application, the following specific embodiments are used for description.

It is to be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described feature, integer, step, operation, element and/or component, but does not exclude one or more other features , whole, step, operation, element, component and/or the presence or addition of a collection thereof.

There are various indicators that reflect the business status of an enterprise. The business indicator that has the greatest impact on the business status of the enterprise may be an indicator with an insignificant change trend and is not easy to be found. If the risk indicator that has the greatest impact on the business status cannot be determined, it will seriously affect the enterprise development of.

To this end, the present application provides a method for predicting risk indicators, by inputting data analysis by inputting the industry category to which the enterprise belongs, the change information of macroeconomic data in the first preset period, and the business indicators of the enterprise in the first preset period. The model can obtain the level of business conditions, so that a more accurate level of business conditions can be obtained by synthesizing industry conditions and macroeconomic conditions, and then the most relevant business indicators are determined according to the level of business conditions, and the most relevant business indicators are used as risk indicators. The most relevant business indicators have the greatest impact on the business status of the enterprise, therefore, the risk indicators that have the greatest impact on the business status of the enterprise can be determined.

The following is an exemplary description of the prediction method of the risk index provided in the present application.

Referring to FIG. 1 , a method for predicting a risk indicator provided by an embodiment of the present application includes:

S101: Acquire the industry category to which the enterprise belongs, the change information of the macroeconomic data in the first preset period, and the operation indicators of the enterprise in the first preset period, where the operation indicators include asset information and revenue change information, The asset information includes asset composition information and asset change information.

Among them, the industry category refers to the manufacturing industry, the construction industry, the advertising industry, the service industry, the tourism industry, the financial industry, the communication industry, the semiconductor industry, etc., and the industry category to which the enterprise belongs can be one or more.

Macroeconomic data may be global or national economic data, such as national income information, national consumption information, and the like. The change information of macroeconomic data can be the monthly, quarterly or annual growth rate of macroeconomic data. The growth rate can be a single value or multiple values. If the growth rate is multiple values, each growth rate is associated with a time. segment corresponds.

Asset composition information includes information such as customer concentration, direct sales ratio, distribution ratio, accounts payable period, number of employees, and R&D investment ratio over time. The asset change information includes the change information of assets and liabilities over time, the change information of cash flow over time, and the change information of the income statement over time, and the change information can be the growth rate. In one embodiment, the asset change information further includes a return on equity calculated based on the financial statement, a net interest rate on total assets, an operating net interest rate, a total asset turnover rate, an equity multiplier, an asset-liability ratio, and the like. The revenue change information includes the total revenue, growth rate, gross profit margin, and competition concentration of the product.

S102: Input the industry category, the change information of the macroeconomic data in the first preset time period, and the business indicators of the enterprise in the first preset time period into a data analysis model, and obtain an output of the data analysis model. The level of business conditions.

Among them, the data analysis model is obtained by training the classification model by using the training samples, and can output the level of the business status.

In one embodiment, the change information of the macroeconomic data in the first preset period of the input data analysis model and the business indicators of the enterprise in the first preset period are normalized data, that is, all business indicators are converted. It is a value between 0 and 1, so that each index can be in the same order of magnitude, which is more suitable for comprehensive analysis, thereby improving the accuracy of the output level of business conditions.

In an embodiment, before normalizing the business indicators, data cleaning and data reduction are performed on the data to improve data quality and calculation accuracy.

In one embodiment, the data analysis model is based on the operating indicators of multiple listed companies in the historical period, the change information of macroeconomic data in the historical period, the industry category to which each listed company belongs, and the level of the operating status of each listed company in the historical period. The training samples are obtained by training the classification model. Among them, the level of the operating status of each listed company in the historical period is determined according to the financial information or business information of each listed company in the historical period. For example, the level of operating status can be determined according to the growth rate of profit or operating income of each listed company. . The level of the business status may be a numerical value for expressing the level, for example, 1, 2, 3, etc., or may be a score value determined according to the business status. The data of multiple listed companies can better reflect the operating conditions of different industries under different macroeconomic conditions.

Optionally, the data analysis model may also use the business indicators and levels of business conditions in the historical period of the enterprise in the same industry category as the current enterprise, and the change information of the macroeconomic data in the historical period as the training samples, and the classification model obtained by training.

In another embodiment, the data analysis model is a training sample based on the operating indicators of the current enterprise in the historical period, the change information of the macroeconomic data in the historical period, and the level of the current enterprise's operating conditions corresponding to different periods in the historical period. The classification model is trained. Wherein, the level of the operating conditions corresponding to the current enterprise in different periods of the historical period is determined according to the financial information or business information of the current enterprise in the historical period. Using the historical data of the current enterprise as the training sample, the obtained data analysis model can better match the current enterprise.

S103: Determine the most relevant index among the management indicators according to the level of the business situation, and use the most relevant index as a risk index.

In one embodiment, the level of the business condition and each business index of the first preset time period are input into the prediction model to obtain the most relevant index output by the prediction model. The prediction model is obtained by training the classification model according to the grades of the operating conditions of multiple listed companies in the historical period, the operating indicators in the historical period and the most relevant indicators as training samples. Among them, the most relevant indicators are obtained by analyzing the long-term data of multiple listed companies. With pre-trained predictive models, the most relevant metrics can be quickly identified.

其中，y表示经营状况的等级，x₁、x₂、x₃…x_n分别表示其中一项经营指标，k₁、k₂、k₃…k_n、b、n分别表示与各项经营指标对应的待拟合系数。根据经营状况的等级和经营指标确定待拟合系数后，即可得到关系函数。可以看出，x₁对y的影响最大，因此，x₁对应的经营指标即为最相关的指标。In another embodiment, a relationship function between the level of the business situation and the business index is fitted according to the level of the business situation and the business index, and the most relevant index among the business indexes is determined according to the relationship function. For example, the function to be fitted is

Among them, y represents the level _of the management status, _{x 1} , _{x 2} , _{x 3 .} the corresponding coefficients to be fitted. The relation function can be obtained after the coefficient to be fitted is determined according to the level of the business condition and the business index. It can be seen that x ₁ has the greatest impact on y. Therefore, the business index corresponding to x ₁ is the most relevant index.

In one embodiment, the initial value of each parameter to be fitted in the function to be fitted is first determined, the initial function is obtained according to the initial value, the fitted value of the level of the business condition is determined according to the initial function and the business index, and the level of the business condition is determined according to the initial value. The fitting value and the level of operating conditions are optimized, and the parameters of the initial function are optimized until the optimal parameters are obtained, and the relationship function is determined according to the optimal parameters. Specifically, the optimal parameter is obtained when the difference between the fitting value of the level of the business condition and the level of the business condition reaches a preset value or reaches the number of iterations. Exemplarily, the relation function can be obtained by fitting the least squares method. In other embodiments, a neural network-based method can also be used to fit the relation function.

In one embodiment, before fitting the relational function, the business index is normalized, and the relational function between the level of the business condition and the business index is fitted according to the level of the business condition and the normalized business index, so that the Keeping each indicator in the same order of magnitude improves the accuracy of the most relevant indicator of subsequent output.

中，从x₁到x_n，各经营指标与经营状况的等级的相关程度依次下降，根据各经营指标对应的系数或者根据经营指标的数量以及预设的权重设定规则即可确定各指标对经营状况的影响权重。例如，可以将各经营指标对应的系数作为各经营指标对应的影响权重。通过计算各经营指标对应的影响权重，可以为企业经营者提供决策依据。在一实施例中，也可以按照影响权重的顺序对各经营指标进行排序或者按照预设规则绘制成图表并输出，以便于向用户直观展示企业经营过程中的风险因素。In a possible implementation manner, after the relationship function is determined, the degree of correlation between different business indicators and the level of the business status is determined according to the relationship function, and the impact weight of each indicator on the business status is determined according to the degree of correlation. Illustratively, the formula

, from x ₁ to x _n , the degree of correlation between each business index and the level of business conditions decreases in turn. According to the coefficient corresponding to each business index, or according to the number of business indicators and the preset weight setting rules, each index pair can be determined. The impact weight of operating conditions. For example, the coefficient corresponding to each business index may be used as the influence weight corresponding to each business index. By calculating the impact weight corresponding to each business index, it can provide decision-making basis for business operators. In one embodiment, the business indicators may also be sorted in order of influence weights or drawn into a chart according to preset rules and output, so as to visually display the risk factors in the business operation process to the user.

In one embodiment, after obtaining the business status level output by the data analysis model, the first level is determined according to the preset index in the business index and the first relational expression. The first relational expression is a preset relational expression used to determine the level of the business status, and may be set by experts in the financial field based on big data or empirical data. The preset indicators may be some of the business indicators in the first preset period, such as operating income, total profit, total assets, and the like. After the first level is determined, the level of the target business condition is determined according to the first level, the level of the business condition, and the preset weight distribution method. The preset weight distribution method may be a relationship of 1:1 between the level of the business status output by the data analysis model and the first level, or a relationship of 7:3. After calculating the level of the target business condition, according to the level of the target business condition, the most relevant index among the management indicators with the level of the target business condition is determined, that is, the index most relevant to the level of the business condition. The level of the target business condition is determined by synthesizing the level of the business condition output by the data analysis model and the first level determined by the artificially set first relational expression, which improves the accuracy of the determined level of the target business condition.

In the above embodiment, by inputting the industry category to which the enterprise belongs, the change information of the macroeconomic data in the first preset period, and the business indicators of the enterprise in the first preset period, into the data analysis model, the level of the operation status can be obtained, so as to obtain the level of the business status. Based on industry conditions and macroeconomic conditions, a more accurate level of business status is obtained, and then the most relevant business indicators are determined according to the level of business status, and the most relevant business indicators are used as risk indicators. Therefore, the risk indicators that have the greatest impact on the business performance of the enterprise can be identified.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Corresponding to the method for predicting the risk index described in the above embodiment, FIG. 2 shows a structural block diagram of the device for predicting the risk index provided by the embodiment of the present application. part.

As shown in Figure 2, the prediction device of the risk index includes,

The acquisition module 21 is used to acquire the industry category to which the enterprise belongs, the change information of the macroeconomic data in the first preset period, and the operation indicators of the enterprise in the first preset period, and the operation indicators include asset information and operation indicators. receive change information, the asset information includes asset composition information and asset change information;

The analysis module 22 is configured to input the industry category, the change information of the macroeconomic data in the first preset period and the business indicators of the enterprise in the first preset period into a data analysis model to obtain the data The level of business conditions output by the analytical model;

The output module 23 is configured to determine, according to the level of the business condition, the most relevant index among the business indicators that is most relevant to the level of the business condition, and use the most relevant index as a risk index.

In a possible implementation manner, the data analysis model is based on the operating indicators of multiple listed companies in the historical period, the change information of macroeconomic data in the historical period, the industry category to which each listed company belongs, and the information of each firm. The grades of the listed companies' operating conditions in the historical period are the training samples, which are obtained by training the classification model.

In a possible implementation manner, the output module 23 is specifically used for:

Fitting a relationship function between the level of the business condition and the business index according to the level of the business condition and the business index;

According to the relationship function, the most relevant index among the business indexes that is most relevant to the level of the business condition is determined.

In a possible implementation manner, the output module 23 is also specifically used for:

Determine the fitted value of the level of the business condition according to the initial function and the business index;

According to the fitted value of the level of the business condition and the level of the business condition, optimize the parameters of the initial function until the optimal parameters are obtained;

The relationship function is determined according to the optimal parameters.

In a possible implementation manner, the output module 23 is also specifically used for:

Normalize the business indicators;

According to the level of the business condition and the normalized business index, a relationship function between the level of the business condition and the business index is fitted.

In a possible implementation manner, the output module 23 is also used for:

The influence weight of each of the business indicators on the business status is determined according to the relationship function.

In a possible implementation manner, the output module 23 is also specifically used for:

Determine the first level according to the preset index in the business index and the first relational expression;

Determine the level of the target business condition according to the first level, the level of the business condition and the preset weight distribution method;

According to the level of the target business condition, the most relevant index among the business indicators that is most relevant to the level of the business condition is determined.

It should be noted that the information exchange, execution process and other contents between the above-mentioned devices/units are based on the same concept as the method embodiments of the present application. For specific functions and technical effects, please refer to the method embodiments section. It is not repeated here.

FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. As shown in FIG. 3 , the electronic device of this embodiment includes: a processor 31 , a memory 32 , and a computer program 33 stored in the memory 32 and executable on the processor 31 . When the processor 31 executes the computer program 33 , the steps in the above-mentioned embodiment of the method for predicting risk indicators are implemented, for example, steps S101 to S103 shown in FIG. 1 . Alternatively, when the processor 31 executes the computer program 33, the functions of the modules/units in the above device embodiments are implemented, for example, the functions of the acquisition module 21 to the output module 23 shown in FIG. 2 .

Exemplarily, the computer program 33 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 32 and executed by the processor 31 to complete the this application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 33 in the electronic device.

Those skilled in the art can understand that FIG. 3 is only an example of an electronic device, and does not constitute a limitation to the electronic device. It may include more or less components than the one shown in the figure, or combine some components, or different components, such as The electronic device may also include an input and output device, a network access device, a bus, and the like.

The processor 31 may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 32 may be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The memory 32 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card equipped on the electronic device, Flash card (Flash Card) and so on. Further, the memory 32 may also include both an internal storage unit of the electronic device and an external storage device. The memory 32 is used to store the computer program and other programs and data required by the electronic device. The memory 32 may also be used to temporarily store data that has been output or is to be output.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the above-described embodiments of the apparatus/electronic device are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the above-mentioned embodiments, those of ordinary skill in the art should understand that: it can still be used for the above-mentioned implementations. The technical solutions described in the examples are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the application, and should be included in the within the scope of protection of this application.

Claims (10)

1. A method for predicting a risk indicator, comprising:

acquiring the industry category of an enterprise, change information of macro economic data of a first preset time period and operation indexes of the enterprise in the first preset time period, wherein the operation indexes comprise asset information and revenue change information, and the asset information comprises asset composition information and asset change information;

inputting the industry category, the change information of the macro economic data of the first preset time period and the operation indexes of the enterprise in the first preset time period into a data analysis model to obtain the grade of the operation condition output by the data analysis model;

and determining the index which is most relevant to the grade of the operation condition in the operation indexes according to the grade of the operation condition, and taking the most relevant index as a risk index.

2. The method as claimed in claim 1, wherein the data analysis model is obtained by training a classification model by using operation indexes of a plurality of listed companies in a historical period, change information of macro-economic data of the historical period, an industry class to which each listed company belongs, and a grade of operation conditions of each listed company in the historical period as training samples.

3. The method of claim 1, wherein said determining the most relevant of said business indicators to said level of business condition based on said level of business condition comprises:

fitting a relation function of the grade of the operation condition and the operation index according to the grade of the operation condition and the operation index;

and determining the index which is most relevant to the grade of the operation condition in the operation indexes according to the relation function.

4. The method of claim 3, wherein fitting the business condition rating to the business indicator as a function of the business condition rating and the business indicator comprises:

determining a fitting value of the grade of the operation condition according to the initial function and the operation index;

optimizing the parameters of the initial function according to the fitting value of the grade of the operating condition and the grade of the operating condition until the optimal parameters are obtained;

and determining the relation function according to the optimal parameters.

5. The method of claim 3, wherein fitting the business condition rating to the business indicator as a function of the business condition rating and the business indicator comprises:

normalizing the operation index;

and fitting a relation function between the grade of the operation condition and the operation index according to the grade of the operation condition and the normalized operation index.

6. The method of claim 3, further comprising:

and determining the influence weight of each index in the operation indexes on the operation condition according to the relation function.

7. The method of claim 1, wherein determining the index of the business indexes that is most relevant to the level of the business condition based on the level of the business condition comprises:

determining a first grade according to a preset index in the operation index and a first relational expression;

determining the grade of the target operation condition according to the first grade, the grade of the operation condition and a preset weight distribution mode;

and determining the index which is most relevant to the grade of the operation condition in the operation indexes according to the grade of the target operation condition.

8. An apparatus for predicting a risk indicator, comprising:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring the industry type of an enterprise, the change information of macroscopic economic data of a first preset time period and the operation index of the enterprise in the first preset time period, the operation index comprises asset information and revenue change information, and the asset information comprises asset composition information and asset change information;

the analysis module is used for inputting the industry category, the change information of the macro economic data of the first preset time period and the operation indexes of the enterprise in the first preset time period into a data analysis model to obtain the grade of the operation condition output by the data analysis model;

and the output module is used for determining the index which is most relevant to the grade of the operation condition in the operation indexes according to the grade of the operation condition, and taking the most relevant index as a risk index.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of predicting a risk indicator of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method of predicting a risk indicator according to any one of claims 1 to 7.

Images