Evaluation model construction method and device, computer equipment, storage medium and program product

Abstract

The invention relates to an evaluation model construction method and device, computer equipment, a storage medium and a program product. The method comprises the steps of inputting operation data of a plurality of enterprises into an initial evaluation model for health evaluation to obtain a health degree, determining an evaluation result according to the health degree and a preset health standard, and adjusting the initial evaluation model according to the evaluation result and the actual health degree of each enterprise to obtain a target evaluation model. According to the method, the initial evaluation model is adjusted according to the health degree evaluation result of the enterprise and the actual health degree to obtain the evaluation model capable of accurately evaluating the health degree of the enterprise, so that the accuracy of the evaluation value of the evaluation model on the health degree of the enterprise is improved; besides, when health degree assessment needs to be carried out on a large number of enterprises, a large amount of operation data of the enterprises does not need to be analyzed manually, and only the adjusted target assessment model needs to be used for health degree assessment, so that the health degree assessment efficiency of the enterprises is greatly improved.

Description

Technical Field

[0001] The present application relates to the technical field of big data analysis, and in particular to a method, apparatus, computer equipment, storage medium and program product for constructing an evaluation model. Background Art

[0002] As the times are running fast, various types of enterprises are also booming. However, with the adjustment of the capital market structure, enterprises are facing the risk of resource structure collapse all the time. Therefore, it is particularly important to analyze the development prospects or operating status of enterprises.

[0003] Corporate health refers to the good degree of corporate business activities and its ability to develop sustainably. It is the foundation and guarantee for the sustainable development of an enterprise and one of the important indicators that corporate managers and investors pay attention to. By evaluating and monitoring corporate health, corporate managers can find problems in a timely manner and take corresponding measures to ensure the health and sustainable development of the enterprise. At present, corporate health analysts mainly analyze the health of enterprises and evaluate their operating conditions based on their operating data and industry experience.

[0004] However, the above enterprise health assessment method has the problem of low assessment accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, storage medium and program product for constructing an evaluation model that can accurately evaluate the health of an enterprise in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for constructing an evaluation model, comprising:

[0007] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0008] Determine the assessment results based on health status and preset health standards;

[0009] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0010] The above method adjusts the initial assessment model according to the health assessment results of the enterprise and the actual health of the enterprise to obtain an assessment model that can accurately assess the health of the enterprise, thereby improving the accuracy of the assessment value of the enterprise health by the assessment model; in addition, when it is necessary to conduct health assessment on a large number of enterprises, there is no need to manually analyze the large amount of operating data of the enterprise. It is only necessary to use the adjusted target assessment model for health assessment, which greatly improves the efficiency of the enterprise's health assessment.

[0011] In one embodiment, the above evaluation results include the evaluation health of each enterprise, and the initial evaluation model is adjusted according to the evaluation results and the actual health of each enterprise to obtain a target evaluation model, including:

[0012] Verify the consistency between the assessed health and actual health of each enterprise and obtain verification results;

[0013] The initial evaluation model is adjusted according to the verification results to obtain the target evaluation model.

[0014] The method for determining the evaluation model provided in the embodiment of the present application adjusts the initial evaluation model based on the consistency verification results of the evaluated health and the actual health, so that the enterprise health predicted based on the adjusted evaluation model is more accurate.

[0015] In one embodiment, the consistency verification of the assessed health and the actual health of each enterprise is performed to obtain the verification results, including:

[0016] Verify the consistency between the assessed health and actual health of each enterprise and obtain the intermediate verification results of each enterprise;

[0017] The verification results are determined based on the preset verification success conditions and the intermediate verification results of each enterprise.

[0018] The present application provides a method for determining a verification result, which compares the consistency of the evaluation result of the initial evaluation model with the actual result to determine whether the initial evaluation model meets the standard, thereby providing a basis for subsequent adjustments to the initial evaluation model that does not meet the standard.

[0019] In one embodiment, the consistency verification of the assessed health and the actual health of each enterprise is performed to obtain the intermediate verification results of each enterprise, including:

[0020] For each enterprise, the chi-square statistic is calculated based on the enterprise's assessed health and the enterprise's actual health, and the chi-square distribution parameters are obtained;

[0021] The degree of consistency between the assessed health of the enterprise and the actual health of the enterprise is determined based on the chi-square distribution parameter.

[0022] The method for determining the intermediate verification results provided in the embodiment of the present application is based on the calculation of the chi-square statistic for the assessed health and actual health of the enterprise to accurately assess the consistency of the health and the actual health, thereby providing data support for the subsequent accurate adjustment of the initial assessment model based on the consistency of the assessed health and the actual health.

[0023] In one embodiment, the initial evaluation model is adjusted according to the verification result to obtain the target evaluation model, including:

[0024] If the verification result indicates that the verification is passed, the initial evaluation model is determined as the target evaluation model;

[0025] If the verification result indicates that the verification has not passed, the weight parameters in the initial evaluation model are adjusted to obtain the target evaluation model.

[0026] The method for determining the target evaluation model provided in the embodiment of the present application, when the verification result indicates that the verification has not passed, adjusts the initial evaluation model until the evaluation model can correctly evaluate the health of the enterprise, thereby improving the evaluation accuracy of the enterprise health.

[0027] In one embodiment, the method further comprises:

[0028] Obtain operating data of multiple enterprises;

[0029] Extract indicator features from the operating data of each enterprise to obtain the indicator data of each enterprise;

[0030] Input the operating data of multiple enterprises into the initial assessment model for health assessment to obtain the health degree, including:

[0031] Input the indicator data of each enterprise into the initial assessment model for health assessment to obtain the health degree.

[0032] The method for obtaining the indicator data of an enterprise provided in the embodiment of the present application is obtained by extracting features from the operating data of the enterprise, thereby ensuring the accuracy of the subsequent assessment of the health of the enterprise.

[0033] In a second aspect, the present application also provides a device for constructing an evaluation model, comprising:

[0034] An assessment module is used to input the operating data of multiple enterprises into the initial assessment model for health assessment to obtain the health degree;

[0035] A determination module is used to determine the evaluation result according to the health degree and the preset health standard;

[0036] The adjustment module is used to adjust the initial assessment model according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0037] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0039] Determine the assessment results based on health status and preset health standards;

[0040] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0042] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0043] Determine the assessment results based on health status and preset health standards;

[0044] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0045] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0046] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0047] Determine the assessment results based on health status and preset health standards;

[0048] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0049] The above-mentioned evaluation model construction method, device, computer equipment, storage medium and program product, the above-mentioned method adjusts the initial evaluation model according to the health evaluation results of the enterprise and the actual health of the enterprise to obtain an evaluation model that can accurately evaluate the health of the enterprise, thereby improving the accuracy of the evaluation value of the enterprise health by the evaluation model; in addition, when it is necessary to conduct health evaluation on a large number of enterprises, there is no need to manually analyze the large amount of operating data of the enterprise, and only the adjusted target evaluation model needs to be used for health evaluation, which greatly improves the efficiency of the enterprise health evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0051] FIG1 is an application environment diagram of a method for constructing an evaluation model in one embodiment;

[0052] Figure 2 A schematic diagram of a process for constructing an evaluation model in one embodiment;

[0053] Figure 3 A schematic diagram of a flow chart of a method for constructing an evaluation model in another embodiment;

[0054] Figure 4 A schematic diagram of a flow chart of a method for constructing an evaluation model in another embodiment;

[0055] Figure 5 A schematic diagram of a flow chart of a method for constructing an evaluation model in another embodiment;

[0056] Figure 6 A schematic diagram of a flow chart of a method for constructing an evaluation model in another embodiment;

[0057] Figure 7 A schematic diagram of a flow chart of a method for constructing an evaluation model in another embodiment;

[0058] Figure 8 A schematic diagram of a flow chart of a method for constructing an evaluation model in another embodiment;

[0059] FIG. 9 is a structural block diagram of a device for constructing an evaluation model in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] As the times are running fast, various types of enterprises are also booming. However, with the adjustment of the capital market structure, enterprises are facing the risk of resource structure collapse all the time. Therefore, it is particularly important to analyze the development prospects or operating status of enterprises.

[0062] Corporate health refers to the degree of good business operations and the ability of sustainable development of an enterprise. It is the foundation and guarantee for the sustainable development of an enterprise and one of the important indicators that corporate managers and investors pay attention to. By evaluating and monitoring the health of an enterprise, it can help corporate managers to find problems in a timely manner and take corresponding measures to ensure the health and sustainable development of the enterprise. At present, it is mainly through corporate health analysts who manually analyze the health of the enterprise and evaluate the operating conditions of the enterprise based on the company's operating data and industry experience. However, the above-mentioned corporate health assessment method has the problem of low assessment accuracy. This application aims to solve this problem.

[0063] After the background technology of the construction method of the evaluation model provided by the embodiment of the present application is introduced above, the implementation environment involved in the construction method of the evaluation model provided by the embodiment of the present application will be briefly described below. The construction method of the evaluation model provided by the embodiment of the present application can be applied to a computer device as shown in Figure 1. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store sample data of various types of business. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for constructing a cause analysis model is implemented.

[0064] Those skilled in the art will understand that the structure shown in FIG. 1 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific terminal may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0065] After introducing the application scenarios of the method for constructing the evaluation model provided in the embodiments of the present application, the following focuses on introducing the method for constructing the evaluation model described in the present application.

[0066] In one embodiment, Figure 2 As shown, a method for constructing an evaluation model is provided, and the method is applied to the computer device in FIG1 as an example for explanation, including the following steps:

[0067] S201. Input the operating data of multiple enterprises into the initial assessment model to perform health assessment and obtain health status.

[0068] Among them, operating data includes data generated by the enterprise in its historical operation process, such as enterprise information, bank loan information, tax enterprise subsidy information, enterprise property data information, enterprise production and operation data information and enterprise bankruptcy liquidation information from the judicial department, enterprise social security payment information, enterprise registration information, enterprise tax information, enterprise subsidy information to employees, corporate legal person information and enterprise operation registration information, etc.

[0069] The initial evaluation model refers to a pre-built model for evaluating the health of an enterprise based on the operation data of the enterprise. For example, the initial evaluation model may be a model determined based on the operation data of the enterprise and the weights corresponding to each operation data. Alternatively, the initial evaluation model may be determined according to the following formula (1):

[0070]

[0071] On the clock, represents the operating data 1 of the enterprise, a represents the weight corresponding to the operating data 1, represents the enterprise's operating data 2, b represents the weight corresponding to the operating data 2, represents the operating data 3 of the enterprise, c represents the weight corresponding to the operating data 3, ..., represents the operating data n of the enterprise, and n represents the weight corresponding to the operating data n. It should be noted that the weight values ​​in the initial evaluation models corresponding to different enterprises are the same.

[0072] In an embodiment of the present application, when it is necessary to construct an evaluation model for evaluating the health of an enterprise, so as to evaluate the health of the enterprise based on the evaluation model, the operating data of multiple enterprises can be obtained separately first, and then the operating data of the multiple enterprises can be input into the initial evaluation model respectively to obtain the corresponding health of each enterprise.

[0073] S202. Determine the evaluation result according to the health level and the preset health standard.

[0074] Among them, the evaluation results represent the health level of the enterprise, including healthy, sub-healthy and unhealthy.

[0075] The preset health standard is used to evaluate the health of the enterprise according to the health of the enterprise. For example, the preset health standard includes a minimum health threshold and a maximum health threshold. If the health of the enterprise is less than the minimum health threshold, the enterprise is determined to be in an unhealthy state. If the health of the enterprise is greater than the maximum health threshold, the enterprise is determined to be in a healthy state. If the health of the enterprise is greater than the minimum health threshold and less than the maximum health, the enterprise is determined to be in a sub-healthy state.

[0076] In the embodiment of the present application, after the health status of each enterprise is obtained as described above, the evaluation result of each enterprise is determined according to the health status of each enterprise and the preset health standard.

[0077] S203. Adjust the initial assessment model according to the assessment results and the actual health of each enterprise to obtain a target assessment model.

[0078] In an embodiment of the present application, after obtaining the evaluation results of each enterprise as described above, the parameters in the initial evaluation model can be adjusted according to the evaluation results of each enterprise and the actual health of the corresponding enterprise to obtain an evaluation model with adjusted parameters, that is, a target evaluation model.

[0079] The method for constructing an evaluation model provided in the embodiment of the present application inputs the operating data of multiple enterprises into the initial evaluation model for health evaluation to obtain health, determines the evaluation results based on the health and preset health standards, and adjusts the initial evaluation model based on the evaluation results and the actual health of each enterprise to obtain a target evaluation model. The above method adjusts the initial evaluation model according to the health evaluation results of the enterprise and the actual health of the enterprise to obtain an evaluation model that can accurately evaluate the health of the enterprise, thereby improving the accuracy of the evaluation value of the enterprise health by the evaluation model; in addition, when a large number of enterprises need to be evaluated for health, there is no need to manually analyze a large amount of operating data of the enterprise, and only the adjusted target evaluation model needs to be used for health evaluation, which greatly improves the efficiency of the enterprise's health evaluation.

[0080] In one embodiment, Figure 2 Based on the embodiment shown, the above evaluation results include the evaluation health of each enterprise, and the process of obtaining the target evaluation model can be described as follows: Figure 3 As shown, the above S203 "adjusting the initial assessment model according to the assessment results and the actual health of each enterprise to obtain a target assessment model" includes:

[0081] S301. Verify the consistency between the assessed health and the actual health of each enterprise to obtain verification results.

[0082] In the embodiment of the present application, after the assessed health of each enterprise is determined as above, the assessed health of each enterprise and the corresponding actual health can be verified for consistency to obtain the consistency verification result of the assessed health of each enterprise and the corresponding actual health, and then the consistency verification result of the assessed health of each enterprise and the corresponding actual health is evaluated to obtain the verification result. For example, after determining the consistency verification result of the assessed health of each enterprise and the corresponding actual health, the enterprise whose consistency verification result is greater than the preset verification threshold is regarded as a qualified enterprise. If the number of qualified enterprises is greater than the preset number, a verification result of qualified is obtained. If the number of qualified enterprises is not greater than the preset number, a verification result of unqualified is obtained.

[0083] S302: Adjust the initial evaluation model according to the verification result to obtain the target evaluation model.

[0084] In the embodiment of the present application, after the verification result is obtained as described above, the parameters in the initial evaluation model are adjusted according to the verification result to obtain the target evaluation model after the parameter adjustment.

[0085] The method for determining the evaluation model provided in the embodiment of the present application adjusts the initial evaluation model based on the consistency verification results of the evaluated health and the actual health, so that the enterprise health predicted based on the adjusted evaluation model is more accurate.

[0086] In one embodiment, Figure 3 Based on the embodiment shown, the process of obtaining the verification result can be described as follows: Figure 4 As shown, the above S301 "conduct consistency verification on the assessed health and actual health of each enterprise to obtain verification results" includes:

[0087] S401. Verify the consistency between the assessed health and the actual health of each enterprise to obtain the intermediate verification results of each enterprise.

[0088] Among them, the intermediate verification results include that the enterprise's assessed health and actual health are consistent, or that the enterprise's assessed health and actual health are inconsistent.

[0089] In an embodiment of the present application, after the assessed health of each enterprise is obtained as described above, the current actual health of each enterprise can be obtained, and then the assessed health of each enterprise and the corresponding actual health can be verified for consistency to obtain an intermediate verification result that the assessed health of the enterprise is consistent with the actual health, or that the assessed health of the enterprise and the actual health are inconsistent.

[0090] S402: Determine the verification result according to the preset verification success conditions and the intermediate verification results of each enterprise.

[0091] Among them, the preset verification success condition refers to the maximum number of enterprises whose assessed health is inconsistent with the actual health.

[0092] In an embodiment of the present application, after the intermediate verification results of each enterprise are obtained as mentioned above, the intermediate verification results are determined to be the number of enterprises whose assessed health and actual health are inconsistent, and the number of enterprises whose assessed health and actual health are inconsistent is compared with the preset verification success condition. If the number of enterprises whose assessed health and actual health are inconsistent is greater than the preset verification success condition, the verification result is determined to be unsatisfactory; if the number of enterprises whose assessed health and actual health are inconsistent is not greater than the preset verification success condition, the verification result is determined to be up to standard.

[0093] The present application provides a method for determining a verification result, which compares the consistency between the evaluation result of the initial evaluation model and the actual result to determine whether the initial evaluation model meets the standard, thereby providing a basis for subsequent adjustments to the initial evaluation model that does not meet the standard.

[0094] In one embodiment, Figure 4 Based on the embodiment shown, the process of obtaining the intermediate verification results of each enterprise can be described as follows: Figure 5 As shown in the above 401, "conduct consistency verification of the assessed health and actual health of each enterprise to obtain verification results", including:

[0095] S501. For each enterprise, calculate the chi-square statistic according to the assessed health of the enterprise and the actual health of the enterprise to obtain the chi-square distribution parameter.

[0096] In an embodiment of the present application, after the assessed health and the corresponding actual health of each enterprise are obtained as described above, a chi-square statistic is calculated for each enterprise based on the assessed health and enterprise health of the enterprise, thereby obtaining the chi-square distribution parameters of the enterprise.

[0097] Optionally, the calculation process of the chi-square statistic can be expressed as follows:

[0098]

[0099] Among them, A is the frequency corresponding to the actual health level, and E is the frequency corresponding to the evaluated health level. It refers to the chi-square distribution parameter of the enterprise.

[0100] S502. Determine the consistency between the assessed health of the enterprise and the actual health of the enterprise according to the chi-square distribution parameter.

[0101] In an embodiment of the present application, after the chi-square distribution parameters of each enterprise are obtained as described above, the Kappa coefficient of each enterprise can be determined based on the relationship between the chi-square distribution parameters and the consistency coefficient (Kappa coefficient), and then the degree of consistency between the assessed health of the enterprise and the actual health of the enterprise can be determined based on the Kappa coefficient of each enterprise.

[0102] It should be noted that the Kappa coefficient is used to characterize the degree of consistency between two parameters. The Kappa calculation result is [0, 1], which can be divided into five groups to represent different levels of consistency: [0, 0.2] represents extremely low consistency, (0.2, 0.4] represents general consistency, (0.4, 0.6] represents medium consistency, (0.6, 0.8] represents high consistency and (0.8, 1] represents almost complete consistency.

[0103] Optionally, if the Kappa coefficient of the determined enterprise is a number between [0, 0.2], it means that the assessed health and actual health of the enterprise have extremely low consistency; if the Kappa coefficient of the determined enterprise is a number between (0.2, 0.4], it means that the assessed health and actual health of the enterprise have relatively general consistency; if the Kappa coefficient of the determined enterprise is a number between (0.4, 0.6], it means that the assessed health and actual health of the enterprise have relatively moderate consistency; if the Kappa coefficient of the determined enterprise is a number between (0.6, 0.8], it means that the assessed health and actual health of the enterprise have a high degree of consistency; if the Kappa coefficient of the determined enterprise is a number between (0.8, 1], it means that the assessed health and actual health of the enterprise are almost completely consistent.

[0104] The method for determining the intermediate verification results provided in the embodiment of the present application is based on the calculation of the chi-square statistic for the assessed health and actual health of the enterprise to accurately assess the consistency of the health and the actual health, thereby providing data support for the subsequent accurate adjustment of the initial assessment model based on the consistency of the assessed health and the actual health.

[0105] In one embodiment, Figure 3 Based on the embodiment shown, the process of obtaining the target evaluation model can be described as follows: Figure 6 As shown, the above 302 "adjusting the initial evaluation model according to the verification results to obtain the target evaluation model" includes:

[0106] S601, determine whether the verification result indicates that the verification is passed, if the verification result indicates that the verification is passed, execute S602, if the verification result indicates that the verification is not passed, execute S603.

[0107] S602: Determine the initial evaluation model as the target evaluation model.

[0108] S603: Adjust the weight parameters in the initial evaluation model to obtain a target evaluation model.

[0109] In an embodiment of the present application, after the verification result is obtained as mentioned above, if the verification result indicates that the verification has passed, the initial evaluation model is directly determined as the target evaluation model; if the verification result indicates that the verification has not passed, the weight parameters in the initial evaluation model are adjusted to obtain a new initial evaluation model; then, the operating data of multiple enterprises are input into the new initial evaluation model for health evaluation to obtain a new evaluation result; and it is determined again whether the new evaluation result has passed the verification; if so, the new initial evaluation model is determined as the target evaluation model; if not, the weight parameters in the new initial evaluation model are adjusted again to obtain the latest initial evaluation model; and the latest initial evaluation model is used as the new initial evaluation model, and the step of inputting the operating data of multiple enterprises into the new initial evaluation model for health evaluation to obtain a new evaluation result is returned to execute, ... until the evaluation result indicates that the verification has passed, and the new initial evaluation model is determined as the target evaluation model.

[0110] The method for determining the target evaluation model provided in the embodiment of the present application, when the verification result indicates that the verification has not passed, adjusts the initial evaluation model until the evaluation model can correctly evaluate the health of the enterprise, thereby improving the evaluation accuracy of the enterprise health.

[0111] In one embodiment, Figure 2 Based on the embodiment shown, the process of obtaining health can be described as follows: Figure 7 As shown in 201, “inputting the operating data of multiple enterprises into the initial assessment model for health assessment to obtain health degree” includes:

[0112] S204. Obtain operation data of multiple enterprises.

[0113] In an embodiment of the present application, before evaluating the health of an enterprise, the operating data of each enterprise may be obtained first; optionally, the operating data of the enterprise may be obtained from an information storage database through a web crawler program or an Extract, Transform and Load (ETL) tool, wherein the web crawler program includes batch crawlers, incremental crawlers, vertical crawlers and other crawler programs.

[0114] It should be noted that after obtaining the operating data of each enterprise, the obtained operating data can also be processed by big data technologies such as data cleaning, association, comparison and backfilling. Data cleaning includes data conversion, missing value processing, outlier processing, etc., to improve data quality and keep the quality of cleaned data at the same level, improve data analysis accuracy and rationality of the indicator system. The processing of missing values ​​usually includes extracting required feature attributes, removing unnecessary feature attributes, deleting missing values ​​and filling missing values; outlier processing usually includes detection based on statistical and distance methods, deleting outliers or retaining outliers; data conversion includes converting data with inconsistent formats, removing duplicate data, avoiding the appearance of data with excessive variance in continuous values, and numerical coding processing.

[0115] S205: Extract indicator features from the operating data of each enterprise to obtain indicator data of each enterprise.

[0116] Among them, the indicator data include at least one of the debt-to-asset ratio, current ratio, quick ratio, accounts receivable turnover rate, turnover rate, employee satisfaction, market share, market growth rate, innovation capability, social welfare, R&D investment ratio, and new product ratio.

[0117] In an embodiment of the present application, after the operating data of each enterprise is obtained as described above, at least one indicator data in the operating data is extracted according to the four aspects of the enterprise's organizational structure, health environment, healthy population and health activities.

[0118] The above S201 “inputting the operating data of multiple enterprises into the initial assessment model to perform health assessment and obtain health degree” includes:

[0119] S201. Input the indicator data of each enterprise into the initial assessment model to conduct health assessment and obtain the health degree.

[0120] In an embodiment of the present application, when it is necessary to construct an evaluation model for evaluating the health of an enterprise so as to evaluate the health of the enterprise based on the evaluation model, after obtaining the operating data of each enterprise, the indicator data of each enterprise can be determined according to the above steps S204 and S205, and then the indicator data of multiple enterprises can be respectively input into the initial evaluation model to obtain the corresponding health of each enterprise.

[0121] The method for obtaining the indicator data of an enterprise provided in the embodiment of the present application is obtained by extracting features from the operating data of the enterprise, thereby ensuring the accuracy of the subsequent assessment of the health of the enterprise.

[0122] In one embodiment, Figure 8 As shown, a complete method for building an evaluation model is also provided, including:

[0123] S10, obtaining operation data of multiple enterprises;

[0124] S11, extracting index features from the operation data of each enterprise to obtain index data of each enterprise;

[0125] S12, inputting the indicator data of multiple enterprises into the initial assessment model to perform health assessment and obtain health degree;

[0126] S13. Determine the assessment results based on the health level and the preset health standards;

[0127] S14. For each enterprise, calculate the chi-square statistic according to the assessed health of the enterprise and the actual health of the enterprise to obtain the chi-square distribution parameter;

[0128] S15. Determine the degree of consistency between the assessed health of the enterprise and the actual health of the enterprise based on the chi-square distribution parameter;

[0129] S16. Determine the verification result according to the preset verification success conditions and the intermediate verification results of each enterprise;

[0130] S17, determining whether the verification result indicates that the verification is passed, if the verification result indicates that the verification is passed, executing S18, if the verification result indicates that the verification is not passed, executing S19;

[0131] S18, determining the initial evaluation model as the target evaluation model;

[0132] S19. Adjust the weight parameters in the initial evaluation model to obtain the target evaluation model.

[0133] The above method adjusts the initial assessment model according to the health assessment results of the enterprise and the actual health of the enterprise to obtain an assessment model that can accurately assess the health of the enterprise, thereby improving the accuracy of the assessment value of the enterprise health by the assessment model; in addition, when it is necessary to conduct health assessment on a large number of enterprises, there is no need to manually analyze the large amount of operating data of the enterprise. It is only necessary to use the adjusted target assessment model for health assessment, which greatly improves the efficiency of the enterprise's health assessment.

[0134] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0135] Based on the same inventive concept, the embodiment of the present application also provides a device for constructing an evaluation model for implementing the method for constructing the evaluation model involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the device for constructing one or more evaluation models provided below can refer to the limitations of the method for constructing the evaluation model above, and will not be repeated here.

[0136] In an exemplary embodiment, as shown in FIG9 , a device for constructing an evaluation model is provided, comprising: an evaluation module 10, a determination module 11 and an adjustment module 12, wherein:

[0137] The evaluation module 10 is used to input the operation data of multiple enterprises into the initial evaluation model to perform health evaluation and obtain the health degree.

[0138] The determination module 11 is used to determine the evaluation result according to the health level and the preset health standard.

[0139] The adjustment module 12 is used to adjust the initial assessment model according to the assessment results and the actual health of each enterprise to obtain a target assessment model.

[0140] In an exemplary embodiment, the above-mentioned evaluation result includes the evaluation health of each enterprise, and the above-mentioned adjustment module includes: a verification unit and an adjustment unit, wherein:

[0141] The verification unit is specifically used to verify the consistency between the assessed health and the actual health of each enterprise and obtain the verification results;

[0142] The adjustment unit is specifically used to adjust the initial evaluation model according to the verification result to obtain the target evaluation model.

[0143] In an exemplary embodiment, the above-mentioned verification unit is specifically used to verify the consistency of the assessed health and actual health of each enterprise to obtain the intermediate verification results of each enterprise; and determine the verification results based on the preset verification success conditions and the intermediate verification results of each enterprise.

[0144] In an exemplary embodiment, the above-mentioned verification unit is specifically used to calculate the chi-square statistic for each enterprise based on the assessed health of the enterprise and the actual health of the enterprise to obtain the chi-square distribution parameters; and determine the degree of consistency between the assessed health of the enterprise and the actual health of the enterprise based on the chi-square distribution parameters.

[0145] In an exemplary embodiment, the adjustment unit is specifically used to determine the initial evaluation model as the target evaluation model if the verification result indicates that the verification has passed; if the verification result indicates that the verification has not passed, adjust the weight parameters in the initial evaluation model to obtain the target evaluation model.

[0146] In an exemplary embodiment, the above device further includes: an acquisition module and an extraction module, wherein:

[0147] An acquisition module is used to obtain the operation data of multiple enterprises;

[0148] The extraction module is used to extract the index characteristics of the operation data of each enterprise and obtain the index data of each enterprise;

[0149] The above-mentioned evaluation module is also used to input the indicator data of each enterprise into the initial evaluation model for health evaluation to obtain the health degree.

[0150] Each module in the above-mentioned evaluation model construction device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0151] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG1. ​​The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the operation data of the enterprise. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for constructing an evaluation model is implemented.

[0152] Those skilled in the art will understand that the structure shown in FIG. 1 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0154] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0155] Determine the assessment results based on health status and preset health standards;

[0156] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0157] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0158] Verify the consistency between the assessed health and actual health of each enterprise and obtain verification results;

[0159] The initial evaluation model is adjusted according to the verification results to obtain the target evaluation model.

[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0161] Verify the consistency between the assessed health and actual health of each enterprise and obtain the intermediate verification results of each enterprise;

[0162] The verification results are determined based on the preset verification success conditions and the intermediate verification results of each enterprise.

[0163] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0164] For each enterprise, the chi-square statistic is calculated based on the enterprise's assessed health and the enterprise's actual health, and the chi-square distribution parameters are obtained;

[0165] The degree of consistency between the assessed health of the enterprise and the actual health of the enterprise is determined based on the chi-square distribution parameter.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] If the verification result indicates that the verification is passed, the initial evaluation model is determined as the target evaluation model;

[0168] If the verification result indicates that the verification has not passed, the weight parameters in the initial evaluation model are adjusted to obtain the target evaluation model.

[0169] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0170] Obtain operating data of multiple enterprises;

[0171] Extract indicator features from the operating data of each enterprise to obtain the indicator data of each enterprise;

[0172] Input the operating data of multiple enterprises into the initial assessment model for health assessment to obtain the health degree, including:

[0173] Input the indicator data of each enterprise into the initial assessment model for health assessment to obtain the health degree.

[0174] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0175] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0176] Determine the assessment results based on health status and preset health standards;

[0177] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0178] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0179] Verify the consistency between the assessed health and actual health of each enterprise and obtain verification results;

[0180] The initial evaluation model is adjusted according to the verification results to obtain the target evaluation model.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0182] Verify the consistency between the assessed health and actual health of each enterprise and obtain the intermediate verification results of each enterprise;

[0183] The verification results are determined based on the preset verification success conditions and the intermediate verification results of each enterprise.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0185] For each enterprise, the chi-square statistic is calculated based on the enterprise's assessed health and the enterprise's actual health, and the chi-square distribution parameters are obtained;

[0186] The degree of consistency between the assessed health of the enterprise and the actual health of the enterprise is determined based on the chi-square distribution parameter.

[0187] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0188] If the verification result indicates that the verification is passed, the initial evaluation model is determined as the target evaluation model;

[0189] If the verification result indicates that the verification has not passed, the weight parameters in the initial evaluation model are adjusted to obtain the target evaluation model.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0191] Obtain operating data of multiple enterprises;

[0192] Extract indicator features from the operating data of each enterprise to obtain the indicator data of each enterprise;

[0193] Input the operating data of multiple enterprises into the initial assessment model for health assessment to obtain the health degree, including:

[0194] Input the indicator data of each enterprise into the initial assessment model for health assessment to obtain the health degree.

[0195] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0196] Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree;

[0197] Determine the assessment results based on health status and preset health standards;

[0198] The initial assessment model is adjusted according to the assessment results and the actual health of each enterprise to obtain the target assessment model.

[0199] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0200] Verify the consistency between the assessed health and actual health of each enterprise and obtain verification results;

[0201] The initial evaluation model is adjusted according to the verification results to obtain the target evaluation model.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] Verify the consistency between the assessed health and actual health of each enterprise and obtain the intermediate verification results of each enterprise;

[0204] The verification results are determined based on the preset verification success conditions and the intermediate verification results of each enterprise.

[0205] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0206] For each enterprise, the chi-square statistic is calculated based on the enterprise's assessed health and the enterprise's actual health, and the chi-square distribution parameters are obtained;

[0207] The degree of consistency between the assessed health of the enterprise and the actual health of the enterprise is determined based on the chi-square distribution parameter.

[0208] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0209] If the verification result indicates that the verification is passed, the initial evaluation model is determined as the target evaluation model;

[0210] If the verification result indicates that the verification has not passed, the weight parameters in the initial evaluation model are adjusted to obtain the target evaluation model.

[0211] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0212] Obtain operating data of multiple enterprises;

[0213] Extract indicator features from the operating data of each enterprise to obtain the indicator data of each enterprise;

[0214] Input the operating data of multiple enterprises into the initial assessment model for health assessment to obtain the health degree, including:

[0215] Input the indicator data of each enterprise into the initial assessment model for health assessment to obtain the health degree.

[0216] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0217] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0218] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0219] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for constructing an evaluation model, characterized in that: The method comprises: Input the operating data of multiple enterprises into the initial assessment model to conduct health assessment and obtain the health degree; Determining an assessment result based on the health level and the preset health standard; The initial assessment model is adjusted according to the assessment results and the actual health of each of the enterprises to obtain a target assessment model.

2. The method according to claim 1, characterized in that The evaluation result includes the evaluation health of each of the enterprises, and the initial evaluation model is adjusted according to the evaluation result and the actual health of each of the enterprises to obtain a target evaluation model, including: Verify the consistency between the assessed health and the actual health of each enterprise to obtain verification results; The initial evaluation model is adjusted according to the verification result to obtain the target evaluation model.

3. The method according to claim 2, characterized in that The consistency verification of the assessed health and the actual health of each enterprise is performed to obtain the verification results, including: Conduct consistency verification on the assessed health and actual health of each of the enterprises, and obtain intermediate verification results for each of the enterprises; The verification result is determined according to the preset verification success condition and the intermediate verification results of each of the enterprises.

4. The method according to claim 3, characterized in that The consistency verification of the assessed health and the actual health of each enterprise is performed to obtain an intermediate verification result for each enterprise, including: For each of the enterprises, a chi-square statistic is calculated according to the assessed health of the enterprise and the actual health of the enterprise to obtain a chi-square distribution parameter; The degree of consistency between the assessed health of the enterprise and the actual health of the enterprise is determined based on the chi-square distribution parameter.

5. The method according to claim 2, characterized in that: The step of adjusting the initial evaluation model according to the verification result to obtain the target evaluation model includes: If the verification result indicates that the verification is passed, the initial evaluation model is determined as the target evaluation model; If the verification result indicates that the verification has not passed, the weight parameters in the initial evaluation model are adjusted to obtain the target evaluation model.

6. The method according to claim 1, characterized in that The method further comprises: Acquiring operation data of the plurality of enterprises; Extracting index features from the operating data of each of the enterprises to obtain index data of each of the enterprises; The operation data of multiple enterprises are input into the initial assessment model to perform health assessment to obtain health status, including: The indicator data of each enterprise is input into the initial assessment model to conduct health assessment and obtain the health degree.

7. A device for constructing an evaluation model, characterized in that: The device comprises: An assessment module is used to input the operating data of multiple enterprises into the initial assessment model for health assessment to obtain the health degree; A determination module, used to determine an evaluation result according to the health degree and a preset health standard; The adjustment module is used to adjust the initial assessment model according to the assessment result and the actual health of each enterprise to obtain a target assessment model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images