A method and system for enterprise evaluation based on big data

By collecting, classifying, calculating, and analyzing enterprise information and operational data, and using big data technology to generate enterprise trust ratings, the problem of users finding it difficult to obtain accurate enterprise evaluations has been solved, achieving both accuracy and comprehensiveness in enterprise evaluations.

CN117787782BActive Publication Date: 2024-11-01GREATER BAY AREA SCI & TECH INNOVATION SERVICE CENT (GUANGZHOU) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311786683.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-22
Publication Date
2024-11-01
Estimated Expiration
2043-12-22

AI Technical Summary

Technical Problem

In a highly competitive market, users find it difficult to obtain accurate information about corporate culture and trustworthiness through existing online reviews and company websites, resulting in biased evaluation information.

Method used

By collecting enterprise information and operational data, classifying and organizing them, performing statistical calculations, and using association analysis, sequence pattern analysis, and cluster analysis methods for distributed storage and analysis, enterprise trust scores are generated and displayed on the cloud platform for users to view.

Benefits of technology

It provides accurate and real-time enterprise evaluation information, helping users understand the company's business status and employee evaluations, thus improving the accuracy and comprehensiveness of the evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117787782B_ABST
    Figure CN117787782B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for evaluating an enterprise based on big data, and belongs to the field of data processing technology. The present invention solves the problem that existing users have a relatively one-sided understanding of the information of target enterprises. By collecting the enterprise information and operating data of the target enterprise, and checking and classifying the enterprise information, the turnover, annual output value growth value, R&D investment funds, R&D investment ratio, and the amount of completed projects of the target enterprise are calculated; and the sorted enterprise information and operating data are distributedly stored, and analyzed based on any one of the association analysis method, sequence pattern analysis method, and cluster analysis method, so as to obtain an overall evaluation of the target enterprise; and then the overall evaluation is displayed on the cloud platform, and the user logs in to the cloud platform to view the business status and employee evaluation of the target enterprise, judge the trustworthiness of the target enterprise, and thus provide users with accurate information on the target enterprise.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an enterprise evaluation method and system based on big data. Background Art

[0002] In the business field, trust refers to the degree of trust that customers, shareholders, employees and other parties have in a company. The trust of a company refers to the outside world's confidence in whether a company can fulfill its promised obligations and claims, whether it has good business ethics and social responsibility, and the company's performance and future development. The trust of a company is vital to its business, so in corporate strategy and business management, it is crucial to establish and maintain the trust of the company. Trust is the foundation of all relationships and the most difficult part of management. For an organization, a high degree of trust can improve employee satisfaction and work efficiency. At the same time, a high degree of trust is the basis for quickly establishing teamwork.

[0003] However, in a highly competitive market, users need to understand corporate culture and corporate trust, but they can only learn about it through online reviews and corporate websites, which results in relatively one-sided corporate evaluation information and makes it difficult to provide users with accurate corporate evaluation information.

[0004] Therefore, the existing needs are not met, and we propose an enterprise evaluation method and system based on big data. Summary of the invention

[0005] The purpose of the present invention is to provide an enterprise evaluation method and system based on big data, which collects enterprise information and business data of target enterprises, verifies and classifies the enterprise information, calculates the business data, and performs distributed storage; analyzes it based on any one of association analysis, sequence pattern analysis and cluster analysis, so as to obtain an overall evaluation of the target enterprise; and then displays the overall evaluation on a cloud platform. Users can log in to the cloud platform to view the business status and employee evaluation of the target enterprise and judge the trustworthiness of the target enterprise, thereby providing users with accurate evaluation information of the target enterprise in real time, solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for enterprise evaluation based on big data, comprising the following steps:

[0007] S1. Collect the target enterprise’s enterprise information and operating data as the big data basis for enterprise evaluation;

[0008] S2. Classify and organize the collected enterprise information and operating data of the target enterprise, thereby obtaining the original data organized by the target enterprise;

[0009] S3. Statistics and calculations are performed on the sorted enterprise information and operating data to obtain the classified enterprise information and operating data of the target enterprise;

[0010] S4. Distribute and store the classified enterprise information and business data, and analyze the enterprise information and business data of the target enterprise through an analytical method, thereby obtaining the trust results of the target enterprise;

[0011] S5. Display the trust results of the target enterprise.

[0012] Furthermore, the enterprise information in S1 includes: the enterprise's registration time, registered capital, business scope of the target enterprise, the number of employees paying social insurance, the starting time of the enterprise's employees paying social insurance, the details of the funds paid by the enterprise's employees for social insurance, the details of the monthly social insurance payment dates, the target enterprise's legal person integrity information, the educational background of the employees and employee evaluations; the operating data includes: the target enterprise's turnover, the target enterprise's annual output value growth value, R&D investment funds, R&D investment ratio, and the amount of projects completed by the target enterprise.

[0013] Furthermore, in S2-S3, the enterprise information and operating data of the target enterprise are classified and sorted, and the sorted enterprise information and operating data are counted and calculated, specifically:

[0014] S2-3.1. Categorize and count the enterprise information of the target enterprises and verify the accuracy of each piece of information;

[0015] S2-3.2. Classify and count the operating data of the target enterprise, and calculate the target enterprise's turnover, annual output value growth, R&D investment funds, R&D investment ratio, and the amount of completed projects, and save the calculated results;

[0016] S2-3.3. Clean the target enterprise's corporate information and operating data, and delete invalid and duplicate data; modify the target enterprise's corporate data after data cleaning, correct identifiable errors in the corporate data, and obtain the organized corporate data of the target enterprise.

[0017] Furthermore, the classified enterprise information and business data are stored in a distributed manner in S4, specifically:

[0018] The enterprise information and operating data of the target enterprise in distributed storage are analyzed by any one of association analysis, sequence pattern analysis and cluster analysis to obtain an overall evaluation of the target enterprise.

[0019] Furthermore, the enterprise information in S1 obtains enterprise evaluation including: employees register and log in using their ID numbers, comparing the employee ID numbers with the enterprise information obtained from the social security department to determine whether the employee is currently working or has worked in the enterprise, and employees who pass the test rate and evaluate the enterprise. The scope of employees' evaluation of the enterprise includes: salary and bonuses, environment and atmosphere, development opportunities, overtime pressure and other benefits.

[0020] Furthermore, the classified enterprise information and business data are distributedly stored, and the enterprise information and business data of the target enterprise are analyzed by an analytical method, thereby obtaining the trust results of the target enterprise, including:

[0021] Detect multiple data types and formats of classified corporate information and operational data;

[0022] Distribute and store classified enterprise information and business data based on multiple data types and data formats;

[0023] Obtain sample data from the enterprise information and operating data of each category, and calculate the average value of the sample data from the enterprise information and operating data of the category;

[0024] Determine the deviation value of each data item in the sample data of each category of enterprise information and operating data, and determine the data deviation degree of the sample data in the enterprise information and operating data of the category according to the deviation value;

[0025] Determine the data evaluation tolerance value according to the data deviation of the sample data in the enterprise information and operating data of each category and the average value of the sample data in the enterprise information and operating data of the category;

[0026] Judging the sample data in the enterprise information and business data of each category according to the data evaluation tolerance value of the sample data in the enterprise information and business data of that category;

[0027] According to the judgment result, the first data item greater than or equal to the data evaluation tolerance value is confirmed as high-trust data, and the second data item less than the data evaluation tolerance value is confirmed as low-trust data;

[0028] Integrate and compile statistics on the high-trust data of each category of enterprise information and sample data in the business data to obtain the integration results;

[0029] Based on the integration results, the high-trust data of the sample data in each category of enterprise information and business data is evaluated in terms of benefits, integrity, production capacity, and cost through analytical methods to obtain the evaluation scores of each dimension;

[0030] Calculate the final score of the high-trust data of the sample data in the enterprise information and business data of each category according to the evaluation score of each dimension of the high-trust data of the sample data in the enterprise information and business data of that category and the weight of the dimension;

[0031] The trustworthiness of the target enterprise is determined based on the final score of the high-trust data of the sample data in each category of enterprise information and operating data.

[0032] Furthermore, it also includes:

[0033] Acquire multiple enterprise evaluation indicators and evaluation content of each enterprise evaluation indicator, and determine the emphasis of each enterprise evaluation indicator according to the evaluation content;

[0034] Determine the matching degree of the target enterprise to each enterprise evaluation index based on the emphasis of each enterprise evaluation index and the main business parameters of the target enterprise;

[0035] Obtaining business requirement information of the target enterprise for the business related to the focus of each enterprise evaluation indicator, and determining a plurality of discrete features for the enterprise evaluation indicator and a standard value of each discrete feature according to the business requirement information;

[0036] Get the current evaluation value of each enterprise evaluation indicator in each discrete feature, and calculate the recommendation index of each enterprise evaluation indicator based on the current evaluation value of each user in each discrete feature, multiple discrete features for the enterprise evaluation indicator, the standard value of each discrete feature, and the matching degree of the target enterprise for each enterprise evaluation indicator:

[0037]

[0038] Among them, F i Expressed as the recommendation index of the i-th enterprise evaluation index, Q i It is represented as the matching degree of the target enterprise to the evaluation index of the i-th enterprise, N is represented as the number of discrete features, j is represented as the j-th discrete feature, P ij It is expressed as the current evaluation value of the i-th enterprise evaluation index at the j-th discrete feature, P sj Denotes the standard value of the jth discrete feature, D i It is represented as the subjective factor influencing factor of the i-th enterprise evaluation index, e is represented as a natural constant with a value of 2.72, S i It is expressed as the universality coefficient of the evaluation index of the i-th enterprise, which is determined by historical evaluation. i It is expressed as the evaluation extensiveness coefficient of the i-th enterprise evaluation index, which is determined by the evaluation data type of the enterprise evaluation index. iIt is expressed as the evaluation limitation coefficient of the i-th enterprise evaluation index, which is determined by the limited evaluation scenario of the i-th enterprise evaluation index;

[0039] According to the recommendation index of each enterprise evaluation index, a target enterprise evaluation index that is greater than or equal to a preset recommendation reference value is selected, and the target enterprise evaluation index is used as a reference index for evaluating the target enterprise.

[0040] An enterprise evaluation system based on big data, comprising:

[0041] The data collection module is used to collect the enterprise information and operating data of the target enterprise, thereby providing data basis for enterprise evaluation;

[0042] The data processing unit is used to classify and sort the enterprise information and business data collected by the data collection module, and calculate various values ​​in the business data;

[0043] Distributed storage module, used for distributed storage of classified enterprise information and business data;

[0044] A data analysis module, which analyzes the enterprise information and business data in the distributed storage module based on any one of the methods of association analysis, sequence pattern analysis and cluster analysis;

[0045] The data display unit is used to display the corporate information, operating data and trust results of the target enterprise.

[0046] Furthermore, the data processing unit includes:

[0047] The data classification module is used to classify the target enterprise's enterprise information and classify it into enterprise content and employee content according to the difference in the enterprise information content;

[0048] The data calculation module is used to perform statistical calculations on the target enterprise's operating data to obtain the target enterprise's turnover and annual output value growth value, thereby determining whether the target enterprise is in a normal operating state;

[0049] The data processing module is used to delete and correct invalid information and erroneous data in the corporate information and operating data of the target enterprise to ensure the accuracy of the target enterprise data.

[0050] Furthermore, the data display unit includes:

[0051] A user login module is used to provide a web page login window for users, and the user login module unit is connected to the cloud platform via a wireless network;

[0052] The cloud platform is used to display the target enterprise's corporate information, operating data and trust results for users to browse, and the cloud platform is connected to the data collection module via a wireless network.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention collects the enterprise information and operating data of the target enterprise, verifies and classifies the enterprise information, calculates the target enterprise's turnover, annual output value growth, R&D investment funds, R&D investment ratio, and the amount of completed projects; and distributes the sorted enterprise information and operating data, analyzes them based on any one of association analysis, sequence pattern analysis and cluster analysis to obtain an overall evaluation of the target enterprise; and then displays the overall evaluation on the cloud platform, and users can log in to the cloud platform to view the target enterprise's business status and employee evaluations, judge the target enterprise's trustworthiness, and provide users with accurate evaluation information on the target enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a composition diagram of the enterprise evaluation system based on big data of the present invention;

[0056] Figure 2 This is a flow chart of the enterprise evaluation method based on big data of the present invention;

[0057] Figure 3 This is a flow chart of steps S2-S3 of the enterprise evaluation method based on big data of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] In order to solve the technical problem that in the current fiercely competitive market, users can only understand corporate culture and corporate trust through online reviews and corporate websites, which leads to the fact that the corporate evaluation information obtained is relatively one-sided and it is difficult to provide users with accurate corporate evaluation information, please refer to Figure 1-Figure 3 , this embodiment provides the following technical solutions:

[0060] A method for evaluating an enterprise based on big data comprises the following steps:

[0061] S1. Collect the target enterprise's corporate information and operating data as a big data basis for enterprise evaluation. In one embodiment, the target enterprise's corporate information can be collected through the National Enterprise Credit Information Publicity System, the China Securities Regulatory Commission, the Industry and Commerce Bureau, and the Social Security Department to obtain various information about the target enterprise. The target enterprise's operating data can be collected through the target enterprise's website and Juchao Information Network to query the company's annual report, financial statements, IPO progress / process, capital flow, etc. Based on the above method, the collected corporate information and operating data are used as the big data basis for enterprise evaluation.

[0062] S2. Classify and organize the collected enterprise information and business data of the target enterprise, thereby obtaining the organized original data of the target enterprise; in one embodiment, the collected enterprise information is classified by category, such as: the enterprise information is divided into: enterprise category and employee category, the enterprise category specifically includes: the enterprise's registration time, registered capital, business scope of the target enterprise, the number of enterprise employees paying social insurance, the starting time of enterprise employees paying social insurance, the details of the funds paid by enterprise employees for social insurance, and the details of the monthly social insurance payment dates; the employee category specifically includes: the target enterprise's legal person integrity information, the employees' educational background composition and employee evaluation; the collected business data is classified by category, such as: the business data is divided into: operation category and achievement category, the operation category specifically includes: the target enterprise's turnover, the target enterprise's annual output value growth value, R&D investment funds, and the R&D investment ratio; the achievement category specifically includes: the target enterprise's completed project amount, and the collected enterprise information and business data are classified and organized based on the above operations.

[0063] S3. Statistics and calculations are performed on the sorted enterprise information and business data to obtain the classified enterprise information and business data of the target enterprise. In one embodiment, the target enterprise turnover and annual output value growth value of the target enterprise are collected, and the annual total turnover and annual output value growth value of the target enterprise in the past five years are calculated to determine whether the target enterprise's business conditions in the past five years are normal. If the annual total turnover and annual output value growth value of the target enterprise are in a steady growth trend, a continuous growth trend or a fluctuating growth trend, it is determined that the target enterprise is in a stable development state in the near future. If the annual total turnover and annual output value growth value of the target enterprise are in a continuous growth trend in the near five years, it is determined that the target enterprise is in a rapid development state in the near future. If the annual total turnover and annual output value growth value of the target enterprise are in a fluctuating growth trend in the near five years, it is determined that the target enterprise is in an unstable development state in the near future, thereby providing users with a reference for enterprise evaluation.

[0064] S4. Distribute and store the classified enterprise information and business data, and analyze the enterprise information and business data of the target enterprise through an analysis method to obtain the trust result of the target enterprise. In one embodiment, the enterprise information and business data are analyzed through any one of the association analysis method, the sequence pattern analysis method and the cluster analysis method, and the enterprise information and business data of the target enterprise are intuitively displayed using a multi-dimensional visualization display method, showing a more intuitive overall evaluation result to the user. The user can judge whether the current enterprise is in a normal development and rising state by browsing the enterprise information, business data and evaluation results of the target enterprise.

[0065] S5. Display the trust results of the target enterprise. In one embodiment, the user can browse the various data and evaluation results of the target enterprise by logging into the cloud platform to ensure the current business status and evaluation information of the enterprise.

[0066] The enterprise information in S1 includes: the enterprise's registration time, the target enterprise's business scope, the starting time of the enterprise's employees' social security payments, the details of the funds paid by the enterprise's employees for social security, the details of the monthly social security payment dates, the target enterprise's legal person integrity information and employee evaluations; the operating data includes: the target enterprise's turnover, the target enterprise's annual output value growth value, R&D investment funds, R&D investment ratio, and the amount of projects completed by the target enterprise.

[0067] In S2-S3, the target enterprise's enterprise information and operating data are classified and sorted, and the sorted enterprise information and operating data are counted and calculated, specifically:

[0068] S2-3.1. Classify and count the enterprise information of the target enterprise, and verify the accuracy of each piece of information; Continuing with the above embodiment, by dividing the enterprise information into enterprise category and employee category, and dividing the business data into business category and achievement category, the user can specifically select a certain data of his own needs for browsing and viewing, thereby optimizing the visibility of the target enterprise data display and improving the efficiency of the user's understanding of the target enterprise.

[0069] S2-3.2. Classify and count the operating data of the target enterprise, and calculate the target enterprise's turnover, annual output value growth, R&D investment, R&D investment ratio, and the amount of completed projects, and save the calculated results; following the above embodiment, by calculating the annual turnover and annual output value growth of the target enterprise in the past five years, and combining the calculation results, the operating status of the target enterprise in the past five years is judged; in addition, the average annual income of employees in the past five years is calculated to intuitively understand the salary and benefits of the target enterprise; such as: in the past five years, the annual total turnover and annual output value growth of the target enterprise are in a continuous upward trend, indicating that the target enterprise is in a rapid development state in the near future; at the same time, in the past five years, the average annual income of employees has increased year by year, indicating that the target enterprise has been in an upward stage in the past five years, and the salaries of employees are in a state of continuous growth. Based on this result, the corporate image and trust of the target enterprise are improved, and the impression of the target enterprise on users is improved.

[0070] S2-3.3. Clean the target enterprise's corporate information and operating data, and delete invalid and duplicate data; modify the target enterprise's corporate data after data cleaning, correct identifiable errors in the corporate data, and obtain the organized corporate data of the target enterprise.

[0071] S4 stores the classified enterprise information and business data in a distributed manner, specifically:

[0072] The enterprise information and operating data of the target enterprise in distributed storage are analyzed by any one of association analysis, sequence pattern analysis and cluster analysis to obtain an overall evaluation of the target enterprise.

[0073] The enterprise evaluation obtained through enterprise information in S1 includes: employees register and log in using their ID numbers, and compare their ID numbers with the enterprise information obtained from the social security department to determine whether the employee is currently working or has worked in the enterprise. Employees who pass the test will score and evaluate the enterprise. The scope of employees' evaluation of the enterprise includes: salary and bonuses, environmental atmosphere, development opportunities, overtime pressure and other benefits.

[0074] A big data-based enterprise evaluation system, the enterprise evaluation system comprising:

[0075] The data collection module is used to collect the corporate information and operating data of the target enterprise, thereby providing a data basis for enterprise evaluation; specifically, the corporate information and operating data of the target enterprise are collected through the data collection module to ensure the user's comprehensive understanding of the target enterprise, optimize the user's understanding needs, and enhance the target enterprise's visibility and corporate culture.

[0076] The data processing unit is used to classify and organize the enterprise information and business data collected by the data collection module, and calculate the various values ​​in the business data; specifically, the data processing unit classifies various information and data to ensure the comprehensiveness and pertinence of the display of various information and data, so that users can query the information they need to know according to their own needs.

[0077] The distributed storage module is used to distribute the classified enterprise information and business data. Specifically, the distributed storage adopts an extensible structure, uses multiple storage servers to share the storage load, and uses the location server to locate the storage information. It not only improves the reliability, availability and access efficiency of the enterprise evaluation system, but also facilitates the expansion of data content.

[0078] A data analysis module, which analyzes the enterprise information and business data in the distributed storage module based on any one of the methods of association analysis, sequence pattern analysis and cluster analysis;

[0079] The data display unit is used to display the corporate information, operating data and trust results of the target enterprise.

[0080] The data processing unit includes:

[0081] The data classification module is used to classify the enterprise information of the target enterprise, and classify it into enterprise content and employee content according to the different contents of the enterprise information; specifically, by dividing the enterprise information into: enterprise category and employee category, such as: the enterprise category includes: the registration time of the enterprise, the business scope of the target enterprise, the starting time of the enterprise employees' social insurance payment, the details of the funds paid by the enterprise employees for social insurance, and the details of the monthly social insurance payment dates; among them, the registration time and business scope of the enterprise can enable users to understand the operating years and content of the target enterprise, so as to determine whether the current enterprise is in a normal operating state; the social insurance payment details and payment date details can enable users to understand the treatment of the target enterprise for employees, and whether it is paid monthly Pay on time to further determine whether the current business operation is normal; for example, the employee category includes: the target enterprise's legal person integrity information and employee evaluations. The above content can allow users to intuitively understand the current enterprise's salary and benefits and employees' evaluations of the enterprise, which can provide users with a deeper foundation for intuitively understanding the enterprise's evaluation information; the business data is divided into: business category and results category, such as: the business category includes: the target enterprise's turnover, the target enterprise's annual output value growth value, the above content can allow users to understand whether the current enterprise's operating status is normal; the results category includes: the target enterprise's technical research and development level and scientific and technological achievements, the target enterprise's completed projects, the above content can allow users to understand the current enterprise's business scope.

[0082] The data calculation module is used to perform statistical calculations on the target enterprise's operating data to obtain the target enterprise's turnover and annual output value growth value, thereby judging whether the target enterprise is in a normal operating state; specifically, by calculating the target enterprise's annual turnover and annual output value growth value, combined with the calculation results, the target enterprise's operating status in the past five years is judged to prevent shell companies from mixing in, thereby improving the efficiency of users' understanding of the actual situation of the enterprise.

[0083] The data processing module is used to delete and correct invalid information and erroneous data in the corporate information and operating data of the target enterprise to ensure the accuracy and timeliness of the target enterprise data.

[0084] The data display unit includes:

[0085] A user login module is used to provide a web page login window for users, and the user login module unit is connected to the cloud platform via a wireless network;

[0086] The cloud platform is used to display the target enterprise's corporate information, operating data and trust results for users to browse, and the cloud platform is connected to the data collection module via a wireless network.

[0087] Working principle: By collecting the corporate information and business data of the target enterprise, checking and classifying the corporate information, calculating the business data and performing distributed storage; analyzing it based on any of the methods such as association analysis, sequence pattern analysis and cluster analysis, so as to obtain an overall evaluation of the target enterprise; then displaying the overall evaluation on the cloud platform, users can log in to the cloud platform to view the target enterprise's business status and employee evaluation, and judge the target enterprise's trust evaluation, thereby providing users with accurate evaluation information of the target enterprise.

[0088] In one embodiment, the classified enterprise information and business data are distributedly stored, and the enterprise information and business data of the target enterprise are analyzed by an analysis method, thereby obtaining the trust results of the target enterprise, including:

[0089] Detect multiple data types and formats of classified corporate information and operational data;

[0090] Distribute and store classified enterprise information and business data based on multiple data types and data formats;

[0091] Obtain sample data from the enterprise information and operating data of each category, and calculate the average value of the sample data from the enterprise information and operating data of the category;

[0092] Determine the deviation value of each data item in the sample data of each category of enterprise information and operating data, and determine the data deviation degree of the sample data in the enterprise information and operating data of the category according to the deviation value;

[0093] Determine the data evaluation tolerance value according to the data deviation of the sample data in the enterprise information and operating data of each category and the average value of the sample data in the enterprise information and operating data of the category;

[0094] Judging the sample data in the enterprise information and business data of each category according to the data evaluation tolerance value of the sample data in the enterprise information and business data of that category;

[0095] According to the judgment result, the first data item greater than or equal to the data evaluation tolerance value is confirmed as high-trust data, and the second data item less than the data evaluation tolerance value is confirmed as low-trust data;

[0096] Integrate and compile statistics on the high-trust data of each category of enterprise information and sample data in the business data to obtain the integration results;

[0097] Based on the integration results, the high-trust data of the sample data in each category of enterprise information and business data is evaluated in terms of benefits, integrity, production capacity, and cost through analytical methods to obtain the evaluation scores of each dimension;

[0098] Calculate the final score of the high-trust data of the sample data in the enterprise information and business data of each category according to the evaluation score of each dimension of the high-trust data of the sample data in the enterprise information and business data of that category and the weight of the dimension;

[0099] The trustworthiness of the target enterprise is determined based on the final score of the high-trust data of the sample data in each category of enterprise information and operating data.

[0100] In this embodiment, the data deviation is represented by the data jump bias of each data item in the sample data of each category of enterprise information and business data;

[0101] In this embodiment, the data evaluation tolerance value is expressed as an evaluation tolerance threshold for whether the data is authentic and valid.

[0102] The beneficial effects of the above technical solution are: invalid data in the sample data of each category of corporate information and business data can be quickly and accurately excluded to ensure the accuracy of the sample data, laying the foundation for the subsequent trust evaluation of the target enterprise and improving practicality. Furthermore, by performing multi-dimensional score evaluation on the high-trust data of the sample data in each category of corporate information and business data, the trust evaluation results of the target enterprise can be comprehensively determined to ensure the reliability and intuitiveness of the evaluation results.

[0103] In one embodiment, it further includes:

[0104] Acquire multiple enterprise evaluation indicators and evaluation content of each enterprise evaluation indicator, and determine the emphasis of each enterprise evaluation indicator according to the evaluation content;

[0105] Determine the matching degree of the target enterprise to each enterprise evaluation index based on the emphasis of each enterprise evaluation index and the main business parameters of the target enterprise;

[0106] Obtaining business requirement information of the target enterprise for the business related to the focus of each enterprise evaluation indicator, and determining a plurality of discrete features for the enterprise evaluation indicator and a standard value of each discrete feature according to the business requirement information;

[0107] Get the current evaluation value of each enterprise evaluation indicator in each discrete feature, and calculate the recommendation index of each enterprise evaluation indicator based on the current evaluation value of each user in each discrete feature, multiple discrete features for the enterprise evaluation indicator, the standard value of each discrete feature, and the matching degree of the target enterprise for each enterprise evaluation indicator:

[0108]

[0109] Among them, F i Expressed as the recommendation index of the i-th enterprise evaluation index, Q i It is represented as the matching degree of the target enterprise to the evaluation index of the i-th enterprise, N is represented as the number of discrete features, j is represented as the j-th discrete feature, P ij It is expressed as the current evaluation value of the i-th enterprise evaluation index at the j-th discrete feature, P sj Denotes the standard value of the jth discrete feature, D i It is represented as the subjective factor influencing factor of the i-th enterprise evaluation index, e is represented as a natural constant with a value of 2.72, S i It is expressed as the universality coefficient of the evaluation index of the i-th enterprise, which is determined by historical evaluation. i It is expressed as the evaluation extensiveness coefficient of the i-th enterprise evaluation index, which is determined by the evaluation data type of the enterprise evaluation index. i It is expressed as the evaluation limitation coefficient of the i-th enterprise evaluation index, which is determined by the limited evaluation scenario of the i-th enterprise evaluation index;

[0110] According to the recommendation index of each enterprise evaluation index, a target enterprise evaluation index that is greater than or equal to a preset recommendation reference value is selected, and the target enterprise evaluation index is used as a reference index for evaluating the target enterprise.

[0111] The beneficial effects of the above technical solution are: by calculating the recommendation coefficient of each enterprise evaluation indicator, the compatibility between the reference evaluation indicator and the target enterprise can be guaranteed, thereby ensuring the objectivity and accuracy of the subsequent evaluation results for the target enterprise, while providing accurate reference indicators for evaluators and improving user experience and practicality.

[0112] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0113] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for enterprise evaluation based on big data, characterized in that: The following steps are involved: S1. Collect the target enterprise’s enterprise information and operating data as the big data basis for enterprise evaluation; S2. Classify and organize the collected enterprise information and operating data of the target enterprise, thereby obtaining the organized original data of the target enterprise; S3. Statistics and calculations are performed on the sorted enterprise information and operating data to obtain the classified enterprise information and operating data of the target enterprise; S4. Distribute and store the classified enterprise information and business data, and analyze the enterprise information and business data of the target enterprise through an analytical method, thereby obtaining the trust results of the target enterprise; The classified enterprise information and business data are distributedly stored, and the enterprise information and business data of the target enterprise are analyzed through analytical methods to obtain the trust results of the target enterprise, including: Detect multiple data types and formats of classified corporate information and operational data; Distribute and store classified enterprise information and business data based on multiple data types and data formats; Obtain sample data from the enterprise information and operating data of each category, and calculate the average value of the sample data from the enterprise information and operating data of the category; Determine the deviation value of each data item in the sample data of each category of enterprise information and operating data, and determine the data deviation degree of the sample data in the enterprise information and operating data of the category according to the deviation value; Determine the data evaluation tolerance value according to the data deviation of the sample data in the enterprise information and operating data of each category and the average value of the sample data in the enterprise information and operating data of the category; Judging the sample data in the enterprise information and business data of each category according to the data evaluation tolerance value of the sample data in the enterprise information and business data of that category; According to the judgment result, the first data item greater than or equal to the data evaluation tolerance value is confirmed as high-trust data, and the second data item less than the data evaluation tolerance value is confirmed as low-trust data; Integrate and compile statistics on the high-trust data of each category of enterprise information and sample data in the business data to obtain the integration results; Based on the integration results, the high-trust data of the sample data in each category of enterprise information and business data is evaluated in terms of benefits, integrity, production capacity, and cost through analytical methods to obtain the evaluation scores of each dimension; Calculate the final score of the high-trust data of the sample data in the enterprise information and business data of each category according to the evaluation score of each dimension of the high-trust data of the sample data in the enterprise information and business data of that category and the weight of the dimension; Determine the trustworthiness of the target enterprise based on the final score of the high-trustworthiness data of the sample data in each category of enterprise information and business data; The S4 stores the classified enterprise information and business data in a distributed manner, specifically: Analyze the enterprise information and business data of the target enterprise in distributed storage by any one of association analysis, sequence pattern analysis and cluster analysis to obtain an overall evaluation of the target enterprise; S5. Display the trust results of the target enterprise; Also includes: Acquire multiple enterprise evaluation indicators and evaluation content of each enterprise evaluation indicator, and determine the emphasis of each enterprise evaluation indicator according to the evaluation content; Determine the matching degree of the target enterprise to each enterprise evaluation index based on the emphasis of each enterprise evaluation index and the main business parameters of the target enterprise; Obtaining business requirement information of the target enterprise for the business related to the focus of each enterprise evaluation indicator, and determining a plurality of discrete features for the enterprise evaluation indicator and a standard value of each discrete feature according to the business requirement information; Get the current evaluation value of each enterprise evaluation indicator in each discrete feature, and calculate the recommendation index of each enterprise evaluation indicator based on the current evaluation value of each user in each discrete feature, multiple discrete features for the enterprise evaluation indicator, the standard value of each discrete feature, and the matching degree of the target enterprise for each enterprise evaluation indicator: Among them, F i Expressed as the recommendation index of the i-th enterprise evaluation index, Q i It is represented as the matching degree of the target enterprise to the evaluation index of the i-th enterprise, N is represented as the number of discrete features, j is represented as the j-th discrete feature, P ij It is expressed as the current evaluation value of the i-th enterprise evaluation index at the j-th discrete feature, P sj Denotes the standard value of the jth discrete feature, D i It is represented as the subjective factor influencing factor of the i-th enterprise evaluation index, e is represented as a natural constant with a value of 2.72, S i It is expressed as the universality coefficient of the evaluation index of the i-th enterprise, which is determined by historical evaluation. i It is expressed as the evaluation extensiveness coefficient of the i-th enterprise evaluation index, which is determined by the evaluation data type of the enterprise evaluation index. i It is expressed as the evaluation limitation coefficient of the i-th enterprise evaluation index, which is determined by the limited evaluation scenario of the i-th enterprise evaluation index; According to the recommendation index of each enterprise evaluation index, a target enterprise evaluation index that is greater than or equal to a preset recommendation reference value is selected, and the target enterprise evaluation index is used as a reference index for evaluating the target enterprise.

2. The enterprise evaluation method based on big data according to claim 1, characterized in that: The enterprise information in S1 includes: the enterprise's registration time, registered capital, business scope of the target enterprise, the number of employees paying social insurance, the starting time of social insurance payment for employees, the details of funds paid by employees, the details of monthly social insurance payment dates, the target enterprise's legal person integrity information, the educational background of employees and employee evaluations; the operating data includes: the target enterprise's turnover, the target enterprise's annual output value growth value, R&D investment funds, R&D investment ratio, and the amount of projects completed by the target enterprise.

3. The enterprise evaluation method based on big data according to claim 1 is characterized by: In S2-S3, the enterprise information and operating data of the target enterprise are classified and sorted, and the sorted enterprise information and operating data are counted and calculated, specifically: S2-3.

1. Categorize and count the enterprise information of the target enterprises and verify the accuracy of each piece of information; S2-3.

2. Classify and count the operating data of the target enterprise, and calculate the target enterprise's turnover, annual output value growth, R&D investment funds, R&D investment ratio, and the amount of completed projects, and save the calculated results; S2-3.

3. Clean the target enterprise’s corporate information and business data and delete invalid and duplicate data; The enterprise data of the target enterprise after data cleaning is revised to correct identifiable errors in the enterprise data, thereby obtaining the organized enterprise data of the target enterprise.

4. The enterprise evaluation method based on big data according to claim 2 is characterized by: The enterprise information acquisition and enterprise evaluation in S1 includes: employees register and log in using their ID numbers, and compare the employee ID numbers with the enterprise information obtained from the social security department to determine whether the employee is or has worked in the enterprise. Employees who pass the test will score and evaluate the enterprise. The scope of employees' evaluation of the enterprise includes: salary and bonus, environment and atmosphere, development opportunities, and overtime pressure.

5. A big data-based enterprise evaluation system, applied to the big data-based enterprise evaluation method according to any one of claims 1 to 4, characterized in that: include: The data collection module is used to collect the enterprise information and operating data of the target enterprise, thereby providing data basis for enterprise evaluation; The data processing unit is used to classify and sort the enterprise information and business data collected by the data collection module, and calculate various values ​​in the business data; Distributed storage module, used for distributed storage of classified enterprise information and business data; A data analysis module, which analyzes the enterprise information and business data in the distributed storage module based on any one of the methods of association analysis, sequence pattern analysis and cluster analysis; The data display unit is used to display the corporate information, operating data and trust results of the target enterprise.

6. The enterprise evaluation system based on big data according to claim 5 is characterized by: The data processing unit comprises: The data classification module is used to classify the target enterprise's enterprise information and classify it into enterprise content and employee content according to the difference in the enterprise information content; The data calculation module is used to perform statistical calculations on the target enterprise's operating data to obtain the target enterprise's turnover and annual output value growth value, thereby determining whether the target enterprise is in a normal operating state; The data processing module is used to delete and correct invalid information and erroneous data in the corporate information and operating data of the target enterprise.

7. The enterprise evaluation system based on big data according to claim 5 is characterized by: The data display unit comprises: A user login module is used to provide a web page login window for users, and the user login module unit is connected to the cloud platform via a wireless network; The cloud platform is used to display the target enterprise's corporate information, operating data and trust results for users to browse, and the cloud platform is connected to the data collection module via a wireless network.