Intelligent analysis method and model for enterprise equity investment

Abstract

The invention discloses an enterprise equity investment intelligent analysis method and model, and belongs to the technical field of enterprise investment decision analysis, and the method comprises the steps: collecting all index data of a target enterprise, and forming an enterprise investment index data set; collecting listed enterprise data of the industry where the enterprise is located to form a standard index; comparing the data of the target enterprise with the corresponding standard index to form a comparison score; constructing a weight processing model according to the enterprise type; and performing weighted calculation on the comparison score of each index to obtain a final score of the target enterprise. The model comprises an object enterprise data collection module, an object enterprise data processing module, a listed enterprise data collection module, a listed enterprise data processing module, a comparison and assignment module, a weight processing model construction module and a weighting calculation module. According to the method, enterprise multi-dimensional data and industry information can be comprehensively analyzed, a comprehensive and accurate comprehensive score is provided for stock right investment, investment decision making is assisted, and the scientificity and efficiency of investment decision making are improved.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of enterprise investment decision analysis, and specifically to an enterprise equity investment intelligent analysis method and model. Background Art

[0002] In corporate investment decisions, traditional methods require the analysis of massive amounts of multi-dimensional corporate data, including financial data (such as balance sheets, income statements, cash flow statements, etc.), non-financial data (such as the background of the corporate management team, corporate culture, market reputation, etc.) and industry information (such as industry competition landscape, industry development trends, and the impact of policies on the industry, etc.). These data come from a wide range of sources and in different formats, and traditional manual analysis methods are difficult to efficiently integrate and process. For example, if an investment manager wants to evaluate the investment potential of a technology company, he needs to collect data such as the company's R&D investment, number of patents, and technical team strength from multiple channels. This process is time-consuming and prone to errors.

[0003] In the past, investment decisions often focused on a single factor, such as paying too much attention to the company's short-term financial benefits, while ignoring the comprehensive consideration of multiple factors such as the company's long-term development potential and industry adaptability. For example, some companies have good financial statements in the short term, but due to their lack of adaptability to emerging technology trends in the industry, they may face development bottlenecks in the future. Traditional analysis methods make it difficult to conduct a comprehensive and accurate comprehensive scoring of companies, thus affecting the accuracy of investment decisions.

[0004] With the development of the financial market, equity investment plays an increasingly important role in corporate financing and investor asset allocation. Whether it is early-stage investment or investment in growing and mature enterprises, more scientific and accurate analysis models are needed. For example, in recent years, with the emergence of a large number of technological innovation companies, the scale of venture capital investment in the field of science and technology has continued to expand, and more accurate analysis models are needed to screen potential investment targets. Therefore, developing an intelligent analysis method and model that can comprehensively analyze multi-dimensional enterprise data and industry information and accurately evaluate the value of equity investment is of great significance to improving the scientificity and efficiency of investment decisions. Summary of the invention

[0005] The technical solution of the present invention aims at the technical problem that the existing technical solutions are too single, and provides a solution that is significantly different from the existing technologies. It mainly provides an intelligent analysis method and model for enterprise equity investment, so as to provide scientific guidance for equity investment decisions through comprehensive and accurate data collection and in-depth analysis.

[0006] The technical solution adopted by the present invention to solve the above technical problems is:

[0007] An intelligent analysis method for corporate equity investment includes the following steps:

[0008] S1. Collect various indicator data of the target enterprise and perform preprocessing to form an enterprise investment indicator data set;

[0009] S2. Collect the data of listed companies in the industry where the enterprise is located, sort and process them, and form standard indicators;

[0010] S3. Compare the target enterprise’s data with the corresponding standard indicators to form a comparative score;

[0011] S4. Construct a weight processing model based on enterprise type;

[0012] S5. Perform weighted calculation on the comparative scores of various indicators according to the constructed weight processing model to obtain the final score of the target enterprise.

[0013] Specifically, in step S1, various indicator data of multiple enterprises are first collected and integrated to form an enterprise comprehensive database; then, for the target enterprise, a search query is performed in the constructed enterprise comprehensive database through the enterprise name and unified social credit code, and the relevant information set of the enterprise is uniformly output and then pre-processed to finally form an enterprise investment indicator data set.

[0014] Specifically, in step S1, the data collection methods include data procurement, government data docking, and manual entry;

[0015] Obtain basic information about enterprises, enterprise patent information, investment and financing information, and enterprise shareholder information through data procurement;

[0016] and / or, obtaining corporate administrative information, tax information and social security information through government data connection channels;

[0017] And / or, enter internal enterprise data and market data through manual entry.

[0018] Specifically, in step S1, data preprocessing includes: first removing invalid data and standardizing the data; then marking the default field content; and finally generating a default value form, which is filled in manually.

[0019] Specifically, step S2 includes:

[0020] S2-1. Extract data on the industry and business content of the target enterprise, and input it into the Alice Chat model built by Wind in the form of API query to obtain the names of the top listed companies in the same category;

[0021] S2-2. Query the established corporate annual report database to obtain the latest annual reports of listed companies and extract the annual report data;

[0022] S2-3. Aggregate and average the annual report data according to the evaluation index system to finally obtain the standard value of each evaluation index.

[0023] Specifically, in step S3, the enterprise investment indicator data set obtained in step S1 is compared with the evaluation indicator standard obtained in step S2 one by one according to each indicator, and points are assigned to obtain the evaluation score of each indicator.

[0024] Specifically, step S4 includes:

[0025] S4-1. Use fuzzy hierarchical analysis method to process weights and transform them into a hierarchical structure model according to the index system. The hierarchical structure model includes target layer, criterion layer and index layer.

[0026] S4-2. The indicators are ranked in order of importance. The ranking rules are adjusted according to the enterprise industry type, market conditions and policy type to achieve dynamic adjustment of the model;

[0027] S4-3, after completing the sorting of each level, a fuzzy complementary judgment matrix is ​​formed;

[0028] S4-4. Solve the weight of the fuzzy complementary judgment matrix and finally obtain the weight of each indicator at the corresponding level.

[0029] Specifically, in step S4-4, R=(r ij ) n*n (i,j=1,2,…,n) is the fuzzy complementary judgment matrix, and W=(W1,W2,…,W i ,…,W n ) is the weight vector of R, and the weight of the fuzzy complementary judgment matrix is ​​solved according to the general formula, which is expressed as follows:

[0030]

[0031] Where W i Factor r i The weight of .

[0032] Specifically, step S5 includes:

[0033] S5-1. Secondary indicator score: obtained by comparing the scores;

[0034] S5-2, first-level indicator score: obtained by first-level indicator score = ∑ second-level indicator weight x corresponding second-level indicator score;

[0035] S5-3, target score: obtained by target score = ∑ first-level indicator weight x corresponding first-level indicator score;

[0036] S5-4. Convert the target score into a percentage system and finally obtain the enterprise investment score.

[0037] The present invention also provides an enterprise equity investment intelligent analysis model, which is applied to the above-mentioned enterprise equity investment intelligent analysis method; the analysis model includes:

[0038] The target enterprise data collection module is used to collect various indicator data of the target enterprise;

[0039] The target enterprise data processing module is used to pre-process and integrate the target enterprise's various indicator data;

[0040] An enterprise investment indicator data set storage module is used to store the integrated enterprise investment indicator data set;

[0041] Listed enterprise data collection module, used to collect listed enterprise data in the industry where the enterprise is located;

[0042] Listed enterprise data processing module, used to organize and process the collected listed enterprise data;

[0043] A standard indicator storage module is used to store standard indicators formed by the listed enterprise data processing module;

[0044] The comparison and scoring module is used to compare the target enterprise data with the corresponding standard indicators and assign scores;

[0045] A weight processing model building module is used to build a weight processing model according to the enterprise type;

[0046] The weighted calculation module is used to perform weighted calculation on the comparison scores of various indicators according to the constructed weight processing model;

[0047] The final score display module is used to display the final investment score of the target enterprise.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] (1) The present invention collects the listed enterprise data of the industry in which the enterprise is located as the standard index, and uses this as the basis to assign points to the investment index data of the target enterprise to show the adaptability of the target enterprise to the emerging technology trends in the industry; then a weight processing model is constructed according to the enterprise type, and the comparison scores of various indicators are weighted according to the weight processing model, and finally the final score of the target enterprise is obtained, and the investment value of the enterprise can be intuitively represented by the final score. Then the present invention can provide an accurate comprehensive score for equity investment and assist investment decision-making.

[0050] (2) The present invention collects multi-dimensional data such as basic enterprise information, enterprise patent information, investment and financing information, enterprise shareholder information, enterprise administrative information, tax information, market data, etc. through channels such as data procurement, government data docking, and manual data entry, so as to provide a comprehensive integrated score for equity investment and avoid the problem that data collection in traditional manual analysis methods is time-consuming and prone to errors.

[0051] (3) The present invention extracts relevant data from the latest annual reports of listed companies, which can ensure real-time acquisition of current market conditions to improve the accuracy of the benchmark enterprise scoring. When constructing a weight processing model, the present invention can adjust the sorting rules according to the enterprise industry type, market conditions and policy type to achieve dynamic adjustment of the model, thereby ensuring the accuracy of the comprehensive score provided.

[0052] In summary, the present invention can comprehensively analyze the multi-dimensional data and industry information of enterprises, accurately evaluate the intelligent analysis method and model of equity investment value, and improve the scientificity and efficiency of investment decisions.

[0053] The present invention will be explained in detail below with reference to the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of the enterprise equity investment intelligent analysis method in the present invention;

[0055] Figure 2 It is a structural block diagram of the enterprise equity investment intelligent analysis model in the present invention.

[0056] Figure numerals: 1. Target enterprise data collection module; 2. Target enterprise data processing module; 3. Enterprise investment indicator data set storage module; 4. Listed enterprise data collection module; 5. Listed enterprise data processing module; 6. Standard indicator storage module; 7. Comparison and scoring module; 8. Weight processing model construction module; 9. Weighted calculation module; 10. Final score display module. DETAILED DESCRIPTION

[0057] To facilitate understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings, but the present invention can be implemented in different forms and is not limited to the embodiments described in the text. On the contrary, these embodiments are provided to make the content disclosed in the present invention more thorough and comprehensive.

[0058] Example 1: Please refer to the attached Figure 1 , an intelligent analysis method for corporate equity investment, comprising:

[0059] 1. Collect various indicator data of the target enterprise and pre-process them to form an enterprise investment indicator data set.

[0060] Specifically:

[0061] Data collection methods include data procurement, government data docking, manual entry and other channels. Data procurement involves purchasing and acquiring various public data of enterprises through the data market, including basic information of enterprises, enterprise patent information, investment and financing information and enterprise shareholder information, etc. Government data docking involves docking with the enterprise government data sharing platform to obtain administrative information, tax information, social security information, etc. of enterprises; manual entry is for technical personnel to enter internal enterprise data and some public market data obtained through offline channels into the corresponding enterprise data.

[0062] Data preprocessing includes: first, removing invalid data such as outliers and duplicate values, and standardizing the data to ensure data quality; then marking the default field content; after completing the above processing, generating a default value form, and manually filling in the default form.

[0063] 2. Collect data on listed companies in the industry in which the company is located, organize and process them, and form standard indicators.

[0064] Specifically:

[0065] When collecting data on listed companies, we first extract data on the industry and business content of the target company, and input it into the Alice Chat large model built by Wind in the form of API query to obtain the names of the top five listed companies of the same type. Then, we query the established annual report database to obtain the latest annual reports of these five companies. After obtaining the annual report, we extract the content of the annual report through OCR (optical character recognition technology), and aggregate and average the annual report data according to the evaluation index system to finally obtain the standard value of each evaluation index.

[0066] The above-mentioned corporate annual report database is accessed through the China Unicom Wind Annual Report Service API, and polls all listed companies every quarter to ensure the latest operating data of listed companies. The evaluation index system is as follows (the index content is determined based on investment experience):

[0067]

[0068]

[0069]

[0070] 3. Compare the target enterprise data with the corresponding standard indicators to form a comparative score;

[0071] Specifically:

[0072] Compare and assign scores. Compare the enterprise investment indicator data set obtained in the first step with the evaluation indicator standard obtained in the second step, assign scores according to the set score standards, and obtain the evaluation scores of each indicator.

[0073] 4. Construct a weight processing model based on the enterprise type;

[0074] Specifically:

[0075] The weight processing model uses fuzzy analytic hierarchy process for weight processing. According to the evaluation index system, it is converted into a hierarchical model. The hierarchical model includes the target layer (final score), the criterion layer (first-level index) and the indicator layer (secondary index). Then the indicators are ranked by importance in two rounds, with a total of seven rankings (one criterion layer ranking and six indicator layer rankings). The sorting rules can be adjusted according to the type of enterprise industry, market conditions and policy types to achieve dynamic adjustment of the model. After completing the sorting of each level, a fuzzy complementary judgment matrix is ​​formed. The weight calculation of each level is performed: R = (r ij ) n*n (i,j=1,2,…,n) is the fuzzy complementary judgment matrix, and W=(W1,W2,…,W i ,…,W n ) is the weight vector of R, and the weight of the fuzzy complementary judgment matrix is ​​solved according to the general formula, which is expressed as follows:

[0076]

[0077] Where W i Factor r i The weight of .

[0078] After the calculation is completed, a consistency check is performed to finally obtain the weight of each indicator at the corresponding level.

[0079] 5. Perform weighted calculation on the comparative scores of various indicators based on the constructed weight processing model to obtain the final score of the enterprise investment.

[0080] Specifically:

[0081] The indicator evaluation scores obtained in the third step are weighted according to the weights of the various data indicators obtained in the fourth step at each level. The processing method is as follows:

[0082] 1) Secondary indicator score: obtained based on comparative scoring;

[0083] 2) First-level indicator score: obtained by first-level indicator score = ∑ second-level indicator weight x corresponding to the second-level indicator score;

[0084] 3) Target score: obtained by target score = ∑ first-level indicator weight x corresponding first-level indicator score;

[0085] 4) Convert the target score into a percentage system to finally get the enterprise investment score. The higher the enterprise investment score, the more recommended the investment is.

[0086] Please refer to the attached Figure 2 , the intelligent analysis model of enterprise equity investment includes:

[0087] The target enterprise data collection module 1 is used to collect various indicator data of the target enterprise;

[0088] The target enterprise data processing module 2 is used to pre-process and integrate the target enterprise's various indicator data;

[0089] The enterprise investment indicator data set storage module 3 is used to store the integrated enterprise investment indicator data set;

[0090] Listed enterprise data collection module 4 is used to collect the listed enterprise data of the industry in which the enterprise is located;

[0091] Listed enterprise data processing module 5, used to organize and process the collected listed enterprise data;

[0092] The standard index storage module 6 is used to store the standard index formed by the listed enterprise data processing module 5;

[0093] Comparison and scoring module 7, used to compare the target enterprise data with the corresponding standard indicators and assign scores;

[0094] A weight processing model building module 8 is used to build a weight processing model according to the enterprise type;

[0095] The weighted calculation module 9 is used to perform weighted calculation on the comparison scores of various indicators according to the constructed weight processing model;

[0096] The final score display module 10 is used to display the final investment score of the target enterprise.

[0097] Embodiment 2: This embodiment differs from Embodiment 1 in that:

[0098] In this embodiment, in step 1, various indicator data of multiple enterprises are first collected and integrated to form a comprehensive enterprise database, specifically: multi-dimensional enterprise data is collected through basic enterprise information to be analyzed (such as enterprise name, unified social credit code, etc.), and multi-dimensional market data of target objects are integrated, including but not limited to enterprise financial information, operating information, R&D information, etc.; a comprehensive enterprise database is built;

[0099] Then, for the target enterprise, search and query are performed in the established enterprise comprehensive database through the enterprise name and unified social credit code. After the relevant information set of the enterprise is uniformly output, it is preprocessed and finally forms the enterprise investment indicator data set.

[0100] The rest is the same as the first embodiment.

[0101] The above is an exemplary description of the present invention in combination with the accompanying drawings. It is obvious that the specific implementation of the present invention is not limited to the above-mentioned method. As long as such non-substantial improvements are made by adopting the method concept and technical solution of the present invention, or the concept and technical solution of the present invention are directly applied to other occasions without improvement, they are all within the protection scope of the present invention.

Claims

1. An intelligent analysis method for corporate equity investment, characterized by: The steps include: S1. Collect various indicator data of the target enterprise and perform preprocessing to form an enterprise investment indicator data set; S2. Collect the data of listed companies in the industry where the enterprise is located, sort and process them, and form standard indicators; S3. Compare the target enterprise’s data with the corresponding standard indicators to form a comparative score; S4. Construct a weight processing model based on enterprise type; S5. Perform weighted calculation on the comparative scores of various indicators according to the constructed weight processing model to obtain the final score of the target enterprise.

2. The method for intelligent analysis of corporate equity investment according to claim 1, characterized in that: In step S1, the various indicator data of multiple enterprises are first collected and integrated to form an enterprise comprehensive database; then, for the target enterprise, the enterprise name and unified social credit code are used to search and query in the constructed enterprise comprehensive database, and the relevant information set of the enterprise is uniformly output and then pre-processed to finally form an enterprise investment indicator data set.

3. The method for intelligent analysis of corporate equity investment according to claim 2, characterized in that: In step S1, data collection methods include data procurement, government data docking, and manual entry; Obtain basic information about enterprises, enterprise patent information, investment and financing information, and enterprise shareholder information through data procurement; and / or, obtaining corporate administrative information, tax information and social security information through government data connection channels; And / or, enter internal enterprise data and market data through manual entry.

4. The method for intelligent analysis of corporate equity investment according to claim 1, characterized in that: In step S1, data preprocessing includes: firstly, removing invalid data and standardizing the data; then marking the default field content; and finally generating a default value form, which is filled in manually.

5. The method for intelligent analysis of corporate equity investment according to claim 1, characterized in that: Step S2 includes: S2-1. Extract data on the industry and business content of the target enterprise, and input it into the Alice Chat model built by Wind in the form of API query to obtain the names of the top listed companies in the same category; S2-2. Query the established corporate annual report database to obtain the latest annual reports of listed companies and extract the annual report data; S2-3. Aggregate and average the annual report data according to the evaluation index system to finally obtain the standard value of each evaluation index.

6. The method for intelligent analysis of corporate equity investment according to claim 1, characterized in that: In step S3, the enterprise investment indicator data set obtained in step S1 is compared with the evaluation indicator standard obtained in step S2 one by one according to each indicator, and scores are assigned to obtain evaluation scores for each indicator.

7. The method for intelligent analysis of corporate equity investment according to claim 1, characterized in that: Step S4 includes: S4-1. Use fuzzy hierarchical analysis method to process weights and transform them into a hierarchical structure model according to the index system. The hierarchical structure model includes target layer, criterion layer and index layer. S4-2. The indicators are ranked in order of importance. The ranking rules are adjusted according to the enterprise industry type, market conditions and policy type to achieve dynamic adjustment of the model; S4-3, after completing the sorting of each level, a fuzzy complementary judgment matrix is ​​formed; S4-4. Solve the weight of the fuzzy complementary judgment matrix and finally obtain the weight of each indicator at the corresponding level.

8. The method for intelligent analysis of corporate equity investment according to claim 7, characterized in that: In step S4-4, R=(r ij ) n*n (i,j=1,2,…,n) is the fuzzy complementary judgment matrix, and W=(W1,W2,…,W i ,…,W n ) is the weight vector of R, and the weight of the fuzzy complementary judgment matrix is ​​solved according to the general formula, which is expressed as follows: Where W i Factor r i The weight of .

9. The method for intelligent analysis of corporate equity investment according to claim 1, characterized in that: Step S5 includes: S5-1. Secondary indicator score: obtained by comparing the scores; S5-2, first-level indicator score: obtained by first-level indicator score = ∑ second-level indicator weight x corresponding second-level indicator score; S5-3, target score: obtained by target score = ∑ first-level indicator weight x corresponding first-level indicator score; S5-4. Convert the target score into a percentage system and finally obtain the enterprise investment score.

10. An enterprise equity investment intelligent analysis model, applied to the enterprise equity investment intelligent analysis method according to any one of claims 1 to 9; characterized in that: The analytical models include: The target enterprise data collection module (1) is used to collect various indicator data of the target enterprise; The target enterprise data processing module (2) is used to pre-process and integrate the target enterprise's various indicator data; An enterprise investment indicator data set storage module (3), used for storing the integrated enterprise investment indicator data set; Listed enterprise data collection module (4), used to collect listed enterprise data in the industry in which the enterprise is located; A listed company data processing module (5), used for sorting and processing the collected listed company data; A standard index storage module (6), used for storing the standard index formed by the listed enterprise data processing module (5); The comparison and scoring module (7) is used to compare the target enterprise data with the corresponding standard indicators and assign scores; A weight processing model building module (8), used to build a weight processing model according to the enterprise type; A weighted calculation module (9), used for performing weighted calculation on the comparison scores of various indicators according to the constructed weight processing model; The final score display module (10) is used to display the final investment score of the target enterprise.

Images