Entrepreneurship risk assessment method based on industry data analysis
By constructing a highly accurate industry database and a two-layer assessment module, combined with a big data analysis model, the problems of data accuracy and adaptability of traditional entrepreneurial risk assessment methods have been solved, achieving accurate assessment and risk reduction of entrepreneurial risks.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHENGZHOU TECHN COLLEGE
- Filing Date
- 2026-01-27
- Publication Date
- 2026-05-08
AI Technical Summary
Traditional entrepreneurial risk assessment methods are insufficient in terms of data dimensions, analytical depth, and dynamic adaptability, making it difficult for entrepreneurs to accurately assess market potential, innovation capabilities, and policy changes, and hindering their ability to quickly respond to risks in the entrepreneurial process.
A highly accurate industry database is built by collecting data from multiple channels. A two-layer risk assessment module and a data aggregation module are constructed. Combined with big data analysis models, statistical methods are used to quantify entrepreneurial risks, including the steps of a preliminary field module, a detailed assessment module, and an aggregation module.
It enables precise assessment of entrepreneurial risks, provides fast and accurate early-stage planning information for startups, and helps entrepreneurs adopt conservative strategies to reduce risks.
Smart Images
Figure CN121998428A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the technical field of entrepreneurial risk assessment calculation, and in particular to an entrepreneurial risk assessment method based on industry data analysis. Background Technology
[0002] Traditional entrepreneurial risk assessment methods, while having developed a certain system through long-term practice, are facing severe challenges brought about by the digital age in terms of data dimensions, analytical depth, and dynamic adaptability. In the current entrepreneurial process, due to inaccurate industry data and unclear data sources, entrepreneurs struggle to cope with various problems that arise. For example, they cannot quickly determine the number of potential customers in the market, cannot quantify their innovation capabilities, cannot make reasonable predictions about technological risks, and cannot quickly adapt to policy changes. Summary of the Invention
[0003] The purpose of this invention is to provide a startup risk assessment method based on industry data analysis. This method relies on a multi-channel data collection mechanism to acquire relevant industry data, constructing a highly accurate and traceable industry database. This ensures the accuracy of the data itself while enabling rapid identification and verification of data sources. Simultaneously, it establishes a two-layer risk assessment module and a data aggregation module, combined with a mature big data analysis model, to quickly output the core assessment information needed for initial startup planning. Based on this, by retrieving and matching target data from the database, statistical analysis methods are used to quantify startup risks, ultimately achieving a precise startup risk assessment based on industry data.
[0004] To achieve the above objectives, this invention provides a startup risk assessment method based on industry data analysis, comprising the following steps: Step 1: Set up a two-tier evaluation module and a summary module. The two-tier evaluation module includes a preliminary domain module and a detailed evaluation module. Step 2: Collect industry data from different fields to form a startup risk area database. The startup risk area database has a data supply module that regularly updates the content of the startup risk area database according to the set update time. Step 3: The user inputs a description of entrepreneurship. The preliminary domain module, in conjunction with the data supply module, determines the specific domain in the entrepreneurship risk domain library based on the description. The entrepreneurship risk domain library then outputs the entrepreneurship data for that specific domain. The data supply module then categorizes the obtained entrepreneurship data. Step 4: Input the categorized startup data into the detailed evaluation module to obtain preliminary evaluation results. The preliminary evaluation results include market risk, technological risk, and policy risk, as well as the calculated weights for the three types of risks. Step 5: Based on the preliminary assessment results, the summary module sets the risk calculation interval and calculates the total entrepreneurial risk according to the risk calculation interval.
[0005] Preferably, in the preliminary domain module of step one, the BERT text classification algorithm is used to identify the industry domain, several domain dictionaries are established, and the relevant descriptions of the entrepreneurial project are verified through the domain dictionaries to identify the specific entrepreneurial domain of the entrepreneurial project.
[0006] Preferably, in step two, publicly available data from the National Bureau of Statistics, industry associations, and professional databases are used as industry data for different fields. The data supply module uses an ETL process to clean, transform, and load the raw data to build a standardized entrepreneurial risk domain database, sets a regular update time, and uses common data update methods to update the content of the entrepreneurial risk domain database.
[0007] Preferably, in step three, the data supply module receives the specific entrepreneurial field output by the preliminary field module, selects entrepreneurial data from the database based on the specific entrepreneurial field, and classifies the entrepreneurial data using the existing Large Language Model (LLM). The classification results are market data, technology data, and policy data.
[0008] Preferably, the detailed evaluation module in step four includes three sub-modules, each employing a different evaluation method, using market data, technical data, and policy data to calculate market risk, technical risk, and policy risk respectively.
[0009] Preferably, the specific implementation of the detailed evaluation module is as follows: Market risk: Market saturation from market data is used to calculate market risk; ; ; Technology risk: Technology risk is comprehensively assessed through three aspects: technology maturity, R&D investment, and number of patents. Policy risk: The frequency of policy changes in policy data is used as the measure of policy risk. The calculation formula is as follows: ; In the above formula, the time interval is artificially defined, and the number of policy changes is the number of policy changes within the time interval. , and To calculate the weights, the percentage of different risks is defined.
[0010] Preferably, one specific implementation of the weight calculation is as follows: The data volume of the entrepreneurial risk domain library is used as the weight, and the calculation formula is as follows: ; ; Using the ratio of the data volume from the entrepreneurial risk domain database as the basis for weighting calculations can better align with the data in the entrepreneurial risk domain database.
[0011] Preferably, in step five, the aggregation module calculates the total entrepreneurial risk based on the preliminary assessment results provided by the detailed assessment module, and calculates it according to the set risk calculation interval, using the following formula: ; In the above formula, the total entrepreneurial risk is within the range It is low risk, within the range For medium risk within the range It is considered high-risk.
[0012] Therefore, the entrepreneurial risk assessment method based on industry data analysis described above, as used in this invention, has the following advantages: By collecting data from multiple sources, a more accurate database can be formed, making the data more accurate and allowing for quick identification of the data source. This facilitates the judgment of the data's accuracy. A two-layer evaluation module and a summary module are established. Through existing big data model processing methods, the information needed for early-stage startup planning can be quickly provided. Combined with relevant information retrieved from the database, data statistics methods are used to calculate startup risks, enabling the assessment of startup risks through industry data.
[0013] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0014] Figure 1 This is a flowchart of a startup risk assessment method based on industry data analysis according to the present invention; Figure 2 This is a specific example of an entrepreneurial risk assessment method based on industry data analysis according to the present invention. Detailed Implementation
[0015] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Specific model specifications need to be selected and determined according to the actual specifications of the device, etc. The specific selection calculation method adopts existing technology in the art, and therefore will not be described in detail.
[0016] Example like Figure 1 As shown, this invention provides a startup risk assessment method based on industry data analysis, comprising the following steps: Step 1: Set up a two-tier evaluation module and a summary module. The two-tier evaluation module includes a preliminary domain module and a detailed evaluation module. Step Two: Collect industry data from different fields to form a startup risk area database. This database has an internal data supply module that regularly updates its content according to a set update schedule. Specifically, publicly available data from the National Bureau of Statistics, industry associations, and professional databases are used as industry data for different fields. The data supply module uses an ETL process to clean, transform, and load the raw data, constructing a standardized startup risk area database. Regular update times are set, and common data update methods are used to update the database's content, removing duplicate and outdated information. Manual screening can also be employed.
[0017] Step 3: The user inputs a description of the startup project. Based on this description, the preliminary domain module, combined with the data supply module, confirms the specific domain corresponding to the startup project description in the startup risk domain database. Specifically, the BERT text classification algorithm is used to identify the industry domain. Several domain dictionaries are established for different industry domains. These domain dictionaries are then used to process the subsequent startup project descriptions to identify the specific startup domain within the project. The startup risk domain database outputs startup data corresponding to these specific domains, and the data supply module categorizes the obtained startup data. During the classification process, the data supply module receives the specific entrepreneurial field output by the preliminary field module, selects entrepreneurial data from the database based on the specific entrepreneurial field, and uses the existing Large Language Model (LLM) to classify the entrepreneurial data. The classification results are market data, technology data, and policy data.
[0018] Step 4: Input the categorized startup data into the detailed evaluation module to obtain preliminary evaluation results. The preliminary evaluation results include market risk, technological risk, and policy risk, as well as the calculation weights corresponding to different risks. The detailed evaluation module includes three sub-modules, each of which adopts a different evaluation method and uses market data, technological data, and policy data to calculate market risk, technological risk, and policy risk respectively.
[0019] The specific calculation is implemented as follows: Market risk: Market saturation from market data is used to calculate market risk; ; ; Technology risk: Technology risk is comprehensively assessed through three aspects: technology maturity, R&D investment, and number of patents. Policy risk: The frequency of policy changes in policy data is used as the measure of policy risk. The calculation formula is as follows: ; In the above formula, the time interval is artificially defined, and the number of policy changes is the number of policy changes within the time interval. , and To calculate the weights, the percentage of different risks is defined.
[0020] One specific implementation of weight calculation is as follows: The data volume of the entrepreneurial risk domain library is used as the weight, and the calculation formula is as follows: ; ; Using the ratio of the data volume from the entrepreneurial risk domain database as the basis for weighting calculations can better align with the data in the entrepreneurial risk domain database.
[0021] Step 5: Based on the preliminary assessment results, the summary module sets the risk calculation interval and calculates the total entrepreneurial risk.
[0022] Based on the set calculation interval and using the previous preliminary evaluation results, the calculation formula is as follows: ; In the above formula, the total entrepreneurial risk is within the range It is low risk, within the range For medium risk within the range It is considered high-risk.
[0023] This application uses publicly available market data to randomly select a startup project for risk assessment calculation, such as... Figure 2 As shown, the risks are higher in March and June, and the company's profits decline accordingly. Therefore, the method in this application can help entrepreneurs adopt a conservative strategy to start a business and reduce entrepreneurial risks.
[0024] Therefore, this invention employs an industry data analysis-based entrepreneurial risk assessment method. It collects data from multiple sources, forming a more accurate database that allows for quick identification of data sources and facilitates the assessment of data accuracy. A two-tiered assessment and aggregation module is established. Using existing big data model processing methods, it quickly provides the information needed for initial entrepreneurial planning. Combined with relevant information retrieval from the database, it uses statistical methods to calculate entrepreneurial risk, achieving an assessment of entrepreneurial risk through industry data.
[0025] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.
Claims
1. A startup risk assessment method based on industry data analysis, characterized in that: Includes the following steps: Step 1: Set up a two-tier evaluation module and a summary module. The two-tier evaluation module includes a preliminary domain module and a detailed evaluation module. Step 2: Collect industry data from different fields to form a startup risk area database. The startup risk area database has a data supply module that regularly updates the content of the startup risk area database according to the set update time. Step 3: The user inputs a description of entrepreneurship. The preliminary domain module, in conjunction with the data supply module, determines the specific domain in the entrepreneurship risk domain library based on the description. The entrepreneurship risk domain library then outputs the entrepreneurship data for that specific domain. The data supply module then categorizes the obtained entrepreneurship data. Step 4: Input the categorized startup data into the detailed evaluation module to obtain preliminary evaluation results. The preliminary evaluation results include market risk, technological risk, and policy risk, as well as the calculated weights for the three types of risks. Step 5: Based on the preliminary assessment results, the summary module sets the risk calculation interval and calculates the total entrepreneurial risk according to the risk calculation interval.
2. The entrepreneurial risk assessment method based on industry data analysis according to claim 1, characterized in that: The preliminary domain module in step one uses the BERT text classification algorithm to identify industry domains, establishes several domain dictionaries, verifies the relevant descriptions of startup projects through the domain dictionaries, and identifies the specific startup domain of the startup project.
3. The entrepreneurial risk assessment method based on industry data analysis according to claim 2, characterized in that: In step two, publicly available data from the National Bureau of Statistics, industry associations, and professional databases are used as industry data for different fields. The data supply module uses an ETL process to clean, transform, and load the raw data to build a standardized entrepreneurial risk domain database. Regular update times are set, and common data update methods are used to update the content of the entrepreneurial risk domain database.
4. The entrepreneurial risk assessment method based on industry data analysis according to claim 3, characterized in that: In step three, the data supply module receives the specific entrepreneurial field output by the preliminary field module, selects entrepreneurial data from the database based on the specific entrepreneurial field, and classifies the entrepreneurial data using the existing Large Language Model (LLM). The classification results are market data, technology data, and policy data.
5. The entrepreneurial risk assessment method based on industry data analysis according to claim 4, characterized in that: The detailed assessment module in step four includes three sub-modules, each employing a different assessment method, using market data, technical data, and policy data to calculate market risk, technical risk, and policy risk, respectively.
6. The entrepreneurial risk assessment method based on industry data analysis according to claim 5, characterized in that: The specific implementation of the detailed evaluation module is as follows: Market risk: Market saturation from market data is used to calculate market risk; ； ； Technology risk: Technology risk is comprehensively assessed through three aspects: technology maturity, R&D investment, and number of patents. Policy risk: The frequency of policy changes in policy data is used as the measure of policy risk. The calculation formula is as follows: ； In the above formula, the time interval is artificially defined, and the number of policy changes is the number of policy changes within the time interval. , and To calculate the weights, the percentage of different risks is defined.
7. The entrepreneurial risk assessment method based on industry data analysis according to claim 6, characterized in that: One specific implementation of weight calculation is as follows: The data volume of the entrepreneurial risk domain library is used as the weight, and the calculation formula is as follows: ； ； Using the ratio of the data volume from the entrepreneurial risk domain database as the basis for weighting calculations can better align with the data in the entrepreneurial risk domain database.
8. The entrepreneurial risk assessment method based on industry data analysis according to claim 6, characterized in that: In step five, the aggregation module calculates the total entrepreneurial risk based on the preliminary assessment results provided by the detailed assessment module, according to the set risk calculation interval. The calculation formula is as follows: ； In the above formula, the total entrepreneurial risk is within the range It is low risk, within the range For medium risk within the range It is considered high-risk.