Primary enterprise scientific and technological innovation ability evaluation method and related products

By building an evaluation index system and using database and large language model technology to obtain data on start-up companies, the subjectivity of traditional evaluation methods is solved and a more accurate assessment of innovation capabilities is achieved.

CN120612014APending Publication Date: 2025-09-09BEIJING GUOKE ZHONGAN TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202510767517.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-10
Publication Date
2025-09-09

AI Technical Summary

Technical Problem

Traditional evaluation methods for start-ups’ technological innovation capabilities are highly subjective and difficult to accurately evaluate a company’s innovation capabilities.

Method used

Build an evaluation index system, obtain and process the secondary evaluation index data of start-ups through database technology, Internet technology and big language model technology, and calculate scores based on weights.

Benefits of technology

It improves the objectivity and accuracy of the evaluation of start-ups' technological innovation capabilities and provides a timely and accurate evaluation plan.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120612014A_ABST
    Figure CN120612014A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of data analysis, and relates to a method and device for evaluating the scientific and technological innovation ability of a initially created enterprise, a storage medium and electronic equipment. The method for evaluating the scientific and technological innovation capability of the initially created enterprise comprises the following steps of: obtaining data required by a secondary evaluation index and storing the data in an evaluation data knowledge base; constructing a cue word for extracting data required by each secondary evaluation index in the evaluation data knowledge base; extracting data required by each secondary evaluation index from an evaluation data knowledge base through the constructed cue word; converting the extracted data required by each secondary evaluation index into a score of the corresponding secondary evaluation index; based on the score of the second-level evaluation index, combining the weight of the second-level evaluation index to calculate the score of the first-level evaluation index; and based on the score of the first-level evaluation index, combining with the weight of the first-level evaluation index to calculate the score of the scientific and technological innovation ability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and in particular relates to a method, device, storage medium and electronic device for evaluating the technological innovation capabilities of start-ups. Background Art

[0002] Promising startups can effectively drive the development of new productivity and accelerate the innovation-driven development of my country's economy. Increasing support for startup innovation is a key measure to enhance the country's international competitiveness. Enterprise innovation capability assessments can effectively identify promising startups, helping government agencies and financial institutions accurately identify promising startups and ultimately enhance the country's scientific and technological innovation capabilities.

[0003] Traditional evaluation methods for scientific and technological innovation capabilities rely on expert evaluation. This method is highly subjective and it is difficult to accurately evaluate the scientific and technological innovation capabilities of start-ups. Summary of the Invention

[0004] One of the purposes of this application is to provide a method, device, storage medium and electronic device for evaluating the technological innovation capabilities of start-ups, so as to improve the objectivity and accuracy of the evaluation of the technological innovation capabilities of start-ups.

[0005] To achieve the above-mentioned and other related purposes, the first aspect of the present application provides a method for evaluating the technological innovation capabilities of start-ups, comprising the following steps: Evaluation data acquisition step, obtaining the data required for the secondary evaluation indicators and storing them in the evaluation data knowledge base; A prompt word construction step, constructing prompt words for extracting data required for each secondary evaluation indicator in the evaluation data knowledge base; The data extraction step extracts the data required for each secondary evaluation indicator from the evaluation data knowledge base through the constructed prompt words; The second-level evaluation indicator score quantification step converts the data required for each extracted second-level evaluation indicator into the score of the corresponding second-level evaluation indicator; The first-level evaluation indicator score calculation step is based on the score of the second-level evaluation indicator and the weight of the second-level evaluation indicator to obtain the score of the first-level evaluation indicator; The steps for calculating the score of scientific and technological innovation capability are based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators to obtain the score of scientific and technological innovation capability.

[0006] A second aspect of the present application provides a device for evaluating the technological innovation capabilities of a start-up enterprise, comprising: Evaluation data acquisition module, used to obtain the data required for secondary evaluation indicators and store them in the evaluation data knowledge base; A prompt word construction module is used to construct prompt words for extracting data required for each secondary evaluation indicator in the evaluation data knowledge base; The data extraction module is used to extract the data required for each secondary evaluation indicator from the evaluation data knowledge base through the constructed prompt words; The secondary evaluation indicator score quantification module is used to convert the data required for each secondary evaluation indicator into the score of the corresponding secondary evaluation indicator; A first-level evaluation indicator score calculation module is used to calculate the score of the first-level evaluation indicator based on the score of the second-level evaluation indicator and the weight of the second-level evaluation indicator; The science and technology innovation capability score calculation module is used to calculate the science and technology innovation capability score based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators.

[0007] A third aspect of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for evaluating the technological innovation capabilities of start-ups.

[0008] A fourth aspect of the present application provides an electronic device, the electronic device comprising a processor and a memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory. When the computer program is executed by the processor, the above-mentioned method for evaluating the technological innovation capabilities of start-ups is implemented.

[0009] This application has at least the following beneficial effects: The above-mentioned start-up enterprise scientific and technological innovation capability evaluation method, device, storage medium and electronic device provided in the embodiments of the present application use database technology, Internet technology, and large language model technology to construct a data extraction process to extract the data required for each secondary evaluation indicator of the start-up enterprise scientific and technological innovation capability evaluation system, thereby greatly improving the objectivity and accuracy of the start-up enterprise scientific and technological innovation capability evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 The present invention is a flowchart of the steps of a method for evaluating the technological innovation capabilities of a start-up enterprise according to an embodiment of the present application.

[0012] Figure 2 This is a schematic diagram of the structural principles of a device for evaluating the technological innovation capabilities of start-ups according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] The following describes the embodiments of the present application through specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in the present application can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0014] In order to solve the problem that traditional scientific and technological innovation capability evaluation methods are not objective enough, the embodiment of the present application provides a method for evaluating the scientific and technological innovation capability of start-ups. This method can well meet the objectivity requirements of evaluating the scientific and technological innovation capability of start-ups by constructing an evaluation index system that can not only characterize the innovation capability of the enterprise but also facilitate the acquisition and processing of the required data through technical means.

[0015] The start-up enterprise described in the embodiment of the present application refers to an enterprise that has been established for a relatively short time. In the specific application of the method of the present application, it can be specifically defined as an enterprise that has been established for less than or equal to 5 years.

[0016] The evaluation index system described in the embodiment of the present application includes multiple first-level evaluation indicators, each of which includes multiple second-level evaluation indicators. In a specific example, the evaluation index system includes 5 first-level evaluation indicators and 12 second-level evaluation indicators.

[0017] For example, first-level evaluation indicators include technical feasibility, corporate social brand, corporate team capabilities, external support, and future development trends. Second-level evaluation indicators for technical feasibility include technology development status, technology development costs, and technical and economic benefits. Second-level evaluation indicators for corporate social brand include domestic social brand and international social brand. Second-level evaluation indicators for corporate team capabilities include talent education background and talent technical experience. Second-level evaluation indicators for external support include corporate financing and government subsidies. Second-level evaluation indicators for future development trends include industry development trends, market technology demand, and technology market size.

[0018] Reference Figure 1 The method for evaluating the technological innovation capability of a start-up enterprise provided in the embodiments of the present application includes the following steps, wherein the method includes an evaluation index system consisting of multiple first-level evaluation indicators and multiple second-level evaluation indicators: S1 Evaluation data acquisition step, obtains the data required for the secondary evaluation indicators and stores it in the evaluation data knowledge base.

[0019] S2 is a prompt word construction step, which constructs prompt words for extracting the data required for each secondary evaluation indicator in the evaluation data knowledge base.

[0020] In the S3 data extraction step, the data required for each secondary evaluation indicator is extracted from the evaluation data knowledge base through the constructed prompt words.

[0021] S4 is a step for quantifying the scores of the secondary evaluation indicators, which converts the data required for each extracted secondary evaluation indicator into the scores of the corresponding secondary evaluation indicators.

[0022] S5 is a step for calculating the score of the first-level evaluation indicator, which is based on the score of the second-level evaluation indicator and combined with the weight of the second-level evaluation indicator to obtain the score of the first-level evaluation indicator.

[0023] S6: Calculation steps for scientific and technological innovation capability score: The score of scientific and technological innovation capability is calculated based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators.

[0024] The following is a detailed description of the method for evaluating the technological innovation capabilities of start-ups provided in the embodiments of the present application with reference to examples.

[0025] S1 evaluation data acquisition steps: Obtain the data required for the secondary evaluation indicators and store them in the evaluation data knowledge base.

[0026] Continuing with the above example of the rating index system, the data required for each secondary evaluation indicator is explained: data required for technology development status includes the number of technology products, technology prototypes or MVPs (minimum viable products); data required for technology development costs include the development costs of the company's products; data required for technical and economic benefits include the beneficial effects of the company's products; data required for domestic social brand includes domestic reports and report sentiment related to the company and its products; data required for international social brand includes international reports and report sentiment about the company and its products; data required for talent education background includes the universities to which the company's talents belong, academic qualifications, and majors; data required for talent technical experience includes the talent's work experience in top companies / laboratories and the fields involved; data required for corporate financing includes the financing rounds, financing amount, and investor influence obtained by the company; data required for government subsidies include the number of subsidized projects, project level, and subsidy amount; data required for industrial development trends include the type of industry to which the company belongs and the future direction of the industry; data required for market technology demand includes the degree of market demand for the company's technology products; data required for technology market size includes the size of the technology and rating.

[0027] The above data can be obtained by crawling through web crawler technology, and then the crawled data is stored in a pre-built evaluation data knowledge base. The specific steps may include the following, taking financing-related data as an example: S111, select data platforms, such as IT Orange, 36kr Venture Capital Platform, iMedia Research, and Qingke Venture Capital; S112, determining the sections and fields to be crawled. For example, if the section is financing data, the fields include company name, financing round, financing time, financing amount, investor, etc.; S113, building crawler codes for each data platform and crawling relevant information; S114: Clean the crawled data, for example, standardize the company names based on the business registration names, and remove duplicate financing events based on the company names; S115, storing the cleaned data in the rating data knowledge base.

[0028] It should be noted that different data resources have different qualities. For example, financing data, government innovation support data for start-ups, cutting-edge industry data, etc. are of higher quality. The quality of such knowledge bases formed using the above steps is also higher. This embodiment of the application defines it as a Class A knowledge base.

[0029] For example, the quality of enterprise product data and talent data is not high. For these data resources, large language models can be used to process them to improve the quality of the acquired data. The following steps can be used, taking enterprise product data as an example: S121, searching through a search engine, such as Bing, Google, Baidu, etc., with a search query such as: XXX company and (product or technology or process or method) S122: Determine the quality of the search using the large language model and perform a re-search or store. For example, prompt="You are an expert in judging the relevance of retrieved web pages. Please judge whether the retrieved information mentions the name of XXX company's main product. If so, return "yes"; if not, return "no"."

[0030] If the result is "yes", the company product name is extracted; prompt = "You are a data extraction expert. Please extract the company product name from the text. The extracted product name needs to be a very specific product name, not a very general product name. The returned result is [company name | product name x]"; the extraction result is stored in the knowledge base; If "No" is returned, determine whether the number of data in the knowledge base meets the target number, such as 10; if yes, end; if no, re-retrieve the data and exclude the results of the previous retrieval. The number of re-retrievals can be preset, for example, a maximum of 5 re-retrievals.

[0031] In the embodiment of the present application, the knowledge base formed in this way is defined as a Class B knowledge base.

[0032] S2 prompt word construction steps: Construct prompt words for extracting the data required for each secondary evaluation indicator in the evaluation data knowledge base.

[0033] Continuing from the above example, the following specific methods can be used to extract the prompt words required for the data of each secondary evaluation indicator: Technology development data, prompt = "Extract the list of enterprise technology products / technical prototypes / minimum viable products and count the number of products; the output format is: {[product name 1; product name 2; ...], product quantity};"; Technology development cost data, prompt="Analyze the development costs of the products / technologies listed in the product catalog. Analyze whether the development costs compare to similar products: very high, high, about the same, low, or much lower. Finally, return the product / technology name and the corresponding cost. The output format is: {[Product Name 1; Development Cost 1], [Product Name 2; Development Cost 2};" Technical and economic benefits, prompt="Analyze the technical and economic benefits of the products / technologies listed in the product catalog. Mainly analyze whether the economic benefits compare favorably with similar products: significantly improved, slightly improved, about the same, decreased, decreased, or significantly decreased. Finally, return the product / technology name and the corresponding economic benefit. Sample output is: {[Product Name 1; Economic Benefit 1], [Product Name 2; Economic Benefit 2]};"; Domestic social brand, prompt="Using internet technology, obtain domestic reports on companies, their technologies / products, and the sentiment of these reports (including sentiment towards the company's technology, products, and culture). Sentiment can be very positive, positive, neutral, negative, or very negative. Return the title and sentiment of the relevant reports. The output format is: {[report title 1; report sentiment 1], [report title 2; report sentiment 2], ...}"; International social brand, prompt="Based on internet technology, obtain international reports on companies, their technologies / products, and the sentiment of these reports (including sentiment towards the company's technology, products, and culture). Sentiments include very positive, positive, neutral, negative, and very negative. Return the title and sentiment of the relevant reports. The output format is: {[report title 1; report sentiment 1], [report title 2; report sentiment 2], ...}"; Talent education background, prompt="Analyze the graduation schools and academic qualifications of the company's core talents. Return the graduation schools and academic qualifications of up to three core talents. The output format is: {[name 1; graduation school 1; academic qualification 1], [name 2; graduation school 2; academic qualification 2], [name 3; graduation school 3; academic qualification 3]}"; Talent technical experience, prompt="Analyze the work experience of the company's core talents. Return the company names and company levels of up to three core talents / teams. The output format is: {[name 1; company name 1]; [name 2; company name 2]; [name 3; company name 3]}"; Enterprise financing, prompt="Extract all enterprise financing information, including the financing round, financing amount, and investor influence level. Investor influence is determined based on internet information. Investor influence is classified into super level (transformative influence), top level (extremely high influence), advanced level (high influence), intermediate level (medium influence), and basic level (low influence). The output format is: {financing round, financing amount, investor influence level}"; Government subsidies, prompt="Extract government innovation support, including project name, project level, and subsidy amount. The output format is: {project name, project level, subsidy amount}"; Industry Trends, prompt="Extract the technology industry to which the enterprise belongs, the industry name corresponding to that technology industry (i.e., the industry to which the enterprise belongs), and the development trend of the industry to which the enterprise belongs, expressed as industry type. Industry types include emerging industries, sunrise industries, declining industries, sunset industries, and obsolete industries. Based on an external database, determine whether it belongs to a strategic emerging industry or a future industry. Return the enterprise's industry, industry to which the enterprise belongs, industry development trend, whether it belongs to a strategic emerging industry (yes / no), and whether it belongs to a future industry (yes / no). The output format is: [industry, industry, development trend, whether it belongs to a strategic emerging industry, whether it belongs to a future industry]"; Market and technical demand, prompt="Analyze the market demand for the company's products. Demand conditions include strong demand, stable demand, weak demand, and shrinking demand. Return the market and technical demand conditions. The output format is: {demand condition}"; Technology market size, prompt="The scale of a company's technology products is analyzed and evaluated mainly from five aspects: total market volume, market growth potential, competitive landscape, technological barriers, and demand stability. Each aspect is divided into 1-10 levels. The larger the number, the higher the total market volume, the greater the market growth potential, the less intense the market competition, the higher the technological barriers, and the more stable the demand. Returns the ratings of the five aspects. The output format is: {[total market volume: total market volume level]; [market growth potential: market growth potential level]; [competitive landscape: competitive landscape level]; [technical barriers: technological barriers level]; [demand stability: demand stability level]}".

[0034] Note: The above prompts only describe the content that needs to be extracted and do not represent the prompts actually used. The prompts actually used include role definition, strict output limitation, output case prompts, etc.

[0035] S3 data extraction steps: Through the constructed prompt words, the data required for each secondary evaluation indicator is extracted from the evaluation data knowledge base.

[0036] Specifically, the constructed evaluation data knowledge base is imported into the large language model, prompt words are executed, and the data required for each secondary evaluation indicator is extracted. The process can be as follows: determine the content to be extracted; upload the corresponding evaluation data knowledge base to the large language model; retrieve the corresponding prompt words; execute the prompt words in the large language model; and save the extracted data. Taking "Technology Development Status Data" as an example: The content to be extracted involves the names of enterprise products, and the corresponding evaluation data knowledge base is a knowledge base that includes a list of enterprise products. The prompt is prompt="Extract the list of enterprise technical products / technical prototypes / minimum viable products, and count the number of products; the output format is: {[product name 1; product name 2; ...], number of products};"; execute the above prompt in the large language model input box; save the extracted data.

[0037] S4 Secondary Evaluation Index Scoring Quantification Steps: The data required for each extracted secondary evaluation indicator is converted into the score of the corresponding secondary evaluation indicator.

[0038] Specifically, based on the data required for the extracted secondary evaluation indicators, the data required for each secondary evaluation indicator is converted into a score according to the preset data conversion rules. Continuing with the above example, the marginal benefit diminishing benefit is introduced and applied to the calculation of the secondary evaluation indicator score: The technology development score is quantified and follows the following rules: the more products / technologies there are, the higher the score; there is a law of diminishing marginal returns, where the score increases less as the number increases; when the number of technologies / products reaches the industry average, a passing score is achieved. The technology development score is calculated as follows: ; When S>=60, ; When S<60, ; in, is the score of the technical development of the secondary evaluation indicator, S is the intermediate calculation score, is the highest value of S among all enterprises, is the lowest value of S among all enterprises, is the number of products of the target enterprise, is the average number of products of all enterprises.

[0039] The technology development cost score is quantified. The higher the technology development cost, the lower the score. The development cost can be divided into very high, high, average, low, and much lower, with corresponding scores of 20, 40, 60, 80, and 100.

[0040] The technical and economic benefit scores are quantified. The greater the improvement in technical and economic benefits, the higher the score. Economic benefits can be divided into significant improvement, slight improvement, about the same, decline, and a lot of decline, with corresponding scores of 100, 80, 60, 40, and 20.

[0041] The domestic social brand score is quantified. The more domestic coverage there is and the more positive the coverage sentiment is, the higher the domestic social brand score is. The coverage sentiment can be divided into very positive, positive, neutral, negative, and very negative, with corresponding sentiment scores of 100, 80, 60, 40, and 20. The calculation method for the domestic social brand score is: ; in, is the domestic social brand score of the secondary evaluation index, RepNum_S is the score of the number of reports, and Emot_S is the score of the emotional report. The calculation method of RepNum_S is the same as .

[0042] The international brand score is quantified and the calculation method of the international brand score is the same as .

[0043] Talents' educational background scores are quantified. Educational qualifications can be categorized as PhD, Master's, Bachelor's, and Other, with corresponding scores of 100, 80, 60, and 40. The scores of the universities graduated from are calculated using the QS rankings (top 200) and the China University Rankings (the Soft Science rankings, which only include 985 / 211 / Double First-Class universities and exclude those in the QS top 200). The calculation method is as follows: ; ; ; Sch_S is the score of the graduating institution, RankQS is the number of universities in the QS ranking list of the graduating institution, RankQS_S is the score of the graduating institution in the QS ranking, RankRK is the number of universities in the Chinese university ranking list of the graduating institution, RankRK_S is the score of the graduating institution in the Chinese university ranking, The number of universities on the QS ranking list, The number of universities on the Chinese university ranking list.

[0044] ; in, is the talent's educational background score, EduL_S is the academic degree score, SchMax_S is the highest score of the colleges and universities that the core talents of the enterprise graduated from, and EduLMax_S is the highest score of the academic degree of the core talents of the enterprise.

[0045] The talent, technology and experience scores are quantified. The talent, technology and experience scores are calculated by introducing the list of the world's top 500 companies and China's top 500 companies (excluding the world's top 500 companies). The calculation method is as follows: ; ; ; in, is the secondary evaluation index talent, technology and experience score, RankWC_S is the company's ranking score among the world's top 500, and RankCC_S is the company's ranking score among China's top 500. The number of Fortune 500 companies, The number of China's top 500 companies, For the ranking of enterprises in the Fortune Global 500 and for the ranking of enterprises in the Fortune China 500.

[0046] The corporate financing score is quantified. Investor influence can be divided into super level (transformative influence), top level (very high influence), advanced level (high influence), intermediate level (medium influence), and basic level (low influence). The corresponding investor scores are 100, 80, 60, 40, and 20. The corporate financing score is calculated as follows: ; ; in, Score for corporate financing, Score the number of financing rounds. Score the amount of financing, Score for corporate investors, is the total amount of financing for the target enterprise. is the average value of the total amount of corporate financing.

[0047] The government subsidy score is quantified. The project level can be divided into national, provincial, and municipal levels, with corresponding project scores of 100, 80, and 60. The government subsidy score is calculated as follows: ; in, The government subsidy score for the secondary evaluation indicator is: Score the project. Score the subsidy amount. is the highest government subsidy amount for each enterprise. The score is calculated based on the same method as the subsidy amount. .

[0048] The industry development trend score is quantified. The newer the industry type, the higher the industry development trend score. Industry types can be divided into emerging industries, sunrise industries, declining industries, sunset industries, and obsolete industries, with corresponding development trend scores of 80, 60, 40, 20, and 0. The more the country values ​​an industry, the higher the industry development trend score. Strategic emerging industries correspond to industry development trend scores of 90, and future industries correspond to industry development trend scores of 100. The industry development trend score is calculated as follows: (Industry type scores, strategic emerging industries scores, and future industries scores) in, Score industry trends.

[0049] The market technology demand score is quantified. The stronger the market technology demand, the higher the market technology demand score. Market technology demand can be divided into strong demand, stable demand, weak demand, and shrinking demand, and the corresponding demand scores are 100, 75, 50, and 25.

[0050] The technology market size score is quantified, with the five aspects of the technology market size corresponding to a score of 1-10. The technology market size score is the average of the scores of the five aspects, namely: ; in, The score for the secondary evaluation indicator technology market size is: The scores for the five aspects of technology market size are shown in Table 1. The size rating is the average of the five aspects (rounded off), with n=5.

[0051] S5 first-level evaluation index score calculation steps: Based on the scores of the secondary evaluation indicators and combined with the weights of the secondary evaluation indicators, the scores of the primary evaluation indicators are calculated.

[0052] Specifically, the specific method for calculating the first-level evaluation index is: ; in, Indicates the first-level evaluation index score, Indicates the secondary evaluation index score, Indicates the weight of the secondary evaluation index.

[0053] S6 Science and Technology Innovation Ability Score Calculation Steps: The score of scientific and technological innovation capability is calculated based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators.

[0054] Specifically, the method for calculating the scientific and technological innovation capability score is as follows: ; in, Indicates the score of scientific and technological innovation ability, Indicates the first-level evaluation index score, Indicates the weight of the first-level evaluation index.

[0055] The weights of the first-level evaluation indicators and the second-level evaluation indicators can be, for example, the values ​​in the following table:

[0056] The method for evaluating the technological innovation capabilities of startups provided in the embodiments of this application utilizes database technology, internet technology, and large language model technology to construct a data extraction process, extracting the data required for each secondary evaluation indicator of the startup technological innovation capability evaluation system. This significantly improves the objectivity and accuracy of the evaluation of the technological innovation capabilities of startups. Compared with existing technologies, it has the following advantages: (1) The evaluation index system for the technological innovation capability of start-ups is built around the company's products, talents, and industries. The data required by the index system is timely and does not require data with a long lag, such as patents, to support it. This provides a new solution for the evaluation of the technological innovation capability of start-ups. (2) The basic data that each indicator system relies on is extracted based on crawler technology, large model technology, and Internet technology, which solves the problem that traditional technology cannot effectively obtain innovation data of start-ups; (3) The introduction of diminishing marginal returns provides a new solution for calculating the scores of secondary evaluation indicators.

[0057] Reference Figure 2 The present application also provides a device for evaluating the technological innovation capabilities of a start-up enterprise, including: Evaluation data acquisition module, used to obtain the data required for secondary evaluation indicators and store them in the evaluation data knowledge base; A prompt word construction module is used to construct prompt words for extracting data required for each secondary evaluation indicator in the evaluation data knowledge base; The data extraction module is used to extract the data required for each secondary evaluation indicator from the evaluation data knowledge base through the constructed prompt words; The secondary evaluation indicator score quantification module is used to convert the data required for each secondary evaluation indicator into the score of the corresponding secondary evaluation indicator; A first-level evaluation indicator score calculation module is used to calculate the score of the first-level evaluation indicator based on the score of the second-level evaluation indicator and the weight of the second-level evaluation indicator; The science and technology innovation capability score calculation module is used to calculate the science and technology innovation capability score based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators.

[0058] An embodiment of the present application further provides a storage medium having a computer program stored thereon, which implements the aforementioned method when executed by a processor.

[0059] An embodiment of the present application further provides an electronic device, the electronic device comprising a processor and a memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory. When the computer program is executed by the processor, the above method is implemented.

[0060] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A method for evaluating the technological innovation capability of a start-up enterprise, characterized by: The steps include: Evaluation data acquisition step, obtaining the data required for the secondary evaluation indicators and storing them in the evaluation data knowledge base; A prompt word construction step, constructing prompt words for extracting data required for each secondary evaluation indicator in the evaluation data knowledge base; The data extraction step extracts the data required for each secondary evaluation indicator from the evaluation data knowledge base through the constructed prompt words; The second-level evaluation indicator score quantification step converts the data required for each extracted second-level evaluation indicator into the score of the corresponding second-level evaluation indicator; The first-level evaluation indicator score calculation step is based on the score of the second-level evaluation indicator and the weight of the second-level evaluation indicator to obtain the score of the first-level evaluation indicator; The steps for calculating the score of scientific and technological innovation capability are based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators to obtain the score of scientific and technological innovation capability.

2. The method for evaluating the technological innovation capability of start-ups according to claim 1 is characterized in that: The evaluation data acquisition step includes: Select a data platform; Determine the sections and fields that need to be crawled; Build crawler codes for various data platforms and perform data crawling; Clean the crawled data; The cleaned data is stored in the rating data knowledge base.

3. The method for evaluating the technological innovation capability of start-ups according to claim 1, characterized in that: The evaluation data acquisition step includes: Search through search engines; The quality of the retrieval is judged by a large language model and re-retrieved or stored.

4. The method for evaluating the technological innovation capability of start-ups according to claim 1 is characterized in that: The data extraction step includes: importing the evaluation data knowledge base into a large language model, executing the prompt words, and extracting the data required for each secondary evaluation indicator.

5. The method for evaluating the technological innovation capability of start-ups according to claim 1, characterized in that: The step of quantifying the scores of the secondary evaluation indicators includes: based on the extracted data required for the secondary evaluation indicators, according to preset data conversion rules, converting the data required for each secondary evaluation indicator into the score of the corresponding secondary evaluation indicator.

6. The method for evaluating the technological innovation capability of start-ups according to claim 1 is characterized in that: The calculation method of the first-level evaluation index score is: ; in Indicates the first-level evaluation index score, Indicates the secondary evaluation index score, Indicates the weight of the secondary evaluation index.

7. The method for evaluating the technological innovation capability of start-ups according to claim 6, characterized in that: The calculation method for the scientific and technological innovation capability score is: ; in, Indicates the score of scientific and technological innovation ability, Indicates the weight of the first-level evaluation index.

8. A device for evaluating the technological innovation capability of a start-up enterprise, characterized in that: include: Evaluation data acquisition module, used to obtain the data required for secondary evaluation indicators and store them in the evaluation data knowledge base; A prompt word construction module is used to construct prompt words for extracting data required for each secondary evaluation indicator in the evaluation data knowledge base; The data extraction module is used to extract the data required for each secondary evaluation indicator from the evaluation data knowledge base through the constructed prompt words; The secondary evaluation indicator score quantification module is used to convert the data required for each secondary evaluation indicator into the score of the corresponding secondary evaluation indicator; A first-level evaluation indicator score calculation module is used to calculate the score of the first-level evaluation indicator based on the score of the second-level evaluation indicator and the weight of the second-level evaluation indicator; The science and technology innovation capability score calculation module is used to calculate the science and technology innovation capability score based on the score of the first-level evaluation indicators and the weight of the first-level evaluation indicators.

9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory; The memory is used to store computer programs; The processor is connected to the memory and is configured to execute a computer program stored in the memory. When the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Science and technology enterprise innovation capability evaluation device and method

    CN110310004A

  • Scoring method for scientific and technological innovation ability of enterprise

    CN112598213A

  • Method and system for realizing e-commerce commodity information interaction by using large language model

    CN117592489A

  • Information extraction method and device based on large language model, equipment and storage medium

    CN119415669A

  • Innovation capability quantitative evaluation system of power grid enterprise

    CN119443840A