Multi-dimensional enterprise department and wound ability evaluation method and computer program product

Abstract

The invention discloses a multi-dimensional enterprise department and wound ability evaluation method and a computer program product, and relates to the technical field of big data processing and application. The multi-dimensional enterprise department and wound ability evaluation method comprises the following steps: pre-constructing a quantitative index and a qualitative index; obtaining enterprise related data; and counting the enterprise related data, and dividing the enterprise related data into numeric data and text data. Calculating the numeric data, assigning values to the corresponding quantitative indexes according to calculation results of the numeric data, and recording the values as quantitative index values; analyzing the text type data, assigning values to corresponding qualitative indexes according to analysis results of the text type data, and recording the values as qualitative index values; and normalizing the quantitative index value and the qualitative index value, and generating an enterprise department and wound ability score. By adopting the technology provided by the invention, the enterprise can be scored in multiple dimensions, and the accuracy of the enterprise department and wound scoring mechanism is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data processing and application technology, and specifically to a multi-dimensional enterprise scientific and technological innovation capability evaluation method and a computer program product. Background Art

[0002] High and New Technology Enterprises are the key force in promoting the improvement of the country's innovation level. Since the official launch of the Science and Technology Innovation Board, it has promoted the deep integration of scientific and technological innovation and the capital market, and increased the emphasis on the scientific and technological innovation capabilities of enterprises, especially those with core technologies and high growth potential.

[0003] However, the evaluation of technological innovation is a complex issue, which is limited by different factors such as the differences in the industry in which the enterprise is located, the path of technological development and the differences in market acceptance. At present, there are still the following problems in the evaluation of the technological innovation capabilities of enterprises: (1) The types of enterprise data are numerous, widely distributed, and have scattered sources: In addition to the business information, financial data, intellectual property rights, and news reports of enterprises, it may also include enterprise-related data such as new product launches and financing that are widely distributed in every corner of the Internet.

[0004] (2) Current evaluation indicators are too centralized and one-sided: The traditional evaluation system mainly focuses on hard indicators such as technological innovation, R&D investment and patent output, and tends to ignore the impact of soft factors such as corporate financing and new product launches on scientific and technological innovation capabilities; (3) Qualitative indicators are difficult to quantify and evaluate: In addition to the above quantitative indicators, there is also public information such as corporate honors, product information and a large amount of media coverage. There is a lack of unified quantitative standards to evaluate the scientific and technological innovation capabilities of enterprises; (4) Unbalanced enterprise scoring: When evaluating the technological innovation capabilities of enterprises, it is easy for most enterprises to score low, while only a few enterprises score high, forming an uneven "80 / 20 rule" distribution phenomenon, resulting in an obvious tailing phenomenon, making it difficult to highlight medium-level and above excellent enterprises. Summary of the invention

[0005] The present invention provides a multi-dimensional enterprise scientific and technological innovation capability evaluation method and a computer program product to solve the problem of uneven enterprise scoring in the prior art.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is to provide a multi-dimensional enterprise scientific and technological innovation capability evaluation method, which includes: Pre-constructing quantitative indicators and qualitative indicators; obtaining enterprise-related data, wherein the enterprise-related data includes government data obtained from a first data source and network data obtained from a second data source; counting the enterprise-related data, and dividing the enterprise-related data into numerical data and text data.

[0007] Calculate the numerical data, and assign values ​​to the corresponding quantitative indicators according to the calculation results of the numerical data, which are recorded as quantitative indicator values; parse the text data, and assign values ​​to the corresponding qualitative indicators according to the parsing results of the text data, which are recorded as qualitative indicator values; normalize the quantitative indicator values ​​and the qualitative indicator values, and generate an enterprise science and technology innovation capability score.

[0008] The technical solution provided by the present invention has the following beneficial effects compared with the prior art: By integrating the government data of the first data source and the network data of the second data source, and distinguishing them into numerical data and text data for independent quantitative calculation, the scientific and technological innovation capabilities of enterprises can be evaluated more comprehensively and objectively. Among them, the addition of text data and its analysis method realizes the quantification of qualitative indicators, which can score enterprises in multiple dimensions, thereby improving the accuracy of the enterprise scientific and technological innovation scoring mechanism.

[0009] In addition, through the above-mentioned normalized quantitative indicator values ​​and qualitative indicator values, the evaluation results can be converted into numerical scores, which is convenient for intuitive comparison among multiple enterprises, and can quickly identify enterprises with medium and above scientific and technological innovation capabilities, improve screening efficiency, and provide data support for subsequent policy braking, investment decisions, etc.

[0010] In some implementations, normalizing the quantitative indicator value and the qualitative indicator value and generating an enterprise scientific and technological innovation capability score includes: The quantitative index value and the qualitative index value are normalized to the maximum value, which is recorded as:

[0011] Wherein, X represents the quantitative index value and the qualitative index value, Represents the base number, , The logarithmic weighted result of the quantitative index value and the qualitative index value is represented;

[0012] in, is the base coefficient, , Indicates the lowest score of the enterprise's scientific and technological innovation ability. represents the minimum value of logarithmic weighting, represents the maximum value of logarithmic weighting, Represents the normalized score of the enterprise's scientific and technological innovation capability.

[0013] In some implementation schemes, generating an enterprise's scientific and technological innovation capability score includes: generating a total score for the enterprise's scientific and technological innovation capability, and corresponding indicator scores for the qualitative indicators and the quantitative indicators.

[0014] In some embodiments, parsing the text data includes: The text data is divided into long text data and short text data; the subject type and / or sentiment classification of the long text data is determined, wherein the subject type includes product release, project cooperation and engineering progress, and the sentiment type includes positive, neutral and negative.

[0015] Perform weighted calculation on the long text data of different topic types and different sentiment types, and assign values ​​to the corresponding qualitative indicators; identify key entities in the short text data, and assign values ​​to the qualitative indicators based on the key entities; calculate the position and proportion of the company's R&D products in the industrial chain through mathematical modeling, and assign values ​​to the corresponding qualitative indicators based on the mathematical modeling results.

[0016] In some embodiments, parsing the text data further includes: Preset event type labels, classify the short text data, and assign type labels to the classification results of the short text data; build an industrial chain model, wherein the industrial chain model covers multiple industrial fields.

[0017] Map the enterprise products in the short text data to the industrial chain model, and determine the positioning of the enterprise products in the industrial chain; calculate the proportion of the enterprise products in the industrial field corresponding to the industrial chain model.

[0018] In some implementation schemes, the pre-constructed quantitative indicators and qualitative indicators include preset first-level indicators, wherein the first-level indicators include scientific and technological innovation resources, scientific and technological innovation input, scientific and technological innovation output, achievement transformation and value realization.

[0019] In some implementation schemes, the pre-constructed quantitative indicators and qualitative indicators further include: subdividing the primary indicators to form secondary indicators, wherein the secondary indicators include quantitative secondary indicators and qualitative secondary indicators.

[0020] In some embodiments, the acquiring of enterprise-related data, wherein the enterprise-related data includes government data acquired by a first data source and network data acquired by a second data source, includes: The government affairs data includes enterprise financial data and government-related information, wherein the enterprise financial data includes one or more of research and development expenses, operating income and technical contract data.

[0021] The network data includes corporate business information, intellectual property information, corporate website information and news media information, wherein the corporate business information includes one or more of the company's registered capital, the number of employees and the company's qualifications, and the news media information includes one or more of company report information, product release information and project cooperation information.

[0022] In some embodiments, the quantitative indicator values ​​and the qualitative indicator values ​​are normalized to generate an enterprise's scientific and technological innovation capability score, and also include: when the enterprise scientific and technological innovation capability scores of multiple enterprises are simultaneously evaluated, the enterprise scientific and technological innovation capability scores of the multiple enterprises conform to a normal distribution.

[0023] In some embodiments, the present application also provides a computer program product, which includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the above-mentioned multi-dimensional enterprise scientific and technological innovation capability evaluation method is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work, among which: Figure 1 This is a schematic diagram of a process of an embodiment of a multi-dimensional enterprise scientific and technological innovation capability evaluation method provided by the present invention. Figure 1 ; Figure 2 This is a schematic diagram of a process of an embodiment of a multi-dimensional enterprise scientific and technological innovation capability evaluation method provided by the present invention. Figure 2 . DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 As shown, Figure 1 The following is a flow chart showing an embodiment of a multi-dimensional enterprise scientific and technological innovation capability evaluation method provided by the present application. Figure 1 .

[0027] In some implementation schemes, the multi-dimensional enterprise scientific and technological innovation capability evaluation method includes: Step S100: pre-constructing quantitative indicators and qualitative indicators.

[0028] Quantitative indicators refer to indicators that can be measured and quantified by numerical values. For example, quantitative indicators can be operating income, R&D investment expenses, etc. in financial data. They can provide specific numerical results, which are convenient for comparison and statistical analysis. Qualitative indicators refer to indicators that involve subjective judgment and interpretation, and descriptive descriptions. For example, qualitative indicators can be emotional tendencies reported by the media, corporate events and activities (such as product launches and project cooperation).

[0029] By pre-constructing quantitative and qualitative indicators, the system can conduct a comprehensive and structured assessment of an enterprise's scientific and technological innovation capabilities when analyzing the enterprise's scientific and technological innovation capabilities.

[0030] Step S200, obtaining enterprise related data.

[0031] The enterprise-related data includes government data obtained from the first data source and network data obtained from the second data source. The first data source refers to data obtained from relevant government departments, which is authoritative. Government data includes but is not limited to enterprise financial information and government subsidy amount data. For example, enterprise financial information includes R&D expenses, operating income, and technical contracts.

[0032] The second data source refers to data sources represented by public news information on the Internet, which has a wide coverage and is more comprehensive. Among them, network data includes news media information, corporate business information, intellectual property information, corporate official website information, etc. For example, news media information includes company reports, product releases, and project cooperation; corporate business information includes corporate registered capital, number of employees, corporate qualifications, etc.; intellectual property information includes corporate patent data, trademark data, and software copyright data; corporate official website information includes corporate products and services, etc.

[0033] Compared with the current data sources for evaluating the scientific and technological innovation capabilities of enterprises, this application adds news media information and official corporate website information in the second data source, for example, information related to the enterprise in Internet news (news title, time, content and tags, etc.) can be captured through API interfaces, etc. This makes the evaluation of the scientific and technological innovation capabilities of enterprises more comprehensive and accurately evaluates the scientific and technological innovation capabilities of enterprises from multiple dimensions. Exemplarily, step S200 also includes real-time monitoring of the first data source and the second data source when acquiring data to ensure timely updating of data.

[0034] Step S300, collecting statistics on enterprise-related data, and dividing the enterprise-related data into numerical data and text data.

[0035] The data obtained in step S200 is classified into quantifiable data (numeric data) and data that needs further analysis (text data), so as to pre-process the numeric data and text data into a unified format. Exemplarily, the numeric data mainly includes the business data and financial data of the enterprise, such as registered capital, number of employees and R&D expenses, wherein step S2300 also includes pre-processing the numeric data, such as data conversion (such as conversion of numeric data such as registered capital data and R&D expenses to a unified unit) and data cleaning (processing missing values, outliers and duplicate values).

[0036] Step S400, calculating numerical data, and assigning values ​​to corresponding quantitative indicators according to the calculation results of the numerical data, which are recorded as quantitative indicator values.

[0037] According to the pre-built quantitative indicators and the adjustment coefficients corresponding to the quantitative indicators, the assignment of the quantitative indicators corresponding to the numerical data can be obtained. For example, if the registered capital in the pre-built quantitative indicators is preset and the adjustment coefficient corresponding to the quantitative indicators is preset, then when the registered capital of the enterprise is 7 million, the assignment of its registered capital is 7 points.

[0038] Combination Figure 2 As shown, Figure 2 The following is a flow chart showing an embodiment of a multi-dimensional enterprise scientific and technological innovation capability evaluation method provided by the present application. Figure 2 .

[0039] Step S500: parse the text data, and assign values ​​to the corresponding qualitative indicators according to the parsing results of the text data, which are recorded as qualitative indicator values. Figure 2 As shown, step S500 includes: Step S510, dividing the text data into long text data and short text data.

[0040] According to the text structure, the text data is classified (for example, a text character count threshold is set). Long text data refers to texts containing a large number of characters, sentences, and short circuits, such as news reports about companies, chapters of related books, etc. Short text data refers to texts containing less information and detailed entity descriptions, such as company product labels. By distinguishing the text data in the above way, different parsing methods can be used to process it, so as to quickly extract the key information of the text data.

[0041] Step S520, determining the topic type and / or sentiment classification of the long text data.

[0042] Since long text data covers more information, for example, natural language processing (NPL) technology can be used for long text data, such as through Bi-LSTM, BERT, CNN and ResNet to perform task splitting, module association and unified processing mechanism for enterprises, products and event types and emotional elements in long text data, so as to improve the recognition effect and accuracy of long text data.

[0043] Among them, topic types include product distribution, project cooperation and engineering progress; deep learning models (such as LSTM, BERT) are used to perform sentiment classification on long text data, where the sentiment types include positive, neutral and negative.

[0044] Step S530 , weighted calculation is performed on the long text data of different topic types and different sentiment types, and corresponding qualitative indicators are assigned values.

[0045] The weight coefficients are predefined for different topic types and sentiment types. For example, when the topic type of a news report is "product release" and the sentiment type is "positive", the weight coefficient of the news report is the topic weight coefficient multiplied by the sentiment weight coefficient. The weight coefficients of multiple news reports are superimposed in sequence to form the value of the qualitative indicator (media coverage). The above-mentioned assignment steps can realize the quantification of long text data. Compared with the current evaluation system, the evaluation of corporate reputation and market recognition has been added, so as to evaluate the scientific and technological innovation capabilities of enterprises in a more multi-dimensional and scientific manner.

[0046] In some implementation plans, such as the news title of long text data "XXX Shares: There are many opportunities in the new energy vehicle field, and the MEMS product line strives to reach world-class standards" and the news content "What are the highlights of XXX Shares in 2023? Answer: This year, the MEMS product line strives to reach world-class levels, and cooperation with major customers will speed up the pre-research of some products. In terms of products: The application of depth pressure gauges and altimeters in wearable devices will bring considerable profits...", the news topic type ("product information") and sentiment type ("positive") can be obtained after algorithm analysis.

[0047] For example, statistics of long text in running script show that there are 124 positive, 34 negative and 57 neutral media reports on enterprises in recent period, and the weight of "positive" is set to "1", and the weight of "negative" is set to "-1". The weight of "neutral" is "0", and the weighted calculation is 90, and the score of "media reports" of qualitative indicators is 8 points.

[0048] Step S540, identifying key entities in the short text data, and assigning values ​​to qualitative indicators according to the key entities.

[0049] For example, named entity recognition (NER) technology can be used for short texts to extract key entities from short texts. For example, product names such as chips, batteries, and solar energy related to corporate products can be extracted, and then the entities can be classified into corresponding entity types, and then different entity types can be assigned values ​​according to preset weight coefficients. Among them, the weight coefficient is set according to the industry field to reduce the interference of different industry fields on the evaluation of corporate scientific and technological innovation capabilities.

[0050] Step S550, calculating the position and proportion of the enterprise's R&D products in the industrial chain through mathematical modeling, and assigning values ​​to corresponding qualitative indicators according to the mathematical modeling results, including: Preset event type labels, classify short text data, and assign type labels to the classification results of short text data; build an industrial chain model, where the industrial chain model covers multiple industrial fields; map the enterprise products in the short text data to the industrial chain model, and determine the positioning of the enterprise products in the industrial chain; calculate the proportion of enterprise products in the corresponding industrial fields in the industrial chain model. Exemplarily, the above type labels include 64 enterprise event types, and the above industrial fields include 110 industrial fields. However, this application does not limit the number of type labels and industrial fields.

[0051] In some application scenarios, such as inputting "XXX Microelectronics Technology Co., Ltd.", the entity "Internet of Vehicles_Sensor, Industrial Mother Machine_Sensor, Smart Home_Sensor, Smart Equipment_Sensor, Internet of Things_Chip, Internet of Things_Infrared Sensor, Drone_MEMS Sensor, Integrated Circuit_Oscillator..." can be obtained from the short text data. After deduplication and sorting, it can be obtained that the company's enterprise products cover the main industrial chain of 14 industrial fields, including Internet of Vehicles, drones, semiconductors, smart wearable devices, and smart equipment. A weight can be assigned to each industrial field, where the weight is determined based on factors such as the market size and technical importance of the industrial field. The "Indicator Industry Technology Proportion" of the qualitative indicator can be assigned a value of 7 points. The technology proportion of each of the above-mentioned enterprise products in the industrial chain is calculated, and the sum of the proportion of each product in the industrial chain is 0.46, and the "Industry Technology Coverage" of the qualitative indicator is assigned a value of 8 points.

[0052] In the embodiments of the present application, by quantifying text data, it is possible to know the market's recognition of the enterprise, and by knowing the position of the enterprise in the industrial chain, a more accurate evaluation of the enterprise can be made.

[0053] Step S600, normalize the quantitative indicator values ​​and the qualitative indicator values, and generate the enterprise's scientific and technological innovation capability score.

[0054] The final values ​​of all qualitative and quantitative indicators are scaled proportionally so that they fall within a constant range (e.g., 1 to 10 points or 1 to 100 points), so as to facilitate the comparison of different indicators and better meet the user's data usage habits. For example, the normalized quantitative indicator values ​​and qualitative indicator values ​​can be normalized by maximum value, logarithmic normalization, and Z score normalization, etc., which is not limited in this application.

[0055] In some application scenarios, when the scientific and technological innovation capabilities of multiple enterprises are scored at the same time, the scores of the scientific and technological innovation capabilities of multiple enterprises conform to the normal distribution. This makes it possible to achieve that the scientific and technological innovation capability scores of most enterprises are distributed near the mean, and the number of high-scoring and low-scoring enterprises far from the mean gradually decreases, which is convenient for effectively tapping medium and above excellent scientific and technological innovation potential enterprises, so that enterprises that can obtain more policy support and resource docking can be more accurate. For example, the scoring range can also be set according to the percentage system, so that users can quickly screen excellent enterprises.

[0056] In some implementation schemes, step S600, normalizing the quantitative indicator values ​​and the qualitative indicator values ​​and generating the enterprise's scientific and technological innovation capability score, includes: The quantitative index values ​​and qualitative index values ​​are normalized to the maximum value, which is recorded as:

[0057] Among them, X represents the quantitative index value and the qualitative index value, Represents the base number, , It represents the logarithmic weighted result of the quantitative index value and the qualitative index value;

[0058] in, is the base coefficient, , Indicates the lowest score of the enterprise's scientific and technological innovation ability. represents the minimum value of logarithmic weighting, represents the maximum value of logarithmic weighting, Represents the normalized score of the enterprise's scientific and technological innovation capability.

[0059] For example, logarithmic transformation can reduce the impact of outliers and retain the relative size relationship of the scores of each indicator in the current scientific and technological innovation capability score, as well as the relative size relationship of the total scientific and technological innovation capability score of multiple companies.

[0060] In some implementation schemes, step S100 pre-constructs quantitative indicators and qualitative indicators, including pre-setting first-level indicators, wherein the first-level indicators include scientific and technological innovation resources, scientific and technological innovation input, scientific and technological innovation output, achievement transformation and value realization.

[0061] For example, scientific and technological innovation resources refer to the talent base of an enterprise for scientific and technological innovation; scientific and technological innovation investment refers to the investment of an enterprise in R&D activities; scientific and technological innovation output refers to the technological achievements directly produced by the enterprise through R&D activities; achievement transformation refers to the products and services generated by the application of technological achievements to the market; and the commercial value of an enterprise based on scientific and technological innovation.

[0062] In some implementation schemes, step S100, pre-constructing quantitative indicators and qualitative indicators, also includes: subdividing the primary indicators and forming secondary indicators, wherein the secondary indicators include quantitative secondary indicators and qualitative secondary indicators.

[0063] For example, this application divides the scientific and technological innovation capabilities of enterprises into five indicators and further refines 41 secondary indicators corresponding to the five indicators. Among them, this application does not limit the number of secondary indicators, for example, more or fewer secondary indicators can be set according to evaluation preferences.

[0064] In some application scenarios, users can obtain the total score, first-level indicator scores and second-level indicator scores of the company's scientific and technological innovation capabilities by entering the company name. The first-level indicator score is the sum of its subordinate second-level indicator scores, and the total score is the sum of all first-level indicator scores.

[0065] For example, when the user enters "XXX Microelectronics Technology Co., Ltd.", the company's total scientific and technological innovation ability score is 90.02 points, including the first-level indicators: scientific and technological innovation resources 73 points, scientific and technological innovation investment 69.1 points, scientific and technological innovation output 69.6 points, results transformation 61 points, and value realization 70 points.

[0066] Secondary indicators under scientific and technological innovation resources: registered capital 7 points, number of employees 9 points, number of company executives 8 points, shareholder information 8 points, corporate honors 7 points, platform qualifications 8 points, number of partners 4 points, number of group members 2 points, media coverage 8 points, third-party rating 5 points, and government subsidies 10 points.

[0067] Secondary indicators under the investment in scientific and technological innovation: salary level 6 points, R&D staff size 5 points, R&D staff quality 9.4 points, R&D team core capabilities and stability 9 points, number of R&D institutions 0 points, R&D expenses 10 points; Secondary indicators under scientific and technological innovation output: number of intellectual property rights (9 points), number of patents (9 points), patent growth rate (1 point), average number of patents in the past three years (8 points), ratio of valid invention patent applications (6 points), number of patents under review (7 points), geographical distribution of patents (6 points), average patent value (6 points), average expected life span of patents (5 points), proportion of industrial technology (7 points), industrial technology coverage (8 points), number of software works (4 points), software works growth rate (10 points), and number of trademark registrations (4 points).

[0068] Secondary indicators under the transformation of results: number of successful bids by the enterprise 2 points, number of product outputs 6 points, number of technical contracts 6 points, number of investments and financings 8 points, and amount of investments and financing 10 points.

[0069] Secondary indicators under value realization: number of media reports on products 7 points, number of customers 6 points, operating income 7 points, and technology product income 8 points.

[0070] In some embodiments, the present application also provides a computer program product, which includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the above-mentioned multi-dimensional enterprise scientific and technological innovation capability evaluation method is implemented.

[0071] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0072] The above description is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, should be included in the protection scope of the present invention.

Claims

1. A multi-dimensional enterprise scientific and technological innovation capability evaluation method, characterized in that: include: Pre-construct quantitative and qualitative indicators; Acquire enterprise-related data, wherein the enterprise-related data includes government affairs data acquired by a first data source and network data acquired by a second data source; Counting the enterprise-related data, and dividing the enterprise-related data into numerical data and text data; Calculating the numerical data, and assigning values ​​to the corresponding quantitative indicators according to the calculation results of the numerical data, which are recorded as quantitative indicator values; Parsing the text data, and assigning values ​​to corresponding qualitative indicators according to the parsing results of the text data, recorded as qualitative indicator values; Normalize the quantitative indicator values ​​and the qualitative indicator values, and generate a scientific and technological innovation capability score for the enterprise.

2. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 1 is characterized in that: Normalizing the quantitative indicator values ​​and the qualitative indicator values, and generating an enterprise scientific and technological innovation capability score, including: The quantitative index value and the qualitative index value are normalized to the maximum value, which is recorded as: Wherein, X represents the quantitative index value and the qualitative index value, Represents the base number, , The logarithmic weighted result of the quantitative index value and the qualitative index value is represented; in, is the base coefficient, , Indicates the lowest score of the enterprise's scientific and technological innovation ability, represents the minimum value of logarithmic weighting, represents the maximum value of logarithmic weighting, Represents the normalized score of the enterprise's scientific and technological innovation capability.

3. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 1 is characterized in that: The generating of enterprise scientific and technological innovation capability score includes: Generate the total score of the enterprise's scientific and technological innovation capability, the corresponding indicator scores of the qualitative indicators and the quantitative indicators.

4. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 1 is characterized in that: The parsing of the text data comprises: Dividing the text data into long text data and short text data; Determine the topic type and / or sentiment classification of the long text data, wherein the topic type includes product release, project cooperation and engineering progress, and the sentiment type includes positive, neutral and negative; Performing weighted calculation on the long text data of different topic types and different sentiment types, and assigning values ​​to the corresponding qualitative indicators; Identifying key entities in the short text data, and assigning values ​​to the qualitative indicators according to the key entities; The position and proportion of the enterprise's R&D products in the industrial chain are calculated through mathematical modeling, and the corresponding qualitative indicators are assigned values ​​according to the mathematical modeling results.

5. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 4 is characterized in that: The parsing of the text data further includes: Preset event type label, Classifying the short text data and assigning a type label to the classification result of the short text data; Construct an industrial chain model, wherein the industrial chain model covers multiple industrial fields Mapping the enterprise products in the short text data to the industrial chain model, and determining the positioning of the enterprise products in the industrial chain; Calculate the proportion of the enterprise's products in the corresponding industrial field in the industrial chain model.

6. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 1 is characterized in that: The pre-constructed quantitative indicators and qualitative indicators include preset first-level indicators, wherein the first-level indicators include scientific and technological innovation resources, scientific and technological innovation input, scientific and technological innovation output, achievement transformation and value realization.

7. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 6 is characterized in that: The pre-constructed quantitative indicators and qualitative indicators also include: subdividing the primary indicators to form secondary indicators, wherein the secondary indicators include quantitative secondary indicators and qualitative secondary indicators.

8. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to claim 1 is characterized in that: The obtaining of enterprise-related data, wherein the enterprise-related data includes government affairs data obtained from a first data source and network data obtained from a second data source, includes: The government affairs data includes enterprise financial data and government-related information, wherein the enterprise financial data includes one or more of research and development expenses, operating income, and technical contract data; The network data includes corporate business information, intellectual property information, corporate website information and news media information, wherein the corporate business information includes one or more of the company's registered capital, the number of employees and the company's qualifications, and the news media information includes one or more of company report information, product release information and project cooperation information.

9. The multi-dimensional enterprise scientific and technological innovation capability evaluation method according to any one of claims 1 to 8, characterized in that: Normalizing the quantitative indicator values ​​and the qualitative indicator values ​​and generating a scientific and technological innovation capability score for the enterprise, further comprising: When the scientific and technological innovation capabilities of multiple enterprises are scored at the same time, the scientific and technological innovation capability scores of the multiple enterprises conform to the normal distribution.

10. A computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the multi-dimensional enterprise scientific and technological innovation capability evaluation method according to any one of claims 1 to 9.

Images