Scientific research project benefit estimation system and method based on big data

Abstract

The embodiment of the invention relates to the technical field of information, in particular to a scientific research project benefit estimation system and method based on big data. The system comprises a first acquisition module, a second acquisition module, a comparison module, a model module and an estimation module, the first acquisition module acquires market information, the second acquisition module reads scientific research public information, extracts a plurality of scientific research keywords of the scientific research public information, acquires a plurality of pieces of product information according to the plurality of scientific research keywords, and estimates the product information according to the plurality of product information. The comparison module compares the market information with the scientific research public information to obtain market demand data, the model module establishes a market demand model according to the market demand data, the input is demand description, the output is an estimation scale, the estimation module reads information of a target scientific research project, and the target scientific research project is input into the model module. And extracting demand description corresponding to related product information of the information of the target scientific research project, and obtaining a benefit estimation result according to the market demand model.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of information technology, and more particularly to a scientific research project benefit estimation system and method based on big data. Background Art

[0002] In today's rapidly developing technological era, the global investment in scientific and technological research and development continues to increase, driving the rapid development of technological innovation and industrial upgrading. However, despite the endless stream of scientific research achievements and many R & D projects achieving technological breakthroughs, it is difficult to transform them into actual productive forces and meet market demands, resulting in frequent waste of resources. This is mainly because the market demands are not accurately grasped during the R & D process, and there is a lack of a set of scientific and effective methods to analyze market demands and transform them into clear scientific and technological research and development directions. The existing R & D management models often focus on the development of technology itself, while ignoring the dynamic changes and actual demands of the market, resulting in the difficulty of R & D achievements to gain a foothold in the market. For example, some scientific research projects may be too theoretical or focus on exploring frontier technologies, but these technologies do not have commercial value or sufficient market demand in the short term, causing the ratio of R & D investment to output to be disproportionate. Therefore, it is necessary to study technologies that can improve the market conversion rate of scientific and technological R & D achievements and achieve the efficient utilization of scientific and technological resources. Summary of the Invention

[0003] Multiple embodiments of this specification describe a scientific research project benefit estimation system and method based on big data.

[0004] In a first aspect, an embodiment of this specification provides a scientific research project benefit estimation system based on big data, including: A first acquisition module, a second acquisition module, a comparison module, a model module, and an estimation module, The first acquisition module acquires market information, where the market information includes several market descriptions and their scales, The second acquisition module reads scientific research public information, extracts several scientific research keywords from the scientific research public information, and obtains several product information based on the several scientific research keywords, The comparison module compares the market information with the scientific research public information to obtain market demand data, where the market demand data includes demand descriptions and estimated scales, The model module establishes a market demand model based on the market demand data, where the input of the market demand model is the demand description and the output is the estimated scale, The estimation module reads the information of the target scientific research project, extracts the relevant product information from the information of the target scientific research project, obtains the corresponding demand description based on the product information, and responds to the demand description according to the market demand model to obtain the benefit estimation result of the target scientific research project.

[0005] In a second aspect, an embodiment of the present specification provides a method for estimating the benefits of scientific research projects based on big data, including the steps of: Obtain market information, where the market information includes several market descriptions and their scales. Read the publicly available scientific research information, extract several scientific research keywords from the publicly available scientific research information, and obtain several product information based on the several scientific research keywords. Compare the market information with the publicly available scientific research information to obtain market demand data, where the market demand data includes demand descriptions and estimated scales. Establish a market demand model based on the market demand data, where the input of the market demand model is the demand description and the output is the estimated scale. Read the information of the target scientific research project, extract the relevant product information of the information of the target scientific research project, obtain the corresponding demand description based on the product information, and obtain the benefit estimation result of the target scientific research project by responding to the demand description according to the market demand model.

[0006] In a third aspect, an embodiment of the present specification provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory to execute the method described in any of the above aspects.

[0007] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0008] In a fifth aspect, an embodiment of the present specification provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0009] The beneficial effects brought by the technical solutions provided by some embodiments of the present specification at least include: In multiple embodiments of this specification, the provided scientific research project benefit prediction system based on big data can help avoid waste of resources caused by incorrect R & D directions and rationally allocate R & D resources. Through the feasibility analysis of requirements and the evaluation of actual application scenarios, it ensures the feasibility and economy of R & D projects. It helps to quickly respond to market demands, launch technology products that meet market demands, and enable the development of technology to more directly benefit consumers. It guides scientific and technological R & D towards the direction of market demands, promotes the transformation and application of scientific and technological achievements, and can promote the improvement of the industrial ecosystem and the enhancement of innovation capabilities, providing assistance for the long-term development of the industry.

[0010] Other features and advantages of multiple embodiments of this specification will be further revealed in the following specific implementation manners and drawings. Brief Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of this specification, the following will briefly introduce the drawings required for the embodiments. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0012] Figure 1 Schematic diagram of the scientific research project benefit prediction system provided for the embodiments of this specification.

[0013] Figure 2 Schematic diagram of the structure of the scientific research project benefit prediction system provided for the embodiments of this specification.

[0014] Figure 3 Schematic diagram of the framework of the scientific research project benefit prediction system provided for the embodiments of this specification.

[0015] Figure 4 Schematic diagram of the interaction interface of the scientific research project benefit prediction system provided for the embodiments of this specification.

[0016] Figure 5 Schematic diagram of the process of obtaining market information provided for the embodiments of this specification.

[0017] Figure 6 Schematic diagram of the process of reading scientific research public information provided for the embodiments of this specification.

[0018] Figure 7 Schematic diagram of the process of obtaining market demand data provided for the embodiments of this specification.

[0019] Figure 8 Schematic diagram of the process of establishing a market demand model provided for the embodiments of this specification.

[0020] Figure 9Schematic diagram of the scientific research project benefit estimation method provided by the embodiments of this specification.

[0021] Figure 10 Schematic diagram of the electronic device provided by the embodiments of this specification.

[0022] Wherein: 11, market information; 12, scientific research public information; 13, product information; 14, requirement description; 15, target scientific research project; 16, benefit estimation result; 20, server; 30, terminal device; 100, first acquisition module; 200, second acquisition module; 300, comparison module; 400, model module; 500, estimation module; 1100, electronic device; 1101, processor; 1102, communication bus; 1103, user interface; 1104, network interface; 1105, memory. Specific embodiments

[0023] The technical solutions of the embodiments of this specification will be explained and described below with reference to the accompanying drawings of the embodiments of this specification. However, the following embodiments are only the preferred embodiments of this specification, not all of them. Based on the embodiments in the implementation manners, other embodiments obtained by those skilled in the art without creative efforts all fall within the protection scope of this specification.

[0024] The terms "first", "second", "third", etc. in the specification, claims and the above-mentioned drawings of this specification are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0025] In the following description, terms such as "inside", "outside", "above", "below", "left", "right", etc. indicating orientation or position relationship are only for the convenience of describing the embodiments and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of this specification.

[0026] The data involved in this application are all information and data authorized by users or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0027] Before introducing the technical solutions described in this specification, the application scenarios of the technical solutions and related technologies are introduced.

[0028] The investment in scientific and technological research and development increases significantly every year, with huge research investment. However, the situation where research results are out of touch with market demand still occurs from time to time. Although many scientific research projects have made breakthroughs in technology, they cannot be transformed into actual productive forces, cannot meet market demand, and cause waste of resources. Therefore, a technology that can extract market information 11, then form an estimate of market demand, and can estimate the benefits of scientific research projects is needed. For this reason, this specification provides a scientific research project benefit estimation system based on big data. Please refer to the appendix Figure 1 In this system, by reading market information 11 and scientific research public information 12 and comparing the two, market demand data is obtained. A market demand model is established and trained through the market demand data. Then, the information of the target scientific research project 15 is extracted to obtain relevant product information 13. The demand description 14 corresponding to the relevant product information 13 is extracted. The demand description 14 is input into the market demand model to obtain the benefit estimation result 16.

[0029] Please refer to the appendix Figure 2 A scientific research project benefit estimation system based on big data provided in this specification includes: A first acquisition module 100, a second acquisition module 200, a comparison module 300, a model module 400, and an estimation module 500. The first acquisition module 100 acquires market information 11, and the market information 11 includes several market descriptions and their scales. The second acquisition module 200 reads scientific research public information 12, extracts several scientific research keywords from the scientific research public information 12, and obtains several product information 13 according to the several scientific research keywords. The comparison module 300 compares the market information 11 with the scientific research public information 12 to obtain market demand data, and the market demand data includes a demand description 14 and an estimated scale. The model module 400 establishes a market demand model according to the market demand data. The input of the market demand model is the demand description 14, and the output is the estimated scale. The estimation module 500 reads the information of the target scientific research project 15, extracts the relevant product information 13 of the information of the target scientific research project 15, obtains the corresponding demand description 14 according to the relevant product information 13, and responds to the demand description 14 according to the market demand model to obtain the benefit estimation result 16 of the target scientific research project 15.

[0030] Exemplarily, the market description of the smartphone market is as follows: Smartphones, as an indispensable part of modern life, are constantly expanding their functions, from high-definition photography, video playback to mobile payment and augmented reality applications, etc. With the development of 5G technology, smartphones are becoming the core hub for connecting Internet of Things devices. Its market size is: According to the latest industry report, the global smartphone shipments last year were approximately 1.35 billion units, and it is expected to grow to approximately 1.43 billion units by 2026. Another exemplarily, the market description of the electric vehicle market is as follows: With the improvement of environmental awareness and technological progress, the electric vehicle (EV) market is experiencing rapid growth. Consumers' demand for longer driving ranges, fast charging technology and vehicle intelligence is increasing day by day. Its market size is: It is predicted that the global electric vehicle sales will reach approximately 14 million units in 2025, and the proportion in the total global vehicle sales is expected to exceed 10%. Another exemplarily, the market description of the health and fitness technology market is as follows: Health and fitness technology products including smartwatches, health monitoring devices, etc. are popular because they can track users' health conditions in real time. Its market size is: It is expected that by 2025, the global health and fitness technology market will reach approximately $60 billion, showing the broad prospects of this field.

[0031] Exemplarily, a piece of scientific research public information 12 is: The research progress on 5G communication technology, especially the application of millimeter waves in high-frequency bands on mobile devices. Scientific research keywords: 5G technology, millimeter waves, mobile communication. Product information 13: Smartphones that support 5G networks, especially millimeter wave bands. Another piece of scientific research public information 12 is: The research on new battery materials (such as solid-state batteries) aimed at improving the driving range and charging speed of electric vehicles. Scientific research keywords: Solid-state batteries, improvement of lithium-ion batteries, fast charging technology. Product information 13: Electric vehicles using new battery technology, with longer driving ranges and faster charging times. Another piece of scientific research public information 12: The progress of biosensor technology in wearable health monitoring devices, especially the technology for continuous blood glucose monitoring. Scientific research keywords: Biosensors, wearable technology, continuous monitoring. Product information 13: Smartwatches or other forms of wearable devices that can achieve non-invasive continuous blood glucose monitoring.

[0032] According to the aforementioned market information 11 and scientific research public information 12, comparing the two, exemplarily, a demand description 14 of market demand can be obtained as follows: With the development of 5G technology, especially the application of millimeter wave bands, the market demand for smartphones that support these new technologies is increasing day by day. Users expect to have faster data transmission speeds, lower latency and better network coverage. Its estimated scale is: By 2026, the global 5G smartphone shipments are expected to reach approximately 1.43 billion units, and among them, devices that support millimeter wave bands will become the mainstream choice in the high-end market, with an expected reach of approximately 230 million units.

[0033] Another demand description 14 for market demand is as follows: Consumers have a strong demand for improving the driving range of electric vehicles and shortening the charging time. The progress of new battery materials and technologies is regarded as the key to solving these problems. Its estimated scale: It is expected that by 2025, the global sales volume of electric vehicles will reach approximately 14 million, and models using advanced battery technologies such as solid-state batteries will occupy a significant market share, expected to reach approximately 6.5 million.

[0034] A market demand model is established. The model module 400 establishes a market demand model based on the market demand data. The input of the market demand model is the demand description 14, and the output is the estimated scale. The market demand model is a neural network model with natural language processing capabilities. Using these market demands to fine-tune a large language model can achieve obtaining a market demand model, or a neural network model such as a regression analysis is established and obtained after training to get the market demand model. Additionally, the large language model can be further pruned and distilled to reduce the volume of the large language model and lower the hardware resources required for the operation of the market demand model.

[0035] The information of the target research project 15 includes: The name of the target research project 15 is the research and development of high-performance and low-power chip technology. The project overview is that this project focuses on developing a new generation of high-performance and low-power chips, aiming to solve the balance problem between performance and energy consumption of current electronic devices. Special attention is paid to the application requirements of mobile devices, Internet of Things (IoT) devices, and data center servers 20. The key technical points are the application of new semiconductor materials to improve the energy efficiency ratio. Innovative circuit design methods reduce static and dynamic power consumption. A highly integrated design scheme reduces the physical size while enhancing the computing power.

[0036] The obtained relevant product information 13 includes: The product name is an efficient processor applicable to smartphones and tablets. The product description is that this processor uses the latest developed high-performance and low-power chip technology, which can significantly reduce energy consumption while providing excellent processing performance, extend the device usage time, and support more complex graphics processing tasks.

[0037] Extract the information of the target scientific research project 15, and the obtained requirement description 14 includes the requirements for performance improvement: The market has a strong demand for high-performance processors that can support high-definition video playback, complex game operations, and fast data processing. Especially in the context of the popularization of 5G networks, users expect devices to handle more tasks without increasing battery consumption. Requirements for low power consumption: With the wide application of mobile devices and Internet of Things devices, how to minimize power consumption as much as possible while ensuring functions has become the key. This not only affects the user experience but also relates to the portability and environmental friendliness of the device. Requirements for miniaturized design: Without affecting performance, the market tends to products with smaller size and lighter weight. This is crucial for meeting consumers' requirements for beauty and portability, and also promotes the innovation and development of miniaturized electronic products such as smart watches and health monitors.

[0038] The response result of the market demand model to the requirement description 14 obtained by extracting the target scientific research project 15 is: By 2026, the global demand for high-performance and low-power chips is expected to reach approximately 3.5 billion, mainly applied to fields such as smartphones, tablets, and Internet of Things devices. In terms of performance improvement: With the popularization of 5G technology and the growth of multimedia applications, the demand for such chips is expected to grow at a rate of 8% per year. In terms of low power consumption: Consumers' increasing attention to extending battery life has prompted manufacturers to pay more attention to low-power solutions, and the annual growth rate of this market segment is expected to reach 10%. In terms of miniaturized design: With the popularity of wearable devices and smart home devices, the demand for miniaturized design has increased significantly, and the market in this area is expected to expand at a rate of 12% per year.

[0039] According to the technologies publicly available in this field, obtain the scale and benefits of the current relevant market segment, and combine with the growth rate prediction given by the market demand model to obtain the benefit estimation result 16. At this time, the benefit estimation result 16 is the market scale value. When the benefit estimation result 16 is expressed as a growth rate, the result given by the market demand model can be directly used as the benefit estimation result 16.

[0040] Please refer to the appendix Figure 3 , which is a schematic diagram of the system architecture in the embodiment of this application. As Figure 3 shown, the system architecture includes a server 20 and a terminal device 30, and an interaction interface is set on the terminal device 30. Among them, please refer to the appendix Figure 4, the interactive interface can run on the terminal device 30 in the form of a browser, or can also run on the terminal device 30 in the form of an independent application (APP), etc. For the specific display form of the interactive interface, no limitation is made here. The server 20 involved in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. The terminal device 30 can be a smart phone, a tablet computer, a laptop computer, a handheld computer, a personal computer, a smart speaker, a smart TV, a smart watch, a vehicle-mounted device, a wearable device, etc., but is not limited thereto. The terminal device 30 and the server 20 can be directly or indirectly connected through wired or wireless communication methods, and no limitation is made in this application. The number of the server 20 and the terminal device 30 is also not limited.

[0041] Please refer to the appendix Figure 5 , when the first acquisition module 100 acquires the market information 11, the following steps are executed: Step S101) Periodically obtain the market information 11 publicly available at the website through web crawlers from a preset number of websites. Determine some industry research institution websites, professional market research platforms, industrial policy websites released by the government, etc. as data sources. Define the time interval for crawler scraping (such as daily or weekly), the selection criteria for target web pages, and the data fields to be extracted. Use web crawler tools to automatically access these websites according to the set rules and scrape the required market information 11. Ensure compliance with the regulations of the robots.txt file of each website to avoid infringement of copyright or violation of usage terms.

[0042] Step S102) Classify the market information 11 according to industry reports, market research data, user feedback information, and existing product descriptions, and then classify it by industry. First, classify the collected information into four categories according to its nature: industry reports, market research data, user feedback information, and existing product descriptions. Under each major category, further subdivide according to different industry fields (such as information technology, medical and health, automotive manufacturing, etc.). For example, all information about the smart phone industry is classified into one category, and that related to electric vehicles is classified into another category.

[0043] Step S103): Obtain the market description based on the industry report, user feedback information, and existing product descriptions, and obtain the scale of each industry according to the market research data. Extract information such as industry development trends, technological innovation points, and the situation of major competitors from the industry report to form a macro understanding of the industry. Analyze the user feedback information to obtain consumers' evaluations, suggestions, and complaints, and identify unmet needs or problem points in the market. Examine the functional characteristics, price ranges, user experiences, etc. of products in the current market through the existing product descriptions, and summarize the market status. Finally, use the data in professional market research reports to evaluate the market scale of each industry, including key indicators such as sales volume, sales amount, and growth rate. Apply statistical methods to process the original data, calculate statistics such as mean, median, and standard deviation; use time series analysis to predict the changing trend of the future market scale.

[0044] When the second acquisition module 200 reads the scientific research public information 12 and extracts several scientific research keywords from the scientific research public information 12, and obtains several product information 13 according to the several scientific research keywords, please refer to the appendix Figure 6 , perform the following steps: Step S201): Periodically obtain the public scientific research public information 12 from a preset scientific research institution. Pre-select some scientific research institutions, universities, technical forums, etc. as data sources. These sources can include, but are not limited to, academic paper databases (such as IEEE Xplore, PubMed), patent databases, white papers or technical reports published by enterprises, etc. Define the time interval for the crawler to capture (such as once a month), the selection criteria for target documents (such as keyword search in a specific field), and the data fields to be extracted (such as title, author, abstract, keywords, etc.). Use a web crawler tool to automatically access these websites according to the set rules and capture the required scientific research public information 12.

[0045] Step S202): Classify the scientific research public information 12 according to market demand, technology comparison report, and technology barrier report, and associate the scientific research institution name and application scenario description. First, classify the collected information into three categories according to its nature: research related to market demand (such as market trend analysis), technology comparison report (such as the comparison of the advantages and disadvantages between different technical solutions), and technology barrier report (such as the challenges and bottlenecks faced by the current technology). Add metadata tags to each piece of information, including the scientific research institution name, release date, application scenario description, etc., so as to quickly locate relevant information and its background during subsequent processing. Create a structured database or file system for storing and retrieving these classified scientific research public information 12.

[0046] Step S203) Extract the keywords of the scientific research public information 12 as scientific research keywords. Preprocess each scientific research document, including removing stop words, punctuation marks, and performing stemming operations. Use natural language processing (NLP) techniques, such as the TF-IDF algorithm or deep learning-based methods, to automatically extract keywords from scientific research documents. Manual annotation of some key documents can also be considered to train the model to improve accuracy. According to the specific field of the scientific research project, further screen out the most representative and relevant keyword set.

[0047] Step S204) Extract product keywords related to the scientific research keywords from the corresponding application scenario description, and generate product information 13 based on the product keywords. Read the application scenario description part and find the content related to the previously extracted scientific research keywords. Exemplarily, it involves applying a certain technology to an actual product, what problems are solved, and what improvements are brought. Or other relevant rule patterns can be obtained from the publicly available technologies in this field, and multiple relevant rule patterns are set manually. Based on the above analysis, identify the keywords describing the final product. For example, if the scientific research keyword is "low-power chip", then the product keywords may be "efficient smartphone processor", "power management unit for Internet of Things devices", etc. Combine the scientific research keywords and product keywords to construct a detailed description of product information 13. This includes but is not limited to the functional characteristics of the product, expected performance improvement, target user group, etc.

[0048] When the comparison module 300 compares the market information 11 with the scientific research public information 12 to obtain market demand data, please refer to the appendix Figure 7 , and perform the following steps: Step S301) Compare the market demand with the industry report and user feedback information, and obtain the matching part as the first matching part. Clearly define the specific content of the market demand, including but not limited to product or service categories, problems to be solved, etc. Compare the market demand with the trends mentioned in the industry report and the specific opinions and suggestions in user feedback to find common points and intersections. For example, if the market demand is to improve the battery life of a certain type of electronic product, and the user feedback also mentions this point, and the industry report predicts significant growth in this field in the next few years, then these are all contents of the first matching part.

[0049] Step S302) Compare the technical comparison report with the existing product description to obtain the matching part as the second matching part. Extract the advantages and disadvantages between different technical solutions from the technical comparison report, especially the content of technical evaluations that may have a significant impact on the performance of existing products. The product feature comparison is to compare the above technical features with the functional features of existing products to find out which technologies can be directly applied or improve existing products. Exemplarily, if a new material can significantly improve the durability of mobile phone casings, while most mobile phones on the current market use relatively fragile materials, this may be a possible content of the second matching part.

[0050] Step S303) Compare the technical barrier report with the user feedback information and the existing product description to obtain the matching part as the third matching part. Analyze the key challenges and technical bottlenecks pointed out in the technical barrier report. Relate to user pain points, and combine the dissatisfaction and complaints in user feedback (such as inconvenient product use, lack of specific functions, etc.) and the deficiencies of existing products to determine how these technical barriers affect the user experience and product performance. Exemplarily, if user feedback generally reflects that a certain software runs slowly, and the technical barrier report points out that the core algorithm on which the software depends is inefficient, this is an exemplary content of the third matching part.

[0051] Step S304) Obtain the requirement description 14 based on the first matching part, the second matching part, and the third matching part. Integrate the information obtained in the previous three steps to form a comprehensive requirement description 14 document. This document not only covers the basic situation of market demand but also includes content such as the latest technologies applicable to the market and the technical problems that need to be overcome.

[0052] Step S305) Obtain the estimated scale according to the industry report, user feedback information, and the scale corresponding to the existing product description. Estimate the size of the target market based on the market trend prediction given in the industry report, the quantity and frequency of user feedback (reflecting the potential user base), and the sales data of existing products. For example, if the industry report shows that a certain emerging technology will rapidly spread in the next few years, and the relevant user feedback is positive, plus the sales volume of existing similar products is considerable, the potential scale of the market demand can be roughly calculated.

[0053] Step S306) Obtain the market demand data according to the requirement description 14 and the estimated scale. Combine the requirement description 14 and the estimated scale to obtain detailed market demand data. This includes information such as the main direction of market demand, the key points of key technology research and development, and the expected market scale, providing solid data support for the subsequent research and development guidelines.

[0054] When the model module 400 establishes a market demand model according to the market demand data, please refer to the appendixFigure 8 , perform the following steps: Step S401) extract keywords from the demand description 14 of the market demand data as demand keywords. Preprocess the text of the demand description 14, including removing stop words, punctuation marks, etc. Apply natural language processing technology (such as TF-IDF algorithm or deep learning-based method) to automatically extract the most representative keywords from the demand description 14. These keywords should accurately reflect the core content of the market demand.

[0055] Step S402) The demand keywords of all market demand data form a demand keyword library, and the sorting position of the demand keywords in the demand keyword library is fixed. The demand keywords extracted from all market demand data are aggregated to form a demand keyword library. To ensure consistency, a fixed sequential position is assigned to each keyword in the demand keyword library. This step is crucial for subsequent vectorization processing because it ensures that the position of the same keyword in different samples is consistent.

[0056] Step S403) According to the sorting position of the demand keyword of the single market demand data in the demand keyword library, a demand keyword vector of the single market demand data is obtained. For each market demand data, a vector is generated according to the position of its demand keyword in the demand keyword library. For example, if the demand keyword library contains 100 keywords, each market demand data can be represented as a vector with a length of 100, in which the position of the corresponding keyword is marked as 1 or assigned according to a certain weight mechanism, and the remaining positions are 0 or processed according to similar rules.

[0057] Step S404) The estimated scale of the market demand data is used as the label of the demand keyword vector to form sample data. The estimated market scale corresponding to each piece of market demand data is used as the label of the demand keyword vector. In this way, a sample data set consisting of features (demand keyword vector) and target variables (market scale estimation) is formed.

[0058] Step S405) Establish and use the sample data to train a neural network model, and obtain a market demand model based on the trained neural network model.

[0059] Select a neural network model that is suitable for the task type (such as predicting market size through regression analysis) and design a suitable network architecture, including the number of layers, the number of neurons in each layer, etc. Train the selected neural network model using the prepared sample data set. During this process, adjust the model parameters to minimize the prediction error.

[0060] Evaluate the model performance through methods such as cross-validation, and further optimize the model structure or adjust the hyperparameters according to the results. After completing the training, save the final version of the market demand model for input of future new market demand data to predict its potential market size.

[0061] Wherein, when the estimation module 500 reads the information of the target scientific research project 15, extracts the relevant product information 13 of the information of the target scientific research project 15, and obtains the corresponding demand description 14 according to the product information 13, the following steps are executed: Extract the keywords of the information of the target scientific research project 15, and obtain the product information 13 of the matching relevant products according to the keywords; Obtain the corresponding demand description 14 according to the comparison between the product information 13 and the market demand data.

[0062] On the other hand, this specification provides a method for estimating the benefits of scientific research projects based on big data. Please refer to the Figure 9 appendix, including the steps: Step S501) Obtain market information 11, where the market information 11 includes several market descriptions and their scales. Step S502) Read the scientific research public information 12, extract several scientific research keywords of the scientific research public information 12, and obtain several product information 13 according to the several scientific research keywords. Step S503) Compare the market information 11 with the scientific research public information 12 to obtain market demand data, where the market demand data includes a demand description 14 and an estimated scale. Step S504) Establish a market demand model according to the market demand data, where the input of the market demand model is the demand description 14 and the output is the estimated scale. Step S505) Read the information of the target scientific research project 15, extract the relevant product information 13 of the information of the target scientific research project 15, obtain the corresponding demand description 14 according to the relevant product information 13, and obtain the benefit estimation result 16 of the target scientific research project 15 according to the response of the market demand model to the demand description 14.

[0063] Please refer to Figure 10 the structural schematic diagram of an electronic device provided by an embodiment of this specification shown in the figure.

[0064] As Figure 10As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. Among them, the user interface 1103 may include buttons, and the optional user interface may further include a standard wired interface and a wireless interface. Among them, the network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 connects various parts within the entire electronic device 1100 through various interfaces and lines, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling the data stored in the memory 1105, it executes various functions of the routing device 1100 and processes data. Optionally, the processor 1101 may be implemented in at least one of the hardware forms of DSP, FPGA, and PLA. The processor 1101 may integrate one or several combinations of a CPU, a GPU, and a modem, etc. Among them, the CPU mainly processes the operating system, the user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0065] It can be understood that the above-mentioned modem may not be integrated into the processor 1101 and may be implemented separately through a single chip.

[0066] Among them, the memory 1105 may include RAM and may also include ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1105 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 1105 may also be at least one storage device located far from the aforementioned processor 1101. The memory 1105, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 can be used to call the application programs stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0067] The embodiments of this specification also provide a computer-readable storage medium. Instructions are stored in this computer-readable storage medium. When they run on a computer or a processor, the computer or the processor is caused to execute multiple steps in the above embodiments. If each component module of the above electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the computer-readable storage medium.

[0068] The embodiments of this specification also provide a computer program product, including a computer program which, when executed by a processor, implements multiple steps in the above embodiments.

[0069] Without conflict, the technical features in this embodiment and the implementation solutions can be combined arbitrarily.

[0070] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes multiple computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this specification are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that integrates multiple available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a Digital Versatile Disc (DVD)), or a semiconductor medium (for example, a Solid State Disk (SSD)), etc.

[0071] When implemented by hardware or firmware, the foregoing method flow is programmed into a hardware circuit to obtain a corresponding hardware circuit structure and implement corresponding functions. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logical functions are determined by a user's programming of the device. A designer can program on their own to "integrate" a digital system on a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there are not only one but many kinds of HDLs. Those skilled in the art should also be clear that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain a hardware circuit that implements the logical method flow.

[0072] The embodiments described above are only described in the preferred embodiment manner of this specification and do not limit the scope of this specification. Without departing from the design spirit of this specification, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of this specification shall fall within the protection scope determined by the claims of this specification.

Claims

1. A scientific research project benefit estimation system based on big data, characterized in that: include: A first acquisition module, a second acquisition module, a comparison module, a model module and an estimation module, The first acquisition module acquires market information, wherein the market information includes a plurality of market descriptions and their scales. The second acquisition module reads the scientific research public information, extracts a number of scientific research keywords from the scientific research public information, and obtains a number of product information according to the scientific research keywords. The comparison module compares the market information with the scientific research public information to obtain market demand data, wherein the market demand data includes demand description and estimated scale. The model module establishes a market demand model according to the market demand data, wherein the input of the market demand model is the demand description and the output is the estimated scale. The estimation module reads the information of the target scientific research project, extracts relevant product information of the target scientific research project, obtains the corresponding demand description according to the relevant product information, responds to the demand description according to the market demand model, and obtains the benefit estimation result of the target scientific research project.

2. According to the big data-based scientific research project benefit estimation system of claim 1, it is characterized in that: When the first acquisition module acquires market information, the following steps are performed: Periodically obtain the market information disclosed at a number of preset websites through web crawlers; Classify the market information according to industry reports, market research data, user feedback information, and existing product descriptions, and then classify by industry; A market description is obtained based on the industry reports, user feedback information, and existing product descriptions, and the scale of each industry is obtained based on the market research data.

3. According to the big data-based scientific research project benefit estimation system of claim 2, it is characterized in that: The second acquisition module reads the scientific research public information, extracts a number of scientific research keywords from the scientific research public information, and obtains a number of product information according to the scientific research keywords, and performs the following steps: Periodically obtain public scientific research information from pre-set scientific research institutions; Classify the public scientific research information according to market demand, technology comparison report, and technology barrier report, and associate the name of the scientific research institution and the description of the application scenario; Extracting keywords from the scientific research public information as scientific research keywords; Extract product keywords related to scientific research keywords in the corresponding application scenario description, and generate product information based on the product keywords.

4. According to the big data-based scientific research project benefit estimation system of claim 3, it is characterized in that: The comparison module compares the market information with the scientific research public information to obtain market demand data, and performs the following steps: Compare the market demand with the industry report and user feedback information to obtain a matching part as a first matching part; Compare the technical comparison report with the existing product description to obtain a matching portion as a second matching portion; Compare the technical barrier report with the user feedback information and the existing product description to obtain a matching part as a third matching part; Obtaining a requirement description according to the first matching part, the second matching part, and the third matching part; Obtain an estimated scale based on the industry reports, user feedback information, and the scale corresponding to the existing product description; Obtain market demand data based on the demand description and estimated scale.

5. According to the big data-based scientific research project benefit estimation system of claim 1, it is characterized in that: When the model module establishes a market demand model according to the market demand data, the following steps are performed: Extracting keywords of the demand description of the market demand data as demand keywords; The demand keywords of all market demand data constitute a demand keyword library, and the ranking positions of the demand keywords in the demand keyword library are fixed; Obtaining a demand keyword vector of the single market demand data according to a ranking position of the demand keyword of the single market demand data in the demand keyword library; Using the estimated scale of the market demand data as a label of the demand keyword vector to form sample data; A neural network model is established and trained using the sample data, and a market demand model is obtained based on the trained neural network model.

6. According to the big data-based scientific research project benefit estimation system of claim 1, it is characterized in that: The estimation module reads the information of the target scientific research project, extracts the relevant product information of the target scientific research project, and performs the following steps when obtaining the corresponding demand description according to the product information: Extract keywords from the information of the target scientific research project, and obtain product information of matching related products according to the keywords; Based on the comparison of the product information and the market demand data, a corresponding demand description is obtained.

7. A method for estimating the benefits of scientific research projects based on big data, characterized in that: Includes steps: Obtaining market information, including several market descriptions and their sizes, Reading scientific research public information, extracting several scientific research keywords from the scientific research public information, and obtaining several product information according to the several scientific research keywords. Compare the market information with the scientific research public information to obtain market demand data, wherein the market demand data includes demand description and estimated scale, A market demand model is established according to the market demand data, wherein the input of the market demand model is the demand description and the output is the estimated scale. The information of the target scientific research project is read, relevant product information of the target scientific research project is extracted, a corresponding demand description is obtained according to the relevant product information, the demand description is responded to according to the market demand model, and a benefit estimation result of the target scientific research project is obtained.

8. An electronic device, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to claim 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to claim 7 is implemented.

Images