Construction method and system of electric power system industrial chain achievement output quality evaluation model

Abstract

The invention relates to the technical field of achievement evaluation, and discloses a construction method and system for an industrial chain achievement output quality evaluation model of a power system, and the method comprises the steps: collecting the technical information of a target industrial chain, building a database, and classifying and storing the collected technical information; processing the technical information to generate scoring data, and establishing a scoring library according to the scoring data; and according to the data string and the score data in the score library, constructing a quality evaluation model, and calculating a result score. According to the method, the achievement literature is simplified into the data string of the key feature word segments and the classification word segments, rapid and dynamic updating is achieved, and literature reanalysis is not needed. The crawler technology monitors the public platform, obtains the latest scientific research data, and automatically updates the classification score library through the preset score library, so that the evaluation system can be dynamically adjusted along with the technology development. And the result score is comprehensively evaluated through the classification word segments and the key feature word segments, so that the evaluation is more accurate and real-time and has macroscopic adaptability.

Description

Technical Field

[0001] The present invention relates to the technical field of achievement evaluation, and specifically to a method and system for constructing an achievement output quality evaluation model for an electric power system industry chain. Background Art

[0002] At present, the digital transformation of industry has become a general consensus. Accelerating the application of scientific and technological achievements and improving the level of transformation of scientific and technological achievements will play an important role in promoting the high-quality development of enterprises. In view of the urgent need for the digital transformation of power grids, the development of traditional power grids towards digitalization and intelligence will inevitably be accompanied by the birth of new major technological achievements. However, in the process of transformation of scientific and technological achievements, there are problems such as imbalance between output and industrialization and low efficiency of information transmission, which will restrict the release of the potential of scientific and technological achievements. Therefore, conducting research on the layout capabilities and cultivation strategies of major achievements in the development of the new power system industrial chain suitable for standard digital transformation, building research on the classification and grading of key achievements, improving the multi-party collaborative model, and optimizing the output path of achievement content can better play the role of the major achievement system, promote closer integration of science and technology with economic and social development, and accelerate the transformation of scientific and technological achievements into real productivity.

[0003] The prior art discloses an intellectual property achievement transformation analysis and evaluation system based on big data processing, which obtains the basic value of the same type of technology based on crawler technology, conducts value evaluation based on similarity, and automatically evaluates the intellectual property achievements. However, some achievements may be research based on immature technologies, such as gas storage and power dispatch, application and protection. Before the immature technology is further developed, these achievements are evaluated as low value due to their low practicality. When the immature technology is improved, the practicality of the achievements relying on this technology will be significantly improved, the defects will be overcome, and the value may be greatly improved. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that in the prior art, after the evaluation is completed, the evaluation criteria will not be changed and the evaluation results will not be updated, thereby burying some high-value achievements.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for constructing a quality evaluation model for the output of results of an electric power system industrial chain, comprising: collecting technical information of the target industrial chain, establishing a database, classifying and storing the collected technical information; processing the technical information to generate scoring data, and establishing a scoring library based on the scoring data; constructing a quality evaluation model based on the data strings and scoring data in the scoring library, and calculating the results score.

[0007] As a preferred scheme for the construction method of the power system industrial chain output quality evaluation model described in the present invention, the technical information includes the technology, achievement documents, scientific research and development materials, technology maturity and practical results of each node in the target industrial chain.

[0008] As a preferred solution for the construction method of the power system industrial chain output quality evaluation model described in the present invention, the database includes a classification library, an achievement library and an information library, the technical information of each node in the industrial chain is extracted and classified, the classified information is collected to construct a classification library; the achievement documents are centrally stored to establish an achievement library; the public scientific research and development data, technology maturity and practical results based on the classification library are obtained to construct an information library.

[0009] As a preferred solution of the method for constructing the power system industry chain output quality evaluation model described in the present invention, the scoring library includes an evaluation information library, a classification scoring library and a key feature word segment scoring library.

[0010] As a preferred solution of the construction method of the power system industry chain output quality evaluation model described in the present invention, wherein: the processing of technical information to generate scoring data, and establishing a scoring library based on the scoring data include: processing the achievement documents through semantic extraction technology, simplifying the achievement documents extraction into key feature segments and classification segments based on classification of the classification library, generating a fixed format data string representing the achievement documents based on the classification segments and key feature segments, and establishing an evaluation information library to store the data string; binding the key feature segments to preset scoring data and storing them as a key feature segment scoring library; extracting key feature segments from scientific research and development materials, technology maturity and practical results classified based on the classification library, and generating scores based on the key feature segment scoring library, and summarizing the scores to generate a classification scoring library.

[0011] As a preferred scheme for the method of constructing the quality evaluation model of the output of the power system industrial chain described in the present invention, wherein: the quality evaluation model is constructed according to the data string and scoring data in the scoring library, and the achievement score is calculated, including reading the data string representing the achievement in the evaluation information library, and generating the achievement score based on the classification segment and key feature segment in the data string based on the classification scoring library and the key feature segment scoring library respectively.

[0012] As a preferred solution of the method for constructing the quality evaluation model of the output of the power system industrial chain described in the present invention, wherein: the quality evaluation model is constructed according to the data string and the scoring data in the scoring library, and the calculation of the achievement score also includes that the achievement score calculation formula is expressed as:

[0013] P C =k f *P f +k g*P g

[0014] Among them, P C Indicates the achievement score, P f represents the score and P of the classification word segment g represents the score and k of the key feature words f represents the technology preference coefficient, k g represents the quality preference coefficient.

[0015] A system for constructing a quality evaluation model for the output of results of an electric power system industry chain using any of the methods described in the present invention, wherein: a database construction module collects technical information of a target industry chain, constructs a classification library, a results library and an information library, and classifies and stores the collected technical information; a scoring library generation module processes the technical information in the database and establishes a scoring library through semantic extraction technology; and a calculation module constructs a quality evaluation model based on an evaluation information library, a classification scoring library and a key feature word segment scoring library, and calculates the results score.

[0016] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.

[0017] A computer-readable storage medium stores a computer program, comprising: when the computer program is executed by a processor, the steps of implementing any one of the methods of the present invention are implemented.

[0018] Beneficial effects of the present invention: The method of the present invention simplifies the achievement documents into data strings of key feature words and classification words by refining the nodes of the industrial chain, establishing classification and information bases, and combining semantic preprocessing technology, so as to achieve rapid dynamic updates without re-parsing the documents. The crawler technology monitors the public platform to obtain the latest scientific research data, and automatically updates the classification scoring library through the preset scoring library, so that the evaluation system can be dynamically adjusted with the development of technology. The achievement scoring is comprehensively evaluated through classification words and key feature words, which can not only reflect the excellence in the technical direction, but also evaluate the degree of technological progress, making the evaluation more accurate, real-time and macro-adaptable. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 them:

[0020] Figure 1An overall flow chart of a method for constructing a quality evaluation model for an output of an industrial chain of a power system provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of the scoring refinement of a power system industry chain output quality evaluation model provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] Example 1, reference Figure 1 and Figure 2 , which is an embodiment of the present invention, provides a method for constructing a quality evaluation model for the output of results of an electric power system industrial chain, including:

[0024] S1: Collect technical information of the target industry chain, establish a database, classify and store the collected technical information.

[0025] Furthermore, the technologies of each node in the industrial chain are extracted and classified in detail, and the classified information is collected to build a classification library. The achievement documents are stored centrally and the achievement library is established; the public scientific research and development data, technology maturity and practical results based on the classification library are obtained through crawler technology, and the information library is built.

[0026] Specifically, taking the power system industry chain as an example, in the process of building the classification library, each technical node in the power system industry chain is extracted in detail, and these technologies are classified according to the links of power generation, transmission, transformation, distribution, power consumption, power electronics and power equipment. In each link, the technology is further subdivided. For example, in the power generation link, solar power generation can be subdivided into photovoltaic cell technology, solar thermal power generation technology, etc.

[0027] Through in-depth analysis of various technologies, the classified information is sorted and summarized, and finally a power system industry chain technology classification library with a hierarchical structure and keyword tags is constructed to facilitate the subsequent accurate evaluation and effective management of the quality of output results.

[0028] In the analysis foundation construction stage, the collected power system industry chain related research documents, including academic papers, patents, technical standards, project reports, etc., will first be centrally stored, and a research library will be established using a database management system to ensure the searchability and security of these literature materials.

[0029] Crawler technology is used to obtain scientific research and development data, technology maturity and practical results based on classification libraries from public information sources, including academic journal websites, patent databases, industry reports and technology analysis websites. Finally, the cleaned, deduplicated and classified data are stored in the information library to provide comprehensive data support for the construction of the quality evaluation model of the power system industry chain results.

[0030] S2: Process the technical information to generate scoring data, and establish a scoring database based on the scoring data.

[0031] Furthermore, the achievement documents are processed by semantic extraction technology, and the achievement documents are extracted and simplified into a number of key feature segments and classification segments classified based on the classification library. A fixed format data string representing the achievement document is generated based on the classification segments and key feature segments, and the data string is stored to establish an evaluation information library. When the achievement documents are processed by semantic extraction technology, a classification tree is generated in the classification library based on the semantic relationship between each classification segment, and the classification tree is used to associate the parent-child relationship of the classification segments.

[0032] The key feature segments for semantic extraction include nouns and adjectives that embody scientific value, technical value, economic value and social value.

[0033] Furthermore, the key feature words are bound to preset scoring data and stored as a key feature word scoring library. The preset scoring data bound to the key feature words are set according to the originality and depth of scientific value, the practicality and cutting-edge of technical value, the direct and indirect impact on the economy of economic value, and the contribution to social progress of social value.

[0034] Key feature phrases are used to extract the degree of progress in the achievement document. The specific progress is divided into scientific value, technical value, economic value and social value. It can rely on the weight of the progress of each aspect of the implementation purpose planning, so as to conduct a progress assessment suitable for the planning blueprint. In the evaluation of scientific value, technical value, economic value and social value, the focus is on the evaluation of practicality, cutting-edge, direct and indirect impact of economic value on the economy, and contribution to social progress. Among them, the originality and depth of scientific value include scientific sharing, filling gaps and method innovation, practicality and cutting-edge include technical level, maturity and market potential, direct and indirect sharing of the economy includes industrial demand, development trend and macro background, and contribution to society includes social sharing, social benefits and social impact. The practicality, cutting-edge, direct and indirect impact of economic value on the economy, contribution to social progress and other aspects will be further refined to conduct a more detailed progress assessment.

[0035] Apply semantic extraction to the information database, extract key feature segments from the development data, technology maturity and practical results of each technology classified based on the classification library, generate scores for each technology based on the key feature segment scoring library, and summarize the scores of each technology to generate a classification scoring library. The score of each technology is updated as the information database is updated, and is also affected by changes in the score of the parent technology.

[0036] Each technology is marked as similar. The similar marking means that the technologies are similar technologies that achieve the same purpose. The score of each technology is also inversely affected by the changes in the score of similar technologies of its parent technology.

[0037] In addition to the development of the current technology, the development of the technology that the technology depends on also determines whether a technology has development prospects. Therefore, generating a classification tree of parent-child relationships can better handle the dependencies between technologies. When the parent technology matures and becomes a popular technology, the impact of its child technology development will be greater and easier to implement. Therefore, changes in the parent technology score will also affect the child technology score. There is also a competitive relationship between technologies. When a technology demonstrates its superiority, the extended application prospects of other competing technologies will be relatively reduced.

[0038] In addition to being updated along with the information database, the classification scoring database also revises the scoring based on the application results after application.

[0039] Relying solely on public information for technology iteration may not meet one's own development needs. Therefore, the results of the transformation are used to correct the score ratio of each technology category, so that the evaluation can be more exclusive and customized to meet one's own development needs.

[0040] It should be noted that when using it, a classification library is first constructed to fragment each node of the industrial chain so that it is classified into several small sections. Then, semantic preprocessing technology is used to abstract the achievement documents into data strings composed of key feature segments and classification segments, which facilitates the subsequent rapid dynamic update of the achievement documents without the need to scan or understand the entire achievement document again.

[0041] In the existing technology, after the evaluation is completed, the evaluation criteria will not change, and the evaluation results will not be updated, thus burying some high-value achievements. Therefore, a method for constructing an output quality evaluation model for the power system industry chain that dynamically updates the technology-related value and the achievement value is needed.

[0042] Crawler technology can monitor information on public platforms and obtain relevant information, so that the evaluation system can be updated with public technology. Specifically, semantic extraction is used again to disassemble key feature segments, and the corresponding public content is converted into technical evaluation under this category using the preset key feature segment scoring library, so as to continuously update the classification scoring library, so that the results can change the evaluation score based on macro-technical changes. In this embodiment, the crawler is used based on network security guidelines, only publicly released information is obtained, and privacy is respected. At the same time, the crawler is also used to monitor new technologies and update the classification library after the user's authorization.

[0043] The results are generated by scoring classification words and key feature words. The classification words can feedback the excellence of the technical direction under technical iteration, so that the results in mature, reliable technology and key or key technical directions have higher scores. The evaluation standards for mature, reliable technology and key or key technical directions will change with the crawling of public information, so that the layout results can be updated with higher scores after the relevant foundation is improved in the later stage. The key feature words generate the degree of technological progress of the result in the description of the result document, and comprehensively evaluate the output of the result by combining the excellence of the technical direction and the degree of technological progress.

[0044] S3: Based on the data strings and scoring data in the scoring library, a quality evaluation model is constructed to calculate the achievement score.

[0045] Furthermore, the data string representing the achievement in the evaluation information library is read, and the classification words and key feature words in the data string are used to generate achievement scores based on the classification scoring library and the key feature word score library respectively. The achievement scores are updated as the classification scoring library is updated.

[0046] Outcome scoring is based on the formula:

[0047] P C =k f *P f +k g *P g

[0048] Among them, P C Indicates the achievement score, P f represents the score and P of the classification word segment g represents the score and k of the key feature words f represents the technology preference coefficient, k g represents the quality preference coefficient.

[0049] Users can choose the scoring bias according to their own needs, and increase k when prioritizing the development of core technologies. f value, so that the scoring is more biased towards technical selection, and k is increased when scientific research progress is prioritized gvalue, thereby making the score more biased towards technological progress.

[0050] This embodiment also provides a system for constructing a quality evaluation model for the output of results of an electric power system industry chain, including a database construction module, which collects technical information of the target industry chain, constructs a classification library, a results library and an information library, and classifies and stores the collected technical information; a scoring library generation module, which processes the technical information in the database and establishes a scoring library through semantic extraction technology; and a calculation module, which constructs a quality evaluation model based on the evaluation information library, the classification scoring library and the key feature word segment scoring library, and calculates the results score.

[0051] Example 2 is an embodiment of the present invention, which provides a method for constructing a quality evaluation model for the output of results of an electric power system industrial chain. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0052] By collecting, classifying and evaluating technical information in the power system industry chain, a database and scoring library are constructed and the achievement scores are calculated, which are ultimately used to judge the scientificity and innovation of the model and its accurate feedback on the quality of the achievements. The experimental objects are selected as several key nodes of the power system, including power generation, transmission, substation, distribution and power electronics, representing scientific research achievements in different periods. The scope of experimental data collection includes relevant academic papers, patents, technical standards, project reports, etc. The public resources obtained through crawler technology provide real-time updates of technology maturity and practical results. The experimental data are shown in Table 1.

[0053] Table 1 Experimental data table

[0054]

[0055]

[0056] From the table data, we can see that the invented power system industry chain output quality evaluation model can evaluate the results of different technical nodes in a hierarchical manner and reflect the excellence of each technology in the power industry chain. By setting the scoring dimensions of scientific, technological, economic and social value, the table can show the difference in contribution of each technology in different dimensions.

[0057] For example, the score of smart substation technology is the highest among all technologies, with a total score of 32.5, which shows that the technology has a high influence in scientific value (8.1 points), technical value (8.5 points) and social value (8.0 points), further illustrating its importance in the modernization of power systems. In photovoltaic cell technology and wind power generation technology, the economic value scores are higher, 6.9 and 7.5 points respectively, indicating that their market potential and direct impact on the economy are more prominent.

[0058] Compared with the existing technology, the innovation of this evaluation model is mainly reflected in the combination of multi-dimensional semantic extraction technology and hierarchical classification and scoring library, making the evaluation more comprehensive and dynamic. The dynamic update mechanism of the classification and scoring library, especially the real-time scientific research data obtained through crawler technology, ensures the system's ability to update synchronously under public technological progress and market dynamics, so that the technology evaluation system can not only reflect the current technological level of the industrial chain, but also adapt to future development trends. At the same time, the reverse feedback adjustment mechanism of the classification segment realizes the reasonable handling of the dependence and inhibition relationship between the parent category and the competing technology, making the scoring results more in line with the actual technology application scenarios. In addition, by setting the technology and quality preference coefficients, the model can also adjust the scoring bias according to user needs, thereby realizing flexible evaluation in a variety of application scenarios.

[0059] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0060] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0061] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0062] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0063] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a quality evaluation model for the output of power system industry chain results, characterized in that: include: Collect technical information of the target industry chain, establish a database, classify and store the collected technical information; Process the technical information to generate scoring data, and establish a scoring database based on the scoring data; Based on the data strings and scoring data in the scoring library, a quality evaluation model is constructed to calculate the outcome score.

2. The method for constructing the power system industry chain output quality evaluation model according to claim 1, characterized in that: The technical information includes the technology, achievement documents, scientific research and development data, technology maturity and practical results of each node in the target industrial chain.

3. The method for constructing the power system industry chain output quality evaluation model according to claim 2, characterized in that: The database includes a classification library, an achievement library and an information library, extracts and classifies the technical information of each node in the industrial chain, collects the classification information and constructs a classification library; Centrally store achievement documents and establish an achievement database; Obtain public scientific research and development information, technology maturity and practical results based on classification libraries, and build an information database.

4. The method for constructing the power system industry chain output quality evaluation model according to claim 3, characterized in that: The scoring library includes an evaluation information library, a classification scoring library and a key feature word segment scoring library.

5. The method for constructing the power system industry chain output quality evaluation model according to claim 4, characterized in that: The processing of the technical information to generate the scoring data and establishing the scoring database according to the scoring data includes: processing the achievement documents by semantic extraction technology, extracting and simplifying the achievement documents into key feature segments and classification segments classified based on the classification library, generating a fixed format data string representing the achievement documents based on the classification segments and the key feature segments, and establishing an evaluation information database to store the data string; Binding the key feature word segment to the preset scoring data and storing the data as a key feature word segment scoring library; Key feature words are extracted from scientific research and development data, technology maturity and practical results classified based on the classification library, and scores are generated based on the key feature word scoring library, and the scores are summarized to generate a classification scoring library.

6. The method for constructing the power system industry chain output quality evaluation model according to claim 5, characterized in that: The quality evaluation model is constructed based on the data strings and scoring data in the scoring library, and the achievement score is calculated, including reading the data strings representing the achievements in the evaluation information library, and generating achievement scores based on the classification segments and key feature segments in the data strings based on the classification scoring library and the key feature segment scoring library respectively.

7. The method for constructing the power system industry chain output quality evaluation model according to claim 6, characterized in that: The quality evaluation model is constructed based on the data string and the scoring data in the scoring library, and the achievement scoring calculation formula is expressed as: P C =k f *P f +k g *P g Among them, P C Indicates the achievement score, P f represents the score and P of the classification word segment g represents the score and k of the key feature words f represents the technology preference coefficient, k g represents the quality preference coefficient.

8. A system for constructing a power system industry chain output quality evaluation model using any one of the methods of claims 1 to 7, characterized in that: include, The database construction module collects technical information of the target industry chain, builds a classification library, achievement library and information library, and classifies and stores the collected technical information; The scoring library generation module processes the technical information in the database and establishes a scoring library through semantic extraction technology; The calculation module builds a quality evaluation model and calculates the achievement score based on the evaluation information database, classification scoring database and key feature word segment scoring database.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method for constructing the power system industrial chain output quality evaluation model as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing a power system industry chain output quality evaluation model as described in any one of claims 1-7 are implemented.

Images