Power system knowledge asset management method and system based on knowledge graph

Abstract

The invention provides an electric power system knowledge asset management method and system based on a knowledge graph, and relates to the technical field of electric power systems, and the method comprises the following steps: S1, knowledge asset investigation and classification; s2, constructing a multi-level label system; s3, constructing and optimizing a knowledge base; s4, developing a technical map management interface; s5, carrying out deep technical map analysis; s6, implementing a knowledge asset management process; s7, precisely matching and applying ecological construction; the system comprises a knowledge carding and classification module, a label system construction module, a knowledge base construction and optimization module, a technical atlas management module, a technical atlas analysis module, a knowledge asset management process control module and a precise matching application module. According to the method, multiple fields of electric power engineering, information technology, knowledge asset management, computer science and the like are spanned, comprehensive consideration of novel electric power system technology innovation network ecology is embodied, and especially deep integration in the aspect of knowledge asset management strategies is embodied.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a power system knowledge asset management method and system based on a knowledge graph. Background Art

[0002] Against the backdrop of global energy transformation, new power systems are undergoing profound changes. The rapid rise of renewable energy, the integration of distributed energy, the innovation of smart grid technology, the reform of the power market and the widespread use of power electronics technology have jointly shaped a complex and dynamic power system technology ecosystem. As important participants in this field, power companies are faced with the challenge of integrating internal scientific research resources with the knowledge of external innovation alliances to adapt to the urgent needs of this transition period.

[0003] The development of technology innovation network and knowledge asset management technology is the core of the research. With the maturity of big data, artificial intelligence (especially natural language processing and machine learning), knowledge graph construction, graph neural network and other technologies, powerful tools are provided for the power system field to manage and analyze massive knowledge assets and promote the precise matching of technology, talents, products and markets. However, the knowledge asset management of the power system has the following shortcomings: 1. Knowledge fragmentation: Knowledge assets in the power system field are scattered in different departments, projects, and documents. There is a lack of unified management and integration, which makes it difficult to effectively use knowledge.

[0004] 2. Low retrieval efficiency: Traditional retrieval methods often cannot accurately understand the diversity, spelling differences and contextual meanings of professional terms, which reduces the efficiency and accuracy of information retrieval.

[0005] 3. Fuzzy knowledge relationships: The correlation between technology, talents, and projects is not clearly presented, which affects the insight into technological innovation paths and cooperation opportunities.

[0006] 4. Lack of dynamism: Knowledge management lacks immediate response to rapidly updated knowledge and technological trends, resulting in untimely decision support.

[0007] To sum up the shortcomings of the existing power system, we propose a power system knowledge asset management method and system based on knowledge graph. Summary of the invention

[0008] The purpose of the present invention is to provide a method and system for power system knowledge asset management based on knowledge graph to solve the above-mentioned deficiencies in the technology.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions: A method for managing knowledge assets of a power system based on a knowledge graph, the method comprising the following steps: S1. Research and classification of knowledge assets: First, initiate a research plan, collect data, and make a preliminary classification based on the collected information; S2. Build a multi-level label system: 1) Define label classification. Based on the preliminary classification, further define the framework of the label system, including major categories such as technology categories and project stages; 2) Refine specific labels. Under each major category, refine more specific labels, such as subdividing solar power generation, wind power generation, etc. under the technology category; 3) Label review and dynamic management: combining automatic identification technology and manual review to label each knowledge asset appropriately, and establishing a regular review mechanism to dynamically update the label system based on new information; S3. Knowledge base construction and optimization. Database construction. Establish innovation achievement databases at the enterprise level, university level and research institution level. Collect and organize relevant data. At the same time, perform data fusion and processing. Use natural language processing technology to identify and extract entities and relationships in the data. Combine machine learning algorithms to optimize the extraction model and improve accuracy. At the same time, we build a knowledge graph, integrate the processed data into the knowledge graph, display the complex network of the technology ecosystem, and support efficient retrieval and association analysis of knowledge; S4. Technology graph management interface development: develop an easy-to-use graphical interface to enable users to intuitively view and edit knowledge graphs; S5. Conduct in-depth technology graph analysis, develop advanced algorithms, conduct in-depth analysis of knowledge graphs, reveal potential correlations, causal relationships, and implicit features between technologies, obtain analysis structures, and present the analysis results in the form of reports, including knowledge association graphs, technology development trend forecasts, etc., to provide a scientific basis for decision-making; S6. Implement knowledge asset management processes, standardize processes, and, through process specifications, conduct cross-domain knowledge circulation to promote knowledge flow and innovative cooperation between different departments and research fields; S7. Accurate matching and application ecosystem construction: 1) Intelligent matching system development, building intelligent matching algorithms based on knowledge graphs and analysis results to achieve accurate matching of talents, institutions, technologies, products and market demands; 2) Application integration and promotion: integrate intelligent recommendation, search query and other functions into internal platforms or external partner systems (such as talent recruitment, project cooperation platforms), and continuously monitor feedback to continuously optimize matching efficiency and user experience.

[0010] Preferably, the research plan in S1 is to form a professional team, clarify the purpose and scope of the research, and cover key information such as the enterprise profile, talent profile, R&D results, technical fields, project progress and cooperation model within the power system.

[0011] Preferably, the research plan in S1 is to form a professional team, clarify the purpose and scope of the research, and cover key information such as the enterprise profile, talent profile, R&D results, technical fields, project progress and cooperation model within the power system.

[0012] Preferably, the preliminary classification process in S1 preliminarily divides the knowledge assets into multiple dimensions such as enterprises, talents, achievements, technology categories (such as renewable energy generation, energy storage technology, etc.), project stages, cooperation models, etc., and ensures that the classification has a granularity with practical application value.

[0013] Preferably, the graphical interface also includes functions such as adding, deleting, modifying, and adjusting relationships, and simultaneously performs settings for a permission control system to achieve fine-grained permission management, ensure data security, and support knowledge sharing and collaboration among users of different roles.

[0014] Preferably, the process is standardized and a complete set of knowledge asset management processes needs to be formulated, covering knowledge collection, classification, entry, labeling, continuous optimization and other aspects.

[0015] The present invention also provides a knowledge graph-based power system knowledge asset management system, comprising: The knowledge sorting and classification module is responsible for conducting a comprehensive survey of the knowledge assets of the power system and classifying them according to multiple dimensions such as enterprises, talents, achievements, technology categories, project stages, and cooperation models to ensure the orderly organization of knowledge assets; Input: original knowledge data, including but not limited to research reports, technical documents, personnel information, project records, etc.; Output: classified knowledge asset catalog; Interface: Provides classification results to the label system building module as the basis for label allocation; The label system building module is used to establish a multi-layer label system, define label classification and specific labels, and maintain label accuracy and timeliness through automatic and manual methods; Input: Output of knowledge combing and classification module; Output: Knowledge asset data with precise labels; Interface: interacts with the knowledge base construction and optimization module to provide label information for the construction of the knowledge graph; The knowledge base construction and optimization module uses natural language processing and machine learning technologies to extract entities and relationships from multi-source databases, build and optimize knowledge graphs; Input: Output of the label system building module and external data sources; Output: knowledge graph after merging the innovation achievement data sub-databases at the enterprise level and the university and research institute level; Interface: Provide knowledge graph data to the technology graph management module to support knowledge addition, deletion, modification and query; The technology graph management module is used to provide user interfaces and tools to support the maintenance and permission management of the knowledge graph and ensure knowledge security and sharing; Input: Output of knowledge base construction and optimization module; Output: real-time updated knowledge graph and permission control strategy; Interface: interact with the technical graph analysis module to ensure the accuracy and real-time nature of the analysis data; The technology graph analysis module is used to use algorithms to deeply analyze the knowledge graph, discover knowledge associations, and support decision-making; Input: Output of the technology map management module; Output: knowledge correlation analysis report, potential technology trends, etc. Interface: Provide analysis results to the precise matching application module to support intelligent matching and recommendation; The knowledge asset management process control module is used to coordinate all the above modules to ensure a smooth process of knowledge asset management, including the full life cycle management of knowledge; Input / output: data flow and control signals between modules; Interface: interact with all other modules to achieve process automation and optimization; The precise matching application module uses knowledge graphs and analysis results to achieve precise matching of talents, institutions, technologies, products and markets; Input: Output of the technology graph analysis module; Output: matching recommendation lists, collaborative innovation opportunities, etc. Interface: Directly facing users, providing query and recommendation services, and may also be integrated with external systems.

[0016] Compared with the prior art, the present invention can solve: 1. Systematic organization and labeling system of knowledge assets: By systematically organizing and carefully classifying knowledge assets, a labeling system is established to improve the accuracy of retrieval and make knowledge resources easy to index, retrieve and reuse.

[0017] 2. Intelligent search technology applies natural language processing and machine learning technologies to realize automatic recognition and expansion of technical terms, support fuzzy and semantic search, improve the comprehensiveness and depth of search, and provide advanced functions such as technology maturity sorting and specific field filtering.

[0018] 3. Visualization of knowledge relationships: Use graphical technology to display technical relationships. Through modes such as node diagrams, link diagrams, and network diagrams, it intuitively displays complex knowledge structures, supports interactive operations and personalized annotations, and enables users to deeply understand technical relationships.

[0019] 4. Intelligent recommendation and dynamic tracking. The intelligent recommendation system provides personalized matching suggestions based on user behavior and needs. At the same time, it dynamically tracks technological development, uses data analysis tools to predict trends, and provides scientific support for decision-making.

[0020] 5. Technology map management and analysis: build and manage technology maps, reveal the dependencies between technologies, standards, and projects through correlation analysis, provide industry maps, and enhance the understanding of the technology ecosystem and the formulation of innovation strategies.

[0021] Based on the technical problems solved above, the present invention brings the following beneficial effects: Interdisciplinary integration,This invention spans multiple fields such as power engineering, information technology,,knowledge asset management and computer science, reflecting the comprehensive consideration of the,network ecology of new power system technology innovation, especially the deep integration of,knowledge asset management strategies.

[0022] Systematic knowledge asset management. The present invention proposes a set of systematic knowledge asset division, label system construction, management system and process design, forming a comprehensive knowledge asset management strategy from micro to macro, from classification to integration, reflecting the pursuit of scientific knowledge asset management.

[0023] The exploration of technological innovation paths, through the technical paths and functional designs of the correlation analysis between innovation resources and technology maps, this invention demonstrates how to use advanced information technology means, such as knowledge maps, intelligent recommendation systems, deep learning, etc., to conduct technology trend forecasting, expert influence assessment and cooperation network analysis, providing a new research approach for technological innovation.

[0024] The practicality and foresight of the functional design. The present invention has designed a series of functions for actual application scenarios, such as talent matching, product and technology matching, market matching, etc., emphasizing the practical value of the knowledge asset management system; at the same time, through functions such as intelligent recommendation, technology map construction and analysis, it demonstrates a forward-looking layout for the knowledge asset management of future power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of the steps of a power system knowledge asset management method based on knowledge graph provided by the present invention; Figure 2 A block diagram of a knowledge graph-based power system knowledge asset management system provided by the present invention. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] To facilitate understanding of the present invention, the present invention will be described more comprehensively below with reference to related references, and several embodiments of the present invention are given. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0028] It should be noted that when an element is referred to as being "fixed on" another element, it may be directly on the other element or there may also be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used in this article are for illustrative purposes only.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this article includes any and all combinations of one or more related listed items.

[0030] Figure 1 A flowchart of a method for managing knowledge assets in a power system based on a knowledge graph is provided in an embodiment of the present invention. The method is applied to a knowledge asset management system for a power system based on a knowledge graph. The system includes: a knowledge combing and classification module, a label system construction module, a knowledge base construction and optimization module, a technology graph management module, a technology graph analysis module, a knowledge asset management process control module, and a precise matching application module. The method includes the following steps: S1. Research and classification of knowledge assets: First, initiate a research plan, collect data, and make a preliminary classification based on the collected information; In S1, the research plan specifically includes forming a professional team, clarifying the purpose and scope of the research, and covering key information such as the enterprise profile, talent profile, R&D results, technical fields, project progress and cooperation model within the power system; The specific research plan is to form a professional team, clarify the purpose and scope of the research, and cover key information such as the corporate profile, talent profile, R&D results, technical fields, project progress and cooperation model within the power system.

[0031] The preliminary classification process divides knowledge assets into multiple dimensions, including enterprises, talents, achievements, technology categories (such as renewable energy generation, energy storage technology, etc.), project stages, cooperation models, etc., and ensures that the classification has a granularity with practical application value.

[0032] S2. Build a multi-level label system: 1) Define label classification. Based on the preliminary classification, further define the framework of the label system, including major categories such as technology categories and project stages; 2) Refine specific labels. Under each major category, refine more specific labels, such as subdividing solar power generation, wind power generation, etc. under the technology category; 3) Label review and dynamic management: combining automatic identification technology and manual review to label each knowledge asset appropriately, and establishing a regular review mechanism to dynamically update the label system based on new information; S3. Knowledge base construction and optimization. Database construction. Establish innovation achievement databases at the enterprise level, university level and research institution level. Collect and organize relevant data. At the same time, perform data fusion and processing. Use natural language processing technology to identify and extract entities and relationships in the data. Combine machine learning algorithms to optimize the extraction model and improve accuracy. At the same time, we build a knowledge graph, integrate the processed data into the knowledge graph, display the complex network of the technology ecosystem, and support efficient retrieval and association analysis of knowledge; S4. Technology graph management interface development: develop an easy-to-use graphical interface to enable users to intuitively view and edit knowledge graphs; It should be noted that the graphical interface also includes functions such as adding, deleting, modifying, and adjusting relationships. At the same time, the permission control system is set up to achieve fine-grained permission management, ensure data security, and support knowledge sharing and collaboration among users of different roles.

[0033] S5. Conduct in-depth technology graph analysis, develop advanced algorithms, conduct in-depth analysis of knowledge graphs, reveal potential correlations, causal relationships, and implicit features between technologies, obtain analysis structures, and present the analysis results in the form of reports, including knowledge association graphs, technology development trend forecasts, etc., to provide a scientific basis for decision-making; S6. Implement knowledge asset management processes, standardize processes, and, through process specifications, conduct cross-domain knowledge circulation to promote knowledge flow and innovative cooperation between different departments and research fields; To standardize the process, it is necessary to develop a complete knowledge asset management process that covers knowledge collection, classification, entry, labeling, and continuous optimization.

[0034] S7. Accurate matching and application ecosystem construction 1) Intelligent matching system development, building intelligent matching algorithms based on knowledge graphs and analysis results to achieve accurate matching of talents, institutions, technologies, products and market demands; 2) Application integration and promotion: integrate intelligent recommendation, search query and other functions into internal platforms or external partner systems (such as talent recruitment, project cooperation platforms), and continuously monitor feedback to continuously optimize matching efficiency and user experience.

[0035] Based on S1 to S7 above, the steps of the method are as follows: S1: Divide power system knowledge assets by multiple dimensions and refine technology categories; S2: Create multi-level tags to achieve accurate management and retrieval of knowledge resources; S3: Collect, classify, and enter knowledge, maintain labels, and optimize the knowledge base; S4: static correlation analysis identifies technical structures, and dynamic analysis tracks trends; S5: search query, knowledge visualization, intelligent recommendation, graph management and analysis; S6: Conduct knowledge asset audits, and use real-time monitoring and feedback mechanisms to ensure efficiency; S7: Conduct intelligent matching of technology, talent, products, organizations and markets.

[0036] Figure 2 An electric power system knowledge asset management system based on a knowledge graph is provided in an embodiment of the present invention, and the system includes: The knowledge sorting and classification module is responsible for conducting a comprehensive survey of the knowledge assets of the power system and classifying them according to multiple dimensions such as enterprises, talents, achievements, technology categories, project stages, and cooperation models to ensure the orderly organization of knowledge assets; Input: original knowledge data, including but not limited to research reports, technical documents, personnel information, project records, etc.; Output: classified knowledge asset catalog; Interface: Provides classification results to the label system building module as the basis for label allocation; The label system building module is used to establish a multi-layer label system, define label classification and specific labels, and maintain label accuracy and timeliness through automatic and manual methods; Input: Output of knowledge combing and classification module; Output: Knowledge asset data with precise labels; Interface: interacts with the knowledge base construction and optimization module to provide label information for the construction of the knowledge graph; The knowledge base construction and optimization module uses natural language processing and machine learning technologies to extract entities and relationships from multi-source databases, build and optimize knowledge graphs; Input: Output of the label system building module and external data sources; Output: knowledge graph after merging the innovation achievement data sub-databases at the enterprise level and the university and research institute level; Interface: Provide knowledge graph data to the technology graph management module to support knowledge addition, deletion, modification and query; The technology graph management module is used to provide user interfaces and tools to support the maintenance and permission management of the knowledge graph and ensure knowledge security and sharing; Input: Output of knowledge base construction and optimization module; Output: real-time updated knowledge graph and permission control strategy; Interface: interact with the technical graph analysis module to ensure the accuracy and real-time nature of the analysis data; The technology graph analysis module is used to use algorithms to deeply analyze the knowledge graph, discover knowledge associations, and support decision-making; Input: Output of the technology map management module; Output: knowledge correlation analysis report, potential technology trends, etc. Interface: Provide analysis results to the precise matching application module to support intelligent matching and recommendation; The knowledge asset management process control module is used to coordinate all the above modules to ensure a smooth process of knowledge asset management, including the full life cycle management of knowledge; Input / output: data flow and control signals between modules; Interface: interact with all other modules to achieve process automation and optimization; The precise matching application module uses knowledge graphs and analysis results to achieve precise matching of talents, institutions, technologies, products and markets; Input: Output of the technology graph analysis module; Output: matching recommendation lists, collaborative innovation opportunities, etc. Interface: Directly facing users, providing query and recommendation services, and may also be integrated with external systems (such as recruitment platforms, project management systems).

[0037] Specifically, the synergy between system modules: The knowledge combing and classification module provides classification results for the label system construction module as the basis for label allocation; The output of the label system construction module is the input of the knowledge base construction and optimization module, providing label information for the construction of the knowledge graph; The knowledge graph constructed by the knowledge base construction and optimization module is used by the technology graph management module to provide user interface and tool support; The technology graph management module ensures knowledge security and sharing, and provides real-time updated data to the technology graph analysis module; The output of the technology graph analysis module is the basis of the precise matching application module, supporting intelligent matching and recommendation; The knowledge asset management process control module coordinates the data flow and control signals between modules to ensure a smooth process.

[0038] The knowledge asset management process of this power system is as follows: Knowledge asset research and classification (S1): Establish a professional team, clarify the purpose and scope of the research, cover multiple key areas within the power system, collect relevant information, and conduct preliminary classification according to multiple dimensions such as enterprises, talents, achievements, and technology categories to ensure that the classification has practical application value; Construct a multi-level labeling system (S2). Based on the preliminary classification, further define the framework of the labeling system, refine specific labels under the major categories, such as solar power generation and wind power generation under the technology category, combine automatic identification technology and manual review to label knowledge assets, and establish a regular review mechanism to dynamically update the labeling system; Knowledge base construction and optimization (S3): Establishing innovation achievement databases at the enterprise level, university level, and research institution level. Using natural language processing and machine learning technologies, identify and extract entities and relationships in the data, integrate the processed data into the knowledge graph, and display the complex network of the technology ecosystem. Technology graph management interface development (S4), providing an easy-to-use graphical interface to support knowledge graph viewing, editing and permission control; In-depth technology graph analysis (S5): Use algorithms to deeply analyze the knowledge graph to reveal the associations and causal relationships between technologies, and present the analysis results in the form of a report to provide a scientific basis for decision-making; Implementation of knowledge asset management process (S6): Develop a complete knowledge asset management process, covering knowledge collection, classification, entry, labeling and other links, to promote knowledge flow and innovative cooperation among different departments and research fields; Precise matching and application ecosystem construction (S7): Based on the knowledge graph and analysis results, build an intelligent matching algorithm to achieve precise docking, integrate intelligent recommendation, search query and other functions into internal or external systems, and continuously optimize matching efficiency and user experience.

[0039] In summary, the present invention constructs a comprehensive knowledge asset management system based on a new power system technology innovation network, which integrates functions such as knowledge graph construction, dynamic technology graph association analysis, frequent item set mining, association rule mining, path analysis, and a series of core functions of innovation resource management and technology graph analysis; By applying advanced technologies such as natural language processing, machine learning, and graph neural networks, the system has achieved accurate classification, intelligent retrieval, dynamic visualization, personalized recommendation, and trend prediction of knowledge assets. The system can track the technology development path, expert influence propagation path, and project evolution path in real time. It can predict the key nodes of technology evolution and potential cooperative relationships through graph neural networks, providing a scientific basis for technology strategy planning.

[0040] At the same time, the functions or modules that are different from existing competing products are: ① Dynamic correlation analysis and prediction capabilities. Compared with existing knowledge management systems, the present invention has made in-depth research on dynamic correlation analysis. It not only analyzes the current status, but also predicts technology development trends and changes in expert influence, providing forward-looking guidance for scientific research directions.

[0041] ② Personalization and depth of intelligent recommendation. By using deep learning technology, the intelligent recommendation module of the present invention can understand user needs more accurately and provide highly personalized and deeply customized knowledge and technology recommendations, rather than recommendations based only on simple historical records.

[0042] ③ Deep mining and visualization of knowledge relationships. Through technologies such as graph neural networks, not only can the construction and visualization of knowledge graphs be realized, but deep information mining can also be carried out to reveal complex relationships and paths, thereby improving the accuracy of decision support.

[0043] ④Multi-dimensional path analysis. Different from single-dimensional analysis tools, the present invention provides multi-dimensional path analysis across technologies, talents, and projects to promote interdisciplinary cooperation and accelerate technological innovation.

[0044] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A knowledge graph-based power system knowledge asset management method, characterized in that: The following steps are involved: S1. Research and classification of knowledge assets: First, initiate a research plan, collect data, and make a preliminary classification based on the collected information; S2. Build a multi-level label system: 1) Define label classification. Based on the preliminary classification, further define the framework of the label system, including major categories such as technology categories and project stages; 2) Refine specific labels. Under each major category, refine more specific labels, such as subdividing solar power generation, wind power generation, etc. under the technology category; 3) Label review and dynamic management: combining automatic identification technology and manual review to label each knowledge asset appropriately, and establishing a regular review mechanism to dynamically update the label system based on new information; S3. Knowledge base construction and optimization. Database construction. Establish innovation achievement databases at the enterprise level, university level and research institution level. Collect and organize relevant data. At the same time, perform data fusion and processing. Use natural language processing technology to identify and extract entities and relationships in the data. Combine machine learning algorithms to optimize the extraction model and improve accuracy. At the same time, we build a knowledge graph, integrate the processed data into the knowledge graph, display the complex network of the technology ecosystem, and support efficient retrieval and association analysis of knowledge; S4. Technology graph management interface development: develop an easy-to-use graphical interface to enable users to intuitively view and edit knowledge graphs; S5. Conduct in-depth technology graph analysis, develop advanced algorithms, conduct in-depth analysis of knowledge graphs, reveal potential correlations, causal relationships, and implicit features between technologies, obtain analysis structures, and present the analysis results in the form of reports, including knowledge association graphs, technology development trend forecasts, etc., to provide a scientific basis for decision-making; S6. Implement knowledge asset management processes, standardize processes, and, through process specifications, conduct cross-domain knowledge circulation to promote knowledge flow and innovative cooperation between different departments and research fields; S7. Accurate matching and application ecosystem construction: 1) Develop an intelligent matching system, build an intelligent matching algorithm based on knowledge graphs and analysis results, and achieve accurate matching of talents, institutions, technologies, products and market demands; 2) Application integration and promotion: integrate intelligent recommendation, search query and other functions into internal platforms or external partner systems, and continuously monitor feedback to continuously optimize matching efficiency and user experience.

2. The power system knowledge asset management method based on knowledge graph according to claim 1 is characterized by: The research plan in S1 is to form a professional team, clarify the purpose and scope of the research, and cover key information such as the corporate profile, talent profile, R&D results, technical fields, project progress and cooperation model within the power system.

3. The power system knowledge asset management method based on knowledge graph according to claim 1 is characterized by: The research plan in S1 is to form a professional team, clarify the purpose and scope of the research, and cover key information such as the corporate profile, talent profile, R&D results, technical fields, project progress and cooperation model within the power system.

4. The power system knowledge asset management method based on knowledge graph according to claim 1 is characterized by: The preliminary classification process in S1 preliminarily divides knowledge assets into multiple dimensions such as enterprises, talents, achievements, technology categories, project stages, cooperation models, etc., and ensures that the classification has a granularity with practical application value.

5. The power system knowledge asset management method based on knowledge graph according to claim 1 is characterized by: The graphical interface also includes functions such as adding, deleting, modifying, and adjusting relationships, and at the same time, sets up an authority control system to achieve fine-grained authority management, ensure data security, and support knowledge sharing and collaboration among users of different roles.

6. The power system knowledge asset management method based on knowledge graph according to claim 1 is characterized by: To standardize the above processes, a complete set of knowledge asset management processes must be developed, covering aspects such as knowledge collection, classification, entry, labeling, and continuous optimization.

7. A knowledge graph-based power system knowledge asset management system, used to implement a knowledge graph-based power system knowledge asset management method as described in claims 1-6, characterized in that: include: The knowledge sorting and classification module is responsible for conducting a comprehensive survey of the knowledge assets of the power system and classifying them according to multiple dimensions such as enterprises, talents, achievements, technology categories, project stages, and cooperation models to ensure the orderly organization of knowledge assets; Input: original knowledge data, including but not limited to research reports, technical documents, personnel information, project records, etc.; Output: catalog of classified knowledge assets; Interface: Provides classification results to the label system building module as the basis for label allocation; The label system building module is used to establish a multi-layer label system, define label classification and specific labels, and maintain label accuracy and timeliness through automatic and manual methods; Input: Output of knowledge combing and classification module; Output: Knowledge asset data with precise labels; Interface: interacts with the knowledge base construction and optimization module to provide label information for the construction of the knowledge graph; The knowledge base construction and optimization module uses natural language processing and machine learning technologies to extract entities and relationships from multi-source databases, build and optimize knowledge graphs; Input: Output of the label system building module and external data sources; Output: knowledge graph after merging the innovation achievement data sub-databases at the enterprise level and the university and research institute level; Interface: Provide knowledge graph data to the technology graph management module to support knowledge addition, deletion, modification and query; The technology graph management module is used to provide user interfaces and tools to support the maintenance and permission management of the knowledge graph and ensure knowledge security and sharing; Input: Output of knowledge base construction and optimization module; Output: real-time updated knowledge graph and permission control strategy; Interface: interact with the technical graph analysis module to ensure the accuracy and real-time nature of the analysis data; The technology graph analysis module is used to use algorithms to deeply analyze the knowledge graph, discover knowledge associations, and support decision-making; Input: Output of the technology graph management module; Output: knowledge correlation analysis report, potential technology trends, etc. Interface: Provide analysis results to the precise matching application module to support intelligent matching and recommendation; The knowledge asset management process control module is used to coordinate all the above modules to ensure a smooth process of knowledge asset management, including the full life cycle management of knowledge; Input / output: data flow and control signals between modules; Interface: interact with all other modules to achieve process automation and optimization; The precise matching application module uses knowledge graphs and analysis results to achieve precise matching of talents, institutions, technologies, products and markets; Input: Output of the technology graph analysis module; Output: matching recommendation lists, collaborative innovation opportunities, etc. Interface: Directly facing users, providing query and recommendation services, and may also be integrated with external systems.

Images