A hidden knowledge to explicit knowledge processing system based on a knowledge graph and a large model

Abstract

This invention discloses a system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models. It includes a knowledge system ontology modeling and management module for constructing and maintaining the knowledge system ontology model in large model applications; a data access and knowledge graph construction module for mapping and loading multi-source heterogeneous data onto the knowledge system ontology; an ontology virtual business environment engine module; a tacit knowledge mining and explicit knowledge generation module that, in a virtual environment, uses graph analysis and large model reasoning to mine tacit knowledge and generate explicit knowledge; and a business strategy planning and workflow orchestration module that transforms explicit knowledge into executable business strategy plans and workflow orchestrations. Through the knowledge system ontology modeling and management module, a systematic knowledge framework is constructed, achieving systematic accumulation of enterprise tacit knowledge, effectively preventing knowledge loss, and improving knowledge reusability and scalability.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence and big data technology, specifically relating to a system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models. Background Technology

[0002] With the continuous advancement of artificial intelligence and big data technologies, the demand for intelligent and efficient solutions in the processing of enterprise data, information, and knowledge is becoming increasingly urgent. In the field of enterprise knowledge management, knowledge base question-and-answer systems have become an important means of information exchange, helping employees quickly obtain the information they need in their daily work and improving work efficiency and quality. However, traditional knowledge management systems (KMS) focus on the storage and retrieval of explicit knowledge such as documents and cases, making it difficult to effectively capture and transform tacit knowledge such as experts' experience and intuition.

[0003] Furthermore, existing enterprise knowledge base question-answering systems suffer from the problem of massive and diverse information, making traditional retrieval methods insufficient to meet employee needs. While question-answering systems based on large models and knowledge graphs have improved query efficiency and matching accuracy to some extent, efficiently performing queries and matching remains a challenge. At the same time, large models still suffer from insufficient depth and incomplete understanding when dealing with enterprise-specific business systems, historical experience, and implicit rules, making them difficult to directly apply to rigorous business decisions and process orchestration.

[0004] To address the aforementioned issues, there is an urgent need to build a knowledge processing system capable of systematically accumulating tacit knowledge, enhancing the intelligence of decision-making, and supporting holistic planning and process orchestration. This system should effectively integrate multi-source heterogeneous data, automatically or semi-automatically constructing an enterprise-specific knowledge graph to form a computable "virtual business environment." Simultaneously, utilizing graph analysis, path mining, and large-scale model reasoning, it should automatically discover and explicitly reveal hidden business knowledge from massive amounts of data, transforming the discovered explicit knowledge into actionable business strategy planning and workflow orchestration, providing enterprises with efficient holistic work planning and specific workflows. Summary of the Invention

[0005] To achieve the above objectives, the technical solution of the present invention is as follows: a system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models, the system comprising: The knowledge system ontology modeling and management module is used to build and maintain the knowledge system ontology model in large-scale model applications. This module includes a domain term extraction unit, a concept classification and hierarchy definition unit, an attribute definition unit, a relation definition unit, a rule and constraint definition unit, and an ontology storage and management unit. The data access and knowledge graph construction module is used to map and load multi-source heterogeneous data onto the knowledge system ontology to build an enterprise-specific knowledge graph. This module includes a multi-source data access unit, an entity extraction and alignment unit, a relation extraction and fusion unit, an attribute extraction and standardization unit, and a knowledge graph storage unit. The ontology virtual business environment engine module, based on knowledge graphs, includes a virtual business space construction unit, a virtual object and scene management unit, a graph computing and analysis engine, and a virtual environment state maintenance unit. The tacit knowledge mining and explicit knowledge generation module uses graph analysis and large model reasoning in a virtual environment to mine tacit knowledge and generate explicit knowledge. This module includes a tacit knowledge identification and analysis unit, a multi-path business insight generation unit, an explicit knowledge structure generation unit, and a knowledge quality assessment and optimization unit. The business strategy planning and workflow orchestration module transforms explicit knowledge into executable business strategy planning and workflow orchestration. This module includes a strategy template library management unit, an automatic strategy solution generation unit, a workflow orchestration unit, a solution evaluation and optimization unit, and an execution feedback and knowledge feedback unit.

[0006] Preferably, in the knowledge graph construction process, a template-based semi-automatic construction method is adopted. This method extracts and aligns entities and relationships from multi-source heterogeneous data, and then uses graph analysis algorithms to construct the knowledge graph. The knowledge graph construction process includes the following steps: (1) Data preprocessing steps: cleaning and standardizing multi-source heterogeneous data, including data normalization and format conversion; (2) Entity recognition and parsing steps: using natural language processing technology to identify and extract entities from text data, including organizations / companies, people, and locations, and classifying and standardizing the entities; 3) Relationship extraction step: Based on rule matching and statistical models, extract the relationships between entities from the data, including job relationships and cooperation relationships; 4) Knowledge graph construction steps: Store the processed data in a graph database, construct the knowledge graph, including constructing the nodes and edges of the graph, and setting the constraints of the graph; 5) Graph optimization step: Optimize the graph using graph analysis algorithms, including merging nodes and edges and removing redundant information.

[0007] Preferably, after the knowledge graph is constructed, the system can provide the following steps through the graph computing and analysis engine: 1) Path analysis steps, supporting multi-path queries, calculating multiple alternative paths through graph algorithms, and returning the optimal path; 2) Similarity calculation steps: Based on the structure and attribute information of the graph, calculate the similarity between two entities; 3) Reasoning steps: Path-based reasoning and template-based reasoning are performed based on the structure and relationships of the graph.

[0008] Preferably, in business strategy planning and workflow orchestration, the system adopts a template-based intelligent generation method, including: 1) Steps for defining business objectives: Clearly define specific business objectives; 2) Strategy solution generation steps: Based on the business objectives, the large model automatically understands and mines the knowledge graph to mine tacit knowledge, extract explicit knowledge, and automatically selects a matching strategy template from the strategy template library, fills in the parameters, and generates a preliminary strategy solution. 3) Process orchestration steps: break down the strategy into specific tasks, roles, systems, and rules to generate an end-to-end workflow; 4) Solution evaluation steps: Conduct multi-dimensional automatic evaluation of strategies and processes, including cost, risk, and feasibility; 5) Perform monitoring steps, monitor the execution status in real time, and collect feedback data; 6) Knowledge update step: The knowledge graph of the ontology is dynamically updated based on the execution feedback.

[0009] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. By constructing a systematic knowledge framework through the knowledge system ontology modeling and management module, a systematic accumulation of enterprise tacit knowledge is achieved, effectively preventing knowledge loss and improving the reusability and scalability of knowledge; 2. Through the data access and knowledge graph construction module, the effective integration of multi-source heterogeneous data is realized, and an enterprise-specific knowledge graph is constructed in an automatic or semi-automatic manner, forming a computable virtual business environment and improving the depth and breadth of knowledge; 3. Through the ontology virtual business environment engine module, a computable and reasonable virtual business environment is provided based on knowledge graphs, supporting parameterized configuration and scenario definition of virtual customers, products, channels, etc., thereby improving the level of intelligent decision-making for enterprises; 4. Through the tacit knowledge mining and explicit knowledge generation modules, using graph analysis, path mining and large model reasoning techniques, hidden business knowledge is automatically discovered and made explicit from massive amounts of data, improving the understandability and usability of knowledge. 5. Through the business strategy planning and workflow orchestration module, the extracted explicit knowledge is automatically transformed into executable business strategy planning and workflow orchestration, providing enterprises with efficient overall work planning and specific workflows with a holistic perspective, effectively supporting overall planning and end-to-end workflow orchestration. 6. Through the deep collaboration of five core modules, a systematic approach to the entire process from data to insights and from insights to strategies has been achieved, breaking through the limitations of traditional knowledge management systems that only focus on the storage and retrieval of explicit knowledge, and effectively improving the enterprise's knowledge management level. Attached Figure Description

[0010] Figure 1 Build flowcharts for knowledge graphs; Figure 2 The process of orchestrating business workflows. Detailed Implementation

[0011] The present invention will be further illustrated below with reference to the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are for illustrative purposes only and are not intended to limit the scope of the invention.

[0012] Example: Figures 1 to 2 As shown, the technical solution of the present invention is as follows: a system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models, the system comprising: The knowledge system ontology modeling and management module is used to build and maintain the knowledge system ontology model in large-scale model applications. This module includes a domain term extraction unit, a concept classification and hierarchy definition unit, an attribute definition unit, a relation definition unit, a rule and constraint definition unit, and an ontology storage and management unit. The data access and knowledge graph construction module is used to map and load multi-source heterogeneous data onto the knowledge system ontology to build an enterprise-specific knowledge graph. This module includes a multi-source data access unit, an entity extraction and alignment unit, a relation extraction and fusion unit, an attribute extraction and standardization unit, and a knowledge graph storage unit. The ontology virtual business environment engine module, based on knowledge graphs, includes a virtual business space construction unit, a virtual object and scene management unit, a graph computing and analysis engine, and a virtual environment state maintenance unit. The tacit knowledge mining and explicit knowledge generation module uses graph analysis and large model reasoning in a virtual environment to mine tacit knowledge and generate explicit knowledge. This module includes a tacit knowledge identification and analysis unit, a multi-path business insight generation unit, an explicit knowledge structure generation unit, and a knowledge quality assessment and optimization unit. The business strategy planning and workflow orchestration module transforms explicit knowledge into executable business strategy planning and workflow orchestration. This module includes a strategy template library management unit, an automatic strategy solution generation unit, a workflow orchestration unit, a solution evaluation and optimization unit, and an execution feedback and knowledge feedback unit.

[0013] Preferably, in the knowledge graph construction process, a template-based semi-automatic construction method is adopted. This method extracts and aligns entities and relationships from multi-source heterogeneous data, and then uses graph analysis algorithms to construct the knowledge graph. The knowledge graph construction process includes the following steps: (1) Data preprocessing steps: cleaning and standardizing multi-source heterogeneous data, including data normalization and format conversion; (2) Entity recognition and parsing steps: using natural language processing technology to identify and extract entities from text data, including organizations / companies, people, and locations, and classifying and standardizing the entities; 3) Relationship extraction step: Based on rule matching and statistical models, extract the relationships between entities from the data, including job relationships and cooperation relationships; 4) Knowledge graph construction steps: Store the processed data in a graph database, construct the knowledge graph, including constructing the nodes and edges of the graph, and setting the constraints of the graph; 5) Graph optimization step: Optimize the graph using graph analysis algorithms, including merging nodes and edges and removing redundant information.

[0014] Preferably, after the knowledge graph is constructed, the system can provide the following steps through the graph computing and analysis engine: 1) Path analysis steps, supporting multi-path queries, calculating multiple alternative paths through graph algorithms, and returning the optimal path; 2) Similarity calculation steps: Based on the structure and attribute information of the graph, calculate the similarity between two entities; 3) Reasoning steps: Path-based reasoning and template-based reasoning are performed based on the structure and relationships of the graph.

[0015] Preferably, in business strategy planning and workflow orchestration, the system adopts a template-based intelligent generation method, including: 1) Steps for defining business objectives: Clearly define specific business objectives; 2) Strategy solution generation steps: Based on the business objectives, the large model automatically understands and mines the knowledge graph to mine tacit knowledge, extract explicit knowledge, and automatically selects a matching strategy template from the strategy template library, fills in the parameters, and generates a preliminary strategy solution. 3) Process orchestration steps: break down the strategy into specific tasks, roles, systems, and rules to generate an end-to-end workflow; 4) Solution evaluation steps: Conduct multi-dimensional automatic evaluation of strategies and processes, including cost, risk, and feasibility; 5) Perform monitoring steps, monitor the execution status in real time, and collect feedback data; 6) Knowledge update step: The knowledge graph of the ontology is dynamically updated based on the execution feedback.

[0016] It should be noted that the above content merely illustrates the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. For those skilled in the art, various improvements and modifications can be made without departing from the principle of the present invention, and all such improvements and modifications fall within the scope of protection of the claims of the present invention.

Claims

1. A system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models, characterized in that, The system includes: The knowledge system ontology modeling and management module is used to build and maintain the knowledge system ontology model in large-scale model applications. This module includes a domain term extraction unit, a concept classification and hierarchy definition unit, an attribute definition unit, a relation definition unit, a rule and constraint definition unit, and an ontology storage and management unit. The data access and knowledge graph construction module is used to map and load multi-source heterogeneous data onto the knowledge system ontology to build an enterprise-specific knowledge graph. This module includes a multi-source data access unit, an entity extraction and alignment unit, a relation extraction and fusion unit, an attribute extraction and standardization unit, and a knowledge graph storage unit. The ontology virtual business environment engine module, based on knowledge graphs, includes a virtual business space construction unit, a virtual object and scene management unit, a graph computing and analysis engine, and a virtual environment state maintenance unit. The tacit knowledge mining and explicit knowledge generation module uses graph analysis and large model reasoning in a virtual environment to mine tacit knowledge and generate explicit knowledge. This module includes a tacit knowledge identification and analysis unit, a multi-path business insight generation unit, an explicit knowledge structure generation unit, and a knowledge quality assessment and optimization unit. The business strategy planning and workflow orchestration module transforms explicit knowledge into executable business strategy planning and workflow orchestration. This module includes a strategy template library management unit, an automatic strategy solution generation unit, a workflow orchestration unit, a solution evaluation and optimization unit, and an execution feedback and knowledge feedback unit.

2. The system according to claim 1, characterized in that, In the knowledge graph construction process, a template-based semi-automatic construction method is adopted. This involves extracting and aligning entities and relationships from multi-source heterogeneous data, and then using graph analysis algorithms to construct the knowledge graph. The knowledge graph construction process includes the following steps: (1) Data preprocessing steps: cleaning and standardizing multi-source heterogeneous data, including data normalization and format conversion; (2) Entity recognition and parsing steps: using natural language processing technology to identify and extract entities from text data, including organizations / companies, people, and locations, and classifying and standardizing the entities; 3) Relationship extraction step: Based on rule matching and statistical models, extract the relationships between entities from the data, including job relationships and cooperation relationships; 4) Knowledge graph construction steps: Store the processed data in a graph database, construct the knowledge graph, including constructing the nodes and edges of the graph, and setting the constraints of the graph; 5) Graph optimization step: Optimize the graph using graph analysis algorithms, including merging nodes and edges and removing redundant information.

3. The system according to claim 1, characterized in that, After the knowledge graph is constructed, the system can provide the following steps through the graph computing and analysis engine: 1) Path analysis steps, supporting multi-path queries, calculating multiple alternative paths through graph algorithms, and returning the optimal path; 2) Similarity calculation steps: Based on the structure and attribute information of the graph, calculate the similarity between two entities; 3) Reasoning steps: Path-based reasoning and template-based reasoning are performed based on the structure and relationships of the graph.

4. The system according to claim 1, characterized in that, In business strategy planning and workflow orchestration, the system employs a template-based intelligent generation method, including: 1) Steps for defining business objectives: Clearly define specific business objectives; 2) Strategy solution generation steps: Based on the business objectives, the large model automatically understands and mines the knowledge graph to mine tacit knowledge, extract explicit knowledge, and automatically selects a matching strategy template from the strategy template library, fills in the parameters, and generates a preliminary strategy solution. 3) Process orchestration steps: break down the strategy into specific tasks, roles, systems, and rules to generate an end-to-end workflow; 4) Solution evaluation steps: Conduct multi-dimensional automatic evaluation of strategies and processes, including cost, risk, and feasibility; 5) Perform monitoring steps, monitor the execution status in real time, and collect feedback data; 6) Knowledge update step: The knowledge graph of the ontology is dynamically updated based on the execution feedback.

Images