Nuclear power field project management method and system based on knowledge graph

Abstract

The invention relates to the technical field of nuclear power project management, and discloses a nuclear power field project management method and system based on a knowledge graph, and the method comprises the steps: obtaining the planning content of a nuclear power project, constructing a nuclear power project knowledge graph, and achieving the mapping correlation between the nuclear power project knowledge graph and a coding rule for each concept node of the nuclear power project knowledge graph, on the nuclear power project knowledge graph, taking the concept node which is inquired and matched by the user as a starting point, and adopting a graph traversal algorithm to obtain information of a semantically associated nuclear power project plan; and for the identified information distortion points of the nuclear power project plan, according to the semantic relationship in the nuclear power project knowledge graph, inferring missing or distorted information of the nuclear power project plan by adopting a semantic completion technology, and carrying out semantic completion on the content of the nuclear power project plan. According to the invention, intelligent management and query of the nuclear power project are realized, and the efficiency and quality of nuclear power project management are improved.

Description

Technical Field

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

[0002] When building a semantic plan retrieval system based on WBS technology, we face the contradiction between the semantic expression of plan content and the semantic understanding of user queries. Plan content is usually organized in a structured form, containing hierarchical relationships and attribute information such as projects and tasks, while user queries are expressed in natural language, which has the diversity and ambiguity of vocabulary, grammar and semantics. It is difficult to obtain accurate retrieval results through direct matching.

[0003] In addition, nuclear power projects generally have stricter requirements. During the planning, delivery and execution process, semantic deviations are likely to occur due to differences in personnel understanding and expression habits, leading to distortion of plan content. In particular, cross-departmental and cross-professional planning collaboration is more likely to produce information gaps. How to automatically identify semantic changes in the plan delivery process through semantic analysis technology, and perform semantic completion and correction to ensure the integrity and accuracy of plan information is an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to overcome one or more of the above-mentioned existing technical problems and provide a project management method and system in the nuclear power field based on knowledge graph.

[0005] To achieve the above purpose, the present invention provides a nuclear power project management method based on knowledge graph, including: Obtain the content of the nuclear power project plan. Based on natural language processing technology, through named entity recognition and relationship extraction, obtain the concepts and semantic relationships in the nuclear power project plan, and build a nuclear power project knowledge graph. The nodes in the nuclear power project knowledge graph represent the concepts in the nuclear power project plan, and the edges represent the semantic relationships. Obtain the pre-established coding rules for nuclear power project plans based on the WBS method. The WBS codes can be divided into 6 groups, namely project code, project section, island, unit and plant, sub-item engineering activities and floor or elevation. For each concept node of the nuclear power project knowledge graph, the coding rules are used to encode and obtain the encoded concept node, so as to realize the mapping association between the nuclear power project knowledge graph and the coding rules. Based on the user's query on the nuclear power project plan, the natural language understanding technology is used to perform semantic analysis on the user's query, obtain the query concept, and map it to the corresponding node in the nuclear power project knowledge graph, converting it into a semantic query for the nuclear power project knowledge graph; On the nuclear power project knowledge graph, starting from the concept node matched by the user query, a graph traversal algorithm is used to query the relevant plan concept nodes through the semantic relationship edges between nodes to obtain the information of semantically related nuclear power project plans; During the transmission of nuclear power project plans, the contents of nuclear power project plans before and after the transmission are obtained, and semantic comparison is performed through semantic similarity calculation to identify information distortion points where semantics change during the transmission of nuclear power project plans; For the identified information distortion points of the nuclear power project plan, semantic completion technology is used according to the semantic relations in the nuclear power project knowledge graph to infer the missing or distorted information of the nuclear power project plan and semantically complete the content of the nuclear power project plan.

[0006] According to one aspect of the present invention, text data of a nuclear power project plan is obtained, and the text data is preprocessed using natural language processing technology, including word segmentation, part-of-speech tagging, and named entity recognition, to obtain a structured representation of the nuclear power project text; For the structured representation of nuclear power project text, the semantic relationship in the text is identified through the relation extraction algorithm, and the nuclear power project relationship triple is constructed in the form of the first concept of nuclear power project, the semantic relationship, and the second concept of nuclear power project; According to the extracted concepts and semantic relationships, a directed graph data structure is constructed, with concepts as nodes and semantic relationships as edges of the directed graph data structure, to obtain the framework of the nuclear power project knowledge graph; For the nodes and edges in the nuclear power project knowledge graph, the nuclear power project ontology and external knowledge base are integrated to expand the attribute information of concept nodes, enrich the semantic associations between concept nodes, and improve the nuclear power project knowledge graph.

[0007] According to one aspect of the present invention, a pre-established coding rule for a nuclear power project plan based on a WBS method is obtained, and each concept node in a nuclear power project knowledge graph is coded using the coding rule to obtain the coded concept node, and the hierarchical relationship between the codes in the coding rule system is determined; Determine the association relationship between the coded concept nodes. If the codes of two concept nodes have a hierarchical relationship in the coding rule system, it is determined that there is a mapping association between the two concept nodes. By mapping and associating the coding rules with the concept nodes, the coded concept nodes are grouped to obtain a grouped concept node set; For each grouped concept node set, the classification of the concept node set in the nuclear power project knowledge graph is determined based on the coding rule system.

[0008] According to one aspect of the present invention, based on a user's query on a nuclear power project plan, a query on a nuclear power project plan in natural language form proposed by the user is obtained, and the query text is preprocessed, including word segmentation, part-of-speech tagging, and named entity recognition; Perform semantic analysis on the pre-processed query text to extract the content in the query, including the plan theme, time, place and people; According to the pre-built nuclear power project knowledge graph, the extracted content is mapped to the corresponding nodes in the nuclear power project knowledge graph to form a semantic query subgraph with the node as the center and the relationship as the edge; Based on the semantic query subgraph, the query language of the graph database performs semantic reasoning and query expansion on the nuclear power project knowledge graph to obtain the nuclear power project plan related to the user query. Generate multi-dimensional nuclear power project cards based on the relevance and importance of nuclear power project plans, and provide visual presentation to users; The generated nuclear power project cards are converted into natural language text through natural language generation technology, and replied to the user in the form of voice or text, completing the query processing of the nuclear power project.

[0009] According to one aspect of the present invention, based on a user's query on a nuclear power project plan, a corresponding concept node is matched in a nuclear power project knowledge graph and used as a starting point node of a graph traversal algorithm; Starting from the starting node, connections are established with other nodes through semantic relationship edges to achieve multi-hop reasoning; In the multi-hop reasoning process, the relevance between nodes is calculated based on the weight values ​​on the semantic relationship edges, and nodes that are highly relevant to the user query are screened out; For the selected related nodes, the information of nuclear power project plans contained therein is extracted and sorted according to the semantic relevance; Clustering the sorted nuclear power project plan information, and generating multiple nuclear power project topics related to the user query based on the clustering results; For each nuclear power project topic, obtain the detailed information of the nuclear power projects semantically associated with it from the nuclear power project knowledge graph and organize them in a logical order; The organized nuclear power project topics and detailed information of the nuclear power projects are returned to the user.

[0010] According to one aspect of the present invention, the content before and after the nuclear power project plan is transmitted is obtained and converted into a structured data format that can be semantically analyzed; Perform word segmentation and part-of-speech tagging on the content of the nuclear power project plan before and after the transmission, and extract keywords and key phrases; According to the pre-built nuclear power project knowledge graph, the semantic similarity of the content of the nuclear power project plan before and after the transfer is calculated; If the semantic similarity is lower than the preset threshold, it is judged that the information point may have semantic changes during the transmission process and marked as a potential information distortion point; All potential information distortion points are grouped through clustering algorithms to identify different types of information distortion patterns. According to different information distortion patterns, corresponding risk warning information is automatically generated; The identified information distortion points and corresponding risk warning information will be fed back to relevant personnel to remind them to pay attention to potential risks of information distortion.

[0011] According to one aspect of the present invention, the semantic relationship of information distortion points is obtained based on a pre-constructed nuclear power project knowledge graph; For information distortion points, infer the relevant nuclear power project plan information through semantic relationships; The inferred information of the nuclear power project plan is used as candidate information, and the optimal complementary information is determined according to the correlation between the candidate information and the information distortion point; The optimal completion information is integrated into the original plan content to obtain the semantically completed plan content; Update the semantic relationship of related nodes in the nuclear power project knowledge graph according to the semantically completed plan content; The semantically completed plan content is structured to form a standard format for nuclear power project plan delivery; During the transmission of the nuclear power project plan, the completeness and accuracy of the information of the nuclear power project plan is monitored in real time. If distortion points are found, the above steps are repeated for semantic completion.

[0012] To achieve the above objectives, the present invention provides a nuclear power project management system based on knowledge graph, comprising: Nuclear power project knowledge graph building module: obtain the content of the nuclear power project plan, and based on natural language processing technology, obtain the concepts and their semantic relationships in the nuclear power project plan through named entity recognition and relationship extraction, and build a nuclear power project knowledge graph. The nodes in the nuclear power project knowledge graph represent the concepts in the nuclear power project plan, and the edges represent the semantic relationships. Semantic mapping association module: obtain the pre-established coding rules for nuclear power project plans based on the WBS method, where WBS codes can be divided into 6 groups, namely project code, project section, island, unit and plant, sub-item engineering activities and floor or elevation. For each concept node of the nuclear power project knowledge graph, the coding rules are used to encode and obtain the encoded concept node, so as to realize the mapping association between the nuclear power project knowledge graph and the coding rules; Semantic query conversion module: Based on the user's query on the nuclear power project plan, the module uses natural language understanding technology to perform semantic analysis on the user's query, obtain the query concept, and map it to the corresponding node in the nuclear power project knowledge graph, converting it into a semantic query for the nuclear power project knowledge graph; Plan information query module: On the nuclear power project knowledge graph, starting from the concept node matched by the user query, the graph traversal algorithm is used to query the relevant plan concept nodes through the semantic relationship edges between nodes to obtain the information of the semantically related nuclear power project plans; Information distortion point acquisition module: During the transmission of nuclear power project plans, the content of nuclear power project plans before and after the transmission is acquired, semantic comparison is performed through semantic similarity calculation, and information distortion points where semantics have changed during the transmission of nuclear power project plans are identified; Semantic completion module: For the information distortion points of the identified nuclear power project plan, semantic completion technology is used according to the semantic relationship in the nuclear power project knowledge graph to infer the missing or distorted information of the nuclear power project plan and semantically complete the content of the nuclear power project plan.

[0013] To achieve the above-mentioned purpose, the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the above-mentioned project management method for the nuclear power field based on a knowledge graph is implemented.

[0014] To achieve the above-mentioned purpose, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned project management method for the nuclear power field based on a knowledge graph is implemented.

[0015] Based on this, the beneficial effects of the present invention are: the method constructs a nuclear power project knowledge graph through natural language processing technology, and associates it with WBS and schedule coding rules. When a user raises a plan query, the present invention performs semantic analysis on the query and performs multi-hop reasoning on the nuclear power project knowledge graph to explore related plan information. During the plan transmission process, the present invention identifies information distortion points through semantic comparison, and uses the semantic relationship of the nuclear power project knowledge graph to complete the information, thereby ensuring the integrity and accuracy of the plan information. This method not only realizes the intelligent management and query of nuclear power project plans, but also effectively prevents information distortion during the transmission of nuclear power project plans, thereby improving the efficiency and quality of project management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a project management method in the nuclear power field based on a knowledge graph according to an exemplary embodiment; Figure 2It is a flow chart of a nuclear power project management system based on a knowledge graph according to an exemplary embodiment. DETAILED DESCRIPTION

[0017] The present invention will now be discussed with reference to exemplary embodiments. It should be understood that the embodiments discussed are only for enabling those skilled in the art to better understand and thereby implement the present invention, rather than implying any limitation on the scope of the present invention.

[0018] As used herein, the term “including” and variations thereof are to be interpreted as open-ended terms meaning “including but not limited to.” The term “based on” is to be interpreted as “based, at least in part, on,” and the terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment.”

[0019] According to one embodiment of the present invention, Figure 1 is a flowchart of a nuclear power project management method based on a knowledge graph according to an exemplary embodiment. Figure 1 As shown, to achieve the above purpose, the present invention provides a nuclear power project management method based on knowledge graph, including: Obtain the content of the nuclear power project plan. Based on natural language processing technology, through named entity recognition and relationship extraction, obtain the concepts and semantic relationships in the nuclear power project plan, and build a nuclear power project knowledge graph. The nodes in the nuclear power project knowledge graph represent the concepts in the nuclear power project plan, and the edges represent the semantic relationships. Obtain the pre-established coding rules for nuclear power project plans based on the WBS method. The WBS codes can be divided into 6 groups, namely project code, project section, island, unit and plant, sub-item engineering activities and floor or elevation. For each concept node of the nuclear power project knowledge graph, the coding rules are used to encode and obtain the encoded concept node, so as to realize the mapping association between the nuclear power project knowledge graph and the coding rules. Based on the user's query on the nuclear power project plan, the natural language understanding technology is used to perform semantic analysis on the user's query, obtain the query concept, and map it to the corresponding node in the nuclear power project knowledge graph, converting it into a semantic query for the nuclear power project knowledge graph; On the nuclear power project knowledge graph, starting from the concept node matched by the user query, the graph traversal algorithm is used to query the relevant plan concept nodes through the semantic relationship edges between nodes to obtain the information of semantically related nuclear power project plans; During the transmission of nuclear power project plans, the contents of nuclear power project plans before and after the transmission are obtained, semantic comparison is performed through semantic similarity calculation, and information distortion points where semantics change during the transmission of nuclear power project plans are identified; For the identified information distortion points of the nuclear power project plan, semantic completion technology is used according to the semantic relations in the nuclear power project knowledge graph to infer the missing or distorted information of the nuclear power project plan and semantically complete the content of the nuclear power project plan.

[0020] According to one embodiment of the present invention, text data of a nuclear power project plan is obtained, and the text data is preprocessed using natural language processing technology, including word segmentation, part-of-speech tagging, and named entity recognition, to obtain a structured representation of the nuclear power project text; For the structured representation of nuclear power project text, the semantic relationship in the text is identified through the relation extraction algorithm, and the nuclear power project relationship triple is constructed in the form of the first concept of nuclear power project, the semantic relationship, and the second concept of nuclear power project; According to the extracted concepts and semantic relationships, a directed graph data structure is constructed, with concepts as nodes and semantic relationships as edges of the directed graph data structure, to obtain the framework of the nuclear power project knowledge graph; For the nodes and edges in the nuclear power project knowledge graph, the nuclear power project ontology and external knowledge base are integrated to expand the attribute information of concept nodes, enrich the semantic associations between concept nodes, and improve the nuclear power project knowledge graph.

[0021] According to one embodiment of the present invention, a pre-established coding rule for a nuclear power project plan based on a WBS method is obtained, and each concept node in a nuclear power project knowledge graph is coded using the coding rule to obtain the coded concept node, and the hierarchical relationship between the codes in the coding rule system is determined; Determine the association relationship between the coded concept nodes. If the codes of two concept nodes have a hierarchical relationship in the coding rule system, it is determined that there is a mapping association between the two concept nodes. By mapping and associating the coding rules with the concept nodes, the coded concept nodes are grouped to obtain a grouped concept node set; For each grouped concept node set, the classification of the concept node set in the nuclear power project knowledge graph is determined based on the coding rule system.

[0022] According to an embodiment of the present invention, based on a user's query on a nuclear power project plan, a query on a nuclear power project plan in natural language form proposed by the user is obtained, and the query text is preprocessed, including word segmentation, part-of-speech tagging, and named entity recognition; Perform semantic analysis on the pre-processed query text to extract the content in the query, including the plan theme, time, place and people; According to the pre-built nuclear power project knowledge graph, the extracted content is mapped to the corresponding nodes in the nuclear power project knowledge graph to form a semantic query subgraph with the node as the center and the relationship as the edge; Based on the semantic query subgraph, the query language of the graph database performs semantic reasoning and query expansion on the nuclear power project knowledge graph to obtain the nuclear power project plan related to the user query. Generate multi-dimensional nuclear power project cards based on the relevance and importance of nuclear power project plans, and provide visual presentation to users; The generated nuclear power project cards are converted into natural language text through natural language generation technology, and replied to the user in the form of voice or text, completing the query processing of the nuclear power project.

[0023] According to one embodiment of the present invention, based on the user's query on the nuclear power project plan, the corresponding concept node is matched in the nuclear power project knowledge graph and used as the starting node of the graph traversal algorithm; Starting from the starting node, connections are established with other nodes through semantic relationship edges to achieve multi-hop reasoning; In the multi-hop reasoning process, the relevance between nodes is calculated based on the weight values ​​on the semantic relationship edges, and nodes that are highly relevant to the user query are screened out; For the selected related nodes, the information of nuclear power project plans contained therein is extracted and sorted according to the semantic relevance; Clustering the sorted nuclear power project plan information, and generating multiple nuclear power project topics related to the user query based on the clustering results; For each nuclear power project topic, obtain the detailed information of the nuclear power projects semantically associated with it from the nuclear power project knowledge graph and organize them in a logical order; The organized nuclear power project topics and detailed information of the nuclear power projects are returned to the user.

[0024] According to one embodiment of the present invention, the content before and after the nuclear power project plan is transmitted is obtained and converted into a structured data format that can be semantically analyzed; Perform word segmentation and part-of-speech tagging on the content of the nuclear power project plan before and after the transmission, and extract keywords and key phrases; According to the pre-built nuclear power project knowledge graph, the semantic similarity of the content of the nuclear power project plan before and after the transfer is calculated; If the semantic similarity is lower than the preset threshold, it is judged that the information point may have semantic changes during the transmission process and marked as a potential information distortion point; All potential information distortion points are grouped through clustering algorithms to identify different types of information distortion patterns. According to different information distortion patterns, corresponding risk warning information is automatically generated; The identified information distortion points and corresponding risk warning information will be fed back to relevant personnel to remind them to pay attention to potential risks of information distortion.

[0025] According to one embodiment of the present invention, the semantic relationship of information distortion points is obtained based on a pre-constructed nuclear power project knowledge graph; For information distortion points, infer the relevant nuclear power project plan information through semantic relationships; The inferred information of the nuclear power project plan is used as candidate information, and the optimal complementary information is determined according to the correlation between the candidate information and the information distortion point; The optimal completion information is integrated into the original plan content to obtain the semantically completed plan content; Update the semantic relationship of related nodes in the nuclear power project knowledge graph according to the semantically completed plan content; The semantically completed plan content is structured to form a standard format for nuclear power project plan delivery; During the transmission of the nuclear power project plan, the completeness and accuracy of the information of the nuclear power project plan is monitored in real time. If distortion points are found, the above steps are repeated for semantic completion.

[0026] According to one embodiment of the present invention, after obtaining the user's natural language plan query, the query text is first segmented using the Jieba word segmentation tool, and then the THULAC tool is used for part-of-speech tagging, and the BERT-BiLSTM-CRF model is used for named entity recognition to identify the key information in the query. Next, using the pre-built knowledge graph containing 500 nuclear power field concepts, the concepts extracted from the query text are mapped to the corresponding nodes in the nuclear power knowledge graph through the TransE-based knowledge representation learning algorithm, and these nodes are used as the center and the relationship is used as the edge to form a semantic query subgraph. Then, using the Cypher query language of the Neo4j graph database, based on the semantic query subgraph, by setting the relevance threshold of 8, semantic reasoning and query expansion within a range of 3 hops are performed on the knowledge graph to obtain the plan knowledge related to the user query. When the query results are post-processed, the TextRank algorithm is used to sort the importance of the knowledge fragments, select the top 10 most relevant fragments, and use the predefined structured template to organize the knowledge fragments into structured JSON format data. According to the relevance and importance, plan knowledge cards containing plan topics, time, location, people and other dimensions are generated, and ECharts is used for visualization. Finally, the Seq2Seq model based on the attention mechanism is used to generate natural and fluent language descriptions with knowledge cards as input, and replies are given to users through speech synthesis or text form, completing the full process of plan query processing.

[0027] According to an embodiment of the present invention, it is first necessary to obtain the plan content before and after the nuclear power project plan is delivered. The unstructured text data can be converted into a structured JSON format through text parsing technology to facilitate subsequent semantic analysis. Then, the Chinese word segmentation tool Jieba is used to segment and tag the text, extract keywords such as nouns, verbs, and adjectives, and then use the TextRank algorithm to identify key phrases. Next, based on the pre-built nuclear power field knowledge graph and HowNet semantic relationship library, the semantic similarity of the plan content before and after the delivery is calculated. If the similarity is lower than the threshold of 8, it is determined that the information point has a semantic change and is marked as a potential distortion point. K-means clustering is performed on all potential distortion points to identify different distortion modes, such as data missing, semantic offset, etc. For each distortion mode, more than 20 rules are designed to automatically generate corresponding risk warnings, such as "missing key indicators may affect the executability of the plan". Finally, the identification results are fed back to relevant personnel through a Web page to prompt potential information distortion risks, and different processing suggestions are provided according to the severity of the distortion, such as re-collecting data, correcting deviations, etc., to form a closed-loop plan delivery optimization process.

[0028] In addition, in order to achieve the above-mentioned purpose of the invention, the present invention also provides a nuclear power project management system based on knowledge graph. Figure 2 is a flowchart of a nuclear power project management system based on a knowledge graph according to an exemplary embodiment, such as Figure 2 As shown, a nuclear power project management system based on knowledge graph in the present invention includes: Nuclear power project knowledge graph building module: obtain the content of the nuclear power project plan, and based on natural language processing technology, obtain the concepts and their semantic relationships in the nuclear power project plan through named entity recognition and relationship extraction, and build a nuclear power project knowledge graph. The nodes in the nuclear power project knowledge graph represent the concepts in the nuclear power project plan, and the edges represent the semantic relationships. Semantic mapping association module: obtain the pre-established coding rules for nuclear power project plans based on the WBS method, where WBS codes can be divided into 6 groups, namely project code, project section, island, unit and plant, sub-item engineering activities and floor or elevation. For each concept node of the nuclear power project knowledge graph, the coding rules are used to encode and obtain the encoded concept node, so as to realize the mapping association between the nuclear power project knowledge graph and the coding rules; Semantic query conversion module: Based on the user's query on the nuclear power project plan, the module uses natural language understanding technology to perform semantic analysis on the user's query, obtain the query concept, and map it to the corresponding node in the nuclear power project knowledge graph, converting it into a semantic query for the nuclear power project knowledge graph; Plan information query module: On the nuclear power project knowledge graph, starting from the concept node matched by the user query, the graph traversal algorithm is used to query the relevant plan concept nodes through the semantic relationship edges between nodes to obtain the information of the semantically related nuclear power project plans; Information distortion point acquisition module: During the transmission of nuclear power project plans, the content of nuclear power project plans before and after the transmission is acquired, semantic comparison is performed through semantic similarity calculation, and information distortion points where semantics have changed during the transmission of nuclear power project plans are identified; Semantic completion module: For the information distortion points of the identified nuclear power project plan, semantic completion technology is used according to the semantic relationship in the nuclear power project knowledge graph to infer the missing or distorted information of the nuclear power project plan and semantically complete the content of the nuclear power project plan.

[0029] In order to achieve the above-mentioned purpose of the invention, the present invention also provides an electronic device, which includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the above-mentioned project management method in the nuclear power field based on the knowledge graph is implemented.

[0030] In order to achieve the above-mentioned purpose of the invention, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned project management method in the nuclear power field based on the knowledge graph is implemented.

[0031] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0032] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0033] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0034] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0035] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0036] If the functions are implemented in the form of software function modules 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 can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling 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 energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0037] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0038] It should be understood that the size of the serial numbers of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A nuclear power project management method based on knowledge graph, characterized in that: include: Obtain the content of the nuclear power project plan. Based on natural language processing technology, through named entity recognition and relationship extraction, obtain the concepts and semantic relationships in the nuclear power project plan, and build a nuclear power project knowledge graph. The nodes in the nuclear power project knowledge graph represent the concepts in the nuclear power project plan, and the edges represent the semantic relationships. Obtain the pre-established coding rules for nuclear power project plans based on the WBS method. The WBS codes can be divided into 6 groups, namely project code, project section, island, unit and plant, sub-item engineering activities and floor or elevation. For each concept node of the nuclear power project knowledge graph, the coding rules are used to encode and obtain the encoded concept node, so as to realize the mapping association between the nuclear power project knowledge graph and the coding rules. Based on the user's query on the nuclear power project plan, the natural language understanding technology is used to perform semantic analysis on the user's query, obtain the query concept, and map it to the corresponding node in the nuclear power project knowledge graph, converting it into a semantic query for the nuclear power project knowledge graph; On the nuclear power project knowledge graph, starting from the concept node matched by the user query, the graph traversal algorithm is used to query the relevant plan concept nodes through the semantic relationship edges between nodes to obtain the information of semantically related nuclear power project plans; During the transmission of nuclear power project plans, the contents of nuclear power project plans before and after the transmission are obtained, semantic comparison is performed through semantic similarity calculation, and information distortion points where semantics change during the transmission of nuclear power project plans are identified; For the identified information distortion points of the nuclear power project plan, semantic completion technology is used according to the semantic relations in the nuclear power project knowledge graph to infer the missing or distorted information of the nuclear power project plan and semantically complete the content of the nuclear power project plan.

2. A nuclear power project management method based on knowledge graph according to claim 1, characterized in that: Obtain text data of nuclear power project plans and pre-process the text data using natural language processing technology, including word segmentation, part-of-speech tagging, and named entity recognition, to obtain a structured representation of the nuclear power project text; For the structured representation of nuclear power project text, the semantic relationship in the text is identified through the relation extraction algorithm, and the nuclear power project relationship triple is constructed in the form of the first concept of nuclear power project, the semantic relationship, and the second concept of nuclear power project; According to the extracted concepts and semantic relationships, a directed graph data structure is constructed, with concepts as nodes and semantic relationships as edges of the directed graph data structure, to obtain the framework of the nuclear power project knowledge graph; For the nodes and edges in the nuclear power project knowledge graph, the nuclear power project ontology and external knowledge base are integrated to expand the attribute information of concept nodes, enrich the semantic associations between concept nodes, and improve the nuclear power project knowledge graph.

3. A nuclear power project management method based on knowledge graph as claimed in claim 2, characterized in that: Obtain the pre-established coding rules for nuclear power project plans based on the WBS method, encode each concept node in the nuclear power project knowledge graph using the coding rules, obtain the encoded concept node, and determine the hierarchical relationship between the codes in the coding rule system; Determine the association relationship between the coded concept nodes. If the codes of two concept nodes have a hierarchical relationship in the coding rule system, it is determined that there is a mapping association between the two concept nodes. By mapping and associating the coding rules with the concept nodes, the coded concept nodes are grouped to obtain a grouped concept node set; For each grouped concept node set, the classification of the concept node set in the nuclear power project knowledge graph is determined based on the coding rule system.

4. A nuclear power project management method based on knowledge graph as claimed in claim 3, characterized in that: Based on the user's query on the nuclear power project plan, the query on the nuclear power project plan in natural language form proposed by the user is obtained, and the query text is preprocessed, including word segmentation, part-of-speech tagging and named entity recognition; Perform semantic analysis on the pre-processed query text to extract the content in the query, including the plan theme, time, place and people; According to the pre-built nuclear power project knowledge graph, the extracted content is mapped to the corresponding nodes in the nuclear power project knowledge graph to form a semantic query subgraph with the node as the center and the relationship as the edge; Based on the semantic query subgraph, the query language of the graph database performs semantic reasoning and query expansion on the nuclear power project knowledge graph to obtain the nuclear power project plan related to the user query. Generate multi-dimensional nuclear power project cards based on the relevance and importance of nuclear power project plans, and provide visual presentation to users; The generated nuclear power project cards are converted into natural language text through natural language generation technology, and replied to the user in the form of voice or text, completing the query processing of the nuclear power project.

5. A nuclear power project management method based on knowledge graph as claimed in claim 4, characterized in that: According to the user's query on the nuclear power project plan, the corresponding concept node is matched in the nuclear power project knowledge graph and used as the starting node of the graph traversal algorithm; Starting from the starting node, connections are established with other nodes through semantic relationship edges to achieve multi-hop reasoning; In the multi-hop reasoning process, the relevance between nodes is calculated based on the weight values ​​on the semantic relationship edges, and nodes that are highly relevant to the user query are screened out; For the selected related nodes, the information of nuclear power project plans contained therein is extracted and sorted according to the semantic relevance; Clustering the sorted nuclear power project plan information, and generating multiple nuclear power project topics related to the user query based on the clustering results; For each nuclear power project topic, obtain the detailed information of the nuclear power projects semantically associated with it from the nuclear power project knowledge graph and organize them in a logical order; The organized nuclear power project topics and detailed information of the nuclear power projects are returned to the user.

6. A nuclear power project management method based on knowledge graph as claimed in claim 5, characterized in that: Obtain content before and after the nuclear power project plan is delivered and convert it into a structured data format that can be semantically analyzed; Perform word segmentation and part-of-speech tagging on the content of the nuclear power project plan before and after the transmission, and extract keywords and key phrases; According to the pre-built nuclear power project knowledge graph, the semantic similarity of the content of the nuclear power project plan before and after the transfer is calculated; If the semantic similarity is lower than the preset threshold, it is judged that the information point may have semantic changes during the transmission process and marked as a potential information distortion point; All potential information distortion points are grouped through clustering algorithms to identify different types of information distortion patterns. According to different information distortion patterns, corresponding risk warning information is automatically generated; The identified information distortion points and corresponding risk warning information will be fed back to relevant personnel to remind them to pay attention to potential risks of information distortion.

7. A nuclear power project management method based on knowledge graph as claimed in claim 6, characterized in that: According to the pre-built nuclear power project knowledge graph, the semantic relationship of information distortion points is obtained; For information distortion points, infer the relevant nuclear power project plan information through semantic relationships; The inferred information of the nuclear power project plan is used as candidate information, and the optimal complementary information is determined according to the correlation between the candidate information and the information distortion point; The optimal completion information is integrated into the original plan content to obtain the semantically completed plan content; Update the semantic relationship of related nodes in the nuclear power project knowledge graph according to the semantically completed plan content; The semantically completed plan content is structured to form a standard format for nuclear power project plan delivery; During the transmission of the nuclear power project plan, the completeness and accuracy of the information of the nuclear power project plan is monitored in real time. If distortion points are found, the above steps are repeated for semantic completion.

8. A nuclear power project management system based on knowledge graph, characterized in that: include: Nuclear power project knowledge graph building module: obtain the content of the nuclear power project plan, and based on natural language processing technology, obtain the concepts and their semantic relationships in the nuclear power project plan through named entity recognition and relationship extraction, and build a nuclear power project knowledge graph. The nodes in the nuclear power project knowledge graph represent the concepts in the nuclear power project plan, and the edges represent the semantic relationships. Semantic mapping association module: obtain the pre-established coding rules for nuclear power project plans based on the WBS method, where WBS codes can be divided into 6 groups, namely project code, project section, island, unit and plant, sub-item engineering activities and floor or elevation. For each concept node of the nuclear power project knowledge graph, the coding rules are used to encode and obtain the encoded concept node, so as to realize the mapping association between the nuclear power project knowledge graph and the coding rules; Semantic query conversion module: Based on the user's query on the nuclear power project plan, the module uses natural language understanding technology to perform semantic analysis on the user's query, obtain the query concept, and map it to the corresponding node in the nuclear power project knowledge graph, converting it into a semantic query for the nuclear power project knowledge graph; Plan information query module: On the nuclear power project knowledge graph, starting from the concept node matched by the user query, the graph traversal algorithm is used to query the relevant plan concept nodes through the semantic relationship edges between nodes to obtain the information of the semantically related nuclear power project plans; Information distortion point acquisition module: During the transmission of nuclear power project plans, the content of nuclear power project plans before and after the transmission is acquired, semantic comparison is performed through semantic similarity calculation, and information distortion points where semantics have changed during the transmission of nuclear power project plans are identified; Semantic completion module: For the information distortion points of the identified nuclear power project plan, semantic completion technology is used according to the semantic relationship in the nuclear power project knowledge graph to infer the missing or distorted information of the nuclear power project plan and semantically complete the content of the nuclear power project plan.

9. An electronic device, characterized in that: It comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, a project management method in the nuclear power field based on a knowledge graph is implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements a project management method in the nuclear power field based on a knowledge graph as described in any one of claims 1 to 7.

Images