A knowledge graph-based nuclear power field project management method and system

Abstract

The application 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, which comprises the following steps: obtaining nuclear power project plan content, constructing a nuclear power project knowledge graph, realizing mapping association of the nuclear power project knowledge graph and coding rules for each concept node of the nuclear power project knowledge graph, taking a concept node matched by user query as a starting point on the nuclear power project knowledge graph, adopting a graph traversal algorithm to obtain information of the nuclear power project plan associated in semantics, adopting a semantic completion technology to infer missing or distorted information of the nuclear power project plan according to semantic relations in the nuclear power project knowledge graph for information distortion points of the recognized nuclear power project plan, and performing semantic completion on the content of the nuclear power project plan. The application realizes intelligent management and query of the nuclear power project, and improves the efficiency and quality of nuclear power project management.

Description

TECHNICAL FIELD

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

[0002] When a semanticized plan retrieval system is constructed based on a WBS technology, a contradiction between semantic expression of plan content and semantic understanding of user query is faced. Plan content is usually organized in a structured form, containing hierarchical relationships and attribute information of projects and tasks, while user query is expressed in natural language, with diversity and ambiguity of vocabulary, grammar and semantics, and direct matching is difficult to obtain accurate retrieval results.

[0003] In addition, nuclear power projects generally require strictness, and due to differences in personnel understanding and expression habits during the formulation, transmission and execution of plans, semantic deviations are easily generated, leading to distortion of plan content. Especially, plan collaboration across departments and specialties is more likely to cause information gaps. How to automatically identify semantic changes in the plan transmission process through semantic analysis technology, and perform semantic completion and correction to ensure the integrity and accuracy of plan information is a problem to be solved. SUMMARY

[0004] The present application aims to overcome one or more of the above-mentioned problems in the prior art, and provides a nuclear power field project management method and system based on a knowledge graph.

[0005] To achieve the above-mentioned purpose, the present application provides a nuclear power field project management method based on a knowledge graph, comprising:

[0006] Obtaining nuclear power project plan content, based on natural language processing technology, through named entity recognition and relation extraction, obtaining concepts in the nuclear power project plan and their semantic relationships, constructing a nuclear power project knowledge graph, nodes in the nuclear power project knowledge graph representing concepts in the nuclear power project plan, and edges representing semantic relationships;

[0007] Obtaining pre-established coding rules for nuclear power project plans based on the WBS method, wherein the WBS code can be divided into 6 groups, namely project code, project board, island, unit and plant, sub-part item engineering activities and floor or elevation, for each concept node of the nuclear power project knowledge graph, the coding rule is used for coding to obtain the coded concept node, realizing the mapping association between the nuclear power project knowledge graph and the coding rule;

[0008] Based on user query of the nuclear power project plan, through natural language understanding technology, the user's query is analyzed semantically, the concepts of the query are obtained, and they are mapped to the corresponding nodes in the nuclear power project knowledge graph, and are converted into semantic queries for the nuclear power project knowledge graph;

[0009] On the nuclear power project knowledge graph, taking the concept node matched with the user query as the starting point, the graph traversal algorithm is adopted, the related plan concept nodes are inquired through the semantic relationship edges between the nodes, and the information of the nuclear power project plan associated in the semantics is acquired;

[0010] In the transmission process of the nuclear power project plan, the contents of the nuclear power project plan before and after the transmission are acquired, the semantic comparison is performed through the semantic similarity calculation, and the information distortion points of the semantic change in the transmission process of the nuclear power project plan are identified;

[0011] According to the semantic relationship in the nuclear power project knowledge graph, the semantic completion technology is adopted to infer the missing or distorted information of the nuclear power project plan, and the semantic completion is performed on the content of the nuclear power project plan.

[0012] According to an aspect of the present application, the text data of the nuclear power project plan is acquired, the natural language processing technology is adopted to pre-process the text data, including word segmentation, part-of-speech tagging and named entity recognition, and the structured representation of the nuclear power project text is obtained;

[0013] According to the structured representation of the nuclear power project text, the semantic relationship existing in the text is identified through the relationship extraction algorithm, the nuclear power project relationship triple is constructed, and the form is a nuclear power project first concept, a semantic relationship and a nuclear power project second concept;

[0014] According to the extracted concept and semantic relationship, a directed graph data structure is constructed, the concept is taken as the node of the directed graph data structure, the semantic relationship is taken as the edge of the directed graph data structure, and the framework of the nuclear power project knowledge graph is obtained;

[0015] According to the nodes and edges in the nuclear power project knowledge graph, the nuclear power field project ontology and the external knowledge base are fused, the attribute information of the concept node is expanded, the semantic association between the concept nodes is enriched, and the nuclear power project knowledge graph is perfected.

[0016] According to an aspect of the present application, the coding rule of the nuclear power project plan based on the WBS method is acquired in advance, the coding rule is adopted to code each concept node in the nuclear power project knowledge graph, the coded concept node is obtained, and the hierarchical relationship between the codes in the coding rule system is determined;

[0017] The association relationship between the coded concept nodes is judged, if the codes of two concept nodes have the upper and lower hierarchical relationship in the coding rule system, it is determined that the two concept nodes have the mapping association;

[0018] Through the mapping association between the coding rule and the concept node, the coded concept node is grouped, and the grouped concept node set is obtained;

[0019] For each grouped concept node set, based on the coding rule system, determine the classification of the concept node set in the nuclear power project knowledge graph.

[0020] According to one aspect of the present application, based on the user's query to the nuclear power project plan, the user's query to the nuclear power project plan in natural language form is obtained, the text of the query is preprocessed, including word segmentation, part-of-speech tagging and named entity recognition;

[0021] The preprocessed query text is analyzed semantically, and the content in the query is extracted, including the plan theme, time, place and characters;

[0022] According to the pre-constructed nuclear power project knowledge graph, the extracted content is mapped to the corresponding node in the nuclear power project knowledge graph to form a semantic query subgraph centered on the node and the relationship as the edge;

[0023] Based on the semantic query subgraph, semantic reasoning and query expansion are performed on the nuclear power project knowledge graph through the graph database query language to obtain the nuclear power project plan related to the user query;

[0024] According to the relevance and importance of the nuclear power project plan, a multi-dimensional nuclear power project card is generated for visual display to the user;

[0025] The generated nuclear power project card is converted into natural language text through natural language generation technology, and the user is replied in the form of voice or text to complete the query process of the nuclear power project.

[0026] According to one aspect of the present application, according to the user's query to the nuclear power project plan, the corresponding concept node in the nuclear power project knowledge graph is matched and taken as the starting node of the graph traversal algorithm;

[0027] Starting from the starting node, the nodes are connected through semantic relationship edges to realize multi-hop reasoning;

[0028] In the multi-hop reasoning process, the relevance between nodes is calculated according to the weight value on the semantic relationship edge, and the nodes highly related to the user query are screened out;

[0029] The information of the screened related nodes is extracted, and the information is sorted according to the semantic correlation degree;

[0030] The sorted nuclear power project plan information is clustered, and multiple nuclear power project themes related to the user query are generated according to the clustering results;

[0031] For each nuclear power project theme, the detailed information of the nuclear power project semantically associated with it is obtained from the nuclear power project knowledge graph, and is organized in logical order;

[0032] Return the organized nuclear power project theme and the detailed information of the nuclear power project to the user.

[0033] According to one aspect of the present application, the content before and after the delivery of the nuclear power project plan is obtained, and is converted into a structured data format that can be subjected to semantic analysis.

[0034] The content of the nuclear power project plan before and after the delivery is subjected to word segmentation and part-of-speech tagging processing, and key words and key phrases are extracted.

[0035] According to a pre-constructed nuclear power project knowledge graph, the semantic similarity of the content of the nuclear power project plan before and after the delivery is calculated.

[0036] If the semantic similarity is lower than a preset threshold, it is judged that the information point may have a semantic change in the delivery process, and is marked as a potential information distortion point.

[0037] All potential information distortion points are grouped by a clustering algorithm, different types of information distortion modes are identified, and corresponding risk prompt information is automatically generated according to different information distortion modes.

[0038] The identified information distortion points and the corresponding risk prompt information are fed back to the relevant personnel, prompting them to pay attention to the potential information distortion risk.

[0039] According to one aspect of the present application, the semantic relationship of the information distortion point is obtained according to the pre-constructed nuclear power project knowledge graph.

[0040] The information of the nuclear power project plan related to the information distortion point is inferred through the semantic relationship.

[0041] The inferred information of the nuclear power project plan is taken as candidate information, and the optimal completion information is determined according to the relevance of the candidate information and the information distortion point.

[0042] The optimal completion information is fused into the original plan content to obtain the plan content after semantic completion.

[0043] According to the plan content after semantic completion, the semantic relationship of the related nodes in the nuclear power project knowledge graph is updated.

[0044] The plan content after semantic completion is structured and represented to form a standard format for the delivery of the nuclear power project plan.

[0045] In the delivery process of the nuclear power project plan, the integrity and accuracy of the information of the nuclear power project plan are monitored in real time, and if a distortion point is found, the above steps are repeated for semantic completion.

[0046] To achieve the above purpose, the present application provides a nuclear power field project management system based on a knowledge graph, comprising:

[0047] The nuclear power project knowledge graph establishment module: obtains the content of the nuclear power project plan, obtains the concepts and semantic relationships in the nuclear power project plan through named entity recognition and relationship extraction based on natural language processing technology, constructs 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 semantic relationships;

[0048] The semantic mapping correlation module: obtains the coding rules for the nuclear power project plan based on the WBS method, wherein the WBS code can be divided into six groups, namely, the project code, the project board, the island, the unit and the plant, the sub-part engineering activity and the floor or elevation, and the coding rules are used to code each concept node of the nuclear power project knowledge graph to obtain the coded concept node, so as to realize the mapping and correlation of the nuclear power project knowledge graph and the coding rules;

[0049] The semantic query conversion module: based on the user's query of the nuclear power project plan, the natural language understanding technology is used to perform semantic analysis on the user's query, obtain the concept of the query, and map it to the corresponding node in the nuclear power project knowledge graph to convert it into a semantic query of the nuclear power project knowledge graph;

[0050] The plan information query module: starting from the concept node matched by the user's query on the nuclear power project knowledge graph, the graph traversal algorithm is used to query the related plan concept nodes through the semantic relationship edges between the nodes to obtain the information of the nuclear power project plan associated in the semantic relationship;

[0051] The information distortion point acquisition module: in the transmission process of the nuclear power project plan, the contents of the nuclear power project plan before and after transmission are obtained, and semantic comparison is performed through semantic similarity calculation to identify the information distortion points in the semantic change in the transmission process of the nuclear power project plan;

[0052] The semantic completion module: for the identified information distortion points of the nuclear power project plan, the semantic completion technology is used to infer the missing or distorted information of the nuclear power project plan according to the semantic relationship in the nuclear power project knowledge graph, and the content of the nuclear power project plan is semantically completed.

[0053] To achieve the above purpose, the present application provides an electronic device, which includes a processor, a memory and a computer program stored on the memory and executable on the processor, and the computer program is executed by the processor to realize the above-mentioned nuclear power field project management method based on knowledge graph.

[0054] To achieve the above purpose, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to realize the above-mentioned nuclear power field project management method based on knowledge graph.

[0055] Based on this, the beneficial effects of the present application are that 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 proposes a plan query, the present application performs semantic analysis on the query and multi-hop reasoning on the nuclear power project knowledge graph to explore relevant plan information, in the plan transmission process, the present application identifies information distortion points through semantic comparison and completes them using the semantic relationship of the nuclear power project knowledge graph to ensure the integrity and accuracy of the plan information, this method not only realizes the intelligent management and query of the nuclear power project plan, but also effectively prevents information distortion in the transmission process of the nuclear power project plan, improves the efficiency and quality of project management. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 is a nuclear power field project management method flowchart based on a knowledge graph according to an exemplary embodiment;

[0057] Figure 2 is a nuclear power field project management system flowchart based on a knowledge graph according to an exemplary embodiment. DETAILED DESCRIPTION

[0058] The content of the present application will now be discussed with reference to exemplary embodiments, it should be understood that the discussed embodiments are only to enable those of ordinary skill in the art to better understand and thus implement the content of the present application, and are not intended to imply any limitation on the scope of the present application.

[0059] As used herein, the term "comprising" and its variants are to be construed as meaning "including but not limited to", the term "based on" is to be construed as "at least partially based on", the terms "one embodiment" and "an embodiment" are to be construed as "at least one embodiment".

[0060] According to one embodiment of the present application, Figure 1 is a nuclear power field project management method flowchart based on a knowledge graph according to an exemplary embodiment, as Figure 1 shown, to achieve the above-mentioned purpose, the present application provides a nuclear power field project management method based on a knowledge graph, comprising:

[0061] Obtaining the content of the nuclear power project plan, based on natural language processing technology, through named entity recognition and relationship extraction, obtaining the concepts in the nuclear power project plan and their semantic relationships, constructing 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;

[0062] The coding rule for the nuclear power project plan based on the WBS method is acquired in advance, wherein the WBS code can be divided into six groups, namely, a project code, a project board, an island, a unit and a plant, a sub-part project activity and a floor or elevation, for each concept node of the nuclear power project knowledge graph, the coding rule is used for coding to obtain a coded concept node, and the mapping association between the nuclear power project knowledge graph and the coding rule is realized;

[0063] Based on the query of the user to the nuclear power project plan, the semantic analysis of the query of the user is performed through the natural language understanding technology, the concept of the query is acquired, and the concept is mapped to the corresponding node in the nuclear power project knowledge graph, and is converted into the semantic query to the nuclear power project knowledge graph;

[0064] On the nuclear power project knowledge graph, the concept node matched by the user query is taken as a starting point, the graph traversal algorithm is used, the related plan concept nodes are queried through the semantic relationship edges between the nodes, and the information of the nuclear power project plan associated in the semantics is acquired;

[0065] In the transmission process of the nuclear power project plan, the contents of the nuclear power project plan before and after transmission are acquired, the semantic comparison is performed through the semantic similarity calculation, and the information distortion point of the semantic change in the transmission process of the nuclear power project plan is recognized;

[0066] For the recognized information distortion point of the nuclear power project plan, the semantic completion technology is used to infer the missing or distorted information of the nuclear power project plan according to the semantic relationship in the nuclear power project knowledge graph, and the semantic completion is performed on the content of the nuclear power project plan.

[0067] According to one embodiment of the present application, the text data of the nuclear power project plan is acquired, the natural language processing technology is used for pre-processing the text data, including word segmentation, part-of-speech tagging and named entity recognition, and the structured representation of the nuclear power project text is obtained;

[0068] For the structured representation of the nuclear power project text, the semantic relationship existing in the text is recognized through the relationship extraction algorithm, the nuclear power project relationship triple is constructed, and the form is a nuclear power project first concept, a semantic relationship and a nuclear power project second concept;

[0069] According to the extracted concept and semantic relationship, a directed graph data structure is constructed, the concept is taken as a node of the directed graph data structure, and the semantic relationship is taken as an edge of the directed graph data structure, and the framework of the nuclear power project knowledge graph is obtained;

[0070] For the nodes and edges in the nuclear power project knowledge graph, the nuclear power field project ontology and the external knowledge base are fused, the attribute information of the concept node is expanded, the semantic association between the concept nodes is enriched, and the nuclear power project knowledge graph is perfected.

[0071] According to one embodiment of the present application, the coding rules of the WBS method for the nuclear power project plan are obtained in advance, each concept node in the nuclear power project knowledge graph is coded by using the coding rules to obtain the coded concept node, and the hierarchical relationship between the codes in the coding rule system is determined;

[0072] The association relationship between the coded concept nodes is determined, if the codes of two concept nodes have the upper and lower hierarchical relationship in the coding rule system, it is determined that the two concept nodes have the mapping association;

[0073] The coded concept nodes are grouped by the mapping association between the coding rules and the concept nodes to obtain the grouped concept node set;

[0074] 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.

[0075] According to one embodiment of the present application, based on the user query of the nuclear power project plan, the natural language query of the nuclear power project plan proposed by the user is obtained, the text of the query is preprocessed, including word segmentation, part-of-speech tagging and named entity recognition;

[0076] The semantic analysis is performed on the preprocessed query text, and the content in the query is extracted, including the plan theme, time, place and person;

[0077] According to the pre-constructed nuclear power project knowledge graph, the extracted content is mapped to the corresponding node in the nuclear power project knowledge graph to form a semantic query subgraph with nodes as the center and relationships as the edges;

[0078] Based on the semantic query subgraph, semantic reasoning and query expansion are performed on the nuclear power project knowledge graph by using the graph database query language to obtain the nuclear power project plan related to the user query;

[0079] According to the relevance and importance of the nuclear power project plan, a multi-dimensional nuclear power project card is generated to visually display the user;

[0080] The generated nuclear power project card is converted into a natural language text by using the natural language generation technology, and the user is replied in the form of voice or text to complete the processing process of the nuclear power project query.

[0081] According to one embodiment of the present application, according to the user query of the nuclear power project plan, the corresponding concept node in the nuclear power project knowledge graph is matched and taken as the starting node of the graph traversal algorithm;

[0082] From the starting node, the connection with other nodes is established through the semantic relationship edge to realize the multi-hop reasoning;

[0083] In the multi-hop reasoning process, the correlation between nodes is calculated according to the weight value on the semantic relationship edge, and the nodes highly related to the user query are screened out;

[0084] The information of the nuclear power project plan contained in the screened relevant nodes is extracted, and the information is sorted according to the semantic correlation degree;

[0085] The sorted information of the nuclear power project plan is clustered, and a plurality of nuclear power project topics related to the user query are generated according to the clustering result;

[0086] For each nuclear power project topic, the detailed information of the nuclear power project semantically associated therewith is obtained from the nuclear power project knowledge graph, and is organized in a logical order;

[0087] The organized nuclear power project topic and the detailed information of the nuclear power project are returned to the user.

[0088] According to one embodiment of the present application, the contents before and after the transmission of the nuclear power project plan are obtained, and are converted into a structured data format that can be subjected to semantic analysis;

[0089] The contents of the nuclear power project plan before and after the transmission are subjected to word segmentation and part-of-speech tagging processing, and key words and key phrases are extracted;

[0090] According to the pre-constructed nuclear power project knowledge graph, the semantic similarity of the contents of the nuclear power project plan before and after the transmission is calculated;

[0091] If the semantic similarity is lower than a preset threshold, it is judged that the information point may have a semantic change in the transmission process, and is marked as a potential information distortion point;

[0092] All potential information distortion points are grouped by a clustering algorithm, different types of information distortion modes are identified, and corresponding risk prompt information is automatically generated according to different information distortion modes;

[0093] The identified information distortion points and the corresponding risk prompt information are fed back to the relevant personnel, prompting them to pay attention to the potential information distortion risk.

[0094] According to one embodiment of the present application, the semantic relationship of the information distortion point is obtained according to the pre-constructed nuclear power project knowledge graph;

[0095] For the information distortion point, the information of the nuclear power project plan related thereto is inferred through the semantic relationship;

[0096] The inferred information of the nuclear power project plan is taken as candidate information, and the optimal completion information is determined according to the correlation degree of the candidate information and the information distortion point;

[0097] Fuse the optimal completion information into the original plan content to obtain the plan content after semantic completion;

[0098] According to the plan content after semantic completion, update the semantic relationship of the related node in the nuclear power project knowledge graph;

[0099] The plan content after semantic completion is structured and represented to form a standard format of nuclear power project plan transmission;

[0100] In the process of nuclear power project plan transmission, the integrity and accuracy of the information of the nuclear power project plan are monitored in real time, and if a distortion point is found, the above steps are repeated for semantic completion.

[0101] According to one embodiment of the present application, after obtaining the user's natural language form of the plan query, firstly, the query text is processed by using the jieba word segmentation tool, 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, by using the pre-constructed knowledge graph containing 500 nuclear power field concepts, through the knowledge representation learning algorithm based on TransE, the extracted concepts in the query text are mapped to the corresponding nodes in the nuclear power knowledge graph, and taking these nodes as the center and the relationship as the edge, a semantic query subgraph is formed. Then, using the Cypher query language of the Neo4j graph database, based on the semantic query subgraph, by setting the correlation threshold 8, the semantic reasoning and query expansion within 3 hops in the knowledge graph are carried out, and the plan knowledge related to the user query is obtained. When post-processing the query result, the TextRank algorithm is used to sort the importance of the knowledge fragments, the top 10 most relevant fragments are selected, and the pre-defined structured template is used to organize the knowledge fragments into structured JSON format data. According to the correlation and importance, the plan knowledge card containing the dimensions of plan theme, time, place, character, etc. is generated, and ECharts is used for visual display. Finally, by using the Seq2Seq model based on attention mechanism, the knowledge card is input to generate natural and fluent language description, which is replied to the user through voice synthesis or text form, and the whole process of plan query is completed.

[0102] According to one embodiment of the present application, first, the plan content before and after the plan delivery of the nuclear power project needs to be obtained, and the unstructured text data can be converted into structured JSON format through text analysis technology, so as to facilitate subsequent semantic analysis. Then, the text is segmented and part-of-speech tagged by using the Chinese segmentation tool Jieba, and the keywords such as nouns, verbs and adjectives are extracted, and the key phrases are identified by using the TextRank algorithm. Next, based on the pre-constructed knowledge graph in the nuclear power field and the HowNet semantic relationship database, 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 semantic change, and is marked as a potential distortion point. The K-means clustering is performed on all potential distortion points to identify different distortion modes, such as data missing and semantic drift. For each distortion mode, more than 20 rules are designed to automatically generate corresponding risk prompts, such as "key indicators missing, which may affect the plan executability". Finally, the identification results are fed back to the relevant personnel through the Web page to prompt the potential information distortion risk, and different processing suggestions are provided according to the distortion severity, such as re-collecting data and correcting deviation, to form a closed-loop plan delivery optimization process.

[0103] Furthermore, in order to achieve the above-mentioned object, the present application also provides a nuclear power field project management system based on a knowledge graph, Figure 2 is a flow chart of a nuclear power field project management system based on a knowledge graph according to an exemplary embodiment, as Figure 2 shown, the nuclear power field project management system based on a knowledge graph in the present application comprises:

[0104] The nuclear power project knowledge graph establishing module: the plan content of the nuclear power project is obtained, based on natural language processing technology, the concepts in the nuclear power project plan and their semantic relationships are obtained through named entity recognition and relationship extraction, the nuclear power project knowledge graph is constructed, 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;

[0105] The semantic mapping and correlation module: the pre-established coding rules for the nuclear power project plan based on the WBS method are obtained, wherein the WBS code can be divided into six groups, namely the project code, the project board, the island, the unit and the plant, the sub-part engineering activity and the floor or elevation, for each concept node of the nuclear power project knowledge graph, the coding rule is used for coding to obtain the coded concept node, and the mapping and correlation between the nuclear power project knowledge graph and the coding rule are realized;

[0106] The semantic query conversion module: based on the user's query to the nuclear power project plan, the user's query is analyzed through natural language understanding technology, the query concept is obtained, and the query concept is mapped to the corresponding node in the nuclear power project knowledge graph to convert the semantic query to the nuclear power project knowledge graph.

[0107] The plan information query module: on the nuclear power project knowledge graph, taking the concept node matched by the user query as the starting point, using a graph traversal algorithm, querying related plan concept nodes through the semantic relationship edges between nodes, and obtaining the information of the nuclear power project plan associated in semantics;

[0108] The information distortion point acquisition module: in the transmission process of the nuclear power project plan, the contents of the nuclear power project plan before and after transmission are acquired, semantic comparison is performed through semantic similarity calculation, and the information distortion points of the semantic change in the transmission process of the nuclear power project plan are identified;

[0109] The semantic completion module: for the identified information distortion points of the nuclear power project plan, according to the semantic relationship in the nuclear power project knowledge graph, using a semantic completion technology, inferring the missing or distorted information of the nuclear power project plan, and performing semantic completion on the content of the nuclear power project plan.

[0110] To achieve the above-mentioned purposes, the application further provides an electronic device, which comprises a processor, a memory and a computer program stored on the memory and executable on the processor, and the computer program is executed by the processor to realize the above-mentioned nuclear power field project management method based on a knowledge graph.

[0111] To achieve the above-mentioned purposes, the application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to realize the above-mentioned nuclear power field project management method based on a knowledge graph.

[0112] Those skilled in the art can realize that the modules and algorithm steps described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0113] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and equipment can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0114] In the embodiments of the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the described apparatus embodiments are merely schematic. The division of the modules is merely logical function division. There can be another division manner for the actual implementation, for example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or modules, and can be in electrical, mechanical or other forms.

[0115] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, i.e., can be located in one place, or can be distributed on multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0116] In addition, each functional module in the embodiments of the present application can be integrated in one processing module, or each module can be physically present alone, or two or more modules can be integrated in one module.

[0117] If the functions are realized 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 solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the energy saving signal transmission / reception method of the embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various program codes that can be stored.

[0118] The above description is merely the preferred embodiments of the present application and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application disclosed in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or equivalent features without departing from the inventive concept. For example, the above features can be replaced with the technical features disclosed in the present application (but not limited to) having similar functions to form technical solutions.

[0119] It should be understood that the size of the serial number of the steps in the summary of the application and the embodiments of the application does not absolutely mean the order of execution, the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

Claims

1. A knowledge graph-based project management method in the nuclear power field, characterized in that, The method comprises the following steps: Obtain the content of the nuclear power project plan, and based on natural language processing technology, obtain the concepts and semantic relationships in the nuclear power project plan through named entity recognition and relationship extraction, and construct a nuclear power project knowledge graph, wherein 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 the nuclear power project plan based on the WBS method, wherein the WBS code can be divided into six groups, namely, project code, project board, island, unit and plant, sub-part engineering activities, and floor or elevation, encode each concept node of the nuclear power project knowledge graph using the coding rules to obtain the encoded concept nodes, and realize the mapping association between the nuclear power project knowledge graph and the coding rules; Obtain the pre-established coding rules for the nuclear power project plan based on the WBS method, and encode each concept node in the nuclear power project knowledge graph using the coding rules to obtain the encoded concept nodes, and determine the hierarchical relationship between the codes in the coding rule system; Determine the association relationship between the encoded concept nodes, if the codes of two concept nodes have a hierarchical relationship in the coding rule system, it is determined that the two concept nodes have a mapping association; Group the encoded concept nodes by the mapping association between the coding rules and the concept nodes to obtain a set of grouped concept nodes; For each set of grouped concept nodes, determine the classification of the concept node set in the nuclear power project knowledge graph based on the coding rule system; Based on the user's query of the nuclear power project plan, the query concept is obtained through semantic analysis of the user's query based on natural language understanding technology, and the query concept is mapped to the corresponding node in the nuclear power project knowledge graph to convert the semantic query of the nuclear power project knowledge graph; In the nuclear power project knowledge graph, the concept node matched by the user query is taken as the starting point, and the graph traversal algorithm is used to query related plan concept nodes through the semantic relationship between nodes to obtain the information of the nuclear power project plan associated in semantics; In the transmission process of the nuclear power project plan, the contents of the nuclear power project plan before and after the transmission are obtained, and the semantic comparison is performed through semantic similarity calculation to identify the information distortion points in the semantic change of the nuclear power project plan in the transmission process; For the identified information distortion points of the nuclear power project plan, the semantic completion technology is used to infer the missing or distorted information of the nuclear power project plan according to the semantic relationship in the nuclear power project knowledge graph, and the semantic completion of the content of the nuclear power project plan is performed.

2. The knowledge graph-based nuclear power field project management method of claim 1, wherein, Obtain the text data of the nuclear power project plan, and pre-process the text data by 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 the nuclear power project text, the semantic relationship existing in the text is identified through a relationship extraction algorithm to construct nuclear power project relationship triples in the form of nuclear power project first concept, semantic relationship, and nuclear power project second concept; According to the extracted concepts and semantic relationships, a directed graph data structure is constructed, with concepts as nodes and semantic relationships as edges, 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 field project ontology and external knowledge base are integrated to expand the attribute information of the concept nodes, enrich the semantic associations between the concept nodes, and perfect the nuclear power project knowledge graph.

3. The knowledge graph-based nuclear power field project management method of claim 2, wherein, Based on the user's query of the nuclear power project plan, the user's natural language query of the nuclear power project plan is obtained, and the query text is preprocessed, including word segmentation, part-of-speech tagging, and named entity recognition; The preprocessed query text is analyzed semantically to extract the content of the query, including the plan theme, time, location, and characters; According to the pre-constructed 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 centered on nodes and edges; Based on the semantic query subgraph, semantic reasoning and query expansion are performed on the nuclear power project knowledge graph through the graph database query language to obtain the nuclear power project plan related to the user query; According to the relevance and importance of the nuclear power project plan, a multi-dimensional nuclear power project card is generated for visual display to the user; The generated nuclear power project card is converted into natural language text through natural language generation technology, and the user is replied in the form of voice or text, completing the query process of the nuclear power project.

4. The knowledge graph-based nuclear power field project management method of claim 3, wherein, According to the user's query of the nuclear power project plan, the corresponding concept node in the nuclear power project knowledge graph is matched and used as the starting node of the graph traversal algorithm; Starting from the starting node, the node is connected to other nodes through semantic relationship edges to realize multi-hop reasoning; During the multi-hop reasoning process, the relevance between nodes is calculated according to the weight values on the semantic relationship edges, and nodes highly relevant to the user query are selected; The selected relevant nodes are extracted for information of the nuclear power project plan, and sorted according to the semantic correlation degree; The sorted information of the nuclear power project plan is clustered, and multiple nuclear power project themes related to the user query are generated based on the clustering results; For each nuclear power project theme, the detailed information of the nuclear power project related to it is obtained from the nuclear power project knowledge graph and organized in logical order; The organized nuclear power project theme and detailed information of the nuclear power project are returned to the user.

5. The knowledge graph-based nuclear power field project management method of claim 4, wherein, The content before and after the transmission of the nuclear power project plan is obtained and converted into a structured data format that can be analyzed semantically; The content of the nuclear power project plan before and after transmission is processed by word segmentation and part-of-speech tagging to extract keywords and key phrases; According to the pre-constructed nuclear power project knowledge graph, the semantic similarity of the content of the nuclear power project plan before and after transmission is calculated; If the semantic similarity is lower than the preset threshold, it is judged that the information point may have semantic changes in the transmission process, and it is marked as a potential information distortion point; Through clustering algorithm, all potential information distortion points are grouped to identify different types of information distortion modes, and according to different information distortion modes, corresponding risk prompt information is automatically generated; The identified information distortion points and the corresponding risk prompt information are fed back to the relevant personnel, prompting them to pay attention to the potential information distortion risk.

6. The knowledge graph-based nuclear power field project management method of claim 5, wherein, According to the pre-constructed nuclear power project knowledge graph, the semantic relationship of the information distortion point is obtained; For the information distortion point, the information of the nuclear power project plan related thereto is inferred through the semantic relationship; The inferred information of the nuclear power project plan is taken as candidate information, and the optimal completion information is determined according to the relevance of the candidate information and the information distortion point; The optimal completion information is fused into the original plan content to obtain the plan content after semantic completion; According to the plan content after semantic completion, the semantic relationship of the related nodes in the nuclear power project knowledge graph is updated; The plan content after semantic completion is structured and represented to form a standard format for the transmission of the nuclear power project plan; During the transmission of the nuclear power project plan, the integrity and accuracy of the information of the nuclear power project plan are monitored in real time, and if a distortion point is found, the above steps are repeated for semantic completion.

7. A knowledge graph-based nuclear power field project management system, characterized in that, It comprises: A nuclear power project knowledge graph establishment module: the content of the nuclear power project plan is obtained, based on natural language processing technology, the concepts in the nuclear power project plan and their semantic relationships are obtained through named entity recognition and relationship extraction, and the nuclear power project knowledge graph is constructed, 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; A semantic mapping association module: the coding rules for the nuclear power project plan based on the WBS method are obtained in advance, wherein the WBS code can be divided into six groups, namely the project code, the project board, the island, the unit and the plant, the sub-part engineering activity and the floor or elevation, for each concept node of the nuclear power project knowledge graph, the coding rule is used for coding to obtain the coded concept node, and the mapping association between the nuclear power project knowledge graph and the coding rule is realized; A semantic query conversion module: based on the user's query of the nuclear power project plan, the user's query is analyzed through natural language understanding technology, the concepts of the query are obtained, and they are mapped to the corresponding nodes in the nuclear power project knowledge graph, and converted into a semantic query of the nuclear power project knowledge graph; A plan information query module: on the nuclear power project knowledge graph, the concept nodes matched by the user's query are taken as the starting point, a graph traversal algorithm is used to query related plan concept nodes through the semantic relationship between nodes, and the information of the nuclear power project plan associated in semantics is obtained; An information distortion point acquisition module: during the transmission of the nuclear power project plan, the contents of the nuclear power project plan before and after transmission are obtained, and semantic comparison is performed through semantic similarity calculation to identify the information distortion points whose semantics change during the transmission of the nuclear power project plan; A semantic completion module: for the identified information distortion points of the nuclear power project plan, according to the semantic relationship in the nuclear power project knowledge graph, the missing or distorted information of the nuclear power project plan is inferred by using the semantic completion technology, and the content of the nuclear power project plan is completed semantically.

8. An electronic device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the knowledge graph-based nuclear power field project management method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the knowledge graph-based nuclear power field project management method in any one of claims 1 to 6.

Images