CN113191497B - Knowledge graph construction method and system for substation site selection - Google Patents
Knowledge graph construction method and system for substation site selection Download PDFInfo
- Publication number
- CN113191497B CN113191497B CN202110589514.5A CN202110589514A CN113191497B CN 113191497 B CN113191497 B CN 113191497B CN 202110589514 A CN202110589514 A CN 202110589514A CN 113191497 B CN113191497 B CN 113191497B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- ontology
- site selection
- layer
- project
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 39
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000011835 investigation Methods 0.000 claims abstract 3
- 238000007726 management method Methods 0.000 claims description 37
- 238000000034 method Methods 0.000 claims description 24
- 238000003058 natural language processing Methods 0.000 claims description 12
- 230000008520 organization Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 12
- 238000013461 design Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000003068 static effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge graph construction method and a system for substation stepping investigation site selection, wherein the knowledge graph construction method comprises the following steps: 1) Carrying out knowledge entity extraction on the acquired knowledge related to substation site selection according to a predetermined term source to obtain a site selection knowledge ontology set, an attribute set and a relationship set; 2) Based on the obtained address selection knowledge ontology set and relationship set, constructing an ontology layer knowledge graph for storing project decision knowledge and project management knowledge; 3) Based on the ontology layer knowledge graph, combining the attribute set to construct an instance layer knowledge graph for storing project case knowledge and expert experience knowledge; 4) Based on the ontology layer knowledge graph, the instance layer knowledge graph and the connection relation between the ontology layer knowledge graph and the instance layer knowledge graph, a project management and site selection decision knowledge system of substation site selection is constructed and is used for search learning and auxiliary decision making of knowledge by industry engineers. The invention can be widely applied to the field of substation stepping investigation and site selection.
Description
Technical Field
The invention relates to the field of electric power engineering survey design and the field of knowledge engineering, in particular to a knowledge graph construction method for substation stepping survey site selection.
Background
The substation site selection knowledge has the characteristics of wide related field, strong practical experience, high fragmentation degree, long learning period consumption and the like, the integration and accumulation of the knowledge in the service field at present basically depend on manual summarization and communication learning, the sharing and spreading range is limited, the learning effect is greatly influenced by personnel quality, and the rapid growth of high-level experts is restricted.
In recent years, the national part of design institute has established an enterprise-level knowledge base. However, due to insufficient knowledge fineness, unstructured reasons and the like, engineering practice knowledge is still distributed and stored in the brain of an expert, and a great amount of precious knowledge experience is taken away by retirement, sentry adjustment or off-duty of the expert, so that knowledge loss is easy to cause. In 2012, google has introduced a search engine service called a knowledge graph, rapidly developed in the fields of semantic search, intelligent question-answering, auxiliary language understanding and the like in the internet field, plays an important role in the fields of finance, medical treatment, electronic commerce and education vertical industry, and provides a new thought for solving the problems. However, how to apply the method to the field of substation site selection, no related technical research exists at present.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a knowledge graph construction method and a knowledge graph construction system for site selection of transformer substation, which are suitable for structural decomposition and knowledge graph construction of site selection knowledge of transformer substation, are used for storing project decision knowledge, project management knowledge, project case knowledge and expert experience knowledge, improve the management efficiency of the existing site selection knowledge of the transformer substation, assist engineering decision, facilitate the improvement of the culture speed of design engineers and further improve the survey design quality of the transformer engineering.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the first aspect of the invention provides a knowledge graph construction method for substation site selection, which comprises the following steps: 1) Carrying out knowledge entity extraction on the acquired knowledge related to substation site selection according to a predetermined term source to obtain a site selection knowledge ontology set, an attribute set and a relationship set; 2) Constructing an ontology layer knowledge graph based on the addressing knowledge ontology set and the relation set obtained in the step 1), wherein the ontology layer knowledge graph is used for storing project decision knowledge and project management knowledge; 3) Based on the ontology layer knowledge graph, combining the attribute set to construct an instance layer knowledge graph for storing project case knowledge and expert experience knowledge; 4) Based on the ontology layer knowledge graph, the instance layer knowledge graph and the connection relation between the ontology layer knowledge graph and the instance layer knowledge graph, a project management and site selection decision knowledge system of substation site selection is constructed and is used for search learning and auxiliary decision making of knowledge by industry engineers.
Further, in the step 1), knowledge entity extraction is performed on the acquired knowledge related to site selection of the substation according to a predetermined term source, so as to obtain a site selection knowledge ontology set, an attribute set and a relationship set, and the method comprises the following steps: 1.1 Collecting structured and unstructured knowledge related to substation site selection and performing topic division to obtain four types of knowledge, namely project decision knowledge, project management knowledge, project case knowledge and expert experience knowledge; 1.2 According to the business association field, acquiring a term source, wherein the term source comprises at least one of the following: a power thesaurus, a government official thesaurus, a technical specification glossary and a project quality management glossary; 1.3 According to the term sources determined in the step 1.2), carrying out knowledge entity extraction on the four types of knowledge related to the substation site selection obtained in the step 1.1), and obtaining a site selection knowledge ontology set, an attribute set and a relationship set.
Further, in the step 1.3), the method for extracting the knowledge entity includes the following steps: 3.1 The project decision knowledge and the project management knowledge are converted into a first entity after being selected according to a preset selection principle; 3.2 For the project case knowledge and expert experience knowledge, adopting NLP natural language processing technology, carrying out semantic word frequency analysis by combining the determined term sources, and screening and extracting high-frequency words as a class-II entity; 3.3 Combining the first entity and the second entity, and obtaining an initial site selection knowledge body and an attribute set after checking the deficiency; 3.4 Carrying out synonym and paraphrase clustering on the initial site selection knowledge body set and the attribute set extracted in the step 3.3), and determining a unique specification expression to obtain a simplified site selection knowledge body set and an attribute set; 3.5 Based on the reduced set of addressing knowledge entities and attributes and the term sources, a set of relationships is obtained.
Further, in the step 2), the method for constructing the ontology layer knowledge graph includes the following steps: 2.1 Dividing the site selection knowledge ontology set into 6 major topics of basic element classes, organization flow classes, influence factors classes, decision basis classes, process information classes and other classes of ontologies, and constructing an ontology class and an ontology class hierarchy; 2.2 Dividing the relation set into functional classes, constraint classes, action classes, logic classes, space classes, time sequence classes and relation other classes according to the application theme, and constructing a relation and relation level system; 2.3 Based on the ontology class and the ontology class level system constructed in the step 2.1) and the relationship level system constructed in the step 2.2), creating an ontology-relationship-ontology triplet according to the address selection business logic to obtain an ontology layer knowledge graph.
Further, in the step 3), the method for constructing the instance layer knowledge graph includes the following steps: 3.1 Creating an instance from the body class derivative, and building an instance-relationship-instance triplet by combining a relationship set to construct an instance layer knowledge graph; 3.2 Defining attributes and numerical types according to the instance description requirements, wherein the attributes are derived from project information and reports, flow records, decision basis, event and expert experience; the value type includes text, value, time, external links.
In a second aspect of the present invention, a knowledge graph construction system for substation site selection is provided, including: the entity extraction module is used for extracting knowledge entities from acquired knowledge related to substation site selection according to a predetermined term source to obtain a site selection knowledge ontology set, an attribute set and a relationship set; the ontology layer knowledge graph construction module is used for constructing an ontology layer knowledge graph for storing project decision knowledge and project management knowledge based on the obtained addressing knowledge ontology set and the relationship set; the instance layer knowledge graph construction module is used for constructing an instance layer knowledge graph for storing project case knowledge and expert experience knowledge by combining the attribute set based on the ontology layer knowledge graph; the knowledge system construction module is used for constructing a project management and site selection decision knowledge system of substation site selection based on the ontology layer knowledge map, the instance layer knowledge map and the connection relation between the ontology layer knowledge map and the instance layer knowledge map.
Further, the entity extraction module includes: the knowledge source acquisition module is used for collecting structured and unstructured knowledge related to substation site selection and carrying out theme division to obtain four types of knowledge, namely project decision knowledge, project management knowledge, project case knowledge and expert experience knowledge; the term source acquisition module is used for acquiring term sources according to the service association field; and the knowledge entity extraction module is used for extracting the knowledge entity of the four acquired knowledge types related to the substation site selection according to the determined term sources to obtain a site selection knowledge ontology set, an attribute set and a relationship set.
Further, the knowledge entity extraction module includes: the first entity extraction module is used for selecting the project decision knowledge and the project management knowledge according to a preset selection principle and converting the project decision knowledge and the project management knowledge into a first entity; the second entity extraction module is used for carrying out semantic word frequency analysis on the project case knowledge and expert experience knowledge by adopting an NLP natural language processing technology and a determined term source, and screening and extracting high-frequency words to serve as a second entity; the initial entity combination determining module is used for combining the first entity and the second entity, checking and supplementing the missing knowledge entity to obtain an initial site selection knowledge body and an attribute set; the entity disambiguation module is used for carrying out synonym and paraphrasing clustering on the extracted initial address selection knowledge body set and attribute set, determining a unique specification expression and obtaining a simplified address selection knowledge body set and attribute set; and the relation set determining module is used for obtaining a corresponding relation set based on the obtained simplified site selection knowledge body set, the attribute set and the term source.
Further, the ontology layer knowledge graph construction module includes: the ontology system construction module is used for dividing the topics of each knowledge entity to obtain 6 major topics of basic element classes, organization flow classes, influence factor classes, decision basis classes, process information classes and other ontology classes, and constructing an ontology class and ontology class hierarchy; the relation system construction module is used for dividing the relation according to the application to obtain a function class, a constraint class, an action class, a logic class, a space class, a time sequence class and other relation classes, and constructing a relation and relation grade system; and the ontology layer knowledge graph module is used for creating an ontology-relationship-ontology triplet according to the address selection business logic based on the constructed ontology class and the ontology class level system, the relationship and the relationship level system to obtain an ontology layer knowledge graph.
Further, the instance layer knowledge graph construction module includes: the instance layer knowledge graph module is used for deriving and creating an instance from the ontology class, combining the relationship to create an instance-relationship-instance triplet, and constructing an instance layer knowledge graph; the attribute and value type definition module is used for defining attribute and value type according to the instance description requirement, wherein the attribute is derived from project information and report, flow records, decision basis, event and expert experience; the numerical type comprises text, numerical value, time and external link. Due to the adoption of the technical scheme, the invention has the following advantages: 1. the invention carries out structural decomposition on knowledge in the substation site selection field, builds a static knowledge system and dynamic information knowledge, and forms a relatively complete site selection knowledge graph. 2. The static knowledge system constructed by the invention is stored by the ontology layer of the knowledge graph, takes the project management knowledge flow directed graph as a main context, correlates and communicates management knowledge such as task targets, design requirements, work contents, organization, personnel organizations and the like and decision-making knowledge such as different professional technical specifications and the like to form an address selection knowledge guide, and provides actual and effective guidance for address selection. 3. The dynamic knowledge constructed by the invention is stored by an instance layer of the knowledge graph, stores project case information and association relations among different cases, supplements the project basic information, site technical and economic schemes, design basis and specifications, expert decision knowledge and external links as attributes, and forms a rich case knowledge base for new engineering retrieval and auxiliary decision making. The knowledge map is stored by adopting Neoj map database, so that knowledge retrieval and relationship visualization can be conveniently realized, and the visualized network relationship structure is similar to the human association thinking mode, thereby being convenient for manual application. Therefore, the invention can be widely applied to the field of electric power engineering survey design and the field of knowledge engineering.
Drawings
FIG. 1 is a flow chart of a knowledge graph construction method for substation site selection;
FIG. 2 is a schematic diagram of the subject matter classification and ranking of the present invention;
FIG. 3 is a schematic diagram of a relationship topic division of the present invention;
FIG. 4 is a schematic diagram of a knowledge graph of the ontology layer according to the present invention;
FIG. 5 is a schematic diagram of a knowledge graph of an example layer of the present invention;
FIG. 6 is a schematic diagram of a property set of an example of an item of the present invention;
FIG. 7 is a diagram illustrating the relationship between an ontology layer and an example layer according to the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings and examples.
The invention carries out deep analysis on sources, contents, characteristics, application requirements and the like of knowledge in the substation site selection field, proposes to construct a knowledge ontology and a relationship class according to theme division, and establishes an ontology knowledge base. And an instance knowledge base is built by deriving the instance from the ontology, so that the aim of structuring, managing and storing the static knowledge system and the dynamic information knowledge for site selection is fulfilled. Wherein, the static knowledge comprises technical rule knowledge and project management knowledge, and the dynamic knowledge comprises project case knowledge and expert experience knowledge.
As shown in fig. 1, in order to achieve the above objective, the present invention provides a knowledge graph construction method for substation site selection, which specifically includes the following steps:
1) Knowledge source acquisition: collecting structured and unstructured knowledge related to site selection of transformer substation, and dividing the collected structured and unstructured knowledge into four types of knowledge topics, wherein the four types of knowledge topics are respectively as follows: project decision knowledge, project management knowledge, project case knowledge, and expert experience knowledge.
2) The term source acquisition: and acquiring an electric power subject matter vocabulary, a government document subject matter vocabulary, a technical specification glossary and a project quality management glossary as term sources according to the business association field.
3) Knowledge entity extraction: and (3) extracting knowledge entities from the four types of knowledge related to the substation site selection obtained in the step (1) according to the term sources determined in the step (2), so as to obtain a site selection knowledge ontology set, an attribute set and a relationship set.
Specifically, the method comprises the following steps:
3.1 For project decision knowledge and project management knowledge related to the power engineering construction field, the power system field and the like in the four kinds of knowledge, the knowledge is converted into an entity after being selected according to a preset selection principle. The preset selection principle refers to selecting based on terms related to internal and external influences in a substation site selection activity, such as standardized terms describing site selection targets, contents, processes, influences, evaluation, decision-making and other industry conventions.
3.2 For the project case knowledge such as site selection technical report, post-evaluation report, engineering quality analysis report and the like, and expert experience knowledge such as expert summary report and the like, adopting NLP natural language processing technology, carrying out semantic word frequency analysis by combining the term sources determined in the step 2), and screening and extracting high-frequency words as entities. The occurrence frequency of the high-frequency vocabulary can be determined according to actual needs.
3.3 Combining the entities obtained in the step 3.1) and the step 3.2), and checking the missing knowledge entities by manual experts in the field of transformer substation site selection work related technology, manufacturing cost and project management to obtain an initial site selection knowledge body and an attribute set.
3.4 And (3) carrying out synonym and paraphrase clustering on the initial site selection ontology set and the attribute set extracted in the step 3.3), and determining a unique specification expression to obtain a simplified site selection ontology set and attribute set.
3.5 Based on the set of addressees knowledge entities and attributes obtained in step 3.3) and the term sources in step 2), a set of relationships is obtained.
4) Ontology layer knowledge graph: based on the address selection knowledge ontology set and the relation set obtained in the step 3), an ontology layer knowledge graph is constructed and used for storing project decision knowledge and project management knowledge, and the knowledge objectively exists and is static knowledge.
The project flow body directed graph is taken as a main context, and a task target, design requirements, work content, organization, personnel organization, different professional technical specifications and the like are associated and communicated with the site selection body layer knowledge graph. Specifically, the method comprises the following steps:
4.1 As shown in fig. 2, the site selection ontology set is divided according to 6 major classes of topics, and an ontology class hierarchy are constructed, wherein the 6 major classes of topics are respectively basic element classes, organization flow classes, influence factor classes, decision basis classes, process information classes and other classes. Each class of theme can be divided into a plurality of subclasses, and the subclasses can be expanded step by step according to requirements. For example, the base element classes can be divided into subclasses of people, roles, organizations, transactions, time and place, etc.; the organization flow can be divided into various links such as planning, surveying, collecting, selecting address, designing, cooperating, countersign, evaluating, verifying and confirming; influence factors can be classified into policy influence factors, non-policy influence factors, and the like; the decision basis classes can be divided into various bases influencing site selection decision such as technical regulations, manufacturing cost regulations, owner regulations, project requirements and the like; the process information class can be divided into subclasses of targets, inputs, processes, outputs, and the like; other classes may be divided into other ontologies not included in the above-described classes.
4.2 As shown in fig. 3, a relationship and a relationship level system are constructed, and the relationship set is divided into a function class, a constraint class, an action class, a logic class, a space class, a time sequence class and other classes according to the application subject, wherein the function class is used for describing the upper and lower relationship between the entities, the constraint class is used for describing the constraint relationship between the entities, the logic class is used for describing the logic association relationship between the entities, the space class is used for describing the relationship of the spatial position between the entities, the time sequence class is used for describing the time sequence relationship between the entities, and the other classes are used for describing other relationships which are not included in the classes.
4.3 As shown in fig. 4, based on the ontology and the ontology class hierarchy constructed in the step 4.1) and the relationship hierarchy constructed in the step 4.2), creating an ontology-relationship-ontology triplet according to the addressing business logic, and obtaining an ontology layer knowledge graph.
5) Example knowledge graph: based on the ontology layer knowledge graph, an instance layer knowledge graph is constructed by combining the attribute set, and is used for storing project case knowledge and expert experience knowledge. Such knowledge is dynamic, with high update rate, depending on project and expert individuals present.
The project case knowledge graph derived from the ontology layer knowledge graph is used for storing project case information and association relations of different project cases, and is supplemented by taking station addresses, technical and economic schemes, design basis and specifications, expert decision knowledge, external links and the like as attributes. Specifically, the method comprises the following steps:
5.1 As shown in fig. 5, an instance is created by deriving from the ontology class, an instance-relationship-instance triplet is created in combination with the relationship set, and an instance layer knowledge graph is constructed.
5.2 As shown in fig. 6, the attributes and the numerical types are defined according to the instance description requirements, and the attributes are derived from project information and reports, flow records, decision bases and events, expert experiences, and the like. The value type includes text, value, time, external links.
6) Based on the ontology layer knowledge graph, the instance layer knowledge graph and various connection relations between the ontology layer knowledge graph and the instance layer knowledge graph, a complete project management and site selection decision knowledge system is constructed and is used for search learning and auxiliary decision making of knowledge by industry engineers.
As shown in FIG. 7, the method is suitable for knowledge structured management of the site selection work of the transformer substation engineering, can construct a complete project management and site selection decision knowledge system according to the ontology layer knowledge graph, the instance layer knowledge graph and various link relations between the ontology layer knowledge graph and the instance layer knowledge graph, and can be continuously expanded along with the large-scale increase of the project number and the updating of expert knowledge. Based on Neoj figure database, the quick retrieval and relation visualization of knowledge can be realized, the network structure is similar to the human associative thinking mode, and the retrieval learning and auxiliary decision making of knowledge by industry engineers are facilitated.
Based on the knowledge graph construction method facing the substation site selection, the invention also provides a knowledge graph construction system facing the substation site selection, which comprises the following steps: the knowledge source acquisition module is used for collecting structured and unstructured knowledge related to substation site selection, and dividing the collected structured and unstructured knowledge into four types of knowledge topics, wherein the four types of knowledge topics are respectively: project decision knowledge, project management knowledge, project case knowledge, and expert experience knowledge; the term source acquisition module is used for acquiring an electric power subject vocabulary, a government document subject vocabulary, a technical specification glossary and a project quality management glossary as term sources according to the service association field; the knowledge entity extraction module is used for extracting the knowledge entity of the four acquired knowledge types related to the substation site selection according to the determined term sources so as to obtain a site selection knowledge ontology set, an attribute set and a relationship set; the ontology layer knowledge graph construction module is used for constructing an ontology layer knowledge graph for storing project decision knowledge and project management knowledge based on the obtained addressing knowledge ontology set and the relationship set; the instance layer knowledge graph construction module is used for constructing an instance layer knowledge graph for storing project case knowledge and expert experience knowledge by combining the attribute set based on the ontology layer knowledge graph; the knowledge system construction module is used for constructing a complete project management and site selection decision knowledge system based on the ontology layer knowledge graph, the instance layer knowledge graph and various connection relations among the ontology layer knowledge graph and the instance layer knowledge graph.
Further, the knowledge entity extraction module includes: the first entity extraction module is used for selecting common terms related to the power engineering construction field and the power system field in the four types of knowledge according to a preset selection principle and then converting the common terms into entities; the second entity extraction module is used for carrying out semantic word frequency analysis on the project case knowledge and expert experience knowledge by adopting an NLP natural language processing technology and a determined term source, and screening and extracting high-frequency words as entities; the initial entity combination determining module is used for combining the entities of the first entity extracting module and the second entity extracting module, checking and supplementing the missing knowledge entities to obtain an initial site selection knowledge body and an attribute set; the entity disambiguation module is used for carrying out synonym and paraphrasing clustering on the extracted initial address selection knowledge body set and attribute set, determining a unique specification expression and obtaining a simplified address selection knowledge body set and attribute set; and the relation set determining module is used for obtaining a corresponding relation set based on the obtained site selection knowledge ontology set, the attribute set and the term source.
Further, the ontology layer knowledge graph construction module includes: the ontology system construction module is used for carrying out theme division on each knowledge entity and constructing ontology class and ontology class grade systems; the relation system construction module is used for dividing the theme of the relation according to the use and constructing a relation and relation grade system; and the ontology layer knowledge graph module is used for creating an ontology-relationship-ontology triplet according to the address selection business logic based on the constructed ontology class and the ontology class level system, the relationship and the relationship level system to obtain an ontology layer knowledge graph.
Further, the example layer knowledge graph construction module includes: the instance layer knowledge graph module is used for deriving and creating an instance from the ontology class, combining the relationship to create an instance-relationship-instance triplet, and constructing an instance layer knowledge graph; and the attribute and value type definition module is used for defining attribute and value types according to the instance description requirements.
Those skilled in the art will appreciate that many changes can be made in the definition of ontology, relationship, and/or network of relationships between entities in accordance with the present invention without departing from the spirit and substance of the invention, and such changes are intended to be covered by the appended claims.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be finally understood that the foregoing embodiments are merely illustrative of the technical solutions of the present invention and not limiting the scope of protection thereof, and although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that various changes, modifications or equivalents may be made to the specific embodiments of the invention, and these changes, modifications or equivalents are within the scope of protection of the claims appended hereto.
Claims (2)
1. The knowledge graph construction method for substation site selection is characterized by comprising the following steps of:
1) Carrying out knowledge entity extraction on the acquired knowledge related to substation site selection according to a predetermined term source to obtain a site selection knowledge ontology set, an attribute set and a relationship set;
2) Constructing an ontology layer knowledge graph based on the addressing knowledge ontology set and the relation set obtained in the step 1), wherein the ontology layer knowledge graph is used for storing project decision knowledge and project management knowledge; 3) Based on the ontology layer knowledge graph, combining the attribute set to construct an instance layer knowledge graph for storing project case knowledge and expert experience knowledge;
4) Based on the ontology layer knowledge graph, the instance layer knowledge graph and the connection relation between the ontology layer knowledge graph and the instance layer knowledge graph, a project management and site selection decision knowledge system of substation site selection is constructed and is used for search learning and auxiliary decision making of knowledge by industry engineers;
In the step 1), knowledge entity extraction is performed on acquired knowledge related to site selection of a substation according to a predetermined term source, and a method for obtaining a site selection knowledge ontology set, an attribute set and a relationship set comprises the following steps:
1.1 Collecting structured and unstructured knowledge related to substation site selection and performing topic division to obtain four types of knowledge, namely project decision knowledge, project management knowledge, project case knowledge and expert experience knowledge;
1.2 According to the business association field, acquiring a term source, wherein the term source comprises at least one of the following: a power thesaurus, a government official thesaurus, a technical specification glossary and a project quality management glossary;
1.3 Carrying out knowledge entity extraction on the four types of knowledge related to the substation site selection obtained in the step 1.1) according to the term sources determined in the step 1.2), and obtaining a site selection knowledge ontology set, an attribute set and a relationship set;
In the step 1.3), the method for extracting the knowledge entity comprises the following steps:
1.3.1 The project decision knowledge and the project management knowledge are converted into a first entity after being selected according to a preset selection principle;
1.3.2 For the project case knowledge and expert experience knowledge, adopting NLP natural language processing technology, carrying out semantic word frequency analysis by combining the determined term sources, and screening and extracting high-frequency words as a second entity;
1.3.3 Combining the first entity and the second entity, and obtaining an initial site selection knowledge body and an attribute set after checking the deficiency;
1.3.4 Synonym and paraphrase clustering are carried out on the initial site selection ontology set and the attribute set extracted in the step 1.3.3), unique specification expression is determined, and the simplified site selection ontology set and attribute set are obtained;
1.3.5 Based on the reduced address knowledge entity set and attribute set and the term source, obtaining a relation set;
in the step 2), the method for constructing the ontology layer knowledge graph comprises the following steps:
2.1 Dividing the site selection knowledge ontology set into 6 major topics of basic element classes, organization flow classes, influence factors classes, decision basis classes, process information classes and other classes of ontologies, and constructing an ontology class and an ontology class hierarchy;
2.2 Dividing the relation set into functional classes, constraint classes, action classes, logic classes, space classes, time sequence classes and relation other classes according to the application theme, and constructing a relation and relation level system;
2.3 Based on the ontology class and the ontology class level system constructed in the step 2.1) and the relationship level system constructed in the step 2.2), creating an ontology-relationship-ontology triplet according to the address selection business logic to obtain an ontology layer knowledge graph;
in the step 3), the method for constructing the instance layer knowledge graph comprises the following steps:
3.1 Creating an instance from the body class derivative, and building an instance-relationship-instance triplet by combining a relationship set to construct an instance layer knowledge graph;
3.2 Defining attributes and numerical types according to the instance description requirements, wherein the attributes are derived from project information and reports, flow records, decision basis, event and expert experience; the value type includes text, value, time, external links.
2. The utility model provides a knowledge graph construction system towards transformer substation's investigation site selection which characterized in that includes: the entity extraction module is used for extracting knowledge entities from acquired knowledge related to substation site selection according to a predetermined term source to obtain a site selection knowledge ontology set, an attribute set and a relationship set;
The ontology layer knowledge graph construction module is used for constructing an ontology layer knowledge graph for storing project decision knowledge and project management knowledge based on the obtained addressing knowledge ontology set and the relationship set;
The instance layer knowledge graph construction module is used for constructing an instance layer knowledge graph for storing project case knowledge and expert experience knowledge by combining the attribute set based on the ontology layer knowledge graph;
The knowledge system construction module is used for constructing a project management and site selection decision knowledge system of substation site selection based on the ontology layer knowledge map, the instance layer knowledge map and the connection relation between the ontology layer knowledge map and the instance layer knowledge map;
the entity extraction module comprises:
The knowledge source acquisition module is used for collecting structured and unstructured knowledge related to substation site selection and carrying out theme division to obtain four types of knowledge, namely project decision knowledge, project management knowledge, project case knowledge and expert experience knowledge;
The term source acquisition module is used for acquiring term sources according to the service association field;
the knowledge entity extraction module is used for extracting the knowledge entity of the four acquired knowledge types related to the substation site selection according to the determined term sources to obtain a site selection knowledge ontology set, an attribute set and a relationship set;
the knowledge entity extraction module comprises:
The first entity extraction module is used for selecting the project decision knowledge and the project management knowledge according to a preset selection principle and converting the project decision knowledge and the project management knowledge into a first entity;
The second entity extraction module is used for carrying out semantic word frequency analysis on the project case knowledge and expert experience knowledge by adopting an NLP natural language processing technology and a determined term source, and screening and extracting high-frequency words to serve as a second entity;
the initial entity combination determining module is used for combining the first entity and the second entity, checking and supplementing the missing knowledge entity to obtain an initial site selection knowledge body and an attribute set;
The entity disambiguation module is used for carrying out synonym and paraphrasing clustering on the extracted initial address selection knowledge body set and attribute set, determining a unique specification expression and obtaining a simplified address selection knowledge body set and attribute set;
the relation set determining module is used for obtaining a corresponding relation set based on the obtained simplified address selection knowledge body set, the attribute set and the term source;
The ontology layer knowledge graph construction module comprises:
The ontology system construction module is used for dividing the topics of each knowledge entity to obtain 6 major topics of basic element classes, organization flow classes, influence factor classes, decision basis classes, process information classes and other ontology classes, and constructing an ontology class and ontology class hierarchy;
The relation system construction module is used for dividing the relation according to the application to obtain a function class, a constraint class, an action class, a logic class, a space class, a time sequence class and other relation classes, and constructing a relation and relation grade system;
the ontology layer knowledge graph module is used for creating an ontology-relationship-ontology triplet according to the address selection business logic based on the constructed ontology class and the ontology class level system, the relationship and the relationship level system to obtain an ontology layer knowledge graph;
The instance layer knowledge graph construction module comprises:
the instance layer knowledge graph module is used for deriving and creating an instance from the ontology class, combining the relationship to create an instance-relationship-instance triplet, and constructing an instance layer knowledge graph;
The attribute and value type definition module is used for defining attribute and value type according to the instance description requirement, wherein the attribute is derived from project information and report, flow records, decision basis, event and expert experience; the numerical type comprises text, numerical value, time and external link.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110589514.5A CN113191497B (en) | 2021-05-28 | 2021-05-28 | Knowledge graph construction method and system for substation site selection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110589514.5A CN113191497B (en) | 2021-05-28 | 2021-05-28 | Knowledge graph construction method and system for substation site selection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113191497A CN113191497A (en) | 2021-07-30 |
| CN113191497B true CN113191497B (en) | 2024-04-23 |
Family
ID=76985702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110589514.5A Active CN113191497B (en) | 2021-05-28 | 2021-05-28 | Knowledge graph construction method and system for substation site selection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191497B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779358B (en) * | 2021-09-14 | 2024-05-24 | 支付宝(杭州)信息技术有限公司 | Event detection method and system |
| CN115796331A (en) * | 2022-11-01 | 2023-03-14 | 清华大学 | Urban resource prediction method and system based on multi-mode urban knowledge graph |
| CN116150929B (en) * | 2023-04-17 | 2023-07-07 | 中南大学 | Construction method of railway route selection knowledge graph |
| CN117592561B (en) * | 2024-01-18 | 2024-04-19 | 国网江苏省电力工程咨询有限公司 | Enterprise digital operation multidimensional data analysis method and system |
| CN118446835A (en) * | 2024-04-02 | 2024-08-06 | 中国长江电力股份有限公司 | Intelligent operation method and system for step power station |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665098A (en) * | 2018-05-04 | 2018-10-16 | 国网山东省电力公司菏泽供电公司 | A kind of addressing constant volume optimization method and device of distributed generation resource access power distribution network |
| CN110427436A (en) * | 2019-07-31 | 2019-11-08 | 北京百度网讯科技有限公司 | The method and device of entity similarity calculation |
| CN111143479A (en) * | 2019-12-10 | 2020-05-12 | 浙江工业大学 | Knowledge graph relation extraction and REST service visualization fusion method based on DBSCAN clustering algorithm |
| CN111444348A (en) * | 2020-02-27 | 2020-07-24 | 上海交通大学 | Method, system and medium for constructing and applying knowledge graph architecture |
| CN111813950A (en) * | 2020-05-20 | 2020-10-23 | 淮阴工学院 | Building field knowledge graph construction method based on neural network self-adaptive optimization and parameter adjustment |
| CN111930932A (en) * | 2020-09-25 | 2020-11-13 | 中国人民解放军国防科技大学 | Knowledge graph representation learning method and device in network space security field |
| CN111949855A (en) * | 2020-07-31 | 2020-11-17 | 国网上海市电力公司 | Knowledge map-based engineering technology knowledge retrieval platform and method thereof |
| CN111949834A (en) * | 2019-05-17 | 2020-11-17 | 上海树融数据科技有限公司 | Site selection method and site selection platform |
| CN112100394A (en) * | 2020-08-10 | 2020-12-18 | 淮阴工学院 | Knowledge graph construction method for recommending medical experts |
-
2021
- 2021-05-28 CN CN202110589514.5A patent/CN113191497B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665098A (en) * | 2018-05-04 | 2018-10-16 | 国网山东省电力公司菏泽供电公司 | A kind of addressing constant volume optimization method and device of distributed generation resource access power distribution network |
| CN111949834A (en) * | 2019-05-17 | 2020-11-17 | 上海树融数据科技有限公司 | Site selection method and site selection platform |
| CN110427436A (en) * | 2019-07-31 | 2019-11-08 | 北京百度网讯科技有限公司 | The method and device of entity similarity calculation |
| CN111143479A (en) * | 2019-12-10 | 2020-05-12 | 浙江工业大学 | Knowledge graph relation extraction and REST service visualization fusion method based on DBSCAN clustering algorithm |
| CN111444348A (en) * | 2020-02-27 | 2020-07-24 | 上海交通大学 | Method, system and medium for constructing and applying knowledge graph architecture |
| CN111813950A (en) * | 2020-05-20 | 2020-10-23 | 淮阴工学院 | Building field knowledge graph construction method based on neural network self-adaptive optimization and parameter adjustment |
| CN111949855A (en) * | 2020-07-31 | 2020-11-17 | 国网上海市电力公司 | Knowledge map-based engineering technology knowledge retrieval platform and method thereof |
| CN112100394A (en) * | 2020-08-10 | 2020-12-18 | 淮阴工学院 | Knowledge graph construction method for recommending medical experts |
| CN111930932A (en) * | 2020-09-25 | 2020-11-13 | 中国人民解放军国防科技大学 | Knowledge graph representation learning method and device in network space security field |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113191497A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113191497B (en) | Knowledge graph construction method and system for substation site selection | |
| Glass et al. | Research in software engineering: an analysis of the literature | |
| Zong et al. | Doctoral dissertations of Library and Information Science in China: A co-word analysis | |
| CN106919689A (en) | Professional domain knowledge mapping dynamic fixing method based on definitions blocks of knowledge | |
| CN111078868A (en) | Knowledge graph analysis-based equipment test system planning decision method and system | |
| US20090300043A1 (en) | Text based schema discovery and information extraction | |
| CN107798387B (en) | Knowledge service system and method suitable for full life cycle of high-end equipment | |
| CN106168965A (en) | Knowledge mapping constructing system | |
| CN106407216A (en) | Clue tracing audition system developed on basis of semantic net construction path and construction method of clue tracing audition system | |
| CN109871393A (en) | A kind of access method based on label system | |
| CN111126461B (en) | Intelligent auditing method based on machine learning model interpretation | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| CN111241299A (en) | Knowledge graph automatic construction method for legal consultation and retrieval system thereof | |
| Pei et al. | Construction of curriculum knowledge map based on ontology | |
| Bhanot et al. | Identifying the perspectives for sustainability enhancement: a text mining approach for a machining process | |
| CN117436519A (en) | Building engineering database construction method supporting knowledge graph | |
| D'Orazio et al. | Tworavens for event data | |
| Rabin et al. | Development of the formal model for the presentation of poorly structured and unstructured information | |
| CN116578612A (en) | Lithium battery finished product detection data asset construction method | |
| CN112668836B (en) | Risk spectrum-oriented associated risk evidence efficient mining and monitoring method and apparatus | |
| Nurhayati et al. | Digitalization of MSMEs: A bibliometric analysis using Biblioshiny and VOSviewer | |
| Peral et al. | Energy consumption prediction by using an integrated multidimensional modeling approach and data mining techniques with Big Data | |
| CN113688250A (en) | Automatic construction method of legal knowledge graph based on part-of-speech and word order analysis | |
| Mubarakah | Software Engineering Taxonomy Reviews | |
| Wyskwarski | Business intelligence-publication analysis using the R language |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |