Self-describing semantic data management method supporting panoramic information monitoring of substations

Abstract

The self-describing semantic data management method supporting the panoramic information monitoring of substations includes combining the semantics of the panoramic information of substations to expand the data type attributes and object attributes of the general network ontology language OWL syntax; using the expanded OWL syntax to model the semantic ontology of the panoramic information of substations, so as to provide the self-describing semantic data management service of the panoramic information of substations and support the data monitoring of the panoramic information of substations. It provides a complete solution for data processing, ontology modeling, knowledge extraction and time series data association for the high-level semantic application of the panoramic information monitoring of substations.

Description

Technical Field

[0001] The present invention belongs to the technical field of self-describing semantic data management for substations, and relates to a self-describing semantic data management method for supporting panoramic information monitoring of substations. Background Art

[0002] The substation panoramic information includes the operation data of the main primary equipment located in power safety zone I, measurement and control protection data, network security monitoring data, fault recording data, metering data, online monitoring data of primary equipment, auxiliary equipment data such as fire protection, security and dynamic environment, and online patrol data located in power safety zone IV.

[0003] Not all monitoring information in a substation can be simply mapped to a field in a table. Self-describing semantic data is a kind of semi-structured data, but the structure varies greatly. It is a basic model of tagging services and can be used for sharing information on the Web. Semi-structured data is generally "modeless" and has the characteristics of self-describing. XML is a more suitable format for storing such semi-structured data. The general Web Ontology Language (OWL) also uses XML syntax constraints to describe the semantics of the ontology.

[0004] The advent of the era of big data and artificial intelligence has provided feasible technologies for redefining industry data in all walks of life. Among them, RDF is a good ontology description method. It can define vocabulary for a certain field based on the understanding of the real world to describe the knowledge in this field, but it cannot restrict the attributes of the local value domain, cannot declare whether two or more classes, attributes and individuals are equivalent, cannot declare that two classes are disjoint, cannot construct new classes by combining certain classes through class union, intersection and complement declarations, cannot declare certain characteristics of attributes (such as transitivity, functionality, symmetry and reciprocity), and cannot constrain the possible or necessary value ranges of certain values. In order to solve the above shortcomings, OWL came into being, and OWL made up for the shortcomings of RDF. As a semantic representation method, OWL uses the logic theory in AI to give semantics to the network, but the description of relationship attributes is not rich enough, and the hierarchical description of attributes is not combined with domain applications. In addition, the substation monitoring system can perform standardized communication and simple integration of the substation's panoramic data, but it cannot provide complete technical support for advanced applications from a semantic level. The substation equipment knowledge graph can semantically characterize and describe the substation's panoramic information, but there is generally no good solution for the association between time series data and ontology instances. Summary of the invention

[0005] In order to solve the deficiencies in the prior art, the present invention provides a self-describing semantic data management method for supporting panoramic information monitoring of substations.

[0006] The present invention adopts the following technical solution.

[0007] The self-describing semantic data management method supporting panoramic information monitoring of substations includes the following steps:

[0008] Step 1: Combined with the semantics of the substation panoramic information, the data type attributes and object attributes of the general network ontology language OWL syntax are expanded;

[0009] Step 2: Use the expanded OWL syntax to perform semantic ontology modeling on the substation panoramic information to provide substation panoramic information self-describing semantic data management services and support substation panoramic information data monitoring.

[0010] Preferably, in step 1, the data type attribute expansion includes:

[0011] Add the following to the description of the data type property DatatypeProperty:

[0012] (1) Object property domain objectPropertyDomain, text index hint textIndexHints and searchable, deleteable, updateable, addable tags, which are used to allow adding properties to edge / objectProperty, specify how to index text in full-text search, configure whether the property is displayed in the "Filter by property" list in the search interface, configure whether the delete button is displayed in the UI and allows deleting the property in REST calls, configure whether the edit button should be displayed in the UI and allow updating the property value in REST calls, and configure whether the add property list should display this property and allow creating property values ​​in REST calls;

[0013] (2) The propertyGroup tag is used to specify that multiple properties can be included under a unified collapsible heading in the Inspector;

[0014] (3) Possible Values ​​possibleValues ​​tag, used to create a selection list on the user interface UI.

[0015] Preferably, in step 1, object attribute expansion includes:

[0016] For the object property objectProperty add:

[0017] The deleteable tag can be deleted and the updateable tag can be updated, which is used to indicate whether the delete and edit buttons are displayed in the UI and whether the attributes in the REST call can be deleted and updated.

[0018] Preferably, the object attribute expansion also includes:

[0019] Add glyph icon file name glyphIconFileName, color color, display type displayType, title format titleFormula, subtitle format subtitleFormula, time format timeFormula, add related concept whitelist addRelatedConceptWhiteList, deletable deleteable, updateable class tags, which are used to describe the image of the entity displayed on the UI, set the color used when underlining the entity in the document text part, specify how the UI displays different types of entities, set the JavaScript code snippet to display title and subtitle information in the search results, set the JavaScript code snippet to display time information in the search results, limit the items that can be added in the "Add Related" dialog box, and set whether the entity can be deleted and updated from the UI.

[0020] Preferably, in step 2, the expanded OWL syntax is used to describe the substation panoramic information in a semantic ontology file, specifically:

[0021] Using the OWL grammar expanded in step 1, the ontology Schema is designed according to the primary equipment main wiring topology, secondary equipment network topology, the correspondence between the sensor and the primary equipment body, the area relationship, and the fault attribution relationship, and described with an OWL file to obtain an ontology Schema description instance.

[0022] Preferably, the types of instances described in the ontology Schema are divided into physical graphs and semantic graphs, wherein the physical graph refers to a knowledge graph constructed by static factual information, and the semantic graph refers to a knowledge graph constructed by extracting knowledge from unstructured documents through machine learning algorithms.

[0023] Preferably, the physical map is generated by:

[0024] After parsing the SCD file, it is mapped to an OWL file description by developing a rule converter. At the same time, when generating a knowledge graph, if the attributes of the ontology instance are associated with time series data, the attribute instance data that conforms to the OWL ontology definition is generated through the conversion rules of the database.

[0025] Preferably, the semantic graph is generated by:

[0026] The fault report, regulations and fault recording data are first designed for the ontology Schema, and then this design is used as the conceptual type of entities, relationships and attributes to guide the knowledge extraction required for the knowledge graph. The pre-trained language representation model based on BERT is used to extract the entities, relationships, attributes and fault event metadata. The extracted metadata is the instantiation data of the knowledge graph ontology Schema. The ontology definition, association relationship and attribute description corresponding to each instance data correspond one by one to the ontology definition of the OWL file.

[0027] Preferably, in step 2, based on the semantic ontology model of the substation panoramic information, a self-describing semantic data management service of the substation panoramic information is provided to support the substation panoramic information data monitoring, specifically:

[0028] According to the OWL definition type of the semantic ontology model, services are provided externally through the REST interface, including:

[0029] Import, export, automatically generate, edit, and delete ontology schemas and their corresponding entities, relationships, attributes, and event instances, and provide conditional search and visual graph display of entities and relationships.

[0030] The beneficial effects of the present invention are as follows:

[0031] In view of the current situation that the semantic description capability of the existing communication model of the substation monitoring system is insufficient, the present invention proposes a panoramic information modeling and representation method of the substation monitoring system based on OWL. First, the description syntax of OWL is extended in vocabulary, and the attribute description of the object attribute (relational data) is added, so that the description of the relational data by the knowledge graph is more delicate and comprehensive, and the data description method of the attribute level is added for the relational data, which is more in line with the way and habit of human beings to process conceptual information. At the same time, through the full-text retrieval, UI display and management of OWL in the ontology, the system is easier to manage the attributes of the knowledge graph in a more fine-grained manner, and the operation of the knowledge graph relational data is richer. At the same time, combined with the expansion of OWL, the present invention provides a method for semantic knowledge acquisition and ontology modeling of the substation panoramic information data, and provides a mapping and conversion method between time series data and knowledge graph ontology attributes that is particularly suitable for substation monitoring scenarios, so as to provide a more complete description and characterization of the panoramic monitoring information of the substation for the knowledge graph, and provide a complete solution for data processing, ontology modeling, knowledge extraction and time series data association for the high-order semantic application of substation panoramic information monitoring.

[0032] The present invention adopts the web ontology language (OWL) which is more friendly to semantic description, performs semantic concept modeling on substation monitoring information, explores the semantic association of various types of data, mines the semantic knowledge of unstructured documents, forms semantic linkage for the panoramic monitoring information of substation, integrates the communication model description and factual storage data and unstructured semantic data of the existing monitoring system, forms a unified semantic modeling and knowledge representation method, and provides services for a series of semantic tasks; expands the object property (objectProperty) of OWL, adds corresponding attribute descriptions to the object property, and marks and expands the full-text retrieval, UI display method and management method of various attributes, and realizes the integration of many extension methods and semantic description based on the underlying data storage and operation capabilities; provides multi-value storage and fast indexing and retrieval support for knowledge graph attribute instances, and realizes one-to-many mapping between attribute instance data and multi-value data based on the storage and fast access support of massive data. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flow chart of a self-describing semantic data management method for supporting panoramic information monitoring of a substation in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0035] like Figure 1 As shown, Embodiment 1 of the present invention provides a self-describing semantic data management method for supporting panoramic information monitoring of a substation. In a preferred but non-limiting embodiment of the present invention, the method includes the following steps:

[0036] Step 1: Combined with the semantic representation of the substation panoramic information, the data type attributes and object attributes of the general network ontology language OWL syntax are expanded;

[0037] Further preferably, the data type attribute expansion includes:

[0038] Add the following to the description of the data type property DatatypeProperty:

[0039] (1) Object property domain objectPropertyDomain, text index hint textIndexHints and searchable, deleteable, updateable, addable tags, which are used to allow adding properties to edge / objectProperty, specify how to index text in full-text search, configure whether the property is displayed in the "Filter by property" list in the search interface, configure whether the delete button is displayed in the UI and allows deleting the property in REST calls, configure whether the edit button should be displayed in the UI and allow updating the property value in REST calls, and configure whether the add property list should display this property and allow creating property values ​​in REST calls;

[0040] (2) Property Group propertyGroup, which is used to specify that multiple properties can be included under a unified collapsible title in the Inspector;

[0041] (3) Possible values ​​possibleValues, used to create a selection list on the user interface UI.

[0042] Object property extensions include:

[0043] For the object property objectProperty add:

[0044] (1) deleteable and updateable are used to indicate whether the delete and edit buttons are displayed in the UI and whether deletion and updating of attributes in REST calls are allowed.

[0045] (2) Add glyph icon file name glyphIconFileName, color color, display type displayType, title format titleFormula, subtitle format subtitleFormula, time format timeFormula, add related concept whitelist addRelatedConceptWhiteList, deleteable deleteable, updateable class tags, which are used to describe the image of the entity displayed on the UI, set the color used when underlining the entity in the document text part, specify how the UI displays different types of entities, set the JavaScript code snippet to display title and subtitle information in the search results, set the JavaScript code snippet to display time information in the search results, limit the items that can be added in the "Add Related" dialog box, and set whether the entity can be deleted and updated from the UI.

[0046] Step 2: Use the expanded OWL syntax to perform semantic ontology modeling on the substation panoramic information to provide substation panoramic information self-describing semantic data management services and support substation panoramic information data monitoring.

[0047] Further preferably, the expanded OWL syntax is used to describe the substation panoramic information in a semantic ontology file, specifically:

[0048] Using the OWL grammar expanded in step 1, the ontology Schema is designed according to the primary equipment main wiring topology, secondary equipment network topology, the corresponding relationship between the sensor and the primary equipment body, the region relationship, and the fault attribution relationship. It is described using an OWL file to obtain an ontology Schema description instance. Combined with the various tags added above, the following example is shown:

[0049]

[0050]

[0051]

[0052] The types of instances described in the ontology schema are divided into physical graphs and semantic graphs. The physical graph refers to the knowledge graph constructed by static factual information such as substation equipment ledgers and equipment topology relationships, while the semantic graph refers to the knowledge graph constructed by extracting knowledge from unstructured documents through machine learning algorithms. They are obtained in the following ways:

[0053] (1) For physical graph generation: After parsing the SCD (substation configuration description) file, it is mapped into an OWL file description by developing a rule converter. At the same time, when generating the physical graph, if the attributes of the ontology instance are associated with time series data, the attribute instance data that conforms to the OWL ontology definition is generated through the conversion rules of the database;

[0054] (2) For semantic graph generation:

[0055] The unstructured data such as fault reports, regulations and fault recordings are first designed with ontology Schema, and then this design is used as the conceptual type of entities, relationships and attributes to guide the knowledge extraction required for the knowledge graph. The pre-trained language representation model based on BERT (Bidirectional Encoder Representation from Transformers) is used to extract metadata such as entities, relationships, attributes and fault events. The extracted metadata is the instantiation data of the knowledge graph ontology Schema. The ontology definition, association relationship and attribute description corresponding to each instance data correspond one-to-one with the ontology definition of the OWL file.

[0056] Further preferably, based on the semantic ontology model of substation panoramic information, the substation panoramic information data monitoring is supported, specifically:

[0057] For the semantic-based high-level applications of the substation monitoring system, services are provided externally through the REST interface according to the OWL definition type of the semantic ontology model, including:

[0058] Import, export, automatically generate, edit, delete and other operations of ontology Schema and its corresponding entities, relationships, attributes and event instances, and provide conditional search and visual graph display of entities and relationships.

[0059] Embodiment 2 of the present invention provides a self-describing semantic data management system supporting panoramic information monitoring of substations, including:

[0060] The attribute extension module is used to combine the semantic representation of the substation panoramic information and expand the data type attributes and object attributes of the general network ontology language OWL syntax;

[0061] The semantic ontology model building module is used to use the expanded OWL syntax to perform semantic ontology modeling on the substation panoramic information, so as to provide substation panoramic information self-describing semantic data management services and support substation panoramic information data monitoring.

[0062] A terminal comprises a processor and a storage medium; the storage medium is used to store instructions;

[0063] The processor is configured to operate according to the instructions to execute the steps of the method.

[0064] A computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0065] The beneficial effects of the present invention are as follows:

[0066] In view of the current situation that the semantic description capability of the existing communication model of the substation monitoring system is insufficient, the present invention proposes a panoramic information modeling and representation method of the substation monitoring system based on OWL. First, the description syntax of OWL is extended in vocabulary, and the attribute description of the object attribute (relational data) is added, so that the description of the relational data by the knowledge graph is more delicate and comprehensive, and the data description method of the attribute level is added for the relational data, which is more in line with the way and habit of human beings to process conceptual information. At the same time, through the full-text retrieval, UI display and management of OWL in the ontology, the system is easier to manage the attributes of the knowledge graph in a more fine-grained manner, and the operation of the knowledge graph relational data is richer. At the same time, combined with the expansion of OWL, the present invention provides a method for semantic knowledge acquisition and ontology modeling of the substation panoramic information data, and provides a mapping and conversion method between time series data and knowledge graph ontology attributes that is particularly suitable for substation monitoring scenarios, so as to provide a more complete description and characterization of the panoramic monitoring information of the substation for the knowledge graph, and provide a complete solution for data processing, ontology modeling, knowledge extraction and time series data association for the high-order semantic application of substation panoramic information monitoring.

[0067] The present invention adopts the web ontology language (OWL) which is more friendly to semantic description, performs semantic concept modeling on substation monitoring information, explores the semantic association of various types of data, mines the semantic knowledge of unstructured documents, forms semantic linkage for the panoramic monitoring information of substation, integrates the communication model description and factual storage data and unstructured semantic data of the existing monitoring system, forms a unified semantic modeling and knowledge representation method, and provides services for a series of semantic tasks; expands the object property (objectProperty) of OWL, adds corresponding attribute descriptions to the object property, and marks and expands the full-text retrieval, UI display method and management method of various attributes, and realizes the integration of many extension methods and semantic description based on the underlying data storage and operation capabilities; provides multi-value storage and fast indexing and retrieval support for knowledge graph attribute instances, and realizes one-to-many mapping between attribute instance data and multi-value data based on the storage and fast access support of massive data.

[0068] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0069] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0070] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0071] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A self-describing semantic data management method supporting panoramic information monitoring of substations, characterized by: The method comprises the following steps: Step 1: Combined with the semantics of the substation panoramic information, the data type attributes and object attributes of the general network ontology language OWL syntax are expanded; Step 2: Use the expanded OWL syntax to perform semantic ontology modeling on the substation panoramic information, so as to provide substation panoramic information self-describing semantic data management services and support substation panoramic information data monitoring; The expanded OWL syntax is used to describe the substation panoramic information in a semantic ontology file, specifically: Using the OWL syntax expanded in step 1, the ontology schema is designed according to the primary equipment main wiring topology, secondary equipment network topology, the correspondence between the sensor and the primary equipment body, the area relationship, and the fault attribution relationship, and described with an OWL file to obtain an ontology schema description instance; The types of instances described in the ontology schema are divided into physical graphs and semantic graphs, where the physical graph refers to the knowledge graph constructed by static factual information, and the semantic graph refers to the knowledge graph constructed by extracting knowledge from unstructured documents through machine learning algorithms; The physical map is generated as follows: After parsing the SCD file, it is mapped to an OWL file description by developing a rule converter. At the same time, when generating the knowledge graph, if the attributes of the ontology instance are associated with time series data, the attribute instance data that conforms to the OWL ontology definition is generated through the conversion rules of the database; The semantic graph is generated in the following way: The fault report, regulations and fault recording data are first designed for the ontology Schema, and then this design is used as the conceptual type of entities, relationships and attributes to guide the knowledge extraction required for the knowledge graph. The pre-trained language representation model based on BERT is used to extract the entities, relationships, attributes and fault event metadata. The extracted metadata is the instantiation data of the knowledge graph ontology Schema. The ontology definition, association relationship and attribute description corresponding to each instance data correspond one by one to the ontology definition of the OWL file.

2. The self-describing semantic data management method for supporting panoramic information monitoring of substations according to claim 1 is characterized in that: In step 1, the data type attribute expansion includes: Add the following to the description of the data type property DatatypeProperty: (1) Object property domain objectPropertyDomain, text index hint textIndexHints and searchable, deleteable, updateable, addable tags, which are used to allow adding properties to edge / objectProperty, specify how to index text in full-text search, configure whether the property is displayed in the "Filter by property" list in the search interface, configure whether the delete button is displayed in the UI and allows deleting the property in REST calls, configure whether the edit button should be displayed in the UI and allow updating the property value in REST calls, and configure whether the add property list should display this property and allow creating property values ​​in REST calls; (2) The propertyGroup tag is used to specify that multiple properties can be included under a unified collapsible heading in the Inspector; (3) Possible Values ​​possibleValues ​​tag, used to create a selection list on the user interface UI.

3. The self-describing semantic data management method for supporting panoramic information monitoring of substations according to claim 1 is characterized in that: In step 1, the object property expansion includes: adding a deleteable tag and an updateable tag to the object property objectProperty, which are used to indicate whether the delete and edit buttons are displayed in the UI and whether deletion and updating of the properties in the REST call are allowed.

4. The self-describing semantic data management method for supporting panoramic information monitoring of substations according to claim 3 is characterized in that: The object property expansion also includes: for the object property objectProperty, adding the glyph icon file name glyphIconFileName, color color, display type displayType, title format titleFormula, subtitle format subtitleFormula, time format timeFormula, adding the related concept whitelist addRelatedConceptWhiteList, deletable deleteable, and updateable class tags, which are respectively used to describe the image of the entity displayed on the UI, set the color used when underlining the entity in the document text part, specify how the UI displays different types of entities, set the JavaScript code snippet to display the title and subtitle information in the search results, set the JavaScript code snippet to display the time information in the search results, limit the items that can be added in the "Add Related" dialog box, and set whether the entity can be deleted or updated from the UI.

5. The self-describing semantic data management method for supporting panoramic information monitoring of substations according to claim 1 is characterized in that: In step 2, based on the semantic ontology model of substation panoramic information, a self-describing semantic data management service of substation panoramic information is provided to support substation panoramic information data monitoring, specifically: According to the OWL definition type of the semantic ontology model, services are provided externally through the REST interface, including: Import, export, automatically generate, edit, and delete ontology schemas and their corresponding entities, relationships, attributes, and event instances, and provide conditional search and visual graph display of entities and relationships.

Images