Multi-subject energy digital object interconnection method, system and device, and storage medium

Abstract

The invention discloses an interconnection method, system and device for multi-main-body energy digital objects and a storage medium. The interconnection method comprises the following steps: identifying an identifier of each main energy digital object to obtain one-to-one corresponding energy digital object bodies; according to the metadata information of the energy digital object, feature data sets of different feature categories are extracted through natural language processing; constructing a feature category ontology of the energy digital object according to a clustering result of the feature data set; forming a node set according to energy digital object nodes constructed by utilizing the energy digital object ontology and feature category nodes constructed by utilizing the feature category ontology; establishing an interconnection relationship between the energy digital object nodes according to an identification coding rule; establishing a connection relationship between the energy digital object node and the feature category node according to similarity analysis; and according to the interconnection relationship and the connection relationship, establishing a topological relationship between the node sets to form an interconnection graph, and completing interconnection of the multi-main-body energy digital objects.

Description

Technical Field

[0001] The present invention relates to the field of intelligent processing of energy data, and relates to a method, system, device and storage medium for interconnecting multi-subject energy digital objects. Background Art

[0002] The Digital Object Architecture (DOA) is a logical extension of the existing Internet architecture. It supports the data interoperability requirements between different systems, rather than simply transferring information in digital form from one location on the Internet to another. The basic element in the DOA is the digital object, which is a unified abstraction of data resources in any information system. A complete digital object can be divided into three parts: identification, metadata, and entity. Among them, the identification is the unique identity tag of the digital object, and the identification does not change with the storage environment, access environment, and content of the digital object; metadata is the descriptive information related to the digital object and the application and business, such as the purpose of the digital object, the classification of the digital object, etc., to support digital object users to search for the required digital objects according to application requirements; the digital object entity is the actual content of the data resource.

[0003] Energy digital objects are aimed at the problems of high interconnection communication and coordination costs and low data access efficiency caused by heterogeneous energy data resources in the energy field, complex cross-subject access modes of energy data, and low controllability of data subject interconnection. Starting from the underlying perspective of models, architectures, and protocols, distributed and heterogeneous energy data are modeled as standardized "digital objects". The energy digital network based on digital objects forms a new type of energy digital network across subjects and heterogeneous networks by designing a unified access protocol for cross-subject digital objects, establishing access links between multi-subject energy digital objects, realizing active access and addressing access of energy digital objects, and providing platform-based and technical data circulation support capabilities; the main purpose of building an energy digital network is to solve the problems of connectability and accessibility of cross-subject and distributed energy digital objects.

[0004] In the existing technology, energy data is large in scale, widely distributed, and changes rapidly. It has the characteristics of multi-source heterogeneity and data islands. The joint search between different data is time-consuming and ineffective. Based on the encapsulation of energy digital objects, the multi-source heterogeneity problem of multi-subject energy data is solved; the construction of energy digital networks solves the data island problem between multi-subject energy data, but the encapsulation of energy digital objects makes it impossible to directly find the corresponding energy data. Although the energy digital network establishes connections between energy data, the relationships between data are complex and the links are long; therefore, based on the existing technology and without configuring and defining the logical or business relationships between different energy digital objects, it is impossible to directly obtain the interconnection relationship between energy digital objects, and it is difficult to directly support the construction of the interconnection relationship between energy digital objects; the efficiency of fast search between energy data, especially cross-subject energy data, is still low. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method, system, device and storage medium for interconnecting multi-subject energy digital objects, which can realize the interconnection and collaboration between multi-subject energy digital objects, meet the needs of fast search and integrated management, and realize on-demand sharing and high-speed access.

[0006] The present invention is achieved through the following technical solutions: The present invention provides a method for interconnecting multi-agent energy digital objects, comprising: Identify the identifiers of each subject's energy digital object and obtain a one-to-one corresponding energy digital object ontology; According to the metadata information of the energy digital object, the feature data sets of different feature categories are extracted through natural language processing; the feature category ontology of the energy digital object is constructed according to the clustering results of the feature data sets; Forming a node set according to energy digital object nodes constructed using energy digital object ontology and feature category nodes constructed using feature category ontology; Establish the interconnection relationship between energy digital object nodes according to the identification coding rules; establish the connection relationship between energy digital object nodes and feature category nodes according to similarity analysis; According to the interconnection relationship and connection relationship, a topological relationship between node sets is established to form an interconnection graph, thereby completing the interconnection of multi-agent energy digital objects.

[0007] Optionally, the identification of the energy digital object obtains a one-to-one corresponding energy digital object ontology, and specifically uses the uniqueness of the energy digital object identification to identify the energy digital object ontology to obtain the energy digital object ontology.

[0008] Optionally, according to the metadata information of the energy digital object, a feature data set of different feature categories is extracted through natural language processing; and a feature category ontology of the energy digital object is constructed according to the clustering result of the feature data set; specifically, Extract metadata information of energy digital objects; Based on natural language processing methods, feature information in metadata is identified, segmented and aligned, and corresponding feature data sets are formed according to feature categories; Clustering the feature data set to obtain a clustering result set; According to the feature categories and preset coding rules, the clustering result set is coded and identified with the feature categories, and the feature category coding identification and attribute information are associated to form a feature category ontology.

[0009] Optionally, the energy digital object nodes constructed using the energy digital object ontology and the feature category nodes constructed using the feature category ontology form a node set; specifically including: The feature category node includes a coding identifier, a feature category and a feature category name obtained from the feature category ontology; The energy digital object node includes an energy digital object identifier, an energy digital object and a name of the energy digital object obtained from the energy digital object ontology; The node set includes all energy digital object nodes and feature category nodes.

[0010] Optionally, the interconnection relationship between energy digital object nodes is established according to the identification coding rules; specifically including: Extract the minimum subdivision subject name and minimum subdivision subject code of the energy digital object according to the energy digital object identifier and metadata information; Energy digital objects with equal minimum subdivision subject codes have a bidirectional interconnection relationship, and the attributes of the bidirectional interconnection relationship are the minimum subdivision subjects with the same name corresponding to the equal minimum subdivision subject code.

[0011] Optionally, the connection relationship between the energy digital object node and the feature category node is established based on the similarity analysis; specifically, Extracting metadata of energy digital objects and semantic information of feature categories, and obtaining semantics of energy digital objects and semantics of feature categories respectively; Calculating the cosine similarity between the semantics of the energy digital object and the semantics of the feature category; There is a unidirectional connection relationship between the energy digital object node whose cosine similarity is greater than or equal to a preset threshold and the feature category node, and the attribute of the unidirectional connection relationship is that the energy digital object node belongs to the feature category node.

[0012] Another aspect of the present invention provides an interconnection system of multi-agent energy digital objects, comprising: The energy digital object identification module is used to identify the identifiers of each subject energy digital object and obtain the energy digital object entities one by one; The feature extraction module of the energy digital object is used to extract feature data sets of different feature categories through natural language processing according to the metadata information of the energy digital object; and to construct the feature category entity of the energy digital object according to the clustering result of the feature data set; A node generation module, used to form a node set according to energy digital object nodes constructed using energy digital object entities and feature category nodes constructed using feature category entities; A relationship establishment module is used to establish interconnection relationships between energy digital object nodes according to identification coding rules; and to establish connection relationships between energy digital object nodes and feature category nodes according to similarity analysis; The relationship interconnection module is used to establish the topological relationship between the node sets according to the interconnection relationship and connection relationship to form an interconnection graph and complete the interconnection of multi-subject energy digital objects.

[0013] Optionally, the feature extraction module of the energy digital object is further used to: Extract metadata information of energy digital objects; Based on natural language processing methods, feature information in metadata is identified, segmented and aligned, and corresponding feature data sets are formed according to feature categories; Clustering the feature data set to obtain a clustering result set; According to the feature categories and preset coding rules, the clustering result set is coded and identified with the feature categories, and the feature category coding identification and attribute information are associated to form a feature category ontology.

[0014] Optionally, the relationship building module is further used to: Extract the minimum subdivision subject name and minimum subdivision subject code of the energy digital object according to the energy digital object identifier and metadata information; Energy digital objects with equal minimum subdivision subject codes have a bidirectional interconnection relationship, and the attributes of the bidirectional interconnection relationship are the minimum subdivision subjects with the same name corresponding to the equal minimum subdivision subject code.

[0015] Optionally, the relationship building module is further used to: Extracting metadata of energy digital objects and semantic information of feature categories, and obtaining semantics of energy digital objects and semantics of feature categories respectively; Calculating the cosine similarity between the semantics of the energy digital object and the semantics of the feature category; There is a unidirectional connection relationship between the energy digital object node whose cosine similarity is greater than or equal to a preset threshold and the feature category node, and the attribute of the unidirectional connection relationship is that the energy digital object node belongs to the feature category node.

[0016] Another aspect of the present invention provides a computer device, comprising: Memory for storing computer programs; A processor is used to implement the method for interconnecting multi-agent energy digital objects as described in any one of the above when executing the computer program.

[0017] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for interconnecting multi-agent energy digital objects as described in any one of the above items is implemented.

[0018] Another aspect of the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for interconnecting multi-agent energy digital objects as described in any one of the above.

[0019] Compared with the prior art, the present invention has the following beneficial technical effects: The method for interconnecting multi-subject energy digital objects described in the present invention adds characteristic category nodes of energy digital objects obtained by extracting and clustering through natural language processing on the basis of energy digital object bodies as nodes, thereby refining the node types and quantities of multi-subject energy digital objects, and being able to obtain original data in the nodes, shortening the data link after cross-domain data association; then, by establishing an interconnection relationship between object nodes and a link relationship between object nodes and characteristic category nodes, a topological relationship between nodes is formed, and an interconnection graph is obtained to characterize the multi-subject energy digital objects and the interconnection; by introducing and associating characteristic relationships extracted by natural language processing in the interconnection graph, the efficiency of rapid search between cross-subject energy data is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings: Figure 1 The present invention is a flowchart of a method for interconnecting multi-agent energy digital objects described in an example of the present invention.

[0021] Figure 2 Schematic diagram of the process of feature extraction method described in an example of the present invention.

[0022] Figure 3A structural block diagram of an interconnected system of multi-agent energy digital objects described in an example of the present invention.

[0023] Figure 4 A schematic diagram of the process of constructing an interconnected graph of multi-subject energy data objects described in an example of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0025] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.

[0026] The present invention provides a method for interconnecting multiple energy digital objects, such as Figure 1 As shown, it includes, S1. Identify the identifiers of each subject energy digital object and obtain a one-to-one corresponding energy digital object ontology; Among them, a digital object is divided into three parts: identification, metadata, and data entity (data source). The identification is the identity ID of the digital object, which uniquely and persistently identifies each digital object; metadata is the descriptive information of the data, which is used to discover and search for digital objects; and the data entity (data source) represents the original data. Therefore, the identification of the digital object corresponds to the digital object ontology one by one, and can be directly obtained through identification. In the field of energy digitalization, the energy digital object ontology can also be obtained through identification of the identification.

[0027] S2. Extracting feature data sets of different feature categories through natural language processing based on metadata information of energy digital objects; constructing feature category ontology of energy digital objects based on clustering results of feature data sets; Among them, metadata is the descriptive information of energy data, which is used to discover and search digital objects. It contains the data characteristics of energy data, such as descriptions of business, ownership, regional distribution and other information. Therefore, feature information is extracted from metadata based on natural language processing (NLP) methods. The extraction can include operations such as recognition, segmentation and alignment, so that feature information can be classified and aggregated according to different feature categories to form feature data sets; further clustering of feature data sets is performed, and finally the feature category ontology is constructed according to the clustering results. In this way, data merging and association of different descriptions of the same data and data in different regional scenarios can be achieved.

[0028] S3, forming a node set according to the energy digital object nodes constructed using the energy digital object ontology and the feature category nodes constructed using the feature category ontology; Among them, the formed node set includes the energy digital object itself, that is, the node in the existing energy digital network, and the characteristic category node of the energy digital object is added as a supplement. The two together communicate the nodes to be interconnected in the scheme of the present invention. Not only the energy digital objects are connected, but also the characteristic types describing the energy data can be used for direct connection, which increases the number of nodes and interconnection relationships in the energy data network and improves the efficiency of retrieval, search and output.

[0029] S4. Establishing interconnection relationships between energy digital object nodes according to identification coding rules; establishing connection relationships between energy digital object nodes and feature category nodes according to similarity analysis; Among them, the establishment of the interconnection relationship between energy digital object nodes is a two-way connection relationship, and the connection relationship between energy digital object nodes and feature category nodes is to classify and establish relationships for energy digital objects based on feature categories, thereby forming an edge relationship in graph computing.

[0030] S5. According to the interconnection relationship and connection relationship, a topological relationship between node sets is established to form an interconnection graph, thereby completing the interconnection of multi-agent energy digital objects.

[0031] Among them, based on the nodes and edges formed in the above steps, the energy digital objects of multiple subjects can be associated and expanded with each other at the object ontology and feature category ontology levels to form an interconnected graph, thereby completing the interconnection of the energy digital objects of multiple subjects.

[0032] Energy data has diverse business characteristics, ownership characteristics, regional distribution characteristics, etc. Therefore, the relationship between multi-subject energy data can be obtained based on the similarity of energy data in terms of business, ownership, regional distribution, etc. Energy digital objects are created based on energy data and inherit the relevant characteristics of energy data. Therefore, the relationship between energy digital objects can be characterized by the similarity of energy digital objects in terms of business, ownership, regional distribution, etc. The calculation results of the correlation between energy digital objects and the analysis results of the subordinate relationship between energy digital objects and feature categories are evaluated as the basis for the interconnection of energy digital objects, providing a basis for the generation of multi-subject energy digital object interconnection maps.

[0033] On this basis, by analyzing the correlation between energy digital objects, a multi-subject energy digital object interconnection map is constructed to achieve interconnection, collaboration, rapid search and integrated management of large-scale energy data, meet the needs of on-demand sharing and efficient access of multi-subject energy data, support subsequent rapid data discovery and intelligent data recommendation, promote the circulation of energy data elements, and promote the release of energy data value.

[0034] In an example provided by the present invention, the uniqueness of the energy digital object identifier is used to identify the energy digital object ontology to obtain the energy digital object ontology.

[0035] In an example provided by the present invention, according to the metadata information of the energy digital object, a feature data set of different feature categories is extracted through natural language processing; a feature category ontology of the energy digital object is constructed according to the clustering result of the feature data set; specifically, Extract metadata information of energy digital objects; Based on natural language processing methods, feature information in metadata is identified, segmented and aligned, and corresponding feature data sets are formed according to feature categories; Clustering the feature data set to obtain a clustering result set; in this preferred embodiment, the BIRCH algorithm is used to cluster the feature data set to obtain a clustering result set; According to the feature category and the preset coding rules, the clustering result set is coded and identified by the feature category, and the feature category coding identification is associated with the attribute information to form a feature category ontology. When performing a specific association in this preferred embodiment, the feature category is coded and identified in the form of "business feature name abbreviation-clustering result serial number", and the ownership characteristics and regional distribution characteristics are associated with the feature category coding identification as attribute information.

[0036] like Figure 2 As shown, for multi-subject energy digital objects such as electricity consumption data, carbon emission data and energy consumption data, after being processed by natural language processing methods, the ownership of the corresponding feature information is obtained, which are Company A, Factory A and Enterprise A, corresponding to different respective identifiers and entities. Through feature recognition and alignment, they are unified into Company A. Since the feature parts are relatively consistent in this extraction process, there is no segmentation operation.

[0037] In an example provided by the present invention, the energy digital object nodes constructed using the energy digital object ontology and the feature category nodes constructed using the feature category ontology form a node set; specifically including: The feature category node includes a coding identifier, a feature category and a feature category name obtained from the feature category ontology; The energy digital object node includes an energy digital object identifier, an energy digital object and a name of the energy digital object obtained from the energy digital object ontology; The node set includes all energy digital object nodes and feature category nodes.

[0038] The final node set V It can be identified as follows.

[0039]

[0040] in: Represents an energy digital object node, Represents a feature category node, Respectively represent the number of energy digital object nodes and feature category nodes.

[0041] In an example provided by the present invention, the interconnection relationship between energy digital object nodes is established according to the identification coding rules; specifically, Extract the minimum subdivision subject name and minimum subdivision subject code of the energy digital object according to the energy digital object identifier and metadata information; Energy digital objects with equal minimum subdivision subject codes have a bidirectional interconnection relationship, and the attributes of the bidirectional interconnection relationship are the minimum subdivision subjects with the same name corresponding to the equal minimum subdivision subject code.

[0042] In this preferred embodiment, the energy digital object identifier is encoded in the form of multi-level prefix + arbitrary suffix, and the encoding format is: 1-level prefix. 2-level prefix... k-level prefix / suffix. The multi-level prefix corresponds to multi-level fields or subject domains, where the last-level prefix is ​​the smallest subdivision subject. Combined with the metadata information of the energy digital object, the smallest subdivision subject name and code of the energy digital object are extracted, and the discrimination rule of the smallest subdivision subject of the energy digital object is established: If the smallest subdivision subject codes of two energy digital objects are equal, then there is a bidirectional interconnection relationship between the two energy digital objects, and the attribute of the interconnection relationship is that they belong to the same smallest subdivision subject.

[0043] In an example provided by the present invention, the connection relationship between the energy digital object node and the feature category node is established based on the similarity analysis; specifically, Extracting metadata of energy digital objects and semantic information of feature categories, and obtaining semantics of energy digital objects and semantics of feature categories respectively; Calculating the cosine similarity between the semantics of the energy digital object and the semantics of the feature category; There is a unidirectional connection relationship between the energy digital object node whose cosine similarity is greater than or equal to a preset threshold and the feature category node, and the attribute of the unidirectional connection relationship is that the energy digital object node belongs to the feature category node.

[0044] The preset threshold value of the present invention is set based on manual experience.

[0045] This method analyzes the association between energy digital objects based on the metadata information of energy digital objects, and realizes the generation of an interconnected graph of energy digital objects for multiple subjects. The interconnected graph of energy digital objects represents the interconnected relationships between energy digital objects, and realizes the interconnected collaboration, rapid search and integrated management of large-scale energy data, meeting the needs of on-demand sharing and efficient access to energy data of multiple subjects, supporting subsequent rapid data discovery and intelligent data recommendation, promoting the circulation of energy data elements, and promoting the release of energy data value.

[0046] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.

[0049] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0050] In the present invention, "module", "device", "system" and the like refer to related entities applied to computers, such as hardware, a combination of hardware and software, software or software in execution, etc. In detail, for example, an element can be, but is not limited to, a process, a processor, an object, an executable element, an execution thread, a program and / or a computer running on a processor. In addition, an application or script program running on a server, a server can all be an element. One or more elements can be in an execution process and / or thread, and an element can be localized on a computer and / or distributed between two or more computers, and can be operated by various computer-readable media. An element can also communicate through local and / or remote processes according to a signal with one or more data packets, for example, a signal from a data that interacts with another element in a local system, a distributed system, and / or a network on the Internet through a signal to interact with other systems.

[0051] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include" and "comprise" include not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such processes, methods, articles or equipment. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or equipment that includes the elements.

[0052] like Figure 3 As shown, the present invention also provides an interconnection system of multi-agent energy digital objects, including: The energy digital object identification module 301 is used to identify the identifiers of each subject energy digital object and obtain the energy digital object entities one by one; The energy digital object feature extraction module 302 is used to extract feature data sets of different feature categories through natural language processing according to the metadata information of the energy digital object; and construct feature category entities of the energy digital object according to the clustering results of the feature data sets; A node generation module 303, used to form a node set according to energy digital object nodes constructed using energy digital object entities and feature category nodes constructed using feature category entities; The relationship establishment module 304 is used to establish the interconnection relationship between energy digital object nodes according to the identification coding rules; establish the connection relationship between energy digital object nodes and feature category nodes according to similarity analysis; The relationship interconnection module 305 is used to establish a topological relationship between node sets to form an interconnection graph based on the interconnection relationship and connection relationship, and complete the interconnection of multi-agent energy digital objects.

[0053] Corresponding to the above-mentioned system and method, in one embodiment of the present invention, the feature extraction module 302 of the energy digital object is further used to: Extract metadata information of energy digital objects; Based on natural language processing methods, feature information in metadata is identified, segmented and aligned, and corresponding feature data sets are formed according to feature categories; Clustering the feature data set to obtain a clustering result set; According to the feature categories and preset coding rules, the clustering result set is coded and identified with the feature categories, and the feature category coding identification and attribute information are associated to form a feature category ontology.

[0054] In this preferred example, the data processing performed by the feature extraction module 302 of the energy digital object can be performed by the module itself as a whole, or can be performed separately by the corresponding extraction unit, natural language processing unit, clustering unit and association unit.

[0055] Corresponding to the above-mentioned system and method, in one embodiment of the present invention, the relationship establishment module 304 is further used to: Extract the minimum subdivision subject name and minimum subdivision subject code of the energy digital object according to the energy digital object identifier and metadata information; Energy digital objects with equal minimum subdivision subject codes have a bidirectional interconnection relationship, and the attributes of the bidirectional interconnection relationship are the minimum subdivision subjects with the same name corresponding to the equal minimum subdivision subject code.

[0056] In this preferred example, the data processing performed by the relationship establishment module 304 can be performed by the module itself as a whole, or can be performed by the corresponding subject extraction unit and the bidirectional interconnection unit respectively.

[0057] Corresponding to the above-mentioned system and method, in one embodiment of the present invention, the relationship establishment module 304 is further used to: Extracting metadata of energy digital objects and semantic information of feature categories, and obtaining semantics of energy digital objects and semantics of feature categories respectively; Calculating the cosine similarity between the semantics of the energy digital object and the semantics of the feature category; There is a unidirectional connection relationship between the energy digital object node whose cosine similarity is greater than or equal to a preset threshold and the feature category node, and the attribute of the unidirectional connection relationship is that the energy digital object node belongs to the feature category node.

[0058] In this preferred example, the data processing performed by the relationship establishment module 304 can be performed by the module itself as a whole, or can be performed separately by the semantic extraction unit, the similarity calculation unit and the unidirectional connection unit.

[0059] An embodiment of the present invention further provides a computer device, including: Memory for storing computer programs; A processor is used to implement the method for interconnecting multi-agent energy digital objects as described in any one of the examples of the present invention when executing the computer program.

[0060] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for interconnecting multi-agent energy digital objects as described in any one of the examples of the present invention is implemented.

[0061] An embodiment of the present invention further provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the steps of the method for interconnecting multi-agent energy digital objects as described in any one of the examples of the present invention are implemented.

[0062] The multi-agent energy digital object interconnection graph is based on graph computing technology, using machine learning and natural language processing methods to realize the interconnection of digital objects by identifying the semantic relationship between digital objects, and then construct a comprehensive network view of nodes, edges and attribute labels, in which energy digital objects and their feature classification categories are used as nodes, the interconnection relationship between energy digital objects and the subordinate relationship between energy digital objects and feature categories are used as edges, and the attached information of nodes and edges is mounted on nodes or edges as attribute labels. Finally, based on the graph database, the multi-agent energy digital object interconnection graph is stored and visualized.

[0063] In one embodiment of the present invention, combined with the above-mentioned management and display of the interconnection map, a specific example of the interconnection method of multi-agent energy digital objects is provided from the perspective of interconnection map construction and application, such as Figure 4 As shown, it can be applied to the establishment of distribution network and distributed new energy data maps to achieve the interconnection of corresponding energy digital objects.

[0064] (1) Generation of nodes in the multi-agent energy digital object interconnection graph The nodes of the multi-agent energy digital object interconnection graph include energy digital object nodes and feature category nodes. The energy digital object nodes are identified and defined based on the energy digital object identifiers, and the feature category nodes obtain and define feature categories by clustering the features of energy digital objects.

[0065] First, the energy digital object ontology is constructed. The energy digital object identifier does not change with the changes in the storage environment, access environment, and content of the digital object. The uniqueness of the identifier is used to identify the energy digital object ontology, and the energy digital object is directly converted into the energy digital object ontology.

[0066] Secondly, we construct the feature category ontology of energy digital objects. We extract metadata information of energy digital objects, identify, segment and align feature information based on natural language processing (NLP) methods, and form different feature data sets according to business, ownership, regional distribution, etc. .

[0067]

[0068] Among them, do represents the energy digital object identifier, biz represents the business characteristics of the energy digital object, own represents the ownership characteristics of the energy digital object, region represents the regional distribution characteristics of the energy digital object, and t represents the number of energy digital objects.

[0069] Use the BIRCH algorithm to cluster the feature data set to form a clustering result set .

[0070]

[0071] Among them, id is the clustering result serial number, The name of the business feature of the clustering result, which comes from the data set In the biz, is the number of clustering results, indicating The t features in can be divided into k categories.

[0072] According to the clustering results, the feature category is coded and identified in the form of "business feature name abbreviation-clustering result serial number". Ownership characteristics and regional distribution characteristics are associated with the feature category coding identification as attribute information, and the feature category ontology is formed on this basis.

[0073] Finally, the nodes of the energy digital object interconnection graph are defined based on the energy digital object ontology and feature category ontology.

[0074] Define 1 node:

[0075] Where id represents the energy digital object identifier or the coding identifier of the energy digital object feature category. Represents energy digital objects or the business, ownership, regional distribution and other characteristic categories of energy digital objects. Indicates the name of an energy digital object or the name of a characteristic category of an energy digital object.

[0076] Using the node definition, nodes are generated for the energy digital object ontology and feature category ontology to form a node set:

[0077] Represents an energy digital object node, Represents a feature category node, Respectively represent the number of energy digital object nodes and feature category nodes.

[0078] (2) Generation of edge graphs of multi-agent energy digital objects The edges of the multi-agent energy digital object interconnection graph represent the connection relationship between energy digital object nodes and the connection relationship between energy digital object nodes and feature category nodes.

[0079] First, the interconnection relationship between energy digital objects is extracted based on the rules. The energy digital object identifier is encoded in the form of multi-level prefix + arbitrary suffix, and the encoding format is: 1-level prefix. 2-level prefix... k-level prefix / suffix. The multi-level prefix corresponds to multi-level fields or subject domains, where the last-level prefix is ​​the smallest subdivision of the subject. Combined with the metadata information of the energy digital object, the smallest subdivision subject name of the energy digital object is extracted ( ) and encoding ( ), establish the discrimination rules of the smallest subdivision subject of energy digital objects: if

[0080] Then the energy digital object and There is a two-way interconnection relationship, and the attributes of the interconnection relationship are that they belong to the same minimum subdivision topic ( ).

[0081] Secondly, the connection relationship between the energy digital object node and the feature category node is established. The semantic information of the energy digital object metadata is extracted, and the cosine similarity between the energy digital object semantics and the feature category semantics is calculated. If the cosine similarity is greater than or equal to the specified threshold, it is determined that there is a unidirectional connection relationship between the energy digital object node and the feature category node, and the attribute of the connection relationship is that the energy digital object node belongs to the feature category node; the threshold is set based on artificial experience.

[0082] Finally, based on the interconnection relationship between energy digital objects and the connection relationship between energy digital object nodes and feature category nodes, the edges of the energy digital object interconnection graph are defined.

[0083] Define 2 edges:

[0084] in, , is the node of the energy digital object interconnection graph, that is, the node in Definition 1, represents the starting node of the edge, represents the end node of the edge, It is the attribute of the edge of the energy digital object interconnection graph, indicating the interconnection relationship between energy digital objects or the connection relationship between energy digital object nodes and feature category nodes.

[0085] Using edge definitions, edges are generated based on the interconnection relationship between energy digital objects and the connection relationship between energy digital object nodes and feature category nodes to form an edge set:

[0086] Among them, e represents the edge generated based on the interconnection relationship between energy digital objects or the connection relationship between energy digital object nodes and feature category nodes, and p is the number of edges.

[0087] (3) Generation of a multi-agent energy digital object interconnection graph Based on the node set and edge set of the energy digital object interconnection graph, define and construct the energy digital object interconnection graph.

[0088] Definition 3: Internet Graph:

[0089] Among them, V represents the node set of the energy digital object interconnection graph, E represents the edge set of the energy digital object interconnection graph, Represents the version of the energy digital object interconnection graph:

[0090] in, Indicates the version number. Indicates the version name, Indicates the date the version was created. Indicates the description of the version.

[0091] (4) Storage, retrieval and update of multi-agent energy digital object interconnected graph According to the characteristics of the multi-agent energy digital object interconnection graph, a multi-agent energy digital object interconnection graph storage module is constructed, and the graph is stored in the graph database in the native graph storage method. The storage module provides node storage interface, edge storage interface, data file import interface, etc.

[0092] In response to the query and retrieval needs of the multi-agent energy digital object interconnected graph, a multi-agent energy digital object interconnected graph retrieval module was constructed, which provided node retrieval interface, edge retrieval interface, etc.

[0093] In view of the changes in the interconnected graph of multi-agent energy digital objects caused by changes in multi-agent energy digital objects, a multi-agent energy digital object interconnected graph update module is constructed, which provides node update interface, edge update interface and attribute update interface, etc.

[0094] Based on container (Docker) technology, the above modules are encapsulated into containers to realize on-demand generation and calling of storage, retrieval and update services, improve resource utilization efficiency and save service costs.

[0095] (5) Visualization of multi-agent energy digital object interconnection graph Based on Vue.js, a multi-agent energy digital object interconnection map visualization module is built to provide services such as panoramic display of multi-agent energy digital object interconnection maps, thematic data interconnection map display, and hot digital object display.

[0096] Based on the method, the present invention can also construct modules such as storage, retrieval, update and visualization of the multi-subject energy digital object interconnected map, thereby providing unified management services and diversified display capabilities for the multi-subject energy digital object interconnected map.

[0097] In one embodiment of the present invention, the method of the present invention is put into practical application to realize the interconnection, fusion and sharing of multi-subject energy digital objects and the cross-domain interconnection of energy data. The interconnection, fusion and sharing of energy consumption data of an industrial park is used as an example for explanation.

[0098] As the core unit of industrial agglomeration development, industrial parks have become one of the key scenarios for industrial green development and energy low-carbon transformation. Therefore, carbon emission reduction in industrial parks is crucial. The primary issue is to verify and evaluate the carbon emission sources in industrial parks, based on the energy consumption data of industrial parks. Industrial parks have the characteristics of a large number of enterprises, dispersed industries, and diversified energy use. Therefore, it is necessary to integrate all relevant energy consumption data to obtain the full amount of energy consumption information of industrial parks, and support the subsequent verification and evaluation analysis of carbon emission sources in industrial parks.

[0099] In the existing technology, energy data of industrial parks in different fields, that is, multi-subject energy digital objects such as electricity data, oil data, coal data, etc., are obtained, the fields of the data are read and analyzed, the fields of data in different fields are manually associated, and associated data tables are established to achieve data penetration and integration. The energy data sharing method is the sharing of all energy data; the main problems are that direct access to source data is required, and there are great security risks such as data tampering and data loss; manual intervention is required, and with the growth of the energy field and data scale, the manpower and time costs increase significantly; data sharing is the sharing of all data, the search speed is slow, and the sharing efficiency is low.

[0100] Using the method described in the present invention, the main process of specific application is as follows: 1) Collect data from energy enterprises involved in the industrial park and build energy digital objects of different granularities based on their own data; 2) Establishing the interconnection of multi-subject energy digital objects using the method of the present invention, thereby obtaining an interconnection graph of energy digital objects involving multiple energy enterprise entities generated during the interconnection; 3) Based on the energy digital object interconnection graph generated in step 2), using "industrial park name" as the search condition, all relevant energy digital object nodes and edges between energy digital object nodes are obtained according to the interconnection relationship between energy digital object nodes; 4) Based on the energy digital object nodes obtained in step 3), search for energy digital object nodes with node attributes related to "electricity consumption, oil consumption, and coal consumption", and on this basis, search and obtain several edges with the attribute of "belonging to the same park enterprise" according to the connection relationship between the energy digital object nodes and the characteristic category nodes, and then obtain all energy digital object nodes connected to these edges; 5) Based on the edges and energy digital object nodes obtained in step 4), an energy digital object association table is created on the basis of the interconnection graph of energy digital objects to connect and integrate energy digital objects; 6) Users retrieve the energy digital objects of the required data objects through the energy digital object interconnection graph, and then obtain data based on the source data attributes of the energy digital objects to achieve multi-granularity data sharing on demand.

[0101] Through the method described in the present invention, the interconnection of multi-subject energy digital objects can be established, so that the sharing and rapid search of multi-subject data in the industrial park can be realized, which greatly reduces the risk of data tampering and loss, and greatly reduces the manpower and time costs.

[0102] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] 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. Any modification or equivalent replacement that does 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 method for interconnecting multi-agent energy digital objects, characterized in that: include, Identify the identifiers of each subject's energy digital object and obtain a one-to-one corresponding energy digital object ontology; According to the metadata information of the energy digital object, feature data sets of different feature categories are extracted through natural language processing; Constructing the feature category ontology of energy digital objects based on the clustering results of the feature data set; Forming a node set according to energy digital object nodes constructed using energy digital object ontology and feature category nodes constructed using feature category ontology; Establish the interconnection relationship between energy digital object nodes according to the identification coding rules; establish the connection relationship between energy digital object nodes and feature category nodes according to similarity analysis; According to the interconnection relationship and connection relationship, a topological relationship between node sets is established to form an interconnection graph, thereby completing the interconnection of multi-agent energy digital objects.

2. A method for interconnecting multi-agent energy digital objects according to claim 1, characterized in that: The identification of the energy digital object is used to obtain a one-to-one corresponding energy digital object ontology. Specifically, the uniqueness of the energy digital object identification is used to identify the energy digital object ontology to obtain the energy digital object ontology.

3. A method for interconnecting multi-agent energy digital objects according to claim 1, characterized in that: According to the metadata information of the energy digital object, feature data sets of different feature categories are extracted through natural language processing; Constructing the feature category ontology of energy digital objects based on the clustering results of the feature data set; Specifically include: Extract metadata information of energy digital objects; Based on natural language processing methods, feature information in metadata is identified, segmented and aligned, and corresponding feature data sets are formed according to feature categories; Clustering the feature data set to obtain a clustering result set; According to the feature categories and preset coding rules, the clustering result set is coded and identified with the feature categories, and the feature category coding identification and attribute information are associated to form a feature category ontology.

4. A method for interconnecting multi-agent energy digital objects according to any one of claims 1 to 3, characterized in that: The energy digital object nodes constructed by using the energy digital object ontology and the feature category nodes constructed by using the feature category ontology form a node set; specifically, The feature category node includes a coding identifier, a feature category and a feature category name obtained from the feature category ontology; The energy digital object node includes an energy digital object identifier, an energy digital object and a name of the energy digital object obtained from the energy digital object ontology; The node set includes all energy digital object nodes and feature category nodes.

5. The method for interconnecting multi-agent energy digital objects according to claim 1, characterized in that: The interconnection relationship between energy digital object nodes is established according to the identification coding rules; specifically, Extract the minimum subdivision subject name and minimum subdivision subject code of the energy digital object according to the energy digital object identifier and metadata information; Energy digital objects with equal minimum subdivision subject codes have a bidirectional interconnection relationship, and the attributes of the bidirectional interconnection relationship are the minimum subdivision subjects with the same name corresponding to the equal minimum subdivision subject code.

6. A method for interconnecting multi-agent energy digital objects according to claim 1, characterized in that: The connection relationship between the energy digital object node and the feature category node is established based on the similarity analysis; specifically, Extracting metadata of energy digital objects and semantic information of feature categories, and obtaining semantics of energy digital objects and semantics of feature categories respectively; Calculating the cosine similarity between the semantics of the energy digital object and the semantics of the feature category; There is a unidirectional connection relationship between the energy digital object node whose cosine similarity is greater than or equal to a preset threshold and the feature category node, and the attribute of the unidirectional connection relationship is that the energy digital object node belongs to the feature category node.

7. An interconnected system of multi-agent energy digital objects, characterized in that: include, The energy digital object identification module is used to identify the identifiers of each subject energy digital object and obtain the energy digital object entities one by one; The feature extraction module of the energy digital object is used to extract feature data sets of different feature categories through natural language processing based on the metadata information of the energy digital object; Constructing characteristic category entities of energy digital objects based on clustering results of characteristic data sets; A node generation module, used to form a node set according to energy digital object nodes constructed using energy digital object entities and feature category nodes constructed using feature category entities; A relationship establishment module is used to establish interconnection relationships between energy digital object nodes according to identification coding rules; and to establish connection relationships between energy digital object nodes and feature category nodes according to similarity analysis; The relationship interconnection module is used to establish the topological relationship between the node sets according to the interconnection relationship and connection relationship to form an interconnection graph and complete the interconnection of multi-subject energy digital objects.

8. The interconnection system of multi-agent energy digital objects according to claim 7 is characterized in that: The feature extraction module of the energy digital object is also used to: Extract metadata information of energy digital objects; Based on natural language processing methods, feature information in metadata is identified, segmented and aligned, and corresponding feature data sets are formed according to feature categories; Clustering the feature data set to obtain a clustering result set; According to the feature categories and preset coding rules, the clustering result set is coded and identified with the feature categories, and the feature category coding identification and attribute information are associated to form a feature category ontology.

9. The interconnection system of multi-agent energy digital objects according to claim 7, characterized in that: The relationship building module is also used to: Extract the minimum subdivision subject name and minimum subdivision subject code of the energy digital object according to the energy digital object identifier and metadata information; Energy digital objects with equal minimum subdivision subject codes have a bidirectional interconnection relationship, and the attributes of the bidirectional interconnection relationship are the minimum subdivision subjects with the same name corresponding to the equal minimum subdivision subject code.

10. The interconnection system of multi-agent energy digital objects according to claim 7, characterized in that: The relationship building module is also used to: Extracting metadata of energy digital objects and semantic information of feature categories, and obtaining semantics of energy digital objects and semantics of feature categories respectively; Calculating the cosine similarity between the semantics of the energy digital object and the semantics of the feature category; There is a unidirectional connection relationship between the energy digital object node whose cosine similarity is greater than or equal to a preset threshold and the feature category node, and the attribute of the unidirectional connection relationship is that the energy digital object node belongs to the feature category node.

11. A computer device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the method for interconnecting multi-agent energy digital objects as described in any one of claims 1 to 6 when executing the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for interconnecting multi-agent energy digital objects according to any one of claims 1 to 6 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for interconnecting multi-agent energy digital objects described in any one of claims 1 to 6 are implemented.

Images