Method and device for determining mapping relation between power distribution and utilization public information model and building management system, equipment, medium and product

Abstract

The invention relates to a method and device for determining a mapping relation between a power distribution and utilization public information model and a building management system, equipment, a medium and a product. Analyzing a description file of a power distribution and utilization common information model (CIM) to obtain a first information model ontology in an ontology format, analyzing a description file of a building management system (BMS) to obtain a second information model ontology in the ontology format, and determining language similarity between each first node in the first information model ontology and each second node in the second information model ontology, determining language similarities greater than or equal to a language similarity threshold in the language similarities corresponding to the first nodes as target language similarities, determining first candidate node pairs having a mapping relationship between second nodes corresponding to the target language similarities and the first nodes, and determining structural similarities between the first nodes and the second nodes, and on the basis of the structural similarity corresponding to each first node and the first candidate node pair, the corresponding target node pair with the mapping relationship is determined, so that the mapping accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of heterogeneous model mapping technology, and in particular to a method, apparatus, equipment, medium and product for determining the mapping relationship between a power distribution public information model and a building management system. Background Technology

[0002] Building automation emerged with the development of building environmental equipment, especially heating, ventilation, air conditioning, and refrigeration (HVAC&R) systems. In recent years, with the rapid development of China's national economy and science and technology, particularly the rapid advancement of IT technologies such as electronics, computers, and automation, building automation technology has experienced unprecedented and rapid development in both its scientific and technological aspects and its applications.

[0003] In traditional smart buildings, building automation systems were typically separate from IT systems. However, with the increasing popularity of enterprise-wide management and the development of open systems technology and the Internet, simple facility management will inevitably be integrated into enterprise management. Automation systems using proprietary communication protocols will be replaced by those using open communication protocols, achieving full interoperability across the entire building automation system. The Internet will become the enterprise-level infrastructure. These trends will inevitably lead to building automation systems being built upon the infrastructure of enterprise management systems, forming networked building systems (NBS), truly becoming a subsystem of the enterprise-level information system.

[0004] The Common Information Model (CIM) was created by ERPI to reduce the complexity of adding new applications to existing systems and improve cost-effectiveness. The CIM model models objects within a power system, with all objects categorized into different packages based on their target business category. Each package consists of several classes. A class is an abstraction of the fundamental characteristics of an object. Each class can have multiple attributes representing the common traits of that class. Logical relationships between classes include association, aggregation, and inheritance, while dependencies between packages are represented through hierarchical nesting. The CIM model is described using the Universal Modeling Language (UML), and application scenarios are visualized using diagrams. In practice, a subset of the model is typically extracted based on actual needs to make the model more relevant. CIM includes subsets such as transformer models, auxiliary equipment models, naming models, and diagram layout models. A building management system (BMS) integrates building automation control systems (BAS), fire alarm and fire-fighting linkage systems (FAS), comprehensive security systems (SAS), public address systems (PAS), parking management systems (CPMS), and other systems directly related to a building. This achieves information sharing and integrated collaborative work among the systems, and has a rapid response linkage function to deal with emergencies.

[0005] To achieve efficient management of BMS systems in public buildings, it is essential to be able to identify the data in the BMS system model. However, due to the large volume of data exchanged in the power distribution network and the variability of the exchange information, manually matching and mapping heterogeneous model data to identify the BMS system model data is time-consuming, labor-intensive, and inaccurate. Summary of the Invention

[0006] Therefore, it is necessary to provide a method, apparatus, equipment, medium, and product for determining the mapping relationship between the power distribution public information model and the building management system, which can reduce time and cost and improve accuracy, in order to address the above-mentioned technical problems.

[0007] Firstly, this application provides a method for determining the mapping relationship between a power distribution public information model and a building management system, including:

[0008] The description file of the Public Information Model for Power Distribution (CIM) is parsed to obtain the first information model ontology in ontology format, and the description file of the Building Management System (BMS) is parsed to obtain the second information model ontology in ontology format.

[0009] For each first node in the first information model ontology, determine the language similarity between the first node and each second node in the second information model ontology;

[0010] The language similarity values ​​of the first node that are greater than or equal to the language similarity threshold are determined as the target language similarity values, and the second node and the first node corresponding to the target language similarity are determined as the first candidate node pair with a mapping relationship;

[0011] For each first node, determine the structural similarity between the first node and each second node;

[0012] Based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, the target node pair with the mapping relationship corresponding to each first node is determined.

[0013] In one embodiment, determining the language similarity between the first node and each second node in the second information model ontology includes:

[0014] For each second node, determine the first similarity between the node name of the first node and the node name of the second node;

[0015] Determine the second similarity between the node labels of the first node and the node labels of the second node;

[0016] Determine the third similarity between the node annotations of the first node and the node annotations of the second node;

[0017] Based on the first similarity, second similarity, and third similarity corresponding to the second node, the linguistic similarity between the first node and the second node is determined.

[0018] In one embodiment, the language similarity between the first node and the second node is determined based on the first similarity, the second similarity, and the third similarity corresponding to the second node, including:

[0019] Determine the first product of the first similarity and the corresponding first weight, the second product of the second similarity and the corresponding second weight, and the third product of the third similarity and the corresponding third weight;

[0020] The linguistic similarity between the first node and the second node is determined by the sum of the first product, the second product, and the third product.

[0021] In one embodiment, based on the structural similarity corresponding to each first node and the first candidate node pair corresponding to each first node, the target node pair with a mapping relationship corresponding to each first node is determined, including:

[0022] For each first node, the structural similarity of the first node that is greater than the preset structural similarity threshold is determined as the target structural similarity, and the second node and the first node corresponding to the target structural similarity are determined as a second candidate node pair with a mapping relationship;

[0023] Based on the first candidate node pair and the second candidate node pair corresponding to the first node, determine the target node pair with a mapping relationship corresponding to the first node.

[0024] In one embodiment, determining the target node pair with a mapping relationship corresponding to the first node based on the first candidate node pair and the second candidate node corresponding to the first node includes:

[0025] Update the first candidate node pair corresponding to the first node based on the second candidate node pair corresponding to the first node to obtain the initial node pair corresponding to the first node with a mapping relationship;

[0026] The initial node pair with the largest historical occurrence count among the initial node pairs is selected as the target node pair.

[0027] In one embodiment, the method further includes:

[0028] Obtain the mapping results of the node pairs with mapping relationships corresponding to each first node;

[0029] The mapping relationship determination method is evaluated based on the mapping results of the node pairs with mapping relationships corresponding to each first node, and the evaluation results are obtained.

[0030] Secondly, this application also provides a device for determining the mapping relationship between a power distribution public information model and a building management system, comprising:

[0031] The parsing module is used to parse the description file of the Public Information Model for Power Distribution (CIM) to obtain the first information model ontology in ontology format, and to parse the description file of the Building Management System (BMS) to obtain the second information model ontology in ontology format.

[0032] The first determining module is used to determine the language similarity between each first node in the first information model ontology and each second node in the second information model ontology.

[0033] The second determining module is used to determine the language similarity that is greater than or equal to the language similarity threshold in the language similarity corresponding to the first node as the target language similarity, and to determine the second node and the first node corresponding to the target language similarity as a first candidate node pair with a mapping relationship;

[0034] The third determining module is used to determine the structural similarity between each first node and each second node;

[0035] The fourth determination module is used to determine the target node pair with a mapping relationship corresponding to each first node based on the structural similarity corresponding to each first node and the first candidate node pair corresponding to each first node.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] The description file of the Public Information Model for Power Distribution (CIM) is parsed to obtain the first information model ontology in ontology format, and the description file of the Building Management System (BMS) is parsed to obtain the second information model ontology in ontology format.

[0038] For each first node in the first information model ontology, determine the language similarity between the first node and each second node in the second information model ontology;

[0039] The language similarity values ​​of the first node that are greater than or equal to the language similarity threshold are determined as the target language similarity values, and the second node and the first node corresponding to the target language similarity are determined as the first candidate node pair with a mapping relationship;

[0040] For each first node, determine the structural similarity between the first node and each second node;

[0041] Based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, the target node pair with the mapping relationship corresponding to each first node is determined.

[0042] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0043] The description file of the Public Information Model for Power Distribution (CIM) is parsed to obtain the first information model ontology in ontology format, and the description file of the Building Management System (BMS) is parsed to obtain the second information model ontology in ontology format.

[0044] For each first node in the first information model ontology, determine the language similarity between the first node and each second node in the second information model ontology;

[0045] The language similarity values ​​of the first node that are greater than or equal to the language similarity threshold are determined as the target language similarity values, and the second node and the first node corresponding to the target language similarity are determined as the first candidate node pair with a mapping relationship;

[0046] For each first node, determine the structural similarity between the first node and each second node;

[0047] Based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, the target node pair with the mapping relationship corresponding to each first node is determined.

[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0049] The description file of the Public Information Model for Power Distribution (CIM) is parsed to obtain the first information model ontology in ontology format, and the description file of the Building Management System (BMS) is parsed to obtain the second information model ontology in ontology format.

[0050] For each first node in the first information model ontology, determine the language similarity between the first node and each second node in the second information model ontology;

[0051] The language similarity values ​​of the first node that are greater than or equal to the language similarity threshold are determined as the target language similarity values, and the second node and the first node corresponding to the target language similarity are determined as the first candidate node pair with a mapping relationship;

[0052] For each first node, determine the structural similarity between the first node and each second node;

[0053] Based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, the target node pair with the mapping relationship corresponding to each first node is determined.

[0054] The aforementioned method, apparatus, equipment, medium, and product for determining the mapping relationship between the power distribution public information model and the building management system (BMS) obtains a first information model ontology in ontology format by parsing the description file of the power distribution public information model (CIM) and a second information model ontology in ontology format by parsing the description file of the building management system (BMS). For each first node in the first information model ontology, the linguistic similarity between the first node and each second node in the second information model ontology is determined. The linguistic similarity values ​​corresponding to the first node that are greater than or equal to the linguistic similarity threshold are determined as the target linguistic similarity. The second node and the first node corresponding to the target linguistic similarity are then used to determine the first candidate node pairs with a mapping relationship. For each first node, the structural similarity between the first node and each second node is determined. Based on the structural similarity corresponding to each first node and the first candidate node pairs corresponding to each first node, the target node pairs with a mapping relationship corresponding to each first node are determined. This eliminates the need for manual matching and mapping of nodes in heterogeneous models to identify data in the BMS system model, thereby saving time and manpower and improving the accuracy of matching. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart illustrating a method for determining the mapping relationship between a power distribution public information model and a building management system, as provided in an embodiment of this application.

[0057] Figure 2 This is a flowchart illustrating a language similarity determination method provided in an embodiment of this application;

[0058] Figure 3 This is a flowchart illustrating another language similarity determination method provided in an embodiment of this application;

[0059] Figure 4 This is a flowchart illustrating a method for determining target node pairs provided in an embodiment of this application;

[0060] Figure 5 This is a flowchart illustrating another method for determining target node pairs provided in an embodiment of this application;

[0061] Figure 6 This is a schematic diagram of the structure of a device for determining the mapping relationship between a power distribution public information model and a building management system, provided in an embodiment of this application.

[0062] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0064] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0065] Building automation emerged with the development of building environmental equipment, especially heating, ventilation, air conditioning, and refrigeration (HVAC&R) systems. In recent years, with the rapid development of China's national economy and science and technology, particularly the rapid advancement of IT technologies such as electronics, computers, and automation, building automation technology has experienced unprecedented and rapid development in both its scientific and technological aspects and its applications.

[0066] With the development of computer technology, digital communication technology, control technology, and microelectronics technology, automatic control systems for other building equipment are gradually being integrated into building automation systems. Modern intelligent building automation systems are highly integrated, harmoniously interactive, and possess a unified operating interface—a "highly intelligent" automation system. The rapid development of information technology has fundamentally transformed building automation systems. In the past, building automation systems were typically separate from IT systems in intelligent buildings. With the increasing popularity of enterprise-wide management and the development of open systems technology and the Internet, simple facility management will inevitably be incorporated into enterprise management; automation systems using proprietary communication protocols will be replaced by those using open communication protocols, achieving full interoperability throughout the entire building automation system. The Internet will become the enterprise-level infrastructure. These trends will inevitably lead to building automation systems being built upon the infrastructure of enterprise management systems, forming networked building systems (NBS), truly becoming a subsystem of the enterprise-level information system.

[0067] The CIM model was created by ERPI to reduce the complexity of adding new applications to existing systems and improve economic efficiency. The CIM model is oriented towards power system object modeling. All objects are divided into different packages according to the different business categories they target. Each package consists of several classes. A class is an abstraction of the basic characteristics of an object. Each class can have multiple attributes, which represent the common characteristics of the class. The logical relationships between classes include association, aggregation and inheritance, etc., and the dependency relationships between packages are reflected through hierarchical nesting

[73] . The CIM model is described using the Universal Modeling Language (UML), and the application scenarios are visualized using diagrams. In application, the corresponding model subset is usually extracted according to the actual situation to make the model more in line with actual needs. CIM includes model subsets such as transformer model, auxiliary equipment model, name model, and diagram layout model. The BMS system integrates building automation control systems (BAS), fire alarm and fire suppression systems (FAS), integrated security systems (SAS), public address systems (PAS), parking management systems (CPMS), and other systems directly related to the building. This achieves information sharing and integrated collaborative work among the systems, and has a rapid response linkage function to deal with emergencies.

[0068] To achieve efficient management of BMS systems in public buildings, it is essential to be able to identify the data in the BMS system model. However, due to the large volume of data exchanged in the power distribution network and the variability of the exchange information, manually matching and mapping heterogeneous model data to identify the BMS system model data is time-consuming, labor-intensive, and inaccurate.

[0069] To address the aforementioned technical problems, embodiments of this application provide a method for determining the mapping relationship between a power distribution public information model and a building management system. For example... Figure 1 As shown, Figure 1 This is a flowchart illustrating a method for determining the mapping relationship between a power distribution public information model and a building management system, provided in an embodiment of this application. This method can be applied to computer equipment and includes:

[0070] S101, parse the description file of the power distribution public information model (CIM) to obtain the first information model ontology in ontology format, and parse the description file of the building management system (BMS) to obtain the second information model ontology in ontology format.

[0071] The first information model ontology can be represented by a knowledge graph, and the second information model ontology can also be represented by a knowledge graph. In this context, G represents the set of concepts, S represents the set of instances, J represents the set of relations between concepts, H represents the function expressing the relations, and L represents the axiom set of semantic logic between ontology elements. The topological structure of a knowledge graph describes the logical positional relationships of its elements; classes representing concepts are located at the center of the topological structure, while classes representing relations are located at the outer edges. The expression for the knowledge graph topological structure is:

[0072] (1)

[0073] Among them, concept set Relationship set J n It is an N-dimensional set representing the set of relations located at the outer edge of the topology, and G is the set of concepts located at the center of the topology.

[0074] S102, for each first node in the first information model ontology, determine the language similarity between the first node and each second node in the second information model ontology.

[0075] The linguistic similarity between the first node and each second node in the second information model ontology can be calculated using Mahalanobis distance. The first node is an "element" in the first information model ontology, and the second node is also an "element" in the first information model ontology. Assume the Mahalanobis distance between the first and second nodes is... Then the Mahalanobis distance is shown in equation (2). Where, The result is obtained using a recursive algorithm.

[0076] (2)

[0077] Here, S1 represents the first node, which can be represented by a vector; S2 represents the second node, which can also be represented by a vector. T represents the transpose of the vector. The inverse matrix represents the covariance matrix, which is constructed based on the set of elements merged from the two knowledge graphs mentioned above, thereby enabling the calculation of similarity between heterogeneous elements using a unified distribution law.

[0078] The "elements" used to calculate similarity are determined based on the categories of concepts and instances defined by the knowledge graph.

[0079] Language similarity can also be calculated using other distance calculation methods, such as edit distance and Euclidean distance.

[0080] S103, determine the language similarity of the first node that is greater than or equal to the language similarity threshold as the target language similarity, and determine the second node and the first node corresponding to the target language similarity as the first candidate node pair with a mapping relationship.

[0081] For example, if there are 5 second nodes, for a single first node, step S102 can calculate the language similarity between the first node and each of the 5 second nodes, resulting in a total of 5 language similarities. If 3 of the 5 language similarities are greater than the language similarity threshold, these 3 language similarities are taken as the target language similarities. These 3 language similarities correspond to three second nodes respectively. The first node and the first of the three second nodes can be considered as a first candidate node pair with a mapping relationship, the first node and the second of the three second nodes can be considered as a second candidate node pair with a mapping relationship, and the first node and the third of the three second nodes can be considered as a third candidate node pair with a mapping relationship. That is, for this first node, a total of 3 candidate node pairs with mapping relationships are obtained.

[0082] The first candidate node pairs corresponding to each first node can be used as background knowledge.

[0083] S104, For each first node, determine the structural similarity between the first node and each second node.

[0084] When calculating the structural similarity of nodes in a heterogeneous information model ontology, only the hierarchical and basic association relationships between nodes need to be considered; there is no need to discuss complex aggregation, generalization, and other association relationships between nodes separately. The structural similarity of nodes in a heterogeneous information model ontology can be calculated using an improved Jaccard similarity method between a first node and a second node.

[0085] Let A be the set of structural information of a first node in the first information model ontology corresponding to the power distribution CIM model, and B be the set of structural information of a second node in the second information model ontology corresponding to the BMS system. Then, the improved Jaccard similarity between the two can be expressed as:

[0086] (3)

[0087] It is a hyperparameter that can be adjusted in size based on the effect of similarity.

[0088] S105, Based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, determine the target node pair with mapping relationship corresponding to each first node.

[0089] In one possible implementation, based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, the target node pair with a mapping relationship corresponding to each first node can be determined in the following way:

[0090] Method 1: For each first node, the structural similarity of the first node that is greater than the preset structural similarity threshold is determined as the target structural similarity, and the second node and the first node corresponding to the target structural similarity are determined as the second candidate node pair with a mapping relationship.

[0091] Update the first candidate node pair corresponding to the first node based on the second candidate node pair corresponding to the first node to obtain the initial node pair corresponding to the first node with a mapping relationship;

[0092] The initial node pair with the largest historical occurrence count among the initial node pairs is selected as the target node pair.

[0093] Method 2: For each first node, the structural similarity with the largest value among the structural similarities corresponding to the first node is determined as the target structural similarity, and the second node and the first node corresponding to the target structural similarity are determined as a second candidate node pair with a mapping relationship.

[0094] Update the first candidate node pair corresponding to the first node based on the second candidate node pair corresponding to the first node, and obtain the target node pair corresponding to the first node with a mapping relationship.

[0095] For example, for the first node in the above example, a total of 3 first candidate node pairs with mapping relationship are obtained. If the structural similarity corresponding to the first first candidate node pair among the 3 first candidate node pairs with mapping relationship is the largest structural similarity, then the first first candidate node pair is taken as the target node pair with mapping relationship corresponding to the first node.

[0096] In this step, the background knowledge can be updated using the structural similarity of each first node, thereby making the final target node pairs with mapping relationships more accurate.

[0097] In this embodiment, a first information model ontology in ontology format is obtained by parsing the description file of the Public Information Model for Power Distribution (CIM), and a second information model ontology in ontology format is obtained by parsing the description file of the Building Management System (BMS). For each first node in the first information model ontology, the linguistic similarity between the first node and each second node in the second information model ontology is determined. The linguistic similarity values ​​of the first nodes that are greater than or equal to the linguistic similarity threshold are determined as the target linguistic similarity values. The second nodes and first nodes corresponding to the target linguistic similarity values ​​are then used to determine first candidate node pairs with a mapping relationship. For each first node, the structural similarity between the first node and each second node is determined. Based on the structural similarity values ​​of each first node and the first candidate node pairs corresponding to each first node, target node pairs with a mapping relationship corresponding to each first node are determined. This eliminates the need for manual matching and mapping of nodes in heterogeneous models to identify data in the BMS system model, thereby saving time and manpower and improving the accuracy of matching.

[0098] In one embodiment, such as Figure 2 As shown, Figure 2 This is a flowchart illustrating a language similarity determination method provided in an embodiment of this application. Based on the above embodiment, S102, which determines the language similarity between the first node and each second node in the second information model ontology, includes:

[0099] S201, For each second node, determine the first similarity between the node name of the first node and the node name of the second node.

[0100] The first and second nodes used to calculate similarity can both be first-level nodes or both be second-level nodes, with the second-level node being the next level node of the first-level node.

[0101] S202, determine the second similarity between the node label of the first node and the node label of the second node.

[0102] S203, determine the third similarity between the node annotation of the first node and the node annotation of the second node.

[0103] S204. Based on the first similarity, second similarity and third similarity corresponding to the second node, determine the language similarity between the first node and the second node.

[0104] Let n be the Mahalanobis distance between the node names of two first-level nodes, l be the Mahalanobis distance between the node labels, and c be the Mahalanobis distance between the node annotations; let n1 be the Mahalanobis distance between the node names of two second-level nodes, l1 be the Mahalanobis distance between the node labels, and c1 be the Mahalanobis distance between the node annotations; then the formulas for calculating the language similarity of first-level nodes and second-level nodes are shown in equations (4) and (5). Where, , and These represent the weights of each item. Based on the order of importance of model node names, labels, and annotations, the following settings are used: =0.6, =0.3, =0.1.

[0105] (4)

[0106] (5)

[0107] in, This represents the similarity between two first-level nodes. This indicates the similarity between two second-level nodes.

[0108] In this embodiment, for each second node, a first similarity is determined between the node name of the first node and the node name of the second node; a second similarity is determined between the node label of the first node and the node label of the second node; and a third similarity is determined between the node annotation of the first node and the node annotation of the second node. Based on the first, second, and third similarities corresponding to the second node, the linguistic similarity between the first node and the second node is determined. Combining the node name, node label, and node annotation can effectively analyze similarity and improve the accuracy of the obtained linguistic similarity.

[0109] In one embodiment, such as Figure 3 As shown, Figure 3 This is a flowchart illustrating another language similarity determination method provided in this application embodiment. Based on the above embodiment, step S204, which determines the language similarity between the first node and the second node based on the first similarity, second similarity, and third similarity corresponding to the second node, includes:

[0110] S301, determine the first product of the first similarity and the corresponding first weight, the second product of the second similarity and the corresponding second weight, and the third product of the third similarity and the corresponding third weight.

[0111] S302, determine the language similarity between the first node and the second node based on the sum of the first product, the second product, and the third product.

[0112] The sum of the first, second, and third products can be used as the language similarity between the first and second nodes. Alternatively, the sum of the first, second, and third products multiplied by a preset value can be used as the language similarity between the first and second nodes.

[0113] In this embodiment, by determining the first product of the first similarity and the corresponding first weight, the second product of the second similarity and the corresponding second weight, and the third product of the third similarity and the corresponding third weight, the language similarity between the first node and the second node is determined based on the sum of the first product, the second product, and the third product. Combining the weights to calculate the language similarity can improve the accuracy of the obtained language similarity.

[0114] In one embodiment, such as Figure 4 As shown, Figure 4 This is a flowchart illustrating a method for determining target node pairs provided in an embodiment of this application. Step S105 above, based on the structural similarity corresponding to each first node and the first candidate node pairs corresponding to each first node, determines the target node pairs with mapping relationships corresponding to each first node, including:

[0115] S401, for each first node, the structural similarity of the first node that is greater than the preset structural similarity threshold is determined as the target structural similarity, and the second node and the first node corresponding to the target structural similarity are determined as a second candidate node pair with a mapping relationship.

[0116] S402, based on the first candidate node pair and the second candidate node pair corresponding to the first node, determine the target node pair with a mapping relationship corresponding to the first node.

[0117] For example, regarding the first node in the above example, three candidate node pairs with mapping relationships are obtained. If the structural similarity of the first and second candidate node pairs among these three candidate node pairs with mapping relationships is greater than a preset structural similarity threshold, then the first and second candidate node pairs can be used as second candidate node pairs. Then, the candidate node pairs with mapping relationships corresponding to the first node are updated using the second candidate node pairs. For example, by deleting the third candidate node pair among the three candidate node pairs with mapping relationships, the candidate node pairs with mapping relationships corresponding to the first node are updated. Then, any one of the updated candidate node pairs with mapping relationships corresponding to the first node can be used as the target node pair with mapping relationships corresponding to the first node. For example, the first candidate node pair can be used as the target node pair with mapping relationships corresponding to the first node, or the second candidate node pair can be used as the target node pair with mapping relationships corresponding to the first node.

[0118] In this embodiment, for each first node, the structural similarity of the first node that is greater than a preset structural similarity threshold is determined as the target structural similarity, and the second node and the first node corresponding to the target structural similarity are determined as a second candidate node pair with a mapping relationship. Based on the first candidate node pair and the second candidate node pair corresponding to the first node, the target node pair with a mapping relationship corresponding to the first node is determined. Since the target node pair with a mapping relationship corresponding to the first node is determined by combining structural similarity and language similarity, the accuracy of the obtained target node pair can be improved.

[0119] In one embodiment, such as Figure 5 As shown, Figure 5 This is a flowchart illustrating another method for determining target node pairs provided in an embodiment of this application. Step S402 above, based on the first candidate node pair and the second candidate node pair corresponding to the first node, determines the target node pair with a mapping relationship corresponding to the first node, including:

[0120] S501, based on the second candidate node pair corresponding to the first node, update the first candidate node pair corresponding to the first node to obtain the initial node pair corresponding to the first node with a mapping relationship.

[0121] For example, regarding the first node in the above example, three candidate node pairs with mapping relationships are obtained. If the structural similarity of the first and second candidate node pairs among these three candidate node pairs with mapping relationships is greater than a preset structural similarity threshold, then the first and second candidate node pairs can be used as second candidate node pairs. Then, the candidate node pairs with mapping relationships corresponding to the first node are updated using the second candidate node pairs. For example, by deleting the third candidate node pair among the three candidate node pairs with mapping relationships, the candidate node pairs with mapping relationships corresponding to the first node are updated, resulting in initial node pairs with mapping relationships corresponding to the first node. These initial node pairs with mapping relationships corresponding to the first node include the first and second candidate node pairs.

[0122] S502, take the initial node pair with the largest historical occurrence count among the initial node pairs as the target node pair.

[0123] The initial node pair with the largest historical occurrence count among the initial node pairs is selected as the target node pair. For example, if the historical occurrence count of the first candidate node pair is greater than that of the second candidate node pair, then the first candidate node pair is selected as the target node pair with the mapping relationship corresponding to that first node. The historical occurrence count can be the number of times the two nodes in the initial node pair have a mapping relationship. Simultaneously, initial node pairs other than the one with the largest historical occurrence count can be deleted.

[0124] In this embodiment, by updating the first candidate node pair corresponding to the first node based on the second candidate node pair corresponding to the first node, an initial node pair with a mapping relationship corresponding to the first node is obtained. The initial node pair with the largest historical occurrence count among the initial node pairs is then used as the target node pair. Determining the target node pair by combining historical occurrence counts can further improve the accuracy of the obtained target node pairs.

[0125] In one embodiment, the method may further include: obtaining the mapping results of the node pairs with mapping relationships corresponding to each first node; and evaluating the mapping relationship determination method based on the mapping results of the node pairs with mapping relationships corresponding to each first node to obtain an evaluation result.

[0126] Let P1 represent a true negative, meaning the mapping relationship is actually correct and the determined mapping relationship is correct; let P2 represent a false negative, meaning the mapping relationship is actually incorrect but the determined mapping relationship is correct; let P3 represent a false positive, meaning the mapping relationship is actually correct but the determined mapping relationship is incorrect; and let P4 represent a true positive, meaning the mapping relationship is actually incorrect but the determined mapping relationship is incorrect. Sensitivity can be used to... Specificity and accuracy At least one of the three indicators is used to evaluate the mapping result.

[0127] (6)

[0128] (7)

[0129] (8)

[0130] In this embodiment, the mapping results of the node pairs with mapping relationships corresponding to each first node are obtained. Based on the mapping results of the node pairs with mapping relationships corresponding to each first node, the mapping relationship determination method is evaluated to obtain the evaluation results. This enables the evaluation of the mapping relationship determination method to verify its accuracy, sensitivity, and specificity.

[0131] In one embodiment, to ensure the integrity of the mapping relationship, facilitate subsequent algorithm reading and parsing, and enable accurate location of the nodes to be mapped using XPath during model data conversion, the mapping relationship optimization results are stored in XML format. The XML file is then parsed and compared for deeper semantic meaning, such as synonyms and near-synonyms.

[0132] To verify the effectiveness of the mapping and association algorithm between the power distribution CIM model and the BMS system proposed in this invention, ontology analysis was performed on the BMS system model and the CIMv16 standard power grid static topology model, and the resulting ontology topology structure was stored. Node similarity was calculated for mapping, the mapping results were optimized and evaluated, and the mapping result file was output in XML format. To clearly illustrate the mapping relationship, the mapping relationships of some typical nodes in the mapping result file are shown in Table 1. Through this mapping relationship, the data of the BMS system model can be identified.

[0133] Table 1

[0134]

[0135] In Table 1, PowerSystemResource defines the power system resources and specifies the internal topology of the power grid; PowerTransformerEnd represents the transformer and specifies voltage level changes, such as from 20 kV to 220 V. TransformerEnd indicates the transformer structure, including equivalent impedance, parallel parameters, and whether it is grounded; RatioTapChanger represents the winding turns ratio; TapChanger represents voltage and phase angle; ConductingEquipment represents equipment directly connected to the distribution network; VoltageLevel represents the voltage level; Substation represents the substation to which it belongs; Terminal represents the electrical port; Plant represents the power source; Bay defines the bay unit; and VoltageControlZone defines the voltage control zone, such as which network supplies power to a certain floor. The first column in Table 1 represents the second node, and the second column represents the first node. Table 1 shows that the mapping relationship between target node pairs with mapping relationships in the same row is accurate.

[0136] As shown in Table 1, the nodes of the expanded BMS system model can be mapped well to the IEC 61968 topology model. The updated BMS system model is basically close to the IEC 61968 definition of the same object. Most of the nodes can be mapped based on node similarity, and a small number of nodes with significantly different names can also be accurately mapped based on structural similarity calculations. The mapping results searched by the program only establish preliminary relationships. During the model data instance conversion process, some special BMS device classes should be instantiated into different subclasses of CIM device classes according to the category defined by the attribute type. Therefore, manual correction of the mapping results is required. Taking the BMS conductive device BMSEquipment class as an example, the mapping relationships of different CIM classes corresponding to different values ​​of its attribute type are shown in Table 2.

[0137] Table 2

[0138]

[0139] After verifying and adjusting the mapping results, conversion scripts can be directly generated based on the mapping relationships to achieve mutual conversion between heterogeneous information models. After constructing a difference fusion model for the topology model and CIM model of heterogeneous public building BMS system, except for some special one-to-many and many-to-one mappings, most of the mapping results searched by the algorithm can be guaranteed to be accurate. The comprehensive evaluation index can generally reach more than 90%, which is much higher than the mapping results of the original heterogeneous model, and greatly reduces the workload of manual matching.

[0140] In Table 2, the information in the second column of the same row is the abbreviation of the information in the third column. Specifically, MFR represents the maximum short-circuit fault rating; DCR represents the disconnector; BES represents the battery; PTR represents the power transformer; LBR represents the circuit breaker; SME represents the generator; ERR represents the ramp rate; and FAR represents the current rating. BMSEquipment represents equipment in the BMS system.

[0141] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0142] Based on the same inventive concept, this application also provides a device for determining the mapping relationship between the power distribution public information model and the building management system to implement the above-mentioned method for determining the mapping relationship between the power distribution public information model and the building management system. The solution provided by this device is similar to the solution described in the above-described method. Therefore, the specific limitations of one or more embodiments of the device for determining the mapping relationship between the power distribution public information model and the building management system provided below can be found in the limitations of the method for determining the mapping relationship between the power distribution public information model and the building management system described above, and will not be repeated here.

[0143] In one exemplary embodiment, such as Figure 6 As shown, Figure 6 This is a schematic diagram of a device for determining the mapping relationship between a power distribution public information model and a building management system, provided in an embodiment of this application. The device 600 includes:

[0144] The parsing module 601 is used to parse the description file of the power distribution public information model (CIM) to obtain the first information model ontology in ontology format, and to parse the description file of the building management system (BMS) to obtain the second information model ontology in ontology format.

[0145] The first determining module 602 is used to determine the language similarity between each first node in the first information model ontology and each second node in the second information model ontology; the second determining module 603 is used to determine the language similarity greater than or equal to the language similarity threshold of the language similarity corresponding to the first node as the target language similarity, and to determine the second node and the first node corresponding to the target language similarity as a first candidate node pair with a mapping relationship; the third determining module 604 is used to determine the structural similarity between each first node and each second node; the fourth determining module 605 is used to determine the target node pair with a mapping relationship corresponding to each first node based on the structural similarity corresponding to each first node and the first candidate node pair corresponding to each first node.

[0146] In one exemplary embodiment, the first determining module 602 includes:

[0147] The first determining unit is used to determine the first similarity between the node name of the first node and the node name of the second node for each second node; the second determining unit is used to determine the second similarity between the node label of the first node and the node label of the second node; the third determining unit is used to determine the third similarity between the node annotation of the first node and the node annotation of the second node; and the fourth determining unit is used to determine the linguistic similarity between the first node and the second node based on the first similarity, the second similarity and the third similarity corresponding to the second node.

[0148] In an exemplary embodiment, the fourth determining unit is specifically used to determine the first product of the first similarity and the corresponding first weight, the second product of the second similarity and the corresponding second weight, and the third product of the third similarity and the corresponding third weight; and to determine the language similarity between the first node and the second node based on the sum of the first product, the second product, and the third product.

[0149] In one exemplary embodiment, the fourth determining module 605 includes:

[0150] The fifth determining unit is used to determine, for each first node, the structural similarity of the structural similarity corresponding to the first node that is greater than the preset structural similarity threshold as the target structural similarity, and to determine the second node and the first node corresponding to the target structural similarity as a second candidate node pair with a mapping relationship; the sixth determining unit is used to determine the target node pair with a mapping relationship corresponding to the first node based on the first candidate node pair and the second candidate node pair corresponding to the first node.

[0151] In an exemplary embodiment, the sixth determining unit is specifically used to update the first candidate node pair corresponding to the first node based on the second candidate node pair corresponding to the first node, to obtain the initial node pair corresponding to the first node with a mapping relationship; and to take the initial node pair corresponding to the largest historical occurrence count among the historical occurrence counts of the initial node pair as the target node pair.

[0152] In one exemplary embodiment, the device 600 further includes:

[0153] The acquisition module is used to obtain the mapping results of the node pairs with mapping relationships corresponding to each first node;

[0154] The fifth determination module is used to evaluate the mapping relationship determination method based on the mapping results of the node pairs with mapping relationships corresponding to each first node, and obtain the evaluation result.

[0155] The modules in the mapping relationship determination device between the aforementioned power distribution public information model and building management system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0156] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for determining the mapping relationship between a power distribution public information model and a building management system. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0157] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0158] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above method embodiments. The technical principles and effects are similar, and will not be repeated here.

[0159] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of any of the above method embodiments. The technical principles and effects are similar and will not be repeated here.

[0160] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of any of the above method embodiments. The technical principles and effects are similar and will not be repeated here.

[0161] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0162] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0163] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0164] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the mapping relationship between a public information model for power distribution and a building management system, characterized in that, The method includes: The description file of the Public Information Model for Power Distribution (CIM) is parsed to obtain the first information model ontology in ontology format, and the description file of the Building Management System (BMS) is parsed to obtain the second information model ontology in ontology format. For each first node in the first information model ontology, determine the language similarity between the first node and each second node in the second information model ontology; The language similarity values ​​of the first node that are greater than or equal to the language similarity threshold are determined as the target language similarity values, and the second node corresponding to the target language similarity and the first node are determined as a first candidate node pair with a mapping relationship. For each first node, determine the structural similarity between the first node and each second node; Based on the structural similarity of each first node and the first candidate node pair corresponding to each first node, target node pairs with mapping relationships are determined for each first node.

2. The method according to claim 1, characterized in that, Determining the language similarity between the first node and each second node in the second information model ontology includes: For each of the second nodes, determine the first similarity between the node name of the first node and the node name of the second node; Determine the second similarity between the node label of the first node and the node label of the second node; Determine the third similarity between the node annotation of the first node and the node annotation of the second node; Based on the first similarity, the second similarity, and the third similarity corresponding to the second node, the language similarity between the first node and the second node is determined.

3. The method according to claim 2, characterized in that, Determining the language similarity between the first node and the second node based on the first similarity, the second similarity, and the third similarity corresponding to the second node includes: Determine the first product of the first similarity and the corresponding first weight, the second product of the second similarity and the corresponding second weight, and the third product of the third similarity and the corresponding third weight; The linguistic similarity between the first node and the second node is determined based on the sum of the first product, the second product, and the third product.

4. The method according to any one of claims 1-3, characterized in that, Based on the structural similarity corresponding to each first node and the first candidate node pair corresponding to each first node, target node pairs with mapping relationships corresponding to each first node are determined, including: For each of the first nodes, the structural similarity values ​​of the first node that are greater than a preset structural similarity threshold are determined as the target structural similarity values, and the second node corresponding to the target structural similarity value and the first node are determined as a second candidate node pair with a mapping relationship. Based on the first candidate node pair and the second candidate node pair corresponding to the first node, the target node pair with a mapping relationship corresponding to the first node is determined.

5. The method according to claim 4, characterized in that, The step of determining the target node pair with a mapping relationship corresponding to the first node based on the first candidate node pair and the second candidate node corresponding to the first node includes: Update the first candidate node pair corresponding to the first node based on the second candidate node pair corresponding to the first node to obtain the initial node pair corresponding to the first node with a mapping relationship; The initial node pair with the largest historical occurrence count among the initial node pairs is taken as the target node pair.

6. The method according to claim 1, characterized in that, The method further includes: Obtain the mapping results of the node pairs with mapping relationships corresponding to each of the first nodes; The mapping relationship determination method is evaluated based on the mapping results of the node pairs with mapping relationships corresponding to each of the first nodes, and the evaluation results are obtained.

7. A device for determining the mapping relationship between a power distribution public information model and a building management system, characterized in that, The device includes: The parsing module is used to parse the description file of the Public Information Model for Power Distribution (CIM) to obtain the first information model ontology in ontology format, and to parse the description file of the Building Management System (BMS) to obtain the second information model ontology in ontology format. The first determining module is used to determine the language similarity between each first node in the first information model ontology and each second node in the second information model ontology. The second determining module is used to determine the language similarity that is greater than or equal to the language similarity threshold in the language similarity corresponding to the first node as the target language similarity, and to determine the second node corresponding to the target language similarity and the first node as a first candidate node pair with a mapping relationship; The third determining module is used to determine the structural similarity between each of the first nodes and each of the second nodes; The fourth determining module is used to determine the target node pair with a mapping relationship corresponding to each of the first nodes based on the structural similarity corresponding to each of the first nodes and the first candidate node pair corresponding to each of the first nodes.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images