Urban information model knowledge graph construction method and device, and readable storage medium

Abstract

The application provides a city information model knowledge graph construction method and device and a readable storage medium. The method comprises: a CIM concept classification system: constructing conceptual knowledge as a standard for inducting or classifying specific CIM entities; CIM entity construction: converting discrete CIM data into specific objects according to the conceptual knowledge; CIM relationship extraction: extracting relationship information from various objects through the processes of knowledge extraction, relationship linking and relationship reasoning; CIM knowledge fusion: quantifying CIM knowledge into a CIM concept layer, a CIM entity layer and a CIM relationship layer by using a top-down construction method to obtain a CIM knowledge graph. The application combines actual CIM business needs, adds CIM business relationships on the basis of main semantic relationships, and is used for fusing semantic relationships and spatial relationships to realize large-scale multi-source heterogeneous data storage management and information retrieval.

Description

Technical Field

[0001] This application relates to the field of digital information technology, and in particular to a method, apparatus and readable storage medium for constructing a knowledge graph of an urban information model. Background Technology

[0002] As City Information Models (CIMs) are steadily advancing across multiple dimensions such as urban planning and design, construction management, and operation and maintenance, and gradually moving from concepts and pilot projects to practical implementation, CIMs based on digital twins will become the information infrastructure platform for new smart cities.

[0003] The storage, classification, and sharing of information are the foundation of urban information model (CIM) construction. Driven by technologies such as big data and artificial intelligence, it is necessary to utilize high-performance computing, cloud computing, big data visual analysis, knowledge graphs, and other technical systems to achieve the analysis and mining of multi-source heterogeneous CIM data.

[0004] However, there is currently no technical method for constructing knowledge graphs for urban information models. Summary of the Invention

[0005] The technical problem to be solved by this application is to address the above-mentioned shortcomings of the prior art by providing a method, apparatus and readable storage medium for constructing a knowledge graph of an urban information model, so as to solve the problems existing in the prior art.

[0006] Firstly, this application provides a method for constructing a knowledge graph for a city information model (CIM), the method comprising: S1. CIM Concept Classification System: Constructing conceptual knowledge as a standard for summarizing or classifying specific CIM entities; S2, CIM Entity Construction: Converting discrete CIM data into concrete objects based on conceptual knowledge; S3, CIM Relation Extraction: The process of extracting relational information from various objects through knowledge extraction, relation linking, and relational reasoning; S4. CIM Knowledge Integration: Adopting a top-down construction approach, CIM knowledge is quantified into CIM concept layer, CIM entity layer and CIM relationship layer to obtain CIM knowledge graph.

[0007] In some embodiments, S1 includes: CIM data is categorized into five dimensions: results, processes, resources, attributes, and applications. Based on data sources, it can be divided into spatiotemporal basic data, resource survey data, planning and control data, engineering construction project data, public thematic data, and IoT sensing data.

[0008] In some embodiments, in S2, the CIM entity includes at least one of time, space, attribute, behavior, state, and process.

[0009] In some embodiments, S3, the CIM relationship includes temporal relationship, spatial relationship and semantic relationship; Among them, time relationship is mainly used to describe various geographical phenomena with obvious time-varying characteristics; Spatial relationships refer to the relationships between geographic spatial instances that are related to spatial characteristics; Semantic relations are used to describe the semantic relationships between concepts, between concepts and instances, and between instances.

[0010] In some embodiments, a formal description of the time relationship includes: Time-varying relationships between events and processes in CIM entities; Changes in the temporal attribute values ​​of spatial information.

[0011] In some embodiments, spatial relationships mainly include topological relationships, distance relationships, and orientational relationships.

[0012] In some embodiments, S4 includes: Geographic knowledge is integrated based on concepts, entities, characteristics, and relationships; By utilizing instance alignment, attribute fusion, and relationship matching methods, instances, their attributes, and relationships extracted from multi-source multimodal corpora are aligned and fused based on multidimensional similarity. For spatial data fusion involved in CIM, the association between attributes and entities is established by using element coding and object tagging, thereby achieving data fusion.

[0013] Secondly, this application provides a device for constructing a knowledge graph of an urban information model, the device comprising: The concept classification module is designed to construct conceptual knowledge as a standard for summarizing or classifying specific CIM entities; The entity building module is configured to convert discrete CIM data into concrete objects based on conceptual knowledge. The relation extraction module is designed to extract relation information from various objects through knowledge extraction, relation linking, and relation reasoning processes. The knowledge fusion module is designed to use a top-down construction approach, quantifying CIM knowledge into CIM concept layer, CIM entity layer and CIM relationship layer to obtain a CIM knowledge graph.

[0014] Thirdly, this application provides a city information model knowledge graph construction device, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to implement the city information model knowledge graph construction method described in the first aspect.

[0015] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the urban information model knowledge graph construction method described in the first aspect.

[0016] This application provides a method, apparatus, and readable storage medium for constructing a knowledge graph for a city information model (CIM). The method includes: a CIM concept classification system: constructing conceptual knowledge as a standard for summarizing or classifying specific CIM entities; CIM entity construction: converting discrete CIM data into specific objects based on conceptual knowledge; CIM relation extraction: extracting relation information from various objects through knowledge extraction, relation linking, and relation reasoning; and CIM knowledge fusion: using a top-down construction approach, quantifying CIM knowledge into a CIM concept layer, a CIM entity layer, and a CIM relation layer to obtain a CIM knowledge graph. This application provides a method for constructing a knowledge graph for a city information model. This application combines knowledge graph technology with city information model (CIM) construction, and for the first time proposes a scheme for constructing a city information model knowledge graph (hereinafter referred to as CIM knowledge graph). Combining the actual needs of CIM business, it adds CIM business relations on the basis of the main semantic relations to integrate semantic relations and spatial relations, realizing large-scale multi-source heterogeneous data storage management and information retrieval. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] Figure 1 A flowchart illustrating a method for constructing a knowledge graph for a city information model, as provided in this application embodiment; Figure 2 A schematic diagram of the CIM entity model provided in the embodiments of this application; Figure 3 A schematic diagram illustrating the CIM relationship classification provided in this application embodiment; Figure 4 A schematic diagram illustrating the construction process of the CIM knowledge graph provided in this application embodiment; Figure 5 A schematic diagram of the CIM knowledge graph provided in an embodiment of this application; Figure 6This is a schematic diagram illustrating the application scenario of the CIM basic platform provided in the embodiments of this application; Figure 7 A schematic diagram of a city information model knowledge graph construction device provided in this application embodiment; Figure 8 This is a schematic diagram of another urban information model knowledge graph construction device provided in an embodiment of this application.

[0019] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solution of this application, the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0021] It is understood that the specific embodiments and accompanying drawings described herein are merely for explaining this application and are not intended to limit this application.

[0022] It is understood that, without conflict, the various embodiments and features in the embodiments of this application can be combined with each other.

[0023] It is understood that, for ease of description, only the parts relevant to this application are shown in the accompanying drawings, while parts unrelated to this application are not shown in the drawings.

[0024] It is understood that each unit or module involved in the embodiments of this application may correspond to only one entity structure, or may be composed of multiple entity structures, or multiple units or modules may be integrated into one entity structure.

[0025] It is understood that the terms "first," "second," etc., used in the embodiments of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0026] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of this application may occur in a different order than those marked in the accompanying drawings.

[0027] It is understood that the flowcharts and block diagrams of this application illustrate the possible architecture, functions, and operations of systems, apparatuses, devices, and methods according to various embodiments of this application. Each block in a flowchart or block diagram may represent a unit, module, program segment, or code, containing executable instructions for implementing the specified function. Furthermore, each block or combination of blocks in the block diagrams and flowcharts may be implemented using a hardware-based system to implement the specified function, or using a combination of hardware and computer instructions.

[0028] It is understood that the units and modules involved in the embodiments of this application can be implemented by software or by hardware. For example, the units and modules can be located in the processor.

[0029] It is understood that the specific values ​​of each parameter in this application are merely illustrative examples, and in practical applications, the parameters can be optimized and adjusted based on specific requirements.

[0030] Knowledge graphs are essentially large-scale semantic networks used to describe concepts, entities, and their relationships in the objective world. While knowledge graph construction and application have a high degree of universality, they also possess certain professional specificities. CIM (City Information Modeling) is based on technologies such as Building Information Modeling (BIM), Geographic Information System (GIS), and Internet of Things (IoT), integrating multi-dimensional and multi-scale spatial data and IoT sensing data from above-ground and underground, indoor and outdoor, historical, current, and future urban areas to construct a three-dimensional digital spatial urban information organic complex. Therefore, CIM uses geometric concepts to abstractly represent geographic objects at different spatial scales, generally classifying them into geometric figures such as points, lines, surfaces, and volumes. The information describing the relationships between these geometric figures is mainly reflected in the spatial and non-spatial characteristics of the geospatial data. Combining the spatial concepts and characteristics of geographic data, we obtain the CIM knowledge graph model: S CIM ={C,S,R,P,A,O}; Wherein, C represents a concept, that is, a set, type, kind, etc. of an ontology; S represents a spatial geometric figure, including points, lines, surfaces, volumes, and aggregate objects; R represents a relation, that is, a certain property relationship between a concept and a geometric figure, between concepts, between a concept and an instance, and between instances, including temporal relations, spatial relations, and semantic relations; P represents an attribute, that is, a general description of the essential characteristics of a thing; A represents a rule, that is, a constraint on the values ​​of relations and attributes and their combinations, including functions (such as some unit conversion formulas) and axioms (such as the length of a river cannot be negative); O represents an instance, that is, a specific object.

[0031] However, there is currently no technical method for constructing knowledge graphs for urban information models. Therefore, this application proposes a method for constructing urban information models based on knowledge graphs, taking into account the uniqueness of knowledge in urban information models and the heterogeneous data types from multiple sources, while drawing on existing general knowledge graph technologies.

[0032] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0033] This application provides a method for constructing a knowledge graph of an urban information model. The workflow of this method can be implemented by electronic devices, such as computers and handheld smart terminals. For ease of explanation, the embodiments of this application are described with the computer as the subject of the method execution.

[0034] Figure 1 This is a schematic diagram of the urban information model knowledge graph construction method provided in the embodiments of this application, such as... Figure 1 As shown, this application provides a method for constructing a knowledge graph for a city information model (CIM), which is applied to the CIM. The method includes steps S1-S4, as follows: S1. CIM Concept Classification System: Constructing conceptual knowledge as a standard for summarizing or classifying specific CIM entities; Conceptual knowledge is essentially a standard for summarizing or classifying specific CIM entities. It is a key link in elevating data-based knowledge with low knowledge value density to high-level knowledge with higher knowledge value density.

[0035] In some embodiments, S1 includes: CIM data is categorized into five dimensions: results, processes, resources, attributes, and applications. Based on data sources, it can be divided into spatiotemporal basic data, resource survey data, planning and control data, engineering construction project data, public thematic data, and IoT sensing data.

[0036] S2, CIM Entity Construction: Converting discrete CIM data into concrete objects based on conceptual knowledge; In essence, CIM entity construction involves transforming discrete CIM data into concrete objects through rule definitions.

[0037] In some embodiments, in S2, the CIM entity includes at least one of time, space, attribute, behavior, state, and process.

[0038] Specifically, Figure 2 This is a schematic diagram of the CIM entity model provided in the embodiments of this application, as shown below. Figure 2 As shown, CIM entities mainly include features such as time, space, attributes, behavior, state, and process. The CIM entity representation model is mainly used to provide a structured description of the features of CIM entities and their logical relationships.

[0039] from Figure 2 As can be seen, based on the various characteristics and relationships of CIM entities, knowledge units of different granularities and levels can be constructed. Each knowledge unit can be expanded and refined according to actual application needs, and there are forms such as inheritance or aggregation between different knowledge units.

[0040] Time and space are the prerequisites for the existence of CIM entities and the basic framework for expressing geographic knowledge. Attribute characteristics are data or data volume used to characterize the properties of CIM entities themselves, and different types of CIM entities have specific attribute characteristics. Geometric characteristics are the atomic spatial concepts of geospatial CIM entities, expressed through abstraction. Behavioral characteristics are used to describe the various activities of CIM entities. Under specific temporal and spatial conditions, combined with the attribute and behavioral characteristics of CIM entities, different states of CIM entities are formed. Based on the temporal relationship of different states, the evolution process of CIM entities can be characterized. According to the spatiotemporal range, the process can be hierarchically classified, from large to small: process as a whole, process stages, and process sequence, presenting an inverted pyramid structure.

[0041] S3, CIM Relation Extraction: The process of extracting relational information from various objects through knowledge extraction, relation linking, and relational reasoning; CIM relation extraction is a process of extracting relation information from various types of data through knowledge extraction, relation linking, and relation reasoning.

[0042] In some embodiments, S3, the CIM relationship includes temporal relationship, spatial relationship and semantic relationship; Among them, time relationship is mainly used to describe various geographical phenomena with obvious time-varying characteristics; Spatial relationships refer to the relationships between geographic spatial instances that are related to spatial characteristics; Semantic relations are used to describe the semantic relationships between concepts, between concepts and instances, and between instances.

[0043] In some embodiments, a formal description of the time relationship includes: Time-varying relationships between events and processes in CIM entities; Changes in the temporal attribute values ​​of spatial information.

[0044] Specifically, Figure 3 This is a schematic diagram of the CIM relationship classification provided in the embodiments of this application, as shown below. Figure 3 As shown, in some embodiments, spatial relationships mainly include topological relationships, distance relationships, and orientation relationships.

[0045] Temporal relationships are primarily used to describe various geographical phenomena with significant time-varying characteristics. Formal descriptions of temporal relationships can be broadly categorized into two types: 1) Time-varying relationships between CIM entities such as events and processes, such as the relationship between "event-location" and "person-location." 2) Changes in the temporal attribute values ​​of spatial information. This can be used for updating map entities and relationships, such as city names and spatial locations, which can change over time. For example, "a car is driving on the road," where the location changes continuously over time, the description of the car's location attribute values ​​(such as latitude and longitude coordinates) needs to include a timestamp. The expression of temporal relationships is generally divided into two types: one is a specific time expression, such as "Monday, March 7, 2022," from which the temporal relationship can be directly extracted; the other is a vague time expression, such as "last year" or "last week," which requires inference from the context to derive the temporal relationship.

[0046] Spatial relationships refer to the spatial characteristic-related relationships between geographic spatial instances. They form the basis for data organization, querying, analysis, and reasoning, and mainly include topological relationships, distance relationships, and orientational relationships. The process of spatial relationship extraction is a semantic transformation from the CIS computational model to natural language spatial relationships, achieved by establishing a dictionary that maps geographic spatial relationships to natural language descriptions. Traditional methods store information in layers during data preprocessing, and spatial analysis is performed in two steps: first, the target layer is determined by querying, and then cross-layer operations are performed to output a one-time layer-level analysis result.

[0047] Semantic relations are used to describe the semantic relationships between concepts, between concepts and instances, and between instances at the semantic level.

[0048] S4. CIM Knowledge Integration: Adopting a top-down construction approach, CIM knowledge is quantified into CIM concept layer, CIM entity layer and CIM relationship layer to obtain CIM knowledge graph.

[0049] In some embodiments, S4 includes: Geographic knowledge is integrated based on concepts, entities, characteristics, and relationships; By utilizing instance alignment, attribute fusion, and relationship matching methods, instances, their attributes, and relationships extracted from multi-source multimodal corpora are aligned and fused based on multidimensional similarity. For spatial data fusion involved in CIM, the association between attributes and entities is established by using element coding and object tagging, thereby achieving data fusion.

[0050] Because CIM knowledge comes from numerous sources, the knowledge descriptions from different data sources exhibit both complementarity and differences. For example, building data is stored as 3D models and basic information such as building height and floors in spatiotemporal foundation data; vector data and information such as construction year, building type, and land area are stored in land surveys; BIM models and design information are stored in engineering construction; and points of interest and place name / address information are stored in public themes. Therefore, knowledge fusion is necessary to link the semantic understanding of different entities in different data to the same entity.

[0051] Specifically, geographical knowledge can be integrated at four levels: concepts, entities, characteristics, and relationships.

[0052] Furthermore, by utilizing methods such as instance alignment, attribute fusion, and relation matching, instances and their attributes and relations extracted from multi-source multimodal corpora are aligned and fused based on multi-dimensional similarity such as lexical and structural similarity, thus solving problems such as knowledge heterogeneity and inconsistency brought about by multi-source corpora.

[0053] Furthermore, for the extensive spatial data fusion involved in CIM, including vector data, image data, model data, and BIM data, data fusion is achieved by establishing the association between attributes and entities through feature coding and object tagging.

[0054] This application draws heavily on existing knowledge graph construction methods, employing a top-down approach that divides the construction into a schema layer and a data layer. The schema layer begins by building a top-level ontology from the highest-level concepts, then refines the concepts and relationships to form a well-structured hierarchical tree of concepts. The data layer fills the constructed schema layer ontology with entity matching obtained from knowledge extraction. Furthermore, considering the uniqueness of CIM knowledge and its diverse and heterogeneous data types, this patent further quantifies CIM knowledge into a CIM concept layer, a CIM entity layer, and a CIM relationship layer, thus forming unique CIM knowledge units of different granularities and levels.

[0055] Specifically, Figure 4 This is a schematic diagram illustrating the construction process of the CIM knowledge graph provided in an embodiment of this application. Figure 5 A schematic diagram of the CIM knowledge graph provided in the embodiments of this application, such as Figure 4 as well as Figure 5As shown, this application formally describes concepts, entities, geometries, attributes, and their interrelationships in the CIM domain. Concepts and entities are interconnected through nodes (Points) and edges (Edges), and the ternary relationships of SPOs (Subject, Predicate, Object) are formally represented using RDF to form a network structure. Points represent geographic concepts, CIM entities, geometries, and attribute values; edges represent relationships between concepts, between concepts and entities, between entities, between entities and geometries, between entities and attributes, and between attributes and attribute values.

[0056] In this application, the construction of the CIM knowledge graph requires expanding the concepts, entities, and relationships of CIM knowledge based on its own characteristics. It primarily addresses professional issues within the current industry or specific sub-sectors, and thus falls under the category of industry knowledge graphs. Based on the types, characteristics, and logical relationships of CIM knowledge, it can be divided into three levels: the CIM concept layer, the CIM entity layer, and the CIM relationship layer.

[0057] This application provides a method for constructing a knowledge graph for a city information model. This application combines knowledge graph technology with the construction of a city information model (CIM) and proposes for the first time a scheme for constructing a knowledge graph for a city information model (hereinafter referred to as CIM knowledge graph). Based on the actual needs of CIM business, CIM business relationships are added on the basis of the main semantic relationships to integrate semantic relationships and spatial relationships, so as to realize large-scale multi-source heterogeneous data storage management and information retrieval.

[0058] Furthermore, the spatiotemporal knowledge graph proposed in this application allocates the complex computational process in spatial analysis to the preprocessing stage. In the spatial pre-analysis stage, spatial analysis information is preloaded onto the knowledge graph, so that in the actual spatial analysis process, it is only necessary to retrieve the pre-analysis results and extract the target attributes from the graph. This brings the analysis process forward and greatly reduces the waiting time for users in the actual spatial analysis process.

[0059] Furthermore, in traditional CIM data storage, using a spatial database alone to store the above information requires creating separate tables for entities and relationships, resulting in data redundancy. Moreover, multiple table join operations are needed when searching for relationships, consuming query time. This application establishes a CIM knowledge graph to combine knowledge and spatial queries. It uses a spatial database to store geometric figures, a relational database to store attribute data and some structured semantic information, and a graph database to store semantic relationships and extracted spatial relationships.

[0060] Figure 6 This is a schematic diagram illustrating the application scenario of the CIM basic platform provided in the embodiments of this application, such as... Figure 6As shown, in accordance with the overall construction requirements of CIM, the CIM basic platform utilizes existing urban e-government infrastructure resources to support applications in multiple fields such as urban planning, construction, comprehensive management, and social public services, and achieves docking or integration with relevant platforms (systems).

[0061] The CIM basic platform connects to the smart city spatiotemporal big data platform and the land and space basic information platform, and connects to or integrates the functions of the existing engineering construction project business collaboration platform (i.e., the "multi-plan integration" business collaboration platform), integrating and sharing relevant information resources such as spatiotemporal foundation, planning control, and resource survey; the CIM knowledge graph re-integrates data resources through entity relationship storage, cleans and reorganizes data of different sources and specifications, improves data utilization, and increases retrieval efficiency.

[0062] The CIM (City Information Modeling) platform supports applications in urban construction, urban management, urban operation, public services, urban health checks, urban safety, housing, pipelines, transportation, water affairs, planning, natural resources, construction site management, green building, community management, healthcare, and emergency command. It connects with systems such as the engineering construction project approval management system and the integrated online government service platform, and supports the construction and operation of other smart city applications. Based on the CIM knowledge graph, relevant big data mining algorithms, including classification and clustering methods, and graph computation methods, including graph traversal, shortest path, pathfinding, authoritative node analysis, group analysis, and similar node discovery, can be used to achieve functions such as CIM entity association analysis and event clustering analysis. This enables the analysis and mining of relationships between people, environments, and events that are discretely distributed in time and space, thereby providing services for relevant decision-making.

[0063] 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 of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0064] Figure 7 This is a schematic diagram of the urban information model knowledge graph construction device provided in the embodiments of this application, such as... Figure 7 As shown, this application provides a device for constructing a knowledge graph of an urban information model, the device comprising: Concept classification module 11 is set up to construct conceptual knowledge as a standard for summarizing or classifying specific CIM entities; Entity building module 12 is configured to convert discrete CIM data into concrete objects based on conceptual knowledge; The relation extraction module 13 is configured to extract relation information from various objects through knowledge extraction, relation linking, and relation reasoning processes. The knowledge fusion module 14 is configured to adopt a top-down construction approach, quantifying CIM knowledge into CIM concept layer, CIM entity layer and CIM relationship layer to obtain CIM knowledge graph.

[0065] Regarding the limitations on the urban information model knowledge graph construction device, please refer to the limitations on the urban information model knowledge graph construction method in the above embodiments of this application, which will not be repeated here.

[0066] Figure 8 Another schematic diagram of the urban information model knowledge graph construction device provided in the embodiments of this application is shown below. Figure 8 As shown, the device includes a memory 22 and a processor 21. The memory stores a computer program, and the processor is configured to run the computer program to perform the methods described in the above embodiments of this application.

[0067] The memory is connected to the processor. The memory can be flash memory, read-only memory or other types of memory. The processor can be a central processing unit or a microcontroller.

[0068] In some embodiments, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described in the above embodiments of this application.

[0069] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, computer program modules or other data. Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), DVD or other optical disc storage, cartridges, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer.

[0070] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this application, and this application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this application, and these modifications and improvements are also considered to be within the scope of protection of this application.

Claims

1. A method for constructing a knowledge graph for a city information model, characterized in that, Applied to City Information Modeling (CIM), the method includes: S1. CIM Concept Classification System: Constructing conceptual knowledge as a standard for summarizing or classifying specific CIM entities; S2, CIM Entity Construction: Converting discrete CIM data into concrete objects based on conceptual knowledge; S3, CIM Relation Extraction: The process of extracting relational information from various objects through knowledge extraction, relation linking, and relational reasoning; S4. CIM Knowledge Integration: Adopting a top-down construction approach, CIM knowledge is quantified into CIM concept layer, CIM entity layer and CIM relationship layer to obtain CIM knowledge graph.

2. The method for constructing a knowledge graph for a city information model according to claim 1, characterized in that, S1 includes: CIM data is categorized into five dimensions: results, processes, resources, attributes, and applications. Based on data sources, it can be divided into spatiotemporal basic data, resource survey data, planning and control data, engineering construction project data, public thematic data, and IoT sensing data.

3. The method for constructing a knowledge graph for a city information model according to claim 1, characterized in that, In S2, a CIM entity includes at least one of time, space, attribute, behavior, state, and process.

4. The method for constructing a knowledge graph for a city information model according to claim 1, characterized in that, In S3, the CIM relationship includes temporal relationship, spatial relationship and semantic relationship; Among them, time relationship is mainly used to describe various geographical phenomena with obvious time-varying characteristics; Spatial relationships refer to the relationships between geographic spatial instances that are related to spatial characteristics; Semantic relations are used to describe the semantic relationships between concepts, between concepts and instances, and between instances.

5. The method for constructing a knowledge graph for a city information model according to claim 4, characterized in that, Formal descriptions of temporal relationships include: Time-varying relationships between events and processes in CIM entities; Changes in the temporal attribute values ​​of spatial information.

6. The method for constructing a knowledge graph for a city information model according to claim 4, characterized in that, Spatial relationships mainly include topological relationships, distance relationships, and orientational relationships.

7. The method for constructing a knowledge graph for a city information model according to claim 1, characterized in that, S4 includes: Geographic knowledge is integrated based on concepts, entities, characteristics, and relationships; By utilizing instance alignment, attribute fusion, and relationship matching methods, instances, their attributes, and relationships extracted from multi-source multimodal corpora are aligned and fused based on multidimensional similarity. For spatial data fusion involved in CIM, the association between attributes and entities is established by using element coding and object tagging, thereby achieving data fusion.

8. A device for constructing a knowledge graph for a city information model, characterized in that, The device includes: The concept classification module is designed to construct conceptual knowledge as a standard for summarizing or classifying specific CIM entities; The entity building module is configured to convert discrete CIM data into concrete objects based on conceptual knowledge. The relation extraction module is designed to extract relation information from various objects through knowledge extraction, relation linking, and relation reasoning processes. The knowledge fusion module is designed to use a top-down construction approach, quantifying CIM knowledge into CIM concept layer, CIM entity layer and CIM relationship layer to obtain a CIM knowledge graph.

9. A device for constructing a knowledge graph for a city information model, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to implement the urban information model knowledge graph construction method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the urban information model knowledge graph construction method as described in any one of claims 1-7.

Images