Spatial relationship knowledge graph data model construction method, device and query method

Abstract

The application provides a knowledge graph data model construction method and device of spatial relationship and a query method. The knowledge graph data model construction method of spatial relationship comprises: assigning a profiled grid code and a time profiled code to space-time data; performing grid modeling on the space-time data loaded in the profiled grid, and extracting space-time entities in the space-time data; introducing the space-time entities into a pre-constructed logical entity knowledge base; and on the basis of the logical entity knowledge base, establishing spatial relationships among the space-time entities through calculation of the profiled grid code, so as to obtain a grid space-time knowledge graph. Through loading the space-time data in the profiled grid and expressing geographic space node multi-source heterogeneous data through the profiled grid, the purpose of supporting efficient expression of the geographic space node multi-source heterogeneous data and providing space-time object storage, retrieval, reasoning, calculation and management is achieved.

Description

Technical Field

[0001] This invention belongs to the field of knowledge graph technology, and in particular relates to a method, apparatus and query method for constructing a knowledge graph data model of spatial relationships. Background Technology

[0002] Spatiotemporal knowledge graphs are extensions of knowledge graphs in time and space, serving as structured spatiotemporal information knowledge bases. They are network-like knowledge structures formed by describing concepts, entities, attributes, and their interrelationships within the geographic spatiotemporal information domain. The core of spatiotemporal knowledge graphs is the effective organization of geographic spatiotemporal information and knowledge, forming a spatiotemporal knowledge network. Through spatiotemporal computing models and natural semantic models, they enable the storage, retrieval, reasoning, computation, and management of spatiotemporal information and knowledge. This allows for semantic search, spatiotemporal computation, spatiotemporal knowledge recommendation, and association analysis, thereby providing the capability for large-scale real-time association, intelligent question answering, and reasoning analysis of geographically and temporally dispersed people, environments, and events.

[0003] Current research on spatiotemporal knowledge graphs mainly includes two aspects: the application of semantic networks in spatiotemporal scenarios and spatiotemporal knowledge graphs based on object-oriented GIS enhancement.

[0004] The application of semantic networks in spatiotemporal scenarios mainly leverages the traditional attributes of knowledge graphs to construct semantic network models describing spatiotemporal objects. Natural language-based semantic models utilize the traditional attributes of knowledge graphs to construct semantic and natural language models to describe spatiotemporal objects. Specifically, this involves aligning and merging knowledge from different sources to form globally unified knowledge identifiers and associations, thus addressing the heterogeneity problem of knowledge graphs. In the field of geographic information, the application of knowledge graphs has emerged to address the diversity and heterogeneity of massive geospatial data. A common development approach utilizes geographic data and knowledge contributed by numerous volunteers on network platforms to extract various types of geographic entities, storing them as a general geographic knowledge graph in the triple (entity, relation, entity) format of the Resource Description Framework (RDF). This method lacks modeling of temporal and spatial features, focuses on logical reasoning, and cannot perform real-time spatial computation. The spatial relationship patterns obtained through logical reasoning are limited, and semantically described spatial relationships are insufficient to meet the needs of complex spatial question answering and computation. Furthermore, traditional knowledge graph spatiotemporal descriptions lack uniqueness, and limited associations make complex spatiotemporal reasoning difficult. The purpose of geographic information spatial analysis is to identify the spatial relationships between geographic entities and related entities. Existing knowledge graphs describe the location of the same island, which may be described using latitude and longitude or by selecting different reference points. Such non-unique spatiotemporal descriptions are difficult to use for complex spatial analysis.

[0005] The spatiotemporal knowledge graph based on object-oriented GIS primarily relies on traditional object-oriented GIS models to organize spatiotemporal objects and perform spatial reasoning. GIS systems are continuous, with an infinite number of relationships, making it difficult to express the relationships between nodes in a knowledge graph. If spatiotemporal relationships are not calculated within the object-oriented GIS system but instead placed entirely into the traditional knowledge graph system—that is, detached from the spatial calculations of the object-oriented GIS system and treating spatiotemporal entities as a system formed by knowledge graph nodes—the relationships between nodes will become infinitely numerous: countless location descriptions, countless distance descriptions, and countless complex spatial relationships. This easily leads to the number of relationships the system needs to maintain exceeding the number of nodes, causing the knowledge graph system to deviate from its conventional use and maintenance scope. A knowledge graph is a knowledge map; the logical relationships between different types of objects need to be expressed on the same map. However, in object-oriented GIS systems, when information is integrated, GIS becomes the smallest map patch, requiring cross-layer calculations using overlays. This thematic map representation method conflicts with the object-identified semantically related representation method of knowledge graphs—they cannot be expressed on a single map. Introducing this into an object-oriented GIS system inevitably leads to cross-system operations and data redundancy. Object-oriented GIS analysis frameworks typically only involve spatial and attribute dimensions, and the description and representation of spatial objects are static. With the development of the geographic information field, dynamically representing spatial objects has become a trend, and the inclusion of the temporal dimension urgently needs to be addressed. Therefore, knowledge graphs with spatiotemporal attributes are a requirement of the new geographic information era and an important development direction for GIS in a broader sense.

[0006] Existing semantic knowledge graphs use "entity-relationship" based data representation, which has stable storage management and reasoning application capabilities for entity and concept nodes and logical relationship knowledge, but they do not support the representation of geographic spatiotemporal nodes (including spatiotemporal entities and time-space data); they do not have efficient spatiotemporal storage, retrieval, reasoning, computation and management capabilities.

[0007] The existing spatiotemporal knowledge graphs, which use entity-oriented GIS models to organize spatial objects, cannot meet the requirements of the big data era for spatiotemporal knowledge graphs to support adaptive expression of spatiotemporal knowledge across the entire domain, support multi-source heterogeneous data and even multimodal data, support collaborative graph evolution, and support dynamic knowledge acquisition through machine mining. Summary of the Invention

[0008] To address the problems existing in the prior art, this invention provides a method, apparatus, and query method for constructing a knowledge graph data model of spatial relationships, which at least partially solves the problem that the prior art cannot support the efficient expression of multi-source heterogeneous data of geospatial nodes.

[0009] In a first aspect, embodiments of this disclosure provide a method for constructing a knowledge graph data model of spatial relationships, including:

[0010] Load spatiotemporal data into a partitioned grid, and assign the spatiotemporal data partitioned grid encoding and temporal partitioning encoding;

[0011] Grid modeling is performed on spatiotemporal data loaded in a partitioned grid, and spatiotemporal entities are extracted from the spatiotemporal data.

[0012] Introduce spatiotemporal entities into a pre-built logical entity knowledge base;

[0013] Based on the logical entity knowledge base, spatial relationships between spatiotemporal entities are established through the calculation of grid-based encoding, thereby obtaining a grid spatiotemporal knowledge graph.

[0014] Optionally, the grid spatiotemporal knowledge graph includes geographic information and multi-source heterogeneous spatiotemporal data; the multi-source heterogeneous spatiotemporal data is converted into standardized time data through spatiotemporal data standardization coding.

[0015] Optionally, the multi-source heterogeneous spatiotemporal data is connected through spatiotemporal data standardization and coding, including:

[0016] Let the universal set of the spatial mesh in the subdivided mesh be... in, Let C represent all grids at level l, and for any two grids C at level l... p(l) C q(l) (p≠q), both have For a spatial entity obj in the spatiotemporal entity, let O(obj) represent the real space it occupies, and let its representation precision correspond to the level l in the grid system. This spatial entity can be described in the partitioned space as a set of several l-level grids.

[0017]

[0018] For the attributes of a grid set, let Attr(·) represent a spatial entity or its expressed attribute, then,

[0019]

[0020] and

[0021] Attr(C (l) ) = Attr(O(C (l) )).

[0022] Optionally, the multi-source heterogeneous spatiotemporal data is connected through spatiotemporal data standardization and coding, including:

[0023] The description of spatiotemporal entities introduces temporal partitioning coding, which directly models the temporal characteristics of spatiotemporal entities and organizes spatial data at different times according to the chronological order and set time intervals.

[0024] The meshing of spatiotemporal entities is described as a three-dimensional set of meshes.

[0025] Optionally, the description of the spatiotemporal entity as a three-dimensional mesh set includes:

[0026] Let obj be a spacetime entity, obj t Represents the spatial state of the spacetime entity at time t, where Representing the entire time domain, the spatiotemporal entity is represented as a set of spatiotemporal grids:

[0027]

[0028] Optionally, the data organization model of the grid spatiotemporal knowledge graph includes:

[0029] The grid-based spatiotemporal knowledge graph organizes and represents data in the form of triples, and introduces spatiotemporal partitioning grids into the graph as nodes. The spatiotemporal partitioning grid is obtained by loading spatiotemporal data into the partitioning grid.

[0030] The data organization model of the grid spatiotemporal knowledge graph includes:

[0031] Knowledge representation, carrying spatiotemporal knowledge, nodes, edges, and attributes in a grid.

[0032] Optionally, the knowledge representation includes representing concepts as classes, and representing the relationship between concepts as subclasses;

[0033] The nodes include entities and meshes;

[0034] The edges include explicit relationships and implicit relationships. Explicit relationships directly represent the spatiotemporal or non-spatiotemporal relationships between entities or classes. Relationships not represented by explicit relationships but obtained through mesh coding algebra are implicit relationships.

[0035] Optionally, spatiotemporal knowledge is carried within the grid, including a representation of the spatiotemporal grid, which comprises space and objects:

[0036]

[0037] Space represents space, GridID represents grid encoding, ObjectID represents object encoding, and TimeID represents time encoding sequence. M, N, and S are all constants.

[0038]

[0039] Object is an object, attribute is an attribute, and m and n are constants.

[0040] Secondly, this disclosure also provides an apparatus for constructing a knowledge graph data model of spatial relationships, comprising:

[0041] The loading module is used to load spatiotemporal data into a partitioned grid and assign partitioned grid encoding and temporal partitioning encoding to the spatiotemporal data.

[0042] The extraction module is used to perform gridded modeling on spatiotemporal data loaded in a mesh, and extract spatiotemporal entities from the spatiotemporal data.

[0043] The module is used to import spatiotemporal entities into a pre-built logical entity knowledge base;

[0044] The construction module is used to establish spatial relationships between spatiotemporal entities based on the logical entity knowledge base through the calculation of grid-based encoding, thereby obtaining a grid spatiotemporal knowledge graph.

[0045] Thirdly, embodiments of this disclosure also provide a query method for a knowledge graph data model based on spatial relationships, including: using a grid spatiotemporal knowledge graph to perform a query based on a selected entity-related grid, wherein the data model of the grid spatiotemporal knowledge graph is constructed by any of the methods described in the first aspect;

[0046] Determine the time attribute of the query grid and return the query results for grids that meet the filtering conditions.

[0047] The spatial relationship knowledge graph data model construction method provided by this invention loads spatiotemporal data into a partitioned grid, and expresses multi-source heterogeneous data of geospatial nodes through the partitioned grid. The grid is a node in the knowledge graph, participates in logical reasoning, and has spatial computing capabilities, thereby achieving the purpose of supporting the efficient expression of multi-source heterogeneous data of geospatial nodes and providing spatiotemporal object storage, retrieval, reasoning, calculation and management. Attached Figure Description

[0048] The above and other objects, features and advantages of this disclosure will become more apparent from the more detailed description of exemplary embodiments of this disclosure taken in conjunction with the accompanying drawings, in which the same reference numerals generally represent the same components.

[0049] Figure 1 A schematic diagram illustrating the conceptual structure of the grid-based spatiotemporal knowledge graph provided in this embodiment of the disclosure;

[0050] Figure 2A principle block diagram for constructing a grid-based spatiotemporal knowledge graph provided in this embodiment of the disclosure;

[0051] Figure 3 This is a schematic diagram of a grid-based spatiotemporal knowledge graph provided in an embodiment of this disclosure;

[0052] Figure 4 A schematic diagram of the attributes of the grid spatiotemporal knowledge graph provided in this embodiment of the disclosure;

[0053] Figure 5 This is a schematic diagram of a grid-based spatiotemporal knowledge graph surrounding entity ship B, provided in an embodiment of this disclosure.

[0054] Figure 6 This is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0055] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0056] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0057] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0058] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The illustrations only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0059] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0060] To overcome key technological challenges such as knowledge extraction based on multi-source heterogeneous data, accurate target recognition under incomplete information, prediction of target group behavior, and the scale and analysis of high-dimensional spatiotemporal changes, and to lay a theoretical and technical foundation for improving spatiotemporal cognitive capabilities, this embodiment proposes a grid-based spatiotemporal knowledge graph. The grid-based spatiotemporal knowledge graph is a specific application of the global partitioned grid system in the field of knowledge graphs. It provides a grid-based management and computational framework for spatiotemporal objects in knowledge graphs and extends the scope of the global partitioned grid's business capabilities. By introducing a spatiotemporal partitioned grid model into the semantic network, it organizes and manages data on nodes with spatiotemporal features and attributes based on the spatiotemporal partitioned grid. Relying on the spatiotemporal representation capabilities and grid algebraic computation capabilities of the spatiotemporal partitioned grid, it achieves "replacing stored spatial information and complex spatial relationships with stored grid encoding," forming a spatiotemporal knowledge network on this basis. This enables more efficient and faster support for spatiotemporal reasoning of the graph and provides fundamental capabilities for graph storage, retrieval, rapid updates, visualization, reasoning, computation, and applications from knowledge graphs to cognitive graphs.

[0061] Figure 1 The diagram illustrates the conceptual structure of a grid-based spatiotemporal knowledge graph. Multi-source, heterogeneous spatiotemporal raw data is standardized and encoded to form a grid-based data model, essentially loading spatiotemporal information into a segmented grid. Combined with entity relationship data, the grid-based spatiotemporal knowledge graph is formed through its data organization model. Based on this knowledge graph, inference, computation, decision, and intent models are designed. These models can output inference and computation results, a spatiotemporal representation of the decision grid, and an intent situational graph. Based on these data and model layers, applications such as comprehensive information retrieval inference, intelligent push of related information, blind spot prediction and completion, trajectory prediction analysis, spatiotemporal knowledge question-and-answer integrated situational fusion analysis, and spatiotemporal knowledge determination can be supported.

[0062] In the study of grid spatiotemporal knowledge graphs, the triplet description framework of grid spatiotemporal knowledge graphs is one of the research focuses.

[0063] In this implementation, the spatiotemporal knowledge graph uses the GeoSOT global spatiotemporal mesh framework to standardize the spatiotemporal modeling and description of spatiotemporal entities and spatiotemporal attributes.

[0064] The method for constructing a knowledge graph data model of spatial relationships disclosed in this embodiment includes:

[0065] Load spatiotemporal data into a partitioned grid, and assign the spatiotemporal data partitioned grid encoding and temporal partitioning encoding;

[0066] Grid modeling is performed on spatiotemporal data loaded in a partitioned grid, and spatiotemporal entities are extracted from the spatiotemporal data.

[0067] Introduce spatiotemporal entities into a pre-built logical entity knowledge base;

[0068] Based on the logical entity knowledge base, spatial relationships between spatiotemporal entities are established through the calculation of grid-based encoding, thereby obtaining a grid spatiotemporal knowledge graph.

[0069] like Figure 2 As shown, the specific steps include: loading spatiotemporal data into an Earth subdivision grid, assigning Earth subdivision grid codes and time subdivision codes to the spatiotemporal data, performing grid-based modeling of the spatiotemporal data, extracting spatiotemporal entities and introducing them into a logical entity knowledge base, and establishing spatial relationships between entities through algebraic calculations of grid codes.

[0070] Based on knowledge graph construction methods, the gridded spatiotemporal knowledge graph includes not only data with ubiquitous geographic information, such as documents, books, and online texts, but also multi-source heterogeneous spatiotemporal data. For multi-source heterogeneous spatiotemporal data, a spatiotemporal gridded data organization method is required.

[0071] Data organization methods for multi-source heterogeneous spatiotemporal data in grid spatiotemporal knowledge graphs:

[0072] Spatially, each GeoSOT-3D mesh has a definite location within the meshing system and can be correlated with a specific area in the real world. GeoSOT spatial meshes can fully represent the location attributes and representation accuracy of spatial entities. The overall concept of GeoSOT meshes is "space-oriented modeling" rather than "object-oriented modeling." Different spatial entities are abstractly represented as a collection of meshes at different scales, based on their location and required representation accuracy. Each mesh in the collection inherits the attributes of the spatial entity at its corresponding location on that mesh.

[0073] Specifically, let the complete set of the spatially partitioned grid (Cell) be... in, Let C represent all grids at level l, and for any two grids C at level l... p(l) C q(l)(p≠q), both have For a spatial entity obj, let O(obj) represent the actual space it occupies, with a precision corresponding to a level l in the grid system. This entity can be described in the partitioned space as a set of several l-level grids.

[0074]

[0075] For the attributes of a grid set, let Attr(·) represent a spatial entity or its expressed attribute, then,

[0076]

[0077] and

[0078] Attr(C (l) ) = Attr(O(C (l) ))

[0079] When modeling spatial entities, different types of mesh sets in the mesh model can be further mapped to the three basic objects of points, lines, and surfaces in the traditional data model.

[0080] For spatial objects with temporal characteristics, GeoSOT-T is based on the assumption that space and time are two mutually orthogonal dimensions. Therefore, GeoSOT-T is introduced to describe spatiotemporal entities, using time encoding to directly model the temporal characteristics of spatiotemporal entities and organizing spatial data at different times according to chronological order and certain time intervals. The meshed description of spatiotemporal objects is essentially a three-dimensional mesh set. Specifically, let obj be a certain spatiotemporal entity, obj t This represents the spatial state of the entity at time t, that is, the subdivision level corresponding to the representation accuracy of the spatial entity at any given time in the spatial grid system. If we represent the entire time domain, then this spatiotemporal entity can be represented as a set of spatiotemporal grids:

[0081]

[0082] Data organization model of grid-based spatiotemporal knowledge graph:

[0083] The grid-based spatiotemporal knowledge graph still organizes and represents data in the form of (node-edge-node) triples. The biggest difference from semantic networks is that it introduces spatiotemporal grids into the graph as nodes, thereby meeting the needs of spatiotemporal standardized modeling and spatiotemporal computation.

[0084] 1) Knowledge representation methods:

[0085] The grid-based spatiotemporal knowledge graph represents concepts as "classes." Relationships between concepts can be represented as "subclasses." For example... Figure 3 As shown, solid circles represent concepts, arrows represent relationships, the outward end of the arrow represents the first element (Subject) of the triple, the inward end represents the predicate (Predicate) of the triple, and the outward end represents the last element (Object) of the triple. Dashed circles represent entities. Relationships between entities can be expressed using triples; for example, "John Smith's father is Jack Smith" can be represented as (John Smith, Father, Jack Smith). Squares represent grids. Dashed lines represent implicit relationships. For example, Grid p and Grid q There is no explicit edge relationship between them, but it can be expressed through relation(Grid). p Grid q The calculation was performed to obtain the result.

[0086] 2) Grids can carry spatiotemporal knowledge:

[0087] The representational basis of spatiotemporal grids:

[0088] Space (Earth) = (Set of grid codes + (Set of object codes + Set of time codes))

[0089]

[0090] Object (point, line, surface, volume) = object ID + mesh code set + attribute set

[0091]

[0092] The properties of a grid, namely the knowledge it carries, can directly answer spatiotemporal questions and perform spatiotemporal calculations. Data, entities, and grids establish logical relationships, enabling direct spatiotemporal question answering—the grid is also a node in a knowledge graph, participating in logical reasoning and inherently possessing spatial computational capabilities.

[0093] 3) Nodes:

[0094] The nodes in the grid spatiotemporal knowledge graph are divided into two types: entities and grids.

[0095] (1) Entity:

[0096] From an ontological perspective, entities can be divided into concepts and instances, which are functionally similar to "classes" and "objects".

[0097] A concept is one of the basic forms of thinking, reflecting the general and essential characteristics of objective things. In the process of human cognition, from perceptual knowledge rising to rational knowledge, the common essential characteristics of the perceived things are abstracted and generalized, becoming an expression of self-cognitive consciousness, which is a concept. For example, "person" does not specifically refer to a certain individual, that is, it does not specifically refer to a certain entity, so it is a class. "American" is also a class.

[0098] An instance is an objectively existing and distinguishable thing. In the grid spatio-temporal knowledge graph, it is considered that any instance may have spatio-temporal characteristics - at what time, the instance has a relationship with what space. For example, "Remote Sensing Building of Peking University" is an instance; "a car with license plate number Beijing A XXXXX" is also an instance.

[0099] (2) Grid:

[0100] The nodes of the grid spatio-temporal knowledge graph can be spatio-temporal subdivision grids. In the design, GeoSOT-3D and GeoSOT-T are used to represent the subdivision codes of spatio-temporal grids respectively. C is used to represent a specific subdivision grid, represented in the form of subdivision grid codes, with the superscript distinguishing the time code (C 时间 ), and the subscript distinguishing the space code (C 空间 ). Spatio-temporal grids of different subdivision scales can all be used as nodes in the grid spatio-temporal knowledge graph. For example, a specific GeoSOT-3D grid on the 15th layer is represented as C i(15) . Spatio-temporal grids can sometimes lack time (a certain fixed object), and sometimes lack space (simply describe a person's birthday); and if you need to describe the time and place of a person's birth, you can directly use a grid without lacking both time and space.

[0101] 4) Edge:

[0102] In the grid spatio-temporal knowledge graph, the nodes are connected by edges to represent the relationships between them. The essence of the relationship is a mapping from one domain to another domain. The edge relationships of the grid spatio-temporal knowledge graph are divided into two types: explicit relationships and implicit relationships.

[0103] Explicit relationship:

[0104] The edges between nodes represent explicit relationships, which are equivalent to the relationships in the semantic network. Explicit relationships can directly represent the spatio-temporal relationships or non-spatio-temporal relationships between entities or classes. For example, "Jack Smith is the father of John Smith" "The Remote Sensing Building of Peking University is in Peking University".

[0105] Implicit relationship:

[0106] The idea behind grid-based spatiotemporal knowledge graphs is to replace complex relation storage with spatiotemporal grid algebraic computation. Therefore, relations that can be obtained through spatiotemporal grid algebraic computation but are not explicitly represented are implicit relations. For example... Figure 3 In the diagram, the dashed lines between the nodes of the mesh represent implicit relationships. For example, C p and C q There is no explicit edge relationship between them, but it can be established through Relation(C p C q The calculations are performed to obtain the results. Computable relationships between grids include: containment, adjacency, separation, distance of XX, angle of XX, etc.

[0107] 5) Attributes:

[0108] The properties of a grid reflect a space-oriented (rather than object-oriented) data organization method—they are both information about the grid and facts related to it. For example, through reasoning, the following facts related to ship B can be derived: at time [time], the water temperature at ship B is 5.5℃, the wind force is 6, and the meaningful wave height is 2.5m. Figure 4 As shown.

[0109] This embodiment also discloses a query method for a knowledge graph data model based on spatial relationships, including: using a grid spatiotemporal knowledge graph to perform a query based on a selected entity-related grid, wherein the data model of the grid spatiotemporal knowledge graph is constructed by the method disclosed in this embodiment;

[0110] Determine the time attribute of the query grid and return the query results for grids that meet the filtering conditions.

[0111] In a specific application scenario, such as Figure 5 As shown, this is a schematic diagram of the spatiotemporal knowledge graph surrounding the entity "Ship B" and an example of reasoning and querying.

[0112] Q1: What is the wind force in the environment where ship B is located at time t1?

[0113] Ship B (entity) is in position at time t1 (Grid), at time t2, is in (Grid). The spatial attributes include "temperature 5.5℃", "significant wave height 2.5m", and "wind force 6", which indicates the ambient temperature, significant wave height, and wind force information of ship B at time t1. The above query selects the grids related to ship B, determines the time attribute of the grids to t1, and returns the wind force of the grids that meet the filtering conditions.

[0114] The construction method disclosed in this embodiment has the following advantages:

[0115] 1) Construct a grid knowledge graph data model to enable the knowledge graph to support the efficient expression of multi-source heterogeneous data of geospatial nodes, and provide support for providing spatiotemporal object storage, retrieval, reasoning, computation and management capabilities.

[0116] 2) The advantages of grids in spatiotemporal knowledge graphs include: (1) Unitization: Heterogeneous data can be integrated through grid regional units, supporting unified management and display of multi-source heterogeneous data across the entire space. This provides a standardized paradigm for spatiotemporal data to enter the graph. (2) Primary keying: Grid encoding is an indexable one-dimensional code, which can be pre-sorted to avoid dynamic sorting overhead and supports rapid retrieval of massive data. At the same time, it naturally meets the requirements of globally unified knowledge identification and association of objects in knowledge graphs. (3) Discretization: Spatial phenomena and targets are discretized into a full spatiotemporal grid index structure, simplifying three-dimensional spatiotemporal calculation and greatly improving performance. The core idea and highlight of grid spatiotemporal knowledge graphs is "only storing codes, not spatial relationships". Spatial relationship reasoning is responded to in real time by grid calculation, thereby improving the spatiotemporal association capability and data fusion capability of traditional knowledge graphs. (4) Parallelization: Spatial blocks are stored in an orderly distribution according to the grid, supporting parallel processing and ensuring large-scale computing efficiency through dynamic resource scheduling. This improves the retrieval and reasoning efficiency of knowledge graphs.

[0117] 3) Grids are the foundation for standardized knowledge graph construction. Traditional knowledge graphs are transformed using spatiotemporal grids. Building upon ontology libraries to standardize relationships between concepts, instances, relationships, entity types, and attributes, the inherent spatiotemporal topological relationships and internal attribute index associations of the data grid itself are added, forming a vast grid relationship network encompassing grids, relationships, attributes, and grid entities. This grid-based standardization and representation of silos of multi-source heterogeneous information—structured, semi-structured, and unstructured—creates a full-spatiotemporal domain knowledge graph. Consistent management and adaptive evolution of the knowledge graph are then performed within the full-spatiotemporal grid, providing a standardized foundation for the construction of "data-information-knowledge" knowledge graphs.

[0118] 4) The grid serves as the foundation for a rapidly evolving, adaptive "living knowledge graph." By inheriting the spatiotemporal framework, vertical aggregation and decomposition of knowledge entity grids, as well as horizontal combination and splitting, can be easily achieved. This significantly accelerates the dynamic updating, spatiotemporal clustering, and automatic reconstruction of the dynamic knowledge graph, making it a "living" graph. After establishing the knowledge graph structure, the learning of entities and relationships, hierarchical concepts, and data patterns is then performed. Finally, a comprehensive method for geographic knowledge alignment and rapid relationship construction reasoning is proposed, and a model framework for semantic search and even intelligent question answering is established based on the learning model.

[0119] This embodiment also discloses a knowledge graph data model construction device for spatial relationships, including:

[0120] The loading module is used to load spatiotemporal data into a partitioned grid and assign partitioned grid encoding and temporal partitioning encoding to the spatiotemporal data.

[0121] The extraction module is used to perform gridded modeling on spatiotemporal data loaded in a mesh, and extract spatiotemporal entities from the spatiotemporal data.

[0122] The module is used to import spatiotemporal entities into a pre-built logical entity knowledge base;

[0123] The construction module is used to establish spatial relationships between spatiotemporal entities based on the logical entity knowledge base through the calculation of grid-based encoding, thereby obtaining a grid spatiotemporal knowledge graph.

[0124] This embodiment also discloses an electronic device, which includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0125] The processor may be a central processing unit (CPU) or other processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of this disclosure, the processor is used to execute computer-readable instructions stored in the memory, causing the electronic device to perform all or part of the steps of the spatial relationship knowledge graph data model construction method of the foregoing embodiments of this disclosure.

[0126] Those skilled in the art will understand that, in order to solve the technical problem of how to achieve a good user experience, this embodiment may also include well-known structures such as communication buses and interfaces, and these well-known structures should also be included within the protection scope of this disclosure.

[0127] like Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. It illustrates a structural schematic diagram suitable for implementing the electronic device in the embodiment of the present disclosure. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0128] like Figure 6As shown, an electronic device may include a processing unit (such as a central processing unit, graphics processing unit, etc.) that can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) or a program loaded from a storage device into random access memory (RAM). The RAM also stores various programs and data required for the operation of the electronic device. The processing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0129] Typically, the following devices can be connected to the I / O interface: input devices, such as sensors or visual information acquisition devices; output devices, such as displays; storage devices, such as magnetic tapes or hard drives; and communication devices. Communication devices allow electronic devices to communicate wirelessly or wiredly with other devices (such as edge computing devices) to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0130] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, all or part of the steps of the spatial relation knowledge graph data model construction method of embodiments of this disclosure are performed.

[0131] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0132] A computer-readable storage medium according to embodiments of the present disclosure stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the spatial relationship knowledge graph data model construction method of the foregoing embodiments of the present disclosure are performed.

[0133] The aforementioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0134] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0135] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0136] In this disclosure, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, devices, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used herein refer to the terms "and / or," and are used interchangeably with them unless the context clearly indicates otherwise. The term "such as" as used herein refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0137] Additionally, as used herein, the “or” used in a list of items beginning with “at least one” indicates a separate list, such that a list of, for example, “at least one of A, B, or C” means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word “exemplary” does not imply that the described example is preferred or better than other examples.

[0138] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0139] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0140] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0141] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for constructing a knowledge graph data model of spatial relationships, characterized in that, include: Load spatiotemporal data into a partitioned grid, and assign the spatiotemporal data partitioned grid encoding and temporal partitioning encoding; Grid modeling is performed on spatiotemporal data loaded in a partitioned grid, and spatiotemporal entities are extracted from the spatiotemporal data. Introduce spatiotemporal entities into a pre-built logical entity knowledge base; Based on the logical entity knowledge base, spatial relationships between spatiotemporal entities are established through the calculation of grid-based encoding, thereby obtaining a grid spatiotemporal knowledge graph; The data organization model of the grid spatiotemporal knowledge graph includes: The grid-based spatiotemporal knowledge graph organizes and represents data in the form of triples, and introduces spatiotemporal partitioning grids into the graph as nodes. The spatiotemporal partitioning grid is obtained by loading spatiotemporal data into the partitioning grid. The data organization model of the grid spatiotemporal knowledge graph includes: Knowledge representation, carrying spatiotemporal knowledge, nodes, edges, and attributes in a grid; The knowledge representation includes representing concepts as classes, and representing the relationship between concepts as subclasses; The nodes include entities and meshes; The edges include explicit relationships and implicit relationships. Explicit relationships directly represent the spatiotemporal or non-spatiotemporal relationships between entities or classes. Relationships not represented by explicit relationships but obtained through mesh coding algebra are implicit relationships.

2. The method for constructing a knowledge graph data model of spatial relationships according to claim 1, characterized in that, The grid spatiotemporal knowledge graph includes geographic information and multi-source heterogeneous spatiotemporal data; The multi-source heterogeneous spatiotemporal data is converted into standardized time data through spatiotemporal data standardization coding.

3. The method for constructing a knowledge graph data model of spatial relationships according to claim 2, characterized in that, The multi-source heterogeneous spatiotemporal data is connected through spatiotemporal data standardization and coding, including: Let the universal set of the spatial mesh in the partitioned mesh be... ,in, Indicates the first All grids at the level, and for the first Any two grids in the hierarchy All have For a certain spatial entity in a spacetime entity ,make It represents the actual space it occupies, and its representation precision corresponds to the level in the mesh system as follows: This spatial entity can be described in the partitioned space as several first-order entities. Collection of hierarchical grids : ， For the properties of the grid set, let If a spatial entity or its expressed attribute is represented, then, ， and 。 4. The method for constructing a knowledge graph data model of spatial relationships according to claim 3, characterized in that, The multi-source heterogeneous spatiotemporal data is connected through spatiotemporal data standardization and coding, including: The description of spatiotemporal entities introduces temporal partitioning coding, which directly models the temporal characteristics of spatiotemporal entities and organizes spatial data at different times according to the chronological order and set time intervals. The meshing of spatiotemporal entities is described as a three-dimensional set of meshes.

5. The method for constructing a knowledge graph data model of spatial relationships according to claim 4, characterized in that, The description of the spatiotemporal entity as a three-dimensional mesh set includes: make As a spacetime entity, express The spatial state of the spacetime entity at that moment, where , Representing the entire time domain, the spatiotemporal entity is represented as a set of spatiotemporal grids: 。 6. The method for constructing a knowledge graph data model of spatial relationships according to claim 1, characterized in that, Spatiotemporal knowledge is carried within the grid, including the representation of the spatiotemporal grid, which comprises space and objects: ， For space, For grid encoding, Encoding objects, It is a time-coded sequence. , and All are constants; ， For objects, The attribute is m, and n are constants.

7. A device for constructing a knowledge graph data model of spatial relationships, characterized in that, include: The loading module is used to load spatiotemporal data into a partitioned grid and assign partitioned grid encoding and temporal partitioning encoding to the spatiotemporal data. The extraction module is used to perform gridded modeling on spatiotemporal data loaded in a mesh, and extract spatiotemporal entities from the spatiotemporal data. The module is used to import spatiotemporal entities into a pre-built logical entity knowledge base; The module is used to establish spatial relationships between spatiotemporal entities based on the logical entity knowledge base through the calculation of grid encoding, thereby obtaining a grid spatiotemporal knowledge graph. The data organization model of the grid spatiotemporal knowledge graph includes: The grid-based spatiotemporal knowledge graph organizes and represents data in the form of triples, and introduces spatiotemporal partitioning grids into the graph as nodes. The spatiotemporal partitioning grid is obtained by loading spatiotemporal data into the partitioning grid. The data organization model of the grid spatiotemporal knowledge graph includes: Knowledge representation, carrying spatiotemporal knowledge, nodes, edges, and attributes in a grid; The knowledge representation includes representing concepts as classes, and representing the relationship between concepts as subclasses; The nodes include entities and meshes; The edges include explicit relationships and implicit relationships. Explicit relationships directly represent the spatiotemporal or non-spatiotemporal relationships between entities or classes. Relationships not represented by explicit relationships but obtained through mesh coding algebra are implicit relationships.

8. A query method for a knowledge graph data model based on spatial relationships, characterized in that, include: Using a grid-based spatiotemporal knowledge graph, queries are performed based on grids related to selected entities, wherein the data model of the grid-based spatiotemporal knowledge graph is constructed by the method described in any one of claims 1-6; Determine the time attribute of the query grid and return the query results for grids that meet the filtering conditions.

Images