Space-time knowledge graph construction method based on large language model and Beidou grid coding

Abstract

The invention discloses a space-time mapping knowledge domain construction method based on a large language model and Beidou grid coding. The method comprises the steps that semantic partitioning is conducted on an input text through the large language model LLM, fact declarative sentence extraction is conducted on each block, and triple extraction, time entity extraction and space geographic entity extraction are conducted on the fact declarative sentences respectively; performing time attribute coding on the time entity; constructing a gridded Beidou satellite geographic map and obtaining a Beidou grid coding data set, and performing associated grid matching coding on spatial geographic entities to form corresponding spatial attributes; and collecting the time entity containing the time attribute, the space geographic entity containing the space attribute and the triple to construct the space-time knowledge graph. According to the method, attribute coding is carried out on the time entities and the space geographic entities, the coded time entities, the coded space geographic entities and the triple are collected and constructed to obtain the space-time knowledge graph, space-time information in the entities can be deeply mined, and the space-time reasoning capability is improved.

Description

Technical Field

[0001] This invention relates to the field of spatiotemporal knowledge graph technology in artificial intelligence and big data processing, and in particular to a method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding. Background Technology

[0002] With the rapid development of artificial intelligence and big data technologies, knowledge graphs, as a core technology for integrating data and semantic relationships, have been widely applied in fields such as smart transportation, urban governance, and environmental monitoring. Knowledge graphs are an information extraction technology that extracts important entities and relationships from massive amounts of information and constructs a connected graph network structure. Because of their ability to mine deep-level relational information and understand global semantics, the application of knowledge graphs significantly improves the accuracy and reliability of Retrieval-Augmented Generation (RAG) outputs and mitigates problems such as knowledge obsolescence and illusion generation in Large Language Models (LLMs). Traditional knowledge graph technology has two main shortcomings: First, the construction process (from unstructured text) relies heavily on traditional Natural Language Processing (NLP) methods, which cannot effectively parse vague descriptions such as "upper and middle reaches of the Yangtze River," "emergency stations near science parks," and "post-flood season river inspections." For example, the vague description of "upper and middle reaches of the Yangtze River" includes the upper reaches (specifically, the section of the Yangtze River from the southwest side of Geladandong Peak in the Tanggula Mountains of the Qinghai-Tibet Plateau to Yichang, Hubei) and the middle reaches (specifically, the section of the Yangtze River from Yichang, Hubei to Hukou, Jiangxi). Second, it primarily represents static knowledge and cannot effectively perceive dynamic changes in time and space, lacking the spatiotemporal semantic understanding capabilities required for real-world business scenarios. For instance, with the vague description of "upper and middle reaches of the Yangtze River," NLP can only identify the semantics and cannot delve into the spatial dimension for deeper understanding and recognition.

[0003] In recent years, spatio-temporal knowledge graphs (STGraphs) technology has emerged. Research shows that constructing STGraphs with spatio-temporal features can enhance spatio-temporal semantic understanding and enable complex spatio-temporal reasoning (such as predicting the future spatial distribution of entities and tracing temporal relationships), providing direct decision-making support for scenario-based business. However, traditional STGraphs have two shortcomings in terms of technology implementation and business adaptation: First, their spatio-temporal reasoning capabilities are weak and their generalization is poor. Traditional STGraphs are mostly limited to simple temporal relationships (such as "event A occurs after event B") or spatial proximity judgments (such as "location C is close to location D"), lacking in-depth mining of complex spatio-temporal dependencies across scales (such as "city-level planning and street-level management") and scenarios (such as "daily monitoring and emergency dispatch"). Moreover, existing STGraphs mostly rely on fixed rule designs or training on specific datasets, resulting in significantly insufficient model adaptability and generalization when facing dynamically changing actual business needs (such as resource dispatch scenarios after sudden disasters). Second, their spatial identifiers are inconsistent and their entity adaptability is poor. On the one hand, traditional spatiotemporal knowledge graphs have not introduced a unified spatial identification standard and lack unified spatial specifications. The spatial identification formats of different data sources are different, which easily leads to problems such as coordinate conflicts, duplicate annotations, and difficulty in data fusion when connecting multi-source data. On the other hand, it is difficult to achieve multi-scale adaptation for different types of geographic entities such as points (such as a single monitoring device), lines (such as roads and rivers), and areas (such as administrative regions and lakes). In particular, it cannot accurately describe the spatial range and relationships of irregularly shaped geographic entities such as rivers and complex administrative regions.

[0004] Furthermore, BeiDou grid coding (GB / T 39409-2020), as a globally unified spatial identification standard, possesses characteristics such as multi-scale three-dimensional coding, high-efficiency computing, and cross-system compatibility. It has been successfully applied in scenarios such as low-altitude economy and emergency command, enabling seamless integration and rapid indexing of multi-source heterogeneous data. Current technologies have not yet systematically integrated it into the entity definition and relationship construction processes of spatiotemporal knowledge graphs, nor have they leveraged the multi-scale coding characteristics of BeiDou grids to solve the problem of accurate representation of irregular geographical entities. At the same time, some spatiotemporal knowledge graph construction methods still rely on large amounts of manually labeled data or specialized model training, resulting in high costs, technical barriers, and long cycles. This makes it difficult to adapt to the needs of small and medium-sized enterprises and rapid application in multiple scenarios, limiting the promotion and application of spatiotemporal knowledge graphs in a wider range of fields. Summary of the Invention

[0005] The purpose of this invention is to provide a method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding. It creatively integrates the standardized spatial representation advantages of BeiDou grid coding with the structured information extraction capabilities of a large language model. The large language model performs semantic segmentation and factual statement extraction on the text, then extracts triples, temporal entities, and spatial geographic entities from the factual statements. Attribute encoding is then applied to the temporal and spatial geographic entities, and the encoded temporal entities, spatial geographic entities, and triples are combined to construct a spatiotemporal knowledge graph. This method addresses the core pain points of traditional knowledge graphs, such as inconsistent spatial benchmarks, inefficient multi-source data fusion, insufficient accuracy in representing irregular geographic entities, inadequate spatiotemporal semantic reasoning capabilities, and reliance on manual annotation or model training.

[0006] The objective of this invention is achieved through the following technical solution: A method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding, the method comprising: S1. Use the Large Language Model (LLM) to semantically segment the input text, extract factual statements from each segment, and extract triples, temporal entities, and spatial geographic entities from each factual statement. Triples contain entities and entity relationships.

[0007] S2. Encode the time attributes of time entities; construct a gridded BeiDou satellite geographic map, and form a BeiDou grid coding dataset by matching the geographic codes of all grids in the BeiDou satellite geographic map. Use the BeiDou grid coding dataset to perform associated grid matching coding of spatial geographic entities to form their corresponding spatial attributes.

[0008] S3. Combine time entities with time attributes, spatial geographic entities with spatial attributes, and triples to construct a spatiotemporal knowledge graph.

[0009] To better achieve the present invention, the present invention also includes the following methods: S4. Associate all time entities in all blocks according to their time attribute codes, and spatially associate all spatial geographic entities in all blocks based on the BeiDou satellite geographic map.

[0010] Preferably, in method S1, a statement extraction is performed on the blocks, and the statements are extracted from the blocks. The function extracts a set of atomic fact statements. The expression is as follows: ,in For large language models, For semantic segmentation, To extract prompt words.

[0011] Preferably, time entity The encoding time attribute expression is as follows: , For entities Unique identifier Represents entity description information, For time type, , These represent the time start boundary, respectively.

[0012] Preferably, in method S2, the spatial attribute expression of the spatial geographic entity is as follows: ,in For entities Unique identifier Represents entity description information, It is a spatial geographic type. This refers to the geographic coordinates (latitude, longitude, and altitude) corresponding to the entity. and These represent the BeiDou grid coding set and BeiDou grid level corresponding to spatial geographic entities, respectively.

[0013] Preferably, method S2 further includes the following method: S21, Through Functions retrieve a set of spatially or geographically related geographic locations. ;pass Function to determine and obtain spatial geographic location Spatial geographic types, BeiDou grid levels; obtaining spatial geographic locations The corresponding latitude, longitude and altitude data are combined with the BeiDou grid hierarchy to perform corresponding encoding of the BeiDou grid encoding set; S22, Constructing a spatial geographic location As a parent node, spatial geographic entity Spatial geographic association is performed as a child node.

[0014] Preferably, the grid in the BeiDou satellite geographic map is divided into hierarchical levels based on spatial location resolution, and the BeiDou grid coded dataset is correspondingly divided into BeiDou grid levels belonging to different scales.

[0015] Preferably, a large language model (LLM) is used to perform spatial geographic location and / or spatial geographic entity spatial geographic association, which includes spatial attribute association and semantic association.

[0016] Preferably, the spatial geographic location and spatial geographic entity include spatial geographic information of spatial geographic type, including points, lines and areas. A point represents a spatial geographic location point, a line represents a linear set of spatial geographic location points, and an area represents a planar set of spatial geographic location points.

[0017] Compared with the prior art, the present invention has the following advantages and beneficial effects: (1) This invention creatively integrates the advantages of standardized spatial representation of Beidou grid coding with the structured information extraction capability of large language model. The large language model performs semantic segmentation and factual statement extraction on the text. Then, it extracts triples, time entities and spatial geographic entities from the factual statements. The time entities and spatial geographic entities are respectively attribute-encoded. The encoded time entities, spatial geographic entities and triples are collected to construct a spatiotemporal knowledge graph. It solves the core pain points of traditional knowledge graphs, such as inconsistent spatial benchmarks, inefficient multi-source data fusion, insufficient accuracy of irregular geographic entity representation, insufficient spatiotemporal semantic reasoning ability, and reliance on manual annotation or model training.

[0018] (2) The method of the present invention realizes the accurate definition and adaptation of spatial geographic entities of various forms such as points, lines and surfaces (including irregular shapes), and solves the problems of coordinate conflict, repeated labeling and difficulty in data fusion of existing knowledge graphs; it realizes fuzzy spatiotemporal association, cross-scale grid adaptation and semantic alignment of multi-source data, and solves the problem that traditional methods cannot support the association and reasoning of Beidou grid and complex spatiotemporal entities. Attached Figure Description

[0019] Figure 1 This is a flowchart of the spatiotemporal knowledge graph construction method of the present invention; Figure 2 This is a flowchart illustrating the method principle of constructing a spatiotemporal knowledge graph in the embodiment. Figure 3 This is a schematic diagram illustrating the principle of spatial geographic entity extraction and spatial attribute encoding using a river as an example in the embodiment. Detailed Implementation

[0020] The present invention will be further described in detail below with reference to embodiments: Example like Figure 1 As shown, a method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding is presented, the method comprising: S1. Use a Large Language Model (LLM) to semantically segment the input text, and extract factual statements from each segment, such as... Figure 2 As shown, factual statements are extracted into triples, temporal entities, and spatial geographic entities, with triples containing entities and entity relationships. In some embodiments, a Large Language Model (LLM) (which leverages contextual understanding and few-shot learning capabilities to automatically perform complex semantic understanding and reasoning) performs semantic chunking on the input text. (chunk) performs statement extraction, using... The function extracts a set of atomic fact statements. For the set of factual statements The expression is as follows: ,in For large language models, For semantic segmentation, To extract prompt words; The function transforms natural language (unstructured text) into reasonable, structured, independent statements. A triple contains entities (including a head entity and a tail entity) and relationships between entities (i.e., the relationship between the head and tail entities). ,in, This is a collection of head entities. A set of relations; This is a collection of tail entities. and Together they form a graph triplet structure. This is a template for extracting prompts from triples. This is a function driven by a large language model (LLM) that outputs structured target content. , where the function This refers to the process of extracting target triples by leveraging the analytical reasoning capabilities of Large Language Modeling (LLM). This refers to the entity resolution process, which involves eliminating and merging entities with similar or recurring meanings. Large Language Modeling (LLM) addresses temporal entities in factual statements. The extraction process focuses on extracting time-related information, and the output is a set of time-related entities. The Large Language Model (LLM) extracts spatial entities from factual statements. Extraction focuses on extracting spatially relevant information, and the output is a collection of spatial entities.

[0021] S2. Encode the time attribute of the time entity, such as... Figure 2 As shown, assume the set of time entities output by the Large Language Model (LLM) is... Using a specific time entity from the set of time entities This section uses an example to introduce time attribute encoding. In some embodiments, time entities... The time attribute expression encoded for a specific time entity in the time entity set is as follows: , For entities Unique identifier Represents entity description information, For time type, , These represent the time start boundary ( Indicates the start time. (Indicates the end time). Time type , ,in To describe a single time event (an event biased towards a specific point in time), such as "being appointed" or "happening". For the time type of a persistent state, associate the start time. With end time If the current period is ongoing, then the end time is... It can be recorded as continuous or infinite. For example, a continuous state is when someone started “serving” as a leader and has been in that position ever since. This indicates a state with no clear time association (leaning towards unrelated time information). Generally, the start time... With end time It can be recorded as None.

[0022] Time Entity Set The extraction expression is as follows: , Enter a declarative sentence; Will be All time entities Extract and populate unique identifiers Description content Time type Time start and Information such as; It is a function for detecting and validating time conflicts between old and new languages ​​based on a large language model; Extract prompt words for time entities.

[0023] A gridded BeiDou satellite geographic map is constructed, and all grids in the BeiDou satellite geographic map correspond to geocoding to form a BeiDou grid-coded dataset. Preferably, the grids in the BeiDou satellite geographic map are hierarchically divided according to spatial location resolution, and the BeiDou grid-coded dataset is correspondingly divided into BeiDou grid levels belonging to different scales. The BeiDou grid-coded dataset is used to perform grid-matching encoding on spatial geographic entities to form their corresponding spatial attributes, such as... Figure 2 As shown, assume that the set of spatial geographic entities output by the Large Language Model (LLM) is... Using a specific time entity within a set of spatial geographic entities This section uses an example to introduce spatial attribute encoding. In some embodiments, spatial geographic entities... The spatial attribute expressions are as follows: ,in For entities Unique identifier Represents entity description information, It is a spatial geographic type. , ,like Refers to the location or coordinates of a specific point; Linear locations (length), such as rivers, streets, etc. This refers to a geographical location, such as an administrative district or a lake. This refers to the geographic coordinates (latitude, longitude, and altitude) corresponding to the entity. and These represent the BeiDou grid coding set and BeiDou grid level corresponding to spatial geographic entities, respectively. , For the BeiDou Navigation Satellite System.

[0024] The present invention further includes the following method in method S2: S21, Through Functions retrieve a set of spatially or geographically related geographic locations. ;pass Function to determine and obtain spatial geographic location Spatial geographic types, BeiDou grid levels; , Enter a declarative sentence; Extract prompts for geographic locations (names) by... Function to determine geographical location Corresponding Type and BeiDou grid level , , The system provides prompts for spatial geographic types and BeiDou grid levels. Leveraging the inherent pre-training knowledge of LLM, it autonomously completes the process of determining... of Type determination (e.g., "Temple of Heaven" corresponding to a single landmark) Type, "Nanjing Road" corresponding linear channel Type, corresponding area of ​​"Qinghai Lake" Type). Secondly, based on Type, semantic features (e.g., "city-level main roads" need to be adapted to a coarser grid level, "street-level monitoring points" need to be adapted to a finer grid level), and Few-shots mesh adaptation example, intelligent estimation BeiDou grid hierarchy Furthermore, for complex and irregularly shaped geographical entities (such as "inter-provincial rivers"), this invention evaluates reasonable [measures] based on entity size, application scenario, and implicit requirements (derived through context). value.

[0025] Obtaining spatial geolocation The corresponding latitude, longitude, and altitude data are combined with the BeiDou grid hierarchy to perform corresponding encoding of the BeiDou grid coding set. Spatial geographic location is then obtained. Corresponding latitude, longitude, and altitude data (set) ,according to As can be seen from the definition, Type-based geographic locations are treated as a point or a single entity, therefore requiring only a single coordinate point for representation; while and Geographical locations of different types need to be represented by a "set of coordinate points" due to their length and area. For example... Figure 3 As shown in the three smaller images a, b, and c, a single coordinate point cannot completely represent the entire river; therefore, it is necessary to follow... The hierarchical distribution of the BeiDou grid evenly samples multiple coordinate points passing through the river and converges them into a coordinate point set to represent the irregular river morphology. Similarly, The type of geographic location should retrieve the set of coordinate points passing through its boundary contour and within the contour. Query or retrieve... Data can also be obtained in two other ways: first, by using data query and boundary extraction tools on a GIS (Geographic Information System) platform; and second, through geocoding APIs provided by various map service providers.

[0026] Get Beidou grid coding set . In the known of and In this case, the mapping method from latitude and longitude coordinates to BeiDou two-dimensional (or three-dimensional) grid location codes. This invention is carried out with reference to the method disclosed in Appendix B of the national standard "BeiDou Grid Location Code" (GB / T 39409-2020) (this standard was published on November 19, 2020 and implemented on June 1, 2021).

[0027] The spatial geographic entities in this embodiment can also be encoded using the encoding method in method S21.

[0028] S22, Constructing a spatial geographic location As a parent node, spatial geographic entity Spatial geographic association is performed as a child node. For example... Figure 3 The small diagram in the middle shows all of them. Create complete spatial geographic entity nodes (Each node corresponds to a BeiDou grid), and the results of the above steps are sequentially filled into its corresponding attributes to complete the spatial geographic entity set. The extraction. Secondly, to better organize subsequent queries. Information, new representative The entity node (parent node), and all its corresponding entities Connected (child nodes). The node will be responsible for recording geographic summary information, Index information, supplementary explanations, etc. The Large Language Model (LLM) is used to perform spatial geographic location and / or spatial geographic entity spatial geographic association, which includes spatial attribute association and semantic association. This embodiment can also utilize the Large Language Model (LLM) for each geographic location. Generate a Spatial Community Report based on the Ledian algorithm, integrating related entity, relationship and attribute data, and additionally summarizing information related to "spatial distribution" and "geographical range", providing a concise and intuitive reference for subsequent scenario-based decision-making and in-depth insights.

[0029] In some embodiments, spatial geographic locations and spatial geographic entities include spatial geographic information of spatial geographic types such as points, lines, and areas. A point represents a spatial geographic location point, a line represents a linear set of spatial geographic location points, and an area represents a planar set of spatial geographic location points.

[0030] S3. Combine time entities with time attributes and spatial geographic entities with spatial attributes with triples to construct a spatiotemporal knowledge graph. All spatiotemporal knowledge graphs constitute a spatiotemporal knowledge graph set. Its expression is as follows: , For a set of triples, A collection of time entities that contain time attributes. It is a collection of spatial geographic entities that includes spatial attributes (including grid matching coding information), relationships, and hierarchical relationships.

[0031] S4. All time entities in the blocks are sequentially associated according to their time attribute codes, and all spatial geographic entities in the blocks are spatially associated based on the BeiDou satellite geographic map. This embodiment relies on BeiDou grid coding to structurally represent different forms of spatial geographic entities in spatial geographic latitude. After the spatiotemporal knowledge graph is constructed, the geographic entities represented by the grid decomposition possess natural independence and geographic matching. Therefore, when data changes, this embodiment only needs to dynamically and incrementally update the information of the "part" of grid nodes corresponding to the "new data," without needing to fully reconstruct the entire spatial geographic entity, ensuring the efficiency and accuracy of the graph update. For example, the information "A new purified water plant is being built upstream of River A" has a clear geographic orientation (specifically referring to the upstream area). In this invention, only the entity data in the "upstream part" of the geographic entity associated with River A needs to be focused on and updated, recording "new purified water plant." Similarly, for the information "The green area of ​​Administrative Region B has increased by 10% compared to last year," only the green area data in the geographic entity referring to the part of Administrative Region B needs to be updated.

[0032] This invention, through the deep fusion of BeiDou grid coding and a large language model, constructs a spatiotemporal knowledge graph without annotations or model training. It achieves multiple optimizations in terms of technical practicality and application value. Regarding improvements in spatial accuracy and fusion efficiency: relying on the globally unified spatial benchmark of BeiDou grid coding, it achieves precise definition and multi-scale adaptation of various types of geographic entities (points, lines, and surfaces), effectively solving the problems of inconsistent spatial benchmarks and difficulty in compatibility with multi-source data in traditional spatiotemporal maps. Regarding enhanced complex spatiotemporal semantic understanding and reasoning: the large language model successfully parses fuzzy spatiotemporal descriptions and implicit temporal relationships that traditional NLP cannot handle, achieving an accuracy rate of over 85% for fuzzy spatial entity extraction and improving cross-scale grid adaptation generalization ability by over 60%, providing semantic understanding support for the practical application of BeiDou grid coding. Regarding reduced construction costs and lower technical barriers to implementation: The structured information extraction capabilities based on large language models eliminate the need for additional manual data annotation or specialized model training, simplifying the map construction process. Actual project verification shows that the implementation cycle is shortened by more than 50% compared to traditional solutions. The low-investment, high-efficiency characteristics lower the entry barrier for SMEs, enabling rapid adaptation to application needs in various fields such as smart transportation, urban governance, and environmental monitoring. Regarding enhanced data reliability and decision support value: The time conflict detection mechanism and spatial standardization coding effectively filter redundant and contradictory data. Actual testing shows that the map data accuracy exceeds 95%. The multi-scale adaptability meets the business decision-making needs of different granularities, effectively improving the scientific and rational nature of decisions in scenarios such as emergency route planning, resource scheduling, and urban management.

[0033] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding, characterized in that: The methods include: S1. Use the Large Language Model (LLM) to semantically segment the input text, extract factual statements from each segment, and extract triples, temporal entities, and spatial geographic entities from the factual statements. Triples contain entities and entity relationships. S2. Encode time attributes for time entities; construct a gridded BeiDou satellite geographic map, and form a BeiDou grid coding dataset by matching the geographic codes of all grids in the BeiDou satellite geographic map with the associated grids. Use the BeiDou grid coding dataset to perform grid matching coding on spatial geographic entities to form the corresponding spatial attributes. S3. Combine time entities with time attributes, spatial geographic entities with spatial attributes, and triples to construct a spatiotemporal knowledge graph.

2. The spatiotemporal knowledge graph construction method based on a large language model and BeiDou grid coding as described in claim 1, characterized in that: It also includes the following methods: S4. Associate all time entities in all blocks according to their time attribute codes, and spatially associate all spatial geographic entities in all blocks based on the BeiDou satellite geographic map.

3. The method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding as described in claim 1, characterized in that: In method S1, statements are extracted from the blocks, and the statements are extracted from the blocks. The function extracts a set of atomic fact statements. The expression is as follows: ,in For large language models, For semantic segmentation, To extract prompt words.

4. The method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding as described in claim 1, characterized in that: Time Entity The encoding time attribute expression is as follows: , For entities Unique identifier Represents entity description information, For time type, , These represent the time start boundary, respectively.

5. The spatiotemporal knowledge graph construction method based on a large language model and BeiDou grid coding as described in claim 1, characterized in that: In method S2, the spatial attribute expressions of spatial geographic entities are as follows: ,in For entities Unique identifier Represents entity description information, It is a spatial geographic type. This refers to the geographic coordinates (latitude, longitude, and altitude) corresponding to the entity. and These represent the BeiDou grid coding set and BeiDou grid level corresponding to spatial geographic entities, respectively.

6. The method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding as described in claim 1 or 5, characterized in that: Method S2 also includes the following methods: S21, Through Functions retrieve a set of spatially or geographically related geographic locations. ;pass Function to determine and obtain spatial geographic location Spatial geographic types and BeiDou grid hierarchy; obtaining spatial geographic locations The corresponding latitude, longitude and altitude data are combined with the BeiDou grid hierarchy to perform corresponding encoding of the BeiDou grid encoding set; S22, Constructing a spatial geographic location As a parent node, spatial geographic entity Spatial geographic association is performed as a child node.

7. The spatiotemporal knowledge graph construction method based on a large language model and BeiDou grid coding as described in claim 1, characterized in that: The grid in the BeiDou satellite geographic map is divided into hierarchical levels based on spatial location resolution, and the BeiDou grid coding dataset is correspondingly divided into BeiDou grid levels belonging to different scales.

8. The method for constructing a spatiotemporal knowledge graph based on a large language model and BeiDou grid coding as described in claim 6, characterized in that: Large Language Model (LLM) is used to perform spatial geographic location and / or spatial geographic entity spatial geographic association, which includes spatial attribute association and semantic association.

9. The spatiotemporal knowledge graph construction method based on a large language model and BeiDou grid coding as described in claim 6, characterized in that: The spatial geographic locations and spatial geographic entities include spatial geographic information of types such as points, lines, and areas. A point represents a spatial geographic location point, a line represents a linear set of spatial geographic location points, and an area represents a planar set of spatial geographic location points.

Images