Map drawing method, device, equipment and medium based on large language model

Abstract

The embodiments of the present application provide a map drawing method, apparatus, device and medium based on a large language model, and relate to the technical field of map drawing based on a large language model. The method includes: acquiring raster image data and vector road data to establish a geographic spatial reference coordinate system; collecting a positioning information text corpus based on natural language descriptions; building a spatial semantic processing model based on the geographic spatial reference coordinate system and the positioning information text corpus based on a self-attention mechanism; receiving mixed instructions input by a user, and converting the mixed instructions into a structured instruction tree; generating a coordinate set based on the structured instruction tree, and generating a coordinate set scheme after verifying the coordinate set; based on the spatial semantic processing model, plotting the coordinate set scheme as an interactive map; supporting user input of mixed data instructions, parsing complex semantics in natural language, automatically drawing maps, and improving map drawing efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of map drawing based on a large language model, and in particular to a map drawing method, apparatus, device and medium based on a large language model. Background Art

[0002] Mapping is the process of graphically annotating geographic information, target locations, or dynamic events on a map. It is widely used in military, emergency command, transportation planning, resource management, and other fields. Traditional map-making systems suffer from the following technical pain points: existing automated tools only support structured data input, are unable to interpret the complex semantics of natural language, and rely on manual operation for symbol drawing and annotation, resulting in low efficiency. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a map drawing method, device, equipment and medium based on a large language model to solve the problem that existing map drawing methods only support structured data input, cannot parse complex semantics in natural language, and rely on manual operations for symbol drawing and annotation, which is inefficient.

[0004] In a first aspect, an embodiment of the present application provides a map drawing method based on a large language model, the method comprising:

[0005] Obtain raster image data and vector road data to establish a geospatial reference coordinate system;

[0006] Collecting a text corpus of positioning information based on natural language descriptions, wherein the text corpus of positioning information includes place name entities, location descriptions, and spatial relationship expressions;

[0007] Based on the geographic spatial reference coordinate system and positioning information text corpus, a spatial semantic processing model is built based on the self-attention mechanism;

[0008] Receive mixed instructions input by the user and convert the mixed instructions into a structured instruction tree;

[0009] Generate a coordinate set according to the structured instruction tree, and generate a coordinate set solution after verifying the coordinate set;

[0010] Based on the spatial semantic processing model, the coordinate set scheme is plotted as an interactive map.

[0011] In the above implementation process, raster image data and vector road data are obtained to establish a geographic spatial reference coordinate system; a positioning information text corpus based on natural language descriptions is collected, wherein the positioning information text corpus contains place name entities, direction descriptions and spatial relationship expressions; a spatial semantic processing model is built based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus; mixed instructions input by the user are received and converted into a structured instruction tree; a coordinate set is generated according to the structured instruction tree, and after verifying the coordinate set, a coordinate set scheme is generated; based on the spatial semantic processing model, the coordinate set scheme is plotted as an interactive map; supporting user input of mixed data instructions, it can parse complex semantics in natural language, automatically draw maps, and improve map drawing efficiency.

[0012] Furthermore, it also includes:

[0013] Verify the conversion results of the interactive map and process the spatial semantic processing model based on the verification results;

[0014] The verification of the conversion result of the interactive map and processing the spatial semantic processing model according to the verification result include:

[0015] Get the difference between the marked position of the interactive map and the actual measurement value;

[0016] If the difference exceeds the set threshold, the retraining process of the spatial semantic processing model is triggered; the retraining process includes: automatically labeling erroneous samples, adjusting the weight parameters of the spatial decoder, and updating the geographic entity knowledge graph;

[0017] If the difference is less than or equal to the set threshold, the interactive map and spatial semantic processing model are retained.

[0018] In the above implementation process, the interactive map is verified and feedback processed to achieve an adaptive error detection and model update closed loop.

[0019] Furthermore, the acquisition of raster image data and vector road data to establish a geographic spatial reference coordinate system includes:

[0020] Obtain raster image data of the target area through the satellite remote sensing data interface;

[0021] Parse the longitude and latitude coordinate system or access open source geographic information database to obtain vector road network data;

[0022] Convert raster image data and vector road data into data in a unified standard format, and fuse the indexes to form a geographic spatial reference system.

[0023] In the above implementation process, a geographic spatial reference system with a unified standard format is established to facilitate the subsequent establishment of a spatial semantic processing model.

[0024] Furthermore, the spatial semantic processing model is built based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus, including:

[0025] A text encoder is used to process the positioning information text corpus, an image encoder is used to parse the building outlines and road topology features in satellite images, and a spatial decoder is used to generate geometric features in the geographic spatial reference coordinate system;

[0026] The attention mechanism is used to achieve cross-modal feature alignment and obtain a spatial semantic processing model;

[0027] The attention mechanism is used to achieve cross-modal feature alignment, including:

[0028] Establish the mapping relationship between semantic elements in text description and spatial coordinates, and the correspondence between annotation entities and plotted icons;

[0029] Build dynamic spatial reasoning capabilities and optimize spatial reasoning capabilities through user feedback data based on reinforcement learning mechanisms.

[0030] In the above implementation process, a spatial semantic processing model is built based on the self-attention mechanism to automatically draw maps and improve map drawing efficiency.

[0031] Furthermore, the receiving of the mixed instruction input by the user and converting the mixed instruction into a structured instruction tree includes:

[0032] Receiving a mixed instruction input by a user; wherein the mixed instruction includes: text, voice and sketch;

[0033] Identify the spatial operation type, geographic reference, spatial relationship description, and operation object in the instruction;

[0034] Convert mixed instructions into a structured instruction tree.

[0035] In the above implementation process, users are supported to input mixed instruction data, and the complex semantics in the natural language are parsed and converted into a structured instruction tree.

[0036] Furthermore, the generation of the coordinate set according to the structured instruction tree and the generation of the coordinate set solution after verification of the coordinate set include:

[0037] Generate a coordinate set according to a structured instruction tree;

[0038] Verify the validity of geographic entities in a coordinate set based on the geographic spatial reference coordinate system, resolve homonymous and heteronymous issues, and perform conflict detection in conjunction with spatial semantic processing models.

[0039] Generate multiple candidate coordinate set solutions with confidence scores;

[0040] The conflict detection is performed by combining the spatial semantic processing model, including:

[0041] The coordinate set is verified in combination with the spatial semantic processing model. Verifying the map information includes verifying the topological consistency of the newly annotated elements with the existing map elements, detecting the adaptability of the scale, and verifying the rationality of the element distribution.

[0042] In the above implementation process, multiple candidate coordinate set solutions with confidence scores are generated, so that the coordinate set solutions can be screened according to the confidence scores.

[0043] Furthermore, the coordinate set scheme is plotted as an interactive map based on the spatial semantic processing model, including:

[0044] Filter out the coordinate set solutions whose confidence scores are greater than the set score threshold;

[0045] Based on the spatial semantic processing model, the coordinate set scheme is generated into a vector map file that meets the set standards;

[0046] Overlay time dimension information on vector map files;

[0047] Render 3D terrain effects on vector map files through the graphics library, and adjust lighting and material parameters;

[0048] Deploy a differential privacy mechanism for vector map files to obfuscate the annotation information of sensitive areas;

[0049] Get the interactive map.

[0050] In the above implementation process, interactive maps are automatically generated to improve map drawing efficiency.

[0051] In a second aspect, an embodiment of the present application further provides a map drawing device based on a large language model, the device comprising:

[0052] A data acquisition module is used to acquire raster image data and vector road data to establish a geographic spatial reference coordinate system;

[0053] A corpus collection module is used to collect a text corpus of positioning information based on natural language descriptions, wherein the text corpus of positioning information includes place name entities, location descriptions, and spatial relationship expressions;

[0054] The model building module is used to build a spatial semantic processing model based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus;

[0055] An instruction processing module is used to receive mixed instructions input by the user and convert the mixed instructions into a structured instruction tree;

[0056] A scheme generating module is used to generate a coordinate set according to the structured instruction tree, and generate a coordinate set scheme after verifying the coordinate set;

[0057] The map drawing module is used to draw the coordinate set scheme into an interactive map based on the spatial semantic processing model.

[0058] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0059] A processor, a memory, and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the map drawing method based on the large language model as described above.

[0060] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a server, the map drawing method based on the large language model as described above is implemented.

[0061] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes instructions. When the instructions are executed by a computer, the computer implements the map drawing method based on the large language model as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0063] Figure 1 A flowchart of a map drawing method based on a large language model provided in an embodiment of the present application;

[0064] Figure 2 A schematic diagram of a process flow of a map drawing device based on a large language model provided in an embodiment of the present application;

[0065] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0067] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0068] Traditional map drawing systems have the following technical pain points: They rely on manual operations for symbol drawing and annotation, which is inefficient; existing automated tools only support structured data input and cannot parse complex semantics in natural language (such as "mark a temporary checkpoint 200 meters east of intersection A"); and they lack intelligent optimization capabilities in dynamic environments, requiring manual intervention to resolve marking conflicts.

[0069] Based on this, an embodiment of the present application provides a map drawing method based on a large language model to solve the above problems.

[0070] Please see Figure 1 , Figure 1 A flowchart of a map drawing method based on a large language model provided in an embodiment of the present application. The map drawing method based on a large language model includes:

[0071] 100. Obtain raster image data and vector road data to establish a geographic spatial reference coordinate system.

[0072] Specifically, a unified geospatial reference coordinate system is established by fusion indexing multiple data sources. Optionally, raster image data of the target area can be obtained through a satellite remote sensing data interface; vector road network data can be obtained by parsing the latitude and longitude coordinate system or accessing an open-source geographic information database; raster image data and vector road data can be converted into data in a unified standard format, and the fusion index can be used to establish a geospatial reference system. Establishing a unified standard format for the geospatial reference system facilitates the subsequent establishment of a spatial semantic processing model.

[0073] 200. Collect a text corpus of positioning information based on natural language descriptions, wherein the text corpus of positioning information includes place name entities, location descriptions, and spatial relationship expressions.

[0074] Specifically, to build a comprehensive and representative corpus of location-based information text, data can be collected from multiple data sources. The collected raw text data often contains noise and redundant information, requiring rigorous data cleaning. This includes removing irrelevant advertisements, links, special symbols, correcting spelling and grammatical errors, and standardizing text formatting. Based on this data cleaning, place names, location descriptions, and spatial relationship expressions in the text are annotated.

[0075] It can be understood that place name entities are one of the core elements in positioning information text, which covers geographical names of various scales; orientation description is used to clarify the relative position relationship between geographical entities and is an important way to express spatial information in natural language; spatial relationship expression is more complex and diverse, which not only involves the orientation relationship between geographical entities, but also includes topological relationships, sequential relationships, etc.

[0076] For example, directional descriptions are used to clarify the relative positional relationships between geographic entities and are an important way to express spatial information in natural language. They can be implemented using a variety of words and phrases. For example, basic directional words like "east," "south," "west," and "north" and their combinations, such as "southeast" and "northwest," are used to describe the relative direction between two locations, such as "the school is east of the park." More specific directional phrases, such as "in front," "behind," "left," "right," and "opposite," can also be used to further refine the location relationship in combination with specific reference objects, such as "the supermarket is opposite the bookstore." In addition, there are also descriptions of distance, such as "nearby," "not far away," and "a few kilometers away," which are used to illustrate the degree of spatial separation between geographic entities.

[0077] For example, in spatial relationship expressions, topological relationships describe spatial structural features such as connectivity, inclusion, and adjacency between geographic entities. For example, "a river runs through a city" reflects the intersecting relationship between the river and the city, while "a residential complex contains multiple buildings" expresses the inclusion relationship between the residential complex and the buildings. Sequential relationships emphasize the spatial arrangement of geographic entities, such as "from left to right are the library, the teaching building, and the gymnasium." These spatial relationship expressions can more comprehensively and accurately describe the spatial connections between geographic entities, providing rich information for spatial positioning and spatial reasoning.

[0078] 300. Based on the geographic spatial reference coordinate system and positioning information text corpus, a spatial semantic processing model is built based on the self-attention mechanism.

[0079] Specifically, a text encoder is used to process the positioning information text corpus (natural language instructions), an image encoder is used to parse the building outlines and road topology features in satellite images, and a spatial decoder is used to generate geometric elements in the geographic spatial reference coordinate system; an attention mechanism is used to achieve cross-modal feature alignment to obtain a spatial semantic processing model.

[0080] For example, the positioning information text corpus usually contains various forms of natural language instructions. Word segmentation technology is used to divide the text into meaningful vocabulary units, perform part-of-speech tagging and named entity recognition, and clarify key information such as location, direction, and distance in the text. Select a suitable text encoder model and use the positioning information text corpus to fine-tune the encoder. During the training process, design appropriate task objectives, such as sequence labeling tasks (identifying location entities in the text) and text classification tasks (determining the type of instructions, such as navigation instructions, location description instructions, etc.), so that the encoder can better understand the semantic features of the positioning information text. The trained text encoder can map the input positioning information text into a high-dimensional semantic vector space. Each dimension in this vector space represents the characteristics of the text at different semantic levels, such as location relevance, direction indication, distance, etc.

[0081] For example, satellite imagery data features high resolution and multispectral characteristics, but before being directly input into an image encoder, it requires a series of preprocessing operations. This includes image correction (geometric correction and radiometric correction) to eliminate geometric distortion and radiometric errors in the imagery, and image enhancement (contrast enhancement and sharpening) to improve the visual quality and feature recognition. A convolutional neural network (CNN) is used as the basic architecture of the image encoder. The image encoder is trained using a large-scale geospatial image dataset containing a variety of geographical scenes, such as urban buildings, rural roads, and natural landscapes. During training, an appropriate loss function, such as the cross-entropy loss function (for image classification) or the mean squared error loss function (for image regression), is designed to enable the encoder to accurately interpret building outlines and road topology features in satellite imagery. The trained image encoder can map the input satellite imagery into a feature map or feature vector. Each location in the feature map corresponds to a local region in the image, and its feature value represents the feature strength of that region. The feature vector represents the global features of the entire image. These features include information such as the height, shape, and texture of buildings, and the orientation, width, and connectivity of roads.

[0082] For example, the feature representations output by the text encoder and image encoder are in different semantic and visual spaces, respectively. To achieve effective spatial semantic fusion, these features need to be converted to a unified geographic spatial reference coordinate system. For example, a geographic coordinate system (such as WGS84) is used as a unified reference framework, and image features and text features are spatially aligned through a coordinate transformation algorithm. The spatial decoder generates geometric features in a geographic spatial reference coordinate system based on the fused feature representations, such as building outlines and road centerlines. A trained spatial decoder can generate initial geometric features based on the input fused features. However, the generated geometric features may contain some inaccuracies or incompleteness and require further optimization. Post-processing algorithms, such as curve fitting and topology correction, can be used to smooth the generated geometric features and optimize their topological structure to improve their accuracy and reliability.

[0083] Among them, the use of the attention mechanism to achieve cross-modal feature alignment includes: establishing a mapping relationship between semantic elements in text descriptions and spatial coordinates, and a corresponding relationship between labeled entities and mapped icons; building dynamic spatial reasoning capabilities, and optimizing spatial reasoning capabilities through user feedback data based on a reinforcement learning mechanism.

[0084] For example, a spatial knowledge graph is constructed to organize spatial entities, relationships, attributes, and other information in a graph structure. Nodes in the knowledge graph represent entities, and edges represent relationships between entities, such as adjacency, inclusion, and functional associations. Through the knowledge graph, structured representation and efficient reasoning of spatial information can be achieved. Based on the laws of spatial cognition and domain knowledge, a series of inference rules can be defined. For example, inferring the reachability of entities based on their positional relationships, or inferring their interactions with other entities based on their functional attributes, can be defined. These inference rules can be defined based on logical rules, probabilistic models, and other methods.

[0085] In addition, in the spatial reasoning system, define the appropriate state space, action space and reward function; select the reinforcement learning algorithm suitable for the spatial reasoning task, and use a large amount of user feedback data to train the reinforcement learning model.

[0086] 400. Receive mixed instructions input by a user, and convert the mixed instructions into a structured instruction tree.

[0087] Specifically, a mixed instruction input by a user is received; wherein the mixed instruction includes: text, voice and sketch; the spatial operation type, geographic reference, spatial relationship description and operation object in the instruction are identified; and the mixed instruction is converted into a structured instruction tree.

[0088] For example, the following items are identified in the instruction: spatial operation type (create / modify / delete map features), geographic reference objects (landmark buildings, POI points), spatial relationship descriptions (adjacency, inclusion, distance constraints), and operation objects (fire hydrants, houses, etc.).

[0089] 500. Generate a coordinate set according to the structured instruction tree, perform verification processing on the coordinate set, and then generate a coordinate set solution.

[0090] Specifically, a coordinate set is generated based on a structured instruction tree; the legitimacy of the geographic entities in the coordinate set is verified based on the geographic spatial reference coordinate system to solve the problem of homonyms (such as the coordinate matching of "Beijing Road" in different cities), and conflict detection is performed in combination with a spatial semantic processing model; and multiple candidate coordinate set solutions with confidence scores are generated.

[0091] As you can understand, the confidence score is a numerical indicator used to measure the reliability of the model's prediction results, usually between 0 and 1 (or 0% to 100%); the higher the score, the greater the model's confidence in the current prediction.

[0092] The performing of conflict detection in combination with the spatial semantic processing model includes:

[0093] The coordinate set is verified in combination with the spatial semantic processing model. Verifying map information includes verifying the topological consistency of newly labeled features with existing map features, detecting the adaptability of the scale (such as the matching degree between road width annotation and the current zoom level), and verifying the rationality of feature distribution.

[0094] 600. Based on the spatial semantic processing model, the coordinate set scheme is plotted as an interactive map.

[0095] 610. Filter out coordinate set solutions whose confidence scores are greater than a set score threshold.

[0096] It can be understood that from a large number of coordinate data sets, coordinate sets with confidence scores greater than a set score threshold are screened out. For example, coordinate data with a confidence score greater than 0.8 are screened out, and the filtered coordinate sets are output in a suitable data format (such as a list, DataFrame, etc.) to facilitate subsequent processing and analysis.

[0097] 620. Based on the spatial semantic processing model, the coordinate set scheme is generated into a vector map file that meets the set standards.

[0098] Optionally, spatial semantic processing models (such as deep learning models and spatial clustering algorithms) can be used to extract features from coordinate data, identifying key points, lines, and surfaces in space. Based on the feature extraction results, the coordinate data can be semantically annotated, such as to identify different types of geographic entities such as buildings, roads, and water bodies. Based on the results of spatial semantic processing, geometric elements (points, lines, and surfaces) in the vector map are constructed. For example, coordinate points of the same category can be aggregated into polygons to represent buildings or areas. Attribute information such as name, type, and area can be added to the geometric elements. This information can be extracted from the original data or the results of spatial semantic processing. Map drawing libraries (such as Matplotlib, Folium, and Geopandas) can be used to draw the geometric elements and attribute information into a vector map.

[0099] 630. Overlay time dimension information on the vector map file.

[0100] Specifically, determine the type of time dimension information, expand the structure of the vector map file (add time attribute fields, use time format standards), and select a suitable data model to achieve the overlay of time dimension information.

[0101] 640. Use the graphics library to render three-dimensional terrain effects on vector map files and adjust lighting parameters and material parameters.

[0102] Specifically, prepare vector map data, select a graphics library to render 3D terrain, adjust lighting parameters, adjust material parameters, add terrain textures and details, and finally optimize performance.

[0103] 650. Deploy a differential privacy mechanism for vector map files and blur the labeling information of sensitive areas.

[0104] In geographic information systems (GIS), vector map files (such as Shapefiles and GeoJSON) often contain sensitive information (e.g., military bases, private resident data, etc.). To protect privacy, sensitive areas require differential privacy processing, either blurring or perturbing them. Fuzzification involves identifying sensitive areas, selecting a blurring technique, achieving differential privacy (adding noise or perturbation), and generating a blurred vector file.

[0105] 660. Get the interactive map.

[0106] It can be understood that based on the spatial semantic processing model, the coordinate set scheme is generated into a vector map file that conforms to the OGC standard (such as Shapefile / KML format); time dimension information is superimposed to support historical version comparison and change trajectory visualization; three-dimensional terrain effects are rendered through graphics libraries such as WebGL, and lighting and material parameters are dynamically adjusted; differential privacy mechanisms are deployed to fuzzy the annotation information of sensitive areas.

[0107] As described above, the embodiment of the present application obtains raster image data and vector road data to establish a geographic spatial reference coordinate system; collects a positioning information text corpus based on natural language descriptions, wherein the positioning information text corpus contains place name entities, orientation descriptions, and spatial relationship expressions; builds a spatial semantic processing model based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus; receives mixed instructions input by the user, and converts the mixed instructions into a structured instruction tree; generates a coordinate set according to the structured instruction tree, and generates a coordinate set scheme after verifying the coordinate set; based on the spatial semantic processing model, plots the coordinate set scheme as an interactive map; supports user input of mixed data instructions, can parse complex semantics in natural language, automatically draw maps, and improve map drawing efficiency.

[0108] 700. Verify the conversion result of the interactive map, and process the spatial semantic processing model according to the verification result.

[0109] 710. Obtain the difference between the marked position of the interactive map and the actual measurement value.

[0110] 720. If the difference exceeds the set threshold, the retraining process of the spatial semantic processing model is triggered; the retraining process includes: automatically labeling erroneous samples, adjusting the weight parameters of the spatial decoder, and updating the geographic entity knowledge graph.

[0111] 730. If the difference is less than or equal to the set threshold, the interactive map and the spatial semantic processing model are retained.

[0112] As you can understand, by accessing the GNSS positioning system to obtain real information to build verification data, during the testing phase, the difference between the annotated position and the actual measurement value is quantified using a certain indicator, such as the root mean square error. When the error exceeds a threshold, the model retraining process is triggered.

[0113] As described above, the multimodal fusion mechanism of the present embodiment achieves bidirectional mapping between text and spatial data. By constructing a multi-task learning model based on the Transformer architecture, integrating a text encoder, an image encoder, and a spatial decoder, cross-modal feature alignment is achieved. The text encoder parses semantic elements (such as place names and location descriptions) in natural language instructions, the image encoder extracts spatial features (such as building outlines and road topology) from satellite imagery, and the spatial decoder dynamically maps semantic elements to a unified geographic coordinate system through an attention mechanism, forming a bidirectional data association. At the same time, a reinforcement learning mechanism is introduced to continuously optimize the matching accuracy between text descriptions and spatial coordinates using user feedback, effectively solving the problem of accurately converting complex semantics (such as "200 meters from the east gate") into geometric coordinates.

[0114] The dynamic spatial reasoning engine of the embodiment of the present application supports the processing of complex constraints. During the instruction parsing stage, the system identifies spatial relationships (including and distance constraints), geographic references, and operation objects through a structured instruction tree, and generates a candidate coordinate set by combining geographic entity legitimacy verification and homonym resolution. The spatial reasoning engine verifies the topological consistency of feature distribution (such as the adjacency relationship between fire hydrants and roads), scale adaptability (the matching degree between annotation dimensions and map levels), and operation conflicts (such as duplicate annotation detection) in real time, and uses the knowledge graph to dynamically load regional geographic rules (such as firefighting facility layout specifications) to achieve joint reasoning of multi-dimensional constraints, and finally outputs an optimization plan with a confidence score to ensure that the annotation results meet the needs of actual business scenarios.

[0115] The embodiment of the present application introduces a security enhancement layer for geographic information privacy protection. During the mapping result output stage, the system uses a differential privacy mechanism to inject Gaussian noise or perform regional fuzzification processing on the coordinate data of sensitive areas (such as military facilities and personal addresses), and uses attribute generalization technology to desensitize metadata such as POI names. The data encryption module implements hierarchical permission control on the generated vector files (such as KML) to ensure that different user roles can only access geographic information at the authorized level. In addition, through dynamic watermark embedding and access log tracking, a full-link security protection system is constructed from data generation, transmission to storage, taking into account both geographic information sharing needs and privacy protection compliance.

[0116] The embodiments of the present application implement an adaptive closed-loop error detection and model update. A quantitative evaluation indicator is established by calculating the root mean square error (RMSE) between the GNSS measured data and the annotated coordinates. When the error exceeds the threshold, the closed-loop optimization process is automatically triggered: the error sample annotation module identifies the semantic description and spatial feature combination of the positioning deviation, the knowledge graph update module corrects the mapping relationship of geographic entity coordinates, and the spatial decoder dynamically adjusts the cross-modal attention weights through backpropagation. This mechanism realizes an automated link from error detection, sample mining to model iteration, ensuring that the system continues to improve spatial reasoning accuracy when regional geographic data is updated (such as road reconstruction) or when user annotation patterns evolve.

[0117] The above steps are not to be performed in a strict order as described in the numbers, but should be understood as an overall solution.

[0118] In the second aspect, based on the above embodiment, the embodiment of the present application further provides a map drawing device based on a large language model, referring to Figure 2 The map drawing device based on the large language model provided in this embodiment specifically includes: a data acquisition module 201, a corpus collection module 202, a model building module 203, an instruction processing module 204, a solution generation module 205 and a map drawing module 206.

[0119] Among them, the data acquisition module 201 is used to acquire raster image data and vector road data to establish a geographic spatial reference coordinate system; the corpus acquisition module 202 is used to collect a positioning information text corpus based on natural language descriptions, wherein the positioning information text corpus contains place name entities, direction descriptions and spatial relationship expressions; the model building module 203 is used to build a spatial semantic processing model based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus; the instruction processing module 204 is used to receive mixed instructions input by the user and convert the mixed instructions into a structured instruction tree; the solution generation module 205 is used to generate a coordinate set according to the structured instruction tree, and generate a coordinate set solution after verifying the coordinate set; the map drawing module 206 is used to draw the coordinate set solution into an interactive map based on the spatial semantic processing model.

[0120] As described above, the embodiment of the present application obtains raster image data and vector road data to establish a geographic spatial reference coordinate system; collects a positioning information text corpus based on natural language descriptions, wherein the positioning information text corpus contains place name entities, orientation descriptions, and spatial relationship expressions; builds a spatial semantic processing model based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus; receives mixed instructions input by the user, and converts the mixed instructions into a structured instruction tree; generates a coordinate set according to the structured instruction tree, and generates a coordinate set scheme after verifying the coordinate set; based on the spatial semantic processing model, plots the coordinate set scheme as an interactive map; supports user input of mixed data instructions, can parse complex semantics in natural language, automatically draw maps, and improve map drawing efficiency.

[0121] In a third aspect, an embodiment of the present application further provides an electronic device that can integrate the large language model-based map drawing device of the user-mode polling mechanism provided in an embodiment of the present application. Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 The electronic device includes: an input device 43, an output device 44, a memory 42, and one or more processors 41; the memory 42 is used to store one or more programs; when the one or more programs are executed by the one or more processors 41, the one or more processors 41 implement the map drawing method based on the large language model of the user-mode polling mechanism provided in the above embodiment. The input device 43, the output device 44, the memory 42, and the processor 41 can be connected via a bus or other means. Figure 3 The bus connection is taken as an example.

[0122] The processor 41 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 42, that is, realizes the map drawing method based on the large language model of the above-mentioned user-mode polling mechanism.

[0123] The electronic device provided above can be used to execute the map drawing method based on the large language model of the user-mode polling mechanism provided in the above embodiment, and has corresponding functions and beneficial effects.

[0124] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the map drawing method based on the large language model as described above, and can achieve the same beneficial effects as described above.

[0125] Of course, the computer-executable instructions of the storage medium provided in the embodiment of the present application are not limited to the map drawing method based on the large language model as described above, and can also execute the relevant operations in the map drawing method based on the large language model provided in any embodiment of the present application.

[0126] In a fifth aspect, the embodiments of the present application further provide a computer program product. The methods described in the various embodiments of the present application can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the various embodiments of the present application are executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model) or other programmable device.

[0127] The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless method. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0129] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0130] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0131] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0132] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0133] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A map drawing method based on a large language model, characterized in that: The method comprises: Obtain raster image data and vector road data to establish a geospatial reference coordinate system; Collecting a text corpus of positioning information based on natural language descriptions, wherein the text corpus of positioning information includes place name entities, location descriptions, and spatial relationship expressions; Based on the geographic spatial reference coordinate system and positioning information text corpus, a spatial semantic processing model is built based on the self-attention mechanism; Receive mixed instructions input by the user and convert the mixed instructions into a structured instruction tree; Generate a coordinate set according to the structured instruction tree, and generate a coordinate set solution after verifying the coordinate set; Based on the spatial semantic processing model, the coordinate set scheme is plotted as an interactive map; The step of generating a coordinate set according to the structured instruction tree and verifying the coordinate set to generate a coordinate set solution includes: Generate a coordinate set according to a structured instruction tree; Verify the validity of geographic entities in a coordinate set based on the geographic spatial reference coordinate system, resolve homonymous and heteronymous issues, and perform conflict detection in conjunction with spatial semantic processing models. Generate multiple candidate coordinate set solutions with confidence scores; The conflict detection is performed by combining the spatial semantic processing model, including: The coordinate set is verified in combination with the spatial semantic processing model, wherein the verified map information includes verifying the topological consistency of the newly annotated elements and the existing map elements, detecting the adaptability of the scale, and verifying the rationality of the element distribution.

2. The map drawing method based on a large language model according to claim 1, characterized in that: Also includes: Verify the conversion results of the interactive map and process the spatial semantic processing model based on the verification results; The verification of the conversion result of the interactive map and processing the spatial semantic processing model according to the verification result include: Get the difference between the marked position of the interactive map and the actual measurement value; If the difference exceeds the set threshold, the retraining process of the spatial semantic processing model is triggered; the retraining process includes: automatically labeling erroneous samples, adjusting the weight parameters of the spatial decoder, and updating the geographic entity knowledge graph; If the difference is less than or equal to the set threshold, the interactive map and spatial semantic processing model are retained.

3. The map drawing method based on a large language model according to claim 1, characterized in that: The obtaining of raster image data and vector road data to establish a geographic spatial reference coordinate system includes: Obtain raster image data of the target area through the satellite remote sensing data interface; Parse the longitude and latitude coordinate system or access open source geographic information database to obtain vector road network data; Convert raster image data and vector road data into data in a unified standard format, and fuse the indexes to form a geographic spatial reference system.

4. The map drawing method based on a large language model according to claim 1, characterized in that: The spatial semantic processing model is built based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus, including: A text encoder is used to process the positioning information text corpus, an image encoder is used to parse the building outlines and road topology features in satellite images, and a spatial decoder is used to generate geometric elements in the geographic spatial reference coordinate system; The attention mechanism is used to achieve cross-modal feature alignment and obtain a spatial semantic processing model; The attention mechanism is used to achieve cross-modal feature alignment, including: Establish the mapping relationship between semantic elements in text description and spatial coordinates, and the correspondence between annotation entities and plotted icons; Build dynamic spatial reasoning capabilities and optimize spatial reasoning capabilities through user feedback data based on reinforcement learning mechanisms.

5. The map drawing method based on a large language model according to claim 1, characterized in that: The receiving of the mixed instruction input by the user and converting the mixed instruction into a structured instruction tree includes: Receiving a mixed instruction input by a user; wherein the mixed instruction includes: text, voice and sketch; Identify the spatial operation type, geographic reference, spatial relationship description, and operation object in the instruction; Convert mixed instructions into a structured instruction tree.

6. The map drawing method based on a large language model according to claim 1, characterized in that: The method of plotting the coordinate set scheme as an interactive map based on the spatial semantic processing model includes: Filter out the coordinate set solutions whose confidence scores are greater than the set score threshold; Based on the spatial semantic processing model, the coordinate set scheme is generated into a vector map file that meets the set standards; Overlay time dimension information on vector map files; Render 3D terrain effects on vector map files through the graphics library, and adjust lighting and material parameters; Deploy a differential privacy mechanism for vector map files to obfuscate the annotation information of sensitive areas; Get the interactive map.

7. A map drawing device based on a large language model, characterized in that: The device comprises: A data acquisition module is used to acquire raster image data and vector road data to establish a geographic spatial reference coordinate system; A corpus collection module is used to collect a text corpus of positioning information based on natural language descriptions, wherein the text corpus of positioning information includes place name entities, location descriptions, and spatial relationship expressions; The model building module is used to build a spatial semantic processing model based on the self-attention mechanism according to the geographic spatial reference coordinate system and the positioning information text corpus; An instruction processing module is used to receive mixed instructions input by the user and convert the mixed instructions into a structured instruction tree; A scheme generating module is used to generate a coordinate set according to the structured instruction tree, and generate a coordinate set scheme after verifying the coordinate set; A map drawing module is used to draw the coordinate set scheme into an interactive map based on a spatial semantic processing model; The step of generating a coordinate set according to the structured instruction tree and verifying the coordinate set to generate a coordinate set solution includes: Generate a coordinate set according to a structured instruction tree; Verify the validity of geographic entities in a coordinate set based on the geographic spatial reference coordinate system, resolve homonymous and heteronymous issues, and perform conflict detection in conjunction with spatial semantic processing models. Generate multiple candidate coordinate set solutions with confidence scores; The conflict detection is performed by combining the spatial semantic processing model, including: The coordinate set is verified in combination with the spatial semantic processing model, wherein the verified map information includes verifying the topological consistency of the newly annotated elements and the existing map elements, detecting the adaptability of the scale, and verifying the rationality of the element distribution.

8. An electronic device, characterized in that: include: A processor, a memory, and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the map drawing method based on a large language model as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a server, implements the map drawing method based on a large language model as described in any one of claims 1 to 6.

Images