Electronic map style configuration method and system based on large model questions and answers

Abstract

The invention discloses an electronic map style configuration method and system based on large model questions and answers, and belongs to the technical field of artificial intelligence, and the method is implemented by the following steps: constructing a large model question and answer framework through Oplama + DeepSeek + Milvus technologies, and sorting and importing electronic map standard style specifications of each industry; constructing an electronic map style configuration format based on an attribute filtering condition and an element style separation principle; fusing natural language input content, electronic map data source geometric information and attribute information, and constructing a large language model Prompt cue word; and extracting style configuration content in a large model return text, converting the style configuration content into a style matching method, and updating an electronic map rendering style. According to the method, the user configuration difficulty of the electronic map style can be reduced, the application scene of the electronic map is expanded, and the electronic map style configuration cost is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for configuring electronic map styles based on large-model question-answering. Background Art

[0002] As the core infrastructure for smart city development, electronic maps play a key role in application areas such as urban planning, urban governance, urban security, and urban transportation. The massive amount of spatiotemporal data elements generated by cities throughout their operations require the configuration of corresponding electronic map styles based on the specific application themes to serve the development of corresponding thematic systems. Currently, with the rapid development of artificial intelligence technology, the construction of smart city thematic applications is gradually entering the "deep water zone." The rapid improvement of cities' real-time perception capabilities is also driving the accelerated integration of electronic maps with artificial intelligence technologies, enabling rapid response to changing application needs and better leveraging the role of electronic maps as the "digital foundation" of cities.

[0003] At present, in the process of smart city construction, the style configuration of electronic maps is difficult, the process is complicated, and it is difficult to cope with the complex and changing electronic map display needs. Summary of the Invention

[0004] The technical task of the present invention is to address the above shortcomings and provide an electronic map style configuration method and system based on large model question and answer, which can reduce the difficulty of user configuration of electronic map style, expand the application scenarios of electronic maps, and effectively reduce the cost of electronic map style configuration.

[0005] The technical solution adopted by the present invention to solve its technical problem is:

[0006] A method for configuring electronic map styles based on large model question-answering, the implementation of which includes the following steps:

[0007] Step S1: Build a large-scale question-answering framework using Ollama+DeepSeek+Milvus technologies, and organize and import standard electronic map styles from various industries;

[0008] Step S2: Based on the principle of separating attribute filtering conditions from feature styles, construct an electronic map style configuration format;

[0009] Step S3: Fusing natural language input content, geometric information and attribute information of electronic map data sources to construct a large language model prompt word;

[0010] Step S4: extract the style configuration content in the text returned by the large model, convert it into a style matching method and update the electronic map rendering style.

[0011] This method makes full use of the universal characteristics of large models and knowledge bases. By understanding the user's natural language input, it automatically completes the electronic map style design and results visualization containing complex geometric information and attribute information, reducing the difficulty of user configuration of electronic map styles and expanding the application scenarios of electronic maps.

[0012] Furthermore, the specific steps of step S1 include:

[0013] Step S11: Install and deploy the Ollama large model running framework and Milvus vector knowledge base, and use Ollama to download and install the DeepSeek-R1 large language model;

[0014] Step S12: Organize and collect common electronic map industry style specification documents, add style description tags according to specific style specifications, and upload them to the Milvus vector knowledge base.

[0015] Furthermore, the specific steps of step S2 include:

[0016] Step S21: Classify the map layers appearing in the electronic map into three categories according to their geometric information: Point, Polyline, and Polygon. Different geom types correspond to different layer style types: Point layer styles support icon and text annotation style information; Polyline layer styles support line segment style information; Polygon layer styles support plane and extruded surface style information;

[0017] Step S22: Design filter conditions for each layer in the electronic map according to consistent structural requirements, where filter attributes mainly include field filter condition array properties, minimum zoom level zoomMin, and maximum zoom level zoomMax;

[0018] Step S23: Based on the style, filter and other attributes, a layer style legend is formed. A single layer can be applied to multiple legends at the same time, and multiple legends can constitute a complete electronic map style configuration object mapStyle.

[0019] Furthermore, in step S21,

[0020] Icon and text annotation style information includes: icon, scale, textField, font information;

[0021] Line segment style information includes lineWidth, outlineWidth, lineColor, OutlineColor, and lineType information;

[0022] Plane and extruded surface style information includes fillColor and extrudeField information.

[0023] Furthermore, the field filtering condition array properties contains the attribute field filtering judgment conditions including field, value, and condition, wherein:

[0024] field represents the attribute field name in the layer attribute information;

[0025] value represents the corresponding field value in the layer attribute information;

[0026] Condition represents the judgment relationship between field name and field value;

[0027] The judgment relationships of numerical attribute fields include: greater than, less than, equal to, greater than or equal to, less than or equal to; the judgment relationships of text attribute fields include: contains, does not contain.

[0028] Furthermore, the specific steps of step S3 include:

[0029] Step S31: Collecting the content of the large model language prompt word Prompt, including: user requirement text description, electronic map data source layer metadata information metaData, electronic map style configuration format requirements, etc.; wherein metaData includes layer basic information, layer geometry type information, layer attribute field type and description information, etc.;

[0030] Step S32: compose a large language model prompt word Prompt, and upload the electronic map style requirements through the Ollama context dialogue interface.

[0031] Furthermore, the specific steps of step S4 include:

[0032] Step S41: Parse the large language model answer content and extract the electronic map style configuration object mapStyle in the returned text;

[0033] Step S42: traverse the legend in mapStyle in sequence and obtain layer unique value data, compare the layer in the electronic map data source according to the layer unique value and add the corresponding layer to the electronic map rendering framework;

[0034] Step S43: Start electronic map rendering, load layer slices according to the current view range, and wait for rendering; when rendering a specific layer slice, obtain the legend array of the corresponding layer in mapStyle, match the style that meets the filter condition based on the level scaling information, geometry information and attribute information of the current layer slice, and execute electronic map rendering of the specific layer slice according to the style information;

[0035] Step S44: sequentially loading and rendering the required layer slices within the current view range, completing the design and configuration process of the electronic map model style required by the user.

[0036] The present invention also claims protection for an electronic map style configuration system based on large model question and answer, comprising:

[0037] Large model question-answering framework construction module, used to build a large model question-answering framework, organize and import standard style specifications of electronic maps in various industries;

[0038] The electronic map style configuration module is used to implement the electronic map style configuration format based on the principle of separating attribute filtering conditions and feature styles;

[0039] The prompt word construction module is used to integrate natural language input content, electronic map data source geometry information and attribute information to build a large language model prompt word;

[0040] The electronic map style update module is used to extract the style configuration content in the text returned by the large model, convert it into a style matching method, and update the electronic map rendering style;

[0041] The system implements electronic map style configuration through the above method.

[0042] The present invention also claims protection for an electronic map style configuration device based on large model question and answer, comprising: at least one memory and at least one processor;

[0043] The at least one memory is configured to store a machine-readable program;

[0044] The at least one processor is configured to call the machine-readable program to implement the above method.

[0045] The present invention also claims protection for a computer-readable medium having computer instructions stored thereon, which implement the above method when executed by a processor.

[0046] Compared with the prior art, the electronic map style configuration method and system based on large model question and answer of the present invention has the following beneficial effects:

[0047] The method of configuring electronic map styles based on a large model question-and-answer format in the present invention further lowers the production technology threshold for electronic map style configuration compared to traditional parameter style configuration methods, and effectively improves the production efficiency of electronic maps.

[0048] This invention uses large-scale model technology to accurately analyze users' requirements for the style of electronic maps, shortening the design and development cycle between user needs and the implementation of results, better responding to the needs of different user groups and different application fields for accurate expression of geographic information features, and expanding the application scenarios of electronic maps. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flowchart of a method for configuring an electronic map style based on a large model question and answer provided by an embodiment of the present invention;

[0050] Figure 2 This is a diagram of the electronic map style configuration object mapStyle provided by an embodiment of the present invention;

[0051] Figure 3 This is a diagram illustrating the structure of the prompt word Prompt provided by an embodiment of the present invention;

[0052] Figure 4 This is a flowchart illustrating the electronic map slice style rendering and updating process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The embodiment of the present invention provides a method for configuring electronic map styles based on large model question and answer, such as Figure 1 As shown, the implementation of this method includes the following steps:

[0054] Step S1: Build a large-model question-answering framework using Ollama+DeepSeek+Milvus technology, and organize and import standard electronic map style specifications for various industries.

[0055] Step S2: Based on the principle of separating attribute filtering conditions from feature styles, construct an electronic map style configuration format.

[0056] Step S3: Integrate the natural language input content, the geometric information and attribute information of the electronic map data source to construct a large language model prompt word.

[0057] Step S4: extract the style configuration content in the text returned by the large model, convert it into a style matching method and update the electronic map rendering style.

[0058] The specific steps of step S1 include:

[0059] Step S11: Install and deploy the Ollama large model running framework and Milvus vector knowledge base, and use Ollama to download and install the DeepSeek-R1 large language model.

[0060] Step S12: Organize and collect common electronic map industry style specification documents, add style description tags according to specific style specifications, and upload them to the Milvus vector knowledge base.

[0061] The specific steps of step S2 include:

[0062] Step S21: The map layers appearing in the electronic map are divided into three categories according to the geometric information geom: Point, Polyline, and Polygon. Different geom types correspond to different layer style types: Point layer styles support icon, scale, textField, font and other icon and text annotation style information; Polyline layer styles support line segment style information such as lineWidth, outlineWidth, lineColor, OutlineColor, and lineType; Polygon layer styles support plane and extruded surface style information such as fillColor and extrudeField.

[0063] Step S22: Various types of layers in the electronic map are designed with filter conditions for map layers according to consistent structural requirements, where the filter attributes mainly include the field filter condition array properties, the minimum zoom level zoomMin, and the maximum zoom level zoomMax; the properties array contains attribute field filter judgment conditions including field, value, and condition, where field represents the attribute field name in the layer attribute information, value represents the corresponding field value in the layer attribute information, and condition represents the judgment relationship between the field name and the field value; the judgment relationship of the numerical attribute field includes: greater than, less than, equal to, greater than or equal to, less than or equal to, and the judgment relationship of the text attribute field includes: contains, does not contain.

[0064] Step S23: Figure 2 As shown in the figure, the style legend of a layer is composed of attributes such as style and filter. A single layer can be applied to multiple legends at the same time, and multiple legends can constitute a complete electronic map style configuration object mapStyle.

[0065] The specific steps of step S3 include:

[0066] Step S31: Gather the content of the large model language prompt word Prompt, which needs to include: user requirement text description, electronic map data source layer metadata information metaData, electronic map style configuration format requirements, etc.; wherein metaData includes layer basic information, layer geometry type information, layer attribute field type and description information, etc.

[0067] Step S32: Figure 3 The structure shown here constitutes the large language model prompt word Prompt, and the electronic map style requirements are uploaded through the Ollama context dialogue interface.

[0068] The specific steps of step S4 include:

[0069] Step S41: Parse the large language model answer content and extract the electronic map style configuration object mapStyle in the returned text.

[0070] Step S42: traverse the legend in mapStyle in sequence and obtain layer unique value data, compare the layer in the electronic map data source according to the layer unique value and add the corresponding layer to the electronic map rendering framework.

[0071] Step S43: Start electronic map rendering and load layer slices according to the current view range and wait for rendering; when rendering a specific layer slice, obtain the legend array of the corresponding layer in mapStyle, such as Figure 4 As shown, the style that meets the filter condition is matched according to the level scaling information, geometric information and attribute information of the current layer slice, and the electronic map rendering of a specific layer slice is performed according to the style information.

[0072] Step S44: sequentially loading and rendering the required layer slices within the current view range, completing the design and configuration process of the electronic map model style required by the user.

[0073] This method makes full use of the universal characteristics of large models and knowledge bases. By understanding the user's natural language input, it automatically completes the electronic map style design and results visualization containing complex geometric information and attribute information, reducing the difficulty of user configuration of electronic map styles and expanding the application scenarios of electronic maps.

[0074] An embodiment of the present invention further provides an electronic map style configuration system based on large model question and answer, comprising:

[0075] Large model question-answering framework construction module, used to build a large model question-answering framework, organize and import standard style specifications of electronic maps in various industries;

[0076] The electronic map style configuration module is used to implement the electronic map style configuration format based on the principle of separating attribute filtering conditions and feature styles;

[0077] The prompt word construction module is used to integrate natural language input content, electronic map data source geometry information and attribute information to build a large language model prompt word;

[0078] The electronic map style update module is used to extract the style configuration content in the text returned by the large model, convert it into a style matching method, and update the electronic map rendering style;

[0079] The system implements electronic map style configuration through the electronic map style configuration method based on large model question and answer described in the above embodiment. The specific implementation steps are as follows:

[0080] Step S1: The large model question answering framework construction module constructs a large model question answering framework through Ollama+DeepSeek+Milvus technology, and organizes and imports standard style specifications of electronic maps in various industries.

[0081] Step S2: The electronic map style configuration module constructs an electronic map style configuration format based on the principle of separating attribute filtering conditions from feature styles.

[0082] Step S3: The Prompt word construction module integrates the natural language input content, the geometric information and attribute information of the electronic map data source, and constructs a large language model Prompt word.

[0083] Step S4: The electronic map style update module extracts the style configuration content in the text returned by the large model, converts it into a style matching method and updates the electronic map rendering style.

[0084] The specific steps of step S1 include:

[0085] Step S11: Install and deploy the Ollama large model running framework and Milvus vector knowledge base, and use Ollama to download and install the DeepSeek-R1 large language model.

[0086] Step S12: Organize and collect common electronic map industry style specification documents, add style description tags according to specific style specifications, and upload them to the Milvus vector knowledge base.

[0087] The specific steps of step S2 include:

[0088] Step S21: The map layers appearing in the electronic map are divided into three categories according to the geometric information geom: Point, Polyline, and Polygon. Different geom types correspond to different layer style types: Point layer styles support icon, scale, textField, font and other icon and text annotation style information; Polyline layer styles support line segment style information such as lineWidth, outlineWidth, lineColor, OutlineColor, and lineType; Polygon layer styles support plane and extruded surface style information such as fillColor and extrudeField.

[0089] Step S22: Various types of layers in the electronic map are designed with filter conditions for map layers according to consistent structural requirements, where the filter attributes mainly include the field filter condition array properties, the minimum zoom level zoomMin, and the maximum zoom level zoomMax; the properties array contains attribute field filter judgment conditions including field, value, and condition, where field represents the attribute field name in the layer attribute information, value represents the corresponding field value in the layer attribute information, and condition represents the judgment relationship between the field name and the field value; the judgment relationship of the numerical attribute field includes: greater than, less than, equal to, greater than or equal to, less than or equal to, and the judgment relationship of the text attribute field includes: contains, does not contain.

[0090] Step S23: Figure 2 As shown in the figure, the style legend of a layer is composed of attributes such as style and filter. A single layer can be applied to multiple legends at the same time, and multiple legends can constitute a complete electronic map style configuration object mapStyle.

[0091] The specific steps of step S3 include:

[0092] Step S31: Gather the content of the large model language prompt word Prompt, which needs to include: user requirement text description, electronic map data source layer metadata information metaData, electronic map style configuration format requirements, etc.; wherein metaData includes layer basic information, layer geometry type information, layer attribute field type and description information, etc.

[0093] Step S32: Figure 3 The structure shown here constitutes the large language model prompt word Prompt, and the electronic map style requirements are uploaded through the Ollama context dialogue interface.

[0094] The specific steps of step S4 include:

[0095] Step S41: Parse the large language model answer content and extract the electronic map style configuration object mapStyle in the returned text.

[0096] Step S42: traverse the legend in mapStyle in sequence and obtain layer unique value data, compare the layer in the electronic map data source according to the layer unique value and add the corresponding layer to the electronic map rendering framework.

[0097] Step S43: Start electronic map rendering and load layer slices according to the current view range and wait for rendering; when rendering a specific layer slice, obtain the legend array of the corresponding layer in mapStyle, such as Figure 4 As shown, the style that meets the filter condition is matched according to the level scaling information, geometric information and attribute information of the current layer slice, and the electronic map rendering of a specific layer slice is performed according to the style information.

[0098] Step S44: sequentially loading and rendering the required layer slices within the current view range, completing the design and configuration process of the electronic map model style required by the user.

[0099] An embodiment of the present invention further provides an electronic map style configuration device based on large model question and answer, comprising: at least one memory and at least one processor;

[0100] The at least one memory is configured to store a machine-readable program;

[0101] The at least one processor is used to call the machine-readable program to implement the electronic map style configuration method based on large model question and answer described in the above embodiment.

[0102] An embodiment of the present invention further provides a computer-readable medium having computer instructions stored thereon. When executed by a processor, the computer instructions cause the processor to execute the electronic map style configuration method based on large-scale model question-and-answering as described in the above-mentioned embodiments. Specifically, a system or device equipped with a storage medium can be provided. The storage medium stores software program code that implements the functions of any of the above-mentioned embodiments, and the computer (or CPU or MPU) of the system or device can be caused to read and execute the program code stored in the storage medium.

[0103] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute part of the present invention.

[0104] Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0105] In addition, it should be clear that the functions of any of the above embodiments can be achieved not only by executing the program code read by the computer, but also by enabling the operating system operating on the computer to complete part or all of the actual operations based on the instructions of the program code.

[0106] In addition, it can be understood that the program code read from the storage medium is written into the memory provided in the expansion board inserted into the computer or into the memory provided in the expansion unit connected to the computer, and then based on the instructions of the program code, the CPU installed on the expansion board or expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above embodiments.

[0107] The present invention has been shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the code review methods in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the scope of protection of the present invention.

Claims

1. A method for configuring electronic map styles based on large model question answering, characterized in that: The implementation of this method includes the following steps: Step S1: Build a large-scale question-answering framework using Ollama+DeepSeek+Milvus technologies, and organize and import standard electronic map styles from various industries; Step S2: Based on the principle of separating attribute filtering conditions from feature styles, construct an electronic map style configuration format; Step S3: Fusing natural language input content, geometric information and attribute information of electronic map data sources to construct a large language model prompt word; Step S4: extract the style configuration content in the text returned by the large model, convert it into a style matching method and update the electronic map rendering style.

2. The electronic map style configuration method based on large model question and answer according to claim 1 is characterized in that: The specific steps of step S1 include: Step S11: Install and deploy the Ollama large model running framework and Milvus vector knowledge base, and use Ollama to download and install the DeepSeek-R1 large language model; Step S12: Organize and collect common electronic map industry style specification documents, add style description tags according to specific style specifications, and upload them to the Milvus vector knowledge base.

3. The electronic map style configuration method based on large model question and answer according to claim 1 is characterized in that: The specific steps of step S2 include: Step S21: Classify the map layers appearing in the electronic map into three categories according to their geometric information: Point, Polyline, and Polygon. Different geom types correspond to different layer style types: Point layer styles support icon and text annotation style information; Polyline layer styles support line segment style information; Polygon layer styles support plane and extruded surface style information; Step S22: Design filter conditions for each layer in the electronic map according to consistent structural requirements, where the filter attributes include the field filter condition array properties, the minimum zoom level zoomMin, and the maximum zoom level zoomMax; Step S23: Composing a style legend of the layer based on the style and filter attributes, wherein a single layer can be applied to multiple legends at the same time, and multiple legends constitute a complete electronic map style configuration object mapStyle.

4. The electronic map style configuration method based on large model question and answer according to claim 3 is characterized in that: The step S21, Icon and text annotation style information includes: icon, scale, textField, font information; Line segment style information includes lineWidth, outlineWidth, lineColor, OutlineColor, and lineType information; Plane and extruded surface style information includes fillColor and extrudeField information.

5. The electronic map style configuration method based on large model question and answer according to claim 3 is characterized in that: The field filter condition array properties contains the attribute field filter judgment conditions including field, value, and condition. field represents the attribute field name in the layer attribute information; value represents the corresponding field value in the layer attribute information; Condition represents the judgment relationship between field name and field value; The judgment relationships of numerical attribute fields include: greater than, less than, equal to, greater than or equal to, less than or equal to; the judgment relationships of text attribute fields include: contains, does not contain.

6. The electronic map style configuration method based on large model question and answer according to claim 1 is characterized in that: The specific steps of step S3 include: Step S31: Gathering the content of the large model language prompt word Prompt, including: user requirement text description, electronic map data source layer metadata information metaData, electronic map style configuration format requirements; wherein metaData includes layer basic information, layer geometry type information, layer attribute field type and description information; Step S32: compose a large language model prompt word Prompt, and upload the electronic map style requirements through the Ollama context dialogue interface.

7. The electronic map style configuration method based on large model question and answer according to claim 3 is characterized in that: The specific steps of step S4 include: Step S41: Parse the large language model answer content and extract the electronic map style configuration object mapStyle in the returned text; Step S42: traverse the legend in mapStyle in sequence and obtain layer unique value data, compare the layer in the electronic map data source according to the layer unique value and add the corresponding layer to the electronic map rendering framework; Step S43: Start electronic map rendering, load layer slices according to the current view range, and wait for rendering; when rendering a specific layer slice, obtain the legend array of the corresponding layer in mapStyle, match the style that meets the filter condition based on the level scaling information, geometry information and attribute information of the current layer slice, and execute electronic map rendering of the specific layer slice according to the style information; Step S44: sequentially loading and rendering the required layer slices within the current view range, completing the design and configuration process of the electronic map model style required by the user.

8. An electronic map style configuration system based on large model question and answer, characterized in that: include: Large model question-answering framework construction module, used to build a large model question-answering framework, organize and import standard style specifications of electronic maps in various industries; The electronic map style configuration module is used to implement the electronic map style configuration format based on the principle of separating attribute filtering conditions and feature styles; The prompt word construction module is used to integrate natural language input content, electronic map data source geometry information and attribute information to build a large language model prompt word; The electronic map style update module is used to extract the style configuration content in the text returned by the large model, convert it into a style matching method, and update the electronic map rendering style; The system implements electronic map style configuration through the method described in any one of claims 1 to 7.

9. An electronic map style configuration device based on large model question and answer, characterized in that: include: at least one memory and at least one processor; The at least one memory is configured to store a machine-readable program; The at least one processor is configured to call the machine-readable program to implement the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer-readable medium stores computer instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 7.

Images