A contour plot drawing method, device, equipment, medium and product

Abstract

This disclosure provides a method, apparatus, device, medium, and product for drawing contour maps. The method includes: acquiring descriptive information about contour map drawing requirements; generating a contour map drawing task based on the descriptive information; decomposing the contour map drawing task to obtain multiple sub-tasks and an execution order of the sub-tasks; and scheduling an intelligent agent module corresponding to each sub-task to execute the sub-tasks sequentially based on the execution order of the sub-tasks, thereby obtaining a contour map that meets the contour map drawing requirements. Through the technical solution of this disclosure, intelligent control of the entire process from natural language input to automatic generation of contour maps of a target area is achieved, improving the intelligence, interactivity, and drawing accuracy of contour map drawing.

Description

Technical Field

[0001] This disclosure relates to the field of geological exploration and development technology, and in particular to a method, apparatus, equipment, medium and product for drawing contour maps. Background Technology

[0002] Contour maps are one of the important tools for spatial visualization in geosciences. Their basic principle is based on spatial statistics, which connects spatial points with the same attribute values ​​into a continuous curve through interpolation algorithms. This reflects the spatial distribution pattern and trend of variables in a two-dimensional plane. They are widely used in the expression and analysis of various geological variables such as stratum thickness, mineral grade, porosity, aquifer thickness, groundwater level, and seismic intensity.

[0003] In the early days of geological mapping, contour maps were mainly drawn using traditional manual methods, including manual interpolation, scale estimation, and equidistant profile methods. With the development of spatial information technology and geoscientific statistical theory, computer-aided mapping and mathematical interpolation algorithms have gradually been introduced into contour map drawing. For example, inverse distance weighting, spline function methods, and kriging methods are widely used in geological spatial interpolation mapping.

[0004] Contour maps are an important tool for modeling and representing spatial variables. Traditional generation methods rely on expert experience and numerical models, demanding not only solid geoscientific knowledge and cartographic skills but also complex workflows, difficulties in parameter adjustment, and untimely feedback. Furthermore, traditional generation methods struggle to meet the interactive, intelligent, and visual representation needs of non-professional users. Summary of the Invention

[0005] This disclosure provides a method, apparatus, device, medium, and product for drawing contour maps, enabling intelligent control of the entire process of automatically generating contour maps of a target area from natural language input.

[0006] According to one aspect of this disclosure, a method for drawing contour maps is provided, comprising:

[0007] Obtain the description information of the contour line drawing requirements, and generate a contour line drawing task based on the description information of the contour line drawing requirements;

[0008] The contour line drawing task is decomposed into multiple sub-tasks and the execution order of the multiple sub-tasks;

[0009] Based on the execution order of the multiple subtasks, the intelligent agent module corresponding to each subtask is scheduled to execute the multiple subtasks in sequence to obtain a contour map that meets the contour drawing requirements.

[0010] According to another aspect of this disclosure, an apparatus for drawing contour maps is provided, the apparatus comprising:

[0011] The contour line drawing task generation module is used to obtain the description information of the contour line drawing requirements and generate contour line drawing tasks based on the description information of the contour line drawing requirements.

[0012] The execution order acquisition module is used to decompose the contour line drawing task into multiple sub-tasks and the execution order of the multiple sub-tasks;

[0013] The contour map generation module is used to schedule the intelligent agent module corresponding to each subtask to execute the multiple subtasks in sequence based on the execution order of the multiple subtasks, so as to obtain a contour map that meets the contour drawing requirements.

[0014] According to another aspect of this disclosure, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the contour map drawing method described in any embodiment of this disclosure.

[0018] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores computer instructions for causing a processor to execute and implement the contour plot drawing method described in any embodiment of this disclosure.

[0019] According to another aspect of this disclosure, a computer program product is provided, which, when executed by a processor, implements a method for drawing contour maps as described in any of the embodiments of this disclosure.

[0020] This embodiment of the disclosure obtains description information of the contour line drawing requirements, generates a contour line drawing task based on the description information, decomposes the contour line drawing task into multiple sub-tasks and the execution order of the multiple sub-tasks, and schedules the intelligent agent module corresponding to each sub-task to execute the multiple sub-tasks in sequence based on the execution order of the multiple sub-tasks, thereby obtaining a contour map that meets the contour line drawing requirements. By generating a contour line drawing task based on the description information of the contour line drawing requirements, decomposing the contour line drawing task into multiple sub-tasks, and forming a collaborative working mechanism of multiple sub-tasks, this embodiment realizes intelligent control of the entire process from natural language input to automatic generation of contour maps of target areas, improving the intelligence, interactivity, and drawing accuracy of contour map drawing.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a method for drawing contour maps according to an embodiment of this disclosure;

[0024] Figure 2 This is a flowchart of a mapping task in an embodiment of this disclosure;

[0025] Figure 3 This is a flowchart illustrating the process of drawing a contour map according to an embodiment of this disclosure;

[0026] Figure 4 This is a schematic diagram of the contour line drawing results in the embodiments of this disclosure;

[0027] Figure 5 This is a schematic diagram of the structure of a contour map drawing device according to an embodiment of this disclosure;

[0028] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0032] Figure 1 This flowchart illustrates a method for drawing contour maps according to an embodiment of the present disclosure. This embodiment is applicable to situations where contour maps meeting requirements are drawn based on information input from natural language. The method can be executed by the contour map drawing device described in this embodiment. This device can be implemented using software and / or hardware and can be integrated into electronic devices such as computer equipment, servers, mobile terminals, and processors. Figure 1 As shown, the method specifically includes the following steps:

[0033] S110, Obtain the description information of the contour line drawing requirements, and generate a contour line drawing task based on the description information of the contour line drawing requirements.

[0034] In this embodiment, the description of the contour line drawing requirement can be specifically understood as the user's requirement information for generating a contour map, input via text or voice. This description information may include, but is not limited to, the target work area, variable type, interpolation method, and map style requirements. For example, the description of the contour line drawing requirement could be "Draw a contour map of the Permian Longtan Formation thickness in the Sichuan Basin, using the ordinary kriging method with a spherical model." The description of the contour line drawing requirement is the core basis for generating the contour line drawing task, directly determining the subsequent specific process and parameter configuration. The contour line drawing task can be specifically understood as a task generated based on the user-input description of the contour line drawing requirement, which involves drawing the contour map. The contour line drawing task can be a structured task instruction.

[0035] Specifically, users input descriptions of their contour line drawing requirements via text or voice through the front-end interactive interface. The system combines a Large Language Model (LLM) with a knowledge graph built on a graph database to convert the user's input into structured instructions, resulting in contour line drawing tasks. This enables the system to understand diverse, complex, or long texts in natural language tasks, while also ensuring the accuracy of geological entities and parameters. Furthermore, it automatically completes missing information, corrects ambiguities, and improves execution efficiency.

[0036] Optionally, based on the above embodiments, generating a contour drawing task based on the descriptive information of the contour drawing requirement includes: performing semantic modeling on the natural language description of the contour drawing requirement; using a semantic transformation model to perform vectorized representation and contextual semantic understanding of the text to obtain the corresponding semantic representation; based on the semantic representation, using the deep semantic parsing capability of a semantic recognition model to identify elements in the task, including task actions, geological entities, spatial regions, variable types, interpolation methods and their parameters; and combining a predefined task template and a geoscience knowledge graph to perform semantic role mapping on the identification results, converting the natural language description into a structured or semi-structured contour drawing task.

[0037] In this embodiment, semantic representation can be specifically understood as a vectorized expression generated by a semantic transformation model based on contextual semantics, used to capture the deep semantic relationships between task elements in natural language. This vectorized representation not only makes the descriptive information computable but also provides a foundation for subsequent semantic reasoning and task generation. The semantic transformation model can be a large language model. The semantic recognition model can be specifically understood as a model used to parse natural language requirements and accurately extract key task elements. Its core function is to locate and identify the core information required for contour line drawing from the semantic representation, paving the way for subsequent generation of structured tasks.

[0038] Specifically, semantic modeling is performed on the natural language description of the contour line drawing requirements. A semantic transformation model is used to vectorize the text and understand its contextual semantics to obtain the corresponding semantic representation. A task template is preset, which is a structured format pre-defined for the contour line drawing task, defining the core fields and their organization required to complete the contour line drawing. The deep semantic parsing capability of the semantic recognition model is used to identify the component parameters in the task, including but not limited to task actions, geological entities, spatial regions, variable types, interpolation methods and their parameters. Task elements are mapped to the corresponding fields in the task template, thereby generating a complete and standardized structured contour line drawing task.

[0039] For example, the task "Draw contour maps of the Permian Longtan Formation thickness in the Sichuan Basin using the ordinary kriging method with a spherical model" can be transformed into a semantic representation. Through contextual semantic understanding, the system automatically extracts "drawing" as the core action, "Sichuan Basin," "Permian Longtan Formation," and "stratum thickness" as the objects of action, and "ordinary kriging" and "spherical" as the method and model. Subsequently, the system maps the parsed results to a task template, resulting in a structured contour drawing task as follows: {"region": "Sichuan Basin","formation": "Permian Longtan Formation","variable": "stratum thickness","method": "ordinary kriging","model": "spherical",...}. This contour drawing task can be used for subsequent data retrieval, interpolation modeling, map rendering, and other processes, achieving automatic mapping and precise execution from user natural language to drawing tasks. This process not only realizes the automatic parsing and structured execution of natural language tasks but also significantly improves the interactive flexibility, automation level, and response efficiency of the intelligent drawing system, providing intelligent technical support for the rapid generation of complex geological maps.

[0040] S120, the contour line drawing task is decomposed to obtain multiple sub-tasks and the execution order of the multiple sub-tasks.

[0041] In this embodiment, task decomposition can be understood as the process of breaking down a structured contour line drawing task into a series of interconnected subtasks according to logical and technical implementation steps, and clarifying the execution order and dependencies of each subtask. A subtask can be understood as a task with independent functional objectives and clearly defined operations, formed after the contour line drawing task is decomposed. Each subtask corresponds to a specific step in the overall process, requires specific data input, performs specific operations, and outputs results that can be directly invoked by subsequent subtasks. The execution order can be understood as a clear set of execution order rules for the multiple decomposed subtasks based on the logical dependencies between them, such as data input / output relationships. This rule constrains the start and completion order of subtasks, ensuring that the output of the previous subtask can serve as valid input for subsequent subtasks, avoiding process chaos or resource waste.

[0042] Specifically, the key fields in the contour line drawing task are analyzed, and based on these fields, multiple subtasks and their execution order are derived. Breaking the task down into clearly defined, independent subtasks facilitates precise management; clarifying the execution order lays the foundation for collaborative scheduling, ensuring that each subtask is logically and orderly connected, thus improving the overall process efficiency and stability.

[0043] Optionally, based on the above embodiments, the contour line drawing task is decomposed to obtain multiple subtasks and the execution order of the multiple subtasks, including: using a large language model combined with contour line mapping process knowledge and context information to identify the task fields and their corresponding process nodes in the structured contour line drawing task, with each process node corresponding to a subtask; generating a dependency structure between multiple subtasks based on the semantic dependencies between task fields, logical constraints in the knowledge graph, and / or the order of the contour line basic drawing process; determining the execution order of the subtasks according to the dependency structure, and using this execution order for the intelligent agent module to schedule and execute the interpolation drawing process.

[0044] In this embodiment, the knowledge of contour mapping process can be specifically understood as a standardized process knowledge system that has been verified through industry practice, covering the entire process of contour drawing. It encompasses all core logic, operational norms, and technical constraints from requirements analysis to output, and serves as the core basis for task decomposition by the large language model. Contextual information can be specifically understood as the sum of all related information relevant to the current task and used to assist in understanding the task objectives, constraints, and execution scenarios. This may include, but is not limited to, historical information from the dialogue process.

[0045] Semantic dependencies can be specifically understood as the dependency relationships formed between structured task fields based on their inherent meaning, business logic, or linguistic associations. This relationship is not a simple sequential arrangement, but a necessary logical association determined by its semantic connotation; that is, the existence or completion of one element is the basis for the existence or execution of another element. Logical constraints in a knowledge graph can be specifically understood as logical constraints imposed through the association relationships and predefined rules between entities in the knowledge graph. The contour line basic drawing process can be specifically understood as a predefined, standardized drawing process based on the general logic of contour line drawing. This process covers all key stages from obtaining descriptive information about contour line drawing requirements to outputting contour line maps, serving as a benchmark reference for task decomposition. Identifying task fields in a structured contour line drawing task can be specifically understood as extracting key information fields directly related to each stage of the contour line basic drawing process from the structured contour line drawing task and matching and associating these fields with the standard stages in the basic process. A process node can be understood as a node with a clear functional boundary that is broken down in the contour line drawing process. Each node corresponds to a key operation step in the entire contour line drawing process and is an intermediate unit connecting the basic process framework and specific sub-tasks.

[0046] Specifically, based on the large language model combined with knowledge of contour mapping processes and contextual information, the task fields and their corresponding contour mapping process nodes in the contour mapping task are determined, with each process node corresponding to a subtask. Based on the semantic dependencies between task fields in the contour mapping task content, logical constraints in the knowledge graph, and / or the sequence of the basic contour mapping process, a dependency structure among multiple subtasks is generated. The execution order of the subtasks is determined based on this dependency structure, and this execution order is used for scheduling and interpolation mapping processes by the intelligent agent module. To explicitly represent the execution order of the subtasks, a task scheduler is introduced to output its mapping task flow, such as... Figure 2 As shown.

[0047] Optionally, based on the above embodiments, each subtask includes at least one of the following: the intelligent agent module identifier corresponding to the subtask, expected input / output information, and the pre-task / post-task information of the subtask.

[0048] In this embodiment, the intelligent agent module can be specifically understood as a module with specific functions that can independently execute corresponding sub-tasks. Optionally, the intelligent agent module can be an Agent (an intelligent agent with task perception and reasoning capabilities), and each sub-task is executed by the corresponding Agent. The intelligent agent module identifier corresponding to the sub-task can be specifically understood as a unique identification identifier used to uniquely point to the intelligent agent module capable of executing the sub-task. Its core function is to establish a precise mapping relationship between the sub-task and the corresponding execution module, ensuring that the task is correctly assigned to the intelligent agent module with the appropriate function. For example, the identifier of the "task scheduling agent module" can be set to "Agent-0"; the identifier of the "data retrieval agent module" can be set to "Agent-1"; the identifier of the "interpolation modeling agent module" can be set to "Agent-2"; the identifier of the "map generation agent module" can be set to "Agent-3"; and the identifier of the "user feedback agent module" can be set to "Agent-4". Using Agents allows for focus on a single sub-task, improving the processing accuracy of each stage through specialized capabilities, and avoiding logical redundancy caused by a single system being compatible with multiple tasks.

[0049] Expected input / output information can be specifically understood as predefined input or output information for a specific subtask. This includes the required input data format and content range before the subtask is executed, as well as the output format after execution. It is a key constraint to ensure smooth connection between the subtask and its preceding and following stages. Pre- and post-task information for a subtask can be specifically understood as predefined task information for each subtask, used to clarify its logical relationship within the overall task flow. This includes pre-defined tasks that must be completed before the subtask is executed (i.e., dependent upstream subtasks), and post-tasks that can be triggered after the subtask is executed (i.e., related downstream subtasks). Its core function is to ensure that subtasks are executed in a predetermined order by clarifying the sequential dependencies between tasks.

[0050] Optionally, based on the above embodiments, the method further includes: performing a matching verification based on the expected input / output information in the subtask and the intelligent agent module identifier corresponding to the subtask; if the expected input / output information in the subtask and the processing function corresponding to the intelligent agent module identifier corresponding to the subtask do not match, further decomposing the subtask.

[0051] In this embodiment, the matching verification can be specifically understood as a verification process that compares the expected input / output information of a subtask with the processing functions bound to the corresponding intelligent agent module identifier to determine whether the intelligent agent module has the ability to execute the subtask. Its core purpose is to detect in advance whether there are subtask allocation errors, ensuring that each subtask is assigned to an intelligent agent module with matching functions, and avoiding task execution failure or abnormal results due to insufficient module capabilities.

[0052] Specifically, a matching verification is performed based on the expected input / output information in the subtask and the corresponding intelligent agent module identifier. If the expected input / output information in the subtask and the processing function corresponding to the intelligent agent module identifier do not match, the subtask is further decomposed. For example, it can be determined whether the intelligent agent module supports the expected input data format / type of the subtask; whether the intelligent agent module can achieve the expected processing goal of the subtask; and whether the intelligent agent module can generate an output result that conforms to the expected format of the subtask.

[0053] S130, based on the execution order of the multiple sub-tasks, schedule the intelligent agent module corresponding to each sub-task to execute the multiple sub-tasks in sequence to obtain a contour map that meets the contour drawing requirements.

[0054] Specifically, based on the execution order of the subtasks, the corresponding intelligent agent modules execute the tasks sequentially. Throughout the process, the scheduling module synchronizes the execution status of each agent in real time to ensure that data is transmitted in order and subtasks are seamlessly connected.

[0055] Optionally, based on the above embodiments, the task scheduling agent module performs the scheduling process for the intelligent agent modules corresponding to the multiple subtasks; the scheduling process further includes: using the task scheduling agent module to perform data transfer, status synchronization and result feedback among the intelligent agent modules corresponding to the multiple subtasks based on the execution order of the subtasks, so as to execute the multiple subtasks.

[0056] Specifically, the task scheduling agent module initiates scheduling based on the execution order and dependencies of subtasks, monitors the execution status of preceding subtasks, and extracts the output data of the corresponding intelligent agent module upon completion. After format validation to match the expected input requirements of subsequent subtasks, the data is then directed to the target module. The "pending execution / in execution / success / failure" status of the intelligent agent modules is synchronized to the task scheduling agent module in real time, dynamically adjusting the execution strategy. When all subtasks are completed sequentially, the scheduling module collects the execution results of each module, ensuring that the contour line drawing subtasks are executed efficiently and collaboratively in sequence. It should be noted that the task scheduling agent module achieves data transmission, status synchronization, and result feedback to the corresponding intelligent agent modules of each subtask through a communication protocol, which can be implemented using MCP (Model Context Protocol). Using MCP ensures consistent information exchange between the task scheduling agent and the intelligent agent modules of each subtask by standardizing data transmission formats, status identifiers, and result feedback rules through a unified protocol, avoiding collaboration gaps caused by interface incompatibility.

[0057] Optionally, based on the above embodiments, the plurality of subtasks includes at least a portion of the data retrieval subtask, the interpolation modeling subtask, and the graph drawing subtask; correspondingly, the intelligent agent module includes at least a portion of the data retrieval agent module, the interpolation modeling agent module, and the graph drawing agent module.

[0058] In this embodiment, the data retrieval subtask can be specifically understood as a subtask specifically responsible for accurately extracting target data from the database after the contour line drawing task is decomposed. This subtask can be implemented by a data retrieval agent module, which can be Agent-0. Its core objective is to provide standardized and complete basic data for subsequent interpolation modeling and map drawing subtasks, serving as the data input starting point for the contour line drawing process. The interpolation modeling subtask can be specifically understood as a subtask that follows the data retrieval task after the contour line drawing task is decomposed. This subtask can be implemented by an interpolation modeling agent module, which can be Agent-1. Its core objective is to transform the data output from the data retrieval subtask into a continuous spatial data model using a scientific interpolation algorithm, providing raster data support that can be directly used for contour line extraction for subsequent map drawing subtasks. The map drawing subtask can be understood as the subtask of drawing contour maps after the contour drawing task is decomposed. It can be implemented by the map drawing agent module, which can be Agent-2. Its core objective is to extract, beautify and generate standardized maps based on the continuous raster data output by the interpolation modeling subtask, and finally output contour map results that meet the user's needs.

[0059] Optionally, based on the above embodiments, the data retrieval subtask includes data retrieval parameters, which include at least one of geological work area, stratigraphic unit, and variable type; the data retrieval agent module constructs a graph database query statement based on the retrieval parameters, and performs data retrieval in the database through the graph database query statement to obtain the target data.

[0060] In this embodiment, the data retrieval parameters can be specifically understood as parameters used to accurately locate the basic data required for contour line drawing. They are key input information for the data retrieval subtask, including key dimensions related to geological data, including at least one or more of the following: geological work area, stratigraphic unit, and variable type. Their function is to provide clear query basis for the data retrieval agent module, ensuring that the target data extracted from the database is highly matched with the contour line drawing requirements.

[0061] Specifically, the data retrieval agent module establishes a connection with the database. The MCP data interface (mcp_tool) can be used to connect the data retrieval agent module to the database, and graph database query statements can be used to retrieve and call data, efficiently obtaining and integrating cartographic data based on graph database retrieval.

[0062] Optionally, based on the above embodiments, the interpolation modeling subtask includes an interpolation method identifier, and the interpolation modeling proxy module performs interpolation processing on the target data based on the interpolation method corresponding to the interpolation method identifier to obtain the interpolation result.

[0063] In this embodiment, the interpolation method identifier can be understood as a unique marker used to specify the type of interpolation algorithm. It forms a one-to-one correspondence with the various pre-defined interpolation methods in the interpolation modeling subtask, and serves as the direct basis for the interpolation modeling proxy module to select a specific interpolation algorithm. For example, if the interpolation method identifier "Kriging-01" corresponds to "ordinary Kriging interpolation" and the identifier "IDW-02" corresponds to "inverse distance weighted interpolation," when the interpolation modeling subtask passes in the identifier "Kriging-01," the interpolation modeling proxy module will directly call the pre-defined ordinary Kriging algorithm logic, performing semi-variogram fitting, parameter optimization, and other operations based on the target data, ultimately generating the corresponding interpolation result. The core function of this identifier is to standardize the interpolation algorithm selection process, ensuring that the interpolation method accurately matches the task requirements and avoiding algorithm invocation errors.

[0064] Specifically, the interpolation modeling proxy module can call the interpolation modeling tool through MCP, perform interpolation processing on the target data according to the corresponding interpolation method identifier, and obtain the interpolation result. The interpolation result can be encapsulated in the MCP protocol format.

[0065] It should be noted that when the user does not select an interpolation method, the interpolation method identifier is set to the default identifier. For example, the default identifier can be set to the identifier corresponding to the ordinary Kriging interpolation method. When the user does not select an interpolation method, the ordinary Kriging interpolation method will be used by default.

[0066] Optionally, based on the above embodiments, the map drawing proxy module sequentially performs contour line extraction, vector layer construction, map style rendering, legend generation, and pattern generation based on the interpolation results, and outputs a contour map.

[0067] Specifically, based on the interpolation results, the map drawing proxy module performs contour extraction, vector layer construction, map style rendering, legend generation, and pattern generation. Contour extraction requires statistical analysis of the interpolation results data and classification of numerical ranges. The system defaults to using an equidistant classification method to divide data values ​​into several levels, while also incorporating an equal-frequency classification method and a natural breakpoint classification method, which can be flexibly switched according to task requirements or data distribution characteristics. After completing the data classification, the system calls the classic Marching Squares algorithm to progressively extract contour lines of corresponding levels on a regular grid and output vectorized curve data, thus forming a preliminary contour map structure.

[0068] Constructing a vector layer requires converting the extracted contour data into a standard geographic information format, such as GeoJSON or Shapefile, and assigning it a unified spatial reference coordinate system, such as WGS84 (World Geodetic System 1984), to ensure compatibility with other spatial data layers. Each contour curve contains complete geometric information and corresponding numerical attributes, supporting subsequent map overlay, spatial analysis, and layer control operations.

[0069] Map style rendering requires automatically loading cartographic templates and performing style mapping based on the map parameters defined in the structured contour drawing task, including but not limited to color schemes and line widths. Color mapping can use linear gradation or natural breakpoints, combined with gradient color bands, such as light yellow to dark red, to represent different contour intervals, ensuring the map is intuitive, clear, and has good visual resolution. It should be noted that default map parameters are pre-set; if no map parameters are specified in the contour drawing task, the default map parameters will be used.

[0070] Legend generation needs to produce legends that conform to geological industry mapping standards, including but not limited to contour line interval descriptions, color labels, and unit information, and supports custom adjustments to parameters such as legend position and display range. Layer control is supported, such as allowing independent switching between visibility and concealment, adjustment of stacking order, and transparency of the generated contour line layer and associated base layer. Style adjustments are also possible; for example, users can freely switch between overall and local views through zoom operations, and combine style adjustments to enable detailed observation at different scales, facilitating multi-scale interactive exploration and visual comparison.

[0071] Map generation requires converting the final rendered maps into various output formats, including but not limited to bitmap images (such as PNG and JPEG), vector data (such as Shapefile and GeoJSON), and interactive web-based maps (such as WebGIS visualization components). The generated results can be directly applied to geographic information platforms, research reports, database entries, or user terminal displays, ensuring high compatibility and usability.

[0072] Optionally, based on the above embodiments, the subtask further includes a user feedback parsing subtask; the intelligent agent module further includes a user feedback parsing agent module.

[0073] In this embodiment, the user feedback parsing subtask can be specifically understood as a subtask specifically responsible for receiving and parsing user feedback suggestions on the generated contour map. This subtask is implemented by the user feedback parsing agent module, which can be Agent-3. Its core objective is to transform the user's natural language description into structured instructions, forming a "drawing-feedback-iteration" mechanism.

[0074] Optionally, based on the above embodiments, the method further includes: obtaining user feedback text, converting the user feedback text into a graph update task through the user feedback parsing proxy module; performing task analysis on the graph update task to obtain at least one new subtask; and scheduling the intelligent proxy module corresponding to each new subtask to execute the new subtask sequentially based on the execution order of the new subtask to obtain an updated contour map.

[0075] In this embodiment, user feedback text can be specifically understood as text submitted by the user in natural language after obtaining the initial contour map, requesting adjustments to the map's quality or content. This text serves as the input basis for triggering the contour map update process. The map update task can be specifically understood as a task generated by the user feedback parsing proxy module after structurally parsing the user feedback text. This task contains clear update goals, scope, and requirements and serves as the core intermediary connecting the user's unstructured needs with the system's automated update operations, guiding subsequent task analysis and the generation of new sub-tasks. The updated contour map can be specifically understood as the final result map generated after specifically optimizing the initial contour map by executing new sub-tasks derived from the map update task. It accurately responds to the adjustment requests in the user feedback text and meets user expectations in terms of data integrity, spatial accuracy, and visualization effects.

[0076] Specifically, after the contour map is output, users can provide feedback on its representation based on their professional judgment, cartographic habits, or specific application needs. Based on the user feedback text, a large language model parses the user input and generates corresponding structured instructions, i.e., the map update task. Task analysis is performed on the map update task, resulting in at least one new subtask. Based on the execution order of the new subtasks, the task scheduling agent module schedules the corresponding intelligent agent module to execute each new subtask sequentially, resulting in the updated contour map.

[0077] For example, in response to user feedback to "change the color band to a blue-red gradient," the large language model can identify the keywords "color band" and "blue-red gradient," and automatically generate the following structured instruction, i.e., the graph update task: {"type": "update_style","target": "colorMap","value": "BlueRed"}. After receiving the graph update task instruction returned by the user feedback parsing agent module, the task scheduling agent module dynamically updates the key parameters in the current task execution context according to the MCP model context protocol, and reschedules the intelligent agent modules corresponding to the relevant subtasks. This mechanism achieves a rapid closed-loop response from user feedback to parameter adjustment to graph update.

[0078] The technical solution of this embodiment obtains the description information of the contour line drawing requirements, generates a contour line drawing task based on the description information, decomposes the contour line drawing task into multiple sub-tasks and the execution order of the multiple sub-tasks, and schedules the intelligent agent module corresponding to each sub-task to execute the multiple sub-tasks in sequence based on the execution order of the multiple sub-tasks, thereby obtaining a contour map that meets the contour line drawing requirements. By generating a contour line drawing task from the description information of the contour line drawing requirements, decomposing the contour line drawing task into multiple sub-tasks, and forming a collaborative working mechanism of multiple sub-tasks, intelligent control of the entire process from natural language input to automatic generation of contour maps of target areas is achieved, improving the intelligence, interactivity, and drawing accuracy of contour map drawing.

[0079] Based on the above embodiments, an optional example is provided, which can be used to analyze typical areas of the Sichuan Basin and draw contour maps of the Permian Longtan Formation thickness in the Sichuan Basin.

[0080] according to Figure 3 The workflow diagram shown illustrates how, based on 291 wells in the Sichuan Basin, the user inputs "draw contour maps of the Permian Longtan Formation thickness in the Sichuan Basin using the ordinary kriging method with a spherical model." The system then analyzes the user's requirements based on the description of the contour drawing needs and generates a structured contour drawing task.

[0081] The task scheduling agent module distributes the contour plotting task to the data retrieval agent module. Based on the contour plotting task, it generates standardized query statements to retrieve relevant geological data from the spatial database and outputs the query results. The retrieval results are then passed to the interpolation modeling agent module, which performs ordinary kriging based on the contour plotting task and outputs the interpolation results. The map plotting agent module performs boundary clipping, contour division, and color banding on the interpolation results, outputting GeoJSON contour data, image files, and Shapefile vector data, achieving full automation from natural language input to geological map output. (See figure.) Figure 4 A schematic diagram of the contour lines.

[0082] Figure 5 This is a schematic diagram of a contour map drawing device provided in an embodiment of the present disclosure. This embodiment is applicable to situations where contour maps meeting requirements are drawn based on information input from natural language. The device can be implemented using software and / or hardware, and can be integrated into any device that provides contour map drawing functionality, such as… Figure 5 As shown, the device for drawing contour maps specifically includes: a contour drawing task generation module 210, an execution order acquisition module 220, and a contour map generation module 230.

[0083] The contour line drawing task generation module 210 is used to obtain the description information of the contour line drawing requirements and generate a contour line drawing task based on the description information of the contour line drawing requirements.

[0084] The execution order acquisition module 220 is used to decompose the contour line drawing task to obtain multiple sub-tasks and the execution order of the multiple sub-tasks;

[0085] The contour map generation module 230 is used to schedule the intelligent agent module corresponding to each subtask to execute the multiple subtasks in sequence based on the execution order of the multiple subtasks, so as to obtain a contour map that meets the contour drawing requirements.

[0086] The technical solution of this embodiment obtains the description information of the contour line drawing requirements, generates a contour line drawing task based on the description information, decomposes the contour line drawing task into multiple sub-tasks and the execution order of the multiple sub-tasks, and schedules the intelligent agent module corresponding to each sub-task to execute the multiple sub-tasks in sequence based on the execution order of the multiple sub-tasks, thereby obtaining a contour map that meets the contour line drawing requirements. By generating a contour line drawing task from the description information of the contour line drawing requirements, decomposing the contour line drawing task into multiple sub-tasks, and forming a collaborative working mechanism of multiple sub-tasks, intelligent control of the entire process from natural language input to automatic generation of contour maps of target areas is achieved, improving the intelligence, interactivity, and drawing accuracy of contour map drawing.

[0087] Based on the above embodiments, optionally, the contour line drawing task generation module 210 is used to: perform semantic modeling on the natural language description of the contour line drawing requirement; use a semantic transformation model to perform vectorized representation and contextual semantic understanding of the text to obtain the corresponding semantic representation; based on the semantic representation, use the deep semantic parsing capability of the semantic recognition model to identify elements in the task, including task actions, geological entities, spatial regions, variable types, interpolation methods and their parameters; combine a predefined task template and a geoscience knowledge graph to perform semantic role mapping on the identification results, and convert the natural language description into a structured or semi-structured contour line drawing task.

[0088] Based on the above embodiments, optionally, the execution order acquisition module 220 is used to: use a large language model combined with knowledge of contour mapping process and context information to identify task fields and their corresponding process nodes in the structured contour drawing task, each process node corresponding to a subtask; generate a dependency structure between multiple subtasks based on the semantic dependencies between task fields, logical constraints in the knowledge graph and / or the order of contour basic drawing process; determine the execution order of subtasks according to the dependency structure, and use the execution order for the intelligent agent module to schedule and execute the interpolation drawing process.

[0089] Based on the above embodiments, optionally, each subtask includes at least one of the following: the intelligent agent module identifier corresponding to the subtask, expected input / output information, and the pre-task / post-task information of the subtask.

[0090] Optionally, based on the above embodiments, the device further includes an identifier verification module, used for: performing a matching verification based on the expected input / output information in the subtask and the intelligent agent module identifier corresponding to the subtask; and, if the expected input / output information in the subtask and the processing function corresponding to the intelligent agent module identifier corresponding to the subtask do not match, continuing to decompose the subtask.

[0091] Based on the above embodiments, optionally, the scheduling process of the intelligent agent modules corresponding to the multiple subtasks can be executed by the task scheduling agent module.

[0092] Based on the above embodiments, optionally, the contour map generation module 230 is used to: through the task scheduling agent module, perform data transfer, status synchronization and result feedback between multiple intelligent agent modules corresponding to the sub-tasks based on the execution order of the sub-tasks, so as to execute the multiple sub-tasks.

[0093] Based on the above embodiments, optionally, the plurality of subtasks include at least a portion of the data retrieval subtask, the interpolation modeling subtask, and the graph drawing subtask; correspondingly, the intelligent agent module includes at least a portion of the data retrieval agent module, the interpolation modeling agent module, and the graph drawing agent module.

[0094] Based on the above embodiments, optionally, the data retrieval subtask includes data retrieval parameters, which include at least one of geological work area, stratigraphic unit, and variable type; the data retrieval agent module constructs a map database query statement based on the retrieval parameters, and performs data retrieval in the database through the map database query statement to obtain target data; the interpolation modeling subtask includes an interpolation method identifier, and the interpolation modeling agent module performs interpolation processing on the target data based on the interpolation method corresponding to the interpolation method identifier to obtain an interpolation result; the map drawing agent module sequentially executes contour line extraction, vector layer construction, map style rendering, legend generation, and map generation based on the interpolation result, and outputs a contour map.

[0095] Based on the above embodiments, optionally, the subtask further includes a user feedback parsing subtask; the intelligent agent module further includes a user feedback parsing agent module.

[0096] Optionally, based on the above embodiments, the device further includes a user feedback module, configured to: acquire user feedback text; convert the user feedback text into a graph update task through the user feedback parsing proxy module; perform task analysis on the graph update task to obtain at least one new subtask; and, based on the execution order of the new subtask, schedule the corresponding intelligent proxy module of each new subtask to execute the new subtask sequentially to obtain an updated contour map.

[0097] The above-described products can perform the methods provided in any embodiment of this disclosure, and have the corresponding functional modules and beneficial effects for performing the methods.

[0098] Figure 6 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0099] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0100] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0101] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for drawing contour maps.

[0102] In some embodiments, the method for drawing contour maps may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for drawing contour maps described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for drawing contour maps by any other suitable means (e.g., by means of firmware).

[0103] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0104] Computer programs used to implement the methods of this disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0105] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0107] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0108] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0109] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0110] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the contour map drawing method according to any embodiment of this disclosure.

[0111] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method of contour plot drawing, characterized by, include: Obtain the description information of the contour line drawing requirements, and generate a contour line drawing task based on the description information of the contour line drawing requirements; The contour line drawing task is decomposed into multiple sub-tasks and the execution order of the multiple sub-tasks; Based on the execution order of the multiple subtasks, the intelligent agent module corresponding to each subtask is scheduled to execute the multiple subtasks in sequence to obtain a contour map that meets the contour drawing requirements.

2. The method of claim 1, wherein, Based on the description information of the contour line drawing requirements, a contour line drawing task is generated, including: Semantic modeling is performed on the natural language description of the contour line drawing requirements, and the text is vectorized and contextual semantic understanding is performed using a semantic transformation model to obtain the corresponding semantic representation. Based on the semantic representation, the deep semantic parsing capability of the semantic recognition model is used to identify elements in the task, including task actions, geological entities, spatial regions, variable types, interpolation methods and their parameters. By combining predefined task templates with geoscience knowledge graphs, semantic role mapping is performed on the recognition results, and the natural language description is converted into a structured or semi-structured contour drawing task.

3. The method of claim 1, wherein, The contour line drawing task is decomposed into multiple subtasks and their execution order, including: By combining large language models with knowledge of contour mapping process and contextual information, the task fields and their corresponding process nodes in the structured contour drawing task are identified, and each process node corresponds to a subtask. Based on the semantic dependencies between task fields, the logical constraints in the knowledge graph, and / or the order of contour line drawing processes, a dependency structure between multiple subtasks is generated. The execution order of subtasks is determined based on the dependency structure, and this execution order is used for the intelligent agent module scheduling and interpolation drawing process.

4. The method of claim 1, wherein, Each of the subtasks includes at least one of the following: the intelligent agent module identifier corresponding to the subtask, expected input / output information, and pre-task / post-task information of the subtask; The method further includes: A matching verification is performed based on the expected input / output information in the subtask and the intelligent agent module identifier corresponding to the subtask. If the expected input / output information in the subtask does not match the processing function corresponding to the intelligent agent module identifier of the subtask, the subtask will continue to be decomposed.

5. The method according to claim 1, characterized in that, The scheduling process for the intelligent agent modules corresponding to the multiple subtasks is executed by the task scheduling agent module. The scheduling process also includes: The task scheduling agent module performs data transfer, status synchronization, and result feedback between multiple intelligent agent modules corresponding to the sub-tasks based on the execution order of the sub-tasks, so as to execute the multiple sub-tasks.

6. The method according to any one of claims 1-5, characterized in that, The multiple subtasks include at least a portion of the data retrieval subtask, the interpolation modeling subtask, and the graph drawing subtask; Accordingly, the intelligent agent module includes at least a portion of the data retrieval agent module, the interpolation modeling agent module, and the graph drawing agent module.

7. The method according to claim 6, characterized in that, The data retrieval subtask includes data retrieval parameters, which include at least one of geological work area, stratigraphic unit, and variable type; the data retrieval agent module constructs a graph database query statement based on the retrieval parameters, and performs data retrieval in the database through the graph database query statement to obtain the target data; The interpolation modeling subtask includes an interpolation method identifier. The interpolation modeling proxy module performs interpolation processing on the target data based on the interpolation method corresponding to the interpolation method identifier to obtain the interpolation result. The map drawing proxy module sequentially performs contour line extraction, vector layer construction, map style rendering, legend generation, and pattern generation based on the interpolation results, and outputs a contour map.

8. The method according to claim 6, characterized in that, The subtask also includes a user feedback parsing subtask; the intelligent agent module also includes a user feedback parsing agent module. The method further includes: Obtain user feedback text, and convert the user feedback text into a graph update task through the user feedback parsing proxy module; Perform task analysis on the graph update task to obtain at least one new subtask; Based on the execution order of the new subtasks, the corresponding intelligent agent module is scheduled to execute the new subtasks in sequence to obtain the updated contour map.

9. An apparatus for drawing contour maps, characterized in that, include: The contour line drawing task generation module is used to obtain the description information of the contour line drawing requirements and generate contour line drawing tasks based on the description information of the contour line drawing requirements. The execution order acquisition module is used to decompose the contour line drawing task into multiple sub-tasks and the execution order of the multiple sub-tasks; The contour map generation module is used to schedule the intelligent agent module corresponding to each subtask to execute the multiple subtasks in sequence based on the execution order of the multiple subtasks, so as to obtain a contour map that meets the contour drawing requirements.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for drawing contour maps according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for drawing contour maps according to any one of claims 1-8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for drawing contour maps according to any one of claims 1-8.

Images