Intelligent auxiliary plotting method and device based on large model

Abstract

The invention relates to the technical field of plotting, and provides an intelligent auxiliary plotting method and device based on a large model. The method comprises the following steps: segmenting the content of a plotting field teaching material to obtain content blocks, inputting the content blocks into a large model, and enabling the large model to extract and output plotting standard knowledge specifications through an instruction prompt mode; and according to the plotting standard knowledge specification, generating plotting steps so as to perform plotting according to the plotting steps. According to the method, the plotting field knowledge base is constructed from the plotting textbook by using the large language model, so that the accuracy of auxiliary plotting can be improved.

Description

Technical Field

[0001] The present invention relates to the field of plotting technology, and in particular to an intelligent assisted plotting method and device based on a large model. Background Art

[0002] With the rapid development of computer software and hardware technologies and the continuous improvement of people's requirements for environmental cognition, environmental visualization has begun to transform from simulation (paper maps, sand table models, remote sensing images) to digital (electronic maps), from planar to three-dimensional, and from static to dynamic. The purpose is to display various elements related to the environment in a visual way for people to carry out corresponding planning and command decisions and carry out corresponding activities close to the real environment. The most important step in environmental visualization is situation visualization, which realizes the intuitive display of the situation by plotting the terrain accordingly, and this method is called plotting. Currently, situation plotting is mainly achieved manually, with a cumbersome and complex process, and requires the plotting personnel to fully understand the plotting standard knowledge and specifications, which places relatively high requirements on the plotting personnel. When unfamiliar personnel plot, it may lead to plotting errors.

[0003] In view of this, overcoming the defects of the existing technology is an urgent problem to be solved in this technical field. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an intelligent assisted plotting method and device based on a large model to improve the accuracy of assisted plotting.

[0005] The present invention adopts the following technical solutions:

[0006] In the first aspect, the present invention provides an intelligent assisted plotting method based on a large model, including:

[0007] Segment the content of the plotting field textbooks to obtain each content block, input each content block into the large model, and through the way of instruction prompts, enable the large model to extract and output the plotting standard knowledge and specifications;

[0008] Generate plotting steps according to the plotting standard knowledge and specifications for plotting according to the plotting steps.

[0009] Preferably, the method further includes:

[0010] Grab plotting data with different resolutions from multiple sources on the network;

[0011] Verify the less reliable plotting data with the more reliable plotting data;

[0012] The verified credible plotting data is stored in a database, and a plotting map is generated using the plotting data in the database; wherein, when displaying the plotting map, priority is given to displaying it at a resolution with the highest area coverage.

[0013] Preferably, the use of high-reliability plotting data to verify low-reliability plotting data specifically includes:

[0014] Multiple confidence levels are pre-set;

[0015] Calculate the matching degree between the marking data according to the text markings in the marking data;

[0016] Cluster the plotted data using the annotation matching degree to obtain cluster sets;

[0017] The first plotting data in the same cluster set is used to verify the second plotting data in the same cluster set; wherein the first plotting data is plotting data with a credibility level higher than a preset level, and the second plotting data is plotting data with a resolution lower than the resolution of the first plotting data.

[0018] Preferably, the verifying the second plotted data in the same cluster set using the first plotted data in the same cluster set specifically includes:

[0019] Using the text annotations that match the second plotting data with the first plotting data, scaling the second plotting data so that the scaled second plotting data is aligned with the first plotting data;

[0020] Calculating a contour matching degree using the contour lines in the scaled second plotted data and the contour lines in the first plotted data;

[0021] Calculate the feature matching degree using the feature symbols in the scaled second plotted data and the feature symbols in the first plotted data;

[0022] Performing weighted summation on the contour matching degree, the feature matching degree, and the annotation matching degree to obtain a data matching degree between the second plotted data and the first plotted data;

[0023] If the data matching degree is greater than the preset matching degree, the second plotting data is verified to be credible.

[0024] Preferably, the calculating the contour matching degree using the contour lines in the scaled second plotted data and the contour lines in the first plotted data specifically includes:

[0025] Use openCV to calculate the similarity between the first contour line and the second contour line; wherein the second contour line is the contour line in the scaled second plotted data, and the first contour line is the contour line in the first plotted data that is closest to the second contour line;

[0026] The average value of the similarities of the contour lines in the scaled second plotted data is used as the contour line matching degree.

[0027] Preferably, the method further comprises:

[0028] For the third plotted data in each cluster set, after the second plotted data in all cluster sets are verified, the data matching degree between the third plotted data and the first plotted data in the cluster set is calculated. If the data matching degree is greater than a preset matching degree, it is determined whether there is a regional overlap between the third plotted data and other plotted data that have been verified as credible. If there is no regional overlap, the third plotted data is verified to be credible.

[0029] The third plotting data is plotting data having a higher resolution than that of the first plotting data.

[0030] Preferably, the capturing of plotting data of different resolutions from multiple sources on the Internet specifically includes:

[0031] Crawl mapping data from local textbooks, expert association or organization websites, and mapping data public websites.

[0032] Preferably, the pre-set multiple credibility levels specifically include:

[0033] The plotted data from textbooks, expert associations or organizational websites are set to the first level of credibility;

[0034] The credibility level of each mapping data is determined according to the level or title of the data publishing user on the mapping data disclosure website; among them, the credibility level of the mapping data on the mapping data disclosure website is lower than the first level credibility, and the lower the level or title of the data publishing user, the lower the credibility level of the corresponding mapping data.

[0035] In a second aspect, the present invention further provides an intelligent assisted plotting device based on a large model, for implementing the intelligent assisted plotting method based on a large model described in the first aspect, the device comprising:

[0036] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor to execute the large model-based intelligent assisted plotting method described in the first aspect.

[0037] In a third aspect, the present invention further provides a non-volatile computer storage medium storing computer-executable instructions that, when executed by one or more processors, are used to implement the method described in the first aspect.

[0038] In a fourth aspect, a chip is provided, including a processor and an interface, configured to call and run a computer program stored in a memory and execute the method as described in the first aspect.

[0039] In a fifth aspect, a computer program product containing instructions is provided, which, when running on a computer or a processor, causes the computer or the processor to execute the method as described in the first aspect.

[0040] The present invention constructs a knowledge base in the plotting field from plotting textbooks using a large language model, which can improve the accuracy of assisted plotting. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required to be used in the embodiments of the present invention. Obviously, the following described drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0042] Figure 1 is a flowchart of the first intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0043] Figure 2 is a flowchart of the second intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0044] Figure 3 is a flowchart of the third intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0045] Figure 4 is a schematic diagram of the fourth intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0046] Figure 5 is a flowchart of the fourth intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0047] Figure 6 is a flowchart of the fifth intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0048] Figure 7 is a flowchart of the sixth intelligent assisted plotting method based on a large model provided by an embodiment of the present invention;

[0049] Figure 8 It is a schematic diagram of the architecture of an intelligent auxiliary plotting device based on a large model provided by an embodiment of the present invention. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] Unless otherwise required by the context, throughout the specification and claims, the term "comprising" is interpreted in an open, inclusive sense, i.e., "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples", etc., are intended to indicate that specific features, structures, materials or characteristics related to the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representations of the above terms are not necessarily referring to the same embodiment or example. In addition, the specific features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner, that is, although they may be carried in the embodiments or examples of the above terms due to reasons such as the order of appearance and position, etc., but it is not limited that they can be carried by one embodiment or example in a combined manner.

[0052] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more. In addition, for example, in the description, for the same type of nouns, the method of adding "A" and "B" at the end is used to describe them as two independent individuals. In this case, the features defined with "A" and "B" are only used for the purpose of distinguishing similar individuals and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features.

[0053] In the description of the present invention, there will be an expression of "A and / or B" (where A and B are used to formally represent specific feature contents), and the corresponding expression includes the following three combinations: only A, only B, and the combination of A and B.

[0054] As used herein, "about," "substantially," or "approximately" includes the stated value and an average value that is within an acceptable range of deviation from the particular value as determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement system).

[0055] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0056] Embodiment 1:

[0057] Embodiment 1 of the present invention provides an intelligent auxiliary plotting method based on a large model, such as Figure 1 As shown, including:

[0058] In step 201, the content of the mapping textbook is segmented into various content blocks, which are then input into a large model. The large model is then prompted to extract and output the mapping standard knowledge specifications. Specifically, the mapping textbooks are first collected and organized. Knowledge points from the textbooks are extracted using the large model. The ChatGLM large model can be used as the base large model. After the textbook content is segmented, it is input into the large model. Through prompting, the large model is prompted to extract the standard knowledge specifications. Using LangChain, a local knowledge vector library (i.e., the mapping standard knowledge specifications) is constructed from the textbook knowledge specifications.

[0059] In step 202, plotting steps are generated based on the plotting standard knowledge specification, so that plotting can be performed according to the plotting steps. Specifically, the current plotting task is obtained in the form of a document Target_text; the large model question instruction Target_Prompt is constructed by combining the knowledge base (i.e., the plotting standard knowledge specification) and Target_text; Target_Prompt is input into the basic large model to obtain the plotting steps described in natural language.

[0060] This embodiment uses a large model to study teaching materials and extract knowledge specifications, and then generates mapping steps according to the knowledge specifications, thereby facilitating mapping by mappers and improving the accuracy of mapping.

[0061] In actual use, the marking tool can also be called directly according to the marking steps for marking, such as constructing a marking tool set mapping table to map the marking instructions and marking actions; according to the marking steps obtained in step 202, the instruction mapping is performed to obtain the marking code script; the marking code script is automatically executed by the marking tool to draw the situation map.

[0062] Combining the above steps 201 and 202, a complete intelligent assisted plotting method can be obtained, including:

[0063] Pre - construct a mapping table for the plotting tool set, segment the content of the plotting field textbooks to obtain each content block, input each content block into a large - model, and in the way of instruction prompting, enable the large - model to extract and output the plotting standard knowledge specification.

[0064] According to the plotting standard knowledge specification, generate plotting steps, and perform instruction mapping according to the plotting steps and the plotting tool set mapping table to obtain a plotting code script; use a plotting tool to execute the plotting code script to realize the drawing of the situation map.

[0065] This embodiment innovatively uses a large - language model to construct a knowledge base in the plotting field from plotting textbooks, which can improve the accuracy of assisted plotting; and the provided intelligent assisted plotting method can understand the plotting text tasks through the large - model and automatically call the plotting tool for plotting, which can replace the cumbersome manual plotting process to a certain extent.

[0066] The above is for custom plotting tasks. In actual use, many plotting tasks are often to obtain the terrain of some areas, and there are usually some plotting data related to the terrain published by some organizations or individuals on the network. However, these plotting data are not integrated, and due to different publishers, the reliability of the data may also be different, resulting in difficulty in use. To solve this problem, as Figure 2 shown, the method of this embodiment further includes:

[0067] In step 301, grab plotting data with different resolutions from multiple sources on the network.

[0068] In step 302, use the plotting data with high credibility to verify the plotting data with low credibility.

[0069] In step 303, store the verified credible plotting data in a database, and use the plotting data in the database to generate a plotting map; among them, when displaying the plotting map, give priority to displaying with the resolution with the highest area coverage rate.

[0070] Among them, the specific process of using the plotting data in the database to generate a plotting map is: arrange the plotting data with the same resolution but different positions according to the positions to obtain larger - area plotting data; the area coverage rate at the corresponding resolution represents the size of the area formed by piecing together at this resolution. The larger the area formed by piecing together, the higher the area coverage rate.

[0071] In actual use, multiple resolution intervals can be divided. All resolutions within a resolution interval can be regarded as the same resolution. When actually piecing and arranging, the minimum value of the resolution interval is used as the benchmark for piecing. For the plotting data with a resolution higher than this minimum value, it is scaled to match this minimum value.

[0072] In an actual application scenario, the grabbing of plotting data with different resolutions from multiple sources from the network specifically includes: grabbing plotting data from textbooks, expert association or organization websites, and plotting data public websites in the region where it is located.

[0073] Among them, the textbooks in the region where it is located refer to local textbooks, that is, grabbing the plotting data of region A from the textbooks of region A. This is because usually, local textbooks have a relatively full understanding of the regional cognition and a relatively low error rate. The plotting data in the expert association or organization websites can be understood as being jointly completed by multiple experts and usually having data verified by professionals, with a relatively high accuracy rate. The plotting data public website can be understood as a website that allows public personnel to register and publish data by themselves. The data on this website is often obtained by individual plotting and has a relatively lower accuracy rate compared to the textbooks and expert association or organization websites in the region where it is located. However, due to its wide data sources, this embodiment also includes it in the scope of data grabbing.

[0074] In a preferred implementation manner, using the plotting data with high credibility to verify the plotting data with low credibility, as Figure 3 shown, specifically includes:

[0075] In step 401, multiple credibility levels are preset; specifically which credibility levels are set is obtained by those skilled in the art through empirical analysis. The setting of multiple credibility levels also includes assigning the plotting data from each source to the corresponding credibility level.

[0076] In step 402, according to the text annotations in each plotting data, the annotation matching degree between each plotting data is calculated. Among them, this embodiment is for the plotting data of terrain, which usually consists of four parts: ground feature symbols, contour lines, text annotations, and map border elements. Among them, the ground feature symbols are to mark corresponding graphic symbols at the corresponding positions on the map, and the text annotations are to mark text (usually place names, etc.) at the corresponding positions on the map. The annotation matching degree is expressed by the following mathematical formula: Among them, MA is the annotation matching degree, a i is the i-th text annotation in a plotting data, I is the total number of text annotations in this plotting data, aj is the j-th text annotation in another plotting data, J is the total number of text annotations in another plotting data, sim(ai,a j ) is a i and aj The text similarity between, when a i and a j are textually identical, sim(a i , a j ) = 1; otherwise, sim(a i , a j ) = 0; dis(a i , a j ) is the distance factor between a i and a j . When the distance between a i and a j is less than the preset distance, dis(a i , a j ) = 1; otherwise, dis(a i , a j ) = 0. The preset distance is obtained by those skilled in the art through empirical analysis.

[0077] In step 403, the use of annotation matching degrees to cluster each plotting data to obtain each clustering set; the use of annotation matching degrees to cluster each plotting data specifically includes: dividing multiple plotting data with annotation matching degrees greater than a preset value between each other into a clustering set. The preset value is obtained by those skilled in the art through empirical analysis. For example: if the annotation matching degree between annotation data A and B is greater than the preset value, the annotation matching degree between annotation data A and C is greater than the preset value, and the annotation matching degree between annotation data B and C is greater than the preset value, then A, B, and C are divided into the same clustering set. If there is also annotation data D with annotation matching degrees greater than the preset value with A, B, and C, then it can also be divided into this clustering set. In actual use, first find the largest annotation matching degree greater than the preset value, form a clustering set with the two annotation data of this annotation matching degree, and then select other annotation data to join this clustering set until no more annotation data can be added, forming a complete clustering set. And so on, and then continue to generate other clustering sets in this way. Take Figure 4For example, if the annotation matching degree between A and B is 1.2, if the annotation matching degree between A and C is 1.3, if the annotation matching degree between A and D is 0.9, if the annotation matching degree between B and D is 1.5, if the annotation matching degree between B and C is 0.3, if the annotation matching degree between C and D is 1.1, assuming the preset value is 1, the maximum annotation matching degree greater than 1 is selected as 1.5, and a clustering set {B, D} is obtained. Then check whether A and C can be added to the clustering set. Among them, the annotation matching degree between A and D is 0.9, and the annotation matching degree between C and B is 0.3, both of which are less than 1, so they cannot be added to this clustering set. It can be considered that the clustering set has been generated. Then continue to select the highest annotation matching degree of the remaining data that has not been added to the clustering set to generate a new clustering set. Since only A and C remain here, and the annotation matching degree between the two is 1.3 which is greater than 1, a new clustering set {A, C} is generated, thus forming two clustering sets {B, D} and {A, C}.

[0078] In step 404, the second plotted data in the same clustering set is verified using the first plotted data in the same clustering set; wherein, the first plotted data is the plotted data with a credibility level higher than the preset level, and the second plotted data is the plotted data with a resolution lower than that of the first plotted data. The preset level is obtained by those skilled in the art through empirical analysis.

[0079] In some embodiments, the multiple credibility levels are preset as follows: the plotted data of textbooks, expert association or organization websites are set as the first-level credibility; according to the level or title of the data publishing users in the plotted data public website, the credibility level of each plotted data is determined; wherein, the credibility level of the plotted data in the plotted data public website is lower than the first-level credibility, and the lower the level or title of the data publishing user, the lower the credibility level of the corresponding plotted data. In an alternative embodiment, the preset level can be the second-level credibility, and the level and title of the data publishing user are both obtained from the plotted data public website.

[0080] In an alternative embodiment, the verification of the second plotted data in the same clustering set using the first plotted data in the same clustering set is as Figure 5 shown, and specifically includes:[[]]END]]

[0081] In step 501, the second plotted data is scaled using the text annotations that match each other between the second plotted data and the first plotted data, so that the scaled second plotted data is aligned with the first plotted data in position.

[0082] In step 502, the contour line matching degree is calculated using the contour lines in the scaled second plotted data and the contour lines in the first plotted data.

[0083] In step 503, the feature matching degree is calculated using the feature symbols in the second plotted data after scaling and the feature symbols in the first plotted data; wherein, the calculation method of the feature matching degree and the calculation method of the annotation matching degree are implemented based on the same concept, that is, the feature matching degree wherein, MF is the feature matching degree, and f m is the m-th feature symbol in one plotted data, M is the total number of feature symbols in this plotted data, and f n is the n-th feature symbol in another plotted data, N is the total number of feature symbols in the other plotted data, and sim(f m , f n ) is the symbol similarity between f m and f n ; when the symbols of f m and f n are the same, sim(f m , f n ) = 1; otherwise, sim(f m , f n ) = 0; dis(f m , f n ) is the distance factor between f m and f n ; when the distance between f m and f n is less than the preset distance, dis(f m , f n ) = 1; otherwise, dis(f m , f n ) = 0. The preset distance is obtained by those skilled in the art through empirical analysis.

[0084] In step 504, the contour matching degree, the feature matching degree, and the annotation matching degree are weighted and summed to obtain the data matching degree between the second plotted data and the first plotted data; the weights used in the weighted summation are obtained by those skilled in the art through empirical analysis, that is, MW = k1MA + k2MF + k3MC, where MW is the data matching degree, MA is the annotation matching degree, MF is the feature matching degree, MC is the contour matching degree, and k1, k2, and k3 are all preset weights obtained by those skilled in the art through empirical analysis.

[0085] In step 505, if the data matching degree is greater than the preset matching degree, it is verified that the second plotted data is credible. The preset matching degree is obtained by those skilled in the art through empirical analysis.

[0086] Among them, the contour matching degree is calculated using the contours in the scaled second plotted data and the contours in the first plotted data, as Figure 6 shown, specifically including:

[0087] In step 601, the similarity between the first contour and the second contour is calculated using openCV; among them, the second contour is the contour in the scaled second plotted data, and the first contour is the contour in the first plotted data that is closest to the second contour; the closest contour is obtained by comparing the minimum bounding rectangles of each contour, that is, calculating the center position, width, and height of the minimum bounding rectangle of each contour, and according to the center position, length, and width of the minimum bounding rectangle, calculating the rectangle similarity SR = αd(p1, p2)+β|w1 - w2|+δ|h1 - h2|, where p1 is the center position of the minimum bounding rectangle of the second contour, w1 is the width of the minimum bounding rectangle of the second contour, h1 is the height of the minimum bounding rectangle of the second contour, p2 is the center position of the minimum bounding rectangle of the corresponding contour in the first plotted data, w2 is the width of the minimum bounding rectangle of the corresponding contour in the first plotted data, h2 is the height of the minimum bounding rectangle of the corresponding contour in the first plotted data, and α, β, and δ are all preset weights obtained by those skilled in the art through empirical analysis, and d(p1, p2) is the distance between p1 and p2. The smaller the rectangle similarity, the closer the two contours are considered. After finding the first contour closest to the second contour, the computeDistance function in the OpenCV tool is used to calculate the similarity between the first contour and the second contour.

[0088] In step 602, the average value of the similarities of the contours in the scaled second plotted data is used as the contour matching degree.

[0089] In actual use, considering that in a clustering set, there may also be third plotted data with a higher resolution than the first plotted data. For this type of data, the method described in this embodiment further includes:

[0090] For the third plotted data in each aggregation set, after the verification of the second plotted data in all clustering sets is completed, the data matching degree between the third plotted data and the first plotted data in the aggregation set where it is located is calculated. If the data matching degree is greater than the preset matching degree, it is determined whether there is an area intersection between the third plotted data and other plotted data that have been verified as credible. If there is no area intersection, it is verified that the third plotted data is credible; among them, the third plotted data is the plotted data with a resolution higher than that of the first plotted data. The calculation method of the data matching degree is implemented based on the same concept as the calculation method of the data matching degree between the second plotted data and the first plotted data, and will not be elaborated here. If there is an area intersection, the third plotted data is considered not credible.

[0091] Embodiment 2:

[0092] Based on Embodiment 1, this embodiment further provides an intelligent auxiliary plotting device based on a large model. The device includes a step generation module, and the step generation module executes the method described in steps 201 - 202 of Embodiment 1, that is, collects and organizes textbooks in the plotting field, extracts textbook knowledge points through the large model. That is, after splitting the textbook content, it is input into the large model, and in the way of instruction prompts, the large model is used to extract standard knowledge specifications; in the way of langchain, a local knowledge vector library is constructed from the textbook knowledge specifications; obtains the current plotting task, which is in the form of a document Target_text; constructs a large model problem instruction Target_Prompt in combination with the knowledge base and Target_text; inputs Target_Prompt into the basic large model to obtain the plotting steps described in natural language.

[0093] As Figure 7 shown, the device further includes a plotting step conversion module, a plotting instruction code script generation module, and a map plotting module. The plotting step conversion module constructs a mapping table of the plotting tool set, maps the plotting instructions and plotting actions, and the plotting instruction code script generation module maps the UI plotting steps to obtain a plotting code script. The map plotting module automatically executes the plotting code script through the plotting tool to draw a situation map.

[0094] As Figure 8 shown, it is a schematic architecture diagram of the intelligent auxiliary plotting device based on a large model according to an embodiment of the present invention. The intelligent auxiliary plotting device based on a large model in this embodiment includes one or more processors 21 and a memory 22. Among them, Figure 8 one processor 21 is taken as an example.

[0095] The processor 21 and the memory 22 can be connected through a bus or other means, Figure 8 Taking the connection through the bus as an example.

[0096] The memory 22, as a non - volatile computer - readable storage medium, can be used to store non - volatile software programs and non - volatile computer - executable programs, such as the intelligent auxiliary plotting method based on a large model in Embodiment 1. The processor 21 executes the intelligent auxiliary plotting method by running the non - volatile software programs and instructions stored in the memory 22.

[0097] The memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 22 may optionally include a memory remotely disposed relative to the processor 21, and these remote memories may be connected to the processor 21 through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0098] The program instructions / modules are stored in the memory 22 and, when executed by the one or more processors 21, perform the intelligent assisted plotting method based on the large model in Embodiment 1 above.

[0099] It should be noted that, for the content such as information interaction and execution process between the modules and units in the above device and system, since it is based on the same concept as the method embodiment of the present invention, the specific content can be referred to the description in the method embodiment of the present invention and will not be elaborated here.

[0100] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

[0101] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent assisted plotting method based on a large model, characterized in that, including: Segment the content of the plotting field textbook to obtain each content block, input each content block into a large model, and use the method of instruction prompting to enable the large model to extract and output the plotting standard knowledge specification; Generate plotting steps according to the plotting standard knowledge specification for plotting according to the plotting steps.

2. The intelligent assisted plotting method based on a large model according to claim 1, wherein The method further includes: Scrape plotting data with different resolutions from multiple sources on the network; Use the plotting data with high credibility to verify the plotting data with low credibility; Store the verified credible plotting data in a database, and use the plotting data in the database to generate a plotting map; wherein, when displaying the plotting map, give priority to displaying at the resolution with the highest area coverage rate.

3. The intelligent assisted plotting method based on a large model according to claim 2, wherein The verification of using the plotting data with high credibility to verify the plotting data with low credibility specifically includes: Preset multiple credibility levels in advance; Calculate the annotation matching degree between each plotting data according to the text annotations in each plotting data; Cluster each plotting data using the annotation matching degree to obtain each clustering set; Use the first plotting data in the same clustering set to verify the second plotting data in the same clustering set; wherein, the first plotting data is the plotting data with a credibility level higher than the preset level, and the second plotting data is the plotting data with a resolution lower than that of the first plotting data.

4. The intelligent assisted plotting method based on a large model according to claim 3, wherein The verification of using the first plotting data in the same clustering set to verify the second plotting data in the same clustering set specifically includes: Use the text annotations that match each other between the second plotting data and the first plotting data to scale the second plotting data so that the scaled second plotting data is aligned with the first plotting data in position; Calculate the contour matching degree using the contour lines in the scaled second plotting data and the contour lines in the first plotting data; Calculate the feature matching degree using each feature symbol in the scaled second plotting data and each feature symbol in the first plotting data; Perform weighted summation on the contour matching degree, the feature matching degree, and the annotation matching degree to obtain the data matching degree between the second plotting data and the first plotting data; If the data matching degree is greater than the preset matching degree, it is verified that the second plotting data is credible.

5. The intelligent assisted plotting method based on a large model according to claim 4, wherein The calculation of the contour matching degree using the contour lines in the scaled second plotting data and the contour lines in the first plotting data specifically includes: Use openCV to calculate the similarity between the first contour line and the second contour line; wherein, the second contour line is the contour line in the scaled second plotting data, and the first contour line is the contour line in the first plotting data that is closest to the second contour line; Use the average value of the similarities of each contour line in the scaled second plotting data as the contour matching degree.

6. The intelligent assisted plotting method based on a large model according to claim 3, wherein, The method further includes: For the third plotted data in each aggregation set, after the verification of the second plotted data in all clustering sets is completed, calculate the data matching degree between the third plotted data and the first plotted data in the aggregation set where the third plotted data is located. If the data matching degree is greater than the preset matching degree, determine whether there is an area intersection between the third plotted data and other plotted data that have been verified as credible. If there is no area intersection, verify that the third plotted data is credible; Among them, the third plotted data is plotted data with a resolution higher than that of the first plotted data.

7. The intelligent assisted plotting method based on a large model according to claim 3, characterized in that The method of scraping plotted data with different resolutions from multiple sources from the network specifically includes: Scraping plotted data from textbooks, websites of expert associations or organizations, and websites for publicizing plotted data in the local area.

8. The intelligent assisted plotting method based on a large model according to claim 7, wherein, The method of presetting multiple credibility levels specifically includes: Setting the plotted data of textbooks, websites of expert associations or organizations as the first-level credibility; Determining the credibility level of each plotted data according to the level or title of the data publishing user in the website for publicizing plotted data; among them, the credibility level of the plotted data in the website for publicizing plotted data is lower than the first-level credibility, and the lower the level or title of the data publishing user, the lower the credibility level of the corresponding plotted data.

9. A non-volatile computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors to complete the intelligent assisted plotting method based on a large model according to any one of claims 1-8.

10. An intelligent auxiliary plotting device based on a large model, characterized in that, It includes: At least one processor; And a memory communicatively connected to the at least one processor; among them, the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor to execute the intelligent assisted plotting method based on a large model according to any one of claims 1-8.

Images