Map visualization method based on large language model

Abstract

The invention discloses a map visualization method based on a large language model, and belongs to the technical field of data processing. The method comprises the steps that a demand text is received, map visualization demand information in the demand text is extracted, target visualization information matched with the demand information is retrieved in a vector database, enhancement cues of a large language model are generated in combination with the demand text and the target visualization information, and the enhancement cues of the large language model are extracted through the large language model. And calling a map visualization function based on the enhanced cue word to generate a visual map. According to the method, the enhanced cue word of the large language model is generated in a retrieval enhanced generation mode according to the demand text of the user, so that the map visualization function is called through the large language model, the visual map is generated, and the threshold of generating the visual map is reduced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a map visualization method based on a large language model. Background Art

[0002] Visual maps are used to intuitively display geographic spatial data on maps through graphics, symbols, colors, animations and other visual means to help users understand the distribution, trends and patterns of geographic information.

[0003] In related technologies, map visualization mainly relies on professional Geographic Information System (GIS) software or customized visualization platforms. Map makers use GIS software tools to create maps based on visualization requirements. Since the data in geographic information is relatively complex, the creation of visualization maps requires map makers to have relevant map drawing skills, which has certain technical barriers.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a map visualization method, device and storage medium based on a large language model, aiming to solve the technical problem that in the process of producing visualized maps, map makers need to have a certain map drawing foundation and have a high technical threshold.

[0006] To achieve the above object, the present application provides a map visualization method based on a large language model, wherein the method comprises the following steps: Receive a demand text, and extract map visualization demand information from the demand text; Retrieving target visualization information matching the requirement information from a vector database; Combining the requirement text and the target visualization information to generate enhanced prompt words of a large language model; Through the large language model, a map visualization function is called based on the enhanced prompt word to generate a visualized map.

[0007] In one embodiment, after the step of generating a visualized map by calling a map visualization function based on the enhanced prompt word through the large language model, the step further includes: Obtaining feedback information of the visualization map; Performing semantic analysis on the feedback information, and determining a parameter adjustment direction and an adjustment step size corresponding to the feedback information according to the semantic analysis result; The large language model is iterated based on the parameter adjustment direction and the adjustment step size.

[0008] In one embodiment, before the step of retrieving target visualization information matching the requirement information from the vector database, the method further includes: Obtaining map visualization information through at least one data source; Mapping the map visualization information into a visualization vector through an embedding model; The visualization vector is stored in the vector database, and a vector index of the visualization vector is constructed.

[0009] In one embodiment, the step of retrieving target visualization information matching the requirement information from the vector database includes: Mapping the demand information into a demand vector; Calculating a vector distance between the demand vector and a visualization vector in the vector database, and determining a similarity between the demand vector and the visualization vector based on the vector distance; Based on the similarity, the target visualization vector is selected from the visualization vectors, and target visualization information corresponding to the target visualization vector is obtained.

[0010] In one embodiment, the step of combining the requirement text and the target visualization information to generate enhanced prompt words of the large language model includes: Obtaining a preset prompt word template, and determining a demand text placeholder and a visual information placeholder in the prompt word template; The requirement text is used to replace the requirement text placeholder, and the target visualization information is used to replace the visualization information placeholder to generate the enhanced prompt word.

[0011] In one embodiment, the step of generating a visualized map by calling a map visualization function based on the enhanced prompt word through the large language model includes: In the enhanced prompt word, determining rendering parameters of the visual map and determining parameter types of the rendering parameters; Based on the function interface corresponding to the parameter type, calling the corresponding map visualization function; Generate corresponding visualized map information based on the rendering parameters through the map visualization function; The visual map information is integrated to generate the visual map.

[0012] In one embodiment, the step of receiving a demand text and extracting map visualization demand information from the demand text includes: After receiving the demand text, performing word segmentation processing on the demand text to obtain demand text word segmentation; By matching the demand text segmentation with a semantic database, the semantic information of the demand text segmentation is identified according to the matching result; The demand information is generated according to the semantic information.

[0013] In one embodiment, after the step of generating a visualized map by calling a map visualization function based on the enhanced prompt word through the large language model, the step further includes: Obtaining a modification requirement text of the visual map, and identifying modification information of the visual map in the modification requirement text; In the vector database, the target visualization information matching the modification information is obtained, and the modification prompt word is generated by combining the target visualization information and the modification information; By using the large language model, a modification action is performed on the visualization map based on the modification prompt word to generate a target visualization map.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a map visualization device based on a large language model, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the map visualization method based on a large language model as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the map visualization method based on a large language model as described above are implemented.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: After receiving a demand text for generating a visual map, the application extracts the demand information for map visualization in the demand text, retrieves target visualization information matching the demand information in a vector database, combines the demand text and the target visualization information, generates enhanced prompt words for a large language model, and guides the large language model with the enhanced prompt words, calls a map visualization function based on the enhanced prompt words, and generates a visual map in an automated manner, thereby lowering the threshold for users to customize and generate visual maps. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is a flowchart of the first embodiment of the map visualization method based on a large language model of the present application; Figure 2 This is a flow chart of a second embodiment of a map visualization method based on a large language model of the present application; Figure 3 This is a schematic diagram of the large language model iteration process involved in the second embodiment of the present application; Figure 4 This is a flowchart of a third embodiment of a map visualization method based on a large language model of the present application; Figure 5 This is a flowchart of a fourth embodiment of a map visualization method based on a large language model of the present application; Figure 6 It is a structural diagram of a map visualization device based on a large language model in the hardware operating environment involved in the embodiment of the present application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: receiving a demand text and extracting demand information for map visualization in the demand text; retrieving target visualization information matching the demand information in a vector database; combining the demand text and the target visualization information to generate enhanced prompt words of a large language model; and calling a map visualization function based on the enhanced prompt words through the large language model to generate a visualized map.

[0024] Visual maps are used to display geographic spatial data on maps through graphics, symbols, colors, animations and other visualization methods to help users understand the distribution, trends and patterns of geographic information. In related technologies, map visualization mainly relies on professional Geographic Information System (GIS) software or customized visualization platforms. Map makers use GIS software tools to create maps based on visualization requirements. Among them, since the data in geographic information is relatively complex, the production of visual maps requires map makers to have relevant map drawing skills, and there is a certain technical threshold.

[0025] After receiving a demand text for generating a visual map, the application extracts the demand information for map visualization in the demand text, retrieves target visualization information matching the demand information in a vector database, combines the demand text and the target visualization information, generates enhanced prompt words for a large language model, and guides the large language model with the enhanced prompt words, calls a map visualization function based on the enhanced prompt words, and generates a visual map in an automated manner, thereby lowering the threshold for users to customize and generate visual maps.

[0026] In order to better understand the above technical solution, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0027] It should be noted that the execution subject of this embodiment can be a map visualization system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a map visualization device based on a large language model, etc., and this embodiment does not specifically limit this. The following takes the map visualization system as an example to illustrate this embodiment and the following embodiments.

[0028] Based on this, the embodiment of the present application provides a map visualization method based on a large language model, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the map visualization method based on a large language model of the present application.

[0029] In this embodiment, the map visualization method based on the large language model includes steps S10 to S40: Step S10: receiving a demand text, and extracting demand information for map visualization from the demand text; In this embodiment, the requirement text is a specific requirement description about map visualization input by the user, which is usually expressed in natural language and contains key information required for map visualization, such as data source, map type, color, annotation and other parameters. The map visualization system can identify and extract the requirement information related to map visualization from the requirement text through natural language processing technology, for example, using a large language model (LLM) to understand the semantics of the natural language text, and identify the specific requirement information related to map visualization in the requirement text according to preset rules and patterns.

[0030] In one embodiment, after receiving the requirement text input by the user, the map visualization system inputs the requirement text into the large language model. The large language model performs semantic analysis on the requirement text and identifies key information therein, such as data source name, map type, color requirements, labeling requirements, etc. The system will further organize and format the extracted requirement information according to preset rules and patterns for use in subsequent steps. For example, the system can match the extracted data source name with the existing data source list to confirm its accuracy, and convert the color requirements into specific color codes, such as RGB (Red, Green and Blue) values.

[0031] In another embodiment, the map visualization system can also identify demand information by semantic analysis based on a preset semantic database. After receiving the demand text, the demand text is segmented by a segmentation tool to obtain demand text segmentation, and the demand text segmentation is matched with the semantic database, and the semantic information of the demand text segmentation is identified according to the matching result, and the demand information is generated according to the semantic information. The demand text segmentation and the semantic database can be matched based on the similarity calculation of the feature vector.

[0032] For example, when a user inputs the requirement text: "Use POI statistical data of XX city districts to create a segmented thematic map with blue as the main color. The more the number, the darker the color." The map visualization system extracts the following requirement information through the large language model: "Data source: POI statistical data of XX city districts; Map type: segmented thematic map; Color requirement: blue. The more the number, the darker the color."

[0033] Step S20: Retrieving target visualization information matching the requirement information from the vector database; In this embodiment, the vector database is used to store and retrieve vector data, and can perform vector similarity search. Among them, the vector database of the map visualization system stores vectorized map visualization information, including map visualization related knowledge, Geographic Information System (GIS) map rendering API information, and existing data source information. The target visualization information is visualization related information that matches the demand information, including map visualization parameters, data source details, map rendering methods, etc., which is retrieved from the vector database and used to assist in generating the final visualization map.

[0034] As an optional implementation for retrieving target visualization information, the map visualization system maps the demand information into a demand vector in a vector space, and determines the similarity between the demand vector and the visualization vector by calculating the vector distance between the demand vector and the visualization vector in the vector database. The vector distance can be calculated based on L2 Euclidean distance or cosine distance. Based on the similarity, the map visualization system selects a target visualization vector from the visualization vectors and obtains the target visualization information corresponding to the target visualization vector.

[0035] As another optional implementation method for retrieving target visualization information, the vector database can also construct a data storage structure based on a tree-like knowledge graph. The vector database can obtain the target visualization information by matching the demand information with the tree-like knowledge graph in a step-by-step manner starting from the root node.

[0036] Step S30: combining the demand text and the target visualization information to generate enhanced prompt words of a large language model; In this embodiment, the enhanced prompt words are the prompt words of the optimized large language model. The map visualization system combines the user's demand text and the target visualization information retrieved from the vector database to generate the enhanced prompt words of the large language model, which are used to more accurately guide the large language model to generate map visualization parameters and call map visualization functions.

[0037] Specifically, the map visualization system can attach the target visualization information as context information to the requirement text, or can semantically fuse the two to generate a more complete and accurate prompt word, or fill the target visualization information and the requirement text into a preset prompt word template. The system inputs the enhanced prompt word into the large language model, and the large language model generates parameters and call instructions that can be recognized by the map visualization function based on the enhanced prompt word.

[0038] As an optional implementation, the map visualization system can obtain a preset prompt word template in the system, and determine the positions of the requirement text placeholder and the visualization information placeholder in the prompt word template. The enhanced prompt word is generated by replacing the requirement text placeholder with the requirement text and replacing the visualization information placeholder with the target visualization information.

[0039] As another optional implementation, the map visualization system can also perform semantic information fusion on multiple target visualization information and demand text through a large language model. The map visualization system can identify, organize and expand the demand text based on the semantic information, form limiting information based on the target visualization information, fill it into the demand text, and generate enhanced prompt words.

[0040] Step S40: calling a map visualization function based on the enhanced prompt word through the large language model to generate a visualized map.

[0041] In this embodiment, the map visualization function is a specific function or method for realizing map visualization, which can be provided by the rendering API of the GIS map, or called by a preset interface in the system. The map visualization function can generate corresponding map visualization results according to the input parameters, that is, a visualized map that displays the map information required by the user in a graphical form.

[0042] Specifically, step S40 includes steps S41 to S44: Step S41: determining rendering parameters of the visual map in the enhanced prompt words, and determining parameter types of the rendering parameters; Step S42: Based on the function interface corresponding to the parameter type, calling the corresponding map visualization function; Step S43: Generate corresponding visualized map information based on the rendering parameters through the map visualization function; In this embodiment, since the visualization map includes different types of rendering parameters, which are used to execute the rendering process of different elements in the visualization map, the rendering parameters of different parameter types are determined based on the enhanced prompt words, and different map visualization functions can be called through the corresponding function interface. The map visualization system inputs the corresponding rendering parameters into the map visualization function, controls the map visualization function to execute the corresponding rendering action, and generates the corresponding visualization map information.

[0043] Step S44: Integrate the visualization map information to generate the visualization map.

[0044] As an optional implementation, the map visualization system can call multiple map visualization functions at the same time, input rendering parameters to perform rendering actions, and after obtaining the map visualization information output by all map visualization functions, splice the map visualization information in an overlapping manner based on the same map coordinate system to generate a visualized map. By calling multiple map visualization functions at the same time, the rendering efficiency of the visualized map can be effectively improved.

[0045] As another optional implementation, the map visualization system may also call the map visualization function in sequence, generate corresponding map visualization information through the map visualization function, and input the map visualization information into the next called map visualization function until all the map visualization functions are called, and the last called map visualization function is used as the visualization map. By calling the map visualization function at multiple levels, each visualization function can obtain the complete rendering result of the current visualization map, thereby improving the accuracy of visualization map generation.

[0046] After receiving a demand text for generating a visual map, the embodiment of the present application extracts the demand information for map visualization in the demand text, retrieves target visualization information matching the demand information in a vector database, combines the demand text and the target visualization information, generates enhanced prompt words for a large language model, guides the large language model with the enhanced prompt words, calls a map visualization function based on the enhanced prompt words, and generates a visual map in an automated manner, thereby lowering the threshold for users to generate customized visual maps.

[0047] Based on the same inventive concept, the present application also provides a second embodiment, referring to Figure 2 , Figure 2 This is a flowchart of the second embodiment of the map visualization method based on a large language model of the present application.

[0048] In this embodiment, the map visualization based on the large language model includes steps S51 to S53: Step S51: Obtaining feedback information of the visual map: Step S52: performing semantic analysis on the feedback information, and determining the parameter adjustment direction and adjustment step size corresponding to the feedback information according to the semantic analysis result; Step S53: iterating the large language model based on the parameter adjustment direction and adjustment step size.

[0049] In this embodiment, based on the dialogue process of the large language model, or the feedback information input by the user in the feedback window, the map visualization system can perform semantic analysis based on the obtained feedback information. The semantic analysis process can be selected as the same semantic analysis module in the demand text analysis process for analysis. Through the semantic analysis results, the corresponding parameter adjustment direction and adjustment step size in the large language model can be determined to perform iteration of the large language model.

[0050] Further, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the iteration process of the large language model involved in the embodiment of the present application. After the large language model is iteratively optimized based on the result feedback, it can perform map visualization actions based on the input of the requirement description again. Among them, the user evaluates the results, points out inappropriate places, and puts forward new and more specific requirements. Repeating the above steps, the large model can optimize the output results until the user's needs are met.

[0051] The embodiment of the present application performs a self-iterative action based on user feedback information by executing a large language model for map visualization, thereby continuously adjusting model parameters to improve the accuracy of visual map generation.

[0052] Since the system introduced in the second embodiment of the present application is a system used to implement the method of the first embodiment of the present application, based on the method introduced in the first embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the system, so it is not repeated here. All systems used in the method of the first embodiment of the present application belong to the scope of protection of this application.

[0053] Based on the same inventive concept, the present application also provides a third embodiment, referring to Figure 4 , Figure 4 This is a flowchart of the third embodiment of the map visualization method based on a large language model of the present application.

[0054] In this embodiment, the map visualization based on the large language model includes steps S01 to S03: Step S01: obtaining map visualization information through at least one data source; Step S02: Mapping the map visualization information into a visualization vector through an embedding model; Step S03: storing the visualization vector in the vector database, and constructing a vector index of the visualization vector.

[0055] In this embodiment, in the process of building a vector database, the map visualization system will first collect and organize map visualization information, including map visualization related industry knowledge, GIS map rendering API, existing data source information, etc., and perform data cleaning and sorting. The cleaned industry knowledge, GIS map rendering API, existing data source information and other map visualization information are vectorized, converted into vector form through an embedding model, and stored in the vector database. Furthermore, the map visualization system can establish a knowledge base index in the vector database to realize vector similarity calculation and improve the accuracy of the vector index.

[0056] Since the system introduced in the third embodiment of the present application is a system used to implement the method of the first embodiment of the present application, based on the method introduced in the first embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the system, so it is not repeated here. All systems used in the method of the first embodiment of the present application belong to the scope of protection of the present application.

[0057] Based on the same inventive concept, the present application also provides a fourth embodiment, referring to Figure 5 , Figure 5 This is a flowchart of the fourth embodiment of the map visualization method based on a large language model of the present application.

[0058] In this embodiment, the map visualization based on the large language model includes steps S61 to S63: Step S61: obtaining a modification requirement text of the visual map, and identifying modification information of the visual map in the modification requirement text; Step S62: acquiring the target visualization information matching the modification information in the vector database, and generating a modification prompt word by combining the target visualization information and the modification information; Step S63: using the large language model, modifying the visualization map based on the modification prompt words to generate a target visualization map.

[0059] In this application, users can also make modifications based on the rendered visualization map.

[0060] Specifically, the map visualization system receives the modification requirement text input by the user and inputs it into the large language model. The large language model performs semantic analysis on the modification requirement text and identifies key information therein, such as the visualization parameters and data sources that need to be modified. The system will further organize and format the identified key information according to preset rules and patterns for use in subsequent steps. For example, the system can match the identified visualization parameters with the existing parameter list to confirm its accuracy; convert the data source name into a specific path, etc. The map visualization system vectorizes the identified modification information, converts it into vector form, and inputs the vector into the vector database. Using the vector similarity search algorithm, it retrieves the target visualization information with the highest similarity to the modification information, combines it with the modification information, and generates a modification prompt word.

[0061] Furthermore, the map visualization system inputs the modification prompt words and the visualized map to be modified into the large language model, and the large language model generates the calling instructions and parameters of the map visualization function according to the modification prompt words. The system calls the map visualization function in the GIS map rendering API according to the generated calling instructions and parameters to perform the map visualization modification operation. The map visualization function generates the modified visualized map according to the input parameters, such as data source path, map type, color gradient range, etc., and returns the result to the user.

[0062] Optionally, based on the modification prompt words, the large language model can also perform a partial erasing action on the visual map. For example, by pre-rendering, when it is determined that the average pixel difference of the image in the target area of ​​the visual map is greater than the average difference threshold, an erasing action is performed to avoid the original visual map information in the visual map affecting the modified map.

[0063] Since the system introduced in the fourth embodiment of the present application is a system used to implement the method of the first embodiment of the present application, based on the method introduced in the first embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the system, so it is not repeated here. All systems used in the method of the first embodiment of the present application belong to the scope of protection of this application.

[0064] The present application provides a map visualization device based on a large language model, the device comprising: 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 at least one processor so that the at least one processor can execute the map visualization method based on the large language model in the above-mentioned embodiment 1.

[0065] Reference below Figure 6, which shows a schematic diagram of the structure of a map visualization device based on a large language model suitable for implementing the embodiment of the present application. The map visualization device based on a large language model in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The map visualization device based on the large language model shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0066] like Figure 6 As shown, the map visualization device based on the large language model may include a processing device 1001 (such as a core processor, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the map visualization device based on the large language model are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the map visualization device based on the large language model to communicate with other devices wirelessly or by wire to exchange data. Although the map visualization device based on the large language model with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0067] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0068] The map visualization device based on a large language model provided by the present application adopts the map visualization method based on a large language model in the above-mentioned embodiment, which can solve the technical problem that in the process of making a visualized map, the map maker needs to have a certain map drawing foundation and the technical threshold is high. Compared with the prior art, the beneficial effects of the map visualization device based on a large language model provided by the present application are the same as the beneficial effects of the map visualization method based on a large language model provided by the above-mentioned embodiment, and the other technical features of the map visualization device based on a large language model are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0069] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0070] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0071] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the map visualization method based on a large language model in the above-mentioned embodiment.

[0072] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0073] The computer-readable storage medium may be included in the map visualization device based on the large language model; or may exist independently without being assembled into the map visualization device based on the large language model.

[0074] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a map visualization device based on a large language model, the map visualization device based on the large language model: receives a demand text and extracts demand information for map visualization in the demand text; retrieves target visualization information matching the demand information from a vector database; generates enhanced prompt words of a large language model by combining the demand text and the target visualization information; and calls a map visualization function based on the enhanced prompt words through the large language model to generate a visualized map.

[0075] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0076] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0077] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0078] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned map visualization method based on a large language model, and can solve the technical problem that in the process of making a visualized map, map makers need to have a certain map drawing foundation and the technical threshold is high. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the map visualization method based on a large language model provided in the above-mentioned embodiment, and will not be repeated here.

[0079] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A map visualization method based on a large language model, characterized in that: The method comprises the following steps: Receive a demand text, and extract map visualization demand information from the demand text; Retrieving target visualization information matching the requirement information from a vector database; Combining the requirement text and the target visualization information to generate enhanced prompt words of a large language model; Through the large language model, a map visualization function is called based on the enhanced prompt word to generate a visualized map.

2. The method according to claim 1, characterized in that After the step of generating a visualized map by calling a map visualization function based on the enhanced prompt word through the large language model, the method further includes: Obtaining feedback information of the visualization map; Performing semantic analysis on the feedback information, and determining a parameter adjustment direction and an adjustment step size corresponding to the feedback information according to the semantic analysis result; The large language model is iterated based on the parameter adjustment direction and the adjustment step size.

3. The method according to claim 1, characterized in that Before the step of retrieving target visualization information matching the requirement information in the vector database, the method further includes: Obtaining map visualization information through at least one data source; Mapping the map visualization information into a visualization vector through an embedding model; The visualization vector is stored in the vector database, and a vector index of the visualization vector is constructed.

4. The method according to claim 1, characterized in that The step of retrieving target visualization information matching the requirement information in the vector database comprises: Mapping the demand information into a demand vector; Calculating a vector distance between the demand vector and a visualization vector in the vector database, and determining a similarity between the demand vector and the visualization vector based on the vector distance; Based on the similarity, the target visualization vector is selected from the visualization vectors, and target visualization information corresponding to the target visualization vector is obtained.

5. The method according to claim 1, characterized in that The step of combining the requirement text and the target visualization information to generate enhanced prompt words of the large language model includes: Obtaining a preset prompt word template, and determining a demand text placeholder and a visual information placeholder in the prompt word template; The requirement text is used to replace the requirement text placeholder, and the target visualization information is used to replace the visualization information placeholder to generate the enhanced prompt word.

6. The method according to claim 1, characterized in that The step of generating a visualized map by calling a map visualization function based on the enhanced prompt word through the large language model comprises: In the enhanced prompt word, determining rendering parameters of the visual map and determining parameter types of the rendering parameters; Based on the function interface corresponding to the parameter type, calling the corresponding map visualization function; Generate corresponding visualized map information based on the rendering parameters through the map visualization function; The visual map information is integrated to generate the visual map.

7. The method according to claim 1, characterized in that The step of receiving the demand text and extracting the map visualization demand information in the demand text includes: After receiving the demand text, performing word segmentation processing on the demand text to obtain demand text word segmentation; By matching the demand text segmentation with a semantic database, the semantic information of the demand text segmentation is identified according to the matching result; The demand information is generated according to the semantic information.

8. The method according to claim 1, characterized in that After the step of generating a visualized map by calling a map visualization function based on the enhanced prompt word through the large language model, the method further includes: Obtaining a modification requirement text of the visual map, and identifying modification information of the visual map in the modification requirement text; In the vector database, the target visualization information matching the modification information is obtained, and the modification prompt word is generated by combining the target visualization information and the modification information; By using the large language model, a modification action is performed on the visualization map based on the modification prompt word to generate a target visualization map.

9. A map visualization device based on a large language model, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the map visualization method based on a large language model as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the map visualization method based on a large language model as described in any one of claims 1 to 8 are implemented.

Images