Map generation method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a map generation method and device, electronic equipment, a storage medium and a program product, and belongs to the technical field of artificial intelligence. The method comprises the steps that character description is input into a pre-trained large language model, and analysis characters output by the large language model are obtained; the text description is description of a target generation path, and the analysis text comprises geographic information and route indication extracted from the text description; generating a route sequence based on the analysis text; the route sequence comprises a plurality of passing nodes arranged in sequence; determining a navigation route between every two adjacent passing nodes; and generating a dynamic map video based on each navigation route. According to the method, the route in the complex scene can be completely planned, the problem of poor adaptability to the complex scene in the prior art is solved, the dynamic map video in the complex scene is generated, and the planned route can be visually and dynamically displayed.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a map generation method, device, electronic device, storage medium and program product. Background Art

[0002] With the development of smart devices and Geographic Information System (GIS) technology, route planning and mapping services have become an integral part of daily life. Whether in navigation applications, travel planning, or logistics and distribution, efficient and accurate map generation and route planning are crucial for improving user experience and business efficiency.

[0003] Existing route planning and mapping services typically focus on routine travel, generating static route maps that fail to meet the practical needs of displaying routes in complex scenarios. Furthermore, existing technologies primarily plan routes based on a single point of departure and destination, making effective route planning difficult for scenarios involving numerous intermediate nodes, such as marathon races.

[0004] Therefore, how to implement path planning and map services in complex scenarios involving a large number of intermediate nodes has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present invention provides a map generation method, device, electronic device, storage medium and program product to address the defects of the existing technology that cannot meet the actual needs of displaying paths in complex scenarios, and the difficulty of effective path planning for usage scenarios involving a large number of intermediate nodes, thereby realizing path planning and map services in complex scenarios involving a large number of intermediate nodes.

[0006] The present invention provides a map generation method, comprising the following steps: Inputting the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; Generate a route sequence based on the analyzed text; the route sequence includes a plurality of passing nodes arranged in sequence; Determine the navigation route between every two adjacent passing nodes; Based on each of the navigation routes, a dynamic map video is generated.

[0007] According to a map generation method provided by the present invention, generating a route sequence based on the analyzed text includes: Extracting a plurality of path nodes from the analyzed text; Based on the sequence, distance relationship and direction relationship between the nodes, the nodes are sorted to obtain a route sequence.

[0008] According to a map generation method provided by the present invention, determining a navigation route between every two adjacent passing nodes includes: Based on the name of each of the passing nodes, the address resolution function of the map API is called to query and obtain the longitude and latitude coordinates of each of the passing nodes; Based on the latitude and longitude coordinates of each of the passing nodes, the path planning function of the map API is called to obtain the navigation route between every two adjacent passing nodes returned by the map API.

[0009] According to a map generation method provided by the present invention, based on the latitude and longitude coordinates of each of the passing nodes, calling the path planning function of the map API to obtain the navigation route between each two adjacent passing nodes returned by the map API, includes: Based on the longitude and latitude coordinates of two adjacent route nodes, the path planning function of the map API is called in sequence to query and obtain the navigation route between the two adjacent route nodes, and obtain the coordinates of all key points on the navigation route; the key points include the bending points on the navigation route.

[0010] According to a map generation method provided by the present invention, generating a dynamic map video based on each navigation route includes: Based on the preset timeline and animation effects, each navigation route is rendered on the map to obtain a dynamic map video.

[0011] According to a map generation method provided by the present invention, after generating a dynamic map video based on each of the navigation routes, the method further includes: The dynamic map video is uploaded to the cloud server.

[0012] The present invention also provides a map generating device, comprising the following modules: A text analysis module is configured to input a text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of a target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; A sequence generation module is used to generate a route sequence based on the analyzed text; the route sequence includes a plurality of passing nodes arranged in sequence; A route determination module is used to determine a navigation route between every two adjacent passing nodes; The video generation module is used to generate a dynamic map video based on each of the navigation routes.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described map generation methods when executing the computer program.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which implements any of the above-mentioned map generation methods when executed by a processor.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the map generating method described above is implemented.

[0016] The map generation method, device, electronic device, storage medium and program product provided by the present invention input a text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text contains geographic information and route instructions extracted from the text description; based on the analysis text, a route sequence is generated; the route sequence includes a plurality of passing nodes arranged in order; the navigation route between every two adjacent passing nodes is determined; and based on each of the navigation routes, a dynamic map video is generated. The present invention accurately extracts each passing node in the text description for a large number of intermediate nodes contained in complex scenes, and composes an overall route sequence, thereby completely planning the route in the complex scene, effectively solving the problem of poor adaptability of the existing technology to complex scenes. In addition, the present invention automatically generates a dynamic map video in a complex scene based on the text description, which can intuitively and dynamically display the planned route and enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is one of the flowcharts of the map generation method provided by the present invention; Figure 2 This is the second flow chart of the map generation method provided by the present invention; Figure 3 It is a structural diagram of the map generating device provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0020] It should be noted that in the description of the embodiments of the present invention, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element. Terms such as "upper" and "lower" indicate positions or location relationships based on those shown in the accompanying drawings and are intended solely for ease of description and simplification of the present invention. They are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed, or operate in a specific orientation, and are therefore not to be construed as limiting the present invention. Unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be broadly construed, for example, to mean a fixed connection, a detachable connection, or an integral connection; a mechanical connection or an electrical connection; a direct connection or an indirect connection through an intermediate medium; or internal communication between two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] The terms "first," "second," and so forth, used herein are used to distinguish similar objects, not to describe a specific order or precedence. It should be understood that such terms are interchangeable where appropriate, allowing embodiments of the present invention to be implemented in an order other than that illustrated or described herein. Furthermore, the terms "first," "second," and so forth generally distinguish objects of a single type, and do not limit the number of objects. For example, the first object may be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the connected objects.

[0022] The following combination Figures 1-4 The map generation method, device, electronic device and storage medium provided by the embodiments of the present invention are described.

[0023] Figure 1 This is one of the flow charts of the map generation method provided by the present invention, such as Figure 1 As shown, the method includes the following: S110, inputting the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; S120, generating a route sequence based on the analyzed text; the route sequence includes a plurality of sequentially arranged passing nodes; S130, determining a navigation route between every two adjacent passing nodes; S140: Generate a dynamic map video based on each of the navigation routes.

[0024] It should be noted that the execution entity of the map generation method provided in the embodiment of the present invention can be a server or a computer device, such as a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).

[0025] In this embodiment of the present invention, the text description can be directly obtained from local user input or uploaded to a backend server after user input. The backend server then executes the map generation method provided by the present invention based on the uploaded text description. Specifically, when generating a dynamic map video, users (such as event organizers, map service providers, and event planners) enter a detailed text description of the scene through a locally deployed application or the user interface (UI) of an online platform. In the case of marathon track generation, this text description could be a marathon course description; in the case of city tour route planning, this text description could be an introduction to a city tour route; or other complex scene path descriptions that require dynamic display. Users can enter the description verbatim manually or select to read a pre-prepared text description file from a local file. These text description files can be in text formats (such as TXT, DOC, and PDF), and the system automatically parses the text description file content to obtain the text description. This process provides basic input data for subsequent processing, ensuring that the system accurately understands the user's needs and performs subsequent processing.

[0026] In S110, after receiving the text description entered by the user, a pre-trained large language model (e.g., one based on the Transformer architecture) is invoked to perform deep semantic analysis on the text. This process is preferably performed on a backend server equipped with powerful computing capabilities to support efficient model operation. The large language model parses the input text sentence by sentence, extracting key information, which may include but is not limited to location names, directions, and distance descriptions. Leveraging its pre-trained knowledge and contextual semantics, the large language model accurately understands the geographic information and route instructions in the text description. For example, the model can recognize a description such as "From the starting point, drive east along Road AA for 3 kilometers, then turn right onto Road BB" and decompose it into specific geographic information (location name) and route instructions (direction of travel, distance traveled, etc.). This process provides accurate data support for subsequent node extraction and path planning, ensuring that the system can accurately understand complex scenario descriptions entered by the user.

[0027] In S120 , the route nodes include the starting point, the end point, and the intermediate nodes between the starting point and the end point. For example, for the text description "start from the starting point, pass the CC Bridge, and arrive at the end point", the route nodes include the starting point, the CC Bridge, and the end point, generating a route sequence of "starting point, CC Bridge, end point".

[0028] In S130 , taking the route sequence of “starting point, CC Bridge, end point” as an example, a navigation route between the starting point and CC Bridge, and a navigation route between CC Bridge and the end point are determined.

[0029] In S140 , a dynamic three-dimensional map effect is generated according to each segment of the navigation route.

[0030] The map generation method provided by the embodiment of the present invention inputs a text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; based on the analysis text, a route sequence is generated; the route sequence includes a plurality of pass nodes arranged in sequence; the navigation route between every two adjacent pass nodes is determined; and based on each of the navigation routes, a dynamic map video is generated. The present invention accurately extracts each pass node in the text description for a large number of intermediate nodes contained in complex scenes, and forms an overall route sequence, thereby completely planning the route in the complex scene, effectively solving the problem of poor adaptability of the existing technology to complex scenes. In addition, the present invention automatically generates a dynamic map video in a complex scene based on the text description, which can intuitively and dynamically display the planned route, enhance the user experience, and can be applied to scenes in many fields such as marathon events, urban tourism, and smart cities.

[0031] In an optional embodiment, generating a route sequence based on the analyzed text includes: Extracting a plurality of path nodes from the analyzed text; Based on the sequence, distance relationship and direction relationship between the nodes, the nodes are sorted to obtain a route sequence.

[0032] In the embodiment of the present invention, after the text analysis is completed, each passing node is screened out from the analyzed text.

[0033] During the specific implementation process, natural language processing technology is used, combined with keyword recognition and semantic understanding, to extract key geographic location information from text descriptions. For example, in the scenario describing "starting from the starting point, passing the CC Bridge, and arriving at the end point", "starting point", "CC Bridge", and "end point" are identified as transit nodes. The extraction of transit nodes not only relies on keyword matching, but also a comprehensive judgment based on the contextual semantics to ensure that the extracted node information is accurate. For example, even if the "starting point" or "end point" is not explicitly mentioned in the text description, the existence of these nodes can be inferred through semantic analysis, thereby ensuring that the system can accurately identify all important nodes in the route, laying the foundation for subsequent path planning.

[0034] In an embodiment of the present invention, after all the transit nodes are extracted, they are logically connected to form a complete route sequence. Specifically, the transit nodes are organized into a clear, orderly sequence based on the order, distance, and other logical relationships between the nodes. For example, according to the logical order of "first passing through point A, then passing through point B, and finally arriving at point C" in the text description, transit nodes A, B, and C are arranged in sequence. In certain complex scenarios, the distance and direction relationships between nodes are considered to ensure that the generated route sequence conforms to the actual geographical conditions.

[0035] The map generation method provided by the embodiment of the present invention extracts the passing nodes from the analyzed text and arranges them in sequence to generate a clear and orderly route node sequence so that subsequent path planning and dynamic map generation can proceed smoothly.

[0036] In an optional embodiment, determining the navigation route between every two adjacent waypoints includes: Based on the name of each of the passing nodes, the address resolution function of the map API is called to query and obtain the longitude and latitude coordinates of each of the passing nodes; Based on the latitude and longitude coordinates of each of the passing nodes, the path planning function of the map API is called to obtain the navigation route between every two adjacent passing nodes returned by the map API.

[0037] In this embodiment of the present invention, after generating a sequence of route nodes, the specific latitude and longitude coordinates of each node are searched within the map application based on the node name. Specifically, this is accomplished by calling the map API (Application Programming Interface), passing the node name as a query parameter, and invoking the API's address resolution function to retrieve the corresponding longitude and latitude coordinates. For example, some map APIs offer an address resolution function that allows users to retrieve precise longitude and latitude information by entering a location name.

[0038] The map generation method provided by the embodiment of the present invention obtains the latitude and longitude coordinates of the passed nodes by calling the address resolution function of the map API, ensuring that the precise location information of each node can be obtained, providing accurate geographic coordinates for path planning, and then determining the navigation route between the passed nodes based on the latitude and longitude coordinates of the passed nodes.

[0039] In an optional embodiment, the calling of a path planning function of a map API based on the latitude and longitude coordinates of each of the waypoints to obtain a navigation route between each two adjacent waypoints returned by the map API includes: Based on the longitude and latitude coordinates of two adjacent route nodes, the path planning function of the map API is called in sequence to query and obtain the navigation route between the two adjacent route nodes, and obtain the coordinates of all key points on the navigation route; the key points include the bending points on the navigation route.

[0040] In an embodiment of the present invention, after obtaining the longitude and latitude coordinates of all transit nodes, the navigation route between the previous and next transit nodes is sequentially queried based on the longitude and latitude coordinate sequence, and the coordinates of the nodes requiring turns in the middle are obtained. Specifically, this is achieved by calling the path planning function of the map API, using the longitude and latitude coordinates of adjacent nodes as the starting and ending points, calling the path planning interface, and obtaining the coordinates of all key points on the path, including the coordinates of the turning points. For example, the path planning function of a certain map API can support multiple travel modes (such as driving, walking, cycling, etc.) and return detailed path information.

[0041] It should be noted that the coordinates of the key point can be the latitude and longitude coordinates of the key point, or the relative position coordinates in the map, and there is no specific limitation here.

[0042] The map generation method provided by the embodiment of the present invention obtains the navigation route and the coordinates of all key points by calling the path planning function of the map API, ensuring the generation of a complete navigation route containing all important details, and providing detailed path information for the generation of dynamic maps.

[0043] In an optional embodiment, generating a dynamic map video based on each of the navigation routes includes: Based on the preset timeline and animation effects, each navigation route is rendered on the map to obtain a dynamic map video.

[0044] In this embodiment of the present invention, after acquiring all path information, a dynamic map video is generated based on the acquired latitude and longitude coordinates of the nodes along the way and the path information. Specifically, a map visualization library (such as Cesium.js) is used to render the node coordinates and path information onto a map, and a dynamic video is generated using animation techniques. This dynamic display of the path can be achieved by setting a timeline and animation effects. For example, Cesium.js supports the fusion of video streams with map data to generate a dynamic three-dimensional map effect.

[0045] The map generation method provided by the embodiment of the present invention renders the passing nodes and navigation routes onto the map according to the timeline and animation effects, and generates a dynamic map video, thereby displaying complex route information in the form of an intuitive dynamic video, enhancing the user experience.

[0046] In an optional embodiment, after generating a dynamic map video based on each of the navigation routes, the method further includes: The dynamic map video is uploaded to the cloud server.

[0047] In an embodiment of the present invention, after the dynamic map video is generated, the generated dynamic map video is output to the user. Specifically, the dynamic map video file can be saved locally or uploaded to a server through a user interface or file download, allowing the user to download or view it online. For example, the user can use a simple graphical interface or command line tool to save the generated dynamic map video as a local file or upload it to a cloud server.

[0048] The map generation method provided by the embodiment of the present invention uploads the dynamic map video to the cloud server for users to download or watch online, meeting the dynamic display requirements in complex scenarios.

[0049] Figure 2 This is the second flow chart of the map generation method provided by the present invention. Figure 2 , the preferred embodiments of the present invention are described.

[0050] like Figure 2As shown, inputting a text description involves the user entering a detailed text description of the scene through a locally deployed application or the user interface of an online platform. Invoking a large model for text analysis involves invoking a pre-trained large language model to perform deep semantic analysis on the text, extracting key information such as location names, directions, and distance descriptions. Extracting path nodes involves filtering each path node from the analyzed text. Composing a route node sequence involves logically connecting the extracted path nodes to form a complete route sequence. Querying node longitude and latitude coordinates involves invoking the address resolution function of the map API to obtain the longitude and latitude coordinates of the path nodes. Querying the navigation route and turning node coordinates involves sequentially querying the navigation route between the previous and next nodes based on the longitude and latitude coordinate sequence, and obtaining the coordinates of any intermediate turning nodes to obtain detailed path information. Generating a dynamic map video involves generating a dynamic map video based on the obtained node coordinates and path information. Outputting the dynamic map video involves saving the dynamic map video locally or uploading it to a server for user download or online viewing.

[0051] The map generating device provided by an embodiment of the present invention is described below. The map generating device described below and the map generating method described above can be referenced to each other.

[0052] Figure 3 This is a schematic diagram of the structure of the map generating device provided by the present invention. Figure 3 As shown, the map generating device may include but is not limited to: The text analysis module 310 is configured to input the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; The sequence generation module 320 is configured to generate a route sequence based on the analyzed text; the route sequence includes a plurality of sequentially arranged route nodes; The route determination module 330 is used to determine a navigation route between every two adjacent passing nodes; The video generation module 340 is used to generate a dynamic map video based on each of the navigation routes.

[0053] In an optional embodiment, the sequence generation module 320 is specifically configured to: Extracting a plurality of path nodes from the analyzed text; Based on the sequence, distance relationship and direction relationship between the nodes, the nodes are sorted to obtain a route sequence.

[0054] In an optional embodiment, the route determination module 330 includes: The coordinate query unit 331 is used to call the address resolution function of the map API based on the name of each of the passing nodes to query and obtain the longitude and latitude coordinates of each of the passing nodes; The path planning unit 332 is used to: call the path planning function of the map API based on the latitude and longitude coordinates of each of the passing nodes, and obtain the navigation route between every two adjacent passing nodes returned by the map API.

[0055] In an optional embodiment, the path planning unit 332 is specifically configured to: Based on the longitude and latitude coordinates of two adjacent route nodes, the path planning function of the map API is called in sequence to query and obtain the navigation route between the two adjacent route nodes, and obtain the coordinates of all key points on the navigation route; the key points include the bending points on the navigation route.

[0056] In an optional embodiment, the video generation module 340 is specifically configured to: Based on the preset timeline and animation effects, each navigation route is rendered on the map to obtain a dynamic map video.

[0057] In an optional embodiment, the map generating device further includes: The video uploading module 350 is used to upload the dynamic map video to the cloud server.

[0058] Figure 4 An example of a physical structure diagram of an electronic device is shown below. Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 440. The processor 410, the communications interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call logic instructions in the memory 430 to execute a map generation method, which includes: Inputting the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; Generating a route sequence based on the analyzed text; the route sequence includes a plurality of passing nodes arranged in sequence; Determine the navigation route between every two adjacent passing nodes; Based on each of the navigation routes, a dynamic map video is generated.

[0059] Furthermore, the logic instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0060] On the other hand, the present invention further provides a computer program product, comprising a computer program, which may be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the map generation method provided by each of the above methods, which includes: Inputting the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; Generating a route sequence based on the analyzed text; the route sequence includes a plurality of passing nodes arranged in sequence; Determine the navigation route between every two adjacent passing nodes; Based on each of the navigation routes, a dynamic map video is generated.

[0061] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the map generation method provided by the above methods, the method comprising: Inputting the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; Generating a route sequence based on the analyzed text; the route sequence includes a plurality of passing nodes arranged in sequence; Determine the navigation route between every two adjacent passing nodes; Based on each of the navigation routes, a dynamic map video is generated.

[0062] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0063] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A map generation method, characterized in that: include: Inputting the text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of the target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; generating a route sequence based on the analyzed text; The route sequence includes a plurality of passing nodes arranged in sequence; Determine the navigation route between every two adjacent passing nodes; Based on each of the navigation routes, a dynamic map video is generated.

2. The map generation method according to claim 1, characterized in that: The generating of a route sequence based on the analyzed text includes: Extracting a plurality of path nodes from the analyzed text; Based on the sequence, distance relationship and direction relationship between the nodes, the nodes are sorted to obtain a route sequence.

3. The map generation method according to claim 1, wherein: Determining the navigation route between every two adjacent passing nodes includes: Based on the name of each of the passing nodes, the address resolution function of the map API is called to query and obtain the longitude and latitude coordinates of each of the passing nodes; Based on the latitude and longitude coordinates of each of the passing nodes, the path planning function of the map API is called to obtain the navigation route between every two adjacent passing nodes returned by the map API.

4. The map generation method according to claim 3, characterized in that: The method of calling the path planning function of the map API based on the latitude and longitude coordinates of each of the passing nodes to obtain the navigation route between each two adjacent passing nodes returned by the map API includes: Based on the longitude and latitude coordinates of two adjacent route nodes, the path planning function of the map API is called in sequence to query and obtain the navigation route between the two adjacent route nodes, and obtain the coordinates of all key points on the navigation route; the key points include the bending points on the navigation route.

5. The map generation method according to claim 4, characterized in that: The generating of a dynamic map video based on each of the navigation routes includes: Based on the preset timeline and animation effects, each navigation route is rendered on the map to obtain a dynamic map video.

6. The map generation method according to claim 1 or 5, characterized in that: After generating the dynamic map video based on each of the navigation routes, the method further includes: The dynamic map video is uploaded to the cloud server.

7. A map generating device, characterized in that: include: A text analysis module is configured to input a text description into a pre-trained large language model to obtain an analysis text output by the large language model; the text description is a description of a target generation path, and the analysis text includes geographic information and route instructions extracted from the text description; A sequence generation module, configured to generate a route sequence based on the analyzed text; The route sequence includes a plurality of passing nodes arranged in sequence; A route determination module is used to determine a navigation route between every two adjacent passing nodes; The video generation module is used to generate a dynamic map video based on each of the navigation routes.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the map generation method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the map generating method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the map generating method according to any one of claims 1 to 6 is implemented.

Images