Method and device for rendering vehicle navigation picture, storage medium and electronic device

Abstract

This invention provides a method, apparatus, storage medium, and electronic device for rendering vehicle navigation screens. The method includes: acquiring initial navigation data of the vehicle in the current road segment in real time, and acquiring the remaining hardware resources of the vehicle in real time, wherein the hardware resources include CPU resources, memory resources, and GPU resources; filtering data in the initial navigation data that meets priority conditions according to the remaining resources to obtain target navigation data; and rendering the target navigation data based on the remaining resources to obtain a lane-level thumbnail navigation screen of the vehicle in the current road segment. This embodiment solves the technical problem in the prior art where insufficient vehicle-side hardware resources lead to the inability to update lane-level thumbnail navigation screens in real time, ensuring the real-time performance of lane-level navigation screens and avoiding stuttering.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically, to a method and apparatus for rendering vehicle navigation screens, a storage medium, and an electronic device. Background Technology

[0002] In related technologies, while traditional AR relies on planar markers and fixed cone projection, Surrounding Reality (SR) reconstructs the technological paradigm of environmental interaction through real-time 3D scene semantic deconstruction, high-density spatial sensor fusion, and dynamic interactive hotspot mapping. SR no longer confines digital content to a screen or a preset plane, but instead achieves precise deployment of interactive entities across the entire domain based on millimeter-level spatial topology recognition and sub-millisecond response. SR aims to enhance users' perception and interactive experience of the vehicle's surrounding environment, thereby improving driving safety and convenience. SR technology captures real-time information about the vehicle's surroundings using onboard sensors (such as cameras, radar, and lidar), and then uses computer vision technology to transform this data into intuitive visualizations displayed on in-vehicle screens or head-up displays, such as achieving lane-level navigation rendering.

[0003] In related technologies, vehicles face insufficient system resources (CPU, memory) when processing road data and performing 3D rendering.

[0004] No efficient and accurate solution has yet been found to address the aforementioned issues in the relevant technologies. Summary of the Invention

[0005] This invention provides a method and apparatus for rendering vehicle navigation screens, a storage medium, and an electronic device to solve technical problems in related technologies.

[0006] According to an embodiment of the present invention, a method for rendering a vehicle navigation screen is provided, comprising: acquiring initial navigation data of the vehicle in the current road segment in real time, and acquiring the remaining amount of hardware resources of the vehicle in real time, wherein the hardware resources include CPU resources, memory resources, and GPU resources; filtering data in the initial navigation data that meets priority conditions according to the remaining amount of resources to obtain target navigation data; and rendering the target navigation data based on the remaining amount of resources to obtain a lane-level thumbnail navigation screen of the vehicle in the current road segment.

[0007] Optionally, real-time acquisition of the vehicle's initial navigation data on the current road segment includes: real-time acquisition of video frames captured by the vehicle's camera, performing target detection on the video frames to obtain navigation environment information, wherein the navigation environment information includes static obstacle information, lane lines, and dynamic obstacle information; real-time acquisition of the vehicle's vehicle status information, wherein the vehicle status information includes vehicle speed and vehicle body angle; real-time acquisition of a screenshot of the vehicle's navigation view interface, identifying the first driving route data in the screenshot on the current road segment, wherein the first driving route data includes driving segment data and turn-by-turn navigation (TBT) data.

[0008] Optionally, filtering data that meets priority conditions in the initial navigation data based on the remaining resource amount includes: obtaining the resource requirement of the initial navigation data, wherein the resource requirement is the minimum amount of resources required for the vehicle to render the initial navigation data; calculating the resource difference between the resource requirement and the remaining resource amount; if the resource difference is greater than a preset threshold, filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data, wherein the data difference between the target navigation data and the initial navigation data is positively correlated with the resource difference.

[0009] Optionally, the hardware resources include CPU resources. Filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data includes: extracting first driving route data from the initial navigation data, wherein the first driving route data includes driving segment data and TBT data; filtering the driving segment data based on the resource difference, and retrieving locally stored road segment scene data corresponding to the driving segment data for the current road segment, wherein the road segment scene data is lane-level scene data pre-rendered by the vehicle when hardware resources were sufficient in a historical time period; and outputting the TBT data as target navigation data.

[0010] Optionally, the hardware resources include memory resources. Filtering data in the initial navigation data that meets priority conditions based on the resource difference to obtain target navigation data includes: classifying the navigation environment information in the initial navigation data to obtain multiple environment elements, wherein the multiple environment elements include: static obstacles, lane lines, and dynamic obstacle materials; filtering a first environment element from the multiple environment elements based on the resource difference to obtain the remaining second environment elements; if the memory usage of the second environment element is less than the remaining memory, maintaining the current rendering frame rate and outputting the second environment element as target navigation data; if the memory usage of the second environment element is greater than or equal to the remaining memory, reducing the current rendering frame rate and calculating the reduced second memory usage; determining whether the second memory usage is less than the remaining memory; if the second memory usage is less than the remaining memory, outputting the reduced second environment element as target navigation data; if the second memory usage is greater than or equal to the remaining memory, filtering dynamic obstacles in the navigation environment information to obtain target navigation data.

[0011] Optionally, filtering the first environment element among the multiple environment elements based on the resource difference to obtain the remaining second environment element includes: determining the priority of the multiple environment elements and calculating the element memory occupied by each of the multiple environment elements; selecting several first environment elements in order according to the priority, wherein the total element memory occupied by the several first environment elements is greater than or equal to the resource difference; filtering the several first environment elements among the multiple environment elements to obtain the remaining second environment element.

[0012] Optionally, the hardware resources include GPU resources. Filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data includes: determining the initial navigation segment to be rendered; filtering the last segment of the initial navigation segment based on the resource difference to shorten the initial navigation segment into the target navigation segment, thereby obtaining target navigation data, wherein the length of the last segment is positively correlated with the resource difference.

[0013] Optionally, the hardware resources include GPU resources. Filtering data in the initial navigation data that meets priority conditions based on the resource difference to obtain target navigation data includes: classifying navigation environment information in the initial navigation data to obtain multiple rendering elements, wherein the multiple rendering elements include: static obstacles, lane lines, dynamic obstacles, and element materials; determining the priority of the multiple rendering elements and calculating the element computing power resources corresponding to each of the multiple rendering elements; selecting several first rendering elements in order according to the priority, wherein the total element computing power resources of the several first rendering elements are greater than or equal to the resource difference; filtering the several first rendering elements from the multiple rendering elements and outputting the remaining second rendering elements as target navigation data.

[0014] Optionally, after determining whether the resource difference is greater than a preset threshold, the method further includes: if the resource difference is less than or equal to the preset threshold, obtaining the second driving route data of the vehicle in the current road segment from the cloud server, wherein the second driving route data includes driving segment data and TBT data; constructing complete navigation data using the vehicle's navigation environment information, vehicle status information, and the second driving route data; rendering the complete navigation data based on the remaining resource quantity to obtain the lane-level complete navigation screen of the vehicle in the current road segment.

[0015] Optionally, after obtaining the second driving route data of the vehicle on the current road segment from the cloud server, the method includes: constructing training samples using the first driving route data and the second driving route data; and training an image recognition model using the training samples, wherein the image recognition model is used to identify the driving route data of the current road segment from a screenshot of the vehicle's navigation view interface.

[0016] According to another embodiment of the present invention, a vehicle navigation screen rendering apparatus is provided, comprising: a first acquisition module, configured to acquire initial navigation data of the vehicle in the current road segment in real time, and to acquire the remaining amount of hardware resources of the vehicle in real time, wherein the hardware resources include CPU resources, memory resources, and GPU resources; a filtering module, configured to filter data in the initial navigation data that meets priority conditions according to the remaining amount of resources, to obtain target navigation data; and a first rendering module, configured to render the target navigation data based on the remaining amount of resources, to obtain a lane-level thumbnail navigation screen of the vehicle in the current road segment.

[0017] Optionally, the first acquisition module includes: a first acquisition unit, configured to acquire video frames captured by the vehicle's camera in real time, perform target detection on the video frames, and obtain navigation environment information, wherein the navigation environment information includes static obstacle information, lane lines, and dynamic obstacle information; a second acquisition unit, configured to acquire vehicle status information of the vehicle in real time, wherein the vehicle status information includes vehicle speed and vehicle body angle; and a third acquisition unit, configured to acquire screenshots of the vehicle's navigation view interface in real time, and identify first driving route data in the screenshots for the current road segment, wherein the first driving route data includes driving segment data and turn-by-turn navigation (TBT) data.

[0018] Optionally, the filtering module includes: an acquisition unit, configured to acquire the resource requirement of the initial navigation data, wherein the resource requirement is the minimum amount of resources required by the vehicle to render the initial navigation data; a calculation unit, configured to calculate the resource difference between the resource requirement and the remaining resource amount; and a filtering unit, configured to filter data in the initial navigation data that meets priority conditions based on the resource difference if the resource difference is greater than a preset threshold, to obtain target navigation data, wherein the data difference between the target navigation data and the initial navigation data is positively correlated with the resource difference.

[0019] Optionally, the hardware resources include CPU resources, and the filtering unit includes: an extraction subunit for extracting first driving route data from the initial navigation data, wherein the first driving route data includes driving segment data and TBT data; a first filtering subunit for filtering the driving segment data based on the resource difference and retrieving locally stored road segment scene data corresponding to the driving segment data for the current road segment, wherein the road segment scene data is lane-level scene data pre-rendered by the vehicle when hardware resources were sufficient in historical time; and a first output subunit for outputting the TBT data as target navigation data.

[0020] Optionally, the hardware resources include memory resources, and the filtering unit includes: a first classification subunit, used to classify the navigation environment information in the initial navigation data to obtain multiple environment elements, wherein the multiple environment elements include: static obstacles, lane lines, and dynamic obstacle materials; a second filtering subunit, used to filter the first environment element among the multiple environment elements based on the resource difference to obtain the remaining second environment elements; a processing subunit, used to maintain the current rendering frame rate and output the second environment element as target navigation data if the memory usage of the second environment element is less than the remaining memory; if the memory usage of the second environment element is greater than or equal to the remaining memory, reduce the current rendering frame rate and calculate the second memory usage after the frame reduction; secondly, determine whether the second memory usage is less than the remaining memory; and a second output subunit, used to output the second environment element after the frame reduction as target navigation data if the second memory usage is less than the remaining memory; if the second memory usage is greater than or equal to the remaining memory, filter the dynamic obstacles in the navigation environment information to obtain the target navigation data.

[0021] Optionally, the second filtering subunit is further configured to: determine the priority of the plurality of environmental elements, and calculate the element-occupied memory of the plurality of environmental elements respectively; select a plurality of first environmental elements in order according to the priority, wherein the total element-occupied memory of the plurality of first environmental elements is greater than or equal to the resource difference; filter the plurality of first environmental elements among the plurality of environmental elements to obtain the remaining second environmental elements.

[0022] Optionally, the hardware resources include GPU resources, and the filtering unit includes: a first determining subunit for determining the initial navigation segment to be rendered; and a third filtering subunit for filtering the last segment of the initial navigation segment based on the resource difference, so as to shorten the initial navigation segment into the target navigation segment and obtain target navigation data, wherein the length of the last segment is positively correlated with the resource difference.

[0023] Optionally, the hardware resources include GPU resources, and the filtering unit includes: a second classification subunit, used to classify the navigation environment information in the initial navigation data to obtain multiple rendering elements, wherein the multiple rendering elements include: static obstacles, lane lines, dynamic obstacles, and element materials; a second determination subunit, used to determine the priority of the multiple rendering elements and calculate the element computing power resources corresponding to the multiple rendering elements respectively; a selection subunit, used to select several first rendering elements in order according to the priority, wherein the total element computing power resources of the several first rendering elements are greater than or equal to the resource difference; and a fourth filtering subunit, used to filter the several first rendering elements among the multiple rendering elements and output the remaining second rendering elements as target navigation data.

[0024] Optionally, the device further includes: a second acquisition module, configured to acquire second driving route data of the vehicle in the current road segment from a cloud server if the resource difference is less than or equal to the preset threshold after the filtering module determines whether the resource difference is greater than a preset threshold, wherein the second driving route data includes driving segment data and TBT data; a construction module, configured to construct complete navigation data using the vehicle's navigation environment information, vehicle status information, and the second driving route data; and a second rendering module, configured to render the complete navigation data based on the remaining resource amount to obtain a lane-level complete navigation screen of the vehicle in the current road segment.

[0025] Optionally, the device includes: a construction module, configured to construct training samples using the first driving route data and the second driving route data after the second acquisition module obtains the second driving route data of the vehicle in the current road segment from the cloud server; and a training module, configured to train an image recognition model using the training samples, wherein the image recognition model is used to identify the driving route data of the current road segment from a screenshot of the vehicle's navigation view interface.

[0026] According to another aspect of the embodiments of this application, a storage medium is also provided, the storage medium including a stored program that executes the above steps when the program is run.

[0027] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: the memory is used to store computer programs; and the processor is used to execute the steps in the above method by running the programs stored in the memory.

[0028] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method.

[0029] The beneficial effects of this invention are:

[0030] 1. The generation of rendering data is placed on the vehicle side, which reduces the dependence on server data, lowers the hardware requirements for cloud servers, reduces data transmission links, and lowers network requirements;

[0031] 2. Some of the data used for lane-level rendering is generated by the edge model and adjusted according to the actual road conditions. When there are sufficient vehicle-side hardware resources, some future data is rendered in advance. When there are insufficient vehicle-side hardware resources, the data to be rendered is filtered to optimize rendering performance and reduce the requirements on vehicle hardware. Attached Figure Description

[0032] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0033] Figure 1 This is a hardware structure block diagram of a vehicle according to an embodiment of the present invention;

[0034] Figure 2 This is a flowchart of a method for rendering a vehicle navigation screen according to an embodiment of the present invention;

[0035] Figure 3 This is a flowchart of lane-level rendering based on the end-side model according to an embodiment of the present invention;

[0036] Figure 4 This is a structural block diagram of a vehicle navigation screen rendering device according to an embodiment of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] Example 1

[0040] The method embodiment provided in Embodiment 1 of this application can be executed in a vehicle, controller, processor, computer, or similar processing device. Taking its operation in a vehicle as an example, Figure 1 This is a hardware structure block diagram of a vehicle according to an embodiment of the present invention. For example... Figure 1 As shown, a vehicle may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the vehicle may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the vehicle described above. For example, the vehicle may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0041] The memory 104 can be used to store vehicle programs, such as application software programs and modules, like the vehicle program corresponding to a vehicle navigation screen rendering method in an embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the vehicle program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the vehicle via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0042] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the vehicle's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0043] This embodiment provides a method for rendering vehicle navigation screens. Figure 2 This is a flowchart of a vehicle navigation screen rendering method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0044] Step S201: Obtain the initial navigation data of the vehicle in the current road segment in real time, and obtain the remaining amount of hardware resources of the vehicle in real time, wherein the hardware resources include CPU resources, memory resources and GPU resources.

[0045] Optionally, the initial navigation data consists of all the basic data required to render the lane-level thumbnail navigation screen. The basic data includes video frames captured by the vehicle's cameras, the hardware usage status of the vehicle's infotainment system, vehicle status information, and the driving route data of the navigation route. Through further analysis, navigation environment information can be obtained from the video frames, including static obstacle information, lane lines, and dynamic obstacle information. The driving route data includes driving segment data and turn-by-turn (TBT) data.

[0046] Optionally, the vehicle's hardware resources include CPU, memory, and GPU.

[0047] Step S202: Filter the data in the initial navigation data that meets the priority conditions according to the remaining resource quantity to obtain the target navigation data;

[0048] Step S203: Render the target navigation data based on the remaining resources to obtain the lane-level thumbnail navigation screen of the vehicle in the current road segment.

[0049] Through the above steps, the initial navigation data of the vehicle in the current road segment is obtained in real time, as well as the remaining amount of hardware resources of the vehicle, including CPU resources, memory resources, and GPU resources. Data in the initial navigation data that meets priority conditions is filtered according to the remaining resources to obtain target navigation data. The target navigation data is then rendered based on the remaining resources to obtain a lane-level thumbnail navigation screen for the vehicle in the current road segment. When vehicle-side hardware resources are insufficient, the data to be rendered is filtered, optimizing rendering performance and reducing the requirements on the vehicle's hardware. This solves the technical problem in the prior art where insufficient vehicle-side hardware resources lead to the inability to update the lane-level thumbnail navigation screen in real time, ensuring the real-time performance of the lane-level navigation screen and avoiding lag.

[0050] In one embodiment of this example, real-time acquisition of initial navigation data of the vehicle on the current road segment includes: real-time acquisition of video frames captured by the vehicle's camera, performing target detection on the video frames to obtain navigation environment information, wherein the navigation environment information includes static obstacle information, lane lines, and dynamic obstacle information; real-time acquisition of vehicle status information, wherein the vehicle status information includes vehicle speed and vehicle body angle; real-time acquisition of a screenshot of the vehicle's navigation view interface, identifying first driving route data in the screenshot on the current road segment, wherein the first driving route data includes driving segment data and TBT data.

[0051] Among them, driving segment data is the basic static data of the navigation map, describing the structured information of the road network itself, including attributes such as the geometry, length, number of lanes, road grade, speed limit, and topological connectivity of the road segment. TBT data is dynamic guidance information generated based on path planning. It is step-by-step instruction data provided to users during real-time navigation (such as driving to the second lane on the right and going straight at the current intersection), directly addressing the driver's guidance needs.

[0052] On the vehicle side, an edge model is created and deployed. This model is designed for multimodal capabilities. Frame images from video captured by the vehicle's cameras are one of the input parameters of this model. The memory and GPU usage of the vehicle's infotainment system are also one of the input parameters. The running data of lane-level navigation on the vehicle is also one of the input parameters, including: the current rendering position of the vehicle logo, surrounding buildings, vehicles on the road, and obstacles. Vehicle driving data is one of the input parameters, including: vehicle speed and vehicle body angle. The vehicle's driving route is one of the input parameters, including: driving segment data and TBT data.

[0053] In this embodiment, the vehicle-side model is a multimodal model. During the preparation phase, the initial multimodal model can be fine-tuned to obtain the target multimodal model. The initial multimodal model can be selected according to actual needs; for example, the initial multimodal model can be chatGPT-4V. The target multimodal model is used for image recognition of the navigation interface and for determining the driving status based on the recognized content. The multimodal model includes multiple models that implement specific functions, including an image recognition model used to recognize screenshots of navigation applications and identify the road segment guidance type. This involves identifying the type of road segment ahead: straight ahead, left turn, right turn, and U-turn. Training method: Using lane-level navigation application screenshots, the guidance type in the screenshots is labeled, and the model is trained using the labeled images. The image recognition model can use open-source models such as SSD and Faster R-CNN. The system status monitoring model can utilize data analysis and anomaly detection functions from models such as One-Class SVM. Training methods include: monitoring system runtime data and resource usage of the lane-level navigation application during normal rendering; and monitoring system resource usage when rendering resources are insufficient, identifying the types and quantities of missing resources (CPU, memory, GPU). The CV (Computer Vision) object detection and recognition model identifies elements in the vehicle's surrounding environment (people, obstacles). The YOLO open-source model can be used, trained by labeling and classifying images of the vehicle's surroundings.

[0054] Optionally, filtering data that meets priority conditions in the initial navigation data based on the remaining resource amount includes: obtaining the resource requirement of the initial navigation data, wherein the resource requirement is the minimum amount of resources required for the vehicle to render the initial navigation data; calculating the resource difference between the resource requirement and the remaining resource amount; if the resource difference is greater than a preset threshold, filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data, wherein the data difference between the target navigation data and the initial navigation data is positively correlated with the resource difference.

[0055] The priority conditions of the initial navigation data can be divided according to the data type (such as driving segment data, TBT data, static obstacles, lane lines, dynamic obstacle materials, etc.) and the road segment to which the data belongs (such as the starting road segment, the middle road segment, the ending road segment).

[0056] For example, optionally, the preset threshold is 0 or the minimum amount of resources to ensure the basic functions of the vehicle system (such as 10% CPU utilization, 120M memory, and 50M GPU). Taking the CPU as an example, if the resource requirement is 30% and the remaining resource is 25%, then 30%-25%=5%. Since 5% is greater than 0, the CPU cannot currently handle the rendering task of the initial navigation data, so the initial navigation data needs to be filtered to reduce the workload of the CPU.

[0057] In one implementation scenario of this embodiment, the hardware resources include CPU resources. Filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data includes: extracting first driving route data from the initial navigation data, wherein the first driving route data includes driving segment data and TBT data; filtering the driving segment data based on the resource difference, and retrieving locally stored road segment scene data corresponding to the driving segment data for the current road segment, wherein the road segment scene data is lane-level scene data pre-rendered by the vehicle when hardware resources were sufficient in a historical time period; and outputting the TBT data as target navigation data.

[0058] When system resources are insufficient, the model calculates the gap between the system resources required for rendering and the resources the system can provide. This calculation involves CPU, memory, and GPU computing power (CPU processes data, memory loads data, and GPU renders data). If CPU is insufficient, the model adjusts the amount of data to be processed (e.g., for 10km of data, only TBT data is processed; straight-line data is generated by the model and does not require CPU processing). Since the driving segment data in the route data generally does not change in a short period (unless there is road construction or temporary traffic control), it can be rendered in advance when vehicle resources are sufficient. The driving segment data is filtered out from the first driving route data to be rendered, while the TBT data needs to be adjusted according to the vehicle's current lane in real time. The CPU only needs to process the filtered TBT data from the first driving route data, which can improve CPU processing speed and efficiency.

[0059] In one example, after determining whether the resource difference is greater than a preset threshold, the method further includes: if the resource difference is less than or equal to the preset threshold, obtaining the second driving route data of the vehicle in the current road segment from the cloud server, wherein the second driving route data includes driving segment data and TBT data; constructing complete navigation data using the vehicle's navigation environment information, vehicle status information, and the second driving route data; rendering the complete navigation data based on the remaining resource quantity to obtain the lane-level complete navigation screen of the vehicle in the current road segment.

[0060] Optionally, after obtaining the second driving route data of the vehicle on the current road segment from the cloud server, the method further includes: constructing training samples using the first driving route data and the second driving route data; and training an image recognition model using the training samples, wherein the image recognition model is used to identify the driving route data of the current road segment from screenshots of the vehicle's navigation view interface.

[0061] When the vehicle has sufficient hardware system resources, it pre-loads TBT data for the driving segment. Based on the TBT data and route, it pre-renders the lane-level scene for that segment, and transmits the scene data and other necessary data to the model. The model then determines whether the data needs modification or adjustment, and stores the processed rendering data locally. When the vehicle reaches that segment (the pre-loaded and rendered segment), it assesses the system's resource usage. If system resources are sufficient, it retrieves data from the cloud server, renders it, and uses the pre-rendered data and the data retrieved from the server as training data for the model. If system resources are insufficient when reaching a certain segment, it loads the pre-stored data.

[0062] In one implementation scenario of this embodiment, the hardware resources include memory resources. Filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data includes: classifying the navigation environment information in the initial navigation data to obtain multiple environment elements, wherein the multiple environment elements include: static obstacles, lane lines, and dynamic obstacle materials; filtering a first environment element from the multiple environment elements based on the resource difference to obtain the remaining second environment elements; if the memory usage of the second environment element is less than the remaining memory, maintaining the current rendering frame rate and outputting the second environment element as target navigation data; if the memory usage of the second environment element is greater than or equal to the remaining memory, reducing the current rendering frame rate and calculating the reduced second memory usage; determining whether the second memory usage is less than the remaining memory; if the second memory usage is less than the remaining memory, outputting the reduced second environment element as target navigation data; if the second memory usage is greater than or equal to the remaining memory, filtering dynamic obstacles in the navigation environment information to obtain target navigation data.

[0063] In one example, filtering a first environment element from a plurality of environment elements based on the resource difference to obtain the remaining second environment elements includes: determining the priority of the plurality of environment elements and calculating the element memory occupied by each of the plurality of environment elements; selecting a plurality of first environment elements in order of priority, wherein the total element memory occupied by the plurality of first environment elements is greater than or equal to the resource difference; and filtering the plurality of first environment elements from the plurality of environment elements to obtain the remaining second environment elements.

[0064] If memory is insufficient, determine the memory deficit and, based on the deficit, filter and load data using the model (through data training, a large model can determine the memory size required for the data to be loaded; the sum of the memory required for all data to be loaded is the required memory amount). According to priority, gradually reduce the data to be loaded (the content to be loaded in order of priority is: buildings, trees, surrounding environment, lane-level routes, rendering materials of obstacles and people, frame rate reduction for obstacles and people, and so on). (For example, if the memory deficit is 200M, buildings are 120M, and trees are 90M, first reduce the loading of buildings; if there is still an 80M memory deficit, then reduce the loading of trees by 90M; if the required memory is sufficient, no further data loading is required).

[0065] In one implementation scenario of this embodiment, the hardware resources include GPU resources. Filtering data that meets priority conditions in the initial navigation data based on the resource difference to obtain target navigation data includes: determining the initial navigation segment to be rendered; filtering the last segment of the initial navigation segment based on the resource difference to shorten the initial navigation segment into the target navigation segment, thereby obtaining target navigation data, wherein the length of the last segment is positively correlated with the resource difference.

[0066] In one implementation scenario of this embodiment, the hardware resources include GPU resources. Filtering data in the initial navigation data that meets priority conditions based on the resource difference to obtain target navigation data includes: classifying navigation environment information in the initial navigation data to obtain multiple rendering elements, wherein the multiple rendering elements include: static obstacles, lane lines, dynamic obstacles, and element materials; determining the priority of the multiple rendering elements and calculating the element computing power resources corresponding to each of the multiple rendering elements; selecting several first rendering elements in order according to the priority, wherein the total element computing power resources of the several first rendering elements are greater than or equal to the resource difference; filtering the several first rendering elements from the multiple rendering elements, and outputting the remaining second rendering elements as target navigation data.

[0067] If the GPU is insufficient, the model will handle the rendering scene. According to priority, the processing methods include: shortening the road segment to be rendered (for example, if the current scale is to render a 500m road segment, it can be shortened to 200m, 100m, etc. depending on the GPU deficit and vehicle speed), gradually reducing the rendering elements (buildings > trees > surrounding environment > lane-level route > obstacles and people), and changing the rendering materials (for example, changing car logos to text or vector graphics, roads to lines, and buildings and trees to 2D rendering).

[0068] The solution in this embodiment runs an edge-side model on a real vehicle. This model's function is to adjust lane-level navigation rendering in real time based on vehicle driving conditions (vehicle speed, surrounding environment, steering, weather, vehicle infotainment system usage, etc.). By controlling data transmission, adjusting rendering content (such as vehicle logos, surrounding environment, buildings, and trees), and dynamically refreshing the rendering frame rate, the goal of real-time adjustment of lane-level navigation rendering performance is achieved. When lane-level navigation is activated while the vehicle is in motion, vehicle speed, vehicle heading angle, turning radius, surrounding environment, lane-level navigation frame rate, and vehicle infotainment system hardware usage are recorded in real time. This data is then used to train the model.

[0069] Figure 3 This is a flowchart of lane-level rendering based on the end-side model in this invention. The system monitors performance in real time, determines the current performance, and assesses whether the vehicle's hardware resources are sufficient. If resources are sufficient, it acquires future driving segment data, generates rendering data, and stores it locally on the vehicle. When the vehicle's end-side large model is running and lane-level navigation for the current segment needs to be rendered, if the vehicle's hardware resources are sufficient, it acquires rendering data from the cloud server to achieve lane-level navigation rendering. If the vehicle's hardware resources are insufficient, it filters based on resource (CPU, memory, GPU) differences, adjusts the data volume, reduces the amount of data loaded, reduces the amount of rendering content, and finally achieves vehicle navigation rendering.

[0070] The solution in this embodiment uses an edge-side model to adjust the generation of lane-level rendering data. Unlike existing solutions where lane-level navigation data is stored on a server, in this solution, some of the data used for lane-level rendering is generated by the edge-side model and will be adjusted according to the actual road conditions. This reduces the dependence on cloud servers and central cloud data, dynamically adjusts the use of system resources, and staggers the use of system resources.

[0071] The solution in this embodiment generates rendering data on the terminal, reducing reliance on server data and lowering hardware requirements for cloud servers. It also reduces data transmission steps and network requirements. Optimized rendering performance further reduces the demands on in-vehicle infotainment hardware.

[0072] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0073] Example 2

[0074] This embodiment also provides a vehicle navigation screen rendering device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0075] Figure 4 This is a structural block diagram of a vehicle navigation screen rendering device according to an embodiment of the present invention, such as... Figure 4 As shown, the device includes:

[0076] The first acquisition module 41 is used to acquire the initial navigation data of the vehicle in the current road segment in real time, and to acquire the remaining amount of hardware resources of the vehicle in real time, wherein the hardware resources include CPU resources, memory resources and GPU resources.

[0077] Filtering module 42 is used to filter data that meets the priority conditions in the initial navigation data according to the remaining resource amount to obtain target navigation data;

[0078] The first rendering module 43 is used to render the target navigation data based on the remaining resources to obtain the lane-level thumbnail navigation screen of the vehicle in the current road segment.

[0079] Optionally, the first acquisition module includes: a first acquisition unit, configured to acquire video frames captured by the vehicle's camera in real time, perform target detection on the video frames, and obtain navigation environment information, wherein the navigation environment information includes static obstacle information, lane lines, and dynamic obstacle information; a second acquisition unit, configured to acquire vehicle status information of the vehicle in real time, wherein the vehicle status information includes vehicle speed and vehicle body angle; and a third acquisition unit, configured to acquire screenshots of the vehicle's navigation view interface in real time, and identify first driving route data in the screenshots for the current road segment, wherein the first driving route data includes driving segment data and turn-by-turn navigation (TBT) data.

[0080] Optionally, the filtering module includes: an acquisition unit, configured to acquire the resource requirement of the initial navigation data, wherein the resource requirement is the minimum amount of resources required by the vehicle to render the initial navigation data; a calculation unit, configured to calculate the resource difference between the resource requirement and the remaining resource amount; and a filtering unit, configured to filter data in the initial navigation data that meets priority conditions based on the resource difference if the resource difference is greater than a preset threshold, to obtain target navigation data, wherein the data difference between the target navigation data and the initial navigation data is positively correlated with the resource difference.

[0081] Optionally, the hardware resources include CPU resources, and the filtering unit includes: an extraction subunit for extracting first driving route data from the initial navigation data, wherein the first driving route data includes driving segment data and TBT data; a first filtering subunit for filtering the driving segment data based on the resource difference and retrieving locally stored road segment scene data corresponding to the driving segment data for the current road segment, wherein the road segment scene data is lane-level scene data pre-rendered by the vehicle when hardware resources were sufficient in historical time; and a first output subunit for outputting the TBT data as target navigation data.

[0082] Optionally, the hardware resources include memory resources, and the filtering unit includes: a first classification subunit, used to classify the navigation environment information in the initial navigation data to obtain multiple environment elements, wherein the multiple environment elements include: static obstacles, lane lines, and dynamic obstacle materials; a second filtering subunit, used to filter the first environment element among the multiple environment elements based on the resource difference to obtain the remaining second environment elements; a processing subunit, used to maintain the current rendering frame rate and output the second environment element as target navigation data if the memory usage of the second environment element is less than the remaining memory; if the memory usage of the second environment element is greater than or equal to the remaining memory, reduce the current rendering frame rate and calculate the second memory usage after the frame reduction; secondly, determine whether the second memory usage is less than the remaining memory; and a second output subunit, used to output the second environment element after the frame reduction as target navigation data if the second memory usage is less than the remaining memory; if the second memory usage is greater than or equal to the remaining memory, filter the dynamic obstacles in the navigation environment information to obtain the target navigation data.

[0083] Optionally, the second filtering subunit is further configured to: determine the priority of the plurality of environmental elements, and calculate the element-occupied memory of the plurality of environmental elements respectively; select a plurality of first environmental elements in order according to the priority, wherein the total element-occupied memory of the plurality of first environmental elements is greater than or equal to the resource difference; filter the plurality of first environmental elements among the plurality of environmental elements to obtain the remaining second environmental elements.

[0084] Optionally, the hardware resources include GPU resources, and the filtering unit includes: a first determining subunit for determining the initial navigation segment to be rendered; and a third filtering subunit for filtering the last segment of the initial navigation segment based on the resource difference, so as to shorten the initial navigation segment into the target navigation segment and obtain target navigation data, wherein the length of the last segment is positively correlated with the resource difference.

[0085] Optionally, the hardware resources include GPU resources, and the filtering unit includes: a second classification subunit, used to classify the navigation environment information in the initial navigation data to obtain multiple rendering elements, wherein the multiple rendering elements include: static obstacles, lane lines, dynamic obstacles, and element materials; a second determination subunit, used to determine the priority of the multiple rendering elements and calculate the element computing power resources corresponding to the multiple rendering elements respectively; a selection subunit, used to select several first rendering elements in order according to the priority, wherein the total element computing power resources of the several first rendering elements are greater than or equal to the resource difference; and a fourth filtering subunit, used to filter the several first rendering elements among the multiple rendering elements and output the remaining second rendering elements as target navigation data.

[0086] Optionally, the device further includes: a second acquisition module, configured to acquire second driving route data of the vehicle in the current road segment from a cloud server if the resource difference is less than or equal to the preset threshold after the filtering module determines whether the resource difference is greater than a preset threshold, wherein the second driving route data includes driving segment data and TBT data; a construction module, configured to construct complete navigation data using the vehicle's navigation environment information, vehicle status information, and the second driving route data; and a second rendering module, configured to render the complete navigation data based on the remaining resource amount to obtain a lane-level complete navigation screen of the vehicle in the current road segment.

[0087] Optionally, the device includes: a construction module, configured to construct training samples using the first driving route data and the second driving route data after the second acquisition module obtains the second driving route data of the vehicle in the current road segment from the cloud server; and a training module, configured to train an image recognition model using the training samples, wherein the image recognition model is used to identify the driving route data of the current road segment from a screenshot of the vehicle's navigation view interface.

[0088] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0089] Example 3

[0090] Embodiments of the present invention also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0091] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0092] S1, real-time acquisition of the vehicle's initial navigation data on the current road segment, and real-time acquisition of the remaining amount of the vehicle's hardware resources, wherein the hardware resources include CPU resources, memory resources, and GPU resources;

[0093] S2, filter the data that meets the priority conditions in the initial navigation data according to the remaining resource quantity to obtain the target navigation data;

[0094] S3, Render the target navigation data based on the remaining resources to obtain the lane-level thumbnail navigation screen of the vehicle in the current road segment.

[0095] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0096] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0097] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0098] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0099] S1, real-time acquisition of the vehicle's initial navigation data on the current road segment, and real-time acquisition of the remaining amount of the vehicle's hardware resources, wherein the hardware resources include CPU resources, memory resources, and GPU resources;

[0100] S2, filter the data that meets the priority conditions in the initial navigation data according to the remaining resource quantity to obtain the target navigation data;

[0101] S3, Render the target navigation data based on the remaining resources to obtain the lane-level thumbnail navigation screen of the vehicle in the current road segment.

[0102] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0103] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, 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, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0105] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0106] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for rendering a vehicle navigation screen, characterized in that, include: The system acquires the vehicle's initial navigation data on the current road segment in real time, and also acquires the remaining amount of the vehicle's hardware resources in real time, including CPU resources, memory resources, and GPU resources. Based on the remaining resource quantity, filter the data in the initial navigation data that meets the priority conditions to obtain the target navigation data; Based on the remaining resources, the target navigation data is rendered to obtain a lane-level thumbnail navigation screen of the vehicle in the current road segment; The filtering of data meeting priority conditions in the initial navigation data based on the remaining resource amount includes: obtaining the resource requirement of the initial navigation data, wherein the resource requirement is the minimum amount of resources required for the vehicle to render the initial navigation data; calculating the resource difference between the resource requirement and the remaining resource amount; if the resource difference is greater than a preset threshold, filtering the data meeting priority conditions in the initial navigation data based on the resource difference to obtain target navigation data, wherein the data difference between the target navigation data and the initial navigation data is positively correlated with the resource difference; The hardware resources include CPU resources. Based on the resource difference, data meeting priority conditions in the initial navigation data are filtered to obtain target navigation data. This includes: extracting first driving route data from the initial navigation data, wherein the first driving route data includes driving segment data and TBT data; filtering the driving segment data based on the CPU resource difference, and retrieving locally stored road segment scene data corresponding to the driving segment data for the current road segment, wherein the road segment scene data is lane-level scene data pre-rendered by the vehicle when hardware resources were sufficient in a historical time period; and outputting the TBT data as target navigation data. The hardware resources include GPU resources. Based on the resource difference, the data in the initial navigation data that meets the priority conditions are filtered to obtain target navigation data, including: determining the initial navigation segment to be rendered; filtering the last segment of the initial navigation segment based on the resource difference of the GPU resources to shorten the initial navigation segment into the target navigation segment, thereby obtaining target navigation data, wherein the length of the last segment is positively correlated with the resource difference.

2. The method according to claim 1, characterized in that, Real-time acquisition of initial navigation data for the vehicle on the current road segment includes: The system acquires video frames captured by the vehicle's camera in real time, performs target detection on the video frames, and obtains navigation environment information, which includes static obstacle information, lane lines, and dynamic obstacle information. The vehicle status information of the vehicle is acquired in real time, including vehicle speed and vehicle body deviation angle. The system acquires screenshots of the vehicle's navigation view interface in real time and identifies the first driving route data in the current road segment within the screenshots. The first driving route data includes driving segment data and turn-by-turn navigation (TBT) data.

3. The method according to claim 1, characterized in that, The hardware resources include memory resources. Based on the resource difference, data in the initial navigation data that meets the priority conditions is filtered to obtain target navigation data, including: The navigation environment information in the initial navigation data is classified to obtain various environmental elements, including: static obstacles, lane lines, and dynamic obstacle materials. Based on the resource difference, filter the first environmental element among the multiple environmental elements to obtain the remaining second environmental element; If the memory usage of the second environment element is less than the remaining memory, maintain the current rendering frame rate and output the second environment element as target navigation data; if the memory usage of the second environment element is greater than or equal to the remaining memory, reduce the current rendering frame rate and calculate the second memory usage after the frame rate reduction. Determine whether the second memory usage is less than the remaining memory. If the second memory usage is less than the remaining memory, the second environment element after frame downsampling is output as target navigation data; if the second memory usage is greater than or equal to the remaining memory, dynamic obstacles in the navigation environment information are filtered out to obtain target navigation data.

4. The method according to claim 3, characterized in that, Based on the resource difference, the first environmental element among the multiple environmental elements is filtered to obtain the remaining second environmental elements, including: Determine the priority of the various environmental elements, and calculate the memory occupied by each of the various environmental elements; Several first environment elements are selected in order of priority, wherein the total memory occupied by the several first environment elements is greater than or equal to the resource difference; Filter the first environmental elements from the multiple environmental elements to obtain the remaining second environmental elements.

5. The method according to claim 1, characterized in that, The hardware resources include GPU resources. Based on the resource difference, data in the initial navigation data that meets priority conditions is filtered to obtain target navigation data, including: The navigation environment information in the initial navigation data is classified to obtain various rendering elements, including: static obstacles, lane lines, dynamic obstacles, and element materials. Determine the priority of the various rendering elements, and calculate the element computing resources corresponding to each of the various rendering elements; Several first rendering elements are selected in order of priority, wherein the total element computing power resources of the several first rendering elements are greater than or equal to the resource difference; Filter the first rendering elements from the multiple rendering elements, and output the remaining second rendering elements as target navigation data.

6. The method according to claim 1, characterized in that, After determining whether the resource difference is greater than a preset threshold, the method further includes: If the resource difference is less than or equal to a preset threshold, the second driving route data of the vehicle in the current road segment is obtained from the cloud server, wherein the second driving route data includes driving segment data and TBT data; Complete navigation data is constructed using the vehicle's navigation environment information, vehicle status information, and the second driving route data; Based on the remaining resources, the complete navigation data is rendered to obtain the lane-level complete navigation screen of the vehicle in the current road segment.

7. The method according to claim 6, characterized in that, After obtaining the vehicle's second driving route data for the current road segment from the cloud server, the method further includes: Training samples are constructed using the first driving route data and the second driving route data; The training samples are used to train an image recognition model, wherein the image recognition model is used to identify the driving route data of the current road segment from a screenshot of the vehicle's navigation view interface.

8. A rendering device for vehicle navigation screens, characterized in that, include: The first acquisition module is used to acquire the initial navigation data of the vehicle in the current road segment in real time, and to acquire the remaining amount of hardware resources of the vehicle in real time, wherein the hardware resources include CPU resources, memory resources and GPU resources. The filtering module is used to filter data that meets the priority conditions in the initial navigation data according to the remaining resource quantity, so as to obtain the target navigation data; The first rendering module is used to render the target navigation data based on the remaining resources to obtain the lane-level thumbnail navigation screen of the vehicle in the current road segment; The filtering module includes: an acquisition unit for acquiring the resource requirement of the initial navigation data, wherein the resource requirement is the minimum amount of resources required by the vehicle to render the initial navigation data; a calculation unit for calculating the resource difference between the resource requirement and the remaining resources; and a filtering unit for filtering data in the initial navigation data that meets priority conditions based on the resource difference if the resource difference is greater than a preset threshold, to obtain target navigation data, wherein the data difference between the target navigation data and the initial navigation data is positively correlated with the resource difference. The hardware resources include CPU resources, and the filtering unit includes: an extraction subunit for extracting first driving route data from the initial navigation data, wherein the first driving route data includes driving segment data and TBT data; a first filtering subunit for filtering the driving segment data based on the resource difference of the CPU resources, and retrieving the road segment scene data of the current road segment corresponding to the driving segment data from local storage, wherein the road segment scene data is lane-level scene data pre-rendered by the vehicle when hardware resources were sufficient in historical time; and a first output subunit for outputting the TBT data as target navigation data. The hardware resources include GPU resources, and the filtering unit includes: a first determining subunit for determining the initial navigation segment to be rendered; and a third filtering subunit for filtering the last segment of the initial navigation segment based on the resource difference of the GPU resources, so as to shorten the initial navigation segment into the target navigation segment and obtain target navigation data, wherein the length of the last segment is positively correlated with the resource difference.

9. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method described in any one of claims 1 to 7 when it is run.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method as described in any one of claims 1 to 7.

Images