A cloud vehicle image quality dynamic adjustment method and device, a data transmission method and a computer program product

Abstract

The application discloses a cloud vehicle machine picture quality dynamic adjustment method and device, a data transmission method and a computer program product, wherein the method comprises the following steps: acquiring vehicle state information, network state information and cloud vehicle machine picture quality parameters during the use of the cloud vehicle machine; processing the acquired data, constructing and periodically updating a picture quality map; the picture quality map comprises a plurality of driving areas, each driving area is associated with adaptive cloud vehicle machine picture quality parameters under a corresponding network state; according to the real-time geographic position of a target vehicle, adaptive cloud vehicle machine picture quality parameters of a driving area where the target vehicle is currently located are matched in the picture quality map, and the cloud vehicle machine picture quality is adjusted according to the adaptive cloud vehicle machine picture quality parameters. Through the construction of the dynamically updated picture quality map, the cloud vehicle machine can dynamically adjust the picture quality parameters according to the current geographic area, so that a smooth interactive experience can be provided at any time and in any place, the driving experience of the user is improved, and the utilization of network resources is optimized.

Description

Technical Field

[0001] This invention relates to the field of intelligent connected vehicle technology, specifically to a method, device, data transmission method, and computer program product for dynamic adjustment of image quality in a cloud-based vehicle system. Background Technology

[0002] As the number and complexity of in-vehicle infotainment applications increase, the computing power and storage space of in-vehicle chips become limited, leading to system lag. Cloud-based in-vehicle infotainment technology adopts a cloud computing, local interaction model, transferring the operation of the in-vehicle infotainment system to the cloud platform. The vehicle only runs the client, reducing local computing power requirements and improving the user experience.

[0003] The cloud-based vehicle infotainment system (V2X) solution is similar to cloud desktops / cloud phones. In the cloud, hardware virtualization technology enables time-sharing resource reuse and elastic scaling, while encoding and compression technology transmits the system interface to the terminal. The terminal installs a client application to enable functions such as account login, instance creation, audio and video display, and control command uploading.

[0004] However, since cloud-based vehicle navigation systems perform computations in the cloud, audio and video must be transmitted to the client via the network, making network quality crucial for user experience. To optimize transmission efficiency, technologies such as content analysis, variable frame rate, encoding compression, and image quality selection have been proposed. Image quality selection can be adjusted automatically or manually on the client side based on network conditions. However, cloud-based vehicle navigation terminals are in a high-frequency, mobile state, and network conditions are prone to fluctuations. Manually adjusting image quality may distract the user and increase driving risks; automatic adjustment may be delayed due to speed measurement and adjustment logic latency, resulting in untimely image quality adjustments. Summary of the Invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a method, device, data transmission method and computer program product for dynamic adjustment of cloud vehicle-mounted camera image quality, so as to realize intelligent and real-time adjustment of cloud vehicle-mounted camera image quality while ensuring driving safety.

[0006] To address the aforementioned technical problems, this invention provides a method for dynamically adjusting the image quality of a cloud-based vehicle navigation system, comprising the following steps:

[0007] Obtain vehicle status information, network status information, and cloud vehicle system image quality parameters during the use of the cloud vehicle system;

[0008] The acquired data is processed to construct and periodically update the image quality map; the image quality map includes multiple driving areas, and each driving area is associated with the corresponding cloud vehicle system image quality parameters under the network state.

[0009] Based on the real-time geographical location of the target vehicle, the cloud vehicle-mounted system image quality parameters of the target vehicle's current driving area are matched in the image quality map, and the cloud vehicle-mounted system image quality is adjusted according to the adapted cloud vehicle-mounted system image quality parameters.

[0010] Preferably, the step of processing the acquired data to construct a high-quality map specifically includes:

[0011] An outlier detection algorithm is used to remove outliers from the acquired data.

[0012] The acquired data is dynamically weighted using an attention mechanism, where the weight coefficient of newly acquired data is higher than that of historical data.

[0013] Based on the network status information of each operator in each driving area, clustering algorithms or neural network analysis are used to obtain the image quality parameters of the adapted cloud vehicle-mounted system for each operator in each driving area. Driving areas with similar network status and adapted cloud vehicle-mounted system image quality parameters are merged into one to construct the image quality map.

[0014] Preferably, the periodic updating of the image quality map specifically includes:

[0015] Obtain the latest network status information and corresponding timestamps uploaded by multiple vehicles within the target area;

[0016] The dynamic weight values ​​of each network status information are determined based on operator type, time period division, and base station update status.

[0017] Based on the dynamic weight values, the network status information is weighted and fused to generate updated adaptive cloud vehicle-machine image quality parameters.

[0018] Preferably, the method further includes:

[0019] Obtain navigation route information for the target vehicle;

[0020] Based on the navigation route information, predict the driving area that the vehicle will enter in the near future;

[0021] The corresponding cloud vehicle system image quality parameters for the driving area to be entered are loaded into the cache queue to achieve seamless switching of cloud vehicle system image quality parameters.

[0022] Preferably, when adjusting the image quality parameters according to the adapted cloud vehicle system, the method further includes:

[0023] Compare the network status information predicted by the cloud with the network status information measured by the cloud vehicle terminal client;

[0024] When a discrepancy occurs between the two, the network status information measured by the cloud vehicle terminal client is used to regenerate the image quality parameters adapted to the cloud vehicle terminal and perform image quality adjustment.

[0025] Preferably, when adjusting the image quality parameters according to the adapted cloud vehicle system, the method further includes:

[0026] Real-time monitoring of the number of concurrent vehicles using cloud vehicle services within the same driving area or the coverage area of ​​the same communication base station;

[0027] When the number of concurrent vehicles exceeds a preset threshold, a cloud vehicle-to-vehicle image quality parameter downgrade operation is uniformly performed on all currently connected vehicles; wherein the image quality parameter downgrade includes a simultaneous reduction in resolution and bitrate.

[0028] Preferably, the method further includes:

[0029] Real-time network status information is encapsulated into system-level signals and broadcast to the cloud-based vehicle application;

[0030] Triggering video-based cloud-based vehicle infotainment applications to perform image quality adaptive operations includes at least one of the following:

[0031] Match the upper limit of video source resolution based on the current network status;

[0032] Dynamically disable high bitrate effects rendering;

[0033] Enable video buffer preloading mechanism.

[0034] The present invention also provides a cloud-based vehicle-mounted system image quality dynamic adjustment device, comprising:

[0035] The acquisition module is used to acquire vehicle status information, network status information, and cloud vehicle system image quality parameters during the use of the cloud vehicle system.

[0036] The construction module is used to process the acquired data, build and periodically update the image quality map; the image quality map includes multiple driving areas, and each driving area is associated with the corresponding cloud vehicle system image quality parameters under the network state;

[0037] The adjustment module is used to match the image quality parameters of the cloud vehicle system to the image quality map of the target vehicle's current driving area based on the target vehicle's real-time geographical location, and to adjust the image quality of the cloud vehicle system according to the image quality parameters.

[0038] The present invention also provides a cloud-based vehicle-mounted system image quality dynamic adjustment device, comprising:

[0039] One or more processors;

[0040] Memory;

[0041] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the cloud vehicle-mounted image quality dynamic adjustment method.

[0042] The present invention also provides a computer program product, including computer instructions that instruct a computer device to perform an operation corresponding to the method.

[0043] The present invention also provides a data transmission method, comprising:

[0044] The vehicle terminal obtains vehicle status information, network status information, and cloud vehicle terminal image quality parameters during the use of the cloud vehicle terminal;

[0045] When a change in the vehicle's geographical location is detected to exceed a set threshold, the vehicle will upload the vehicle status information, network status information, and cloud vehicle-mounted image quality parameters to the cloud server.

[0046] The vehicle status information, network status information, and cloud vehicle-to-vehicle image quality parameters are used to construct and periodically update an image quality map containing multiple driving areas. Each driving area is associated with the corresponding cloud vehicle-to-vehicle image quality parameters under the network status.

[0047] Implementing this invention offers the following advantages: By constructing a dynamically updated multi-dimensional image quality map, the cloud-based vehicle system can dynamically adjust image quality parameters based on the current geographical location and operator information, thereby providing a smooth interactive experience at any time and place. This not only enhances the user's driving experience but also optimizes network resource utilization and reduces communication burden caused by image quality mismatch. Simultaneously, through real-time geographical location matching and navigation path prediction mechanisms, dynamic switching of image quality parameters is achieved, ensuring seamless image quality degradation / recovery when the vehicle enters areas with network fluctuations. Combined with a base station-level concurrent connection monitoring mechanism, the system intelligently adjusts regional image quality levels during peak hours, comprehensively guaranteeing a continuous and high-quality in-vehicle service experience in complex mobile scenarios. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a method for dynamically adjusting the image quality of a cloud-based vehicle system according to an embodiment of the present invention. Detailed Implementation

[0050] The following description of the embodiments is taken with reference to the accompanying drawings, which illustrate specific embodiments in which the invention can be implemented.

[0051] Please refer to Figure 1 As shown, Embodiment 1 of the present invention provides a method for dynamically adjusting the image quality of a cloud-based vehicle navigation system, comprising the following steps:

[0052] Obtain vehicle status information, network status information, and cloud vehicle system image quality parameters during the use of the cloud vehicle system;

[0053] The acquired vehicle status information, network status information, and cloud vehicle-mounted system image quality parameters are processed to construct and periodically update an image quality map. The image quality map includes multiple driving areas, and each driving area is associated with the corresponding cloud vehicle-mounted system image quality parameters under the network status.

[0054] Based on the real-time geographical location of the target vehicle, the cloud vehicle-mounted system image quality parameters of the target vehicle's current driving area are matched in the image quality map, and the cloud vehicle-mounted system image quality is adjusted according to the adapted cloud vehicle-mounted system image quality parameters.

[0055] As demonstrated by the above steps, this invention enables the cloud-based vehicle navigation system to quickly match and obtain suitable image quality parameters from the image quality map based on the real-time geographical location of the target vehicle. This allows for dynamic adjustment of the cloud-based vehicle navigation system's image quality, improving its adaptability to different network environments and geographical areas, while also ensuring smooth interaction and a superior user experience. Furthermore, periodically updating the image quality map promptly reflects changes in the network environment and driving area, making image quality adjustments more accurate and efficient, further enhancing the system's intelligence and user satisfaction.

[0056] Specifically, in this embodiment of the invention, vehicle status information includes the vehicle's latitude, longitude, altitude, speed, etc.; network status information includes signal strength, carrier, two-way latency, etc.; and cloud-based vehicle-device image quality parameters include resolution, bitrate, etc. The methods for collecting each piece of information include:

[0057] The vehicle's geographical location (including latitude, longitude, and altitude) and driving speed are continuously collected through onboard sensors.

[0058] Network status parameters are obtained through the vehicle communication module, including the currently connected operator information, 4G / 5G signal strength, and uplink / downlink network latency;

[0059] The cloud-based vehicle-to-everything (V2X) system synchronously records the current image quality parameters, including video stream resolution (e.g., 1080P, 720P) and video bitrate (e.g., 2Mbps, 5Mbps), and uploads this data to a cloud server. The cloud server stores and manages this data for subsequent analysis and processing. The preceding vehicle can also periodically record and upload this data so that following vehicles can refer to its experience. Preferably, data upload is triggered when the vehicle's geographical location changes beyond a set threshold (e.g., moving 50 meters), reducing redundant data transmission.

[0060] Next, based on online maps, we first mine the network conditions of different driving areas and the image quality parameters that allow for smooth interaction between the cloud-based vehicle navigation system and the system. These parameters are then stored in a database as the foundation for image quality map construction. For example, in urban areas, most open roads and open-air parking lots have good network conditions, allowing for smooth interaction with the cloud-based vehicle navigation system at 1080P resolution. Some underground parking lots or tunnels have been equipped with 4G / 5G base stations, allowing for smooth interaction with the cloud-based vehicle navigation system at 1080P or 720P resolution. However, on cross-sea bridges or in parking garages, due to the distance between adjacent communication base stations or the large number of communication devices inside, the cloud-based vehicle navigation system needs to use 540P or 360P resolution to ensure smooth interaction.

[0061] Since multiple vehicles may use cloud-based vehicle systems in the same area, and different vehicles use different operators, the pedestrian traffic in the area varies at different times of the day. Operators continuously update and build new base stations, so it is necessary to further process the original network strength and smooth operation resolution to form a periodically updated image quality map that can ensure the smooth operation of the cloud-based vehicle system, and ensure the accuracy and timeliness of the image quality map.

[0062] Specifically, the steps to create this high-quality map include:

[0063] (1) Use outlier detection algorithms (such as FastABOD, AutoEncoder) to remove outliers.

[0064] During data acquisition, some abnormal data may be present due to equipment malfunctions, network anomalies, or other reasons. If this abnormal data is not processed, it may affect the accuracy and reliability of the image map. Outlier detection algorithms can identify and remove this abnormal data, ensuring that the image map is built based on accurate and reliable data.

[0065] (2) The attention mechanism algorithm is used to give higher weight to newly acquired time series data.

[0066] In the process of constructing image quality maps, newly acquired time-series data (i.e., the aforementioned vehicle status information, network status information, and cloud-vehicle system image quality parameters) often contain the latest network conditions and image quality requirements, which are of great significance for reflecting the current network environment and image quality status. Through attention mechanism algorithms, newly acquired data can receive more attention during the image quality map construction process, thereby improving the timeliness and accuracy of the image quality map.

[0067] (3) Use clustering algorithms (such as DBSCAN, GMMs) or neural networks (such as RNN) to obtain the smooth interaction resolution of cloud vehicle-to-vehicle systems from multiple operators in different driving areas.

[0068] In different driving areas, due to differences in factors such as network coverage, base station distribution, and user density, the network conditions and image quality performance of different operators may vary. By using clustering algorithms or neural networks, image quality data from different operators in different driving areas can be analyzed and processed to obtain the smooth interactive resolution of each operator in that area, providing support for the construction of image quality maps. In other words, based on factors such as geographical location, road type, building density, and pedestrian traffic, similar network conditions and image quality requirements can be grouped into the same driving area to collectively construct an image quality map, thus more accurately reflecting the network conditions and image quality requirements of different driving areas.

[0069] As an example, the image quality parameters of the adapted cloud vehicle system associated with each driving area under the corresponding network condition are as follows:

[0070] Urban open road sub-area: When the network signal strength is ≥-80dBm, it is compatible with 1080P resolution + 5Mbps bitrate;

[0071] Underground parking lot sub-area: When the signal strength is -90dBm to -80dBm, it is compatible with 720P resolution + 3Mbps bitrate;

[0072] Sub-area of ​​the cross-sea bridge: When the signal strength is <-90dBm, it is compatible with 540P resolution + 1.5Mbps bitrate.

[0073] Furthermore, the periodic updates to the image quality map specifically include:

[0074] Obtain the latest network status information and corresponding timestamps uploaded by multiple vehicles within the target area;

[0075] The dynamic weight values ​​of each network status information are determined based on operator type, time period division, and base station update status.

[0076] Based on the dynamic weight values, the network status information is weighted and fused to generate updated adaptive cloud vehicle-machine image quality parameters.

[0077] For example, when a commercial area experiences network congestion during the evening rush hour (time period division) due to the gathering of vehicles from multiple operators (China Mobile / China Telecom), and it is detected that a base station has been expanded in the last 2 hours (base station update status), the cloud automatically increases the weight of real-time data and recalculates that the appropriate image quality parameters for the area during the evening rush hour should be downgraded from 1080P to 720P. The image quality map can then be refreshed through the above update mechanism.

[0078] Once the image quality map is built, the cloud-based vehicle navigation system can dynamically adjust its image quality parameters during use to ensure smooth interaction and improve user experience. As mentioned earlier, the cloud-based vehicle navigation client continuously uploads vehicle status information, network status information, and image quality parameters to the cloud during use. After receiving the information uploaded by the client, the cloud uses this information to find image quality parameters suitable for the current network status and vehicle location within the image quality map.

[0079] After finding suitable image quality parameters in the cloud, the resolution and bitrate of the cloud vehicle-mounted infotainment client are automatically adjusted to an appropriate level. In this way, when the network conditions are poor, reducing the resolution and bitrate can ensure the smoothness of cloud vehicle-mounted infotainment interaction; when the network conditions are good, it can improve the visual effect and user experience of cloud vehicle-mounted infotainment.

[0080] The cloud-based vehicle navigation client can also upload the area the vehicle will be arriving at in the next 10 seconds to the cloud in advance, based on the vehicle's navigation route. The cloud can then know the area the vehicle is about to enter and prepare the corresponding image quality parameters. Based on the information uploaded by the client, the cloud can pre-load the corresponding image quality parameters for the cloud-based vehicle navigation system into a cache queue, allowing for a seamless switch of the system's resolution to suit the new area. This pre-switching further improves the smoothness of the cloud-based vehicle navigation system's interaction and the visual user experience, because the image quality is already adjusted when the vehicle enters a new area, eliminating the need for a waiting adjustment process.

[0081] As a further improvement to this invention, a vehicle-side network status assessment priority mechanism is also established. Since the cloud-based vehicle terminal client continuously collects network status information during the use of the cloud-based vehicle terminal, while the cloud predicts network status based on historical data, there may be discrepancies between the two. In the event of such discrepancies, this invention regenerates and adjusts the image quality parameters adapted to the cloud-based vehicle terminal using the network status information collected by the cloud-based vehicle terminal client, as this more directly reflects the current network environment of the vehicle, thus ensuring that decisions such as image quality adjustments are based on the most accurate information.

[0082] Meanwhile, this embodiment of the invention also includes a mechanism for adjusting image quality based on the number of vehicles using the cloud-based vehicle-to-everything (V2X) system. Specifically, when the number of vehicles using the cloud-based V2X system within a certain driving area is large, the network may become congested. In this case, the cloud system uniformly performs a downgrade operation on the image quality parameters of all currently connected vehicles, simultaneously reducing the resolution and bitrate to ensure that all vehicles can obtain a relatively smooth service experience. For example, within a certain driving area, up to 10 vehicles using the cloud-based V2X system are allowed 1080P, while more than 20 vehicles are forcibly downgraded to 720P. This image quality adjustment based on the number of vehicles helps balance network load and improve overall service efficiency. When the number of concurrent vehicles exceeds a preset threshold,

[0083] Furthermore, in this embodiment of the invention, the real-time network status can be transmitted as a system-level signal to applications running on the cloud-based vehicle system, such as video applications. During operation, if the network status is poor and the video content resolution is too high, playback may be choppy or delayed. By receiving the network status signal, the video application can adjust to appropriate image quality and animation effects in advance, avoiding the playback of high-resolution content when the cloud-based vehicle system is running at low resolution, thereby ensuring smooth video playback and a good user experience. For example, if the current network status corresponds to image quality parameters of 540P resolution and 1.5Mbps bitrate, the video application will proactively switch to matching image quality, loading only 540P video sources and disabling high-definition animation effects. Therefore, in this embodiment of the invention, the video-based cloud-based vehicle system application can be triggered to perform image quality adaptive operations, including at least one of the following: matching the upper limit of the video source resolution according to the current network status; dynamically disabling high-bitrate special effects rendering; and enabling a video buffer preloading mechanism.

[0084] Corresponding to the cloud-to-vehicle camera image quality dynamic adjustment method described in Embodiment 1 of the present invention, Embodiment 2 of the present invention also provides a cloud-to-vehicle camera image quality dynamic adjustment device, comprising:

[0085] The acquisition module is used to acquire vehicle status information, network status information, and cloud vehicle system image quality parameters during the use of the cloud vehicle system.

[0086] The construction module is used to process the acquired data, build and periodically update the image quality map; the image quality map includes multiple driving areas, and each driving area is associated with the corresponding cloud vehicle system image quality parameters under the network state;

[0087] The adjustment module is used to match the image quality parameters of the cloud vehicle system to the image quality map of the target vehicle's current driving area based on the target vehicle's real-time geographical location, and to adjust the image quality of the cloud vehicle system according to the image quality parameters.

[0088] Corresponding to the cloud-to-vehicle camera image quality dynamic adjustment method described in Embodiment 1 of the present invention, Embodiment 3 of the present invention also provides a cloud-to-vehicle camera image quality dynamic adjustment device, comprising:

[0089] One or more processors;

[0090] Memory;

[0091] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the cloud vehicle image quality dynamic adjustment method described in Embodiment 1 of the present invention.

[0092] Corresponding to the cloud-to-vehicle image quality dynamic adjustment method described in Embodiment 1 of the present invention, Embodiment 4 of the present invention also provides a computer program product, including computer instructions, which instruct a computer device to perform the operation corresponding to the cloud-to-vehicle image quality dynamic adjustment method described in Embodiment 1 of the present invention.

[0093] Preferably, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor. The processor is the control center of the device, connecting various parts of the device through various interfaces and lines.

[0094] The memory mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., while the data storage area can store related data, etc. Furthermore, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard drive, a SmartMedia Card (SMC), a Secure Digital (SD) card, and a Flash Card, or other volatile solid-state storage devices.

[0095] It should be noted that the above-mentioned devices may include, but are not limited to, processors and memory, as will be understood by those skilled in the art.

[0096] Corresponding to the cloud-to-vehicle image quality dynamic adjustment method described in Embodiment 1 of the present invention, Embodiment 5 of the present invention also provides a data transmission method, including:

[0097] The vehicle terminal obtains vehicle status information, network status information, and cloud vehicle terminal image quality parameters during the use of the cloud vehicle terminal;

[0098] When a change in the vehicle's geographical location is detected to exceed a set threshold, the vehicle will upload the vehicle status information, network status information, and cloud vehicle-mounted image quality parameters to the cloud server.

[0099] The vehicle status information, network status information, and cloud vehicle-to-vehicle image quality parameters are used to construct and periodically update an image quality map containing multiple driving areas. Each driving area is associated with the corresponding cloud vehicle-to-vehicle image quality parameters under the network status.

[0100] The data transmission method in this embodiment specifically includes two stages: vehicle-side data acquisition and intelligent uploading. During the data acquisition stage, the vehicle continuously collects its geographical location (including latitude, longitude, and altitude) and speed using onboard sensors; it also monitors 4G / 5G signal strength and bidirectional network latency in real time via the onboard communication module; the cloud-based vehicle system synchronously records the current image quality parameters, including video stream resolution (e.g., 1080P, 720P) and video bitrate (e.g., 2Mbps, 5Mbps), and aligns these with the vehicle status and network parameters using timestamps. The intelligent uploading mechanism uses a set threshold; when the vehicle's geographical location changes beyond the set threshold (e.g., moving 50 meters), data uploading is triggered, reducing redundant data transmission.

[0101] As mentioned earlier, vehicle status information, network status information, and cloud-based vehicle-to-everything (V2X) image quality parameters will be used to construct and periodically update an image quality map containing multiple driving areas. Each driving area is associated with the corresponding cloud-based V2X image quality parameters under the corresponding network status. For example, an outlier detection algorithm is used to remove outliers from the acquired data; an attention mechanism is used to assign dynamic weights to the acquired data, where the weight coefficient of newly acquired data is higher than that of historical data; based on the network status information of each operator in each driving area, clustering algorithms or neural network analysis are used to obtain the corresponding cloud-based V2X image quality parameters for each operator in each driving area, and driving areas with similar network status and corresponding cloud-based V2X image quality parameters are merged into one to construct the image quality map.

[0102] For the working principle and process of the above embodiments, please refer to the description of Embodiment 1 of the present invention, which will not be repeated here.

[0103] As explained above, compared with existing technologies, the beneficial effects of this invention are as follows: By constructing a dynamically updated multi-dimensional image quality map, the cloud-based vehicle system can dynamically adjust image quality parameters based on the current geographical location and operator information, thereby providing a smooth interactive experience at any time and place. This not only improves the user's driving experience but also optimizes the utilization of network resources and reduces the communication burden caused by image quality mismatch. Simultaneously, through real-time geographical location matching and navigation path prediction mechanisms, dynamic switching of image quality parameters is achieved, ensuring seamless image quality degradation / recovery when the vehicle enters areas with network fluctuations. Combined with a base station-level concurrent connection monitoring mechanism, the regional image quality level is intelligently adjusted during peak hours, comprehensively guaranteeing a continuous and high-quality in-vehicle service experience in complex mobile scenarios.

[0104] The above description is merely a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. Therefore, any equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for dynamically adjusting the image quality of a cloud-based vehicle navigation system, characterized in that, Includes the following steps: Obtain vehicle status information, network status information, and cloud vehicle system image quality parameters during the use of the cloud vehicle system; The acquired data is processed to construct and periodically update the image quality map; the image quality map includes multiple driving areas, and each driving area is associated with the corresponding cloud vehicle system image quality parameters under the network state. Based on the real-time geographical location of the target vehicle, the cloud vehicle-mounted system image quality parameters of the target vehicle's current driving area are matched in the image quality map, and the cloud vehicle-mounted system image quality is adjusted according to the adapted cloud vehicle-mounted system image quality parameters.

2. The method according to claim 1, characterized in that, The process of processing the acquired data to construct a high-quality map specifically includes: An outlier detection algorithm is used to remove outliers from the acquired data. The acquired data is dynamically weighted using an attention mechanism, where the weight coefficient of newly acquired data is higher than that of historical data. Based on the network status information of each operator in each driving area, clustering algorithms or neural network analysis are used to obtain the image quality parameters of the adapted cloud vehicle-mounted system for each operator in each driving area. Driving areas with similar network status and adapted cloud vehicle-mounted system image quality parameters are merged into one to construct the image quality map.

3. The method according to claim 2, characterized in that, The periodic map quality updates specifically include: Obtain the latest network status information and corresponding timestamps uploaded by multiple vehicles within the target area; The dynamic weight values ​​of each network status information are determined based on operator type, time period division, and base station update status. Based on the dynamic weight values, the network status information is weighted and fused to generate updated adaptive cloud vehicle-machine image quality parameters.

4. The method according to claim 1, characterized in that, Also includes: Obtain navigation route information for the target vehicle; Based on the navigation route information, predict the driving area that the vehicle will enter in the near future; The corresponding cloud vehicle system image quality parameters for the driving area to be entered are loaded into the cache queue to achieve seamless switching of cloud vehicle system image quality parameters.

5. The method according to claim 1, characterized in that, When adjusting the image quality parameters according to the adapted cloud vehicle system, the following is also included: Compare the network status information predicted by the cloud with the network status information measured by the cloud vehicle terminal client; When a discrepancy occurs between the two, the network status information measured by the cloud vehicle terminal client is used to regenerate the image quality parameters adapted to the cloud vehicle terminal and perform image quality adjustment.

6. The method according to claim 1, characterized in that, When adjusting the image quality parameters according to the adapted cloud vehicle system, the following is also included: Real-time monitoring of the number of concurrent vehicles using cloud vehicle services within the same driving area or the coverage area of ​​the same communication base station; When the number of concurrent vehicles exceeds a preset threshold, a cloud vehicle-to-vehicle image quality parameter downgrade operation is uniformly performed on all currently connected vehicles; wherein the image quality parameter downgrade includes a simultaneous reduction in resolution and bitrate.

7. The method according to claim 1, characterized in that, Also includes: Real-time network status information is encapsulated into system-level signals and broadcast to the cloud-based vehicle application; Triggering video-based cloud-based vehicle infotainment applications to perform image quality adaptive operations includes at least one of the following: Match the upper limit of video source resolution based on the current network status; Dynamically disable high bitrate effects rendering; Enable video buffer preloading mechanism.

8. A cloud-based vehicle-mounted camera image quality dynamic adjustment device, characterized in that, include: The acquisition module is used to acquire vehicle status information, network status information, and cloud vehicle system image quality parameters during the use of the cloud vehicle system. The construction module is used to process the acquired data, build and periodically update the image quality map; the image quality map includes multiple driving areas, and each driving area is associated with the corresponding cloud vehicle system image quality parameters under the network state; The adjustment module is used to match the image quality parameters of the cloud vehicle system to the image quality map of the target vehicle's current driving area based on the target vehicle's real-time geographical location, and to adjust the image quality of the cloud vehicle system according to the image quality parameters.

9. A cloud-based vehicle-mounted camera image quality dynamic adjustment device, characterized in that, include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the cloud vehicle-mounted image quality dynamic adjustment method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, It includes computer instructions that instruct a computer device to perform the operation corresponding to the cloud vehicle image quality dynamic adjustment method as described in any one of claims 1 to 7.

11. A data transmission method, characterized in that, include: The vehicle terminal obtains vehicle status information, network status information, and cloud vehicle terminal image quality parameters during the use of the cloud vehicle terminal; When a change in the vehicle's geographical location is detected to exceed a set threshold, the vehicle will upload the vehicle status information, network status information, and cloud vehicle-mounted image quality parameters to the cloud server. The vehicle status information, network status information, and cloud vehicle-to-vehicle image quality parameters are used to construct and periodically update an image quality map containing multiple driving areas. Each driving area is associated with the corresponding cloud vehicle-to-vehicle image quality parameters under the network status.

Images