Vehicle-mounted system remote rendering and control method and system based on cloud computing power reconstruction

Abstract

The application discloses a kind of based on cloud computing power reconstruction's vehicle-mounted system remote rendering and control method and system, the method includes: obtaining the request instruction input by vehicle user through vehicle equipment;According to instruction analysis rule and the request instruction, determine the corresponding multiple associated rendering tasks;According to the task parameter of the associated rendering task, predict the rendering load corresponding to the request instruction;When the rendering load exceeds the vehicle computing power load corresponding to the vehicle equipment, the request instruction is forwarded to cloud device for execution;The cloud device executes the request instruction and returns the execution rendering result to the vehicle equipment for display.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for remote rendering and control of an in-vehicle system based on cloud computing power reconstruction. Background Technology

[0002] With the rapid growth of smart cockpit applications, automotive companies and users are increasingly emphasizing the real-time responsiveness and stability of in-vehicle rendering tasks. A key technical challenge is how to dynamically schedule rendering to avoid rendering stuttering or failures. Existing technologies typically obtain user-input requests, use simple keyword matching or fixed parsing rules to determine rendering tasks, and process the results either directly based on local computing power or through static cloud forwarding to meet basic rendering needs. However, existing solutions lack in-depth analysis of command parsing rules, load prediction for multiple related rendering tasks, and intelligent forwarding and feedback mechanisms when the load exceeds thresholds. This makes it difficult to achieve dynamic load sharing and scheduling between local and cloud environments. Commonly used static or coarse-grained allocation strategies cannot adapt to real-time changes in vehicle computing power, resulting in insufficient rendering response and stability. Insufficient vehicle computing power can easily lead to rendering stuttering or failures, limiting the real-time performance, reliability, and user experience of in-vehicle rendering tasks. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for remote rendering and control of vehicle system based on cloud computing power reconstruction, which can realize dynamic rendering scheduling with intelligent sharing between local and cloud, improve the real-time response and stability of rendering tasks, and reduce the risk of rendering lag or failure due to insufficient vehicle computing power.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction, the method comprising: Obtain the request commands input by the vehicle user through the vehicle's equipment; Based on the instruction parsing rules and the request instruction, determine the corresponding multiple associated rendering tasks; Based on the task parameters of the associated rendering task, predict the rendering load corresponding to the request instruction; When the rendering load exceeds the vehicle's computing power load corresponding to the vehicle device, the request instruction is forwarded to the cloud device for execution; the cloud device executes the request instruction and sends the execution rendering result back to the vehicle device for display.

[0005] As an optional implementation, in a first aspect of the invention, the request instruction includes at least one of touch screen operation, text data, gesture visual data, gesture light reflection data, and voice data.

[0006] As an optional implementation, in the first aspect of the present invention, determining the corresponding multiple associated rendering tasks according to the instruction parsing rules and the request instruction includes: The request instruction is input into the trained type classifier model to obtain the output instruction data type; The parsing model corresponding to the instruction data type is determined from multiple candidate instruction parsing models; The request instruction is input into the parsing model to obtain the output instruction structured data; Based on the structured data of the instructions, multiple associated rendering tasks are determined.

[0007] As an optional implementation, in the first aspect of the present invention, determining the corresponding plurality of associated rendering tasks based on the instruction structured data includes: Each structured data point of the instruction structured data is input into the trained rendering-related prediction model to obtain the corresponding rendering relevance; the rendering-related prediction model is trained using a training dataset that includes multiple training instruction structured data points and corresponding rendering task relevance labels. The structural data with rendering relevance greater than a preset relevance threshold are filtered out to obtain multiple related structural data. For each historical rendering task record, calculate the average data similarity between the task instruction data and each of the related structural data in the historical rendering task record to obtain the record association degree corresponding to the historical rendering task record. The rendering tasks corresponding to all historical rendering task records whose correlation degree is greater than a preset correlation degree threshold are identified as associated rendering tasks.

[0008] As an optional implementation, in the first aspect of the present invention, predicting the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task includes: For each associated rendering task, determine the multiple historical execution rendering devices corresponding to the associated rendering task; Send a load survey request to each of the historical execution rendering devices to obtain the corresponding execution load; Calculate the weighted average of the execution loads of all the historical execution rendering devices to obtain the task load corresponding to the associated rendering task; wherein, the calculation weight of each execution load is proportional to the instruction similarity between the corresponding execution instruction and the request instruction; Based on the task load corresponding to all the associated rendering tasks, predict the rendering load corresponding to the request instruction.

[0009] As an optional implementation, in the first aspect of the present invention, predicting the rendering load corresponding to the request instruction based on the task load corresponding to all the associated rendering tasks includes: The task parameters corresponding to all the associated rendering tasks are input into the trained execution order prediction model to obtain the output task execution order; the execution order prediction model is trained using a training dataset that includes multiple sets of training rendering tasks and corresponding execution order annotations. Based on the task execution order, at least one set of parallel tasks is determined; the set of parallel tasks consists of at least two of the associated rendering tasks that are executed simultaneously. Calculate the average load of all tasks corresponding to each set of parallel tasks to obtain the set load; The rendering load corresponding to the request instruction is obtained by calculating the weighted sum of the loads of all the sets and the loads of all the associated rendering tasks that are not in the set of parallel tasks.

[0010] As an optional implementation, in the first aspect of the present invention, the task execution order includes a plurality of sequentially ordered task information; the task information is a single associated rendering task or a set of parallel tasks composed of a plurality of associated rendering tasks; the calculation weight corresponding to each set load or task load in the load weighted sum is proportional to the degree of priority of the corresponding task information in the task execution order.

[0011] As an optional implementation, in the first aspect of the present invention, forwarding the request instruction to a cloud device for execution includes: The request command and the device parameters of the vehicle equipment are forwarded to the cloud device; the cloud device is used to perform the following steps: A virtual rendering sandbox with the same rendering environment as the vehicle equipment is generated based on the device parameters; The request command is executed based on the virtual rendering sandbox to obtain the rendering result.

[0012] A second aspect of this invention discloses a remote rendering and control system for an in-vehicle system based on cloud computing power reconstruction, the system comprising: The acquisition module is used to acquire request commands input by vehicle users through vehicle devices; The determination module is used to determine multiple associated rendering tasks based on the instruction parsing rules and the request instruction. The prediction module is used to predict the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task. The forwarding module is used to forward the request instruction to the cloud device for execution when the rendering load exceeds the vehicle computing power load corresponding to the vehicle device; the cloud device executes the request instruction and sends the execution rendering result back to the vehicle device for display.

[0013] As an optional implementation, in a second aspect of the invention, the request instruction includes at least one of touch screen operation, text data, gesture visual data, gesture light reflection data, and voice data.

[0014] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method of the corresponding multiple associated rendering tasks according to the instruction parsing rules and the request instruction, including: The request instruction is input into the trained type classifier model to obtain the output instruction data type; The parsing model corresponding to the instruction data type is determined from multiple candidate instruction parsing models; The request instruction is input into the parsing model to obtain the output instruction structured data; Based on the structured data of the instructions, multiple associated rendering tasks are determined.

[0015] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method of the corresponding multiple associated rendering tasks based on the instruction structured data, including: Each structured data point of the instruction structured data is input into the trained rendering-related prediction model to obtain the corresponding rendering relevance; the rendering-related prediction model is trained using a training dataset that includes multiple training instruction structured data points and corresponding rendering task relevance labels. The structural data with rendering relevance greater than a preset relevance threshold are filtered out to obtain multiple related structural data. For each historical rendering task record, calculate the average data similarity between the task instruction data and each of the related structural data in the historical rendering task record to obtain the record association degree corresponding to the historical rendering task record. The rendering tasks corresponding to all historical rendering task records whose correlation degree is greater than a preset correlation degree threshold are identified as associated rendering tasks.

[0016] As an optional implementation, in a second aspect of the invention, the specific method by which the prediction module predicts the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task includes: For each associated rendering task, determine the multiple historical execution rendering devices corresponding to the associated rendering task; Send a load survey request to each of the historical execution rendering devices to obtain the corresponding execution load; Calculate the weighted average of the execution loads of all the historical execution rendering devices to obtain the task load corresponding to the associated rendering task; wherein, the calculation weight of each execution load is proportional to the instruction similarity between the corresponding execution instruction and the request instruction; Based on the task load corresponding to all the associated rendering tasks, predict the rendering load corresponding to the request instruction.

[0017] As an optional implementation, in a second aspect of the invention, the specific method by which the prediction module predicts the rendering load corresponding to the request instruction based on the task load corresponding to all the associated rendering tasks includes: The task parameters corresponding to all the associated rendering tasks are input into the trained execution order prediction model to obtain the output task execution order; the execution order prediction model is trained using a training dataset that includes multiple sets of training rendering tasks and corresponding execution order annotations. Based on the task execution order, at least one set of parallel tasks is determined; the set of parallel tasks consists of at least two of the associated rendering tasks that are executed simultaneously. Calculate the average load of all tasks corresponding to each set of parallel tasks to obtain the set load; The rendering load corresponding to the request instruction is obtained by calculating the weighted sum of the loads of all the sets and the loads of all the associated rendering tasks that are not in the set of parallel tasks.

[0018] As an optional implementation, in a second aspect of the present invention, the task execution order includes multiple sequentially ordered task information; the task information is a single associated rendering task or a set of parallel tasks composed of multiple associated rendering tasks; the computational weight corresponding to each set load or task load in the load weighted sum is proportional to the priority of the corresponding task information in the task execution order.

[0019] As an optional implementation, in the second aspect of the present invention, the specific method by which the forwarding module forwards the request instruction to the cloud device for execution includes: The request command and the device parameters of the vehicle equipment are forwarded to the cloud device; the cloud device is used to perform the following steps: A virtual rendering sandbox with the same rendering environment as the vehicle equipment is generated based on the device parameters; The request command is executed based on the virtual rendering sandbox to obtain the rendering result.

[0020] A third aspect of this invention discloses another remote rendering and control system for in-vehicle systems based on cloud computing power reconstruction, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the remote rendering and control method for vehicle systems based on cloud computing power reconstruction disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the remote rendering and control method for vehicle systems based on cloud computing power reconstruction disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention obtains the pending request instructions input by the user, determines multiple associated rendering tasks and predicts the rendering load based on instruction parsing rules, and forwards the rendering to the cloud for execution and returns the rendering results when the load exceeds the vehicle's computing power threshold. This enables dynamic rendering scheduling with intelligent sharing between local and cloud, improves the real-time response and stability of rendering tasks, and reduces the risk of rendering lag or failure due to insufficient vehicle computing power. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0024] Figure 1 This is a flowchart illustrating a remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction, as disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of the structure of a vehicle-mounted system remote rendering and control system based on cloud computing power reconstruction, as disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another vehicle system remote rendering and control system based on cloud computing power reconstruction disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses a remote rendering and control method and system for in-vehicle systems based on cloud computing power reconstruction. By acquiring user-input requests, it determines multiple associated rendering tasks and predicts the rendering load based on command parsing rules. When the load exceeds the vehicle's computing power threshold, it forwards the task to the cloud for execution and returns the rendering results. This enables dynamic rendering scheduling with intelligent sharing between local and cloud resources, improving the real-time response and stability of rendering tasks and reducing the risk of rendering stuttering or failure due to insufficient vehicle computing power. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction, as disclosed in an embodiment of the present invention. Figure 1 The described cloud-based computing power-based remote rendering and control method for vehicle systems can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 1 As shown, the remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction can include the following operations: 101. Obtain the request command input by the vehicle user through the vehicle's equipment.

[0032] Optionally, the request instruction may include at least one of touch screen operation, text data, gesture visual data, gesture light reflection data, and voice data.

[0033] Optionally, the vehicle equipment can be an in-vehicle infotainment system (IVI), a digital head-up display (HUD), a streaming rearview mirror, a rear-seat entertainment tablet, or a smart cockpit domain controller; the present invention does not limit this.

[0034] Optionally, the method of obtaining the request command can be: collecting voice through an in-vehicle high-fidelity microphone array, collecting gesture light reflection signals through a cockpit time-of-flight (ToF) camera, or collecting touch trajectory through a capacitive / pressure-sensitive central control touch screen. This invention does not limit the method.

[0035] 102. Based on the instruction parsing rules and request instructions, determine the corresponding multiple associated rendering tasks.

[0036] Optionally, the instruction parsing rule can be a text matching rule based on regular expressions, a logical extraction rule based on semantic dependency analysis, or an intent association rule based on knowledge graphs; this invention does not impose any limitations.

[0037] Optionally, the associated rendering task can be a 3D car model pose rendering task, a dynamic weather effects rendering task, or a high-precision rendering task. Figure 3 This invention does not limit the scope of tasks such as navigation path rendering, streaming video decoding and rendering, or in-vehicle interface (HMI) animation rendering.

[0038] 103. Based on the task parameters of the associated rendering task, predict the rendering load corresponding to the request command.

[0039] Optionally, the task parameters can be the number of model vertices, texture map resolution, shader complexity, estimated rendering frames per second (FPS), or required video memory (VRAM), and this invention does not limit these parameters.

[0040] Optionally, the rendering load can be expressed as estimated graphics card utilization, processor computation cycle, memory bandwidth usage, or estimated instruction execution time; this invention does not limit this.

[0041] 104. When the rendering load exceeds the vehicle's computing power load corresponding to the vehicle equipment, the request command will be forwarded to the cloud equipment for execution.

[0042] Optionally, the cloud device executes the request command and sends the rendering result back to the vehicle device for display.

[0043] Optionally, the cloud device can be a public cloud server cluster, an edge computing node (MEC), a private cloud data center, or a distributed fog computing gateway; this invention does not limit the scope of the device.

[0044] Optionally, the implementation of the rendering result return can be: compressed return via H.264 / H.265 encoded video stream, or real-time synchronous return via lightweight rendering command stream. This invention does not limit the implementation.

[0045] As can be seen, the above-described embodiments of the invention obtain the pending request instructions input by the user, determine multiple associated rendering tasks and predict the rendering load based on the instruction parsing rules, and forward the rendering to the cloud for execution and return the rendering results when the load exceeds the vehicle's computing power threshold. This enables dynamic rendering scheduling with intelligent sharing between local and cloud, improves the real-time response and stability of rendering tasks, and reduces the risk of rendering lag or failure due to insufficient vehicle computing power.

[0046] As an optional embodiment, the step described above, determining the corresponding multiple associated rendering tasks based on the instruction parsing rules and request instructions, includes: The request command is input into the trained type classifier model to obtain the data type of the output command. Determine the parsing model corresponding to the instruction data type from multiple candidate instruction parsing models; The request instruction is input into the parsing model to obtain the output instruction structured data; Based on the structured data of the instructions, determine the corresponding multiple associated rendering tasks.

[0047] Optionally, the classifier model of this type can be a random forest, a multilayer perceptron (MLP), a support vector machine (SVM), or a text classification model based on a Transformer encoder; this invention does not limit the specific model.

[0048] Optionally, the structured data of the instruction can be in JSON format, XML format, Protocol Buffers binary format, or predefined C language structure data, and this invention does not limit it.

[0049] As can be seen, through the above optional embodiments, by determining the data type of the instruction input type classifier model and matching it with the corresponding parsing model, the structured data of the instruction is output and the associated rendering task is determined accordingly. This achieves accurate structured parsing and task association extraction based on instruction type, improves the accuracy and efficiency of rendering task identification, and reduces the risk of parsing failure caused by diverse instruction formats.

[0050] As an optional embodiment, the step above, determining the corresponding multiple associated rendering tasks based on the instruction structured data, includes: Each structured data point of the instruction structured data is input into the trained rendering-related prediction model to obtain the corresponding rendering relevance. Filter out structural data with rendering relevance greater than a preset relevance threshold to obtain multiple related structural data; For each historical rendering task record, calculate the average data similarity between the task instruction data and each related structural data in the historical rendering task record to obtain the record association degree corresponding to the historical rendering task record. Record all historical rendering tasks with a correlation score greater than a preset correlation score threshold as associated rendering tasks.

[0051] Optionally, the rendering-related prediction model is trained using a training dataset that includes multiple training instruction structure data and corresponding annotations on the relevance of rendering tasks.

[0052] Optionally, the algorithm for calculating the data similarity can be cosine similarity, Hamming distance, Levenshtein distance, or Jaccard similarity coefficient, and this invention does not limit it.

[0053] As can be seen, through the above optional embodiments, by inputting the structured data of the instruction structured data into the rendering-related prediction model to obtain the rendering relevance and filtering the structured data with high relevance, and then calculating the correlation of historical rendering task records to filter related rendering tasks, accurate rendering task association based on relevance and historical matching is achieved, improving the pertinence and reliability of task prediction and reducing the risk of task omission due to ignoring historical records.

[0054] As an optional embodiment, the step of predicting the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task in the above steps includes: For each associated rendering task, identify the multiple historical rendering devices corresponding to that associated rendering task; Send a load survey request to each historical rendering device to obtain the corresponding execution load; Calculate the weighted average of the execution loads of all historical rendering devices to obtain the task load corresponding to the associated rendering task.

[0055] Based on the task load corresponding to all associated rendering tasks, predict the rendering load corresponding to the request command.

[0056] Optionally, the computational weight of each execution load is proportional to the instruction similarity between the corresponding execution instruction and the request instruction.

[0057] Optionally, the load survey request can be sent via SNMP protocol, Remote Procedure Call (RPC) or custom heartbeat monitoring message, and the present invention is not limited thereto.

[0058] As can be seen, through the above optional embodiments, the execution load of the historical rendering device is determined based on load survey, and the task load of each associated rendering task is calculated based on the weight related to the similarity of the computation time instruction. The rendering load corresponding to the instruction is predicted by combining the loads of all tasks, so as to improve the comprehensiveness and accuracy of rendering load estimation.

[0059] As an optional embodiment, the step of predicting the rendering load corresponding to the request instruction based on the task load corresponding to all associated rendering tasks includes: Input the task parameters corresponding to all associated rendering tasks into the trained execution order prediction model to obtain the output task execution order; Based on the task execution order, at least one set of parallel tasks is determined; Calculate the average load of all tasks corresponding to each set of parallel tasks to obtain the set load; Calculate the weighted sum of the loads of all sets and the loads of all associated rendering tasks not in the parallel task set to obtain the rendering load corresponding to the request instruction.

[0060] Optionally, the execution order prediction model is trained using a training dataset that includes multiple sets of training rendering tasks and corresponding execution order annotations.

[0061] Optionally, the set of parallel tasks consists of at least two associated rendering tasks that are executed simultaneously; Optionally, the execution order prediction model can be a scheduling neural network based on a directed acyclic graph (DAG), a reinforcement learning (RL) scheduler, or a bidirectional long short-term memory network (Bi-LSTM), and this invention does not limit it.

[0062] Optionally, the task execution order includes multiple sequentially ordered task information; the task information is a single associated rendering task or a set of parallel tasks composed of multiple associated rendering tasks.

[0063] Optionally, the computational weight of each set of loads or task loads in the load-weighted sum is proportional to the priority of the corresponding task information in the task execution order.

[0064] As can be seen, through the above optional embodiments, by inputting the task parameters of the associated rendering tasks into the execution order prediction model to obtain the task execution order, determining the set of parallel tasks and calculating the weighted sum of the set load and the non-parallel load to obtain the rendering load, accurate load quantification based on order prediction and parallel optimization is achieved, improving the comprehensiveness and accuracy of rendering load estimation, and reducing the risk of load underestimation caused by neglecting task parallelism.

[0065] As an optional embodiment, the step of forwarding the request instruction to the cloud device for execution in the above steps includes: The request command and the vehicle equipment parameters are forwarded to the cloud device; the cloud device then performs the following steps: A virtual rendering sandbox is generated based on device parameters, mirroring the rendering environment of the vehicle equipment. The virtual rendering sandbox is used to execute request commands to obtain the rendering results.

[0066] Optionally, the device parameters can be the architecture model of the in-vehicle graphics card, the OpenGL / Vulkan version number, the screen resolution parameters, the operating system kernel version, or a list of pre-installed graphics library plugins; this invention does not impose any limitations on these parameters.

[0067] Optionally, the virtual rendering sandbox can be a lightweight container environment based on Docker, a KVM virtual machine, a standalone browser instance based on WebGL, or a headless rendering environment based on Unity; this invention does not limit the scope of the invention.

[0068] As can be seen, through the above optional embodiments, by forwarding the request command and vehicle equipment parameters to the cloud device, a virtual rendering sandbox execution command identical to the vehicle rendering environment is generated in the cloud to obtain the rendering result feedback, thereby realizing the accurate generation of rendering results by cloud virtualization execution, improving rendering quality and consistency, and reducing the risk of local rendering quality degradation due to insufficient vehicle computing power.

[0069] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a remote rendering and control system for an in-vehicle system based on cloud computing power reconstruction, as disclosed in an embodiment of the present invention. Figure 2 The described cloud-based computing power-reconstructed vehicle system remote rendering and control system can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, the vehicle-mounted system remote rendering and control system based on cloud computing power reconstruction may include: The acquisition module 201 is used to acquire the request command input by the vehicle user through the vehicle equipment.

[0070] The determination module 202 is used to determine the corresponding multiple associated rendering tasks based on the instruction parsing rules and request instructions.

[0071] The prediction module 203 is used to predict the rendering load corresponding to the request command based on the task parameters of the associated rendering task.

[0072] The forwarding module 204 is used to forward the request command to the cloud device for execution when the rendering load exceeds the vehicle computing power load corresponding to the vehicle device.

[0073] Optionally, the cloud device executes the request command and sends the rendering result back to the vehicle device for display.

[0074] As can be seen, the above-described embodiments of the invention obtain the pending request instructions input by the user, determine multiple associated rendering tasks and predict the rendering load based on the instruction parsing rules, and forward the rendering to the cloud for execution and return the rendering results when the load exceeds the vehicle's computing power threshold. This enables dynamic rendering scheduling with intelligent sharing between local and cloud, improves the real-time response and stability of rendering tasks, and reduces the risk of rendering lag or failure due to insufficient vehicle computing power.

[0075] As an optional embodiment, the request instruction includes at least one of touch screen operation, text data, gesture visual data, gesture light reflection data, and voice data.

[0076] As can be seen, the data content of the request instruction is defined through the above optional embodiments to accurately characterize the control instruction features of the vehicle user, assist in realizing dynamic rendering scheduling with intelligent sharing between local and cloud, and improve the real-time response and stability of rendering tasks.

[0077] As an optional embodiment, the determining module determines the specific method for the corresponding multiple associated rendering tasks based on the instruction parsing rules and request instructions, including: The request command is input into the trained type classifier model to obtain the data type of the output command. Determine the parsing model corresponding to the instruction data type from multiple candidate instruction parsing models; The request instruction is input into the parsing model to obtain the output instruction structured data; Based on the structured data of the instructions, determine the corresponding multiple associated rendering tasks.

[0078] As can be seen, through the above optional embodiments, by determining the data type of the instruction input type classifier model and matching it with the corresponding parsing model, the structured data of the instruction is output and the associated rendering task is determined accordingly. This achieves accurate structured parsing and task association extraction based on instruction type, improves the accuracy and efficiency of rendering task identification, and reduces the risk of parsing failure caused by diverse instruction formats.

[0079] As an optional embodiment, the determining module determines the specific method for determining multiple associated rendering tasks based on the instruction structured data, including: Each structured data point of the instruction structured data is input into the trained rendering-related prediction model to obtain the corresponding rendering relevance; optionally, the rendering-related prediction model is trained using a training dataset that includes multiple training instruction structured data points and corresponding rendering task relevance labels. Filter out structural data with rendering relevance greater than a preset relevance threshold to obtain multiple related structural data; For each historical rendering task record, calculate the average data similarity between the task instruction data and each related structural data in the historical rendering task record to obtain the record association degree corresponding to the historical rendering task record. Record all historical rendering tasks with a correlation score greater than a preset correlation score threshold as associated rendering tasks.

[0080] As can be seen, through the above optional embodiments, by inputting the structured data of the instruction structured data into the rendering-related prediction model to obtain the rendering relevance and filtering the structured data with high relevance, and then calculating the correlation of historical rendering task records to filter related rendering tasks, accurate rendering task association based on relevance and historical matching is achieved, improving the pertinence and reliability of task prediction and reducing the risk of task omission due to ignoring historical records.

[0081] As an optional embodiment, the prediction module predicts the specific method by which it predicts the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task, including: For each associated rendering task, identify the multiple historical rendering devices corresponding to that associated rendering task; Send a load survey request to each historical rendering device to obtain the corresponding execution load; Calculate the weighted average of the execution loads of all historical rendering devices to obtain the task load corresponding to the associated rendering task; optionally, the calculation weight of each execution load is proportional to the instruction similarity between the corresponding execution instruction and the request instruction; Based on the task load corresponding to all associated rendering tasks, predict the rendering load corresponding to the request command.

[0082] As can be seen, through the above optional embodiments, the execution load of the historical rendering device is determined based on load survey, and the task load of each associated rendering task is calculated based on the weight related to the similarity of the computation time instruction. The rendering load corresponding to the instruction is predicted by combining the loads of all tasks, so as to improve the comprehensiveness and accuracy of rendering load estimation.

[0083] As an optional embodiment, the prediction module predicts the rendering load corresponding to the request instruction based on the task load corresponding to all associated rendering tasks in a specific way, including: Input the task parameters corresponding to all associated rendering tasks into the trained execution order prediction model to obtain the output task execution order; optionally, the execution order prediction model is trained using a training dataset that includes multiple sets of training rendering tasks and corresponding execution order annotations. Based on the task execution order, at least one set of parallel tasks is determined; optionally, the set of parallel tasks consists of at least two related rendering tasks that are executed simultaneously. Calculate the average load of all tasks corresponding to each set of parallel tasks to obtain the set load; Calculate the weighted sum of the loads of all sets and the loads of all associated rendering tasks not in the parallel task set to obtain the rendering load corresponding to the request instruction.

[0084] As can be seen, through the above optional embodiments, by inputting the task parameters of the associated rendering tasks into the execution order prediction model to obtain the task execution order, determining the set of parallel tasks and calculating the weighted sum of the set load and the non-parallel load to obtain the rendering load, accurate load quantification based on order prediction and parallel optimization is achieved, improving the comprehensiveness and accuracy of rendering load estimation, and reducing the risk of load underestimation caused by neglecting task parallelism.

[0085] As an optional embodiment, the task execution order includes multiple sequentially ordered task information; the task information is a single associated rendering task or a set of parallel tasks composed of multiple associated rendering tasks; the computational weight corresponding to each set load or task load in the load weighted sum is proportional to the priority of the corresponding task information in the task execution order.

[0086] As can be seen, by limiting the content of the task execution order and the weight details of the load calculation, the above optional embodiments can help achieve accurate load quantization based on order prediction and parallel optimization, thereby improving the comprehensiveness and accuracy of rendering load estimation.

[0087] As an optional embodiment, the specific method by which the forwarding module forwards the request instruction to the cloud device for execution includes: The request command and the vehicle equipment parameters are forwarded to the cloud device; the cloud device then performs the following steps: A virtual rendering sandbox is generated based on device parameters, mirroring the rendering environment of the vehicle equipment. The virtual rendering sandbox is used to execute request commands to obtain the rendering results.

[0088] As can be seen, through the above optional embodiments, by forwarding the request command and vehicle equipment parameters to the cloud device, a virtual rendering sandbox execution command identical to the vehicle rendering environment is generated in the cloud to obtain the rendering result feedback, thereby realizing the accurate generation of rendering results by cloud virtualization execution, improving rendering quality and consistency, and reducing the risk of local rendering quality degradation due to insufficient vehicle computing power.

[0089] Example 3 Please see Figure 3 , Figure 3 This is another vehicle-mounted system remote rendering and control system based on cloud computing power reconstruction disclosed in the embodiments of the present invention. Figure 3 The described cloud-based computing power-reconstructed vehicle system remote rendering and control system is applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 3 As shown, the vehicle-mounted system remote rendering and control system based on cloud computing power reconstruction may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the remote rendering and control method for the vehicle system based on cloud computing power reconstruction described in Embodiment 1.

[0090] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction described in Embodiment 1.

[0091] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction described in Embodiment 1.

[0092] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0094] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0095] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0097] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0099] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0100] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0101] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0102] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0103] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0104] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0105] Finally, it should be noted that the remote rendering and control method and system for vehicle systems based on cloud computing power reconstruction disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote rendering and control method for an in-vehicle system based on cloud computing power reconstruction, characterized in that, The method includes: Obtain the request commands input by the vehicle user through the vehicle's equipment; Based on the instruction parsing rules and the request instruction, determine the corresponding multiple associated rendering tasks; Based on the task parameters of the associated rendering task, predict the rendering load corresponding to the request instruction; When the rendering load exceeds the vehicle's computing power load corresponding to the vehicle device, the request instruction is forwarded to the cloud device for execution; the cloud device executes the request instruction and sends the execution rendering result back to the vehicle device for display.

2. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 1, characterized in that, The request instruction includes at least one of touch screen operation, text data, gesture visual data, gesture light reflection data, and voice data.

3. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 1, characterized in that, The step of determining multiple associated rendering tasks based on the instruction parsing rules and the request instruction includes: The request instruction is input into the trained type classifier model to obtain the output instruction data type; The parsing model corresponding to the instruction data type is determined from multiple candidate instruction parsing models; The request instruction is input into the parsing model to obtain the output instruction structured data; Based on the structured data of the instructions, multiple associated rendering tasks are determined.

4. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 3, characterized in that, The step of determining the corresponding multiple associated rendering tasks based on the instruction structured data includes: Each structured data point of the instruction structured data is input into the trained rendering-related prediction model to obtain the corresponding rendering relevance; the rendering-related prediction model is trained using a training dataset that includes multiple training instruction structured data points and corresponding rendering task relevance labels. The structural data with rendering relevance greater than a preset relevance threshold are filtered out to obtain multiple related structural data. For each historical rendering task record, calculate the average data similarity between the task instruction data and each of the related structural data in the historical rendering task record to obtain the record association degree corresponding to the historical rendering task record. The rendering tasks corresponding to all historical rendering task records whose correlation degree is greater than a preset correlation degree threshold are identified as associated rendering tasks.

5. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 1, characterized in that, The step of predicting the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task includes: For each associated rendering task, determine the multiple historical execution rendering devices corresponding to the associated rendering task; Send a load survey request to each of the historical execution rendering devices to obtain the corresponding execution load; Calculate the weighted average of the execution loads of all the historical execution rendering devices to obtain the task load corresponding to the associated rendering task; wherein, the calculation weight of each execution load is proportional to the instruction similarity between the corresponding execution instruction and the request instruction; Based on the task load corresponding to all the associated rendering tasks, predict the rendering load corresponding to the request instruction.

6. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 5, characterized in that, The step of predicting the rendering load corresponding to the request instruction based on the task load corresponding to all the associated rendering tasks includes: The task parameters corresponding to all the associated rendering tasks are input into the trained execution order prediction model to obtain the output task execution order; the execution order prediction model is trained using a training dataset that includes multiple sets of training rendering tasks and corresponding execution order annotations. Based on the task execution order, at least one set of parallel tasks is determined; the set of parallel tasks consists of at least two of the associated rendering tasks that are executed simultaneously. Calculate the average load of all tasks corresponding to each set of parallel tasks to obtain the set load; The rendering load corresponding to the request instruction is obtained by calculating the weighted sum of the loads of all the sets and the loads of all the associated rendering tasks that are not in the set of parallel tasks.

7. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 6, characterized in that, The task execution order includes multiple sequentially ordered task information; the task information is a single associated rendering task or a set of parallel tasks composed of multiple associated rendering tasks; the calculation weight corresponding to each set load or task load in the load weighted sum is proportional to the priority of the corresponding task information in the task execution order.

8. The remote rendering and control method for vehicle systems based on cloud computing power reconstruction according to claim 1, characterized in that, The step of forwarding the request instruction to the cloud device for execution includes: The request command and the device parameters of the vehicle equipment are forwarded to the cloud device; the cloud device is used to perform the following steps: A virtual rendering sandbox with the same rendering environment as the vehicle equipment is generated based on the device parameters; The request command is executed based on the virtual rendering sandbox to obtain the rendering result.

9. A remote rendering and control system for vehicle systems based on cloud computing power reconstruction, characterized in that, The system includes: The acquisition module is used to acquire request commands input by vehicle users through vehicle devices; The determination module is used to determine multiple associated rendering tasks based on the instruction parsing rules and the request instruction. The prediction module is used to predict the rendering load corresponding to the request instruction based on the task parameters of the associated rendering task. The forwarding module is used to forward the request instruction to the cloud device for execution when the rendering load exceeds the vehicle computing power load corresponding to the vehicle device; the cloud device executes the request instruction and sends the execution rendering result back to the vehicle device for display.

10. A remote rendering and control system for vehicle systems based on cloud computing power reconstruction, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the remote rendering and control method for vehicle systems based on cloud computing power reconstruction as described in any one of claims 1-8.

Images