Automobile OTA upgrading optimization method and system, medium and electronic equipment

Abstract

The invention discloses an optimization method and system for automobile OTA upgrade, a medium and electronic equipment. The optimization method comprises the following steps: acquiring automobile end system data; based on the vehicle end system data, predicting the vehicle state of the vehicle to obtain a prediction result, and performing multi-dimensional upgrade risk assessment according to the prediction result to obtain an upgrade risk score; executing a corresponding upgrading processing strategy based on the upgrading risk score; and determining the priority of the current upgrading task based on the vehicle end system data, and executing corresponding upgrading processing based on the priority of the current upgrading task and matching a current upgrading processing strategy, the prediction result in the preset time interval is obtained based on the vehicle end system data, risk assessment is carried out based on the prediction result, potential risks in the OTA upgrading process can be avoided in advance, the corresponding upgrading processing strategy is executed according to the upgrading risk score, the OTA upgrading opportunity is determined, the upgrading interruption or failure risk caused by sudden change of the vehicle state is remarkably reduced, and the upgrading efficiency is improved. And the integrity of the upgrading process and the vehicle function safety are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile software updating, and in particular to an automobile OTA upgrading optimization method, system, medium and electronic device. BACKGROUND

[0002] With the evolution of automotive electronic and electrical architecture and the popularity of software-defined car concept, OTA (Over-the-Air) technology has become a core function of modern intelligent and connected cars. It allows manufacturers to remotely update vehicle software, fix bugs, improve performance, and add new features, greatly improving user experience and vehicle lifecycle value.

[0003] The existing OTA upgrade is based on the current state of the vehicle to make decisions, which can easily lead to improper upgrade timing selection, interruption or failure when the user needs to use the vehicle, causing multiple repeated upgrade operations, occupying vehicle system resources, or still forcibly upgrading in high-risk scenarios, causing safety problems. SUMMARY

[0004] The purpose of the present application is to solve the problems existing in the prior art and provide an automobile OTA upgrading optimization method, system, medium and electronic device.

[0005] In order to achieve the above purpose, the present application adopts the following technical scheme: an automobile OTA upgrading optimization method, the optimization method is configured in the vehicle system, comprising: Obtain vehicle end system data, wherein the vehicle end system data is obtained in real time by a sensor; Based on the vehicle end system data, the vehicle state of the vehicle is predicted to obtain a prediction result, and a multi-dimensional upgrade risk assessment is performed according to the prediction result to obtain an upgrade risk score; Based on the upgrade risk score, the corresponding upgrade processing strategy is executed; And based on the vehicle end system data, determine the priority of the current upgrade task, based on the priority of the current upgrade task and match the current upgrade processing strategy, execute the corresponding upgrade processing.

[0006] As a further description of the above technical scheme: the vehicle end system data includes at least one of vehicle operation data, network communication data, vehicle location data, user behavior data and upgrade data.

[0007] As a further description of the above technical scheme: the prediction of the vehicle state of the vehicle to obtain a prediction result includes: Based on the vehicle end system data, feature extraction is performed to obtain corresponding feature data; Input the feature data into a preset prediction model to obtain a prediction result in a preset time interval.

[0008] As a further description of the above technical solution: the multi-dimensional upgrade risk assessment according to the prediction result comprises: determining a corresponding risk factor and a weight value according to the vehicle-end system data corresponding to the prediction result; inputting the risk factor and the weight value into a risk assessment model to obtain the upgrade risk score.

[0009] As a further description of the above technical solution: the corresponding upgrade processing strategy is executed based on the upgrade risk score, comprising: determining a corresponding risk level based on a threshold range corresponding to the upgrade processing strategy, wherein the threshold range comprises a first threshold and a second threshold, and the first threshold is less than the second threshold; if the upgrade risk score is less than or equal to the first threshold, it is determined as a low risk level, and the upgrade processing strategy is to execute upgrade; if the upgrade risk score is greater than the first threshold and less than or equal to the second threshold, it is determined as a medium risk level, and the upgrade processing strategy is to delay upgrade or upgrade in stages; if the upgrade risk score is greater than the second threshold, it is determined as a high risk level, and the upgrade processing strategy is to suspend upgrade.

[0010] As a further description of the above technical solution: the current upgrade task is matched based on the priority of the current upgrade task and the current upgrade processing strategy, comprising: obtaining an upgrade task sent by the cloud, wherein the upgrade task comprises an OTA upgrade data packet marked with a priority and a corresponding key ciphertext, the OTA upgrade data packet is encrypted by a key to generate an upgrade package ciphertext, and the upgrade package ciphertext is encrypted by a vehicle identification to generate a key ciphertext; decrypting the key ciphertext by using a vehicle identification private key to obtain the key; decrypting the upgrade package ciphertext based on the key to obtain the OTA upgrade data packet.

[0011] As a further description of the above technical solution: the prediction model and / or the risk assessment model are configured in the cloud for optimization training, obtain optimized parameter data, and update the prediction model and / or the risk assessment model.

[0012] Further comprising an optimization system for automobile OTA upgrade, comprising: an acquisition module for obtaining vehicle-end system data, wherein the vehicle-end system data is obtained in real time by a sensor; a prediction evaluation module configured to predict a vehicle state of the vehicle to obtain a prediction result, and perform multi-dimensional upgrade risk evaluation based on the prediction result to obtain an upgrade risk score; a decision module configured to execute a corresponding upgrade processing strategy based on the upgrade risk score, and determine a priority of a current upgrade task based on the vehicle-side system data; an upgrade module configured to execute corresponding upgrade processing based on the priority of the current upgrade task and matching the upgrade processing strategy.

[0013] The application further provides a computer readable storage medium storing a computer program for running the optimization method, wherein the computer program causes a computer to execute the optimization method according to any one of the above technical solutions.

[0014] The application further provides an electronic device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs are used to execute the optimization method according to any one of the above technical solutions.

[0015] The above technical solutions have the following advantages or beneficial effects: The current vehicle-side system data is used for prediction to obtain a prediction result in a preset time interval, multi-dimensional upgrade risk evaluation is performed based on the prediction result, potential risks in the OTA upgrade process can be avoided in advance, a corresponding upgrade processing strategy is executed according to the upgrade risk score, the timing of OTA upgrade is determined, the risk of upgrade interruption or failure caused by sudden change of the vehicle state is significantly reduced, and the integrity of the upgrade process and the functional safety of the vehicle are ensured. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0017] Figure 1 a flowchart of the optimization method provided by the present application; Figure 2 a flowchart of the prediction of the vehicle state in the present application; Figure 3 a flowchart of the risk evaluation based on the prediction result in the present application; Figure 4A flowchart for analyzing OTA upgrade data packets in the present application; Figure 5 A structure schematic diagram of the optimization system proposed in the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] Referring to Figure 1 An embodiment provided by the present application is an optimization method for automobile OTA upgrade, which is configured in a vehicle-mounted system and includes the following steps. S1, acquiring vehicle-end system data, wherein the vehicle-end system data is acquired in real time by a sensor; S2, predicting a vehicle state of the vehicle based on the vehicle-end system data to obtain a prediction result, performing multi-dimensional upgrade risk assessment according to the prediction result, and obtaining an upgrade risk score; S3, executing a corresponding upgrade processing strategy based on the upgrade risk score, and determining a priority of a current upgrade task based on the vehicle-end system data; S4, executing corresponding upgrade processing based on the priority of the current upgrade task and matching the current upgrade processing strategy.

[0020] In the present embodiment, the current vehicle-end system data is acquired in real time by a sensor, a prediction result in a preset time interval is obtained based on the current vehicle-end system data, risk assessment is performed based on the prediction result, potential risks in the OTA upgrade process can be avoided in advance, a corresponding upgrade processing strategy is executed according to the upgrade risk score, the timing of OTA upgrade is determined, system resources required for upgrade are acquired, upgrade request information is sent to the cloud, OTA upgrade data packets corresponding to the priority are determined, and OTA upgrade is performed according to the priority and the upgrade processing strategy, thereby significantly reducing the risk of upgrade interruption or failure caused by sudden changes in the vehicle state, and ensuring the integrity of the upgrade process and the functional safety of the vehicle.

[0021] The vehicle-end system data includes at least one of vehicle operation data, network communication data, vehicle location data, user behavior data and upgrade data.

[0022] In this embodiment, vehicle operation data is collected by sensors, including vehicle speed, engine / motor status, gear position, brake status, steering wheel angle, battery power (SOC), charging status (charging / discharging), charging power, charging duration, battery temperature, ambient temperature, etc. The data is collected through CAN bus sampling at a frequency of 1 Hz.

[0023] Network communication data is obtained, including cellular network signal strength (RSRP / SINR), Wi-Fi connection status and signal strength, network type (4G / 5G), available bandwidth, etc. The data is collected through T-BOX sampling at a frequency of 5 Hz.

[0024] Vehicle location data is obtained through GPS, including GPS location, geofencing information (home, company, parking lot), current road type (highway, city, rural), traffic conditions (congestion / flow), etc., with a sampling frequency of 1 Hz.

[0025] User behavior data is collected through the vehicle system, including historical driving habits (common departure / arrival time, common vehicle time period), historical OTA upgrade behavior (acceptance / rejection, completion time), user preference settings (whether to allow silent upgrade, upgrade time preference), etc.

[0026] Upgrade data is obtained through the communication port, including the type (safety critical / non-critical), size, expected upgrade duration, dependency relationship, rollback complexity, etc.

[0027] Referring to Figure 2 The vehicle state of the vehicle is predicted to obtain a prediction result, including: S211, feature extraction based on vehicle system data to obtain corresponding feature data; S212, input the feature data into the preset prediction model to obtain the prediction result in the preset time interval.

[0028] In this embodiment, the collected vehicle system data is preprocessed by cleaning and normalization, and after filtering the data, feature extraction is performed to construct feature data for prediction and risk assessment. The feature data contains multi-dimensional information such as vehicle state, network state, environmental state, user behavior and upgrade data. It provides comprehensive input for subsequent prediction and risk assessment, avoiding judgment bias caused by single data.

[0029] The characteristic data is input into a preset prediction model, which can be an LSTM (Long Short Term Memory) model or a Transformer model, preferably an LSTM model, including an input layer for obtaining the characteristic data, a hidden layer with 128 nodes including an input gate, a forgetting gate and an output gate, and an output layer for predicting the probability distribution of the future state of the vehicle and outputting the corresponding prediction result. The preset time interval is 24 hours, and the state prediction is performed once an hour to output the prediction result.

[0030] Referring to Figure 3 According to the prediction result, multi-dimensional upgrade risk assessment includes: S221, determining the corresponding risk factor and weight value according to the vehicle end system data corresponding to the prediction result; S222, inputting the risk factor and weight value into the risk assessment model to obtain the upgrade risk score.

[0031] In this embodiment, the risk factors include energy risk, environmental risk, upgrade risk and user interference risk, and the weight value is dynamically adjusted according to the vehicle type, user historical behavior and system upgrade processing strategy. For example, new energy vehicles increase the energy weight, and users who have historically refused to upgrade increase the user interference weight.

[0032] The risk assessment model is: upgrade risk score = Σ (weight x risk factor); Specifically, the communication risk is based on the matching degree of the current and predicted network stability, available bandwidth and upgrade package data size or upgrade time length, and the communication risk = (1-network stability score) x (upgrade package data size / bandwidth); The energy risk is based on the comparison of the current power, the predicted power depletion time and the upgrade required time, and the energy risk = (predicted SOC-current SOC) / upgrade required time; The environmental risk is determined based on the current geographic location, such as poor signal in tunnels, underground garages and weather conditions, and the environmental risk = (1-geographic location safety score) x (1-weather safety score); The upgrade risk is based on the software package type, such as higher risk of safety critical package, size, complexity and rollback difficulty, and the upgrade risk = safety critical coefficient x (upgrade package data size + upgrade time length + rollback difficulty); The user interference risk is determined based on the conflict degree of the predicted user vehicle usage time and the upgrade plan time, and the user interference risk = user usage probability x upgrade time conflict coefficient; The corresponding upgrade risk score is obtained by weighted calculation of multiple risk factors through the risk assessment model, and the higher the upgrade risk score, the greater the upgrade risk.

[0033] Based on the upgrade risk score, the corresponding upgrade processing strategy is executed, including: determining a corresponding risk level based on a threshold range corresponding to the upgrade processing strategy, wherein the threshold range includes a first threshold and a second threshold, the first threshold being less than the second threshold; If the upgrade risk score is less than or equal to the first threshold, it is determined as a low risk level, and the upgrade processing strategy is to perform the upgrade; If the upgrade risk score is greater than the first threshold and less than or equal to the second threshold, it is determined as a medium risk level, and the upgrade processing strategy is to delay the upgrade or upgrade in stages; If the upgrade risk score is greater than the second threshold, it is determined as a high risk level, and the upgrade processing strategy is to suspend the upgrade.

[0034] In this embodiment, the upgrade risk score is graded and scheduled, if the upgrade risk score is less than or equal to the first threshold M, it is confirmed to perform the upgrade and to select silent upgrade or prompt upgrade according to user preference, silent upgrade: automatically complete download and installation at a predicted low-risk time interval, such as charging at home at night, without user confirmation; prompt upgrade: push upgrade notification to the user and suggest to perform at a predicted time interval, such as when the vehicle is stationary, the network is good, and the user has no urgent vehicle demand.

[0035] If the upgrade risk score is greater than the first threshold M and less than or equal to the second threshold H, the upgrade processing strategy is to delay the upgrade and automatically find the next low-risk window; or upgrade in stages, such as only download and not install, install in stages, and reduce system resource occupation, such as when the vehicle is driving at low speed but the network fluctuates, and the upgrade is performed after the vehicle is parked.

[0036] If the upgrade risk score is greater than the second threshold H, terminate the current upgrade and send an explicit risk prompt to the user, such as when driving at high speed, the battery is low, or the user is using a critical function.

[0037] During the execution of the upgrade processing strategy, the vehicle state is continuously monitored, if the upgrade risk score dynamically increases to a high risk level during the upgrade process, an emergency rollback or safety suspension mechanism is triggered, the upgrade is suspended until the upgrade risk score decreases to a low risk level, and then prompt upgrade is performed at a predicted low-risk time interval.

[0038] Further, based on the upgrade processing strategy, the cloud is sent upgrade request information containing the risk level, the cloud determines the transmission priority of the OTA upgrade data package according to the upgrade request information and the urgency of the upgrade task, such as the priority of a safety patch being higher than that of an information and entertainment system update, to ensure that critical upgrades are processed first. Specifically, the OTA master ECU, such as the gateway or T-BOX, is upgraded first to solve potential problems in the OTA upgrade itself; then the ECU supporting dual backup, such as the power system and the battery management system, is upgraded using A / B partition backup; finally, the ECU not supporting dual backup, such as the information and entertainment system, is upgraded and the configuration file is updated.

[0039] The upgrade priority can be configured according to different OTA upgrade tasks and controller requirements to ensure the stability and safety of the upgrade process.

[0040] Referring to Figure 4 based on the priority of the current upgrade task and matching the current upgrade processing strategy includes: S41, obtaining the upgrade task sent by the cloud, wherein the upgrade task includes an OTA upgrade data packet marked with a priority and a corresponding key ciphertext; S42, the OTA upgrade data packet is encrypted by the key to generate an upgrade package ciphertext, and the upgrade package ciphertext is encrypted by the vehicle identification to generate the key ciphertext; S43, the key ciphertext is decrypted by the vehicle identification private key to obtain the key; S44, the upgrade package ciphertext is decrypted based on the key to obtain the OTA upgrade data packet.

[0041] In this embodiment, the OTA upgrade data packet sent by the cloud is protected by double-layer encryption of key encryption and vehicle identification encryption: first, the OTA upgrade data packet is encrypted by the OTA encryption key to generate an upgrade package ciphertext, and then the OTA encryption key is encrypted by the vehicle identification (such as the VIN code public key) to generate the key ciphertext.

[0042] After the vehicle obtains the key ciphertext, the key ciphertext is decrypted by the vehicle identification private key to obtain the OTA encryption key, and the upgrade package ciphertext is decrypted by the OTA encryption key to obtain the OTA upgrade data packet plaintext. The OTA upgrade data packet is prevented from being tampered with or stolen by double-layer encryption, wherein the OTA upgrade data packet plaintext also contains a digital signature, and the validity of the digital signature is verified to ensure that the OTA upgrade data packet has not been tampered with.

[0043] Further, based on the obtained OTA upgrade data packet, system resources are called to upgrade, and system resources are adjusted according to the current vehicle state and priority, such as: When the vehicle is driving: limit CPU / memory resource usage, reduce flashing speed, and avoid affecting driving performance.

[0044] When the vehicle is charging: adjust the download bandwidth according to the charging power to avoid affecting the charging speed.

[0045] When the vehicle is stationary: maximize resource usage to speed up download and flashing speed.

[0046] The system resource allocation is realized by the resource management module of the vehicle-mounted system to ensure that the upgrade process does not affect the normal function of the vehicle.

[0047] The prediction model and / or the risk assessment model are configured to be optimized in the cloud, obtain optimized parameter data, and update the prediction model and / or the risk assessment model.

[0048] In the embodiment, the cloud records the upgrade process log, the final result (success / failure / interruption), user behavior feedback, and corresponding vehicle-side system data. The historical vehicle-side system data is used as a training set to optimize the prediction model and the risk assessment model. The prediction model and the risk assessment model are optimized in the cloud, and the optimized model parameters or a lightweight model are downloaded to the vehicle system to perform prediction and risk assessment. Only the parameters are updated, not the full model, thereby saving bandwidth and storage.

[0049] With reference to Figure 5 The embodiment also includes an optimization system for automotive OTA upgrade, comprising: A collection module 1 obtains vehicle-side system data, wherein the vehicle-side system data is obtained in real time through sensors. A prediction and evaluation module 2 predicts the vehicle state of a vehicle to obtain a prediction result, performs multi-dimensional upgrade risk assessment based on the prediction result, and obtains an upgrade risk score. A decision module 3 executes a corresponding upgrade processing strategy based on the upgrade risk score, and determines the priority of a current upgrade task based on the vehicle-side system data. An upgrade module 4 executes corresponding upgrade processing based on the priority of the current upgrade task and the current upgrade processing strategy.

[0050] In the embodiment, the collection module 1 obtains vehicle-side system data through sensors. The prediction and evaluation module 2 receives the vehicle-side system data sent by the collection module 1, extracts features, obtains corresponding feature data, inputs the data into a preset prediction model, obtains a prediction result in a preset time interval, determines corresponding risk factors and weight values based on the prediction result and the vehicle-side system data, performs multi-dimensional upgrade risk assessment through a risk assessment model, and obtains an upgrade risk score.

[0051] The decision module 3 executes a corresponding upgrade processing strategy based on the upgrade risk score output by the prediction and evaluation module 2, and sends an upgrade request information to the cloud to obtain a key ciphertext corresponding to the encrypted OTA upgrade data packet in the cloud.

[0052] The upgrade module 4 parses the obtained OTA upgrade data packet according to the priority and the upgrade processing strategy to perform OTA upgrade.

[0053] The embodiment also includes a computer-readable storage medium storing a computer program for running an optimization method, wherein the computer program causes a computer to perform the following steps: S1, acquire vehicle-end system data, wherein the vehicle-end system data is acquired in real time through sensors; S2, based on the vehicle-end system data, predict the vehicle state in a preset time interval to obtain a prediction result, perform risk assessment according to the prediction result, and obtain an escalation risk score; S3, execute a corresponding escalation processing strategy based on the escalation risk score; and Send an escalation request information to the cloud to determine the corresponding priority OTA upgrade data package; S4, parse the OTA upgrade data package and perform OTA upgrade according to the priority and the escalation processing strategy.

[0054] The computer readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transfer of computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general or special purpose computer. For example, the computer readable storage medium is coupled to the processor, so that the processor can read information from the computer readable storage medium and write information to the computer readable storage medium. Of course, the computer readable storage medium can also be an integral part of the processor. The processor and the computer readable storage medium can be located in an application specific integrated circuit (ASIC). In addition, the ASIC can be located in the user equipment. Of course, the processor and the computer readable storage medium can also exist as discrete components in the communication device.

[0055] Specifically, the computer readable storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0056] Also includes an electronic device, comprising: one or more processors; memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and are used to perform the following steps: S1, acquiring vehicle-end system data, wherein the vehicle-end system data is acquired in real time through a sensor; S2, based on the vehicle-end system data, predicting a vehicle state in a preset time interval to obtain a prediction result, performing risk assessment according to the prediction result to obtain an escalation risk score; S3, performing a corresponding escalation processing strategy based on the escalation risk score; and sending an escalation request information to the cloud end, so as to make the cloud end determine an OTA escalation data packet corresponding to a priority; S4, analyzing the OTA escalation data packet and performing OTA escalation according to the priority and the escalation processing strategy.

[0057] a memory for storing a computer program. The memory can include a high-speed random access memory (RAM), and can also include a non-volatile memory (NVM), such as at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0058] a processor for executing the computer program stored in the memory, which can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor, or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0059] Optionally, the memory can be independent or integrated with the processor.

[0060] ​When the memory is a device independent of the processor, the electronic device can further include a bus. The bus is used to connect the memory and the processor. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0061] It should be noted that, through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and necessary universal hardware platforms. Based on such understanding, the above technical solutions can be embodied in the form of software products, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments. In this paper, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the processes, methods, articles or devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0062] Finally, it should be noted that: the above only describes the preferred embodiments of the present application, and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features, as long as they are within the spirit and principles of the present application. Any modification, equivalent replacement, improvement, etc. made shall be included in the protection scope of the present application.

Claims

1. An optimization method for automotive OTA upgrade, characterized in that, The optimization method is configured in a vehicle-mounted system, comprising: acquiring vehicle-end system data, wherein the vehicle-end system data is acquired in real time through sensors; based on the vehicle-end system data, predicting the vehicle state of the vehicle to obtain a prediction result, performing multi-dimensional upgrade risk assessment according to the prediction result to obtain an upgrade risk score; based on the upgrade risk score, executing a corresponding upgrade processing strategy; and based on the vehicle-end system data, determining the priority of the current upgrade task, and based on the priority of the current upgrade task and matching the current upgrade processing strategy, executing the corresponding upgrade processing.

2. The optimization method of claim 1, wherein: The vehicle-end system data includes at least one of vehicle operation data, network communication data, vehicle location data, user behavior data, and upgrade data.

3. The optimization method of claim 1, wherein: The prediction result of the vehicle state of the vehicle includes: based on the vehicle-end system data, extracting features to obtain corresponding feature data; input the feature data into a preset prediction model to obtain a prediction result within a preset time interval.

4. The optimization method of claim 3, wherein: The multi-dimensional upgrade risk assessment according to the prediction result includes: determining the risk factor and weight value corresponding to the vehicle-end system data according to the prediction result; input the risk factor and the weight value into the risk assessment model to obtain the upgrade risk score.

5. The optimization method of claim 1, wherein: The corresponding upgrade processing strategy based on the upgrade risk score includes: based on the threshold range corresponding to the upgrade processing strategy, determining the corresponding risk level, wherein the threshold range includes a first threshold and a second threshold, and the first threshold is less than the second threshold; if the upgrade risk score is less than or equal to the first threshold, it is determined as a low risk level, and the upgrade processing strategy is to execute the upgrade; if the upgrade risk score is greater than the first threshold and less than or equal to the second threshold, it is determined as a medium risk level, and the upgrade processing strategy is to delay the upgrade or upgrade in stages; if the upgrade risk score is greater than the second threshold, it is determined as a high risk level, and the upgrade processing strategy is to suspend the upgrade.

6. The optimization method of claim 1, wherein: Based on the priority of the current upgrade task and matching the current upgrade processing strategy includes: acquiring the upgrade task sent by the cloud, wherein the upgrade task includes an OTA upgrade data packet marked with priority and a corresponding key ciphertext, the OTA upgrade data packet is encrypted by a key to generate an upgrade package ciphertext, and the upgrade package ciphertext is encrypted by a vehicle identifier to generate a key ciphertext; decrypt the key ciphertext using a vehicle identifier private key to obtain the key; decrypt the upgrade package ciphertext based on the key to obtain the OTA upgrade data packet.

7. The optimization method of claim 4, wherein: The prediction model and / or the risk assessment model are configured in the cloud for optimization training, obtain optimized parameter data, and update the prediction model and / or the risk assessment model.

8. An optimization system for automotive OTA upgrade, characterized in that, including: a collection module for acquiring vehicle-end system data, wherein the vehicle-end system data is acquired in real time through sensors; A prediction evaluation module predicts a vehicle state of the vehicle to obtain a prediction result, performs multi-dimensional upgrade risk evaluation according to the prediction result, and obtains an upgrade risk score; A decision module executes a corresponding upgrade processing strategy based on the upgrade risk score, and determines a priority of a current upgrade task based on the vehicle-side system data; An upgrade module executes corresponding upgrade processing based on the priority of the current upgrade task and matching the current upgrade processing strategy.

9. A computer-readable storage medium, characterized in that, It stores a computer program for running an optimization method, wherein the computer program causes the computer to execute the optimization method according to any one of claims 1-7.

10. An electronic device, comprising: Comprise: One or more processors; Memory; And One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs are used to execute the optimization method according to any one of claims 1-7.

Images