OTA upgrading method and system of intelligent network connection unmanned vehicle and storage medium

Abstract

The invention relates to an OTA upgrading method and system for an intelligent network-connected unmanned vehicle and a storage medium, and the method comprises the steps: M1, carrying out the safety verification of the integrity and source of an upgrade package through employing a public key encryption and digital signature technology before the upgrade package is downloaded, obtaining the data information of the upgrade package after the safety verification, and obtaining the data information of a current vehicle OTA version; and M2, based on the data information of the upgrade package after security verification and the data information of the OTA version of the current vehicle, performing simplified screening on the upgrade package by adopting a feature selection algorithm based on improved maximum correlation minimum redundancy to obtain the data information of the upgrade package after simplified screening. According to the method, the integrity and the source reliability of the upgrade package are ensured, hostile attacks are effectively prevented, the data transmission time is remarkably shortened, and the upgrade efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicles, and in particular to an OTA upgrade method, system and storage medium for an intelligent networked unmanned vehicle. Background Art

[0002] With the rapid development of intelligent network technology, unmanned vehicles have become an important part of future transportation. In order to ensure the safety, performance optimization and function expansion of unmanned vehicles, frequent software and firmware updates have become essential. Traditional upgrade methods, such as upgrading through physical media (such as USB flash drives, SD cards), are not only inefficient, but also have safety hazards and inconvenient operation. Therefore, the development of an efficient and secure OTA upgrade method and system is of great significance to the long-term development of intelligent networked unmanned vehicles. Summary of the invention

[0003] In view of the above problems, the present invention provides an OTA upgrade method, system and storage medium for an intelligent connected unmanned vehicle, which not only ensures the integrity and source reliability of the upgrade package and effectively prevents malicious attacks, but also significantly reduces data transmission time and improves upgrade efficiency.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0005] An OTA upgrade method for an intelligent connected unmanned vehicle, the method comprising:

[0006] M1. Before downloading the upgrade package, use public key encryption and digital signature technology to verify the integrity and source of the upgrade package, obtain the data information of the upgrade package after security verification, and obtain the data information of the current vehicle OTA version;

[0007] M2. Based on the data information of the upgrade package after the security verification and the data information of the current vehicle OTA version, the upgrade package is simplified and screened using an improved maximum relevance minimum redundancy feature selection algorithm to obtain the data information of the simplified and screened upgrade package;

[0008] M3. Based on the simplified data information of the upgrade package after screening, an adaptive multi-stage upgrade model based on a dynamic learning factor is constructed to perform a multi-stage upgrade on the OTA to obtain the data information of the OTA after the multi-stage upgrade;

[0009] M4. Based on the data information of the OTA after the multi-stage upgrade, construct an OTA upgrade detection function Q, detect the upgraded OTA, and output the data information of the detection value of the upgraded OTA.

[0010] Furthermore, the method further comprises:

[0011] M5. Based on the data information of the detection value of the upgraded OTA, a preset threshold is set. If the detection value of the upgraded OTA is greater than the preset threshold, the requirement is met and the OTA upgrade of the unmanned vehicle is successful. If the detection value of the upgraded OTA is less than the preset threshold, the requirement is not met and the OTA of the unmanned vehicle automatically rolls back to the previous version.

[0012] Furthermore, in step M2, the simplified screening of the upgrade package using the improved maximum relevance minimum redundancy feature selection algorithm includes:

[0013] M21. Based on the data information of the upgrade package after the security verification, establish a feature extraction function W of the upgrade package,

[0014]

[0015] Among them, x is the data information of the upgrade package after security verification, α1, α2 and α3 are feature extraction factors of the upgrade package, feature extraction is performed on the upgrade package, and a feature data set of the upgrade package is constructed to obtain data information of the feature data set of the upgrade package;

[0016] M22. Based on the data information of the feature data set of the upgrade package and the data information of the current vehicle OTA version, establish the maximum correlation function R and the minimum redundancy function U between the upgrade package and the current vehicle OTA version,

[0017]

[0018] Among them, S is the data information of the feature data set of the upgrade package, c is the data information of the current vehicle OTA version, and y i is the i-th feature data subset of the feature data set of the upgrade package, y j is the jth feature data subset of the feature data set of the upgrade package, i is a positive integer, j is a positive integer, I(y i ; c) is the mutual information function of the i-th feature data subset of the feature data set of the upgrade package and the data information of the current vehicle OTA version, I(y i ;y j ) is the mutual information function between the i-th feature data subset and the j-th feature data subset of the feature data set of the upgrade package;

[0019] M23. Based on the maximum correlation function R and the minimum redundancy function U between the upgrade package and the current vehicle OTA version, the upgrade package is simplified and screened to obtain data information of the simplified and screened upgrade package.

[0020] Furthermore, the mutual information function I(y i; c) is,

[0021]

[0022] The mutual information function I(y) between the i-th feature data subset and the j-th feature data subset of the feature data set of the upgrade package i ;y j )for,

[0023]

[0024] Among them, c is the data information of the current vehicle OTA version, y i is the i-th feature data subset of the feature data set of the upgrade package, y j is the j-th feature data subset of the feature data set of the upgrade package, i is a positive integer, and j is a positive integer.

[0025] Furthermore, the feature extraction factors α1, α2 and α3 of the upgrade package are:

[0026]

[0027] Among them, x is the data information of the upgrade package after security verification.

[0028] Furthermore, in step M3, constructing an adaptive multi-stage upgrade model based on dynamic learning factors to perform multi-stage upgrade on OTA includes:

[0029] M31. Based on the data information of the simplified screened upgrade package, construct a simplified screened upgrade package data set;

[0030] M32. Input the simplified and screened upgrade package data set into the adaptive multi-stage upgrade model based on dynamic learning factors for training and learning, and determine the adaptive multi-stage upgrade function G of the dynamic learning factor of the upgrade package.

[0031]

[0032] Among them, z is the dataset of the simplified and screened upgrade package, β1, β2 and β3 are the dynamic learning factors of the upgrade package, and the adaptive multi-stage upgrade model of the trained dynamic learning factors is obtained;

[0033] M33. Based on the adaptive multi-stage upgrade model of the trained dynamic learning factor, the data information of the simplified and screened upgrade package is input, and the OTA is upgraded in multiple stages to obtain the data information of the OTA after the multi-stage upgrade.

[0034] Furthermore, the constraints of the dynamic learning factors β1, β2 and β3 of the upgrade package are:

[0035]

[0036] Furthermore, the detection function Q of the OTA upgrade is:

[0037]

[0038] Among them, r is the data information of OTA after multi-stage upgrade, and δ1, δ2 and δ3 are the detection factors of OTA after multi-stage upgrade.

[0039] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides an OTA upgrade system for an intelligent connected unmanned vehicle, including a computer device, which is programmed or configured to execute the steps of any one of the OTA upgrade methods for the intelligent connected unmanned vehicle.

[0040] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the OTA upgrade methods for the intelligent connected unmanned vehicle.

[0041] The present invention has the following positive effects:

[0042] 1. The present invention simplifies the screening of upgrade packages by adopting a feature selection algorithm based on improved maximum relevance minimum redundancy, and combines it with the construction of an adaptive multi-stage upgrade model based on dynamic learning factors to perform multi-stage upgrades on OTA, which not only significantly reduces the data transmission time and improves the upgrade efficiency, but also the multi-stage upgrade strategy and downgrade mechanism ensure the controllability of the upgrade process and the ability to recover after failure. The cloud server can flexibly configure the upgrade strategy according to actual conditions to meet the needs of different markets and users.

[0043] 2. The present invention constructs an OTA upgrade detection function Q to detect the upgraded OTA, and combines public key encryption and digital signature technology to perform security verification on the integrity and source of the upgrade package. This not only ensures the integrity and source reliability of the upgrade package and effectively prevents malicious attacks, but also can automatically roll back to the previous version if a serious error occurs during the upgrade process, thereby ensuring the basic operating capability of the unmanned vehicle and reducing the risk of upgrade failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0045] Figure 2 It is a flow chart of the feature selection algorithm based on improved maximum relevance and minimum redundancy of the present invention;

[0046] Figure 3A schematic diagram of a process for constructing an adaptive multi-stage upgrade model based on dynamic learning factors according to the present invention;

[0047] Figure 4 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0048] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0049] Example 1: Figure 1 As shown, an OTA upgrade method for an intelligent connected unmanned vehicle, the method comprising:

[0050] M1. Before downloading the upgrade package, use public key encryption and digital signature technology to verify the integrity and source of the upgrade package, obtain the data information of the upgrade package after security verification, and obtain the data information of the current vehicle OTA version;

[0051] M2. Based on the data information of the upgrade package after the security verification and the data information of the current vehicle OTA version, the upgrade package is simplified and screened using an improved maximum relevance minimum redundancy feature selection algorithm to obtain the data information of the simplified and screened upgrade package;

[0052] M3. Based on the simplified data information of the upgrade package after screening, an adaptive multi-stage upgrade model based on a dynamic learning factor is constructed to perform a multi-stage upgrade on the OTA to obtain the data information of the OTA after the multi-stage upgrade;

[0053] M4. Based on the data information of the OTA after the multi-stage upgrade, construct an OTA upgrade detection function Q, detect the upgraded OTA, and output the data information of the detection value of the upgraded OTA.

[0054] In this embodiment, the method further includes:

[0055] M5. Based on the data information of the detection value of the upgraded OTA, a preset threshold is set. If the detection value of the upgraded OTA is greater than the preset threshold, the requirement is met and the OTA upgrade of the unmanned vehicle is successful. If the detection value of the upgraded OTA is less than the preset threshold, the requirement is not met and the OTA of the unmanned vehicle automatically rolls back to the previous version.

[0056] In this embodiment, if Figure 2As shown, in step M2, the simplified screening of the upgrade package using the improved maximum relevance minimum redundancy feature selection algorithm includes:

[0057] M21. Based on the data information of the upgrade package after the security verification, establish a feature extraction function W of the upgrade package,

[0058]

[0059] Among them, x is the data information of the upgrade package after security verification, α1, α2 and α3 are feature extraction factors of the upgrade package, feature extraction is performed on the upgrade package, and a feature data set of the upgrade package is constructed to obtain data information of the feature data set of the upgrade package;

[0060] M22. Based on the data information of the feature data set of the upgrade package and the data information of the current vehicle OTA version, establish the maximum correlation function R and the minimum redundancy function U between the upgrade package and the current vehicle OTA version,

[0061]

[0062] Among them, S is the data information of the feature data set of the upgrade package, c is the data information of the current vehicle OTA version, and y i is the i-th feature data subset of the feature data set of the upgrade package, y j is the jth feature data subset of the feature data set of the upgrade package, i is a positive integer, j is a positive integer, I(y i ; c) is the mutual information function of the i-th feature data subset of the feature data set of the upgrade package and the data information of the current vehicle OTA version, I(y i ;y j ) is the mutual information function between the i-th feature data subset and the j-th feature data subset of the feature data set of the upgrade package;

[0063] M23. Based on the maximum correlation function R and the minimum redundancy function U between the upgrade package and the current vehicle OTA version, the upgrade package is simplified and screened to obtain data information of the simplified and screened upgrade package.

[0064] In this embodiment, the mutual information function I(y) between the i-th feature data subset of the feature data set of the upgrade package and the data information of the current vehicle OTA version is i ; c) is,

[0065]

[0066] The mutual information function I(y) between the i-th feature data subset and the j-th feature data subset of the feature data set of the upgrade package i ;y j )for,

[0067]

[0068] Among them, c is the data information of the current vehicle OTA version, y i is the i-th feature data subset of the feature data set of the upgrade package, y j is the j-th feature data subset of the feature data set of the upgrade package, i is a positive integer, and j is a positive integer.

[0069] In this embodiment, the feature extraction factors α1, α2 and α3 of the upgrade package are:

[0070]

[0071] Among them, x is the data information of the upgrade package after security verification.

[0072] In this embodiment, if Figure 3 As shown, in step M3, the construction of an adaptive multi-stage upgrade model based on a dynamic learning factor and the multi-stage upgrade of OTA include:

[0073] M31. Based on the data information of the simplified screened upgrade package, construct a simplified screened upgrade package data set;

[0074] M32. Input the simplified and screened upgrade package data set into the adaptive multi-stage upgrade model based on dynamic learning factors for training and learning, and determine the adaptive multi-stage upgrade function G of the dynamic learning factor of the upgrade package.

[0075]

[0076] Among them, z is the dataset of the simplified and screened upgrade package, β1, β2 and β3 are the dynamic learning factors of the upgrade package, and the adaptive multi-stage upgrade model of the trained dynamic learning factors is obtained;

[0077] M33. Based on the adaptive multi-stage upgrade model of the trained dynamic learning factor, the data information of the simplified and screened upgrade package is input, and the OTA is upgraded in multiple stages to obtain the data information of the OTA after the multi-stage upgrade.

[0078] In this embodiment, the constraints of the dynamic learning factors β1, β2 and β3 of the upgrade package are:

[0079]

[0080] Example 2: Based on the OTA upgrade method of an intelligent connected unmanned vehicle in Example 1, the present invention is further illustrated and described below.

[0081] like Figure 1 As shown, an OTA upgrade method for an intelligent connected unmanned vehicle, the method comprising:

[0082] M1. Before downloading the upgrade package, use public key encryption and digital signature technology to verify the integrity and source of the upgrade package, obtain the data information of the upgrade package after security verification, and obtain the data information of the current vehicle OTA version;

[0083] M2. Based on the data information of the upgrade package after the security verification and the data information of the current vehicle OTA version, the upgrade package is simplified and screened using an improved maximum relevance minimum redundancy feature selection algorithm to obtain the data information of the simplified and screened upgrade package;

[0084] M3. Based on the simplified data information of the upgrade package after screening, an adaptive multi-stage upgrade model based on a dynamic learning factor is constructed to perform a multi-stage upgrade on the OTA to obtain the data information of the OTA after the multi-stage upgrade;

[0085] M4. Based on the data information of the OTA after the multi-stage upgrade, construct an OTA upgrade detection function Q, detect the upgraded OTA, and output the data information of the detection value of the upgraded OTA.

[0086] In this embodiment, the detection function Q of the OTA upgrade is:

[0087]

[0088] Among them, r is the data information of OTA after multi-stage upgrade, and δ1, δ2 and δ3 are the detection factors of OTA after multi-stage upgrade.

[0089] In this embodiment, the present invention provides an OTA upgrade system for an intelligent connected unmanned vehicle, including a computer device, which is programmed or configured to execute the steps of any one of the OTA upgrade methods for the intelligent connected unmanned vehicle.

[0090] In this embodiment, if Figure 4 As shown, the cloud server is responsible for storing and distributing upgrade packages, and providing upgrade strategy configuration, such as the release time of the upgrade package, the target vehicle range, etc.

[0091] On-board OTA controller: As the core of the vehicle, it is responsible for receiving cloud commands, managing the entire process of downloading, verifying, and installing the upgrade package, and communicating with the vehicle ECU (electronic control unit) to coordinate the vehicle status during the upgrade process.

[0092] Vehicle ECU: Executes specific software or firmware update operations according to the instructions of the OTA controller, and feedbacks the upgrade results after the upgrade.

[0093] Communication module: supports multiple wireless communication methods such as 4G / 5G and Wi-Fi to ensure stable transmission of upgraded data.

[0094] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the OTA upgrade methods for an intelligent connected unmanned vehicle.

[0095] In this embodiment, any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0096] In summary, the present invention not only ensures the integrity and source reliability of the upgrade package and effectively prevents malicious attacks, but also significantly reduces data transmission time and improves upgrade efficiency.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An OTA upgrade method for an intelligent connected unmanned vehicle, characterized in that: The method comprises: M1. Before downloading the upgrade package, use public key encryption and digital signature technology to verify the integrity and source of the upgrade package, obtain the data information of the upgrade package after security verification, and obtain the data information of the current vehicle OTA version; M2. Based on the data information of the upgrade package after the security verification and the data information of the current vehicle OTA version, the upgrade package is simplified and screened using an improved maximum relevance minimum redundancy feature selection algorithm to obtain the data information of the simplified and screened upgrade package; M3. Based on the simplified data information of the upgrade package after screening, an adaptive multi-stage upgrade model based on a dynamic learning factor is constructed to perform a multi-stage upgrade on the OTA to obtain the data information of the OTA after the multi-stage upgrade; M4. Based on the data information of the OTA after the multi-stage upgrade, construct an OTA upgrade detection function Q, detect the upgraded OTA, and output the data information of the detection value of the upgraded OTA.

2. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 1, characterized in that: The method further comprises: M5. Based on the data information of the detection value of the upgraded OTA, a preset threshold is set. If the detection value of the upgraded OTA is greater than the preset threshold, the requirement is met and the OTA upgrade of the unmanned vehicle is successful. If the detection value of the upgraded OTA is less than the preset threshold, the requirement is not met and the OTA of the unmanned vehicle automatically rolls back to the previous version.

3. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 1, characterized in that: In step M2, the simplified screening of the upgrade package using the improved maximum relevance minimum redundancy feature selection algorithm includes: M21. Based on the data information of the upgrade package after the security verification, establish a feature extraction function W of the upgrade package, Among them, x is the data information of the upgrade package after security verification, α1, α2 and α3 are feature extraction factors of the upgrade package, feature extraction is performed on the upgrade package, and a feature data set of the upgrade package is constructed to obtain data information of the feature data set of the upgrade package; M22. Based on the data information of the feature data set of the upgrade package and the data information of the current vehicle OTA version, establish the maximum correlation function R and the minimum redundancy function U between the upgrade package and the current vehicle OTA version, Among them, S is the data information of the feature data set of the upgrade package, c is the data information of the current vehicle OTA version, and y i is the i-th feature data subset of the feature data set of the upgrade package, y j is the jth feature data subset of the feature data set of the upgrade package, i is a positive integer, j is a positive integer, I(y i ; c) is the mutual information function of the i-th feature data subset of the feature data set of the upgrade package and the data information of the current vehicle OTA version, I(y i ;y j ) is the mutual information function between the i-th feature data subset and the j-th feature data subset of the feature data set of the upgrade package; M23. Based on the maximum correlation function R and the minimum redundancy function U between the upgrade package and the current vehicle OTA version, the upgrade package is simplified and screened to obtain data information of the simplified and screened upgrade package.

4. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 3, characterized in that: The mutual information function I(y) between the i-th feature data subset of the feature data set of the upgrade package and the data information of the current vehicle OTA version i ; c) is, The mutual information function I(y) between the i-th feature data subset and the j-th feature data subset of the feature data set of the upgrade package i ;y j )for, Among them, c is the data information of the current vehicle OTA version, y i is the i-th feature data subset of the feature data set of the upgrade package, y j is the j-th feature data subset of the feature data set of the upgrade package, i is a positive integer, and j is a positive integer.

5. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 3, characterized in that: The feature extraction factors α1, α2 and α3 of the upgrade package are: Among them, x is the data information of the upgrade package after security verification.

6. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 1, characterized in that: In step M3, the step of constructing an adaptive multi-stage upgrade model based on a dynamic learning factor and performing a multi-stage upgrade on OTA includes: M31. Based on the data information of the simplified screened upgrade package, construct a simplified screened upgrade package data set; M32. Input the simplified and screened upgrade package data set into the adaptive multi-stage upgrade model based on dynamic learning factors for training and learning, and determine the adaptive multi-stage upgrade function G of the dynamic learning factor of the upgrade package. Among them, z is the dataset of the simplified and screened upgrade package, β1, β2 and β3 are the dynamic learning factors of the upgrade package, and the adaptive multi-stage upgrade model of the trained dynamic learning factors is obtained; M33. Based on the adaptive multi-stage upgrade model of the trained dynamic learning factor, the data information of the simplified and screened upgrade package is input, and the OTA is upgraded in multiple stages to obtain the data information of the OTA after the multi-stage upgrade.

7. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 6, characterized in that: The constraints of the dynamic learning factors β1, β2 and β3 of the upgrade package are:

8. The OTA upgrade method for an intelligent connected unmanned vehicle according to claim 1, characterized in that: The detection function Q of the OTA upgrade is, Among them, r is the data information of OTA after multi-stage upgrade, and δ1, δ2 and δ3 are the detection factors of OTA after multi-stage upgrade.

9. An OTA upgrade system for an intelligent connected unmanned vehicle, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the OTA upgrade method for an intelligent connected unmanned vehicle as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the OTA upgrade method for the intelligent connected unmanned vehicle as described in any one of claims 1 to 8.

Images