Vehicle-mounted software automatic upgrading method and system based on artificial intelligence and related components

Abstract

The invention discloses a vehicle-mounted software automatic upgrading method and system based on artificial intelligence and a server, and the method comprises the steps: querying whether a data cloud server has new software of target vehicle-mounted software through an AI application program, and responding to the query that the new software of the target vehicle-mounted software exists in the data cloud server, obtaining the new software from the data cloud server; the target vehicle-mounted software is software deployed on a target vehicle; and performing performance comparison on the new software and current software deployed on the target vehicle by the target vehicle-mounted software, and updating the target vehicle-mounted software deployed on the target vehicle according to a performance comparison result. According to the vehicle-mounted software updating method and device, automatic updating of the vehicle-mounted software can be achieved, the updating efficiency and updating timeliness of the vehicle-mounted software are improved, and for a plurality of different vehicle-mounted software, the different vehicle-mounted software can be correspondingly updated only through corresponding query of the AI application program, so that the overall updating efficiency is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted software upgrade, and in particular to an artificial intelligence-based vehicle-mounted software automatic upgrade method, system and related components. Background Art

[0002] The prior art mainly uses a personal computer to manually query new software versions on the Internet from time to time when updating and upgrading vehicle-mounted software, and then manually verify whether the newly downloaded software is better than the vehicle-mounted software currently used by the vehicle. If the new version of the software is better than the vehicle-mounted software currently used by the vehicle, continue to manually update the code of the current software, and then compile it into new software, and update it to the vehicle-mounted controller for version upgrade. Obviously, this software update and upgrade method is inefficient, and because the new version is queried manually from time to time, there is also the problem of untimely query and update. In addition, the prior art usually only queries and updates a single vehicle-mounted algorithm / software, and if the above-mentioned vehicle-mounted software update and upgrade method is adopted, then the update efficiency will be even lower for the overall multiple vehicle-mounted algorithms of the vehicle-mounted system.

[0003] Therefore, how to improve the update and upgrade efficiency and timeliness of vehicle-mounted software is a problem that technical personnel in this field need to solve. Summary of the invention

[0004] The embodiments of the present invention provide an artificial intelligence-based automatic upgrade method, system, computer device, storage medium and computer program product for vehicle-mounted software, aiming to improve the upgrade efficiency and timeliness of vehicle-mounted software.

[0005] In a first aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle software automatic upgrade method, comprising:

[0006] querying the data cloud server through the AI ​​application whether there is new software of the target vehicle-mounted software, and in response to querying that the new software of the target vehicle-mounted software exists in the data cloud server, obtaining the new software from the data cloud server; the target vehicle-mounted software is the software deployed on the target vehicle;

[0007] A performance comparison is performed between the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and the target vehicle-mounted software deployed on the target vehicle is updated according to the result of the performance comparison.

[0008] In a second aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle software automatic upgrade method, which is applied to a data cloud server.

[0009] The data cloud server sends the new software of the target vehicle-mounted software to the local server, so that the local server compares the performance of the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and updates the target vehicle-mounted software deployed on the target vehicle according to the result of the performance comparison; wherein, the new software is sent by the data cloud server after the local server queries through the AI ​​application that the new software of the target vehicle-mounted software exists on the data cloud server; the target vehicle-mounted software is the software deployed on the target vehicle.

[0010] In a third aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle software automatic upgrade method, which is applied to a vehicle controller.

[0011] Receive new software of the target vehicle-mounted software sent by the local server; the new software is obtained from the data cloud server after the local server queries the data cloud server through the AI ​​application program to find that the new software of the target vehicle-mounted software exists, and compares the performance of the new software with the current software of the target vehicle-mounted software deployed on the target vehicle, and sends it according to the result of the performance comparison; the target vehicle-mounted software is the software deployed on the target vehicle;

[0012] The current software deployed for the target vehicle software on the target vehicle is updated to the new software.

[0013] In a fourth aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle software automatic upgrade system, including a local server, a data cloud server, and a vehicle controller, wherein:

[0014] The local server queries the data cloud server through the AI ​​application whether there is new software of the target vehicle-mounted software, and, in response to the query that the new software of the target vehicle-mounted software exists in the data cloud server, obtains the new software from the data cloud server; wherein the target vehicle-mounted software is the software deployed on the target vehicle;

[0015] The data cloud server sends the new software of the target vehicle software to the local server;

[0016] The local server obtains the new software of the target vehicle-mounted software, performs a performance comparison between the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and sends the new software of the target vehicle-mounted software to the vehicle-mounted controller according to the result of the performance comparison;

[0017] The vehicle controller receives new software of the target vehicle software sent by the local server, and updates the current software deployed on the target vehicle for the target vehicle software to the new software.

[0018] In a fifth aspect, an embodiment of the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for automatic vehicle software upgrade based on artificial intelligence as described in any one of the first to third aspects is implemented.

[0019] In the sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for automatic vehicle software upgrade based on artificial intelligence as described in any one of the first to third aspects is implemented.

[0020] In the seventh aspect, an embodiment of the present invention provides a computer program product, which, when executed by a processor, implements the artificial intelligence-based automatic vehicle software upgrade method as described in any one of the first to third aspects.

[0021] The embodiment of the present invention provides an automatic upgrade method, system, computer device, storage medium and computer program product for vehicle-mounted software based on artificial intelligence. The method uses an AI application to query a data cloud server whether there is new software for the target vehicle-mounted software, and downloads the new software from the data cloud server when the query is found, and compares the performance of the new software with the current software deployed on the target vehicle by the target vehicle software, so as to update the target vehicle-mounted software deployed on the target vehicle according to the result of the performance comparison. In this way, not only can the automatic upgrade of the vehicle-mounted software be realized, but also the update efficiency and timeliness of the vehicle-mounted software can be improved. For multiple different vehicle-mounted software, only corresponding queries and subsequent update operations through the AI ​​application can be performed, so that different vehicle-mounted software can be updated accordingly, which can greatly improve the update efficiency of the overall vehicle-mounted system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0023] Figure 1 A system architecture diagram of an artificial intelligence-based vehicle software automatic upgrade system provided in an embodiment of the present invention;

[0024] Figure 2 A system interaction diagram of an artificial intelligence-based vehicle software automatic upgrade system provided by an embodiment of the present invention;

[0025] Figure 3 A flowchart of an automatic vehicle software upgrade method based on artificial intelligence provided by an embodiment of the present invention;

[0026] Figure 4 A schematic diagram of a sub-process of an automatic vehicle software upgrade method based on artificial intelligence provided by an embodiment of the present invention;

[0027] Figure 5 An example diagram of an automatic vehicle software upgrade method based on artificial intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0030] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0031] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0032] In order to improve the timeliness and efficiency of updating the in-vehicle software deployed on the vehicle, an embodiment of the present application provides an automatic upgrade method for in-vehicle software based on artificial intelligence. In this method, an AI application is periodically applied through a local server to automatically query new algorithms corresponding to one / multiple target in-vehicle software through the AI ​​application, and then a performance comparison is performed between the new software of the target in-vehicle software and the current software of the target in-vehicle software deployed on the target vehicle, and the target in-vehicle software deployed on the target vehicle is updated according to the results of the performance comparison.

[0033] It should be understood that the aforementioned target vehicle is any vehicle that needs to update the on-board software, and the target vehicle is the software deployed on the target vehicle (i.e., the on-board software); the on-board software in the embodiment of the present application can be the software of the vehicle's on-board system, and the on-board software can be a filter algorithm, or it can be any one or more software such as a torque model, a temperature model, navigation software, music software, etc.

[0034] It should be understood that the AI ​​application in the embodiment of the present application can be a computer program that implements the technical solution of the embodiment of the present application; the AI ​​application in the embodiment of the present application can also be an intelligent software tool (such as ChartGTP and other software tools) that provides voice recognition, vision, decision logic and other intelligent functions that imitate human rationality, which can have text recognition and interaction capabilities, such as but not limited to text recognition interaction capabilities, voice recognition interaction capabilities, or other interaction capabilities; that is, when the AI ​​application includes text recognition interaction capabilities, the user can input the software keyword "navigation" of the navigation software (i.e., the target vehicle-mounted software) to be updated through the user interaction interface (GUI) corresponding to the AI ​​application, or the user can input the update indication information "Update navigation software" for updating the navigation software through the GUI, and then the AI ​​application can extract the software keyword "navigation" of the navigation software based on the information indicated by the user, thereby querying and updating the navigation software for new software.

[0035] like Figure 1 As shown, in order to implement the aforementioned artificial intelligence vehicle software automatic upgrade method, the embodiment of the present application also provides an artificial intelligence-based vehicle software automatic upgrade system, including: a local server 100, a data cloud server 200 and a vehicle controller 300, wherein:

[0036] The local server 100 queries the data cloud server 200 through the AI ​​application whether there is new software of the target vehicle-mounted software, and, in response to the query that the data cloud server 200 has the new software of the target vehicle-mounted software, obtains the new software from the data cloud server 200; wherein the target vehicle-mounted software is the software deployed on the target vehicle;

[0037] The data cloud server 200 sends the new software of the target vehicle software to the local server 100;

[0038] The local server 100 obtains the new software of the target vehicle-mounted software, performs a performance comparison between the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and sends the new software of the target vehicle-mounted software to the vehicle-mounted controller 300 according to the result of the performance comparison;

[0039] The vehicle controller 300 receives the new software of the target vehicle software sent by the local server 100, and updates the current software deployed on the target vehicle for the target vehicle software to the new software.

[0040] In this embodiment, combined with Figure 2 , the local server 100 calls the AI ​​application to query the data cloud server 200 whether there is new software of the target vehicle software. When the AI ​​application queries the data cloud server 200 to have new software, the local server 100 sends a new software acquisition request to the data cloud server 200 through the AI ​​application; after receiving the new software acquisition request, the data cloud server 200 sends the new software to the AI ​​application; the local server 100 obtains the new software through the AI ​​application, and compares the performance test of the new software with the current software deployed on the target vehicle by the target vehicle software, and obtains the corresponding performance test comparison result. The local server 100 sends the new software to the vehicle controller 300 of the target vehicle according to the result of the performance test comparison. The vehicle controller 300 upgrades and updates the target vehicle software according to the received new software.

[0041] The aforementioned local server 100 can be an independent server, server cluster corresponding to the vehicle system, or a local service terminal corresponding to the vehicle; the data cloud server 200 is an independent server, server cluster, cloud or distributed system corresponding to the target vehicle software; the vehicle controller 300 can be a controller, processor or processing unit on the vehicle, etc. Technical personnel in this field can select specific equipment of the local server 100, data cloud server 200 and vehicle controller 300 according to actual needs.

[0042] The specific technologies of the local server 100, the data cloud server 200 and the vehicle controller 300 in the embodiment of the present application are further described below.

[0043] The following content of the embodiment of the present application further explains the specific technologies of the local server 100, the data cloud server 200 and the vehicle controller 300 in the artificial intelligence vehicle software automatic upgrade method.

[0044] See below Figure 3 , an embodiment of the present invention provides an artificial intelligence-based vehicle software automatic upgrade method, which can be applied to a local server 100, specifically comprising: steps S301 to S302.

[0045] Step S301, querying a data cloud server through an AI application whether there is new software of the target vehicle-mounted software, and in response to querying that the new software of the target vehicle-mounted software exists in the data cloud server, obtaining the new software from the data cloud server; the target vehicle-mounted software is the software deployed on the target vehicle;

[0046] Step S302: Perform a performance comparison between the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and update the target vehicle-mounted software deployed on the target vehicle according to the result of the performance comparison.

[0047] In this embodiment, the data cloud server is first queried through an AI application (i.e., AI software, such as ChartGTP and other software tools), and the AI ​​application is used to determine whether the latest version of the target vehicle software, i.e., new software, exists in the data cloud server. When the AI ​​application queries the new software, the new software is downloaded from the data cloud server, and then the new software is obtained from the AI ​​application, and the performance of the new software is compared with the current software deployed on the target vehicle by the target vehicle software, and the target vehicle software deployed on the target vehicle is updated according to the results of the performance comparison, so that not only the automatic upgrade of the vehicle software can be achieved, but also the update efficiency and timeliness of the vehicle software can be improved, and for multiple different vehicle software, only the corresponding query and subsequent update operation through the AI ​​application can make different vehicle software get corresponding updates, so that the update efficiency of the overall vehicle system can be greatly improved.

[0048] In one embodiment, step S301 includes:

[0049] The software keywords of the target vehicle-mounted software are determined through an AI application, and based on the software keywords, a query is made on a data cloud server matching the software keywords to determine whether there is new software for the target vehicle-mounted software; wherein the software keywords are pre-set in the AI ​​application, or the software keywords are determined according to the keyword information indicated by the user according to the AI ​​application.

[0050] In this embodiment, the query is triggered by setting the software keywords of the target vehicle software, so that the AI ​​application program queries the data cloud server based on the software keywords to see whether there is corresponding new software. For example, when the target vehicle software is a filter algorithm, the user can call the AI ​​application program in the local server and enter the software keyword "filter algorithm" or the instruction information "upgrade filter" in the AI ​​application program, thereby querying the data cloud server through the AI ​​application program whether there is the latest version of the filter algorithm. For another example, the software keyword "filter algorithm" can be set in advance in the AI ​​application program, so that when the software automatic update condition is triggered, the AI ​​application program can directly and automatically query based on the set software keyword.

[0051] In one embodiment, the step S301 further includes:

[0052] When the conditions for automatic software update are triggered, the data cloud server is queried through the AI ​​application whether there is new software for the target vehicle software; wherein the conditions for triggering automatic software update include: reaching the periodic update periodic time, and / or the AI ​​application receives keyword information indicated by the user for the target vehicle software.

[0053] In this embodiment, when calling the AI ​​application, the AI ​​application can be called according to a preset calling cycle, for example, calling the AI ​​application every several days to check whether there is new software, or according to the user's instructions, for example, the user enters the corresponding software keyword in the AI ​​application in the local server, and the AI ​​application can query according to the software keyword. In other words, when calling the AI ​​application, it can be called periodically and can be called at any time based on the user's needs.

[0054] In one embodiment, the comparing the performance of the new software and the current software of the target vehicle software deployed on the target vehicle, and updating the target vehicle software deployed on the target vehicle according to the result of the performance comparison, comprises:

[0055] In response to the result of the performance comparison being that the new software is better than the current software, the new software is sent to the onboard controller of the target vehicle, so that the onboard controller updates the current software deployed on the target vehicle for the target onboard software to the new software.

[0056] In this embodiment, when the performance comparison result shows that the performance of the new software is better than the current software, the new software is sent to the vehicle controller, and then the vehicle controller uses the new software to upgrade the target vehicle software. Of course, if the performance comparison result shows that the performance of the new software is worse than the current software, it means that the performance of the current software is better, and there is no need to update the current software.

[0057] In one embodiment, if Figure 4 As shown, the step S302 may include the following steps S401 to S403 to compare the performance of the new and old target vehicle software.

[0058] Step S401: Load the code of the new software into a preset test file to perform a performance test and obtain a first performance test score;

[0059] Step S402, loading the code of the current software deployed by the target vehicle-mounted software on the target vehicle into the test file to perform a performance test, and obtaining a second performance test score;

[0060] Step S403: Perform a performance test comparison between the new software and the current software according to the first performance test score and the second performance test score to obtain the performance test comparison result.

[0061] In step S403, after obtaining the first performance test score and the second performance test score, a performance comparison can be performed using the first performance test score and the second performance test score, specifically including: when the first performance test score is higher than the second performance test score, the performance test comparison result is that the new software performance is better than the current software performance; when the first performance test score is lower than the second performance test score, the performance test comparison result is that the new software performance is worse than the current software performance.

[0062] In the embodiment of the present application, the new software of the target vehicle software and the current software currently deployed on the target vehicle can be compared in performance with a test file set by one or more programming tools (such as but not limited to C language, C++, Java or Python, etc.), and the target vehicle software deployed on the target vehicle can be updated according to the result of the performance comparison; the performance comparison of the new and old software using a test file constructed in C language is described as an example below:

[0063] In step S401, the method may specifically include: loading the new code into the C file and the H file, inputting the preset test data into the C file and the H file loaded with the new code, and running the test according to the dimension to obtain the first performance test score;

[0064] In step S402, the following may be specifically included: the local server loads the current code into a C file and an H file; inputs preset test data into the C file and the H file loaded with the current code, and runs the test according to the dimension to obtain the second performance test score;

[0065] It should be understood that the C file and H file in steps S401 and S402 are the C language source file and C language header file respectively. The C file is usually used to store the specific definitions of variables, arrays, and functions, and the H file is usually used to store the declarations of variables, arrays, and functions defined in the C file with the same name, as well as declarations that need to be used externally by the C file.

[0066] In this embodiment, when performing performance test comparison, on the one hand, the new software is tested by the test software to obtain the performance test score corresponding to the new software, and on the other hand, the current software is tested by the test software to obtain the performance test score corresponding to the current software, and then the performance test comparison result is determined by the two performance test scores. Specifically, in this embodiment, when the code of the vehicle-mounted software is loaded into the C file and the H file (the C file is a source file of the C language, containing function implementation, variable definition, etc., and the H file is a header file of the C language, containing function declaration, macro definition, structure definition, etc.), the preset test data is then injected into the code, and the test file is run to obtain the corresponding performance test score. Further, for vehicle-mounted software with different performance, multiple groups of test data can be set for multiple rounds of testing, so that the test file is run periodically, and multiple performance test results are obtained accordingly. For example, for the filter algorithm, its test dimensions include one or any combination of accuracy, robustness, convergence speed and computational complexity, etc., so performance testing can be performed round by round to obtain the performance test score of each dimension.

[0067] In one embodiment, the first performance test score and the second performance test score obtained in step S401 and step S402 are both one-dimensional performance test scores, or the first performance test score and the second performance test score are both multi-dimensional performance test scores;

[0068] When the first performance test score and the second performance test score obtained in step S401 and step S402 are one-dimensional performance test scores, the performance test comparison result can be obtained directly according to the comparison result of the first performance test score and the second performance test score in step S403;

[0069] When the first performance test score and the second performance test score obtained in step S401 and step S402 are multidimensional performance test scores, in step S403, the first performance test score can be weighted by dimension to obtain a weighted first performance test score, and the first performance test score can be weighted by dimension to obtain a weighted second performance test score, and the performance test comparison result can be obtained based on the comparison result of the weighted first performance test score and the weighted second performance test score.

[0070] This embodiment takes into account that when performing performance testing, it may not be just a single-dimensional test, but there may be multi-dimensional tests. Therefore, for test scores with only a single dimension, the performance test comparison results can be determined directly based on the one-dimensional performance test scores. For test scores with multiple dimensions, it is necessary to first weight the test scores of multiple dimensions by preset weights, and then determine the performance test comparison results based on the results of the weighted processing. For example, when performing performance testing on a filter algorithm, there are multiple test dimensions including accuracy, robustness, convergence speed, and computational complexity. Therefore, after obtaining the performance test scores for each dimension in the filter algorithm, the performance test scores of these dimensions are weighted and summarized, and then the performance of the new software and the old software is compared based on the total score of the weighted summary; wherein, the embodiment of the present application does not limit the principles and methods for setting specific weights for multiple dimensions, and those skilled in the art can set them according to actual needs.

[0071] In one embodiment, in step S302, in response to the result of the performance comparison being that the new software is better than the current software, sending the new software to the onboard controller of the target vehicle includes:

[0072] When the result of the performance comparison is that the new software is better than the current software, formatting the code of the new software so that the code format of the new software is adapted to the format of the target vehicle-mounted software deployed on the target vehicle;

[0073] After the format compilation is completed, the new software is sent to the on-board controller of the target vehicle.

[0074] In this embodiment, since the vehicle controller cannot directly run the code in the C file and the H file, before transferring the new software to the vehicle controller, it is necessary to convert the format of the new software so that the new software can be compatible with the vehicle controller, thereby completing the vehicle software upgrade. Specifically, compile the code in all C files and H files required by the vehicle controller into ASCII files such as Hex (a common format for representing binary data), S19 (a hexadecimal text file format) or BIN (abbreviation for binary file, this file format refers to all files in the form of binary content), and then flash the ASCII files such as Hex, S19, BIN to the vehicle controller.

[0075] In another embodiment, in response to the result of the performance comparison being that the new software is better than the current software, sending the new software to the onboard controller of the target vehicle further includes:

[0076] The new software is transmitted to the onboard controller of the target vehicle by using over-the-air download technology, so that the onboard controller updates the current software deployed for the target onboard software on the target vehicle to the new software.

[0077] Over-the-air download technology (OTA technology) is a technology that remotely manages SIM card data and applications through the air interface of mobile communications (GSM or CDMA). The air interface can use WAP, GPRS, CDMAlx and the most popular short message technology. The application of OTA technology enables mobile communications to provide not only mobile voice and data services, but also new mobile services.

[0078] In an actual application scenario, taking the filter algorithm as an example, the filter algorithm can eliminate interference factors in the signal, so that the filtered signal can better reflect the actual information of the signal. Figure 5 In this embodiment, the local server first calls the AI ​​software to query whether there is a new filter algorithm in the data cloud server, and when there is a new filter algorithm, the new filter algorithm is obtained, and the new filter algorithm is compared with the current filter algorithm by verifying the original data (i.e., the test data), that is, the code of the new filter algorithm and the code of the current filter algorithm are loaded into the test file respectively, and then the test file is run to obtain the performance test scores corresponding to the new filter algorithm and the current filter algorithm, and then the two performance test scores are compared to obtain the performance test comparison result. When the performance test score of the new filter algorithm is higher than the performance test score of the current filter algorithm, the new filter algorithm is compiled so that it can adapt to the vehicle controller, and then the new filter algorithm is downloaded to the vehicle controller through OTA technology, so that the vehicle controller can upgrade the filter algorithm.

[0079] The embodiment of the present invention provides an artificial intelligence-based vehicle software automatic upgrade method, which can be applied to the aforementioned data cloud server 200.

[0080] The data cloud server sends the new software of the target vehicle-mounted software to the local server, so that the local server compares the performance of the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and updates the target vehicle-mounted software deployed on the target vehicle according to the result of the performance comparison; wherein, the new software is sent by the data cloud server after the local server queries through the AI ​​application that the new software of the target vehicle-mounted software exists on the data cloud server; the target vehicle-mounted software is the software deployed on the target vehicle.

[0081] The embodiment of the present invention provides an automatic vehicle software upgrade method based on artificial intelligence, which can be applied to a vehicle controller 300.

[0082] Receive new software of the target vehicle-mounted software sent by the local server; the new software is obtained from the data cloud server after the local server queries the data cloud server through the AI ​​application program to find that the new software of the target vehicle-mounted software exists, and compares the performance of the new software with the current software of the target vehicle-mounted software deployed on the target vehicle, and sends it according to the result of the performance comparison; the target vehicle-mounted software is the software deployed on the target vehicle;

[0083] The current software deployed for the target vehicle software on the target vehicle is updated to the new software.

[0084] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed, the steps provided in the above embodiment can be implemented. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0085] The embodiment of the present invention also provides a computer device, which may include a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps provided in the above embodiment may be implemented. Of course, the computer device may also include various network interfaces, power supplies and other components.

[0086] An embodiment of the present invention further provides a computer program product, which, when executed by a processor, implements the above-mentioned method for automatic vehicle software upgrade based on artificial intelligence.

[0087] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

[0088] It should also be noted that, in this specification, relational terms such as first and second, etc. 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 these entities or operations. Moreover, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. An automatic vehicle software upgrade method based on artificial intelligence, It is characterized in that include: querying a data cloud server through an AI application whether there is new software of the target vehicle-mounted software, and in response to querying that the new software of the target vehicle-mounted software exists in the data cloud server, obtaining the new software from the data cloud server; The target vehicle software is the software deployed on the target vehicle; A performance comparison is performed between the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and the target vehicle-mounted software deployed on the target vehicle is updated according to the result of the performance comparison.

2. The method according to claim 1, It is characterized in that The querying of the data cloud server by the AI ​​application whether there is new software of the target vehicle software includes: The software keywords of the target vehicle-mounted software are determined through an AI application, and based on the software keywords, a query is made on a data cloud server matching the software keywords to determine whether there is new software for the target vehicle-mounted software; wherein the software keywords are pre-set in the AI ​​application, or the software keywords are determined according to the keyword information indicated by the user according to the AI ​​application.

3. The method according to claim 1, It is characterized in that The querying of the data cloud server by the AI ​​application whether there is new software of the target vehicle software also includes: When the conditions for automatic software update are triggered, the data cloud server is queried through the AI ​​application whether there is new software for the target vehicle software; wherein the conditions for triggering automatic software update include: reaching the periodic update periodic time, and / or the AI ​​application receives keyword information indicated by the user for the target vehicle software.

4. The method according to claim 1, It is characterized in that The performing of a performance comparison between the new software and the current software of the target vehicle software deployed on the target vehicle, and updating the target vehicle software deployed on the target vehicle according to the result of the performance comparison, comprises: In response to the result of the performance comparison being that the new software is better than the current software, the new software is sent to the onboard controller of the target vehicle, so that the onboard controller updates the current software deployed on the target vehicle for the target onboard software to the new software.

5. The method according to claim 1, It is characterized in that The comparing the performance of the new software and the current software deployed on the target vehicle with the target vehicle software further includes: Loading the code of the new software into a preset test file to perform a performance test and obtain a first performance test score; Loading the code of the current software deployed by the target vehicle-mounted software on the target vehicle into the test file to perform a performance test, and obtaining a second performance test score; A performance test comparison is performed between the new software and the current software according to the first performance test score and the second performance test score to obtain the performance test comparison result.

6. The method according to claim 5, It is characterized in that The first performance test score and the second performance test score are both one-dimensional performance test scores, or the first performance test score and the second performance test score are both multi-dimensional performance test scores; The performing a performance test comparison between the new software and the current software according to the first performance test score and the second performance test score to obtain the performance test comparison result includes: When the first performance test score and the second performance test score are one-dimensional performance test scores, the performance test comparison result is obtained directly according to the comparison result of the first performance test score and the second performance test score; When the first performance test score and the second performance test score are multidimensional performance test scores, the first performance test score is weighted by dimension to obtain a weighted first performance test score, and the second performance test score is weighted by dimension to obtain a weighted second performance test score, and the performance test comparison result is obtained based on the comparison result of the weighted first performance test score and the weighted second performance test score.

7. The method according to claim 5, It is characterized in that The step of loading the code of the new software into a preset test file for performance testing to obtain a first performance test score includes: Loading the code of the new software into a C file and an H file; wherein the C file and the H file are respectively stored in the local server, the C file is a source file of the C language, and the H file is a header file of the C language; Inputting the preset test data into the C file and the H file loaded with the code of the new software, and running the test according to the dimension to obtain the first performance test score; The step of loading the code of the current software deployed by the target vehicle-mounted software on the target vehicle into the test file for performance testing to obtain a second performance test score includes: Load the code of the current software into C files and H files; The preset test data is input into the C file and the H file loaded with the code of the current software, and the test is run by dimension to obtain the second performance test score.

8. The method according to claim 4, It is characterized in that In response to the result of the performance comparison being that the new software is better than the current software, sending the new software to the on-board controller of the target vehicle comprises: When the result of the performance comparison is that the new software is better than the current software, formatting the code of the new software so that the code format of the new software is adapted to the format of the target vehicle-mounted software deployed on the target vehicle; After the format compilation is completed, the new software is sent to the on-board controller of the target vehicle.

9. The method according to claim 4, It is characterized in that In response to the result of the performance comparison being that the new software is better than the current software, sending the new software to the on-board controller of the target vehicle also includes: The new software is transmitted to the onboard controller of the target vehicle by using over-the-air download technology, so that the onboard controller updates the current software deployed for the target onboard software on the target vehicle to the new software.

10. An automatic vehicle software upgrade method based on artificial intelligence, It is characterized in that Applied to data cloud servers, The data cloud server sends the new software of the target vehicle-mounted software to the local server, so that the local server compares the performance of the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and updates the target vehicle-mounted software deployed on the target vehicle according to the result of the performance comparison; wherein, the new software is sent by the data cloud server after the local server queries through the AI ​​application that the new software of the target vehicle-mounted software exists on the data cloud server; the target vehicle-mounted software is the software deployed on the target vehicle.

11. An automatic vehicle software upgrade method based on artificial intelligence, It is characterized in that Applied to vehicle controllers, Receive new software of the target vehicle-mounted software sent by the local server; the new software is obtained from the data cloud server after the local server queries the data cloud server through the AI ​​application program to find that the new software of the target vehicle-mounted software exists, and compares the performance of the new software with the current software of the target vehicle-mounted software deployed on the target vehicle, and sends it according to the result of the performance comparison; the target vehicle-mounted software is the software deployed on the target vehicle; The current software deployed for the target vehicle software on the target vehicle is updated to the new software.

12. An automatic vehicle software upgrade system based on artificial intelligence, It is characterized in that It includes local server, data cloud server and vehicle controller, including: The local server queries the data cloud server through the AI ​​application whether there is new software of the target vehicle-mounted software, and, in response to the query that the new software of the target vehicle-mounted software exists in the data cloud server, obtains the new software from the data cloud server; wherein the target vehicle-mounted software is the software deployed on the target vehicle; The data cloud server sends the new software of the target vehicle software to the local server; The local server obtains the new software of the target vehicle-mounted software, performs a performance comparison between the new software and the current software of the target vehicle-mounted software deployed on the target vehicle, and sends the new software of the target vehicle-mounted software to the vehicle-mounted controller according to the result of the performance comparison; The vehicle controller receives new software of the target vehicle software sent by the local server, and updates the current software deployed on the target vehicle for the target vehicle software to the new software.

13. A computer device, It is characterized in that It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for automatic vehicle software upgrade based on artificial intelligence as described in any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for automatically upgrading the vehicle software based on artificial intelligence as described in any one of claims 1 to 11 is implemented.

15. A computer program product, It is characterized in that When the computer program product is executed by a processor, the method for automatic vehicle software upgrade based on artificial intelligence as described in any one of claims 1 to 11 is implemented.

Images