A research method, medium and terminal device for automotive open source boundary based on large language model

Abstract

The present invention discloses a method, medium and terminal device for studying automobile open source boundaries based on a large language model. The present invention obtains first open source component information by performing static code analysis on extracted program files; performs large language model analysis on extracted engineering build files and configuration files to obtain second open source component information; performs automatic driving system firmware analysis and jointly uses SCA software component analysis technology to obtain third open source component information; performs large language model analysis on Apk configuration files to obtain fourth open source component information; and performs data merging and data deduplication on the first open source component information, the second open source component information, the third open source component information and the fourth open source component information. The method of using large model technology to parse the construction information of source code engineering and the configuration information in firmware to obtain open source component information improves the efficiency and effectiveness of obtaining open source information.

Description

Technical Field

[0001] The present invention belongs to the field of data processing, and in particular relates to an automobile open source boundary research method, medium and terminal equipment based on a large language model. Background Art

[0002] As the automobile becomes more intelligent, the vehicle safety monitoring function is receiving more and more attention. There are two main methods for dividing the automotive open source field: source code analysis and reverse engineering from automotive firmware. In the source code analysis method, it is necessary to analyze the engineering component files and source code files of the source code program. The source code files can determine the open source components used by string comparison. The open source code boundaries in the automotive software field are determined by the open source components found in the engineering component files and source code files. By determining the boundaries of automotive open source code, the software code risks of automotive products can be managed.

[0003] At present, in the field of automobile R&D, automobile engineering source code is the core asset of automobile companies or suppliers, and also represents part of the core competitiveness of enterprises, so it is very difficult to obtain automobile product engineering source code. When analyzing automobile engineering build files and automobile source code files, string comparison can be used to determine the open source projects used by automobile software. However, due to the large number of open source projects, complex structure of engineering component files, and numerous types of source code languages ​​and framework interfaces, it is difficult to write string comparison rules, and it is very easy to miss open source components. Summary of the invention

[0004] At present, the original data source used for analysis, that is, the automotive engineering source code, is obtained through automotive alliance research and open source project search, with Android Automotive, ROS, ROS2, Automotive Grade Linux, openQNX, and openHarmony project source code as the research data source. Among them, Android Automotive, Automotive Grade Linux, and openHarmony are commonly used basic source code projects in the smart cockpit domain; ROS and ROS2 are basic source code projects used in the early stage of the autonomous driving domain, and openQNX is the basic source code project for the instrument system. In this way, the data source for the source code research is determined. However, the selected source code data source does not include the traditional ECU development part, so the research on Autosar and actuator ECU is not included in this study. Also because the concept of open source is often not involved in the engineering of Autosar and actuator ECU.

[0005] In order to expand the open source projects of application layer software in the smart cockpit domain and the open source projects of application layer software in the autonomous driving domain (advanced assisted driving domain), the firmware reverse analysis method is added to the overall research method. This method is only used to reverse Baidu Apollo autonomous driving system, Mobileye autonomous driving system, Huawei ADS, and BYD DiPilot intelligent driving assistance system. By reversing these autonomous driving related system software, the open source scope related to autonomous driving in automotive software can be expanded. The application layer software in the smart cockpit system mainly exists in the form of in-vehicle application apps, which also use open source software to build applications. Therefore, the open source scope related to smart cockpit applications can be expanded by reverse analyzing the IVI system applications of various models.

[0006] Large models, or large language models (LLM), refer to language models that contain tens of billions or more parameters and are trained with large-scale text data. By expanding the number of parameters and data in the pre-trained language model, the large language model can significantly improve the effect while having the ability to understand natural language and solve complex tasks through text generation. Commonly used LLM models include GPT-4, Bard, Turing-NLG, LLaMa, etc. With the help of large language models, it is mainly used to identify automotive engineering build files and source code files. The identified source code files are then merged, and the results are used as the scope of automotive software open source components.

[0007] The technical solution adopted by the present invention to solve the above technical problems is:

[0008] The present invention provides a method for studying automobile open source boundaries based on a large language model, the method comprising the following steps:

[0009] S1. According to the type of vehicle, obtain the source code engineering files of the vehicle, the in-vehicle infotainment (IVI) system firmware, and the automatic driving system firmware;

[0010] S2. Classify the automobile source code engineering files according to the file suffixes to obtain program files, engineering build files and configuration files;

[0011] S3, performing SAST static code analysis on the extracted program file to obtain first open source component information;

[0012] S4, performing large language model parsing on the extracted project build files and configuration files to obtain second open source component information;

[0013] S5, parsing the IVI system firmware and extracting the apk file and the jar file;

[0014] S6. Analyze the firmware of the autonomous driving system and use the SCA software component analysis technology together with the jar file extracted from the IVI system firmware to obtain the third open source component information;

[0015] S7. Decompress the apk file and extract the configuration file, which includes xml, pom, build, gradle, and depended files;

[0016] S8,Apk’s configuration file is parsed by the large language model to obtain the fourth open source component information;

[0017] S9, after merging and deduplicating the first open source component information, the second open source component information, the third open source component information, and the fourth open source component information, obtain the automotive software open source component scope information;

[0018] Furthermore, the automotive source code engineering files include Android Automotive, ROS, ROS2, AutomotiveGrade Linux, openQNX, and openHarmony project source codes;

[0019] Furthermore, IVI system firmware includes open source components for expanding the scope of in-vehicle application app development technology.

[0020] Furthermore, the autonomous driving systems include Baidu Apollo autonomous driving system, Mobileye autonomous driving system, Huawei ADS, and BYD DiPilot intelligent driving assistance system;

[0021] Furthermore, the extracted program files are subjected to SAST static code analysis, and the first open source component information obtained includes:

[0022] S31, collecting program files to be analyzed, including source code, header files, and library files;

[0023] S32. According to Checkmarx, set up the tool's scanning rules, including custom rules and checks, to identify open source components and related licenses;

[0024] S33. Scan the code base and generate a report, and extract the first open source component information from the report, where the first open source component information includes component name, version, license type, and usage location.

[0025] Furthermore, the extracted project build files and configuration files are parsed using a large language model to obtain the second open source component information including:

[0026] S41. Obtain the Makefile, CMakeLists.txt, build.gradle, pom.xml, and package.json files in the project build files and configuration files;

[0027] S42, preprocessing the file, including removing comments, blank lines, and special characters, and dividing the file content into manageable segments, such as function calls and dependency declarations;

[0028] S43, extract key features such as dependency name, version number, license statement,

[0029] S44. Select a large language model, use a pre-trained model, and fine-tune it on relevant datasets.

[0030] S45, inputting the preprocessed file into the fine-tuned large language model to obtain open source component information;

[0031] S46: Compare and merge the information obtained by model analysis with the existing open source component database to obtain second open source component information.

[0032] Furthermore, the large language model is the LLAMA2 model;

[0033] Furthermore, the LLAMA2 model training process includes:

[0034] S441, collecting pre-training data in a preset format in the project build file and the configuration file;

[0035] S442, performing word segmentation processing on the pre-trained data in the predetermined format according to the word segmenter;

[0036] S443. Pre-train the LLAMA2 basic model based on the word segmentation results.

[0037] S443, fine-tuning the instructions of the LLAMA2 basic model using the fine-tuning data to obtain a first language model;

[0038] Similarly, the second language model for the configuration file of Apk is generated according to the same process;

[0039] Furthermore, the IVI system firmware is parsed and the apk and jar files extracted include:

[0040] S51, obtaining the firmware image of the IVI system; using the virtual machine to mount the image file, browsing the mounted file system, and identifying the directory containing the APK and JAR files;

[0041] S52, analyzing the dependency relationship between the APK and JAR files by analyzing the AndroidManifest.xml file or viewing the build.gradle file of the project;

[0042] Furthermore, the firmware of the autonomous driving system is parsed, and the SCA software component analysis technology is used together with the jar file extracted from the IVI system firmware to obtain the third open source component information including:

[0043] S61. For the automatic driving system firmware, extract the executable file, library file, and configuration file;

[0044] S62. Configure the SCA tool, including defining the file types to be scanned, setting the scan scope and depth, and configuring the report output format;

[0045] S63. Run the SCA tool to scan the JAR files in the autonomous driving system firmware and the IVI system firmware.

[0046] Furthermore, after merging and deduplicating the first open source component information, the second open source component information, the third open source component information, and the fourth open source component information, the automotive software open source component scope information includes:

[0047] S91. Merge open source component information from different sources into a unified database or dataset;

[0048] S92, identifying and deleting duplicate component records. The component records include a comparison of component names, versions, and license information; wherein a hash function or similarity algorithm is used to assist in identifying duplicate items;

[0049] S93. Verify the merged data.

[0050] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and a processor executes the computer program to implement an automobile open source boundary research method based on a large language model.

[0051] The present invention provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement an automobile open source boundary research method based on a large language model.

[0052] The beneficial effects of the present invention are as follows:

[0053] 1) A method of using big model technology to parse the build information of source code projects and the configuration information in firmware to obtain open source component information improves the efficiency and effectiveness of obtaining open source information.

[0054] 2) By setting up multi-source automotive open source information acquisition, the efficiency and accuracy of depicting the scope of automotive software open source components can be improved and the false negative rate can be reduced.

[0055] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above description and other purposes, features and advantages of the present invention more obvious and easy to understand, the preferred embodiments are specifically cited and described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0057] Figure 1 A flowchart of a method for studying automobile open source boundaries based on a large language model provided by the present invention;

[0058] Figure 2 A schematic diagram of the structure of a terminal device provided by the present invention. DETAILED DESCRIPTION

[0059] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0060] In the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be connected, detachably connected, or integrated; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] Example 1

[0062] like Figure 1 As shown, the present invention provides a method for studying automobile open source boundaries based on a large language model, and the method comprises the following steps:

[0063] S1. According to the type of vehicle, obtain the source code engineering files of the vehicle, the in-vehicle infotainment (IVI) system firmware, and the automatic driving system firmware;

[0064] S2. Classify the automobile source code engineering files according to the file suffixes to obtain program files, engineering build files and configuration files;

[0065] S3, performing SAST static code analysis on the extracted program file to obtain first open source component information;

[0066] S4, performing large language model parsing on the extracted project build files and configuration files to obtain second open source component information;

[0067] S5, parsing the IVI system firmware and extracting the apk file and the jar file;

[0068] S6. Analyze the firmware of the autonomous driving system and use the SCA software component analysis technology together with the jar file extracted from the IVI system firmware to obtain the third open source component information;

[0069] S7. Decompress the apk file and extract the configuration file, which includes xml, pom, build, gradle, and depended files;

[0070] S8,Apk’s configuration file is parsed by the large language model to obtain the fourth open source component information;

[0071] S9, after merging and deduplicating the first open source component information, the second open source component information, the third open source component information, and the fourth open source component information, obtain the automotive software open source component scope information;

[0072] Furthermore, the automotive source code engineering files include Android Automotive, ROS, ROS2, AutomotiveGrade Linux, openQNX, and openHarmony project source codes;

[0073] Furthermore, IVI system firmware includes open source components for expanding the scope of in-vehicle application app development technology.

[0074] Furthermore, the autonomous driving systems include Baidu Apollo autonomous driving system, Mobileye autonomous driving system, Huawei ADS, and BYD DiPilot intelligent driving assistance system;

[0075] Furthermore, the extracted program files are subjected to SAST static code analysis, and the first open source component information obtained includes:

[0076] S31, collecting program files to be analyzed, including source code, header files, and library files;

[0077] S32. According to Checkmarx, set up the tool's scanning rules, including custom rules and checks, to identify open source components and related licenses;

[0078] S33. Scan the code base and generate a report, and extract the first open source component information from the report, where the first open source component information includes component name, version, license type, and usage location.

[0079] Furthermore, the extracted project build files and configuration files are parsed using a large language model to obtain the second open source component information including:

[0080] S41. Obtain the Makefile, CMakeLists.txt, build.gradle, pom.xml, and package.json files in the project build files and configuration files;

[0081] S42, preprocessing the file, including removing comments, blank lines, and special characters, and dividing the file content into manageable segments, such as function calls and dependency declarations;

[0082] S43, extract key features such as dependency name, version number, license statement,

[0083] S44. Select a large language model, use a pre-trained model, and fine-tune it on relevant datasets.

[0084] S45, inputting the preprocessed file into the fine-tuned large language model to obtain open source component information;

[0085] S46: Compare and merge the information obtained by model analysis with the existing open source component database to obtain second open source component information.

[0086] Furthermore, the large language model is the LLAMA2 model;

[0087] Furthermore, the LLAMA2 model training process includes:

[0088] S441, collecting pre-training data in a preset format in the project build file and the configuration file;

[0089] S442, performing word segmentation processing on the pre-trained data in the predetermined format according to the word segmenter;

[0090] S443. Pre-train the LLAMA2 basic model based on the word segmentation results.

[0091] S443, fine-tuning the instructions of the LLAMA2 basic model using the fine-tuning data to obtain a first language model;

[0092] Similarly, the second language model for the configuration file of Apk is generated according to the same process;

[0093] Furthermore, the IVI system firmware is parsed and the apk and jar files extracted include:

[0094] S51, obtaining the firmware image of the IVI system; using the virtual machine to mount the image file, browsing the mounted file system, and identifying the directory containing the APK and JAR files;

[0095] S52, analyzing the dependency relationship between the APK and JAR files by analyzing the AndroidManifest.xml file or viewing the build.gradle file of the project;

[0096] Furthermore, the firmware of the autonomous driving system is parsed, and the SCA software component analysis technology is used together with the jar file extracted from the IVI system firmware to obtain the third open source component information including:

[0097] S61. For the automatic driving system firmware, extract the executable file, library file, and configuration file;

[0098] S62. Configure the SCA tool, including defining the file types to be scanned, setting the scan scope and depth, and configuring the report output format;

[0099] S63. Run the SCA tool to scan the JAR files in the autonomous driving system firmware and the IVI system firmware.

[0100] Furthermore, after merging and deduplicating the first open source component information, the second open source component information, the third open source component information, and the fourth open source component information, the automotive software open source component scope information includes:

[0101] S91. Merge open source component information from different sources into a unified database or dataset;

[0102] S92, identifying and deleting duplicate component records. The component records include a comparison of component names, versions, and license information; wherein a hash function or similarity algorithm is used to assist in identifying duplicate items;

[0103] S93. Verify the merged data.

[0104] The beneficial effects of the present invention are as follows:

[0105] 1) A method of using big model technology to parse the build information of source code projects and the configuration information in firmware to obtain open source component information improves the efficiency and effectiveness of obtaining open source information.

[0106] 2) By setting up multi-source automotive open source information acquisition, the efficiency and accuracy of depicting the scope of automotive software open source components can be improved and the false negative rate can be reduced.

[0107] Example 2

[0108] The present invention provides a terminal device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method. The at least one processor in the terminal device can execute the above method, and thus has at least the same advantages as the above method.

[0109] Optionally, the terminal device also includes interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors can be used together with multiple memories, and / or multiple buses can be used together with multiple memories. Similarly, multiple electronic devices can be connected (for example, as a server array, a group of blade servers, or a multi-processor system), and each device provides some necessary operations. Figure 2 A processor 301 is taken as an example.

[0110] The memory 302 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the automotive open source boundary research method based on a large language model in the embodiment of the present invention. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 302, that is, realizing the above-mentioned automotive open source boundary research method based on a large language model.

[0111] The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0112] The terminal device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303 and the output device 304 may be connected via a bus or other means. Figure 2 The example of connecting through bus is taken in the following.

[0113] The input device 303 can receive input digital or character information, and the output device 304 can include a display device, an auxiliary lighting device (e.g., LED), and a tactile feedback device (e.g., a vibration motor), etc. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0114] Example 3

[0115] This embodiment provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable the computer to execute the above method. The computer instructions on the computer-readable storage medium are used to enable the computer to execute the above method, and thus have at least the same advantages as the above method.

[0116] The medium in the present invention may adopt any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of the medium (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0117] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0118] The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0119] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0120] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for studying the boundaries of automotive open source based on a large language model, characterized in that: The method comprises the following steps: S1. Obtain the source code engineering files, in-vehicle infotainment IVI system firmware, and autonomous driving system firmware of the vehicle according to the vehicle type; S2. Classify the automobile source code engineering files according to the file suffixes to obtain program files, engineering build files and configuration files; S3, performing SAST static code analysis on the extracted program file to obtain first open source component information; The extracted program files are subjected to SAST static code analysis, and the first open source component information obtained includes: S31, collecting program files to be analyzed, including source code, header files, and library files; S32. According to Checkmarx, set up the tool's scanning rules, including custom rules and checks, to identify open source components and related licenses; S33, scanning the code base and generating a report, extracting first open source component information from the report, where the first open source component information includes component name, version, license type, and usage location; S4, performing large language model parsing on the extracted project build files and configuration files to obtain second open source component information; S5, parsing the IVI system firmware and extracting the apk file and the jar file; S6. Analyze the firmware of the autonomous driving system and use the SCA software component analysis technology together with the jar file extracted from the IVI system firmware to obtain the third open source component information; S7. Decompress the apk file and extract the configuration file, which includes xml, pom, build, gradle, and depended files; S8,Apk’s configuration file is parsed by the large language model to obtain the fourth open source component information; S9. After merging and deduplicating the first open source component information, the second open source component information, the third open source component information, and the fourth open source component information, the automotive software open source component scope information is obtained.

2. The automotive open source boundary research method based on a large language model according to claim 1 is characterized by: The automotive source code engineering files include Android Automotive, ROS, ROS2, Automotive Grade Linux, openQNX, and openHarmony project source codes.

3. The automotive open source boundary research method based on a large language model according to claim 1 is characterized by: IVI system firmware, including open source components for expanding the scope of in-vehicle application app development technology.

4. The automotive open source boundary research method based on a large language model according to claim 1 is characterized by: The autonomous driving systems include Baidu Apollo autonomous driving system, Mobileye autonomous driving system, Huawei ADS, and BYD DiPilot intelligent driving assistance system.

5. The automotive open source boundary research method based on a large language model according to claim 1 is characterized by: The extracted project build files and configuration files are parsed using a large language model to obtain the second open source component information including: S41. Obtain the Makefile, CMakeLists.txt, build.gradle, pom.xml, and package.json files in the project build files and configuration files; S42, preprocessing the file, including removing comments, blank lines, and special characters, and dividing the file content into manageable segments, such as function calls and dependency declarations; S43, extract key features such as dependency name, version number, license statement, S44. Select a large language model, use a pre-trained model, and fine-tune it on relevant datasets. S45, inputting the preprocessed file into the fine-tuned large language model to obtain open source component information; S46: Compare and merge the information obtained by model analysis with the existing open source component database to obtain second open source component information.

6. The automotive open source boundary research method based on a large language model according to claim 1 is characterized by: Parse the IVI system firmware and extract the apk and jar files including: S51, obtaining the firmware image of the IVI system; using the virtual machine to mount the image file, browsing the mounted file system, and identifying the directory containing the APK and JAR files; S52. Analyze the dependencies between the APK and JAR files by analyzing the AndroidManifest.xml file or viewing the project's build.gradle file.

7. The automotive open source boundary research method based on a large language model according to claim 1 is characterized by: The firmware of the autonomous driving system is parsed, and together with the jar file extracted from the IVI system firmware, the SCA software component analysis technology is used to obtain the third open source component information including: S61. For the automatic driving system firmware, extract the executable file, library file, and configuration file; S62. Configure the SCA tool, including defining the file types to be scanned, setting the scan scope and depth, and configuring the report output format; S63. Run the SCA tool to scan the JAR files in the autonomous driving system firmware and the IVI system firmware to obtain the third open source component information.

8. A computer-readable storage medium storing a computer program, characterized in that: The processor executes the computer program to implement the automotive open source boundary research method based on a large language model as described in any one of claims 1-7.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes the computer program to implement the automotive open source boundary research method based on a large language model as described in any one of claims 1-7.

Images