Perception log analysis method based on vehicle-mounted domain controller and related equipment

Abstract

The invention provides a perceptual log analysis method based on a vehicle-mounted domain controller and related equipment, and the method comprises the steps: obtaining perceptual data from the vehicle-mounted domain controller, and recording the perceptual data to a log file; analyzing the log files in different formats, and extracting at least one type of performance parameters related to system performance and corresponding historical numerical values from the log files; based on each extracted performance parameter and the corresponding historical numerical value, generating a time sequence data set according to timestamp sorting; and carrying out visual display on the time series data set to display the trend of each performance parameter changing along with time. According to the method, the key performance parameters of the domain controller are extracted by adopting an automatic log analysis technology and are visually displayed, so that manual intervention is reduced, the extraction accuracy of the key performance parameters is improved, and the data processing process is accelerated. And the running state and the performance trend of the system can be visually presented, so that developers can conveniently monitor and optimize the performance of the system.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a perception log analysis method and related devices based on an in-vehicle domain controller. Background Art

[0002] With the rapid development of intelligent driving technology, in-vehicle computing platforms are gradually evolving from a distributed electronic control unit architecture to a centralized domain controller architecture to improve computing efficiency, data processing capabilities, and system stability. Currently, domain controllers are increasingly widely used in intelligent driving systems, and various in-vehicle domain controllers have been developed by different manufacturers to support functions such as autonomous driving and ADAS (Advanced Driving Assistance System). During the development and optimization of domain controllers, they need to be deployed on actual vehicles, tested under different road environments and driving conditions, and the perception data recorded during operation is analyzed to evaluate system performance, optimize computing resource allocation, and ensure the stability and reliability of the perception system.

[0003] Log analysis tools are mostly developed by specific manufacturers for their own products and are difficult to be compatible with domain controllers of different architectures. Since domain controllers of different manufacturers use different log formats and data storage methods, existing log analysis methods mostly rely on manual parsing or simple text queries, making it difficult to efficiently extract key perception data. At the same time, the lack of graphical processing capabilities for perception data affects the intuitive judgment and optimization of system status by developers. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, this application provides a perception log analysis method and related devices based on an in-vehicle domain controller to at least solve problems such as low data extraction efficiency and insufficient data visualization ability in the existing technology.

[0005] To achieve the above objectives and other advantages, this application is implemented by adopting the following technical solutions:

[0006] In a first aspect, this application provides a perception log analysis method based on an in-vehicle domain controller, including:

[0007] Obtain perception data from the in-vehicle domain controller and record it in a log file;

[0008] Parse the log files in different formats and extract at least one type of performance parameter related to system performance and the corresponding historical values from the log files;

[0009] Based on each of the extracted performance parameters and the corresponding historical values, generate a time series data set sorted by timestamp;

[0010] Visualize the time series data set to show the trend of each performance parameter changing over time.

[0011] According to a perception log analysis method based on a vehicle-mounted domain controller provided by the present application, the performance parameters include at least one type of the average frame rate and latency of the camera, the operating frequency and utilization rate of the computing unit, and temperature information.

[0012] According to a perception log analysis method based on a vehicle-mounted domain controller provided by the present application, the step of parsing the log files in different formats and extracting at least one type of performance parameter related to system performance and the corresponding historical values from the log files includes:

[0013] Identify the log format by analyzing the file header or file name suffix of the log file;

[0014] According to different log formats, adopt different data field extraction rules to extract performance parameters and the corresponding historical values from multiple log data of the log file;

[0015] Verify whether the values of the performance parameters conform to the corresponding data format specifications, and mark or fill in the missing or abnormal data.

[0016] According to a perception log analysis method based on a vehicle-mounted domain controller provided by the present application, the log formats include structured, semi-structured, and unstructured;

[0017] For log files in structured format, extract perception data according to the field name matching rule;

[0018] For log files in semi-structured format, extract perception data according to the keyword matching rule;

[0019] For log files in unstructured format, extract perception data based on natural language processing technology or regular expressions.

[0020] According to a perception log analysis method based on a vehicle-mounted domain controller provided by the present application, the step of generating a time series data set by sorting according to the time stamp based on each of the extracted performance parameters and the corresponding historical values includes:

[0021] Parse the time stamps of each log data containing the performance parameters, and standardize different formats of time stamps;

[0022] Based on the historical values extracted for each performance parameter, sort the data in ascending order according to the standardized time stamps to form a time series data set;

[0023] Use data interpolation method to complete the missing data points in the time series dataset;

[0024] Use a denoising algorithm to smooth the time series dataset.

[0025] According to a perception log analysis method based on a vehicle-mounted domain controller provided by the present application, it further includes:

[0026] Perform statistical analysis on the time series dataset to calculate the average value, maximum value, and minimum value of each performance parameter, and mark them in the visualization graph.

[0027] According to a perception log analysis method based on a vehicle-mounted domain controller provided by the present application, it further includes:

[0028] Classify and store the time series dataset according to different test conditions;

[0029] Allow users to retrieve the time series dataset within a specified time period or under a specific test environment through a query interface;

[0030] Conduct comparative analysis based on historical data to evaluate the performance of the domain controller under different working conditions.

[0031] In a second aspect, the present application provides an electronic device, and the electronic device includes:

[0032] One or more processors; and a memory storing computer program instructions, and when the computer program instructions are executed, the processors execute the perception log analysis method based on a vehicle-mounted domain controller as described in any one of the above.

[0033] In a third aspect, the present application provides a computer-readable storage medium, on which computer programs / instructions are stored, and when the computer programs / instructions are executed by a processor, the perception log analysis method based on a vehicle-mounted domain controller as described in any one of the above is implemented.

[0034] In a fourth aspect, the present application provides a computer program product, including computer programs / instructions, and when the computer programs / instructions are executed by a processor, the perception log analysis method based on a vehicle-mounted domain controller as described in any one of the above is implemented.

[0035] A method and related devices for analyzing perception logs based on an in-vehicle domain controller provided by this application obtain perception data from the in-vehicle domain controller and record it in a log file; parse log files in different formats, and extract at least one type of performance parameter related to system performance and corresponding historical values from the log file; generate a time series data set sorted by timestamp based on each extracted performance parameter and corresponding historical value; perform visual display on the time series data set to display the trend of each performance parameter changing over time. This application uses automated log parsing technology to extract key performance parameters of the domain controller and perform visual display, reducing manual intervention, improving the extraction accuracy of key performance parameters, and accelerating the data processing process. And it enables the system operation status and performance trend to be intuitively presented, facilitating developers to monitor and optimize system performance. It improves the management efficiency of in-vehicle domain controller log data. It provides important data support for the optimization of autonomous driving and ADAS systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] To more clearly illustrate the technical solutions in the embodiments of this application, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these drawings.

[0037] Figure 1 is a flowchart of the method for analyzing perception logs based on an in-vehicle domain controller provided by the embodiments of this application;

[0038] Figure 2 is a sample log file containing multiple performance parameters provided by the embodiments of this application;

[0039] Figure 3 is a graph showing the change in the average frame rate of the camera in the visual display provided by the embodiments of this application;

[0040] Figure 4 is a graph showing the change in the camera delay time in the visual display provided by the embodiments of this application;

[0041] Figure 5 is a graph showing the change in the temperature of the domain controller in the visual display provided by the embodiments of this application;

[0042] Figure 6 is a schematic structural diagram of an electronic device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following preferred embodiments are specifically given, and in conjunction with the accompanying drawings, the details are described as follows.

[0044] It should be noted that those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in this application can be combined with other embodiments without conflict. Unless otherwise defined, the technical terms or scientific terms involved in this application should be the ordinary meanings understood by those with general skills in the technical field to which this application belongs. The similar terms such as "a", "an", "one kind", "the" involved in this application do not indicate a quantity limit and can represent a single or plural number. The terms "including", "comprising", "having" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; the terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0045] Refer to Figure 1 As shown, an embodiment of this application provides a perception log analysis method based on a vehicle-mounted domain controller, including:

[0046] Step S1: Obtain perception data from the vehicle-mounted domain controller and record it in a log file.

[0047] Specifically, the vehicle-mounted domain controller (DCU) establishes a communication connection with sensor devices (such as cameras, radars, lidars, IMU sensors, etc.) through a communication bus (such as CAN bus, Ethernet, gigabit multimedia serial link, etc.). The vehicle-mounted domain controller periodically obtains perception data by calling the sensor data interface or the driver layer API. For example, the sampling frequency of the data can be set to sample once per second. These perception data record important perception information such as temperature information, the computing load information of the computing unit (such as the operating frequency and usage rate of the CPU and BPU), the average frame rate and latency time of the camera, etc.

[0048] There may be differences in the data acquisition times of different sensors. Therefore, timestamp synchronization is required to ensure the temporal consistency of the data.

[0049] According to the requirements of the log record format, write the collected perception data into a log file. The storage format can be structured storage (JSON, CSV, XML file formats, which are convenient for parsing) or semi-structured storage (TXT file format, which records in the form of timestamp + key-value pairs). Or without format conversion, directly record the perception data of the domain controller in the form of a raw text file and store it as complete log data.

[0050] Adopt a rolling log recording mechanism. When the log file reaches the set size or time interval, the system automatically creates a new log file to prevent data storage overflow.

[0051] In this embodiment, the performance parameters include at least one type of the average frame rate and latency of the camera, the operating frequency and utilization rate of the computing unit, and temperature information.

[0052] It should be noted that in the design and optimization process of the in-vehicle domain controller (DCU), multiple core performance parameters directly affect the reliability, real-time performance, and safety of the system. For example, for the intelligent driving domain controller used in autonomous driving or advanced driver assistance systems (ADAS), this domain controller is mainly used for processing intelligent driving perception data. Its temperature management, CPU (Central Processing Unit) load, BPU (Brain Processing Unit) computing power, and camera frame rate play a crucial role in the real-time performance, reliability, and safety of the system. Specifically, the temperature management of the domain controller is of crucial importance in the system of the domain controller, directly affecting the reliability, performance, and lifespan of its system. This is a key factor that must be considered in the design of the domain controller. The CPU utilization rate of the domain controller is closely related to the system's response time. When the CPU utilization rate is high, the system's response time may increase, especially when dealing with complex calculations or multiple tasks are executed simultaneously. This will lead to a decrease in the real-time performance of the system, which may cause an increase in the latency of autonomous driving or advanced driver assistance systems, posing a great safety hazard during the actual driving process. The influence of the operating frequency and utilization rate of the BPU is similar to that of the CPU. The BPU is mainly responsible for executing complex AI algorithms, especially object detection and path planning in intelligent driving. Its operating frequency and computing power directly affect the intelligent level of the system. The core sensing device of the domain controller is the camera, and its frame rate (FPS) determines the environmental perception ability of the autonomous driving system. A series of driving schemes can only be executed through the camera, and the frame rate of the camera needs to be maintained within a reasonable range. A lower frame rate will increase the system's untimely response to dynamic scenes, resulting in perception latency, which may pose a safety hazard when the vehicle is driving at high speed or in complex road conditions. In autonomous driving or advanced driver assistance systems, these factors determine whether the system can operate stably in a complex driving environment and avoid safety hazards.

[0053] In other embodiments, different performance parameters can be selected for monitoring and analysis according to different types of domain controllers.

[0054] Step S2: Parse log files in different formats and extract at least one type of performance parameter related to system performance and its corresponding historical values from the log files.

[0055] In this embodiment, step S2 specifically includes:

[0056] Step S201: Identify the log format by analyzing the file header or file name suffix of the log file.

[0057] Specifically, since domain controllers of different manufacturers adopt different log formats and data storage methods. During the parsing process, the log format is first identified to ensure compatibility with domain controllers of different manufacturers. The file formats of log files usually have fixed extensions, such as *.log, *.txt, *.csv, *.json, *.xml, etc. Some log files contain format descriptions at the beginning. For example, XML format usually starts with "<?xml version = "1.0" encoding = "UTF-8"?". After identifying the log format, the system classifies it into structured logs, semi-structured logs, and unstructured logs. This can be compatible with different log formats, applicable to domain controllers of different manufacturers, enhancing the data adaptation ability. Cross-platform data parsing and general analysis can be achieved.

[0058] Step S202: According to different log formats, adopt different data field extraction rules to extract performance parameters and corresponding historical values from multiple log data in the log file.

[0059] For log files in structured format, extract perception data according to the field name matching rule;

[0060] For log files in semi-structured format, extract perception data according to the keyword matching rule;

[0061] For log files in unstructured format, extract perception data based on natural language processing technology or regular expressions.

[0062] Specifically, structured logs are usually stored in formats such as JSON, XML, CSV, etc. The data fields are clear and suitable for directly matching fields to extract perception data. For example, use a recursive traversal method to parse a multi-layer nested JSON data structure and extract parameter values according to the preset field name matching rule. For CSV format logs, use column name indexing to extract parameter values according to the preset field name.

[0063] Semi-structured format logs are usually stored in key-value pairs (Key-Value) or fixed format text. The data fields are relatively standardized, but there is no standardized structure, such as Figure 2As shown in the figure. The key-value pair data can be extracted by using the keyword matching + delimiter parsing method. Taking the captured performance parameter: Average FPS as an example. Create a data list for storing the captured average frame rate data. For the specified log file, read the data line by line in read-only mode. Check whether each line contains the keyword "average". If the keyword is found, it is considered that the line contains the average frame rate data of the camera. Extract the frame rate data from a specific element position in the line and remove irrelevant characters (such as commas). Convert the extracted parameter value to a floating point number and store it in the data list.

[0064] Unstructured format logs are usually in free text format and do not have fixed field identifiers. Data extraction needs to be based on natural language processing (NLP) techniques or regular expressions. In this way, through different parsing methods, it is possible to ensure the accurate extraction of performance parameters and their corresponding parameter values from log files in various formats.

[0065] Step S203: Verify whether the numerical values of the performance parameters conform to the corresponding data format specifications, and mark or fill in the missing or abnormal data.

[0066] Specifically, for performance parameters such as average frame rate and latency time, their data type should be floating point numbers. If it is found during verification that it is a non-floating point character type, it is marked as abnormal and needs to be converted to a floating point character type. For the CPU usage performance parameter, if it is found during verification that the numerical value contains the unit "%", it is marked as abnormal and the unit symbol needs to be removed. For the BPU operating frequency performance parameter, if it is found during verification that the numerical value is "800MHz", it is marked as abnormal and the unit needs to be removed and converted to the integer "800000000". If some data points are missing, interpolation algorithms or default values can be used for filling. This ensures the accuracy and integrity of the data and prevents abnormal data from affecting subsequent calculations and visual displays.

[0067] Step S3: Based on each extracted performance parameter and its corresponding historical values, generate a time series data set sorted by timestamp.

[0068] In this embodiment, step S3 specifically includes:

[0069] Step S301: Parse the timestamps of each log data containing performance parameters and standardize timestamps in different formats;

[0070] Step S302: Based on the historical values extracted for each performance parameter, sort the data in ascending order according to the standardized timestamps to form a time series data set;

[0071] Step S303: Use data interpolation methods to fill in the missing data points in the time series data set;

[0072] Step S304: Smooth the time series data set using a denoising algorithm.

[0073] Specifically, parse the timestamps in each log data, and uniformly convert timestamps in different formats into a standard format to ensure data consistency. Sort the values of each extracted performance parameter in ascending order according to the standardized timestamps to ensure that the time series data is arranged in increasing order of time. After sorting the timestamps, an ordered time series data set is formed. Since the sensed data recorded in the log file may have inconsistent sampling times and some time points may be missing, an interpolation algorithm needs to be used to complete the data. For the case of uniform time intervals, linear interpolation can be used to complete the missing data. The data may have noise points due to sensor jitter, measurement errors, etc., and smoothing processing is required. The mean value of the data can be calculated using a sliding window to eliminate sudden outliers. The smoothed data is more representative, reducing the influence of sensor noise and improving the accuracy of system performance analysis.

[0074] Step S4: Visualize the time series data set to show the trend of each performance parameter over time.

[0075] Specifically, for different types of performance data, select appropriate visualization charts. A line chart can be used to show the trends of the temperature of the domain controller, the average frame rate of the camera, and the latency over time; a bar chart can also be used to show the fluctuations in the computing unit load (CPU load, BPU load).

[0076] Exemplarily, in a Python environment, using the interactive data visualization libraries Plotly or Dash, line charts, bar charts, scatter plots, heatmaps, etc. can be drawn. The drawn charts support mouse hover to display data, support zooming in, zooming out, and dragging operations, and are suitable for time series analysis. The drawn charts support display on pages such as Jupyter Notebook and the Web. Plotly can be used for offline analysis of data trends, and Dash can be used for online monitoring of system status. If only interactive visualization charts need to be drawn (such as CPU load trends, camera FPS changes), Plotly can be used, which is suitable for local analysis and JupyterNotebook display. If a complete Web dashboard needs to be built to real-time monitor data such as the load of the computing unit, the average frame rate and latency of the camera, and the temperature, then Dash is used for server-side deployment and remote data visualization. Plotly charts can also be embedded in the Dash page to achieve remote interaction and real-time data visualization.

[0077] In this embodiment, visualizing the time series data set further includes:

[0078] Perform statistical analysis on the time series dataset to calculate the average, maximum, and minimum values of each performance parameter, and identify them in the visualization graph. In the graph, use a horizontal line to mark the average level of the entire time series for the average value. Highlight the maximum and minimum values to emphasize possible high-load and low-load states. Alternatively, mark the key statistical values in the visualization graph as a title. By identifying the key statistical values in the graph, it is convenient for users to intuitively observe the performance change range and anomalies of the system.

[0079] Among them, for the analysis of the average frame rate (Average Fps) of the camera, its visualization graph is as Figure 3 shown. It can be seen from the graph that the average frame rate of the domain controller camera almost fluctuates in the range of 19 to 25. Looking at the entire curve, its fluctuation is relatively stable. When the road conditions are good, the frame rate of the camera will show a relatively large value. On the contrary, when dealing with complex road conditions, the frequency of the camera is lower.

[0080] For the analysis of the delay time (Delay) of the camera, its visualization graph is as Figure 4 shown. It can be seen from the graph that when dealing with good road conditions, the camera does not need to perform much processing at this time, so its delay will be lower. When dealing with complex road conditions, the delay of the camera will increase. This also corresponds to the average frame rate of the camera. When the average frame rate of the camera is relatively large, its delay will be lower, and when the average frame rate of the camera is relatively small, its delay will increase.

[0081] For the analysis of the temperature (Temprature) of the domain controller, its visualization graph is as Figure 5 shown. It can be seen from the graph that the temperature of the domain controller gradually increases with time because the system is in operation, so the temperature will keep increasing. Based on this temperature change situation, it is helpful to better design the temperature management plan to optimize the product and reduce risks.

[0082] In this embodiment, it further includes:

[0083] Classify and store the time series dataset according to different test conditions;

[0084] Allow users to retrieve the time series dataset for a specified time period or a specific test environment through the query interface;

[0085] Conduct comparative analysis based on historical data to evaluate the performance of the domain controller under different conditions.

[0086] Specifically, the test conditions refer to different test environments or operating states, such as urban roads, highways, adverse weather, or operating states under different computing loads. For these different test conditions, it is necessary to classify and store the time series data to ensure that subsequent individual analysis can be carried out for specific conditions, which helps to further optimize the system performance. When classifying and storing data, indexes (such as timestamps, condition categories) can be added as needed to ensure that subsequent queries can quickly locate the data. Classifying and storing the time series data set according to different test conditions reduces data confusion and prevents the data under different test environments from affecting each other, resulting in incorrect analysis.

[0087] Provide a query interface that allows users to filter data by time range or test conditions. Query by test environment, such as querying the CPU load, BPU load, and camera FPS data in the highway test environment. Query by time, such as querying parameters such as CPU load and temperature during a certain period. The queried data can be used to draw corresponding trend charts for a specific period or test environment. This can focus on the data for a certain period or a certain test environment and support fine-grained data analysis.

[0088] Compare the same performance parameters under different conditions based on historical data, and analyze the changes in performance parameters such as camera frame rate and computing load under different conditions. Through historical comparison and analysis, it is easier to discover the computing bottleneck to optimize CPU task scheduling, BPU computing resource allocation, etc.

[0089] In summary, the perception log analysis method based on the vehicle-mounted domain controller provided in the embodiment of the present application obtains perception data from the vehicle-mounted domain controller and records it in a log file; parses log files in different formats and extracts at least one type of performance parameter related to system performance and the corresponding historical values from the log file; based on each extracted performance parameter and the corresponding historical value, generates a time series data set sorted by timestamp; and visually displays the time series data set to show the trend of each performance parameter changing over time. The present application uses an automated log parsing technology to extract the key performance parameters of the domain controller and visually display them, reducing manual intervention, improving the extraction accuracy of key performance parameters, and accelerating the data processing process. And it enables the system operating state and performance trend to be presented intuitively, facilitating developers to monitor and optimize the system performance. It provides important data support for the optimization of autonomous driving and ADAS systems.

[0090] Those skilled in the art can understand that in the above method of the specific implementation manner, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0091] In addition, some embodiments of the present application further provide an electronic device. The electronic device can be various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and so on. The electronic device can also be various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0092] The electronic device includes: one or more processors; and a memory storing computer program instructions, which when executed cause the processors to execute the perception log analysis method based on the in-vehicle domain controller provided by any one or more of the above embodiments. Figure 6 An exemplary structural diagram of the electronic device is disclosed. As Figure 6 shown, the electronic device includes: one or more processors 1101, a memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Each component is interconnected using different buses and can be installed on a common motherboard or in other ways as needed. The processor can process instructions executed within the electronic device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Among them, the components, their connections and relationships, and their functions shown herein are only examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0093] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103, and the output device 1104 can be connected through a bus or other means, Figure 6 taking connection through a bus as an example.

[0094] The input device 1103 can receive input digital or character information and generate key signal inputs related to the user settings and function control of the electronic device, such as input devices like touchscreens, keypads, mice, trackpads, touchpads, pointing sticks, one or more mouse buttons, trackballs, joysticks, etc. The output device 1104 can include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), etc. The display device can include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device can be a touchscreen.

[0095] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or an LCD monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide inputs to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and inputs from the user can be received in any form (including acoustic input, voice input, or haptic input).

[0096] In the embodiments of this application, computer programs / instructions are stored on a computer-readable medium. When the computer programs / instructions are executed by a processor, the perception log analysis method based on the in-vehicle domain controller provided in any one or more of the above embodiments is implemented. The computer-readable medium can be included in the electronic device described in the above embodiments; or it can exist separately without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0097] The memory 1102 can be used as a non-transitory computer-readable storage medium for storing non-transitory software programs, non-transitory computer-executable programs, and modules. By running the non-transitory software programs, instructions, and modules stored in the memory 1102, the processor 1101 executes various functional applications and data processing of the server to implement the program instructions / modules corresponding to the methods provided in any one or more of the above embodiments of this application.

[0098] The memory 1102 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the electronic device and the like. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 1102 may optionally include a memory remotely disposed relative to the processor 1101, and these remote memories may be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0099] It should be noted that more specific examples of computer-readable storage media may include but are not limited to: an electrical connection having 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 a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

[0100] A computer-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0101] Computer program code for performing the operations of the present application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone 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 can 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 can be connected to an external computer (e.g., by connecting through the Internet using an Internet service provider).

[0102] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. For example, an application-specific integrated circuit (ASIC) or a general-purpose computer or any other similar hardware device can be used. In some embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, or a floppy disk and the like. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with the processor to execute each step or function.

[0103] The computer program product provided by the embodiments of the present application includes one or more computer programs / instructions. When the computer program / instructions are executed by a processor, they wholly or partly generate the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that integrates one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive, SSD).

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0105] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily mention changes or substitutions, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A perception log analysis method based on an in-vehicle domain controller, characterized in that, Including: Obtain perception data from the vehicle-mounted domain controller and record it in a log file; Parse the log files in different formats, and extract at least one type of performance parameter related to system performance and the corresponding historical values from the log files; Based on each of the extracted performance parameters and the corresponding historical values, generate a time series data set sorted by timestamp; Visually display the time series data set to show the trend of each performance parameter changing over time.

2. The perception log analysis method according to claim 1, wherein The performance parameters include at least one of the average frame rate and latency of the camera, the operating frequency and utilization rate of the computing unit, and temperature information.

3. The perception log analysis method according to claim 1, characterized in that The step of parsing the log files in different formats and extracting at least one type of performance parameter related to system performance and the corresponding historical values from the log files includes: Identify the log format by analyzing the file header or file name suffix of the log file; According to different log formats, adopt different data field extraction rules to extract performance parameters and the corresponding historical values from multiple log data in the log file; Verify whether the values of the performance parameters conform to the corresponding data format specifications, and mark or fill in the missing or abnormal data.

4. The perception log analysis method according to claim 3, wherein The log formats include structured, semi-structured, and unstructured; For log files in structured format, extract perception data according to the field name matching rule; For log files in semi-structured format, extract perception data according to the keyword matching rule; For log files in unstructured format, extract perception data based on natural language processing technology or regular expressions.

5. The perception log analysis method according to claim 1 or 3, characterized in that The step of generating a time series data set sorted by timestamp based on each of the extracted performance parameters and the corresponding historical values includes: Parse the timestamps of each log data containing the performance parameter, and standardize the timestamps in different formats; Based on the historical values extracted for each performance parameter, sort the data in ascending order according to the standardized timestamps to form a time series data set; Adopt a data interpolation method to complete the missing data points in the time series data set; Adopt a denoising algorithm to smooth the time series data set.

6. The perception log analysis method according to claim 1, wherein It also includes: Conduct statistical analysis on the time series data set to calculate the average value, maximum value, and minimum value of each performance parameter, and mark them in the visualization graph.

7. The perception log analysis method according to claim 1, wherein It also includes: Classify and store the time series data set according to different test conditions; Allow users to retrieve the time series data set within a specified time period or under a specific test environment through a query interface; Conduct comparative analysis based on historical data to evaluate the performance of the domain controller under different conditions.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; and a memory storing computer program instructions, which when executed by the processor, cause the processor to execute the perception log analysis method according to any one of claims 1-7.

9. A computer-readable storage medium having computer programs / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, the perception log analysis method according to any one of claims 1-7 is implemented.

10. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the method for analyzing a perception log as described in any one of claims 1-7 is implemented.

Images