Electronic control unit log analysis method, device, equipment and storage medium

Abstract

The present application discloses an electronic control unit log analysis method, device, equipment and storage medium, which relate to the field of automotive electronic technology, including: obtaining a log data set; processing the log data set according to preset log filtering conditions to obtain error log entries; splitting and reorganizing the error log entries to obtain multiple error log problems; analyzing the error log problems to obtain error log analysis results, automatically identifying abnormal patterns in the log, predicting potential system failures, and providing maintenance suggestions to improve the reliability and safety of the automobile.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and in particular to methods, apparatus, devices and storage media for electronic control unit log analysis. Background Art

[0002] As vehicles become increasingly electronic, the ECU plays an increasingly important role. It controls various vehicle functions, such as engine management, braking systems, and airbags. During operation, the ECU generates a large amount of log data, which is crucial for vehicle maintenance and fault diagnosis.

[0003] However, traditional log analysis methods often rely on manual interpretation, which is inefficient and error-prone.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide an electronic control unit log analysis method, device, equipment and storage medium, aiming to solve the technical problem of low log analysis efficiency.

[0006] To achieve the above objectives, the present application proposes an electronic control unit log analysis method, which includes:

[0007] Retrieve the log data collection;

[0008] The log data set is processed according to preset log filtering conditions to obtain error log entries;

[0009] The error log entries are split and reassembled to obtain multiple error log issues;

[0010] The error log problem was analyzed, and the error log analysis results were obtained.

[0011] In one embodiment, the step of processing the log data set according to preset log filtering conditions to obtain error log entries includes:

[0012] Create a data preprocessing script based on preset log filtering conditions;

[0013] Retrieve multiple log entries corresponding to the log data set;

[0014] The log entries are processed by the data preprocessing script to obtain multiple error log entries that meet the preset log filtering conditions.

[0015] In one embodiment, the step of analyzing the error log problem to obtain the error log analysis result includes:

[0016] Create deep learning models;

[0017] The error log problem is input into the deep learning model to analyze the causal relationship of the error log and determine the cause of the failure.

[0018] The cause of the fault was analyzed, and the error log analysis results were obtained.

[0019] In one embodiment, after the step of obtaining the error log analysis results, the method further includes:

[0020] The error log analysis results are processed using machine learning algorithms to determine the risk of failure.

[0021] Prioritize the aforementioned failure risks;

[0022] Based on the priority of the aforementioned fault risks, fault maintenance and intelligent notification are performed in sequence.

[0023] In one embodiment, after the step of obtaining the log data set, the method further includes:

[0024] Acquire vehicle sensor data;

[0025] The vehicle sensor data and the log data set are combined to obtain aggregated data;

[0026] Key performance indicators are calculated based on the aggregated data, and the performance of the electronic control unit is evaluated based on the key performance indicators.

[0027] In one embodiment, after the step of obtaining the error log analysis results, the method further includes:

[0028] The fault type is determined based on the error log analysis results;

[0029] Determine the preset fault handling process based on the fault type;

[0030] Fault maintenance is performed based on the preset fault handling process.

[0031] In one embodiment, the step of splitting and reorganizing the error log entries to obtain multiple error log issues includes:

[0032] Obtain historical error log data and construct an error log template based on the historical error log data;

[0033] Based on the error log template, the keywords of the error log entries are split to obtain error log entries belonging to the same fault type;

[0034] Based on the error log template, match the error log entries belonging to the same fault type to determine the error log problem corresponding to each error log entry;

[0035] Error log entries belonging to the same error log issue will be reorganized to obtain multiple error log issues.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic control unit log analysis device, the device comprising:

[0037] The data acquisition module is used to acquire log data sets;

[0038] The data processing module is used to process the log data set according to preset log filtering conditions to obtain error log entries; and to split and reassemble the error log entries to obtain multiple error log issues.

[0039] The error analysis module is used to analyze the error log issues and obtain the error log analysis results.

[0040] In addition, to achieve the above objectives, this application also proposes an electronic control unit log analysis device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the electronic control unit log analysis method as described above.

[0041] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the electronic control unit log analysis method described above.

[0042] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the electronic control unit log analysis method described above.

[0043] One or more technical solutions proposed in this application have at least the following technical effects:

[0044] Acquire a set of log data; process the log data set according to preset log filtering conditions to obtain error log entries; split and reorganize the error log entries to obtain multiple error log issues; analyze the error log issues to obtain error log analysis results, automatically identify abnormal patterns in the logs, predict potential system failures, and provide maintenance suggestions to improve the reliability and safety of the vehicle. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 This is a flowchart illustrating an embodiment of the electronic control unit log analysis method of this application.

[0048] Figure 2 A flowchart of log analysis and error diagnosis based on a deep learning model is provided for Embodiment 1 of the electronic control unit log analysis method of this application;

[0049] Figure 3 This is a flowchart illustrating Embodiment 2 of the electronic control unit log analysis method of this application.

[0050] Figure 4 This is a schematic diagram of the module structure of the electronic control unit log analysis device according to an embodiment of this application;

[0051] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the electronic control unit log analysis method in this application embodiment.

[0052] The purpose, features and advantages of this application will be further explained with reference to the accompanying drawings in conjunction with the embodiments. Detailed Implementation

[0053] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, an electronic control unit log analysis device, etc. The following uses the electronic control unit log analysis device as an example to illustrate this embodiment and the following embodiments.

[0056] Based on this, embodiments of this application provide an electronic control unit log analysis method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the electronic control unit log analysis device method of this application.

[0057] In this embodiment, the electronic control unit log analysis device method includes steps S10 to S40:

[0058] Step S10: Obtain the log data set;

[0059] In practice, a set of log data corresponding to the ECU system to be analyzed is collected based on a preset log collection tool.

[0060] It should be noted that the log acquisition methods of this strategy include real-time collection and periodic collection: real-time collection, for systems that require immediate response, the log collection module can be configured to monitor and collect data in real time to ensure the timeliness of the data; periodic collection, for data that does not require immediate response, can be set up as a scheduled task to automatically collect log data at preset time intervals (such as hourly or daily).

[0061] This strategy includes two forms of data source access: direct access and indirect access. In direct access, the log acquisition module can directly connect to the output port of the ECU to obtain log data in real time. In indirect access, in some cases, the ECU may not directly support data output, and the log acquisition module can indirectly obtain data through the vehicle's diagnostic interface (OBD) or other communication protocols.

[0062] This strategy supports multiple log data formats, such as text, JSON, and XML, to meet the output requirements of different ECUs. At the same time, the module can perform real-time conversion for non-standard data formats to ensure that the data is compatible with subsequent processing flows.

[0063] During the data acquisition process, the module performs data verification, such as CRC check, to ensure that the data has not been tampered with during transmission. At the same time, for multiple ECUs in a distributed system, the module can synchronize data to ensure data consistency.

[0064] To protect data security during transmission, the module supports encryption of the collected data. Simultaneously, the module implements strict access control, ensuring that only authorized users and systems can access the collected log data.

[0065] Under high load, the module can dynamically allocate acquisition tasks to optimize resource usage and improve acquisition efficiency. Simultaneously, to reduce storage space and improve transmission efficiency, the module can compress data during acquisition.

[0066] This strategy provides a user-friendly configuration interface, allowing users to customize data collection strategies and set collection parameters. Simultaneously, this module can monitor the collection status and generate reports on collection activities, enabling users to understand the efficiency and status of data collection.

[0067] These detailed functions and operations enable efficient and reliable collection of ECU log data, providing a foundation for subsequent log processing and intelligent analysis.

[0068] Furthermore, after step S10, the following steps are also included:

[0069] Obtain vehicle sensor data;

[0070] The vehicle sensor data and the log data set are combined to obtain aggregated data;

[0071] Key performance indicators (KPIs) are calculated based on aggregated data, and the performance of the electronic control unit is evaluated based on these KPIs.

[0072] Step S20: Process the log data set according to the preset log filtering conditions to obtain error log entries;

[0073] It should be noted that preset log filtering conditions refer to a series of rules defined in advance based on the needs of log analysis, used to filter log entries that meet specific characteristics. These conditions may include error type, occurrence time, occurrence location, error description, etc.

[0074] In the specific implementation, a data preprocessing script is written based on preset log filtering conditions to automatically retrieve multiple log entries corresponding to the log data set stored in the preset log center, and at the same time automatically generate multiple error log entries that match the preset log filtering conditions.

[0075] In one feasible implementation, step S20 may include steps A11 to A13:

[0076] Step A11: Create a data preprocessing script based on preset log filtering conditions;

[0077] It should be noted that a data preprocessing script is a piece of code that automates preprocessing tasks, used to filter and process log data based on preset filtering conditions.

[0078] In practice, programming languages ​​such as Python are used to write scripts to perform functions such as reading, filtering, cleaning, and formatting log data. The scripts can include extraction logic such as regular expressions to match specific log entries.

[0079] Step A12: Retrieve multiple log entries corresponding to the log data set;

[0080] In the specific implementation, a preprocessing script is written to automatically retrieve log entries from the log data set that match preset conditions from the log center.

[0081] Step A13: Process the log entries using a data preprocessing script to obtain multiple error log entries that meet the preset log filtering conditions.

[0082] In the actual implementation, after the script executes, it returns a list containing log entries that meet preset conditions. Each entry includes information such as the occurrence time, error type, location of occurrence, and error description. These entries are the error log entries that match the preset log filtering conditions.

[0083] Step S30: Split and reassemble the error log entries to obtain multiple error log issues;

[0084] In the specific implementation, multiple error log entries are split using a preset log issue template and then recombined to obtain multiple error log issues.

[0085] In one feasible implementation, step S30 may include steps A21 to A24:

[0086] Step A21: Obtain historical error log data and construct an error log template based on the historical error log data;

[0087] In the specific implementation, historical error log data is exported from the log management system, including but not limited to the time of error occurrence, error level, error message, error code, etc.; noise and inconsistencies in the data are cleaned, such as removing irrelevant log entries and correcting incorrect formats; historical error log data is analyzed to identify common error patterns and fault types; and based on the identified error patterns, error log templates are constructed. The templates should include keywords, error codes, and message structures that represent specific error types; and the templates are compared with historical data to verify their accuracy and coverage, ensuring that they match the majority of known errors.

[0088] Step A22: Based on the error log template, split the keywords of the error log entries to obtain error log entries belonging to the same fault type;

[0089] In the specific implementation, keywords and error codes are extracted from the error log template, which will be used to identify and split log entries; real-time or newly collected error log entries are scanned, and regular expressions or text matching technology is used to identify keywords in the template; log entries containing the same keywords are classified into corresponding fault types; for log entries containing multiple keywords, they are split into multiple independent entries according to the template, each entry corresponds to a specific fault type.

[0090] Step A23: Match error log entries belonging to the same fault type based on the error log template to determine the error log problem corresponding to each error log entry;

[0091] In the specific implementation, the constructed error log template is used to match the categorized log entries to determine whether they conform to the error type defined in the template; for each matching log entry, the specific error problem corresponding to it is determined, such as memory leak, network timeout, etc.; the matching log entries are associated with known error problems, and each entry is marked with an error problem identifier; the accuracy of the matching results is verified through manual review or automated testing.

[0092] Step A24: Reorganize error log entries belonging to the same error log issue to obtain multiple error log issues.

[0093] In the specific implementation, all log entries matching the same error problem are grouped together; the grouped log entries are reorganized, which may include merging duplicate error entries, sorting entries, etc.; a clear problem description is defined for each reorganized error log set, including the problem name, scope of impact, possible causes, etc.; the reorganized error log problems are output as structured data for easy subsequent analysis and processing; and a unique tracking identifier is assigned to each error log problem to facilitate problem tracking and management.

[0094] Step S40: Analyze the error log problem and obtain the error log analysis results.

[0095] In the specific implementation, a log analysis model is constructed based on a preset large language model, and multiple error log issues are input into the log analysis model to obtain the error log analysis results corresponding to the ECU system to be analyzed.

[0096] It should be noted that the error log analysis result includes at least the error log entry, error log problem, error log generation time and error cause, etc.

[0097] In one feasible implementation, after step S40, steps A31 to A33 may be included:

[0098] Step A31: Process the error log analysis results based on machine learning algorithms to determine the risk of failure;

[0099] In the specific implementation, key features, such as the frequency of error occurrence, error code, and error message, are extracted from the error log. These features will be used as input to the machine learning model. Appropriate machine learning algorithms, such as random forest, support vector machine, and neural network, are selected to process the log data and predict failure risk. The model is trained using historical error log data so that it can learn to identify different failure modes and risk levels. The model is then used to score each error log entry to determine its corresponding failure risk level.

[0100] Step A32: Prioritize the failure risks;

[0101] In practice, the failure risk is quantitatively scored based on the output of the machine learning model; priority rules are set according to the severity, probability of occurrence, and detectability of the failure; all failure risks are sorted according to the set rules to determine the priority order of processing; and the priority of failure risks is dynamically adjusted based on real-time monitoring and new log data.

[0102] Step A33: Prioritize fault risks and perform fault maintenance and intelligent notification in sequence.

[0103] In practice, maintenance plans are developed based on the priority of fault risks. For high-priority fault risks, relevant personnel are promptly notified through intelligent notification systems (such as email, SMS, and application push notifications). Fault maintenance work is carried out according to the maintenance plan, including but not limited to system updates, hardware replacements, and configuration adjustments. The progress of maintenance work is tracked, and verification and evaluation are conducted after maintenance is completed.

[0104] In another feasible implementation, after step S40, steps A41 to A43 may be included:

[0105] A41: Determine the fault type based on the error log analysis results;

[0106] In practice, error logs are analyzed to identify specific error patterns and fault symptoms; error logs are then categorized into known fault types, such as network faults, hardware faults, and software faults.

[0107] A42: Determine the preset fault handling process based on the fault type;

[0108] In practice, the pre-defined fault handling process is matched according to the determined fault type; and the pre-defined fault handling process is continuously optimized based on historical handling experience and the latest technological developments.

[0109] A43: Perform fault maintenance based on the preset fault handling process.

[0110] In practice, specific maintenance operations are performed according to the matching fault handling process; the results of fault handling and any new findings are recorded to provide a reference for future fault handling; and the handling results are fed back into the fault handling process to improve and optimize the process.

[0111] It should be noted that this strategy can also execute specific system calls and user interactions based on the output of the log analysis module to achieve automated fault response and maintenance operations, including:

[0112] For known fault modes, the agent can automatically execute predefined repair steps, such as resetting services and updating configurations; at the same time, the agent can remotely connect to the ECU to perform real-time diagnostics and make necessary adjustments based on the analysis results.

[0113] Based on the results of predictive maintenance, specific maintenance tasks can be generated. Maintenance plans can also be optimized and downtime reduced based on vehicle usage and the availability of maintenance resources. The intelligent agent can send custom notifications via SMS, email, or application push according to user preferences. The user interface allows users to query maintenance status, fault reports, and system health information.

[0114] It can collect user feedback on fault handling and maintenance operations to improve services, and can also use user feedback and new log data to continuously optimize its performance through machine learning algorithms.

[0115] Before executing any system call, it is necessary to verify the user or system permissions to ensure the security of the operation, and record detailed logs of all system calls and user interactions to facilitate auditing and troubleshooting.

[0116] This strategy allows other systems and services to invoke the agent's functions, enabling system integration and expansion. It also employs a plug-in architecture design, facilitating the addition of new functional modules, such as new fault handling strategies or maintenance tools.

[0117] The performance of the monitoring and calling tool modules is optimized to ensure response time and system resources are optimized. Under high load, the agent can dynamically allocate tasks to optimize resource usage and improve processing efficiency.

[0118] like Figure 2 As shown, Figure 2This is a flowchart for log analysis and error diagnosis based on deep learning models. First, enter the "Log Collection Module," where log data sets are collected using a preset log collection tool. The data is then fed into the "Log Preprocessing Module," where log data sets are preprocessed using preset log filtering conditions and data preprocessing scripts are written to prepare for further analysis. The process then branches into two main branches. The first branch is the "Error Problem Acquisition Module," which is responsible for splitting and combining error log problems and identifying and classifying error logs using preset log problem templates. The second branch is the application of a "deep learning model," where a "log analysis model" is constructed that can process and learn complex patterns in log data to determine the root cause of faults and predict multiple possible fault labels in multi-fault diagnosis scenarios. In the "Log Analysis Module," the system automatically extracts and segments log data and configures log collection paths and extraction rules in the configuration file. In addition, this module also involves a "log center system call tool" for "processing and analyzing the returned content" and "optimizing the generation process of the inference stage"; finally, the analysis results are used to "output the error log analysis results" to complete the fault diagnosis process.

[0119] This embodiment provides an electronic control unit (ECU) log analysis method that utilizes deep learning technology to understand and analyze ECU-generated log data through a pre-trained large language model, thereby enabling fault diagnosis, performance monitoring, and predictive maintenance. It can automatically identify abnormal patterns in the logs, predict potential system faults, and provide maintenance suggestions to improve the reliability and safety of automobiles.

[0120] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S40 includes steps S401 to S302:

[0121] Step S401: Create a deep learning model;

[0122] It should be noted that this deep learning model consists of four parts, including a multi-layer perceptron (MLP), which is used to process structured data, such as numerical features in logs, and learn nonlinear relationships between data through multi-layer neural networks; a convolutional neural network (CNN), which is suitable for processing data with spatial correlation, such as time series data, and extracts local features through convolutional layers; a recurrent neural network (RNN) and a long short-term memory network (LSTM), which are particularly suitable for processing sequence data, such as log timestamps, and can capture long-term dependencies; and a large language model call, which has strong processing capabilities for text and natural language and strong interactivity.

[0123] Step S402: Input the error log problem into the deep learning model, analyze the causal relationship of the error log, and determine the cause of the failure;

[0124] In the specific implementation, a deep learning model learns the causal relationships in log data to determine the root cause of the fault. In multi-fault diagnosis scenarios, the model can simultaneously predict multiple possible fault labels.

[0125] It should be noted that causal relationship learning uses causal inference techniques, such as Granger causality test or methods based on latent variable models, to identify causal relationships between variables; these causal relationships are added as constraints in model training to improve the accuracy of fault diagnosis.

[0126] It should be understood that deep learning models can also achieve automatic feature extraction, automatically learning features from raw log data, reducing the need for manual feature engineering. At the same time, through unsupervised learning methods such as autoencoders, high-dimensional data can be reduced in dimensionality to improve the training efficiency and generalization ability of the model.

[0127] Identify log patterns under normal operating conditions and identify anomalous log entries that deviate from these patterns. Assign an anomalous score to each log entry to quantify the degree to which it deviates from normal behavior.

[0128] It can also monitor ECU performance metrics in real time and predict performance degradation or failure. By learning the performance baseline under normal operating conditions, the model can identify early signs of performance degradation.

[0129] It should be understood that the model training process can utilize data augmentation techniques, such as rotation and scaling, to increase the diversity of training data and improve the model's robustness. Simultaneously, using a pre-trained model as a starting point, fine-tuning can be applied to adapt to specific ECU log datasets, reducing training time and resources. The trained model can then be integrated into the ECU log parsing system to achieve automated log analysis. Furthermore, this model can be deployed on cloud or edge devices to achieve real-time or near real-time log analysis.

[0130] Step S403: Analyze the cause of the fault and obtain error log analysis results;

[0131] In the specific implementation, the data processed by the deep learning model is further analyzed to extract useful information, generate diagnostic reports, and provide decision support.

[0132] It should be noted that this strategy can also identify the root cause of the fault by analyzing patterns and anomalies in the log data. The analysis results are mapped to standard fault codes to facilitate technicians to understand and handle;

[0133] Calculate key performance indicators (KPIs) such as response time, processing speed, and resource utilization. Also compare current performance with historical data or industry benchmarks to assess system performance.

[0134] Based on log analysis results, the timing and content of the next maintenance are predicted. Furthermore, different maintenance tasks are prioritized according to the degree of failure risk and performance degradation.

[0135] Identify possible security incidents and violations and trigger alerts. Ensure that the collection and processing of log data complies with relevant laws, regulations and industry standards;

[0136] It provides a user-friendly dashboard that displays real-time data, historical trends, and analysis results. It also allows users to generate custom reports as needed, including fault diagnosis, performance evaluation, and maintenance recommendations.

[0137] Technical personnel are notified in real time when critical issues or anomalies are detected. Notifications are intelligently escalated based on the severity and urgency of the problem to ensure a timely response.

[0138] User feedback and new log data are used for continuous training and optimization of the model. Analysis parameters and thresholds are automatically adjusted based on analysis results and user feedback.

[0139] Provides APIs and plugins for integration with other systems (such as CRM and ERP) to achieve data sharing and process automation. Designs modular analytics modules to facilitate the addition of new analytics tools and technologies to adapt to evolving needs.

[0140] This embodiment provides an electronic control unit (ECU) log analysis method, which creates a deep learning model; inputs error log problems into the deep learning model, analyzes the causal relationships of the error logs, and determines the cause of the fault; analyzes the cause of the fault to obtain the error log analysis results. By utilizing the advanced feature extraction capabilities of the deep learning model, abnormal patterns and potential problems in the ECU logs can be identified more accurately, thereby improving the accuracy of fault diagnosis. It can also provide practical insights and suggestions for ECU maintenance and optimization, thereby improving the reliability and safety of the vehicle.

[0141] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the electronic control unit log analysis method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0142] This application also provides an electronic control unit log analysis device, please refer to Figure 4 , the electronic control unit log analysis device includes:

[0143] Data acquisition module 10 is used to acquire log data sets;

[0144] Data processing module 20 is used to process the log data set according to preset log filtering conditions to obtain error log entries; and to split and reorganize the error log entries to obtain multiple error log issues.

[0145] Error analysis module 30 is used to analyze error log issues and obtain error log analysis results.

[0146] The electronic control unit log analysis device provided in this application utilizes the electronic control unit log analysis method of the aforementioned embodiment to resolve the technical issue of low log analysis efficiency. Compared to the prior art, the electronic control unit log analysis device provided in this application has the same beneficial effects as the electronic control unit log analysis method provided in the aforementioned embodiment, and the other technical features of the electronic control unit log analysis device are the same as those disclosed in the aforementioned embodiment method, and are not further described here.

[0147] In one embodiment, the data processing module 20 is further configured to create a data preprocessing script based on preset log filtering conditions;

[0148] Retrieve multiple log entries corresponding to a log data set;

[0149] The log entries are processed by a data preprocessing script to obtain multiple error log entries that meet the preset log filtering conditions.

[0150] In one embodiment, the error analysis module 30 is further configured to create a deep learning model;

[0151] By inputting error log issues into a deep learning model, the causal relationships in the error logs can be analyzed to determine the cause of the failure.

[0152] The cause of the failure was analyzed, and the error log analysis results were obtained.

[0153] In one embodiment, the error analysis module 30 is further configured to process the error log analysis results based on machine learning algorithms to determine the risk of failure;

[0154] Prioritize the failure risks;

[0155] Based on the priority of fault risks, fault maintenance and intelligent notification are performed in that order.

[0156] In one embodiment, the data acquisition module 10 is further configured to acquire vehicle sensor data;

[0157] By combining vehicle sensor data and log data sets, aggregated data is obtained;

[0158] Key performance indicators (KPIs) are calculated based on aggregated data, and the performance of the electronic control unit is evaluated based on these KPIs.

[0159] In one embodiment, the error analysis module 30 is further configured to determine the fault type based on the error log analysis results;

[0160] Determine the preset fault handling process based on the fault type;

[0161] Perform fault maintenance based on the preset fault handling process.

[0162] In one embodiment, the data processing module 20 is further configured to acquire historical error log data and construct an error log template based on the historical error log data;

[0163] Based on the error log template, the keywords of the error log entries are split to obtain error log entries belonging to the same fault type;

[0164] Based on the error log template, match error log entries belonging to the same fault type to determine the error log problem corresponding to each error log entry;

[0165] Error log entries belonging to the same error log problem are reorganized to obtain multiple error log problems.

[0166] This application provides an electronic control unit log analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the electronic control unit log analysis method in Embodiment 1 above.

[0167] Reference below Figure 5 The diagram illustrates a structural schematic of an electronic control unit log analysis device suitable for implementing embodiments of this application. The electronic control unit log analysis device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic control unit log analysis device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0168] like Figure 5 As shown, the electronic control unit log analysis device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic control unit log analysis device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 can allow the electronic control unit log analysis device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows an electronic control unit log analysis device with various systems, it should be understood that it is not required to implement or include all of the systems shown. More or fewer systems may be implemented or included instead.

[0169] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0170] The electronic control unit (ECU) log analysis device provided in this application, employing the ECU log analysis method described in the above embodiments, can solve the technical problem of low log analysis efficiency. Compared with the prior art, the beneficial effects of the ECU log analysis device provided in this application are the same as those of the ECU log analysis device method provided in the above embodiments, and other technical features of this ECU log analysis device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0171] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0172] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0173] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the electronic control unit log analysis method in the above embodiments.

[0174] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: 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 embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0175] The computer-readable storage medium may be included in the electronic control unit log analysis device; or may exist independently without being assembled into the electronic control unit log analysis device.

[0176] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic control unit log analysis device, the electronic control unit log analysis device: obtains a log data set; processes the log data set according to preset log filtering conditions to obtain error log entries; splits and reorganizes the error log entries to obtain multiple error log problems; analyzes the error log problems to obtain error log analysis results.

[0177] Computer program code for performing the operations of the present application 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 stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving 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).

[0178] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0179] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0180] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described electronic control unit log analysis method, thereby solving the technical problem of low log analysis efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the electronic control unit log analysis method provided in the above embodiments, and will not be repeated here.

[0181] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the electronic control unit log analysis method described above.

[0182] The computer program product provided in this application can solve the technical problem of low log analysis efficiency. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the electronic control unit log analysis method provided in the above embodiments, and will not be repeated here.

[0183] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An electronic control unit log analysis method, characterized in that: The electronic control unit log analysis method comprises: Get the log data collection; Processing the log data set according to a preset log filtering condition to obtain an error log entry; Splitting and reorganizing the error log entries to obtain multiple error log questions; The error log problem is analyzed to obtain an error log analysis result.

2. The electronic control unit log analysis method according to claim 1, characterized in that: The step of processing the log data set according to the preset log filtering condition to obtain an error log entry includes: Create data preprocessing scripts based on preset log filtering conditions; Retrieving a plurality of log entries corresponding to the log data set; The log entries are processed by the data preprocessing script to obtain a plurality of error log entries that meet the preset log filtering conditions.

3. The electronic control unit log analysis method according to claim 1, characterized in that: The step of analyzing the error log problem to obtain an error log analysis result includes: Create deep learning models; Input the error log problem into the deep learning model, analyze the cause and effect relationship of the error log, and determine the cause of the fault; The cause of the fault is analyzed to obtain an error log analysis result.

4. The electronic control unit log analysis method according to claim 1, characterized in that: After the step of obtaining the error log analysis result, the method further includes: Processing the error log analysis results based on a machine learning algorithm to determine the failure risk; assigning priorities to the failure risks; According to the priority of the fault risk, fault maintenance and intelligent notification are performed in sequence.

5. The electronic control unit log analysis method according to claim 1, characterized in that: After the step of obtaining the log data set, the method further includes: Get vehicle sensor data; Combining the vehicle sensor data with the log data set to obtain aggregated data; Key performance indicators are calculated based on the aggregated data, and electronic control unit performance is evaluated based on the key performance indicators.

6. The electronic control unit log analysis method according to claim 1, characterized in that: After the step of obtaining the error log analysis result, the method further includes: Determine the fault type according to the error log analysis result; Determine a preset fault handling process according to the fault type; Perform fault maintenance based on the preset fault handling process.

7. The electronic control unit log analysis method according to claim 1, characterized in that: The step of splitting and reorganizing the error log entries to obtain multiple error log problems includes: Acquire historical error log data, and construct an error log template based on the historical error log data; Splitting the keywords of the error log entries based on the error log template to obtain error log entries belonging to the same fault type; Matching the error log entries belonging to the same fault type based on the error log template to determine the error log problem corresponding to each of the error log entries; The error log entries belonging to the same error log problem are reorganized to obtain multiple error log problems.

8. An electronic control unit log analysis device, characterized in that: The device comprises: A data acquisition module is used to acquire a set of log data; A data processing module is used to process the log data set according to a preset log filtering condition to obtain an error log entry; split and reorganize the error log entry to obtain multiple error log issues; The error analysis module is used to analyze the error log problem and obtain the error log analysis result.

9. An electronic control unit log analysis device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the electronic control unit log analysis method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the electronic control unit log analysis method according to any one of claims 1 to 7 are implemented.

Images