Intelligent networked automobile monitoring and alarming method and system based on data real-time monitoring

Abstract

The invention discloses an intelligent networked automobile monitoring and alarming method and system based on data real-time monitoring, and particularly relates to the technical field of automobile monitoring and alarming. Firstly, various sensors are used for collecting vehicle and surrounding environment data in real time, effective preprocessing is carried out, and the consistency of the data is ensured; secondly, extracting vehicle driving characteristics and driving environment characteristics from the preprocessed data, carrying out data analysis and model training, identifying potential dangerous conditions and sending out dangerous signals, meanwhile, carrying out real-time monitoring in the data preprocessing and characteristic extraction stage, evaluating the stability of the working state of the vehicle-mounted computer in time, and when abnormal working is found, carrying out real-time monitoring on the vehicle-mounted computer; according to the method, the vehicle-mounted computer can be diagnosed and repaired immediately, the accuracy and real-time performance of the repaired vehicle-mounted computer are evaluated, finally, the information accuracy and the command real-time performance after repair are comprehensively analyzed, possible risk faults are predicted and warned in advance, and the vehicle driving safety is effectively improved by monitoring and managing the vehicle-mounted computer in an omnibearing mode.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile monitoring and alarm technology, and in particular to an intelligent networked automobile monitoring and alarm method and system based on real-time data monitoring. Background Art

[0002] The safety warning system of smart connected cars uses the vehicle's built-in sensors and communication technology to continuously capture information about the vehicle and its surroundings. This information is analyzed and processed by algorithms to observe and monitor the vehicle's operating conditions and changes in the surrounding environment. Once the system finds a potentially dangerous or abnormal condition, such as the possibility of a traffic accident, deterioration of the road environment, driver fatigue or discomfort, the warning system will be activated and the driver will be immediately notified to let them know that safety measures need to be taken. The purpose of this is to maximize driving safety.

[0003] The main working principle of the system is to continuously collect and analyze data about the vehicle and its surroundings to accurately identify various possible risks and provide feedback to the driver as soon as possible to help them prevent accidents. This is not only a breakthrough in the field of safety for smart connected cars, but also uses Internet technology and artificial intelligence to enable vehicles to understand and adapt to complex road conditions more intelligently, providing drivers with a safer and more convenient driving environment.

[0004] The on-board computer plays a vital role in the real-time data monitoring and alarm system of intelligent connected vehicles. Its main responsibility is to receive, process and analyze data from the vehicle and its surrounding environment. With the help of the on-board computer equipped with a high-performance processor and specialized algorithms, it can process massive amounts of sensor data in real time, identify and predict possible dangerous conditions, such as the risk of traffic accidents, deterioration of road conditions, and possible driver fatigue, etc., and then activate the corresponding monitoring and alarm system based on these prediction results, so as to achieve timely reminders to drivers so that they can respond in time and take necessary driving safety measures, thereby effectively improving our driving safety and driving comfort.

[0005] The prior art has the following deficiencies: When a smart connected car monitors and alarms based on real-time data monitoring, if the on-board computer's working state is abnormal, the system may be out of control, and the vehicle may not be able to accurately identify the surrounding environment or other vehicles, making it impossible to accurately execute driving commands. At the same time, an abnormal on-board computer may not be able to correctly identify traffic signals, road signs and road signs, causing the vehicle to fail to comply with traffic rules and road sign instructions. This may cause the vehicle to take action at the wrong time, such as running a red light or mistakenly entering a prohibited area, causing serious traffic accidents. Summary of the invention

[0006] The purpose of the present invention is to provide a smart connected vehicle monitoring and alarm method and system based on real-time data monitoring to solve the shortcomings of the background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a monitoring and alarm method for intelligent networked vehicles based on real-time data monitoring, comprising the following steps; S1: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors, and pre-processes the collected raw data to ensure data consistency; S2: Extract vehicle driving characteristics and driving environment characteristics from the preprocessed data. Based on the extracted characteristic data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance; S3: Real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at that time is evaluated. According to the evaluation results, a normal working signal of the on-board computer and an abnormal working signal of the on-board computer are respectively issued; S4: When the on-board computer sends out a signal of abnormal operation, diagnose and repair the on-board computer and its components, analyze the accuracy of the repaired on-board computer in identifying road information, and evaluate the accuracy of the repaired on-board computer in identifying information; analyze the execution effect of the vehicle executing the command issued by the on-board computer, and evaluate the real-time performance of the command issued by the on-board computer; S5: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of commands issued by the on-board computer, and make early predictions and warnings on risk failures of the on-board computer during vehicle driving.

[0008] In a preferred embodiment, in S1, the collected raw data is preprocessed by Gaussian filtering to divide the data into consistent data and inconsistent data, including: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors. For the one-dimensional data x={x1,x2,...,xN}, Gaussian filtering is applied for preprocessing. The window size of the Gaussian filter is obtained and marked as w. The filtered data is yi. The calculation expression of the filtered data is: yi= *exp ; Where σ is the standard deviation of the Gaussian filter, and yi is the filtered data; For the filtered data yi, the fluctuation degree of each data point is calculated as a measure of data quality. The specific calculation expression of the fluctuation degree of the data point is: = ;in, is the fluctuation degree of the data points, is the mean of the data, is the standard deviation of the data; The fluctuation degree of the acquired data point is compared with the fluctuation threshold. If the fluctuation degree of the data point is greater than or equal to the fluctuation threshold, the data is marked as inconsistent data; if the fluctuation degree of the data point is less than the fluctuation threshold, the data is marked as consistent data.

[0009] In a preferred embodiment, in S3, the data calculation efficiency and speed of the on-board computer during the preprocessing process are monitored, the data processing speed delay ratio is obtained in real time, and the data processing efficiency is judged according to the data processing speed delay ratio. The method for obtaining the data processing speed delay ratio is: During the data processing, the arrival timestamp and processing completion timestamp of each data packet are recorded. For each data packet, the time required from its arrival to its processing completion is calculated. For all data packets in a time period, the average processing time is calculated, that is, the average processing time of each data packet. The data processing speed is calculated by adding the processing time of all data packets and then dividing it by the number of data packets; Determine a fixed time window size M for delay monitoring of data processing speed. For each arriving data processing speed, record its arrival time. ,in, , K is a positive integer greater than 0, maintaining a sliding window. When new data arrives, it is added to the window and the earliest data in the window is removed to keep the window size unchanged; Calculate the delay time of data processing speed, that is, the time difference between the latest data processing speed and the earliest data processing speed. The calculation expression of delay time is: delay = - ;in, is the timestamp of the latest arriving data processing speed, It is the earliest timestamp of data processing speed arriving in the window, and delay is the delay time; Compare the delay time with the window size to get the delay ratio. The calculation formula for the data processing speed delay ratio is: delayratio= ;in, is the window size, which indicates the time period for delay monitoring, and delayratio is the data processing speed delay ratio.

[0010] In a preferred embodiment, in S3, when the vehicle driving data collection frequency deviates from the vehicle driving data collection frequency under the standard state, the vehicle driving data collection frequency outlier index is obtained, and the method for obtaining the collection frequency outlier index is: Cluster the vehicle driving data according to the collection frequency, and randomly select k data points as the initial cluster centers, where k is the preset number of clusters; For each data point , calculate its relationship with each cluster center The specific calculation expression is: = ; In the formula, For data points To cluster center The distance between the data points Assigned to the nearest cluster center, Assign to cluster center , where jm= ; In the formula, jm is the data point With all cluster centers Distance The index of the smallest cluster center; For each cluster j, update its cluster center is the mean of all data points in the cluster. The specific calculation expression is: = ;in, represents the set of all data points of the jth cluster, express The mean of all data points in the cluster; Data points within a cluster and The mean of all data points in the cluster Compare and calculate the collection frequency outlier index. The specific calculation expression is: = ; In the formula, is the collection frequency outlier index.

[0011] In a preferred embodiment, the data processing speed delay ratio and the acquisition frequency outlier index are normalized, and the stability coefficient of the on-board computer working state is calculated based on the normalized data processing speed delay ratio and the acquisition frequency outlier index.

[0012] In a preferred embodiment, the acquired stability coefficient of the on-board computer's working state is compared with a stability threshold. If the stability coefficient of the on-board computer's working state is greater than or equal to the stability threshold, a normal operation signal of the on-board computer is issued. If the stability coefficient of the on-board computer's working state is less than the stability threshold, an abnormal operation signal of the on-board computer is issued.

[0013] In a preferred embodiment, in S4, when the onboard computer sends a work abnormality signal, the onboard computer and its components are diagnosed and repaired, the accuracy of the repaired onboard computer in identifying road information is analyzed, and the information time deviation index of the onboard computer is obtained. The method for obtaining the information time deviation index is: Obtain the real-time feedback data of the on-board computer during the process of identifying road traffic signal information, and extract the information feedback time in the real-time feedback data , information recognition time And information reading time , obtain the expected information feedback time, information recognition time and information reading time, and calculate the information feedback time deviation value c, information recognition time deviation value c and information reading time deviation value c. Calculate the information time deviation index. The specific calculation expression is: = ; In the formula, is the information time deviation index.

[0014] In a preferred embodiment, in S4, the execution effect of the vehicle executing the command issued by the on-board computer is analyzed, the command response efficiency abnormality index of the on-board computer is obtained, and the real-time performance of the command issued by the on-board computer is evaluated. The method for obtaining the command response efficiency abnormality index is: Get the number of commands issued within time t and mark it as F, where F= , g is a positive integer greater than 0, and the actual command response speed of the on-board computer is measured, marked as D, and the utilization rate of the command queuing system is calculated. The specific calculation expression is: = ; In the formula, The utilization rate of the command queuing system is calculated by calculating the average queue length in the command queuing system. The specific calculation expression is: ;in, is the average queue length in the command queuing system, and calculates the average queue time in the command queuing system. The specific calculation expression is: ;in, is the average queuing time in the command queuing system. The average queuing time in the command queuing system is compared with the standard queuing time value to calculate the command response efficiency abnormality index. The specific calculation expression is: = ; In the formula, is the command response efficiency abnormality index, It is the standard queue time value.

[0015] In a preferred embodiment, in S5, the accuracy of the repaired on-board computer information recognition and the real-time performance of the on-board computer issuing commands are comprehensively analyzed, specifically: The information time deviation index and the command response efficiency abnormality index are normalized, and the risk assessment coefficient of the vehicle computer failure is calculated by the normalized information time deviation index and the command response efficiency abnormality index; The obtained risk assessment coefficient of the on-board computer failure is compared with the risk threshold. If the risk assessment coefficient of the on-board computer failure is greater than or equal to the risk threshold, a risk warning signal is issued; if the risk assessment coefficient of the on-board computer failure is less than the risk threshold, no risk warning signal is issued.

[0016] The present invention also provides an intelligent networked vehicle monitoring and alarm system based on real-time data monitoring, including a data processing module, a feature extraction module, a vehicle-mounted computer working state classification module, an analysis and evaluation module, and a prediction and warning module; Data processing module: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors, and pre-processes the collected raw data to ensure data consistency; Feature extraction module: extracts vehicle driving features and driving environment features from preprocessed data. Based on the extracted feature data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance. On-board computer working state classification module: real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at that time is evaluated. According to the evaluation results, the on-board computer working normal signal and the on-board computer working abnormal signal are respectively issued. Analysis and evaluation module: When the on-board computer sends out a signal of abnormal operation, the on-board computer and its components are diagnosed and repaired, the accuracy of the repaired on-board computer in identifying road information is analyzed, and the accuracy of the information identification of the repaired on-board computer is evaluated; the execution effect of the vehicle executing the command issued by the on-board computer is analyzed, and the real-time performance of the command issued by the on-board computer is evaluated; Prediction and warning module: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of the commands issued by the on-board computer, and provide early prediction and warning of risk failures of the on-board computer during vehicle driving.

[0017] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention monitors the data preprocessing stage and feature extraction stage in real time to ensure the efficiency and accuracy of data processing. When the vehicle sends a danger signal, the system will immediately evaluate the stability of the working state of the on-board computer. According to the evaluation results, the system will correspondingly send a normal working signal of the on-board computer or an abnormal working signal of the on-board computer to remind relevant personnel to take necessary actions. By real-time monitoring of vehicle status, predicting potential dangerous situations, and issuing alarms when necessary, the safety and stability of intelligent connected vehicles can be effectively improved, providing a safer travel environment for drivers and passengers.

[0018] 2. The present invention diagnoses and repairs the on-board computer and its components when the on-board computer sends out an abnormal working signal, analyzes the accuracy of the repaired on-board computer in identifying road information, and evaluates the accuracy of the repaired on-board computer in identifying information; analyzes the execution effect of the vehicle executing the command issued by the on-board computer, and evaluates the real-time performance of the command issued by the on-board computer; comprehensively analyzes the accuracy of the repaired on-board computer in identifying information and the real-time performance of the command issued by the on-board computer, and predicts and warns the risk of on-board computer failures during vehicle driving in advance. Potential failure risks can be discovered in advance, measures can be taken to prevent possible safety issues, and the safety and reliability of vehicle driving can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0020] Figure 1 The figure is a flow chart of the method of the present invention.

[0021] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Example 1 See also Figure 1 As shown, the intelligent networked vehicle monitoring and alarm method based on real-time data monitoring described in this embodiment includes the following steps: S1: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors, and pre-processes the collected raw data to ensure data consistency; S2: Extract vehicle driving characteristics and driving environment characteristics from the preprocessed data. Based on the extracted characteristic data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance; S3: Real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at that time is evaluated. According to the evaluation results, a normal working signal of the on-board computer and an abnormal working signal of the on-board computer are respectively issued; S4: When the on-board computer sends out a signal of abnormal operation, diagnose and repair the on-board computer and its components, analyze the accuracy of the repaired on-board computer in identifying road information, and evaluate the accuracy of the repaired on-board computer in identifying information; analyze the execution effect of the vehicle executing the command issued by the on-board computer, and evaluate the real-time performance of the command issued by the on-board computer; S5: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of commands issued by the on-board computer, and make early predictions and warnings on risk failures of the on-board computer during vehicle driving.

[0024] Among them, in S1, the on-board computer collects raw data from the vehicle and the surrounding environment in real time through various sensors, and pre-processes the collected raw data to ensure data consistency.

[0025] The collected raw data is preprocessed through Gaussian filtering to divide the data into consistent data and inconsistent data, including: The on-board computer collects raw data from the vehicle and its surrounding environment in real time through various sensors, including data collected by sensors such as cameras, radars, and lidars.

[0026] For one-dimensional data x={x1,x2,...,xN}, apply Gaussian filtering for preprocessing, obtain the window size of the Gaussian filter and mark it as w, and the filtered data is yi. Then the calculation expression of the filtered data is: yi= *exp ; Where σ is the standard deviation of the Gaussian filter and yi is the filtered data.

[0027] For the filtered data yi, the fluctuation degree of each data point is calculated as a measure of data quality. The specific calculation expression of the fluctuation degree of the data point is: = ;in, is the fluctuation degree of the data points, is the mean of the data, is the standard deviation of the data; The fluctuation degree of the acquired data points is compared with the fluctuation threshold. If the fluctuation degree of the data points is greater than or equal to the fluctuation threshold, the data is marked as inconsistent data. Although the data has a low signal-to-noise ratio, it may still contain useful information. The on-board computer can use more complex data processing technologies, such as machine learning or deep learning algorithms, to further analyze and mine inconsistent data to extract useful features and information; if the fluctuation degree of the data points is less than the fluctuation threshold, the data is marked as consistent data. The on-board computer can be directly used to identify and predict potential dangerous situations, such as traffic obstacles, pedestrians, etc.

[0028] S2: Extract vehicle driving characteristics and driving environment characteristics from the preprocessed data. Based on the extracted feature data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance.

[0029] Vehicle driving feature extraction includes: extracting the vehicle's real-time speed and acceleration information from sensor data, which is essential for evaluating the vehicle's current state of motion. By detecting changes in speed and acceleration, behaviors such as acceleration, deceleration, and turning can be identified. By analyzing changes in the vehicle's steering angle, it can be inferred whether the vehicle is turning or changing direction. Extracting the vehicle's current position and trajectory information, including GPS data or position and direction data provided by an inertial measurement unit (IMU). This information can be used to determine the vehicle's driving path and predict future driving directions.

[0030] Driving environment feature extraction includes: identifying obstacles in the surrounding environment, such as other vehicles, pedestrians, road obstacles, etc. through sensor data. Information such as the location, speed, and distance of obstacles is crucial for assessing potential collision risks. Identifying traffic signs and road markings, such as traffic signals, stop signs, lane markings, etc., to help the system understand the current traffic environment and driving rules. Analyzing road conditions and weather conditions, such as slippery roads and poor visibility, to adjust vehicle driving strategies and predict possible dangerous situations.

[0031] Data analysis and model training include: using the extracted vehicle driving characteristics and driving environment characteristics for data analysis and model training. Machine learning, deep learning and other technologies can be used to build models to classify and predict potential dangerous situations, such as collision risks, road obstructions, etc. When training the model, it is necessary to use real-world data sets for training, and verify the accuracy and generalization ability of the model through methods such as cross-validation.

[0032] By extracting vehicle driving characteristics and driving environment characteristics and performing data analysis and model training based on these characteristics, on-board computers can more accurately identify potential dangerous situations and issue danger signals, providing a safer driving experience for smart connected vehicles.

[0033] S3: Real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at this time is evaluated. According to the evaluation results, a normal on-board computer working signal and an abnormal on-board computer working signal are respectively issued.

[0034] Monitor the data calculation efficiency and speed of the on-board computer during the preprocessing process to ensure that the data of the on-board computer can be processed in time, obtain the data processing speed delay ratio in real time, and judge the data processing efficiency according to the data processing speed delay ratio. The method for obtaining the data processing speed delay ratio is: During the data processing, the arrival timestamp and processing completion timestamp of each data packet are recorded. For each data packet, the time required from its arrival to its processing completion is calculated. The processing time is obtained by calculating the difference between the processing completion timestamp and the arrival timestamp. For all data packets in a time period, the average processing time is calculated, that is, the average processing time of each data packet. The data processing speed is calculated by adding the processing time of all data packets and then dividing it by the number of data packets; A fixed time window size M is determined, where the window size indicates the time for delay monitoring of data processing speed.

[0035] For each arriving data processing speed, record its arrival time ,in, =1, 2, 3, ..., K, where K is a positive integer greater than 0. A sliding window is maintained. When new data arrives, it is added to the window and the earliest data in the window is removed to keep the window size unchanged.

[0036] Calculate the delay time of data processing speed, that is, the time difference between the latest data processing speed and the earliest data processing speed. The calculation expression of delay time is: delay = - ;in, is the timestamp of the latest arriving data processing speed, It is the earliest timestamp of data processing speed arriving in the window, and delay is the delay time; Compare the delay time with the window size to get the delay ratio. The calculation formula for the data processing speed delay ratio is: delayratio= ;in, is the window size, which indicates the time period for delay monitoring, and delayratio is the data processing speed delay ratio.

[0037] The data processing speed delay ratio is an important indicator to measure the data processing efficiency and stability of the vehicle computer. The larger the delay ratio, the slower the data processing speed and the larger the processing delay, which may affect the real-time performance and responsiveness of the system, thereby reducing the stability of the vehicle computer's working state.

[0038] A high latency ratio means that there is a large gap between the data processing time and the data arrival time, resulting in the system being unable to respond to real-time sensor data in a timely manner. This may reduce the real-time performance of the monitoring and alarm system, making it impossible for the system to detect potential dangerous situations in a timely manner. Data processing delays will reduce the system's ability to respond to emergencies. If the latency ratio is large, the on-board computer may not be able to process sensor data in a timely manner, resulting in the system being unable to issue an alarm or take countermeasures in a timely manner. Data processing delays may cause system instability, such as data loss, memory overflow, and other problems, which in turn affect the normal operation of the system.

[0039] When the data processing speed delay ratio is large, it means that the data processing efficiency of the on-board computer is low, and the processing capacity may not meet the real-time needs of the system. In this case, the working state of the on-board computer may be relatively unstable, and there is a risk of system performance degradation, which may affect the overall performance and reliability of the intelligent networked vehicle monitoring and alarm system.

[0040] The data preprocessing stage and feature extraction stage are monitored in real time, and the efficiency and accuracy of feature extraction are analyzed to ensure that the extracted features can accurately reflect the vehicle's driving status and surrounding environment. When the vehicle driving data collection frequency deviates from the vehicle driving data collection frequency under the standard state, the vehicle driving data collection frequency outlier index is obtained. The method for obtaining the collection frequency outlier index is: The vehicle driving data is clustered according to the collection frequency, and k data points are randomly selected as the initial cluster centers, where k is the preset number of clusters.

[0041] For each data point , calculate its relationship with each cluster center The distance is usually calculated using Euclidean distance or other distance measurement methods. The specific calculation expression is: = ; In the formula, For data points To cluster center The distance between the data points Assigned to the nearest cluster center, Assign to cluster center , where jm= ; In the formula, jm is the data point With all cluster centers Distance The index of the smallest cluster center; For each cluster j, update its cluster center is the mean of all data points in the cluster. The specific calculation expression is: = ;in, represents the set of all data points of the jth cluster, express The mean of all data points in the cluster; Data points within a cluster and The mean of all data points in the cluster Compare and calculate the collection frequency outlier index. The specific calculation expression is: = ; In the formula, is the collection frequency outlier index.

[0042] The larger the acquisition frequency outlier index is, the greater the deviation of the acquisition frequency of some data points from that of most data points. This may indicate that the working state of the on-board computer is not stable enough, or there is an abnormality or failure. Specifically, when the acquisition frequency outlier index is large, the following situations may exist: System failure or anomaly: The onboard computer may have a failure or anomaly, causing the collection frequency of some data points to be significantly different from that of other data points.

[0043] Data collection is unstable. There may be problems with the data collection equipment or sensors, which leads to reduced stability of data collection and abnormal collection frequency of some data points.

[0044] Environmental changes or interference,Changes or interference in the vehicle's surrounding environment may affect the stability of data collection, resulting in abnormal fluctuations in the collection frequency of some data points.

[0045] The data processing speed delay ratio and the acquisition frequency outlier index are normalized, and the stability coefficient of the on-board computer working state is calculated according to the normalized data processing speed delay ratio and the acquisition frequency outlier index.

[0046] For example, the present invention can use the following formula to calculate the stability coefficient of the working state of the on-board computer, and the calculation expression is: = ; In the formula, is the stability coefficient, delayratio is the data processing speed delay ratio, is the collection frequency outlier index, is the ratio of data processing speed delay, the proportional coefficient of the acquisition frequency outlier index, and 0; The data processing speed delay ratio and the acquisition frequency outlier index are inversely proportional to the stability coefficient, that is, as the data processing speed delay ratio and the acquisition frequency outlier index increase, the stability coefficient gradually decreases, and the stability of the on-board computer working state becomes worse.

[0047] The obtained stability coefficient of the working state of the on-board computer is compared with the stability threshold. If the stability coefficient of the working state of the on-board computer is greater than or equal to the stability threshold, a normal working signal of the on-board computer is issued. If the stability coefficient of the working state of the on-board computer is less than the stability threshold, an abnormal working signal of the on-board computer is issued. The abnormal working signal of the on-board computer is sent to the relevant system or personnel in the form of a notification, such as displaying it on the dashboard of the vehicle cockpit, or notifying the owner or relevant maintenance personnel through a mobile device or application connected to the vehicle, so as to remind the driver or relevant personnel that there is a problem and prompt them to take appropriate measures.

[0048] In this embodiment, first, the on-board computer collects the raw data of the vehicle and the surrounding environment in real time through various sensors, and pre-processes the data to ensure the accuracy and consistency of the data. Then, the vehicle driving characteristics and driving environment characteristics are extracted from the pre-processed data, and these characteristics are used for data analysis and model training. Through the trained model, the on-board computer can identify potential dangerous situations and send out danger signals when necessary, so as to take corresponding measures in advance to ensure the safety of the vehicle. At the same time, the system monitors the pre-processing stage and feature extraction stage of the data in real time to ensure the efficiency and accuracy of data processing. When the vehicle sends out a danger signal, the system will immediately evaluate the stability of the working state of the on-board computer. According to the evaluation results, the system will send out a normal working signal of the on-board computer or an abnormal working signal of the on-board computer to remind relevant personnel to take necessary actions. By monitoring the vehicle status in real time, predicting potential dangerous situations, and issuing alarms when necessary, the safety and stability of intelligent networked vehicles can be effectively improved, providing a safer travel environment for drivers and passengers.

[0049] Example 2 S4: When the on-board computer sends out a signal of abnormal operation, diagnose and repair the on-board computer and its components, analyze the accuracy of the repaired on-board computer in identifying road information, and evaluate the accuracy of the repaired on-board computer in identifying information; analyze the execution effect of the vehicle executing the command issued by the on-board computer, and evaluate the real-time performance of the command issued by the on-board computer; When the on-board computer sends out an abnormal working signal, the on-board computer and its components are diagnosed and repaired, the accuracy of the repaired on-board computer in identifying road information is analyzed, and the information time deviation index of the on-board computer is obtained. The method for obtaining the information time deviation index is: Obtain the real-time feedback data of the on-board computer during the process of identifying road traffic signal information, and extract the information feedback time in the real-time feedback data , information recognition time And information reading time , obtain the expected information feedback time, information recognition time and information reading time, and calculate the information feedback time deviation value c, information recognition time deviation value c and information reading time deviation value c. Calculate the information time deviation index. The specific calculation expression is: = ; In the formula, is the information time deviation index.

[0050] The larger the information time deviation index is, the greater the time difference between the repaired onboard computer's recognition of road information and the actual situation is. This may indicate that the repaired onboard computer has low accuracy or is unstable in recognizing road information, specifically: Information recognition delay: The on-board computer may have a large delay in recognizing road information, resulting in a time difference between the recognition result and the actual situation.

[0051] Incorrect identification: the repaired onboard computer may have incorrectly identified road information, causing the identification result to be inconsistent with the actual situation, thereby causing time deviation.

[0052] Unstable recognition: The information recognition performance of the on-board computer may fluctuate or be unstable, resulting in inconsistent or large changes in the time deviation of the recognition results.

[0053] The execution effect of the vehicle executing the command issued by the on-board computer is analyzed, the command response efficiency abnormality index of the on-board computer is obtained, and the real-time performance of the command issued by the on-board computer is evaluated. The method for obtaining the command response efficiency abnormality index is as follows: Get the number of commands issued within time t and mark it as F, where F= , g is a positive integer greater than 0, and the actual command response speed of the on-board computer is measured, marked as D, and the utilization rate of the command queuing system is calculated. The specific calculation expression is: = ; In the formula, The utilization rate of the command queuing system is calculated by calculating the average queue length in the command queuing system. The specific calculation expression is: ;in, is the average queue length in the command queuing system, and calculates the average queue time in the command queuing system. The specific calculation expression is: ;in, is the average queuing time in the command queuing system. The average queuing time in the command queuing system is compared with the standard queuing time value to calculate the command response efficiency abnormality index. The specific calculation expression is: = ; In the formula, is the command response efficiency abnormality index, It is the standard queue time value.

[0054] The larger the command response efficiency abnormality index is, the worse the real-time performance of the commands issued by the on-board computer is. Specifically, when the command response efficiency abnormality index is large, the commands issued by the on-board computer take a long time to be received and executed by the vehicle, resulting in the real-time performance of the commands being affected. This may be caused by communication delays, processing delays, or other system performance issues.

[0055] At the same time, an increase in the command response efficiency abnormality index may mean that the response time of the on-board computer is unstable, that is, the response time of the command fluctuates greatly under different circumstances. This may cause the real-time performance of the command to be unreliable and unable to meet the needs of real-time applications. A larger command response efficiency abnormality index may indicate that the performance of the on-board computer has reached a bottleneck and cannot effectively process commands and respond in a timely manner.

[0056] S5: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of commands issued by the on-board computer, and make early predictions and warnings on risk failures of the on-board computer during vehicle driving.

[0057] The information time deviation index and the command response efficiency abnormality index are normalized, and the risk assessment coefficient of vehicle computer failure is calculated based on the normalized information time deviation index and command response efficiency abnormality index.

[0058] For example, the present invention may use the following formula to calculate the risk assessment coefficient of the vehicle-mounted computer failure, and the calculation expression is: = ; In the formula, is the risk assessment coefficient, is the information time deviation index, is the command response efficiency abnormality index, are the proportional coefficients of information time deviation index and command response efficiency abnormality index, respectively, and 0.

[0059] It can be seen from the calculation expression that the information time deviation index and the command response efficiency abnormality index are positively correlated with the risk assessment coefficient of vehicle-mounted computer failure, and as the information time deviation index and the command response efficiency abnormality index increase, the risk assessment coefficient of computer failure gradually increases, and the greater the risk of computer failure.

[0060] The obtained risk assessment coefficient of the on-board computer failure is compared with the risk threshold. If the risk assessment coefficient of the on-board computer failure is greater than or equal to the risk threshold, it means that the risk of the on-board computer failure may be high. At this time, a risk warning signal is issued to remind relevant personnel or systems to take necessary response measures, including further diagnosis, repair or replacement of the on-board computer to reduce the risk of failure; if the risk assessment coefficient of the on-board computer failure is less than the risk threshold, it means that the risk of the on-board computer failure may be low. At this time, no risk warning signal is issued, but the status of the on-board computer should still be monitored continuously and failure risk assessment should be performed regularly.

[0061] In this embodiment, when the on-board computer sends out a signal of abnormal operation, the on-board computer and its components are diagnosed and repaired, the accuracy of the repaired on-board computer in identifying road information is analyzed, and the accuracy of the repaired on-board computer information identification is evaluated; the execution effect of the vehicle executing the command issued by the on-board computer is analyzed, and the real-time performance of the command issued by the on-board computer is evaluated; the accuracy of the repaired on-board computer information identification and the real-time performance of the on-board computer in issuing commands are comprehensively analyzed, and the risk failure of the on-board computer during the vehicle driving process is predicted and warned in advance. By comprehensively evaluating the performance and stability of the repaired on-board computer, its accuracy and real-time performance in identifying road information and executing commands are ensured. At the same time, by predicting and warning of risk failures, potential failure risks can be discovered in advance, measures can be taken to prevent possible safety issues, and the safety and reliability of vehicle driving can be guaranteed.

[0062] Example 3 See also Figure 2 As shown, the intelligent networked vehicle monitoring and alarm system based on real-time data monitoring described in this embodiment includes a data processing module, a feature extraction module, a vehicle computer working state classification module, an analysis and evaluation module, and a prediction and warning module; Data processing module: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors, and pre-processes the collected raw data to ensure data consistency; Feature extraction module: extracts vehicle driving features and driving environment features from preprocessed data. Based on the extracted feature data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance. On-board computer working state classification module: real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at that time is evaluated. According to the evaluation results, the on-board computer working normal signal and the on-board computer working abnormal signal are respectively issued. Analysis and evaluation module: When the on-board computer sends out a signal of abnormal operation, the on-board computer and its components are diagnosed and repaired, the accuracy of the repaired on-board computer in identifying road information is analyzed, and the accuracy of the information identification of the repaired on-board computer is evaluated; the execution effect of the vehicle executing the command issued by the on-board computer is analyzed, and the real-time performance of the command issued by the on-board computer is evaluated; Prediction and warning module: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of the commands issued by the on-board computer, and provide early prediction and warning of risk failures of the on-board computer during vehicle driving.

[0063] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0064] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0065] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0066] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0067] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0068] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for monitoring and alarming intelligent networked vehicles based on real-time data monitoring, characterized in that: The steps include: S1: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors, and pre-processes the collected raw data to ensure data consistency; S2: Extract vehicle driving characteristics and driving environment characteristics from the preprocessed data. Based on the extracted characteristic data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance; S3: Real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at that time is evaluated. According to the evaluation results, a normal working signal of the on-board computer and an abnormal working signal of the on-board computer are respectively issued; S4: When the on-board computer sends out a signal of abnormal operation, diagnose and repair the on-board computer and its components, analyze the accuracy of the repaired on-board computer in identifying road information, and evaluate the accuracy of the repaired on-board computer in identifying information; analyze the execution effect of the vehicle executing the command issued by the on-board computer, and evaluate the real-time performance of the command issued by the on-board computer; S5: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of commands issued by the on-board computer, and make early predictions and warnings on risk failures of the on-board computer during vehicle driving.

2. According to claim 1, a method for monitoring and alarming intelligent networked vehicles based on real-time data monitoring is characterized in that: In S1, the collected raw data is preprocessed by Gaussian filtering to divide the data into consistent data and inconsistent data, including: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors. For the one-dimensional data x={x1,x2,...,xN}, Gaussian filtering is applied for preprocessing. The window size of the Gaussian filter is obtained and marked as w. The filtered data is yi. The calculation expression of the filtered data is: yi= *exp ; Where σ is the standard deviation of the Gaussian filter, and yi is the filtered data; For the filtered data yi, the fluctuation degree of each data point is calculated as a measure of data quality. The specific calculation expression of the fluctuation degree of the data point is: = ;in, is the fluctuation degree of the data points, is the mean of the data, is the standard deviation of the data; The fluctuation degree of the acquired data point is compared with the fluctuation threshold. If the fluctuation degree of the data point is greater than or equal to the fluctuation threshold, the data is marked as inconsistent data; if the fluctuation degree of the data point is less than the fluctuation threshold, the data is marked as consistent data.

3. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 2 is characterized in that: In S3, the data calculation efficiency and speed of the on-board computer during the preprocessing process are monitored, the data processing speed delay ratio is obtained in real time, and the data processing efficiency is judged according to the data processing speed delay ratio. The method for obtaining the data processing speed delay ratio is: During the data processing, the arrival timestamp and processing completion timestamp of each data packet are recorded. For each data packet, the time required from its arrival to its processing completion is calculated. For all data packets in a time period, the average processing time is calculated, that is, the average processing time of each data packet. The data processing speed is calculated by adding the processing time of all data packets and then dividing it by the number of data packets; Determine a fixed time window size M for delay monitoring of data processing speed. For each arriving data processing speed, record its arrival time. ,in, , K is a positive integer greater than 0, maintaining a sliding window. When new data arrives, it is added to the window and the earliest data in the window is removed to keep the window size unchanged; Calculate the delay time of data processing speed, that is, the time difference between the latest data processing speed and the earliest data processing speed. The calculation expression of delay time is: delay = - ;in, is the timestamp of the latest arriving data processing speed, It is the earliest timestamp of data processing speed arriving in the window, and delay is the delay time; Compare the delay time with the window size to get the delay ratio. The calculation formula for the data processing speed delay ratio is: delayratio= ;in, is the window size, which indicates the time period for delay monitoring, and delayratio is the data processing speed delay ratio.

4. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 3 is characterized in that: In S3, when the vehicle driving data collection frequency deviates from the vehicle driving data collection frequency under the standard state, the vehicle driving data collection frequency outlier index is obtained, and the method for obtaining the collection frequency outlier index is: Cluster the vehicle driving data according to the collection frequency, and randomly select k data points as the initial cluster centers, where k is the preset number of clusters; For each data point , calculate its relationship with each cluster center The specific calculation expression is: = ; In the formula, For data points To cluster center The distance between the data points Assigned to the nearest cluster center, Assign to cluster center , where jm= ; In the formula, jm is the data point With all cluster centers Distance The index of the smallest cluster center; For each cluster j, update its cluster center is the mean of all data points in the cluster. The specific calculation expression is: = ;in, represents the set of all data points of the jth cluster, express The mean of all data points in the cluster; Data points within a cluster and The mean of all data points in the cluster Compare and calculate the collection frequency outlier index. The specific calculation expression is: = ; In the formula, is the collection frequency outlier index.

5. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 4 is characterized in that: The data processing speed delay ratio and the acquisition frequency outlier index are normalized, and the stability coefficient of the on-board computer working state is calculated according to the normalized data processing speed delay ratio and the acquisition frequency outlier index.

6. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 5 is characterized in that: The obtained stability coefficient of the on-board computer's working status is compared with the stability threshold. If the stability coefficient of the on-board computer's working status is greater than or equal to the stability threshold, a signal indicating that the on-board computer is working normally is issued. If the stability coefficient of the on-board computer's working status is less than the stability threshold, a signal indicating that the on-board computer is working abnormally is issued.

7. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 6 is characterized by: In S4, when the on-board computer sends a work abnormality signal, the on-board computer and its components are diagnosed and repaired, the accuracy of the repaired on-board computer in identifying road information is analyzed, and the information time deviation index of the on-board computer is obtained. The method for obtaining the information time deviation index is: Obtain the real-time feedback data of the on-board computer during the process of identifying road traffic signal information, and extract the information feedback time in the real-time feedback data , information recognition time And information reading time , obtain the expected information feedback time, information recognition time and information reading time, and calculate the information feedback time deviation value c, information recognition time deviation value c and information reading time deviation value c. Calculate the information time deviation index. The specific calculation expression is: = ; In the formula, is the information time deviation index.

8. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 7 is characterized in that: In S4, the execution effect of the vehicle executing the command issued by the on-board computer is analyzed, the command response efficiency abnormality index of the on-board computer is obtained, and the real-time performance of the command issued by the on-board computer is evaluated. The method for obtaining the command response efficiency abnormality index is: Get the number of commands issued within time t and mark it as F, where F= , g is a positive integer greater than 0, and the actual command response speed of the on-board computer is measured, marked as D, and the utilization rate of the command queuing system is calculated. The specific calculation expression is: = ; In the formula, The utilization rate of the command queuing system is calculated by calculating the average queue length in the command queuing system. The specific calculation expression is: ;in, is the average queue length in the command queuing system, and calculates the average queue time in the command queuing system. The specific calculation expression is: ;in, is the average queuing time in the command queuing system. The average queuing time in the command queuing system is compared with the standard queuing time value to calculate the command response efficiency abnormality index. The specific calculation expression is: = ; In the formula, is the command response efficiency abnormality index, It is the standard queue time value.

9. The intelligent networked vehicle monitoring and alarm method based on real-time data monitoring according to claim 8 is characterized in that: In S5, the accuracy of the repaired on-board computer information recognition and the real-time performance of the on-board computer issuing commands are comprehensively analyzed, specifically: The information time deviation index and the command response efficiency abnormality index are normalized, and the risk assessment coefficient of the vehicle computer failure is calculated by the normalized information time deviation index and the command response efficiency abnormality index; The obtained risk assessment coefficient of the on-board computer failure is compared with the risk threshold. If the risk assessment coefficient of the on-board computer failure is greater than or equal to the risk threshold, a risk warning signal is issued; if the risk assessment coefficient of the on-board computer failure is less than the risk threshold, no risk warning signal is issued.

10. A monitoring and alarm system for intelligent networked vehicles based on real-time data monitoring, used to implement a monitoring and alarm method for intelligent networked vehicles based on real-time data monitoring as claimed in any one of claims 1 to 9, characterized in that: It includes data processing module, feature extraction module, vehicle computer working state classification module, analysis and evaluation module and prediction and warning module; Data processing module: The on-board computer collects raw data from the vehicle and its surroundings in real time through various sensors, and pre-processes the collected raw data to ensure data consistency; Feature extraction module: extracts vehicle driving features and driving environment features from preprocessed data. Based on the extracted feature data, the on-board computer performs data analysis and model training to identify potential dangerous situations and issue danger signals so that corresponding measures can be taken in advance. On-board computer working state classification module: real-time monitoring of the data preprocessing stage and feature extraction stage. When the vehicle sends out a danger signal, the stability of the on-board computer working state at that time is evaluated. According to the evaluation results, the on-board computer working normal signal and the on-board computer working abnormal signal are respectively issued. Analysis and evaluation module: When the on-board computer sends out a signal of abnormal operation, the on-board computer and its components are diagnosed and repaired, the accuracy of the repaired on-board computer in identifying road information is analyzed, and the accuracy of the information identification of the repaired on-board computer is evaluated; the execution effect of the vehicle executing the command issued by the on-board computer is analyzed, and the real-time performance of the command issued by the on-board computer is evaluated; Prediction and warning module: Comprehensively analyze the accuracy of information recognition of the repaired on-board computer and the real-time performance of the commands issued by the on-board computer, and provide early prediction and warning of risk failures of the on-board computer during vehicle driving.

Images