Intelligent vehicle driving data abnormal scene extraction method and system based on artificial intelligence

Abstract

The invention discloses an intelligent vehicle driving data abnormal scene extraction method and system based on artificial intelligence, and relates to the field of data analysis, and the method comprises the steps: calling basic information of each intelligent vehicle, and obtaining an abnormal risk assessment value of each intelligent vehicle; matching to obtain a driving data extraction proportion of each intelligent vehicle; driving data packets of all the intelligent vehicles are obtained, and comprehensive scene data are counted, processed and then imported into the integrated AI cloud computing center; according to the intelligent vehicle driving data abnormal scene extraction method based on artificial intelligence, the basic information of the intelligent vehicle is obtained from a plurality of data transmission terminals, the abnormal risk is analyzed and evaluated, the data extraction proportion is dynamically adjusted, and the risk vehicle is efficiently identified. And data features are mined by using a professional module, and abnormal scenes are labeled through clustering analysis, so that the data analysis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to an artificial intelligence-based method and system for extracting abnormal scenes from smart car driving data. Background Art

[0002] With the development of artificial intelligence technology, intelligent vehicles have become an important research direction in the automotive industry. Intelligent vehicles are equipped with various sensors (such as radar, camera, lidar, etc.) and advanced computing systems to realize the perception, decision-making and control of the surrounding environment, thereby realizing partial or full autonomous driving functions. However, in complex actual traffic environments, intelligent vehicles may encounter various abnormal scenarios, which are often the main cause of traffic accidents. Therefore, how to effectively extract and identify these abnormal scenarios is crucial to improving the safety and reliability of intelligent vehicles.

[0003] The prior art, such as the invention patent with announcement number: CN113992533B, is a method for detecting and identifying anomaly in vehicle CAN bus data. It adopts a modified self-attention mechanism and a model architecture of a multi-layer GRU network. It uses the characteristics of the self-attention mechanism to enhance the timing characteristics of the data. The multi-layer GRU network is used to further extract multi-dimensional timing data features, thereby improving the recognition accuracy of CAN bus data.

[0004] The prior art, such as the invention patent with announcement number: CN111448783B, is a vehicle network anomaly detection system and a vehicle network anomaly detection method. The vehicle network anomaly detection system comprises: a first communication unit, which receives first unit data as communication unit data under a first protocol from a first network; an anomaly judgment database, which contains information on anomaly judgment rules; an anomaly judgment unit, which uses the anomaly judgment rules to determine whether the first unit data has an anomaly; a unit data conversion unit, which extracts second unit data as communication unit data under a second protocol from the first unit data determined by the anomaly judgment unit to not contain an anomaly; and a second communication unit, which sends the extracted second unit data to the second network, the first unit data contains source information representing a first device as a sending source, and the second unit data contains a data identifier. When the anomaly judgment unit compares the combination of the sending source information and the data identifier with the anomaly judgment rule and determines that the first unit data contains an anomaly, the anomaly judgment unit performs a prescribed anomaly response process.

[0005] Based on the above technical solutions, it can be seen that in the field of abnormal scene detection, the existing technology has a relatively single data collection source, and the data processing method requires a large amount of computing resources. However, in actual applications, different smart cars may face different abnormal scenes, and the abnormal scene risks of different smart cars are also different. If only data from a single source is analyzed, the analysis results may not be universal. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides an artificial intelligence-based intelligent vehicle driving data abnormal scene extraction method and system. To achieve the above purpose, the present invention is implemented through the following technical solutions: an artificial intelligence-based intelligent vehicle driving data abnormal scene extraction method and system, including: The basic information of each smart car is retrieved from multiple data transmission terminals, and the abnormal risk assessment value of each smart car is obtained through analysis and processing. Based on the abnormal risk assessment value of each smart car, the driving data extraction ratio of each smart car is matched.

[0007] Based on the driving data extraction ratio of each smart car, the driving data packet of each smart car is obtained, and the time point of each driving abnormality mark is obtained at the same time. The comprehensive scene data of each driving abnormality mark time point is counted from the driving data packet, and the classified data is processed and then imported into the integrated AI cloud computing center.

[0008] The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs clustering processing to generate abnormal scene data of each smart car and stores it.

[0009] As a preferred technical solution, the basic information of each smart car is retrieved from multiple data transmission terminals. The specific process is as follows: A connection request is initiated from the integrated AI cloud computing center to each data transmission terminal. After receiving the connection request, each data transmission terminal packages the basic information of each smart car and sends it to the central server of the integrated AI cloud computing center.

[0010] The basic information of each smart car includes the accumulated mileage, accumulated driving time and accumulated number of driving failures of each smart car.

[0011] As a preferred technical solution, the analysis and processing to obtain the abnormal risk assessment value of each smart car specifically includes: The basic information of each smart car is analyzed and processed to obtain a basic information average value set and a basic information median value set.

[0012] The basic information average value set includes the cumulative average driving mileage, the cumulative average driving time and the cumulative average number of driving failures.

[0013] The basic information median value set includes the median value of the cumulative driving mileage, the median value of the cumulative driving time, and the median value of the cumulative number of driving failures.

[0014] The basic information average value set and the basic information median value set are comprehensively analyzed and processed to obtain the basic information median adjusted average value set, including the cumulative median adjusted average mileage, the cumulative median adjusted average driving time and the cumulative median adjusted average number of failures.

[0015] The basic information of each smart car is compared and analyzed with the set of adjusted median average values ​​of the basic information to obtain an abnormal risk assessment value of each smart car, and the abnormal risk assessment value of each smart car is used to characterize the risk of abnormality of each smart car during driving.

[0016] As a preferred technical solution, the driving data extraction ratio of each smart car is obtained by matching the abnormal risk assessment value of each smart car, which specifically includes: Based on the abnormal risk assessment value of each smart car, the driving data extraction ratio corresponding to each abnormal risk assessment value interval in the built-in database of the integrated AI cloud computing center is mapped and matched to obtain the driving data extraction ratio of each smart car.

[0017] As a preferred technical solution, the obtaining of each driving abnormality marking time point and counting of comprehensive scene data of each driving abnormality marking time point from the driving data packet specifically include: Identify the time points marked as driving abnormalities in the driving data packets of each smart car, and count the longitudinal abnormal time point data and lateral abnormal time period data of each driving abnormality marked time point, and record them as comprehensive scene data of each driving abnormality marked time point.

[0018] The comprehensive scenario data at each driving abnormality marking time point includes environmental perception data and control system data at each driving abnormality marking time point.

[0019] The environmental perception data includes image data, point cloud data and radar data at each driving abnormality marking time point.

[0020] The control system data includes engine response time, braking deceleration, braking distance, suspension compression and suspension rebound speed at each driving abnormality marking time point.

[0021] As a preferred technical solution, the classified data is processed and then imported into the integrated AI cloud computing center, specifically including: The image data, point cloud data and radar data at each driving abnormality marking time point are respectively imported into the local image feature extraction module, point cloud geometric feature extraction module and radar feature extraction module of the AI ​​cloud computing center, and corresponding data processing is performed to obtain the image feature data, point cloud geometric feature data and radar feature data at each driving abnormality marking time point.

[0022] The control system data at each driving abnormality marking time point is compared and analyzed with the control system data verification set pre-stored in the local database to obtain the control system state characteristic value at each driving abnormality marking time point. The control system state characteristic value at each driving abnormality marking time point is used to confirm whether the control system at each driving abnormality marking time point is normal. If the control system state characteristic value at a certain driving abnormality marking time point is greater than or equal to a preset control system state abnormality threshold, the control system at the driving abnormality marking time point is determined to be abnormal. If the control system state characteristic value at a certain driving abnormality marking time point is less than the control system state abnormality threshold, the control system at the driving abnormality marking time point is determined to be normal.

[0023] The statistical control system marks the time point of each driving anomaly when it is abnormal, which is recorded as the marking time point of each abnormal control system, and the image feature data, point cloud geometric feature data and radar feature data of each abnormal control system marking time point are stored in the database under the abnormal control system label.

[0024] The control system data verification set includes an engine response time threshold, a braking deceleration threshold, a braking distance threshold, a suspension compression threshold and a suspension rebound speed threshold.

[0025] The image feature data, point cloud geometric feature data, and radar feature data at each driving abnormality marking time point when the control system is normal are collectively recorded as the processed comprehensive scene data at each driving abnormality marking time point.

[0026] As a preferred technical solution, the integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs clustering processing to generate abnormal scene data of each smart car and stores it. The specific processing conditions are: The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs K-means clustering processing and analysis to obtain multiple abnormal scene feature clusters of each driving abnormality marking time point, and obtains the data features of each abnormal cluster of each driving abnormality marking time point after iterative updating, and matches the data features of each abnormal cluster of each driving abnormality marking time point with the corresponding abnormal scene labels pre-stored in the integrated AI cloud computing center to obtain each abnormal scene label of each driving abnormality marking time point.

[0027] Based on each abnormal scene label at each driving abnormality marking time point, the processed comprehensive scene data at each driving abnormality marking time point is stored in a database under each corresponding abnormal scene label.

[0028] As a preferred technical solution, it also includes detecting the transmission channel performance parameters from each data transmission terminal to the integrated AI cloud computing center, processing and analyzing to generate data quality repair factors and performing data quality repair, specifically including: The transmission channel performance parameters include real-time signal strength, interface rate, real-time delay and real-time signal-to-noise ratio of each data transmission terminal.

[0029] The transmission channel performance verification parameters are retrieved from the built-in database of the integrated AI cloud computing center, including real-time signal strength verification value, interface rate verification value, real-time delay verification value and real-time signal-to-noise ratio verification value.

[0030] A comprehensive comparison and analysis is performed on the transmission channel performance parameters and the transmission channel performance verification parameters to obtain the data quality impact value of each transmission channel, and the data quality impact value of each transmission channel is mapped and matched with the data quality repair factors corresponding to each data quality impact value interval pre-stored in the built-in database of the integrated AI cloud computing center to obtain the data quality repair factor of each transmission channel. The data quality impact value of each transmission channel is used to characterize the impact of the performance of each transmission channel on the data quality, and data quality repair is performed based on the data transmission repair factor.

[0031] As a preferred technical solution, the analysis and processing obtains the abnormal risk assessment value of each smart car, and the specific processing method is: ; in, For the The abnormal risk assessment value of a smart car, For the The accumulated mileage of a smart car, For the The cumulative driving time of a smart car, For the The cumulative number of driving failures of a smart car, The average mileage adjusted for the cumulative median mileage driven is The average time for driving is adjusted for the cumulative median. The cumulative median adjusted average number of failures for driving, is the weight factor of accumulated mileage, is the weight factor of the accumulated driving time, is the weight factor of the average number of cumulative failures during driving, Number the smart car. , is the total number of smart cars. The softplus function is a built-in function in Python. .

[0032] The AI-based intelligent vehicle driving data abnormal scene extraction system includes: The abnormal risk assessment module is used to retrieve the basic information of each smart car from multiple data transmission terminals, analyze and process to obtain the abnormal risk assessment value of each smart car, and match the driving data extraction ratio of each smart car based on the abnormal risk assessment value of each smart car.

[0033] The data extraction module is used to obtain the driving data packet of each smart car based on the driving data extraction ratio of each smart car, and at the same time obtain the time point of each driving abnormality mark, count the comprehensive scene data of each driving abnormality mark time point from the driving data packet, and import it into the integrated AI cloud computing center after classified data processing.

[0034] The scene extraction module is used to enable the integrated AI cloud computing center to receive the processed comprehensive scene data of each driving abnormality marking time point, perform clustering processing and analysis to generate abnormal scene data of each smart car and store it.

[0035] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects: (1) The present invention provides an artificial intelligence-based method and system for extracting abnormal scenarios from driving data of smart cars. The method obtains comprehensive data by retrieving basic information of smart cars from multiple data transmission terminals, analyzes and processes the basic information of smart cars, obtains abnormal risk assessment values, dynamically adjusts the driving data extraction ratio, effectively allocates data collection resources, and improves efficiency.

[0036] (2) The present invention comprehensively analyzes the driving environment by statistically synthesizing scene data, including environmental perception data and control system data. The image feature extraction module, point cloud geometric feature extraction module and radar data processing module are used to classify and process the data, and the feature information in the data is deeply mined. Through clustering processing and analysis, different abnormal scenes can be identified, and each scene can be labeled to facilitate subsequent data storage and analysis.

[0037] (3) The present invention detects the performance parameters of the data transmission channel and generates a data quality repair factor to ensure the integrity and accuracy of the data during the transmission process, reduce maintenance costs, and improve data processing efficiency.

[0038] Of course, any product implementing the present invention does not necessarily need to achieve all of the above advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0040] Figure 2 It is a schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0042] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0043] See also Figure 1 As shown, an embodiment of the present invention provides an abnormal scene extraction method for smart car driving data based on artificial intelligence, comprising: The basic information of each smart car is retrieved from multiple data transmission terminals, and the abnormal risk assessment value of each smart car is obtained through analysis and processing. Based on the abnormal risk assessment value of each smart car, the driving data extraction ratio of each smart car is matched.

[0044] The specific process of retrieving basic information of each smart car from multiple data transmission terminals is as follows: A connection request is initiated from the integrated AI cloud computing center to each data transmission terminal. After receiving the connection request, each data transmission terminal packages the basic information of each smart car and sends it to the central server of the integrated AI cloud computing center.

[0045] The integrated AI cloud computing center is an integrated cloud processor for receiving, sending, calculating, retrieving and storing data in an embodiment of the present invention.

[0046] The various data transmission terminals, in the embodiment of the present invention, are data transmission ports pre-configured in each smart car, and are used to send basic information and driving data packets of each smart car.

[0047] The basic information of each smart car includes the accumulated mileage, accumulated driving time and accumulated driving fault times of each smart car, which is obtained by retrieving the driving record log of each smart car.

[0048] The accumulated mileage refers to the total mileage that the smart car has traveled since it was manufactured to the current time point. The accumulated mileage can be used to evaluate the usage intensity of the vehicle.

[0049] The accumulated driving time refers to the accumulated driving time of the smart car since it was manufactured to the current time point. The accumulated time can be used to understand the average running time and idle time of the vehicle, so as to evaluate its operating efficiency. Long-term operation may cause aging of vehicle components, and the accumulated time helps to evaluate the overall condition of the vehicle.

[0050] The cumulative number of driving failures refers to the total number of failures that have occurred in the smart car since it left the factory until the current time point. The reliability of the vehicle can be evaluated by the number of failures.

[0051] The analysis and processing obtains the abnormal risk assessment value of each smart car, specifically including: The basic information of each smart car is analyzed and processed to obtain a basic information average value set and a basic information median value set.

[0052] The basic information average value set includes the cumulative average driving mileage, the cumulative average driving time and the cumulative average number of driving failures.

[0053] The basic information median value set includes the median value of the cumulative driving mileage, the median value of the cumulative driving time, and the median value of the cumulative number of driving failures.

[0054] The basic information average value set and the basic information median value set are comprehensively analyzed and processed to obtain the basic information median adjusted average value set, including the cumulative median adjusted average mileage, the cumulative median adjusted average driving time and the cumulative median adjusted average number of failures.

[0055] The basic information of each smart car is compared and analyzed with the set of adjusted median average values ​​of the basic information to obtain an abnormal risk assessment value of each smart car, and the abnormal risk assessment value of each smart car is used to characterize the risk of abnormality of each smart car during driving.

[0056] The analysis and processing obtains the abnormal risk assessment value of each smart car, and the specific processing method is: ; ; ; ; in, For the The abnormal risk assessment value of a smart car, For the The accumulated mileage of a smart car, For the The cumulative driving time of a smart car, For the The cumulative number of driving failures of a smart car, is the average accumulated mileage. is the average cumulative driving time, is the average number of cumulative failures during driving, is the median value of the accumulated mileage. is the median value of the cumulative driving time, is the median value of the cumulative number of driving failures, The average mileage adjusted for the cumulative median mileage driven is The average time for driving is adjusted for the cumulative median. The cumulative median adjusted average number of failures for driving, is the weight factor of accumulated mileage, is the weight factor of the accumulated driving time, is the weight factor of the average number of cumulative failures during driving, Adjust the scale factor for the mean, Adjust the scale factor for the median value, Number the smart car. , is the total number of smart cars. The softplus function is a built-in function in Python. .

[0057] It should be noted that the mean value adjustment coefficient and the median value adjustment coefficient are both between 0 and 1 and meet the The average value adjustment coefficient is an influencing factor of the median adjusted average value of each basic information preset in the integrated AI cloud computing center, which indicates the numerical value of the influence degree of the average value on the median adjusted average value of each basic information. The median value adjustment coefficient is an influencing factor of the median adjusted average value of each basic information preset in the integrated AI cloud computing center, which indicates the numerical value of the influence degree of the median value on the median adjusted average value of each basic information. When used, the average value adjustment coefficient and the median value adjustment coefficient can be directly obtained from the integrated AI cloud computing center, and the corresponding relationship is a preset mapping relationship. For example: the basic information of each smart car involved in the embodiment of the present invention includes the accumulated mileage, accumulated driving time and accumulated driving failure times of each smart car. After the average value and median value are calculated, the mapping set is input for mapping matching to obtain the average value adjustment coefficient and the median value adjustment coefficient involved in the embodiment of the present invention, and the mapping relationship is one-to-one correspondence.

[0058] It should be noted that the weight factor of the accumulated mileage, the accumulated driving time and the accumulated average number of failures are all within the range of 0 to 1 and meet the following conditions: The weight factor of the accumulated mileage is an influencing factor of the abnormal risk assessment value of each smart car preset in the integrated AI cloud computing center, indicating the degree of influence of the accumulated mileage on the abnormal risk assessment value of each smart car; the weight factor of the accumulated driving time is an influencing factor of the abnormal risk assessment value of each smart car preset in the integrated AI cloud computing center, indicating the degree of influence of the accumulated driving time on the abnormal risk assessment value of each smart car; the weight factor of the average number of accumulated driving failures is an influencing factor of the abnormal risk assessment value of each smart car preset in the integrated AI cloud computing center, indicating the influence of the average number of accumulated driving failures on the abnormal risk assessment value of each smart car degree; when in use, the weight factor of the accumulated mileage, the weight factor of the accumulated driving time and the weight factor of the average number of accumulated driving failures can be directly obtained from the integrated AI cloud computing center, and the acquisition method is a preset mapping relationship, for example: the basic information of each smart car involved in the embodiment of the present invention, including the accumulated mileage, accumulated driving time and accumulated driving failure times of each smart car, is input into the preset mapping set in the database for mapping and matching to obtain the weight factor of the accumulated mileage, accumulated driving time and accumulated driving failure average number of weight factors involved in the embodiment of the present invention, and the mapping relationship is one-to-one correspondence.

[0059] It should also be noted that the basic information of each smart car includes the cumulative mileage, cumulative driving time and cumulative driving fault number of each smart car. There is a certain correlation between these parameters and they are inseparable from each other. Usually, the cumulative mileage and cumulative driving time are directly related. The longer the mileage of the vehicle, the more time it usually takes. The relationship between these two parameters is also affected by the average driving speed of the vehicle. The faster the speed, the more mileage is accumulated in the same time; the slower the speed, the less mileage is accumulated in the same time. As the cumulative mileage increases, vehicle parts may be more prone to failure due to wear, so these two parameters show a positive correlation. Long-term operation may cause overheating or fatigue of vehicle parts, thereby increasing the number of failures. In the absence of other factors, the cumulative mileage and cumulative driving time are usually positively correlated with the cumulative number of driving faults, that is, as the mileage or time increases, the number of failures may also increase.

[0060] The driving data extraction ratio of each smart car is obtained by matching the abnormal risk assessment value of each smart car, specifically including: Based on the abnormal risk assessment value of each smart car, the driving data extraction ratio corresponding to each abnormal risk assessment value interval in the built-in database of the integrated AI cloud computing center is mapped and matched to obtain the driving data extraction ratio of each smart car.

[0061] The driving data extraction ratio of each smart car is used to determine the driving data extraction amount of each smart car. For example, if the driving data extraction ratio corresponding to the abnormal risk assessment value of a smart car is 20%, then 20% of the driving data of the smart car is selected.

[0062] By matching the abnormal risk assessment values ​​of each smart car to obtain the corresponding driving data extraction ratio, different data extraction strategies are formulated according to the risk levels of different vehicles. High-risk vehicles will be assigned a higher data extraction ratio to ensure that more resources are invested in high-risk smart cars, while reducing unnecessary data collection and lowering data storage and processing costs.

[0063] It should be noted that the embodiment of the present invention also includes detecting the transmission channel performance parameters from each data transmission terminal to the integrated AI cloud computing center, and processing and analyzing to generate data quality repair factors, specifically including: The transmission channel performance parameters include real-time signal strength, interface rate, real-time delay and real-time signal-to-noise ratio.

[0064] Real-time signal strength refers to the strength of the signal level in the transmission channel, usually expressed in decibels (dB). Signal strength is directly related to the transmission distance and anti-interference ability of the signal. The higher the signal strength, the longer the transmission distance, and the stronger the ability to resist external interference. If the signal strength is too low, it may cause data transmission errors or interruptions.

[0065] The interface rate refers to the transmission rate of the data transmission channel, usually expressed in bits per second (bps) or megabits per second (Mbps). The interface rate determines the speed of data transmission. The higher the rate, the greater the amount of data that can be transmitted per unit time.

[0066] Real-time latency refers to the time required for data to travel from the sender to the receiver, usually measured in milliseconds (ms). The lower the latency, the better the real-time performance of the data. High latency may cause the real-time performance of data transmission to deteriorate, affecting the performance of the application.

[0067] Real-time signal-to-noise ratio (SNR) refers to the ratio of signal power to noise power, usually expressed in decibels (dB). SNR is an important parameter for measuring signal quality. The higher the SNR, the greater the ratio of effective information in the signal to noise, and the higher the reliability of data transmission. A low SNR means a high noise level, which may cause data transmission errors or packet loss.

[0068] The transmission channel performance verification parameters are retrieved from the built-in database of the integrated AI cloud computing center, including real-time signal strength verification value, interface rate verification value, real-time delay verification value and real-time signal-to-noise ratio verification value.

[0069] The performance parameters of each transmission channel are comprehensively compared and analyzed with the performance verification parameters of the transmission channel to obtain the data quality impact value of each transmission channel, and the data quality impact value of each transmission channel is mapped and matched with the data quality repair factors corresponding to each data quality impact value interval pre-stored in the built-in database of the integrated AI cloud computing center to obtain the data quality repair factor of each transmission channel. The larger the data quality impact value, the larger the data quality repair factor. The data quality repair factor of each transmission channel is used to repair the data loss incurred during the transmission from each data transmission terminal to the integrated AI cloud computing center.

[0070] The obtaining of the data quality impact value of each transmission channel specifically includes: ; in, For the The data quality impact value of each transmission channel is: For the Real-time signal strength of each transmission channel, For the The interface rate of the transmission channel, For the The real-time delay of each transmission channel, For the Real-time signal-to-noise ratio of each transmission channel, is the real-time signal strength verification value, is the interface rate check value, is the real-time delay check value, is the real-time signal-to-noise ratio verification value, is the transmission channel number, , is the total number of transmission channels, is the real-time delay weight factor, is the real-time signal strength weight factor, is the interface rate weight factor, is the real-time signal-to-noise ratio weight factor.

[0071] It should be noted that the real-time delay weight factor, real-time signal strength weight factor, interface rate weight factor and real-time signal-to-noise ratio weight factor all have a value range between 0 and 1 and meet The real-time delay weight factor is the impact factor corresponding to the data quality impact value of each transmission channel preset in the integrated AI cloud computing center, which indicates the numerical value of the impact degree of real-time delay on the data quality impact value of each transmission channel. The real-time signal strength weight factor is the impact factor corresponding to the data quality impact value of each transmission channel preset in the integrated AI cloud computing center, which indicates the numerical value of the impact degree of real-time signal strength on the data quality impact value of each transmission channel. The interface rate weight factor is the impact factor corresponding to the data quality impact value of each transmission channel preset in the integrated AI cloud computing center, which indicates the numerical value of the impact degree of interface rate on the data quality impact value of each transmission channel. The real-time signal-to-noise ratio weight factor is the data quality impact value corresponding to the data quality impact value of each transmission channel preset in the integrated AI cloud computing center. The impact factor represents the numerical value of the influence degree of the real-time signal-to-noise ratio on the data quality impact value of each transmission channel. When used, the real-time delay weight factor, the real-time signal strength weight factor, the interface rate weight factor and the real-time signal-to-noise ratio weight factor can be directly obtained from the integrated AI cloud computing center. The acquisition method is a preset mapping relationship. For example, the data quality impact value of each transmission channel involved in the embodiment of the present invention, such as the transmission channel performance parameters including real-time signal strength, interface rate, real-time delay and real-time signal-to-noise ratio, is input into the preset mapping set in the database for mapping and matching to obtain the real-time delay weight factor, real-time signal strength weight factor, interface rate weight factor and real-time signal-to-noise ratio weight factor involved in the embodiment of the present invention, wherein the mapping relationship is one-to-one correspondence.

[0072] It should be noted that the transmission channel performance parameters include real-time signal strength, interface rate, real-time delay and real-time signal-to-noise ratio. These parameters have a certain correlation and are inseparable from each other. The real-time signal strength is a component of the real-time signal-to-noise ratio. The higher the signal strength, the higher the signal-to-noise ratio is usually because the ratio of signal power to noise power increases. The real-time signal strength can affect the interface rate. If the signal strength is high enough, the transmission channel can support a higher data rate. On the contrary, if the signal strength decreases, it may cause a decrease in the transmission rate because the system may need to reduce the rate to ensure the reliability of the data. The real-time signal-to-noise ratio is an important factor affecting the interface rate. A high signal-to-noise ratio can support a higher data rate because there is more valid information in the signal and the error rate is lower. A low signal-to-noise ratio may cause data transmission errors, which requires data retransmission, which reduces the actual effective transmission rate. The real-time signal strength and the real-time signal-to-noise ratio are interrelated, and they jointly determine the clarity and transmission quality of the signal. The interface rate is affected by the real-time signal strength and the real-time signal-to-noise ratio because these parameters determine the capacity and reliability of the transmission channel. Real-time latency can be affected by all other parameters because it reflects the time it takes for data to get from the sender to the receiver, which is affected by signal quality, transmission rate, and network conditions.

[0073] The repair data is lost during the transmission from each data transmission terminal to the integrated AI cloud computing center. The specific process is as follows: Based on the data quality repair factor of each transmission channel, the data quality repair parameter set corresponding to the data quality repair factor of each transmission channel pre-stored in the integrated AI cloud computing center is matched to obtain the data quality repair parameter set of each transmission channel, wherein the data quality repair parameter set includes a data cleaning ratio adjustment value, a data filling ratio adjustment value and a data deduplication ratio adjustment value.

[0074] The larger the data quality repair factor is, the larger the data quality repair parameter set including the data cleaning ratio adjustment value, the data filling ratio adjustment value and the data deduplication ratio adjustment value is.

[0075] Based on the data quality repair parameter set of each transmission channel, the basic information and driving data packets of each smart car after transmission are repaired accordingly. For example, the data cleaning ratio adjustment value of a certain transmission channel is 30%, the data filling ratio adjustment value is 20%, and the data deduplication ratio adjustment value is 15%. Then, the basic information and driving data packets of each smart car transmitted by the transmission channel are cleaned, filled and deduplicated in corresponding proportions.

[0076] Based on the driving data extraction ratio of each smart car, the driving data packet of each smart car is obtained, and the time point of each driving abnormality mark is obtained at the same time. The comprehensive scene data of each driving abnormality mark time point is counted from the driving data packet, and the classified data is processed and then imported into the integrated AI cloud computing center.

[0077] The step of obtaining each driving abnormality marking time point and collecting comprehensive scene data of each driving abnormality marking time point from the driving data packet specifically includes: Identify the time points marked as driving abnormalities in the driving data packets of each smart car, integrate the time points marked as driving abnormalities in the driving data packets of each smart car into each driving abnormality marking time point, count the longitudinal abnormal time point data and the lateral abnormal time period data of each driving abnormality marking time point, and comprehensively record them as the comprehensive scene data of each driving abnormality marking time point.

[0078] The longitudinal abnormal time point data of each driving abnormality mark time point is used to locate the position of each driving abnormality mark time point in the driving data packet.

[0079] The horizontal abnormal time period data refers to the data contained in the time period before and after each driving abnormality mark time point is intercepted according to the preset time period length of each smart car after locating the position of each driving abnormality mark time point in the driving data packet, and the data is recorded as the comprehensive scene data of each driving abnormality mark time point.

[0080] The preset time period length of each smart car specifically includes: Based on the abnormal risk assessment value of each smart car, the preset time period length corresponding to each abnormal risk assessment value interval in the database is mapped and matched to obtain the preset time period length of each smart car. The higher the abnormal risk assessment value of a smart car, the longer the corresponding preset time period length.

[0081] The comprehensive scenario data at each driving abnormality marking time point includes environmental perception data and control system data at each driving abnormality marking time point.

[0082] The environmental perception data includes image data, point cloud data and radar data at each driving abnormality marking time point.

[0083] The image data includes scene images of the front, rear, side, top and bottom views of each smart car acquired through a driving recorder and an external integrated camera.

[0084] The point cloud data includes the edge three-dimensional coordinates of each object in the scene, the laser intensity and the reflectivity of the laser pulse, which are obtained by the laser radar sensor. Among them, the edge three-dimensional coordinates refer to the spatial position of each point on the edge of the object in the scene, usually expressed as (X, Y, Z). It is used to determine the exact position of the object in three-dimensional space (i.e., abnormal scene). The three-dimensional shape and structure of the object can be reconstructed through the edge coordinates. Laser intensity refers to the intensity value returned by the laser pulse emitted by the laser radar after being reflected by the object. Objects of different materials reflect different laser intensities, which is used to identify the material of the object. Laser intensity can reflect the smoothness or roughness of the surface of an object. The reflectivity of the laser pulse refers to the proportion of light reflected back to the sensor after the laser pulse interacts with the surface of the object. Different objects have different reflectivities, which are used to classify objects and detect obstacles.

[0085] The radar data includes distance information, speed information and radar cross section (RCS), where the distance information is calculated by emitting a pulse from a transmitter and measuring the time it takes for the pulse to be reflected back, including the straight-line distance between each smart car and other objects in the scene. The speed information is measured by a laser speed meter, including the absolute speed and relative speed between each smart car and other objects in the scene. The radar cross section is the ability of an object to reflect a radar signal, and is used to estimate the size and shape of objects in the scene.

[0086] The control system data includes engine response time, braking deceleration, braking distance, suspension compression and suspension rebound speed at each driving abnormality marking time point, which are obtained through the on-board diagnostic system.

[0087] Engine response time refers to the time from when an acceleration request is issued (for example, pressing the accelerator pedal) to when the engine output power begins to increase. Engine response time is an important indicator of engine dynamic performance.

[0088] Braking deceleration is the rate at which a vehicle loses speed during braking, usually measured in meters per second² (m / s²). Braking deceleration reflects the effectiveness of the braking system. A higher braking deceleration can slow down or stop the vehicle in a shorter distance, which is essential for safe parking in emergency situations.

[0089] Braking distance refers to the distance a vehicle needs to stop completely from a certain speed. Braking distance is an important indicator of vehicle safety. Short braking distance can provide more reaction time and space in an emergency, thus reducing the occurrence of accidents.

[0090] Suspension compression refers to the degree of compression of the vehicle suspension system when it is subjected to a load (such as vehicle weight, acceleration or braking), which mainly reflects the deformation of the suspension system. In the embodiment of the present invention, the degree of compression of the vehicle suspension system is measured by the compressed length of the spring, in units of mm (millimeter). Suspension compression affects the driving stability, comfort and handling of the vehicle. Appropriate suspension compression can ensure good contact between the wheels and the ground and improve grip.

[0091] Suspension rebound speed refers to the speed at which the suspension system returns to its original position after releasing the load. Suspension rebound speed affects the dynamic behavior and ride comfort of the vehicle. Fast rebound can reduce the fluctuation of the vehicle on bumpy roads and improve the vehicle's handling and stability.

[0092] The classified data is then processed and imported into the integrated AI cloud computing center, specifically including: The image data, point cloud data and radar data at each driving abnormality marking time point are respectively imported into the local image feature extraction module, point cloud geometric feature extraction module and radar data processing module of the AI ​​cloud computing center, and corresponding data processing is performed to obtain the image feature data, point cloud geometric feature data and radar feature data at each driving abnormality marking time point.

[0093] The obtaining of the image feature data, point cloud geometric feature data and radar feature data at each driving abnormality marking time point specifically includes: After preprocessing the image data of each driving abnormality marking time point, the image feature extraction module uses the ORB feature extraction algorithm to encode the identified image features (such as traffic lights, pedestrians, vehicles and road traffic signs) into feature vectors, and uses the PCA feature selection algorithm to filter the feature vectors and summarize them into image feature data of each driving abnormality marking time point.

[0094] After preprocessing the point cloud data of each driving abnormality marking time point, the point cloud geometric feature extraction module uses PCL to calculate the surface normal, curvature and other geometric features of the point cloud, and summarizes them into the point cloud geometric feature data of each driving abnormality marking time point.

[0095] After preprocessing the radar data at each driving abnormality marking time point, the radar data processing module identifies the moving objects in the radar data through the CFAR algorithm and performs path tracking, extracts the motion data of each moving object, including the average speed, direction and distance of movement, and summarizes them as radar feature data.

[0096] It should be noted that the ORB feature extraction algorithm (Oriented FAST and Rotated BRIEF) is an algorithm used for feature detection and description in computer vision. The ORB feature extraction algorithm includes FAST key point detection and BRIEF feature descriptor, specifically including: FAST (Features from Accelerated Segment Test) is an algorithm for detecting key points (feature points) in an image. A pixel is compared to its surrounding pixels to determine whether it is a key point. If a pixel is brighter or darker than enough pixels in its neighborhood, it is marked as a key point. ORB uses the FAST algorithm to quickly detect key points in an image.

[0097] BRIEF (Binary Robust Independent Elementary Features) is a feature descriptor that generates a binary string (a sequence of 0s and 1s) by comparing the brightness of a pair of pixels around a key point. This string is the descriptor of the key point and is used in the subsequent matching process.

[0098] In order to make the BRIEF descriptor rotation-invariant, the ORB algorithm first computes the orientation of each keypoint. This is usually done by computing the histogram of gradient orientations within the neighborhood of the keypoint and finding the dominant orientation. The pixel pairs that the BRIEF descriptors are compared against are rotated according to this orientation, ensuring that the descriptors are insensitive to image rotation.

[0099] ORB achieves scale invariance by building a pyramid of images and applying FAST to detect key points at different scales. This allows key points to be detected at different scales, allowing the algorithm to handle image features of different sizes.

[0100] The PCA feature selection algorithm (Principal Component Analysis) is a statistical method that transforms a set of possibly correlated variables into a set of linearly uncorrelated variables through orthogonal transformation. These new variables are called principal components. PCA is mainly used for data dimensionality reduction, that is, reducing the dimension of the data while retaining the original data information as much as possible. In feature selection, PCA can help identify and select the most important features. The basic steps of PCA include: Step 1: Standardize the data. Since PCA is greatly affected by the data scale, it is usually necessary to standardize the data first.

[0101] Step 2: Calculate the covariance matrix. The covariance matrix describes the correlation between the features in the data. If the covariance of two features is large, it means that they are likely to change together.

[0102] Step 3: Calculate the eigenvalues ​​and eigenvectors of the covariance matrix. By calculating the eigenvalues ​​and eigenvectors of the covariance matrix, we can find the main directions of the data (i.e., the principal components).

[0103] Step 4: Select the main components. The size of the eigenvalue represents the variance of the data in the direction of the corresponding eigenvector. Select the eigenvectors corresponding to the largest eigenvalues. These eigenvectors are the main components of the data.

[0104] Step 5: Form the projection matrix. The selected eigenvectors are combined into a new matrix called the projection matrix. This matrix will be used to project the original data into a lower dimensional space.

[0105] Step 6: Transform the data. Use the projection matrix to transform the original data into the new space.

[0106] In feature selection, PCA can help identify which principal components contain most of the information in the data.

[0107] By observing the size of the eigenvalues ​​of each principal component for the data, we can determine which original features contribute the most to the variance of the data. If the first few principal components can explain most of the variance of the data, then these principal components can be used to replace the original features, thereby achieving data dimensionality reduction.

[0108] The PCL (Point Cloud Library) is an open source library for 2D / 3D image and point cloud processing.

[0109] The CFAR (Constant False Alarm Rate) algorithm is a detection technique used in radar and sonar signal processing. The false alarm rate is kept at a predetermined level by adaptively adjusting the detection threshold, even under changing environmental noise or interference levels. The CFAR algorithm is widely used in target detection in radar systems to ensure that real targets can be stably identified in complex background noise.

[0110] Image feature data is used to identify key visual elements in the driving environment and detect abnormal events (such as vehicle deviation from the lane, collision, etc.).

[0111] The point cloud geometric feature data is used to provide the three-dimensional structural information of the surrounding environment, and the geometric features such as surface normal and curvature are used to identify and classify obstacles on the road, such as pedestrians, vehicles, etc. The surface normal is used to represent the vector of the surface direction of each point in the point cloud. The curvature is used to describe the degree of curvature of the point cloud surface and is used to identify the shape of the object.

[0112] The radar data obtains dynamic information of objects in the scene through moving object recognition and path tracking, including the average speed, direction and distance of each object. It is mainly used to analyze the speed status and relative position of the vehicle, and to determine whether there is a rear-end collision, whether a safe distance is maintained, and other abnormal driving conditions.

[0113] The control system data at each driving abnormality marking time point is compared and analyzed with the control system data verification set pre-stored in the local database, the control system data verification set includes the engine response time threshold, the braking deceleration threshold, the braking distance threshold, the suspension compression threshold and the suspension rebound speed threshold, and the control system state characteristic value at each driving abnormality marking time point is obtained. The control system state characteristic value at each driving abnormality marking time point is used to confirm whether the control system at each driving abnormality marking time point is normal. The specific processing method is: ; in, For the The control system state characteristic value at the driving abnormality marking time point, For the The engine response time at each driving abnormality mark time point, For the The braking deceleration at the time point of the driving abnormality mark, For the The braking distance at the time point marked with driving abnormality, For the The suspension compression at the time point of the driving abnormality mark, For the The suspension rebound speed at the driving abnormality mark time point, is the engine response time threshold, is the braking deceleration threshold, is the braking distance threshold, is the suspension compression threshold, is the suspension rebound speed threshold, Mark the time point number for driving abnormality, , The total number of time points marked for driving abnormality, is the transmission channel number, , is the total number of transmission channels, is the engine response time weight factor, is the braking distance weight factor, is the suspension compression weight factor, is the braking deceleration weight factor, is the suspension rebound speed weight factor.

[0114] It should be noted that the engine response time weight factor, braking distance weight factor, suspension compression weight factor, braking deceleration weight factor and suspension rebound speed weight factor all have a value range between 0 and 1 and meet The engine response time weight factor is an influence factor corresponding to the control system state characteristic value of each driving abnormality mark time point preset in the integrated AI cloud computing center, which indicates the numerical value of the influence degree of the engine response time on the control system state characteristic value of each driving abnormality mark time point. The braking distance weight factor is an influence factor corresponding to the control system state characteristic value of each driving abnormality mark time point preset in the integrated AI cloud computing center, which indicates the numerical value of the influence degree of the braking distance on the control system state characteristic value of each driving abnormality mark time point. The suspension compression weight factor is an influence factor corresponding to the control system state characteristic value of each driving abnormality mark time point preset in the integrated AI cloud computing center, which indicates the numerical value of the influence degree of the suspension compression on the control system state characteristic value of each driving abnormality mark time point. The braking deceleration weight factor is an influence factor corresponding to the control system state characteristic value of each driving abnormality mark time point preset in the integrated AI cloud computing center, which indicates the control deceleration on each driving abnormality mark time point. The numerical value of the influence degree of the system state characteristic value, the suspension rebound speed weight factor is the influence factor corresponding to the control system state characteristic value of each driving abnormality mark time point preset in the integrated AI cloud computing center, and represents the numerical value of the influence degree of the suspension rebound speed on the control system state characteristic value of each driving abnormality mark time point. When used, the engine response time weight factor, braking distance weight factor, suspension compression weight factor, braking deceleration weight factor and suspension rebound speed weight factor can be directly obtained from the integrated AI cloud computing center, and the acquisition method is a preset mapping relationship. For example: the engine response time, braking distance, suspension compression, braking deceleration and suspension rebound speed involved in the embodiment of the present invention are input into the mapping set preset in the database for mapping and matching to obtain the engine response time weight factor, braking distance weight factor, suspension compression weight factor, braking deceleration weight factor and suspension rebound speed weight factor involved in the embodiment of the present invention, wherein the mapping relationship is one-to-one correspondence.

[0115] It should be noted that the control system data includes the engine response time, braking deceleration, braking distance, suspension compression and suspension rebound speed at each driving abnormality marking time point. There is a certain correlation between these parameters. The engine response time affects the acceleration performance of the vehicle, while the braking deceleration affects the deceleration performance of the vehicle. In operations such as emergency avoidance or rapid lane change, the vehicle may need to decelerate quickly and then accelerate immediately, so these two parameters jointly determine the overall dynamic response capability of the vehicle. Braking deceleration directly determines the braking distance. The greater the braking deceleration, the shorter the braking distance required for the vehicle at the same initial speed. These two parameters are the core indicators of braking performance evaluation and are directly related to each other. During braking, the suspension system may be compressed due to the forward shift of the vehicle's center of gravity, which will affect the contact between the tire and the ground, and then affect the braking distance. Excessive suspension compression may cause an increase in braking distance. The rebound speed of the suspension system affects the speed at which the suspension recovers from a compressed state to a normal state, which is related to the stability and comfort of the vehicle on continuously bumpy roads. The greater the suspension compression, the faster the rebound speed may be required to maintain the dynamic balance of the vehicle. The performance of the suspension system not only affects the comfort of the vehicle, but also affects the vehicle posture control during braking. If the suspension system cannot effectively control the vehicle posture, it may increase the braking distance and reduce the braking efficiency during braking.

[0116] If the control system state characteristic value at a certain driving abnormality mark time point is greater than or equal to the control system state abnormality threshold, the control system at the driving abnormality mark time point is judged to be abnormal; if the control system state characteristic value at a certain driving abnormality mark time point is less than the abnormality threshold, the control system at the driving abnormality mark time point is judged to be normal.

[0117] The time points of each driving abnormality marking of the abnormal control system are counted and recorded as the marking time points of each abnormal control system, and the image feature data, point cloud geometric feature data and radar feature data of each abnormal control system marking time point are stored in the database under the abnormal control system label.

[0118] It should be noted that abnormal scenarios caused by abnormal control systems themselves are internal factors and should be stored separately. In addition, if the data of each driving abnormality marking time point of the abnormal control system is combined with other data for deep data clustering analysis, it may lead to overfitting in the analysis process, affecting the analysis results.

[0119] The abnormal state threshold is processed as follows: in a specific embodiment, the abnormal state threshold is set directly in the database during the development of the abnormal scene extraction system for intelligent vehicle driving data based on artificial intelligence involved in the embodiment of the present invention. There are many methods for setting the abnormal state threshold, such as obtaining it through statistical analysis, including counting the control system state characteristic values ​​when the historical control system state is normal (for example, the engine response time is less than or equal to 0.5 seconds), and averaging the control system state characteristic values ​​obtained multiple times to obtain the abnormal state threshold.

[0120] The image feature data, point cloud geometric feature data, and radar feature data of each driving abnormality marking time point of the normal control system are collectively recorded as the processed comprehensive scene data of each driving abnormality marking time point.

[0121] The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs clustering processing and analysis to generate and store the abnormal scene data of each smart car.

[0122] The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs clustering processing and analysis to generate abnormal scene data of each smart car and stores it. The specific processing conditions are: The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, standardizes the processed comprehensive scene data of each driving abnormality marking time point, performs K-means clustering analysis to obtain multiple abnormal scene feature clusters of each driving abnormality marking time point, obtains each abnormal cluster data feature of each driving abnormality marking time point through iterative updating, and matches each abnormal cluster data feature of each driving abnormality marking time point with the corresponding abnormal scene label pre-stored in the integrated AI cloud computing center to obtain each abnormal scene label of each driving abnormality marking time point.

[0123] The processing of the processed comprehensive scene data at each driving abnormality marking time point is standardized, specifically including: calculating the mean and standard deviation of each feature, and standardizing the processed comprehensive scene data at each driving abnormality marking time point based on the mean and standard deviation, and the processing method is Z-score standardization, and the specific expression is:

[0124] in, For the The standardized processing results of the features are For the Features, For the The feature mean, For the The characteristic standard deviation, is the feature number, , is the total amount of features, and the processed data is recorded as the data set of each driving abnormality marking time point.

[0125] The K-means clustering is a typical unsupervised learning method for machine learning, which is used to divide the data set of each driving abnormality marking time point into several clusters composed of similar elements. The data points in the data set of each driving abnormality marking time point are assigned to K clusters so that the sum of the squared distances between each data point and the center of its assigned cluster is minimized. The following are the basic steps and principles of K-means clustering: Step 1: Randomly select K data points as the initial cluster centers.

[0126] Step 2: For each data point, calculate its distance from each cluster center and assign it to the cluster represented by the nearest cluster center.

[0127] Step 3: Recalculate the center of each cluster, usually taking the mean of all points in the cluster as the new cluster center.

[0128] Step 4: Repeat steps 2 and 3 until a stop condition is met. In the embodiment of the present invention, the stop condition is reaching a preset number of iterations.

[0129] In the embodiment of the present invention, the Euclidean distance is used to measure the similarity between data points. In other embodiments of the invention, other distance measurement methods may also be used, such as Manhattan distance or cosine similarity.

[0130] The K-means algorithm aims to minimize the square error within the cluster, and its objective function can be expressed as: ; in, is the objective function of K-means, For the Clusters, for The data points, for The center of is the cluster number, , is the total number of clusters, for The data point number, , for It should be noted that the K value is preset. In the embodiment of the present invention, the K value is set to the number of abnormal scene labels.

[0131] The data features of each abnormal cluster are compared with the feature templates corresponding to each abnormal scene label pre-stored in the integrated AI cloud computing center. In an embodiment of the present invention, the similarity between the current abnormal cluster data feature and a feature in the feature template corresponding to the pre-stored abnormal scene label is calculated using the Euclidean distance, specifically including: Suppose the characteristic vector expression of a certain abnormal cluster data feature is .

[0132] Suppose the feature vector expression of a feature of a feature template corresponding to a certain abnormal scene label is .

[0133] ; in, is the similarity between the abnormal cluster data feature and a feature in the feature template corresponding to a certain abnormal scene label, is the number of each vector in the feature vector expression, , is the total number of vectors.

[0134] Based on the similarity calculation results, a machine learning classifier is used to determine whether each abnormal cluster data feature matches each abnormal scene label. If the classifier determines that it matches, the corresponding abnormal scene label is assigned to the current abnormal cluster data feature.

[0135] The Euclidean distance refers to the real distance between two points in an m-dimensional space, or the natural length of a vector (ie, the distance from the point to the origin).

[0136] Based on each abnormal scene label at each driving abnormality marking time point, the processed comprehensive scene data at each driving abnormality marking time point is stored in a database under each corresponding abnormal scene label.

[0137] For example, if the abnormal scene labels of a certain driving abnormality marking time point include "rear-end collision", "sudden braking" and "collision", the processed comprehensive scene data of the driving abnormality marking time point will be stored in the database under the "rear-end collision", "sudden braking" and "collision" labels, and put into the integrated AI cloud computing center for learning and updating. When scene data similar to the driving abnormality marking time point appears again, the integrated AI cloud computing center can identify and mark the abnormal scene.

[0138] It should also be specifically stated that the abnormal scene labels of a certain driving abnormality marking time point include "rear-end collision", "sudden braking" and "collision". For example, the features in the feature template of the abnormal scene label of the "rear-end collision" include speed change features, following vehicle distance features, acceleration change features and deformation degree features of the rear end of the leading vehicle.

[0139] In this embodiment, if Figure 2 As shown, the present invention provides an abnormal scene extraction system for smart car driving data based on artificial intelligence, which specifically includes: The abnormal risk assessment module is used to retrieve the basic information of each smart car from multiple data transmission terminals, analyze and process to obtain the abnormal risk assessment value of each smart car, and match the driving data extraction ratio of each smart car based on the abnormal risk assessment value of each smart car.

[0140] The data extraction module is used to obtain the driving data packet of each smart car based on the driving data extraction ratio of each smart car, and at the same time obtain the time point of each driving abnormality mark, count the comprehensive scene data of each driving abnormality mark time point from the driving data packet, and import it into the integrated AI cloud computing center after classified data processing.

[0141] The scene extraction module is used to enable the integrated AI cloud computing center to receive the processed comprehensive scene data of each driving abnormality marking time point, perform clustering processing and analysis to generate abnormal scene data of each smart car and store it.

[0142] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0143] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. An artificial intelligence-based method for extracting abnormal scenes from smart car driving data, characterized in that: include: Retrieving basic information of each smart car from multiple data transmission terminals, analyzing and processing to obtain abnormal risk assessment values ​​of each smart car, and matching to obtain driving data extraction ratios of each smart car based on the abnormal risk assessment values ​​of each smart car; Based on the driving data extraction ratio of each smart car, the driving data packet of each smart car is obtained, and at the same time, the time point of each driving abnormality mark is obtained. The comprehensive scene data of each driving abnormality mark time point is counted from the driving data packet, and the classified data is processed and then imported into the integrated AI cloud computing center; The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs clustering processing to generate abnormal scene data of each smart car and stores it.

2. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: The specific process of retrieving basic information of each smart car from multiple data transmission terminals is as follows: A connection request is initiated from the integrated AI cloud computing center to each data transmission terminal. After receiving the connection request, each data transmission terminal packages the basic information of each smart car and sends it to the central server of the integrated AI cloud computing center; The basic information of each smart car includes the accumulated mileage, accumulated driving time and accumulated number of driving failures of each smart car.

3. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: The analysis and processing obtains the abnormal risk assessment value of each smart car, specifically including: Analyze and process the basic information of each smart car to obtain a basic information average value set and a basic information median value set; The basic information average value set includes the cumulative average driving mileage, the cumulative average driving time and the cumulative average number of driving failures; The basic information median value set includes the median value of the cumulative driving mileage, the median value of the cumulative driving time, and the median value of the cumulative number of driving failures; Comprehensively analyzing and processing the basic information average value set and the basic information median value set to obtain the basic information median adjusted average value set, including the cumulative median adjusted average mileage, the cumulative median adjusted average driving time, and the cumulative median adjusted average number of failures; The basic information of each smart car is compared and analyzed with the set of adjusted median average values ​​of the basic information to obtain an abnormal risk assessment value of each smart car, and the abnormal risk assessment value of each smart car is used to characterize the risk of abnormality of each smart car during driving.

4. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: The driving data extraction ratio of each smart car is obtained by matching the abnormal risk assessment value of each smart car, specifically including: Based on the abnormal risk assessment value of each smart car, the driving data extraction ratio corresponding to each abnormal risk assessment value interval in the built-in database of the integrated AI cloud computing center is mapped and matched to obtain the driving data extraction ratio of each smart car.

5. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: The step of obtaining each driving abnormality marking time point and collecting comprehensive scene data of each driving abnormality marking time point from the driving data packet specifically includes: Identify the time points marked as driving abnormalities in the driving data packets of each smart car, and count the longitudinal abnormal time point data and the lateral abnormal time period data of each driving abnormality marked time point, and record them as the comprehensive scene data of each driving abnormality marked time point; The comprehensive scene data at each driving abnormality marking time point includes environmental perception data and control system data at each driving abnormality marking time point; The environmental perception data includes image data, point cloud data and radar data at each driving abnormality marking time point; The control system data includes engine response time, braking deceleration, braking distance, suspension compression and suspension rebound speed at each driving abnormality marking time point.

6. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: The classified data is then processed and imported into the integrated AI cloud computing center, specifically including: The image data, point cloud data and radar data at each driving abnormality marking time point are respectively imported into the local image feature extraction module, point cloud geometric feature extraction module and radar feature extraction module of the AI ​​cloud computing center, and the corresponding data processing is performed to obtain the image feature data, point cloud geometric feature data and radar feature data at each driving abnormality marking time point; Compare and analyze the control system data at each driving abnormality marking time point with the control system data check set pre-stored in the local database to obtain the control system state characteristic value at each driving abnormality marking time point, wherein the control system state characteristic value at each driving abnormality marking time point is used to confirm whether the control system at each driving abnormality marking time point is normal. If the control system state characteristic value at a certain driving abnormality marking time point is greater than or equal to a preset control system state abnormality threshold, the control system at the driving abnormality marking time point is determined to be abnormal. If the control system state characteristic value at a certain driving abnormality marking time point is less than the control system state abnormality threshold, the control system at the driving abnormality marking time point is determined to be normal. The time points of each driving abnormality marking when the statistical control system is abnormal are recorded as the marking time points of each abnormal control system, and the image feature data, point cloud geometric feature data and radar feature data of each abnormal control system marking time point are stored in the database under the abnormal control system label; The control system data verification set includes an engine response time threshold, a brake deceleration threshold, a brake distance threshold, a suspension compression threshold, and a suspension rebound speed threshold; The image feature data, point cloud geometric feature data, and radar feature data at each driving abnormality marking time point when the control system is normal are collectively recorded as the processed comprehensive scene data at each driving abnormality marking time point.

7. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs clustering processing to generate abnormal scene data of each smart car and stores it. The specific processing conditions are: The integrated AI cloud computing center receives the processed comprehensive scene data of each driving abnormality marking time point, performs K-means clustering processing and analysis to obtain multiple abnormal scene feature clusters of each driving abnormality marking time point, obtains each abnormal cluster data feature of each driving abnormality marking time point through iterative updating, and matches each abnormal cluster data feature of each driving abnormality marking time point with the corresponding abnormal scene label pre-stored in the integrated AI cloud computing center to obtain each abnormal scene label of each driving abnormality marking time point; Based on each abnormal scene label at each driving abnormality marking time point, the processed comprehensive scene data at each driving abnormality marking time point is stored in a database under each corresponding abnormal scene label.

8. The method for extracting abnormal scenes from smart car driving data based on artificial intelligence according to claim 1 is characterized by: It also includes detecting the transmission channel performance parameters from each data transmission terminal to the integrated AI cloud computing center, processing and analyzing to generate data quality repair factors and performing data quality repair, specifically including: The transmission channel performance parameters include the real-time signal strength, interface rate, real-time delay and real-time signal-to-noise ratio of each data transmission terminal; Retrieve transmission channel performance verification parameters from the built-in database of the integrated AI cloud computing center, including real-time signal strength verification value, interface rate verification value, real-time delay verification value, and real-time signal-to-noise ratio verification value; A comprehensive comparison and analysis is performed on the transmission channel performance parameters and the transmission channel performance verification parameters to obtain the data quality impact value of each transmission channel, and the data quality impact value of each transmission channel is mapped and matched with the data quality repair factors corresponding to each data quality impact value interval pre-stored in the built-in database of the integrated AI cloud computing center to obtain the data quality repair factor of each transmission channel. The data quality impact value of each transmission channel is used to characterize the impact of the performance of each transmission channel on the data quality, and data quality repair is performed based on the data transmission repair factor.

9. The method for extracting abnormal scenes from driving data of a smart car based on artificial intelligence according to claim 3 is characterized by: The analysis and processing obtains the abnormal risk assessment value of each smart car, and the specific processing method is: ; in, For the The abnormal risk assessment value of a smart car, For the The accumulated mileage of a smart car, For the The cumulative driving time of a smart car, For the The cumulative number of driving failures of a smart car, The average mileage adjusted for the cumulative median mileage driven is The average time for driving is adjusted for the cumulative median. The cumulative median adjusted average number of failures for driving, is the weight factor of accumulated mileage, is the weight factor of the accumulated driving time, is the weight factor of the average number of cumulative failures during driving, Number the smart car. , is the total number of smart cars. The softplus function is a built-in function in Python. .

10. An abnormal scene extraction system for intelligent vehicle driving data based on artificial intelligence, characterized in that: include: The abnormal risk assessment module is used to retrieve the basic information of each smart car from multiple data transmission terminals, analyze and process to obtain the abnormal risk assessment value of each smart car, and match and obtain the driving data extraction ratio of each smart car based on the abnormal risk assessment value of each smart car; A data extraction module is used to obtain the driving data packets of each smart car based on the driving data extraction ratio of each smart car, and at the same time obtain the time point of each driving abnormality mark, collect the comprehensive scene data of each driving abnormality mark time point from the driving data packet, and import it into the integrated AI cloud computing center after classified data processing; The scene extraction module is used to enable the integrated AI cloud computing center to receive the processed comprehensive scene data of each driving abnormality marking time point, perform clustering processing and analysis to generate abnormal scene data of each smart car and store it.

Images