Vehicle driving risk determination method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle driving risk determination method and device, electronic equipment and a storage medium, and the method comprises the steps: monitoring a sound signal of a driver in a current vehicle state, carrying out the feature extraction of a breath sound signal and a sound ray signal, obtaining the breath feature of the breath sound signal and the acoustic feature of the sound ray signal, and determining the driving risk of the driver; judging the current driving state of the driver by adopting the breathing characteristics and the acoustic characteristics, determining whether the driver is in an abnormal driving state, and when the driver is determined to be in the abnormal driving state, determining the driving risk level of the driver according to the abnormal driving state, or determining the driving risk level of the driver according to the abnormal driving state and the current vehicle state. And determining a driving risk level of the driver. According to the invention, non-contact monitoring and multi-dimensional identification are carried out on the sound of the driver in the current vehicle state, the driving state of the driver is judged, and the accuracy of determining the vehicle driving risk is improved through the association of the abnormal driving state and the vehicle state and the independent triggering of the abnormal driving state.

Description

Technical Field

[0001] The present invention relates to the field of driving monitoring technology, and in particular to a vehicle driving risk determination method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of intelligent driving technology, monitoring of the driver's driving status has become a key component to improve driving safety. At present, the driver's driving status monitoring is mainly divided into the following two solutions: visual perception solution and bioelectric signal solution.

[0003] Visual perception solutions use infrared / visible light cameras to capture the driver's facial expressions (such as the length of time their eyes are closed and their head posture) and combine them with image recognition algorithms to determine fatigue or distraction. However, this monitoring method is susceptible to environmental or other interference. When the driver wears a mask or sunglasses or in night scenes, the accuracy of driving status recognition is affected, making it impossible to accurately determine driving risks. Bioelectric signal solutions typically use wearable devices (such as smart bracelets) to monitor physiological indicators such as heart rate and blood oxygen, or indirectly infer changes in vital signs through steering wheel grip sensors. This single bioelectric signal cannot distinguish between physiological abnormalities (such as hypoglycemia) and state changes caused by focused driving (such as gripping the steering wheel and causing an increase in heart rate). It also affects the accuracy of driving status recognition, is prone to triggering false alarms, and cannot accurately determine driving risks. Therefore, the monitoring signal of the current driving status is single and easily interfered with, making it difficult to identify the driver's abnormal driving status, affecting the accuracy of driving status monitoring and making it impossible to accurately determine driving risks. Summary of the Invention

[0004] In view of this, the present invention aims to propose a vehicle driving risk determination method, device, electronic device and storage medium to solve the problem that the monitoring signal of the current driving status is single and easily interfered with, making it difficult to identify the driver's abnormal driving status, affecting the monitoring accuracy of the driving status, and thus making it impossible to accurately determine the driving risk.

[0005] According to a first aspect of the present invention, a method for determining vehicle driving risk is provided, the method comprising: Monitoring the driver's voice signal in the current vehicle state; wherein the voice signal includes a breathing sound signal and a sound line signal; performing feature extraction on the breathing sound signal and the sound line signal to obtain a breathing feature of the breathing sound signal and an acoustic feature of the sound line signal; Using the breathing characteristics and the acoustic characteristics to judge the current driving state of the driver, and determining whether the driver is in an abnormal driving state; In the case where it is determined that the driver is in an abnormal driving state, the driver's driving risk level is determined according to the abnormal driving state, or the driver's driving risk level is determined according to the abnormal driving state and the current vehicle state.

[0006] Optionally, monitoring the driver's voice signal in the current vehicle state includes: Acquire the current vehicle state of the vehicle and use a directional microphone array to monitor the sound signals in the seat area under the current vehicle state; The sound signal in the main driving area is denoised to filter out the vehicle's ambient noise and the noise of passengers in the non-main driving area, and the denoised sound signal of the driver in the main driving area is obtained.

[0007] Optionally, before performing denoising on the sound signal in the main driver's area, filtering out the vehicle's ambient noise and the noise of passengers in the non-main driver's area, and obtaining the denoised sound signal of the driver in the main driver's area, the method further includes: Matching the sound signal in the main driving area with a pre-generated historical sound database to determine whether the driver in the main driving area has passed the identity verification; wherein the historical sound database includes the voices of users who have passed the identity verification; If it is determined that the driver in the main driving area has passed the identity verification, directionally identifying the sound signal in the main driving area; Otherwise, the voice signal of the driver in the main driving area is updated to the historical voice database.

[0008] Optionally, the extracting features of the breathing sound signal and the sound line signal to obtain the breathing features of the breathing sound signal and the acoustic features of the sound line signal includes: Extract the respiratory frequency, respiratory rhythm and respiratory amplitude of the respiratory signal to obtain the respiratory characteristics of the respiratory signal. Feature extraction is performed on the sound line signal to extract high-frequency features and energy mutations of the sound line signal to obtain acoustic features of the sound line signal.

[0009] Optionally, the judging the current driving state of the driver by using the breathing feature and the acoustic feature to determine whether the driver is in an abnormal driving state includes: Predetermining normal breathing characteristics and normal acoustic characteristics of the driver under normal driving conditions; Comparing the breathing feature with the normal breathing feature, and comparing the acoustic feature with the normal acoustic feature to obtain a feature deviation degree; If the characteristic deviation degree is greater than or equal to a preset deviation threshold, it is determined that the driver's current driving state is an abnormal driving state.

[0010] Optionally, when it is determined that the driver is in an abnormal driving state, determining the driver's driving risk level according to the abnormal driving state, or determining the driver's driving risk level according to the abnormal driving state and the current vehicle state, includes: In the case where the driver is determined to be in an abnormal driving state, if the characteristic deviation degree under the abnormal driving state is greater than or equal to the preset danger threshold, the driving risk level is determined to be a severe abnormal level; If the degree of characteristic deviation under the abnormal driving state is less than the preset danger threshold, driving risk identification is performed based on the abnormal driving state and the current vehicle state, and the driving risk level is determined to be one of a low abnormality level, a medium abnormality level, and a severe abnormality level.

[0011] Optionally, in the case where the driver is determined to be in an abnormal driving state, after determining the driver's driving risk level according to the abnormal driving state, or determining the driver's driving risk level according to the abnormal driving state and the current vehicle state, the method further includes: If the driving risk level is a low abnormality level, generating an abnormality prompt of the low abnormality level, and controlling the vehicle to output the abnormality prompt; If the driving risk level is a medium abnormality level, generating a warning signal of the medium abnormality level, and controlling the vehicle to output the warning signal; If the driving risk level is a serious abnormal level, the vehicle is controlled to trigger emergency measures.

[0012] According to a second aspect of the present invention, a vehicle driving risk determination device is provided, the device comprising: A sound monitoring module is used to monitor the driver's sound signal in the current vehicle state; wherein the sound signal includes a breathing sound signal and a sound line signal; a feature extraction module, configured to extract features from the breathing sound signal and the sound line signal to obtain a breathing feature of the breathing sound signal and an acoustic feature of the sound line signal; a driving state module, configured to judge the driver's current driving state by using the breathing characteristics and the acoustic characteristics, and determine whether the driver is in an abnormal driving state; The risk level module is used to determine the driver's driving risk level based on the abnormal driving state when it is determined that the driver is in an abnormal driving state, or to determine the driver's driving risk level based on the abnormal driving state and the current vehicle state.

[0013] According to another aspect of the present invention, there is provided an electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the vehicle driving risk determination method as described above.

[0014] According to another aspect of the present invention, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle driving risk determination method as described above are implemented.

[0015] The vehicle driving risk determination method provided by the embodiment of the present invention monitors the driver's sound signal in the current vehicle state, the sound signal including the breathing sound signal and the sound line signal, performs feature extraction on the breathing sound signal and the sound line signal, obtains the breathing characteristics of the breathing sound signal and the acoustic characteristics of the sound line signal, uses the breathing characteristics and acoustic characteristics to judge the driver's current driving state, determines whether the driver is in an abnormal driving state, and if the driver is determined to be in an abnormal driving state, determines the driver's driving risk level based on the abnormal driving state, or determines the driver's driving risk level based on the abnormal driving state and the current vehicle state. The embodiment of the present invention performs non-contact monitoring of the driver's breathing sound and the sound line in the current vehicle state, combines the breathing characteristics and the acoustic characteristics, and identifies and judges the driver's driving state in multiple dimensions. By associating the abnormal driving state with the vehicle state and independently triggering the abnormal driving state, a dual verification mechanism is formed to accurately identify the risk level of the driving state, thereby achieving precise monitoring of the driver's driving state, improving the accuracy of determining vehicle driving risk, further improving user experience and driving safety, and providing strong protection for the driver's safe driving.

[0016] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings: Figure 1 This is a flowchart of the steps of a method for determining vehicle driving risk provided by an embodiment of the present invention; Figure 2 yes Figure 1 Flowchart of step 101 in the vehicle driving risk determination method provided by an embodiment of the present invention; Figure 3 yes Figure 1 Flowchart of step 102 in the vehicle driving risk determination method provided by an embodiment of the present invention; Figure 4 yes Figure 1 Flowchart of step 103 in the vehicle driving risk determination method provided by an embodiment of the present invention; Figure 5 yes Figure 1 Flowchart of step 104 in the vehicle driving risk determination method provided by an embodiment of the present invention; Figure 6 is an interactive schematic diagram of a vehicle driving risk determination method provided by an embodiment of the present invention; Figure 7 1 is a schematic structural diagram of a vehicle driving risk determination device provided by an embodiment of the present invention; Figure 8 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, each embodiment of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present invention, many technical details are provided to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in this application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with each other and referenced to each other under the premise that there is no contradiction.

[0019] Reference Figure 1 , shows a flowchart of the steps of a method for determining vehicle driving risk provided by an embodiment of the present invention, the method may include: Step 101 , monitoring the driver's voice signal in the current vehicle state; wherein the voice signal includes a breathing signal and a sound line signal.

[0020] In an embodiment of the present invention, in order to solve the problem that the monitoring signal of the current driving status is single and easily interfered with, it is difficult to identify the driver's abnormal driving status, which affects the monitoring accuracy of the driving status and thus cannot accurately determine the driving risk, the embodiment of the present invention performs non-contact monitoring of the driver's breathing and voice in the current vehicle state, identifies and judges the driver's driving status in multiple dimensions, and forms a dual verification mechanism through the association of abnormal driving status with vehicle status, and independent triggering of abnormal driving status, accurately identifies the risk level of the driving status, realizes precise monitoring of the driver's driving status, and further improves the accuracy of determining the driving risk classification.

[0021] In this embodiment, the driver's voice signals are monitored in the current vehicle state. The current vehicle state can be acquired by the vehicle controller via vehicle sensors and includes vehicle body posture data and driving control data. A directional microphone array is used to monitor the driver's voice signals in the current vehicle state. The voice signals are the sounds made by the driver while driving. The voice signals include respiratory signals and acoustic line signals, such as speech, talking, and breathing sounds. Respiratory signals refer to the sounds produced by the driver's breathing airflow through the nasal cavity, throat, or chest cavity, including the rhythm of inhalation or exhalation, the predominantly low-frequency breathing rate, or the amplitude of breathing such as snoring or wheezing. Acoustic line signals refer to the speech signals produced by the driver when speaking, shouting, or humming, including high-level semantic information such as language content, intonation, and speech rate. The acoustic line signals have a wide frequency band, with energy concentrated in the high-frequency region. The vehicle controller analyzes and processes the sound signals collected by the directional microphone array.

[0022] In this embodiment, a directional microphone is used to continuously capture the breathing rhythm, breath intensity, and sudden changes in breathing (such as gasping / pausing) of the driver in the main driving area, and to monitor the voice (such as sudden pauses and tremors in the speaking voice). At the same time, the ambient noise in the vehicle and the voice signals of other passengers are collected to denoise the driver's voice signal. These will not be detailed here.

[0023] It should be noted that the vehicle driving risk determination method of the embodiment of the present invention can be integrated into a vehicle controller, which obtains the current vehicle status through vehicle sensors and analyzes and processes the sound signals collected by the directional microphone array. Specifically, a directional microphone array is pre-deployed on the vehicle to cover the vehicle's seating area, which includes the driver's seat, the front passenger seat, and the rear area. The directional microphone array includes at least four microphones, which are used to continuously capture the driver's breathing, speaking, and other sounds. In some embodiments, the driver's sound signals can also be collected in real time through a head-mounted microphone, which is not specifically limited here.

[0024] Step 102 : extracting features from the breathing sound signal and the sound line signal to obtain breathing features of the breathing sound signal and acoustic features of the sound line signal.

[0025] In an embodiment of the present invention, after monitoring the breathing sound signal and voice line signal of the driver in the vehicle, feature extraction is performed on the breathing sound signal and the voice line signal to obtain the breathing characteristics of the breathing sound signal and the acoustic characteristics of the voice line signal. The breathing characteristics of the breathing sound signal include breathing frequency, breathing rhythm and breathing amplitude, and the acoustic characteristics of the voice line signal include high-frequency characteristics and energy mutation. Through multi-level feature extraction, the driver's driving status can be judged in multiple dimensions.

[0026] Specifically, the breathing signal is analyzed in the time domain to detect its periodicity. The period of the breathing signal reflects the breathing rhythm, thereby obtaining the breathing rhythm characteristics. The breathing signal is analyzed in the frequency domain to detect the frequency peak of the breathing signal and extract the breathing frequency characteristics. The breathing signal is analyzed in the energy domain to extract the breathing amplitude characteristics. The sound line signal is analyzed in the frequency domain to detect the high-frequency components in the sound line signal and determine the high-frequency characteristics. The sound line signal is analyzed in the energy domain to detect the energy mutation of the sound line signal through the energy changes and fluctuations of the signal waveform and determine the energy mutation.

[0027] Step 103 : Using the breathing characteristics and acoustic characteristics to judge the current driving state of the driver, and determine whether the driver is in an abnormal driving state.

[0028] In an embodiment of the present invention, breathing characteristics and acoustic characteristics are used to judge the driver's current driving state and determine whether the driver is in an abnormal driving state. Specifically, based on the normal breathing characteristics and normal acoustic characteristics of the driver in a predetermined normal driving state, the breathing characteristics are compared with the normal breathing characteristics to obtain the deviation of the breathing characteristics. Similarly, the acoustic characteristics are compared with the normal acoustic characteristics to obtain the deviation of the acoustic characteristics. The deviation of the breathing characteristics and the deviation of the acoustic characteristics are summed to obtain the characteristic deviation degree of the sound signal. If the characteristic deviation degree is greater than or equal to the preset deviation threshold, the driver's current driving state is determined to be an abnormal driving state. Abnormal driving states may include fatigue driving, distracted driving, emotional fluctuations, etc.

[0029] In this embodiment, the preset deviation threshold is a pre-set minimum deviation. If the characteristic deviation is greater than or equal to the preset deviation threshold, the driver's current driving state is determined to be abnormal; otherwise, the driver's current driving state is determined to be normal. The characteristic deviation is calculated based on a comprehensive calculation of breathing characteristics and acoustic characteristics. When the characteristic deviation is greater than or equal to the preset deviation threshold, the driver's abnormal state is quickly identified, providing a basis for subsequent warning and intervention.

[0030] Step 104 , when it is determined that the driver is in an abnormal driving state, the driving risk level of the driver is determined based on the abnormal driving state, or the driving risk level of the driver is determined based on the abnormal driving state and the current vehicle state.

[0031] In an embodiment of the present invention, when it is determined that the driver is in an abnormal driving state, the driver's driving risk level is directly determined based on the abnormal driving state, or the driver's driving risk level is determined based on the abnormal driving state and the current vehicle state. It should be noted that when it is determined that the driver is in an abnormal driving state, if the characteristic deviation degree in the abnormal driving state is greater than or equal to the preset danger threshold, indicating that the current driver's driving state is extremely abnormal, then there is no need to consider the vehicle state, and the driving risk level is determined to be a severe abnormal level. If the characteristic deviation degree in the abnormal driving state is less than the preset danger threshold, that is, indicating that the current driver's driving state is generally abnormal, then a comprehensive driving risk identification is performed based on the abnormal driving state and the current vehicle state. The current vehicle state can be obtained by the vehicle controller through the vehicle sensor. The vehicle state includes vehicle body posture data and driving control data. The driving risk level is divided according to the degree of danger, including one of a low abnormal level, a medium abnormal level and a severe abnormal level.

[0032] In some embodiments, based on the driving risk level, the vehicle is controlled to execute a safety response strategy corresponding to the driving risk level to handle abnormal driving conditions. Specifically, low-level abnormality levels can prompt the driver to relax and rest through voice prompts or other means; medium-level abnormality levels can alleviate the driver's abnormality through intervention measures such as early warnings and alerts; and severe abnormality levels require triggering emergency measures, such as automatically slowing the vehicle down and finding a safe place to stop, while calling for emergency assistance. This embodiment provides safety response strategies that match different driving risk levels, promptly and effectively handling abnormal driving conditions and improving vehicle driving safety.

[0033] The vehicle driving risk determination method provided by the embodiment of the present invention monitors the driver's sound signal in the current vehicle state, the sound signal including the breathing sound signal and the sound line signal, performs feature extraction on the breathing sound signal and the sound line signal, obtains the breathing characteristics of the breathing sound signal and the acoustic characteristics of the sound line signal, uses the breathing characteristics and acoustic characteristics to judge the driver's current driving state, determines whether the driver is in an abnormal driving state, and if the driver is determined to be in an abnormal driving state, determines the driver's driving risk level based on the abnormal driving state, or determines the driver's driving risk level based on the abnormal driving state and the current vehicle state. The embodiment of the present invention performs non-contact monitoring of the driver's breathing sound and the sound line in the current vehicle state, combines the breathing characteristics and the acoustic characteristics, and identifies and judges the driver's driving state in multiple dimensions. By associating the abnormal driving state with the vehicle state and independently triggering the abnormal driving state, a dual verification mechanism is formed to accurately identify the risk level of the driving state, thereby achieving precise monitoring of the driver's driving state, improving the accuracy of determining vehicle driving risk, further improving user experience and driving safety, and providing strong protection for the driver's safe driving.

[0034] Further, refer to Figure 2 , showing Figure 1 A flowchart of step 101 of a method for determining vehicle driving risk is provided. This method is substantially the same as the method for determining vehicle driving risk provided in the first embodiment of the present invention. Step 101 may include: Step 1011 , obtaining the current vehicle state of the vehicle, and using a directional microphone array to monitor the sound signal of the seat area under the current vehicle state; Step 1012 , denoising the sound signal in the main driving area is performed to filter out the ambient noise of the vehicle and the noise of passengers in the non-main driving area of the vehicle, thereby obtaining a denoised sound signal of the driver in the main driving area.

[0035] It should be noted that in an embodiment of the present invention, multiple directional microphones are installed in areas such as the main driver's seat, the front passenger seat, and the rear seat to form a distributed directional microphone array to ensure that the sound signals inside the entire vehicle can be covered. The vehicle controller obtains the current vehicle state of the vehicle and uses a directional microphone array to monitor the sound signals of the seat area under the current vehicle state. The sound signals include the sound signals of the main driver's seat area and the sound signals of the non-main driver's seat area. In order to accurately monitor the driver's driving state, this embodiment obtains the current vehicle state of the vehicle and uses a directional microphone array to monitor the sound signals of the seat area under the current vehicle state. Since the presence of interference noise in the vehicle affects the analysis of the driver's sound signal, the collected sound signal needs to be denoised. The sound signal of the main driver's seat area is denoised, and the ambient noise of the vehicle and the noise of the passengers in the non-main driver's seat area of the vehicle are filtered to remove the interference of the ambient noise and other passengers in the vehicle, and obtain the denoised sound signal of the driver in the main driver's seat area to ensure the purity of the sound signal of the driver in the main driver's seat area.

[0036] Specifically, the sound signal in the main driver's seat area is denoised to filter out the vehicle's ambient noise and the noise of the occupants in the vehicle's non-main driver's seat area. The sound signal in the main driver's seat area can be used as the desired signal, and the vehicle's ambient noise and the noise of the occupants in the vehicle's non-main driver's seat area can be used as reference signals. The noise is eliminated through an adaptive filter. The adaptive filter can automatically adjust the filter parameters according to the characteristics of the input signal to minimize the noise. The frequency spectrum can also be processed to reduce the noise component, and the sound signal in the main driver's seat area, the vehicle's ambient noise, and the noise of the occupants in the vehicle's non-main driver's seat area can be converted into frequency domain signals. The ambient noise and the noise of the occupants in the non-main driver's seat area can be suppressed in the frequency domain. I will not go into details here.

[0037] It should be noted that the directional microphone array installed inside the vehicle covers the vehicle's main driver's area, co-driver's area and rear seats. The directional microphone array collects sound signals from each seat area through multi-channel synchronous collection, and can capture the driver's breathing signals, voice signals, and breathing signals and voice signals of other passengers. The collected sound signals are transmitted to the vehicle processor in real time through the on-board communication bus for processing.

[0038] The embodiments of the present invention accurately collect sound signals in the main driving area, avoid interference from sound signals in non-main driving areas, and filter out interference from ambient noise and other passengers in the vehicle, thereby ensuring the purity of the driver's sound signal in the main driving area and improving the accuracy of driver's driving status recognition.

[0039] Specifically, step 1012 performs denoising on the sound signal in the main driver's area, filters the vehicle's ambient noise and the noise of passengers in the non-main driver's area, and obtains the denoised sound signal of the driver in the main driver's area, and may further include: Matching the sound signal in the main driving area with a pre-generated historical sound database to determine whether the driver in the main driving area has passed the identity verification; wherein the historical sound database includes the voices of users who have passed the identity verification; If it is determined that the driver in the main driving area has passed the identity verification, the sound signal in the main driving area is directionally identified; Otherwise, the voice signal of the driver in the main driving area is updated to the historical voice database.

[0040] It should be noted that in the above steps, after collecting the sound signals from the vehicle's seating area, the sound signals from the main driver's area are matched against a pre-generated historical sound database, and voiceprint recognition is used to determine whether the driver in the main driver's area has passed identity verification. If the current driver in the main driver's area passes identity verification, indicating that the driver is an authorized user, the sound signals from the main driver's area of the vehicle are then targeted for recognition. If the driver fails identity verification, indicating that the driver is an unauthorized user, the sound signals from the current driver in the main driver's area are updated to the historical voiceprint database for subsequent identity verification.

[0041] Specifically, the sound signal of the main driver's area is matched with the historical sound database, and through voiceprint recognition, voice feature comparison and other processing, it is determined whether the driver of the main driver's area has passed the identity authentication. During the matching process, similarity algorithms such as cosine similarity and Euclidean distance can be used to calculate the similarity between the sound signal of the main driver's area and the sound signal in the historical sound database. Based on the sound similarity, it is determined whether the driver of the main driver's area has passed the identity authentication.

[0042] In this embodiment, the historical sound database includes the voices of users who have passed the identity authentication, that is, the voice signals of users who have passed the identity authentication previously. The historical sound database is obtained by collecting and verifying the voices of drivers in the historical main driving area and storing them. In this embodiment, when a new user is detected, the incremental learning mechanism is triggered to update the voice signal of the new user so that only the voice signal of the driver who has passed the identity authentication is processed, which can eliminate the interference of the co-pilot or rear passengers, realize the isolation of driving and riding identities in shared travel scenarios, and avoid misjudgment caused by data mixing.

[0043] In this embodiment, in order to directionally enhance the driver's voice signal of the main driver's seat, the sound signal of the main driver's area of the vehicle can be beamformed to obtain the driver's voice signal of the main driver's area of the vehicle. Specifically, the collected sound signal of the main driver's area of the vehicle is beamformed, and the intensity of the driver's voice signal is enhanced by spatial filtering technology, while suppressing noise signals in other directions to obtain a clear and high signal-to-noise ratio driver's voice signal. Among them, beamforming can be achieved through delayed sum beamforming, minimum variance distortionless response beamforming, etc., which is not specifically limited here. Beamforming processing can effectively enhance the intensity of the driver's voice signal, reduce the interference of environmental noise and other occupants' voices, and improve the clarity and reliability of the driver's voice signal.

[0044] The embodiment of the present invention effectively prevents unauthorized users from interfering with driver status monitoring through an identity authentication mechanism, and adopts user identity authentication to dynamically update the historical sound database to adapt to changes in vehicle users, thereby improving the flexibility and accuracy of identity authentication.

[0045] Further, refer to Figure 3 , showing Figure 1 A flowchart of step 102 of a method for determining vehicle driving risk is provided. This method is substantially the same as the method for determining vehicle driving risk provided in the first embodiment of the present invention. Step 102 may include: Step 1021, performing feature extraction on the respiratory sound signal to extract the respiratory frequency, respiratory rhythm, and respiratory amplitude of the respiratory sound signal to obtain respiratory features of the respiratory sound signal; Step 1022 : extract features from the sound line signal, extract the high frequency features and energy mutation of the sound line signal, and obtain the acoustic features of the sound line signal.

[0046] It should be noted that, in an embodiment of the present invention, after the vehicle controller obtains the voice signal of the driver in the main driving area collected by the directional microphone array, it performs feature extraction on the breathing sound signal and the sound line signal to analyze the driver's voice condition. Specifically, feature extraction is performed on the breathing sound signal to extract the breathing frequency, breathing rhythm and breathing amplitude of the breathing sound signal to obtain the breathing characteristics of the breathing sound signal. Feature extraction is performed on the sound line signal to extract the high-frequency characteristics and energy mutation of the sound line signal to obtain the acoustic characteristics of the sound line signal.

[0047] In this embodiment, the breathing sound signal can be analyzed in the time domain to determine its periodicity and obtain breathing rhythm characteristics. Frequency domain analysis can be performed to determine the peak frequency of the breathing sound signal and obtain breathing frequency characteristics. Energy analysis can also be performed to obtain breathing amplitude characteristics. Similarly, frequency domain analysis can be performed on the acoustic signal to extract high-frequency components and determine high-frequency characteristics, including high-frequency bands and peaks. Energy analysis can also be performed on the acoustic signal to determine energy mutations based on energy changes and fluctuations in the signal waveform. Energy mutations can be used to reflect sudden changes in the driver's voice tone caused by respiratory obstruction or breath holding.

[0048] The embodiment of the present invention extracts the features of breathing sound signals and sound line signals in multiple dimensions through frequency domain analysis and time domain analysis, so as to combine breathing features and acoustic features to judge the driver's driving status in multiple dimensions and improve the accuracy of status judgment.

[0049] Further, refer to Figure 4 , showing Figure 1 A flowchart of step 103 of a method for determining vehicle driving risk is provided. This method is substantially the same as the method for determining vehicle driving risk provided in the first embodiment of the present invention. Step 103 may include: Step 1031 , predetermining normal breathing characteristics and normal acoustic characteristics of the driver in a normal driving state; Step 1032: Compare the breathing feature with the normal breathing feature, and compare the acoustic feature with the normal acoustic feature to obtain a feature deviation degree; Step 1033: If the characteristic deviation degree is greater than or equal to the preset deviation threshold, it is determined that the driver's current driving state is an abnormal driving state.

[0050] It should be noted that in an embodiment of the present invention, the normal breathing characteristics and normal acoustic characteristics of the driver in a normal driving state are generated in advance based on historical sound signals and historical vehicle states to reflect the sound characteristics of the driver in a normal driving state. Specifically, a large amount of sample data (such as the driver's breathing sound signal and the driver's voice line signal) can be used to statistically analyze the breathing frequency, breathing rhythm, and breathing amplitude in a normal driving state to obtain normal breathing characteristics, and the acoustic characteristics of the voice line signal in a normal driving state can be statistically analyzed to obtain normal acoustic characteristics, thereby providing a reference standard for abnormal state judgment.

[0051] In this embodiment, the breathing feature is compared with the normal breathing feature to obtain the deviation of the breathing feature, and the acoustic feature is compared with the normal acoustic feature to obtain the deviation of the acoustic feature. The deviation of the breathing feature and the deviation of the acoustic feature are summed to obtain the degree of feature deviation. The breathing feature and the acoustic feature can be converted into feature vectors, and vector calculations are performed with the normal breathing feature and the normal acoustic feature respectively. Specifically, a feature vector calculation algorithm such as Euclidean distance and Mahalanobis distance can be used to calculate the distance between the breathing feature and the normal breathing feature to obtain the deviation of the breathing feature. Similarly, the distance calculation is performed between the acoustic feature and the normal acoustic feature to obtain the deviation of the acoustic feature. The deviation of the breathing feature and the deviation of the acoustic feature are summed to obtain the degree of feature deviation of the sound signal. Specifically, the degree of characteristic deviation of the driver's voice signal is determined based on a preset deviation threshold. The preset deviation threshold is a pre-set minimum deviation. The preset deviation threshold can be dynamically set and adjusted based on different driving scenarios and individual driver differences. This embodiment does not impose specific limitations on this. If the characteristic deviation is greater than or equal to the preset deviation threshold, the driver's current driving state is determined to be abnormal; otherwise, the driver's current driving state is determined to be normal. In this embodiment, the characteristic deviation is calculated based on a comprehensive calculation of breathing characteristics and acoustic characteristics. When the characteristic deviation is greater than or equal to the preset deviation threshold, the driver's abnormal state is quickly identified, providing a basis for subsequent warning and intervention.

[0052] The embodiment of the present invention calculates the deviation between the characteristics of the driver's voice signal and the characteristics of the voice signal under normal driving conditions, and improves the accuracy of abnormal state judgment through deviation quantification and threshold judgment, quickly identifies the driver's abnormal state, and timely monitors changes in the driver's state, thereby improving the accuracy and real-time performance of driving state recognition.

[0053] Further, refer to Figure 5 , showing Figure 1 A flowchart of step 104 of a method for determining vehicle driving risk is provided. This method is substantially the same as the method for determining vehicle driving risk provided in the first embodiment of the present invention. Step 104 may include: Step 1041: If it is determined that the driver is in an abnormal driving state, and if the characteristic deviation degree in the abnormal driving state is greater than or equal to a preset danger threshold, then the driving risk level is determined to be a severe abnormal level; In step 1042, if the characteristic deviation degree in the abnormal driving state is less than the preset danger threshold, driving risk identification is performed based on the abnormal driving state and the current vehicle state, and the driving risk level is determined to be one of a low abnormality level, a medium abnormality level, and a severe abnormality level.

[0054] In an embodiment of the present invention, the preset danger threshold is a safety threshold used to reflect abnormal driving conditions. The preset danger threshold is greater than the preset deviation threshold. The preset danger threshold can be dynamically adjusted based on different driving scenarios and individual driver differences. When the driver is determined to be in an abnormal driving state, if the characteristic deviation degree in the abnormal driving state is greater than or equal to the preset danger threshold, indicating that the current driver's driving state is extremely abnormal, the driving risk level is determined to be a severe abnormality level without considering the vehicle state. If the characteristic deviation degree in the abnormal driving state is less than the preset danger threshold, indicating that the current driver's driving state is moderately abnormal, the current vehicle state can be comprehensively considered to perform driving risk identification. The vehicle controller obtains the current vehicle state through the vehicle sensor, performs driving risk identification based on the abnormal driving state and the current vehicle state, and determines the driving risk level as one of a low abnormality level, a medium abnormality level, and a severe abnormality level.

[0055] If the characteristic deviation degree under an abnormal driving state is less than a first threshold and the vehicle state is relatively stable (e.g., low speed driving, smooth steering), the driving risk level is determined to be a low abnormality level. A low abnormality level indicates that the driver's driving state presents a slight risk but does not immediately endanger safety. If the characteristic deviation degree under an abnormal driving state is greater than the first threshold and less than a second threshold, and the vehicle state presents a certain risk (e.g., medium speed driving, unstable steering), the driving risk level is determined to be a medium abnormality level. A medium abnormality level indicates that the driver's driving state presents a moderate risk and may affect driving safety. If the characteristic deviation degree under an abnormal driving state is greater than a second threshold and the vehicle state presents a significant risk (e.g., high speed driving, sharp turns, sudden braking), the driving risk level is determined to be a severe abnormality level. A severe abnormality level indicates that the driver's driving state presents a significant risk and may endanger life. The first threshold is less than the second threshold, and the second threshold is less than or equal to a preset danger threshold. The preset danger threshold is a safety threshold used to reflect abnormal driving conditions. In this embodiment, the first threshold, the second threshold, and the preset danger threshold can all be dynamically adjusted based on different driving scenarios and individual driver differences, and this embodiment is not limited to this.

[0056] It should be noted that, in this embodiment, the vehicle controller can collect the vehicle status through the vehicle's built-in sensors. The vehicle status includes body posture data and driving control data, which may specifically include vehicle speed, acceleration, yaw angular velocity, steering wheel angle, throttle / brake pedal pressure, etc. The vehicle controller can obtain the vehicle status in real time through the CAN bus.

[0057] For example, if the degree of characteristic deviation in the abnormal driving state is less than the preset danger threshold, the current vehicle state is obtained, and the driving risk is identified by combining the abnormal driving state and the vehicle state. For example, when the driver is breathing rapidly and the steering wheel shakes continuously for a period of time at high frequency, which may affect driving safety, the driving risk level is determined to be a low abnormal level. When the driver speaks intermittently and weakly and the vehicle body deviates from the lane line and drives unsteadily, the driving risk level is determined to be a medium abnormal level. If the degree of characteristic deviation in the abnormal driving state is greater than or equal to the preset danger threshold, such as when the driver suddenly stops breathing or has severe breathing disorder, the driving risk level is directly determined to be a severe abnormal level.

[0058] The embodiment of the present invention monitors the driver's abnormal driving state and vehicle status in real time, and combines the abnormal driving state and vehicle status to evaluate driving risks in multiple dimensions, thereby improving the accuracy of risk identification. Through graded identification of low-level abnormality level, medium-level abnormality level and severe abnormality level, the driving risk of the driving state is comprehensively evaluated.

[0059] In this embodiment, when it is determined that the driver is in an abnormal driving state, after determining the driver's driving risk level based on the abnormal driving state, or determining the driver's driving risk level based on the abnormal driving state and the current vehicle state, the following steps may be specifically included: If the driving risk level is a low abnormality level, a low abnormality level abnormality prompt is generated, and the vehicle is controlled to output the abnormality prompt; If the driving risk level is a medium abnormality level, a medium abnormality level warning signal is generated and the vehicle is controlled to output the warning signal; If the driving risk level is a serious abnormal level, the vehicle will be controlled to trigger emergency measures.

[0060] In an embodiment of the present invention, based on the driving risk level, the vehicle is controlled to execute a safety response strategy corresponding to the driving risk level, and the vehicle is controlled to handle abnormal driving conditions. Specifically, for low-level abnormality levels, such as fatigue driving or emotional abnormality, the driver can be reminded to relax and rest through voice prompts and other means; for medium abnormality levels, intervention measures such as early warnings can be used to alleviate the driver's abnormality; for severe abnormality levels, emergency measures can be triggered, and the vehicle automatically slows down and finds a safe place to stop, while calling for emergency rescue. Based on different driving risk levels, a safety response strategy that matches the risk level is provided to promptly and effectively handle abnormal driving conditions and improve vehicle driving safety.

[0061] Specifically, if the driving risk level is low, the driver's abnormal driving behavior is less dangerous and requires a driver alert. Therefore, a low-level abnormality alert is generated, and the vehicle is controlled to output the abnormality alert. This can be through voice alerts (e.g., "You are short of breath, please pay attention") or instrument panel signal lights. If the driving risk level is medium, the current abnormal driving behavior may affect driving safety, requiring a more effective driver warning. Therefore, a medium-level warning signal is generated, and the vehicle is controlled to output the warning signal. The warning signal may include warning lights, audible warnings, or steering wheel and seat vibrations. The warning signal is more critical than the abnormality alert. If the driving risk level is severe, the vehicle is immediately controlled to trigger emergency measures, automatically engaging the vehicle's safety systems and activating protection mechanisms to avoid danger. The vehicle automatically slows down and seeks a safe location to stop, while calling for emergency assistance.

[0062] The embodiments of the present invention adopt corresponding safety response strategies according to different driving risk levels, from primary reminders to protection mechanisms for major anomalies, comprehensively ensuring driving safety, improving user experience and driving safety, and providing strong protection for the driver's safe driving.

[0063] To facilitate those skilled in the art to understand the vehicle driving risk determination solution provided in this embodiment, refer to Figure 6 , shows an interactive schematic diagram of a vehicle driving risk determination method provided by an embodiment of the present invention, including a driver, a directional microphone array, a vehicle sensor, a vehicle controller and a vehicle safety response system, wherein the driver will produce sounds such as breathing sounds and speaking voice lines, the directional microphone array monitors and transmits sound signals such as breathing sounds and voice lines to the vehicle controller, the vehicle controller extracts the breathing characteristics and voice line characteristics of the breathing sounds, and determines whether the driver's driving state is abnormal. When it is determined that the driver is in an abnormal driving state, a request is made to the vehicle sensor to obtain the vehicle state, and the vehicle sensor transmits the vehicle state to the vehicle controller. Through the association of the abnormal driving state and the vehicle state, and the independent triggering of the abnormal driving state, a dual verification mechanism is formed to accurately identify the driving risk level. The vehicle safety response system adopts a corresponding safety response strategy based on the driving risk level and feeds back to the driver.

[0064] Reference Figure 7 , shows a schematic structural diagram of a vehicle driving risk determination device provided by an embodiment of the present invention, the device comprising: The sound monitoring module 201 is used to monitor the driver's sound signal in the current vehicle state; wherein the sound signal includes a breathing sound signal and a sound line signal; A feature extraction module 202 is configured to extract features from the breathing sound signal and the sound line signal to obtain a breathing feature of the breathing sound signal and an acoustic feature of the sound line signal; A driving state module 203 is configured to use the breathing characteristics and the acoustic characteristics to judge the current driving state of the driver and determine whether the driver is in an abnormal driving state; The risk level module 204 is used to determine the driver's driving risk level based on the abnormal driving state when it is determined that the driver is in an abnormal driving state, or to determine the driver's driving risk level based on the abnormal driving state and the current vehicle state.

[0065] Optionally, the sound monitoring module 201 includes: The acquisition submodule is used to obtain the current vehicle status of the vehicle and use a directional microphone array to monitor the sound signals in the seat area under the current vehicle status; The denoising submodule is used to denoise the sound signal in the main driving area, filter out the vehicle's ambient noise and the noise of passengers in the non-main driving area of the vehicle, and obtain the denoised sound signal of the driver in the main driving area.

[0066] Optionally, the sound monitoring module 201 further includes: A verification submodule is configured to match the sound signal in the primary driver's area with a pre-generated historical sound database to determine whether the driver in the primary driver's area has passed identity verification; wherein the historical sound database includes the voices of users who have passed identity verification; an identification submodule, configured to, if it is determined that the driver in the main driving area has passed the identity verification, directionally identify the sound signal in the main driving area; The updating submodule is configured to update the voice signal of the driver in the main driving area to the historical voice database otherwise.

[0067] Optionally, the feature extraction module 202 includes: The first extraction submodule is used to extract the features of the respiratory sound signal, extract the respiratory frequency, respiratory rhythm and respiratory amplitude of the respiratory sound signal, and obtain the respiratory features of the respiratory sound signal. The second extraction submodule is configured to perform feature extraction on the sound line signal, extract the high frequency features and energy mutation of the sound line signal, and obtain the acoustic features of the sound line signal.

[0068] Optionally, the driving status module 203 includes: a predetermination submodule, for predetermining normal breathing characteristics and normal acoustic characteristics of the driver under normal driving conditions; a comparison submodule, configured to compare the respiratory feature with the normal respiratory feature, and to compare the acoustic feature with the normal acoustic feature, to obtain a degree of feature deviation; The state submodule is configured to determine that the driver's current driving state is an abnormal driving state if the characteristic deviation degree is greater than or equal to a preset deviation threshold.

[0069] Optionally, the risk level module 204 includes: A first determination submodule is configured to, when determining that the driver is in an abnormal driving state, determine that the driving risk level is a severe abnormal level if the characteristic deviation degree in the abnormal driving state is greater than or equal to a preset danger threshold; The second determination submodule is used to identify the driving risk based on the abnormal driving state and the current vehicle state if the degree of characteristic deviation under the abnormal driving state is less than the preset danger threshold, and determine the driving risk level as one of a low abnormality level, a medium abnormality level, and a severe abnormality level.

[0070] Optionally, the device further comprises: a first control module, configured to generate an abnormality prompt of the low abnormality level if the driving risk level is a low abnormality level, and control the vehicle to output the abnormality prompt; a second control module, configured to generate a warning signal of the medium abnormality level if the driving risk level is the medium abnormality level, and control the vehicle to output the warning signal; The third control module is configured to control the vehicle to trigger emergency measures if the driving risk level is a serious abnormality level.

[0071] The vehicle driving risk determination device provided by the embodiment of the present invention monitors the driver's sound signal in the current vehicle state, the sound signal including the breathing sound signal and the sound line signal, performs feature extraction on the breathing sound signal and the sound line signal, obtains the breathing characteristics of the breathing sound signal and the acoustic characteristics of the sound line signal, uses the breathing characteristics and acoustic characteristics to judge the driver's current driving state, and determines whether the driver is in an abnormal driving state. If the driver is determined to be in an abnormal driving state, the driver's driving risk level is determined based on the abnormal driving state, or the driver's driving risk level is determined based on the abnormal driving state and the current vehicle state. The embodiment of the present invention performs non-contact monitoring of the driver's breathing sound and the sound line in the current vehicle state, combines the breathing characteristics and the acoustic characteristics, and identifies and judges the driver's driving state in multiple dimensions. By associating the abnormal driving state with the vehicle state and independently triggering the abnormal driving state, a dual verification mechanism is formed to accurately identify the risk level of the driving state, thereby achieving precise monitoring of the driver's driving state, improving the accuracy of determining vehicle driving risk, further improving user experience and driving safety, and providing strong protection for the driver's safe driving.

[0072] Reference Figure 8 , an embodiment of the present invention further provides an electronic device, such as Figure 8 As shown, it includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304. Processor 301; a memory 303 for storing processor-executable instructions; The processor 301 is configured to execute the instructions to implement the vehicle driving risk determination method as described above.

[0073] The communication bus mentioned in the terminal above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0074] The communication interface is used for communication between the above terminal and other devices.

[0075] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0076] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0077] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the vehicle driving risk determination method described in any of the above embodiments is implemented.

[0078] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in accordance with the embodiments of the present invention are generated. 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state disk (SSD)).

[0079] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0080] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A method for determining vehicle driving risk, characterized in that: The method comprises: Monitoring the driver's voice signal in the current vehicle state; wherein the voice signal includes a breathing sound signal and a sound line signal; performing feature extraction on the breathing sound signal and the sound line signal to obtain a breathing feature of the breathing sound signal and an acoustic feature of the sound line signal; Using the breathing characteristics and the acoustic characteristics to judge the current driving state of the driver, and determining whether the driver is in an abnormal driving state; In the case where it is determined that the driver is in an abnormal driving state, the driver's driving risk level is determined according to the abnormal driving state, or the driver's driving risk level is determined according to the abnormal driving state and the current vehicle state.

2. The method according to claim 1, characterized in that The monitoring of the driver's voice signal in the current vehicle state includes: Acquire the current vehicle state of the vehicle and use a directional microphone array to monitor the sound signals in the seat area under the current vehicle state; The sound signal in the main driving area is denoised to filter out the vehicle's ambient noise and the noise of passengers in the non-main driving area, and the denoised sound signal of the driver in the main driving area is obtained.

3. The method according to claim 2, characterized in that Before performing denoising on the sound signal in the primary driver's area, filtering out the vehicle's ambient noise and the noise of passengers in the non-primary driver's area, and obtaining the denoised sound signal of the driver in the primary driver's area, the method further includes: matching the sound signal in the primary driver's area with a pre-generated historical sound database to determine whether the driver in the primary driver's area has passed identity authentication; wherein the historical sound database includes the voices of users who have passed identity authentication; If it is determined that the driver in the main driving area has passed the identity verification, directionally identifying the sound signal in the main driving area; Otherwise, the voice signal of the driver in the main driving area is updated to the historical voice database.

4. The method according to claim 1, wherein The extracting features of the breathing sound signal and the sound line signal to obtain the breathing features of the breathing sound signal and the acoustic features of the sound line signal includes: Extract the respiratory frequency, respiratory rhythm and respiratory amplitude of the respiratory signal to obtain the respiratory characteristics of the respiratory signal. Feature extraction is performed on the sound line signal to extract high-frequency features and energy mutations of the sound line signal to obtain acoustic features of the sound line signal.

5. The method according to claim 1, wherein The step of using the breathing characteristics and the acoustic characteristics to judge the current driving state of the driver and determining whether the driver is in an abnormal driving state includes: Predetermining normal breathing characteristics and normal acoustic characteristics of the driver under normal driving conditions; Comparing the breathing feature with the normal breathing feature, and comparing the acoustic feature with the normal acoustic feature to obtain a feature deviation degree; If the characteristic deviation degree is greater than or equal to a preset deviation threshold, it is determined that the driver's current driving state is an abnormal driving state.

6. The method according to claim 5, characterized in that In the case where it is determined that the driver is in an abnormal driving state, determining the driver's driving risk level according to the abnormal driving state, or determining the driver's driving risk level according to the abnormal driving state and the current vehicle state, includes: In the case where the driver is determined to be in an abnormal driving state, if the characteristic deviation degree under the abnormal driving state is greater than or equal to the preset danger threshold, the driving risk level is determined to be a severe abnormal level; If the degree of characteristic deviation under the abnormal driving state is less than the preset danger threshold, driving risk identification is performed based on the abnormal driving state and the current vehicle state, and the driving risk level is determined to be one of a low abnormality level, a medium abnormality level, and a severe abnormality level.

7. The method according to claim 6, characterized in that After determining that the driver is in an abnormal driving state, determining the driver's driving risk level according to the abnormal driving state, or determining the driver's driving risk level according to the abnormal driving state and the current vehicle state, the method further includes: If the driving risk level is a low abnormality level, generating an abnormality prompt of the low abnormality level, and controlling the vehicle to output the abnormality prompt; If the driving risk level is a medium abnormality level, generating a warning signal of the medium abnormality level, and controlling the vehicle to output the warning signal; If the driving risk level is a serious abnormal level, the vehicle is controlled to trigger emergency measures.

8. A vehicle driving risk determination device, characterized in that: The device comprises: A sound monitoring module is used to monitor the driver's sound signal in the current vehicle state; wherein the sound signal includes a breathing sound signal and a sound line signal; a feature extraction module, configured to extract features from the breathing sound signal and the sound line signal to obtain a breathing feature of the breathing sound signal and an acoustic feature of the sound line signal; a driving state module, configured to judge the driver's current driving state by using the breathing characteristics and the acoustic characteristics, and determine whether the driver is in an abnormal driving state; The risk level module is used to determine the driver's driving risk level based on the abnormal driving state when it is determined that the driver is in an abnormal driving state, or to determine the driver's driving risk level based on the abnormal driving state and the current vehicle state.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the vehicle driving risk determination method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle driving risk determination method according to any one of claims 1 to 7 is implemented.

Images