Vehicle control method and device for preventing fatigue driving and electronic equipment

Abstract

The invention provides a vehicle control method and device for preventing fatigue driving and electronic equipment, and the method comprises the steps: collecting multi-mode driving state data in a vehicle driving process, the multi-mode driving state data comprising human body state characterization data of a driver and driving state data; the human body state characterization data is utilized to determine multi-dimensional quantization factors, and the multi-dimensional quantization factors comprise a time factor, a posture stiffness factor, a micro-motion factor and a physiological calm factor; determining a fatigue index according to the time factor, the attitude stiffness factor, the micro-motion factor and the physiological calm factor; and according to the fatigue index and the driving state data, a hierarchical response strategy for preventing fatigue driving is determined, and the vehicle is controlled according to the hierarchical response strategy. By adopting the vehicle control method and device for preventing fatigue driving and the electronic equipment, the detection accuracy of a driver fatigue monitoring system is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and more specifically, to a vehicle control method, device, and electronic device for preventing fatigue driving. Background Technology

[0002] With the development of science and technology and the improvement of people's living standards, the use of vehicles has become increasingly common. Consequently, road traffic safety issues have become increasingly serious, such as the increasing frequency of traffic accidents caused by fatigued driving. Currently, driver fatigue monitoring systems rely on direct analysis methods such as respiratory rate, heart rate, blood pressure, blood oxygen saturation, and pulse.

[0003] However, existing driver fatigue monitoring systems have significant shortcomings in terms of detection accuracy and are prone to misjudging fatigue. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a vehicle control method, device and electronic device for preventing fatigue driving, so as to overcome at least one of the above-mentioned defects.

[0005] In a first aspect, embodiments of this application provide a vehicle control method for preventing fatigued driving, including: Collect multimodal driving state data during vehicle operation. The multimodal driving state data includes driver's physical state representation data and vehicle state data. Using human body state representation data, multi-dimensional quantitative factors are determined, including time factor, posture stiffness factor, micro-movement factor, and physiological calm factor. The fatigue index is determined based on time factor, posture stiffness factor, micro-movement factor, and physiological calm factor. The fatigue index is corrected using driving status data to determine a graded response strategy to prevent fatigued driving, and the vehicle is controlled according to the graded response strategy.

[0006] Optionally, the human body state representation data includes facial expression data, and the micro-motion factor is determined by the following methods: extracting features from the facial expression data to obtain the temporal features of the expression; determining whether the fatigue candidate conditions are met based on the temporal features of the expression; if the fatigue candidate conditions are met, acquiring the human body micro-motion signal, performing a Fourier transform on the human body micro-motion signal, and extracting the frequency band energy of the preset micro-motion frequency range; comparing the frequency band energy with the reference energy to determine the micro-motion factor based on the comparison result.

[0007] Optionally, the human state representation data comprises seat pressure data, and the time factor is determined by: determining continuous driving time according to the seat pressure data; constructing a first factor prediction model in which a dependent variable is monotonously increased in a non-linear manner with an increase of an independent variable; inputting the continuous driving time into the first factor prediction model as the independent variable to determine the time factor.

[0008] Optionally, the seat pressure data comprises a pressure distribution matrix, and the posture rigidity factor is determined by: constructing a second factor prediction model with segmented changes; determining a standard deviation change rate of the pressure distribution matrix; inputting the standard deviation change rate into the second factor prediction model as the independent variable to determine the posture rigidity factor.

[0009] Optionally, the human state representation data comprises heart rate data, and the physiological calm factor is determined by: determining a heart rate variability index according to the heart rate data; comparing the heart rate variability index with a reference variability index to determine the physiological calm factor according to a comparison result.

[0010] Optionally, the step of determining the fatigue index according to the time factor, the posture rigidity factor, the micro-motion factor and the physiological calm factor comprises: determining the fatigue index according to a dynamic weighted geometric mean value of the time factor, the posture rigidity factor, the micro-motion factor and the physiological calm factor.

[0011] Optionally, the fatigue index is corrected by using the driving state data, and the step of determining the hierarchical response strategy for preventing fatigue driving comprises: determining an index correction coefficient according to the driving state data; adjusting the fatigue index by using the index correction coefficient to determine the hierarchical response strategy by using the adjusted fatigue index.

[0012] Optionally, the driving state data comprises a vehicle driving speed and a vehicle position, and the step of determining the index correction coefficient according to the driving state data comprises: determining a current driving condition according to the vehicle driving speed and the vehicle position; determining the index correction coefficient according to a preset coefficient corresponding to the current driving condition.

[0013] In a second aspect, the embodiments of the present application further provide a vehicle control device for preventing fatigue driving, and the device comprises: a data acquisition module configured to acquire multi-modal driving state data in a vehicle driving process, the multi-modal driving state data comprising human state representation data of a driver and driving state data; a factor determination module configured to determine multi-dimensional quantitative factors by using the human state representation data, the multi-dimensional quantitative factors comprising a time factor, a posture rigidity factor, a micro-motion factor and a physiological calm factor; an index calculation module configured to determine a fatigue index according to the time factor, the posture rigidity factor, the micro-motion factor and the physiological calm factor; The vehicle control module is used to correct the fatigue index using driving status data, determine a graded response strategy to prevent fatigued driving, and control the vehicle according to the graded response strategy.

[0014] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the vehicle control method for preventing fatigue driving as described above are performed.

[0015] The embodiments of this application bring the following beneficial effects: This application provides a vehicle control method, device, and electronic device for preventing fatigued driving. It can evaluate the driver's state from multiple dimensions, determine a fatigue index reflecting the driver's fatigue level, and correct the fatigue index using driving status data to accurately formulate a graded response strategy corresponding to the current fatigue level. This further improves the accuracy of fatigue-preventing vehicle control and solves the problem of low detection accuracy of driver fatigue monitoring systems compared with existing fatigue-preventing vehicle control methods.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of the vehicle control method for preventing fatigue driving provided in an embodiment of this application is shown; Figure 2 A flowchart illustrating the steps for determining the micro-motion factor provided in the embodiments of this application is shown; Figure 3 A flowchart illustrating the steps for determining the time factor provided in an embodiment of this application is shown; Figure 4 A flowchart illustrating the steps for determining the attitude stiffness factor provided in an embodiment of this application is shown; Figure 5 A flowchart illustrating the steps for determining physiological calming factors provided in embodiments of this application is shown; Figure 6A flow chart of a step of determining a hierarchical response strategy provided by the embodiment of the application is shown. Figure 7 A structural schematic diagram of a vehicle control device for preventing fatigue driving provided by the embodiment of the application is shown. Figure 8 A structural schematic diagram of an electronic device provided by the embodiment of the application is shown. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the application clearer, the following will be combined with the accompanying drawings for the embodiments of the application to clearly and completely describe the technical solutions of the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application but not all the embodiments of the application. The components of the embodiments of the application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the application. Based on the embodiments of the application, every other embodiment obtained by a person skilled in the art without creative work falls within the scope of protection of the application.

[0020] To facilitate the understanding of the embodiments, the following will take, for example, the application of a vehicle control method for preventing fatigue driving provided by the embodiments of the application to a driver fatigue monitoring system to describe the above exemplary steps respectively provided by the embodiments of the application.

[0021] Please refer to Figure 1 , Figure 1 A flow chart of a vehicle control method for preventing fatigue driving provided by the embodiments of the application is shown. As shown in Figure 1 , the vehicle control method for preventing fatigue driving provided by the embodiments of the application comprises: Step S101, collecting multi-modal driving state data in a vehicle driving process.

[0022] The multi-modal driving state data can refer to driving state data of multiple modes, and the multi-modal driving state data comprises human state representation data of a driver and driving state data.

[0023] The vehicle is provided with a pressure sensor, a camera, a millimeter wave radar, and an ultrasonic sensor. The human state representation data can be collected through these sensors in the vehicle driving process, and the driving state data can be acquired through the vehicle CAN bus.

[0024] The human state representation data comprises heart rate data, facial expression data, and seat pressure data. The facial expression data can be captured by the camera, the heart rate data can be collected by the millimeter wave radar, and the seat pressure data can be collected by the pressure sensor.

[0025] In the embodiment of the present application, different types of sensors collect human state representation data in real time and transmit the data to the driver fatigue monitoring system. The driver fatigue monitoring system pre-processes the received human state representation data and the driving state data sent by the vehicle CAN bus in each monitoring period, for example, the pre-processing includes time and space alignment and elimination of abnormal values. Then, the multi-modal driving state data in a preset time length closest to the current time is used to calculate the multi-dimensional quantization factor in the monitoring period.

[0026] In step S102, the multi-dimensional quantization factor is determined using the human state representation data.

[0027] The multi-dimensional quantization factor includes a time factor, a posture rigidity factor, a micro-motion factor, and a physiological calm factor. The time factor is used to quantify the fatigue degree of the driver from the dimension of continuous driving time; the posture rigidity factor is used to quantify the fatigue degree of the driver from the dimension of body posture stability; the micro-motion factor is used to quantify the fatigue degree of the driver from the dimension of intensity and activity of body unconscious micro-motion; and the physiological calm factor is used to quantify the fatigue degree of the driver from the dimension of regulation activity of the autonomic nervous system.

[0028] The determination process of the micro-motion factor will be described below with reference to Figure 2 .

[0029] Figure 2 A flow chart of the determination step of the micro-motion factor provided by the embodiment of the present application is shown in Figure 2 , which includes: In step S1011, facial expression data is feature extracted to obtain expression time sequence features.

[0030] The facial expression data includes facial expression data at different times, and the facial expression data at different times can be feature extracted to obtain expression time sequence features in the monitoring period.

[0031] In step S1012, whether the fatigue candidate condition is met is determined according to the expression time sequence features.

[0032] The expression time sequence features include eye time sequence features, mouth time sequence features, and facial muscle time sequence features. After the expression time sequence features are determined, the eye time sequence features, the mouth time sequence features, and the facial muscle time sequence features are time aligned according to the time stamp.

[0033] The preset time length (such as 5 seconds) is adopted for the sliding window, and the time sequence feature statistics of the time-aligned expression time sequence features in the sliding window are calculated every time the sliding window slides 1 second. The time sequence feature statistics include eye time sequence feature statistics, mouth time sequence feature statistics, and facial muscle time sequence feature statistics.

[0034] For the eye time sequence features, the eye time sequence feature statistics include the mean value of the percentage of eyelid covering pupil per unit time (PERCLOS), the mean value of pupil dilation rate, and the blinking interval coefficient of variation. If the time sequence of PERCLOS shows a monotonous upward trend and multiple eye time sequence feature statistics all satisfy the first preset threshold condition, it is determined that the eye time sequence features satisfy the fatigue candidate condition. The multiple eye time sequence feature statistics all satisfying the first preset threshold condition includes that the mean value of PERCLOS in the sliding window is greater than a set closing threshold (such as 0.2), the blinking interval coefficient of variation in the sliding window is less than a set interval threshold (such as 0.3), and the mean value of pupil dilation rate in the sliding window is less than a set pixel threshold (such as 0.5).

[0035] For the mouth time sequence features, the mouth time sequence feature statistics include the mean value of mouth opening degree change rate and the yawning duration proportion. If the time sequence of the mouth opening degree change rate shows a monotonous upward trend and multiple mouth time sequence features all satisfy the second preset threshold condition, it is determined that the mouth time sequence features satisfy the fatigue candidate condition. The multiple mouth time sequence features all satisfying the second preset threshold condition includes that the mouth opening degree change rate is greater than a set change rate threshold (such as 0.5) and the yawning duration proportion is greater than a set duration proportion threshold (such as 15%). The mouth opening degree change rate is determined based on the difference in opening degree between adjacent frames.

[0036] For the facial muscle time sequence features, the facial muscle time sequence feature statistics include the muscle relaxation time sequence variance. If the time sequence of the muscle relaxation degree shows a monotonous upward trend and the muscle relaxation time sequence variance satisfies the third preset threshold condition, it is determined that the facial muscle time sequence features satisfy the fatigue candidate condition. The muscle relaxation time sequence variance satisfying the third preset threshold condition includes that the muscle relaxation time sequence variance is less than a set relaxation threshold (such as 0.1).

[0037] If the eye time sequence features, the mouth time sequence features, and the facial muscle time sequence features all satisfy the fatigue candidate condition, it is determined that the facial expression of the driver satisfies the fatigue candidate condition, and step S1013 is performed.

[0038] In step S1013, if the fatigue candidate condition is satisfied, the human micro-motion signal is obtained, and the human micro-motion signal is subjected to Fourier transform, and the frequency band energy of the preset micro-motion frequency interval is extracted.

[0039] When the fatigue candidate condition is met, the human micro-motion signals in the same sliding window are extracted from the pressure sensor, the human micro-motion signals are subjected to Fourier transform to obtain frequency domain signals, the frequency domain signals in a preset micro-motion frequency interval (0.5Hz-2Hz micro-motion frequency interval) are intercepted, and the frequency band energy in the frequency band is calculated.

[0040] In step S1014, the frequency band energy is compared with the reference energy to determine the micro-motion factor according to a comparison result.

[0041] An energy mean value of the preset micro-motion frequency interval when the driver is normally driving (non-fatigue driving) is obtained, and the energy mean value is taken as the reference energy.

[0042] The ratio of the frequency band energy to the reference energy is calculated, and the difference between a preset value and the ratio is determined as the micro-motion factor. Here, the preset value can be 1, the closer the frequency band energy and the reference energy, the closer the micro-motion factor to 0, indicating that the micro-motion is more normal; the farther the frequency band energy and the reference energy, the closer the micro-motion factor to 1, indicating that the micro-motion is more abnormal.

[0043] The determination process of the time factor will be described below with reference to Figure 3 .

[0044] Figure 3 A flow chart of the determination step of the time factor provided by the embodiments of the present application is shown in Figure 3 , which includes: In step S1021, the continuous driving time and the pressure distribution matrix are determined according to the seat pressure data.

[0045] The seat pressure data includes the effective pressure signal and the pressure distribution matrix, and the continuous driving time of the driver can be determined according to the continuity of the effective pressure signal.

[0046] In step S1022, a first factor prediction model in which the dependent variable monotonously increases with the independent variable in a non-linear manner is constructed, the continuous driving time is taken as the independent variable and input into the first factor prediction model to determine the time factor.

[0047] The first factor prediction model is: , wherein t represents the continuous driving time, , and t represents the time factor. The continuous driving time is taken as the value of the independent variable and input into the first factor prediction model to determine the time factor.

[0048] The determination process of the posture rigidity factor will be described below with reference to Figure 4 .

[0049] Figure 4 A flow chart of the determination step of the posture rigidity factor provided by the embodiments of the present application is shown in Figure 4As shown, the steps for determining the attitude stiffness factor include: Step S1031: Construct a second factor prediction model for segmented changes.

[0050] When the driver frequently adjusts their posture (e.g., swaying shoulders, shifting hips), the standard deviation of the pressure distribution matrix changes significantly, indicating moderate driver fatigue. When the driver's posture remains almost unchanged (muscle relaxation, stiff sitting), the standard deviation of the pressure distribution matrix changes very little, indicating severe driver fatigue or postural stiffness. When the driver's posture is stable and there are slight natural adjustments, the standard deviation of the pressure distribution matrix changes moderately, indicating a normal driver condition. The standard deviation of the pressure distribution matrix is ​​denoted as: .

[0051] Therefore, the second factor prediction model can be: ; Where P represents the attitude stiffness factor; This represents the first threshold, such as 0.03; For example, 0.2.

[0052] Step S1032: Determine the rate of change of the standard deviation of the pressure distribution matrix, and input the rate of change of the standard deviation as the independent variable into the second factor prediction model to determine the attitude stiffness factor.

[0053] Based on the pressure distribution matrices collected at different times, the global standard deviation of the pressure distribution can be determined. The global standard deviation reflects the dispersion of the pressure distribution in a single frame. A standard deviation sequence is constructed from multiple global standard deviations within a sliding window, and the rate of change of this sequence is calculated to obtain the standard deviation change rate.

[0054] By inputting the rate of change of standard deviation into the second factor prediction model, the posture stiffness factor can be calculated.

[0055] The following reference Figure 5 This section will introduce the process of determining physiological calming factors.

[0056] Figure 5 A flowchart illustrating the steps for determining physiological calming factors provided in embodiments of this application is shown, as follows: Figure 5 As shown, the steps for determining physiological calming factors include: Step S1041: Determine the heart rate variability index based on the heart rate data.

[0057] The time interval between two adjacent normal sinus beats (labeled as N waves) is extracted from the heart rate data. A heartbeat interval sequence is generated based on multiple time intervals. Outliers in the heartbeat interval sequence (such as abrupt changes caused by premature beats) are removed. The heartbeat interval sequence is then completed using a linear interpolation algorithm to finish the data preprocessing.

[0058] The pre-processed heartbeat interval sequence is subjected to a fast Fourier transform to decompose the time series signal into a spectrum of sinusoidal waves of different frequencies superimposed, and a power spectral density (PSD) of the spectrum is determined.

[0059] The power spectral densities of different frequency intervals are integrated to determine a first power and a second power, wherein the different frequency intervals include a low frequency interval (0.04-0.15 Hz) and a high frequency interval (0.15-0.4 Hz), the first power is the power under the low frequency interval, and the second power is the power under the high frequency interval.

[0060] The ratio of the first power to the second power is calculated, and the power ratio is determined as a heart rate variability index.

[0061] In step S1042, the heart rate variability index is compared with a reference variability index to determine a physiological calmness factor according to a comparison result.

[0062] The heart rate variability index of the driver when driving normally (non-fatigue driving) is obtained, i.e., the ratio of the first power to the second power when driving normally, and the ratio of the first power to the second power when driving normally is taken as the reference variability index.

[0063] The ratio of the heart rate variability index to the reference variability index is calculated, and the ratio is determined as the physiological calmness factor. The closer the physiological calmness factor is to 1, the more fatigue-free the driver is; the greater the physiological calmness is than 1, the more fatigue the driver is; and the smaller the physiological calmness is than 1, the more relaxed the driver is.

[0064] In step S103, a fatigue index is determined according to the time factor, the posture rigidity factor, the micro-motion factor, and the physiological calmness factor.

[0065] Specifically, the fatigue index can be determined according to the sum of dynamic weights of the time factor, the posture rigidity factor, the micro-motion factor, and the physiological calmness factor.

[0066] The calculation formula of the fatigue index is: wherein M represents the micro-motion factor, B represents the physiological calmness factor, 、 、 、 respectively represent the weight coefficients of the corresponding factors.

[0067] In step S104, the fatigue index is corrected using the driving state data, and a hierarchical response strategy for preventing fatigue driving is determined to control the vehicle according to the hierarchical response strategy.

[0068] The determination process of the hierarchical response strategy will be described below with reference to Figure 6 .

[0069] Figure 6 A flow chart of the determining step of the hierarchical response strategy provided by the embodiment of the application is shown in FIG. 1. Figure 6 As shown in the figure, the determining step of the hierarchical response strategy comprises: Step S1051, determining an index correction coefficient according to the driving state data.

[0070] The driving state data comprises a vehicle driving speed and a vehicle position.

[0071] Specifically, a current driving condition is determined according to the vehicle driving speed and the vehicle position, and then an index correction coefficient is determined according to a preset coefficient corresponding to the current driving condition.

[0072] For example, if the vehicle driving speed is greater than a first set speed (e.g. 80 km / h), it is determined that the current driving condition is high-speed cruising; if the vehicle driving speed is less than a second set speed, it is determined that the current driving condition is slow driving in congestion; and if the vehicle driving speed is a third set speed (e.g. 0), it is determined that the current driving condition is parking waiting, wherein the second set speed is greater than the third set speed.

[0073] If the current driving condition is high-speed cruising, it is determined that the preset coefficient is , , ; if the current driving condition is urban driving, it is determined that the preset coefficient is , , ; and if the current driving condition is slow driving in congestion, it is determined that the preset coefficient is , , .

[0074] The index correction coefficient under the current driving condition is determined by using the formula .

[0075] Step S1052, adjusting the fatigue index by using the index correction coefficient, so as to determine the hierarchical response strategy by using the adjusted fatigue index.

[0076] The product of the index correction coefficient and the fatigue index is determined as the final fatigue index, and the hierarchical response strategy is determined according to the numerical interval corresponding to the final fatigue index and the current driving condition.

[0077] Specifically, the hierarchical response strategy comprises three levels, i.e. a first-level response strategy, a second-level response strategy and a third-level response strategy, wherein the first-level response strategy is a strategy for representing gentle reminding, the second-level response strategy is a strategy for representing comfortable intervention, and the third-level response strategy is a strategy for representing active service.

[0078] According to the final fatigue index, a target hierarchical response strategy is determined, and it is determined whether the current driving condition meets the preset condition corresponding to the target hierarchical response strategy. If the preset condition is not met, the target hierarchical response strategy is downgraded to a first level; if the preset condition is met, the vehicle is controlled to execute the target hierarchical response strategy.

[0079] For example, the preset condition corresponding to the set three-level hierarchical response strategy is that the driving condition is a parking waiting state. If the target hierarchical response strategy is a three-level response strategy, it is determined whether the current driving condition is a parking waiting state. If it is not a parking waiting state, the target hierarchical response strategy is downgraded to a two-level response strategy, and the vehicle is controlled to execute the target hierarchical response strategy, so as to realize dynamic hierarchical response strategy making.

[0080] Among them, the first level response strategy can be seat vibration and atmosphere lamp flicker, the second level response strategy can be seat massage, air conditioning temperature adjustment and refreshing music playing, and the third level response strategy can be navigation to recommended service area, reservation of rest time and "please get up" prompt.

[0081] The vehicle control method for preventing fatigue driving provided in the embodiments of the present application can evaluate the state of the driver from multiple dimensions, determine a fatigue index reflecting the fatigue degree of the driver, and correct the fatigue index through driving state data, so as to accurately make a hierarchical response strategy corresponding to the current fatigue degree, and further improve the accuracy of the vehicle control for preventing fatigue, thereby solving the problem of low detection accuracy of the driver fatigue monitoring system.

[0082] Based on the same inventive concept, the embodiments of the present application also provide a vehicle control device for preventing fatigue driving corresponding to the vehicle control method for preventing fatigue driving. Since the principle of solving problems in the device of the embodiments of the present application is similar to the vehicle control method for preventing fatigue driving described above, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described herein.

[0083] Please refer to Figure 7 , Figure 7 is a structural schematic diagram of a vehicle control device for preventing fatigue driving provided in the embodiments of the present application. As shown in Figure 7 , the vehicle control device for preventing fatigue driving 200 comprises: A data acquisition module 201 is configured to acquire multi-modal driving state data in the process of driving the vehicle, and the multi-modal driving state data comprises human state representation data of the driver and driving state data. A factor determination module 202 is configured to determine multi-dimensional quantitative factors by using the human state representation data, and the multi-dimensional quantitative factors comprise a time factor, a posture rigidity factor, a micro-motion factor and a physiological calmness factor. The index calculation module 203 is configured to determine the fatigue index according to the time factor, the posture rigidity factor, the micro-motion factor and the physiological calm factor. The vehicle control module 204 is configured to correct the fatigue index by using the driving state data, determine a grading response strategy for preventing fatigue driving, and control the vehicle according to the grading response strategy.

[0084] Please refer to Figure 8 , Figure 8 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 3. Figure 8 As shown in FIG. 3, the electronic device 300 includes a processor 310, a memory 320 and a bus 330.

[0085] The memory 320 stores machine readable instructions executable by the processor 310, and when the electronic device 300 is running, the processor 310 and the memory 320 communicate through the bus 330. When the machine readable instructions are executed by the processor 310, the steps of the vehicle control method for preventing fatigue driving in the method embodiment shown in FIG. 2 can be performed. For specific implementation, please refer to the method embodiment, which will not be described here. Figure 1 The processor 310, the memory 320 and the bus 330 can perform the steps of the vehicle control method for preventing fatigue driving in the method embodiment shown in FIG. 2. For specific implementation, please refer to the method embodiment, which will not be described here.

[0086] The present application also provides a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the vehicle control method for preventing fatigue driving in the method embodiment shown in FIG. 2 can be performed. For specific implementation, please refer to the method embodiment, which will not be described here. Figure 1 The processor 310, the memory 320 and the bus 330 can perform the steps of the vehicle control method for preventing fatigue driving in the method embodiment shown in FIG. 2. For specific implementation, please refer to the method embodiment, which will not be described here.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be described here.

[0088] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0090] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0091] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, and various program code storage media.

[0092] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, used to illustrate the technical solutions of the present application, and not to limit them, the protection scope of the present application is not limited thereto, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand: any skilled person familiar with the technical field can modify or easily think of changes to the technical solutions recorded in the foregoing embodiments within the technical range disclosed by the present application, or make equivalent replacement to part of the technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and all should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A vehicle control method for preventing fatigued driving, characterized in that, include: Collect multimodal driving state data during vehicle operation, including driver's physical state representation data and vehicle state data; Using the human body state representation data, multi-dimensional quantification factors are determined, including time factors, posture stiffness factors, micro-movement factors, and physiological calmness factors. The fatigue index is determined based on the time factor, the posture stiffness factor, the micro-movement factor, and the physiological calm factor. The fatigue index is corrected using the driving status data to determine a graded response strategy for preventing fatigued driving, and the vehicle is controlled according to the graded response strategy.

2. The method according to claim 1, characterized in that, The human body state representation data includes facial expression data, and the micro-motion factor is determined through the following methods: Feature extraction is performed on the facial expression data to obtain temporal features of the expressions; Based on the aforementioned facial expression timing characteristics, determine whether the fatigue candidate condition is met; If the fatigue candidate condition is met, the human body micro-motion signal is acquired, and the human body micro-motion signal is subjected to Fourier transform, and the frequency band energy of the preset micro-motion frequency range is extracted. The frequency band energy is compared with a reference energy to determine the micro-motion factor based on the comparison result.

3. The method according to claim 1, characterized in that, The human body condition characterization data includes seat pressure data, and the time factor is determined in the following way: The continuous driving time is determined based on the seat pressure data. A first factor prediction model is constructed in which the dependent variable increases nonlinearly and monotonically with the increase of the independent variable. The continuous driving time is input into the first factor prediction model as an independent variable to determine the time factor.

4. The method according to claim 3, characterized in that, The seat pressure data includes a pressure distribution matrix, and the posture stiffness factor is determined in the following way: Construct a second-factor prediction model for segmented changes; Determine the rate of change of the standard deviation of the pressure distribution matrix, and input the rate of change of the standard deviation as an independent variable into the second factor prediction model to determine the attitude stiffness factor.

5. The method according to claim 1, characterized in that, The human body state characterization data includes heart rate data, and the physiological calm factor is determined through the following methods: Based on the heart rate data, determine the heart rate variability index; The heart rate variability index is compared with a reference variability index to determine the physiological calm factor based on the comparison results.

6. The method according to claim 3, characterized in that, The step of determining the fatigue index based on the time factor, the posture stiffness factor, the micro-motion factor, and the physiological calm factor includes: The fatigue index is determined based on the dynamic weighted geometric mean of the time factor, the posture stiffness factor, the micro-motion factor, and the physiological calm factor.

7. The method according to claim 1, characterized in that, The step of correcting the fatigue index using the driving status data and determining a graded response strategy to prevent fatigued driving includes: Based on the driving status data, determine the index correction coefficient; The fatigue index is adjusted using the index correction coefficient, and the adjusted fatigue index is used to determine a graded response strategy.

8. The method according to claim 7, characterized in that, The driving status data includes vehicle speed and vehicle position. The step of determining the exponential correction coefficient based on the driving status data includes: The current driving conditions are determined based on the vehicle's speed and position. The index correction coefficient is determined based on the preset coefficient corresponding to the current driving conditions.

9. A vehicle control device for preventing fatigued driving, characterized in that, include: The data acquisition module is used to collect multimodal driving state data during vehicle operation. The multimodal driving state data includes driver's human body state representation data and driving state data. The factor determination module is used to determine multi-dimensional quantitative factors using the human body state characterization data. The multi-dimensional quantitative factors include time factors, posture stiffness factors, micro-movement factors, and physiological calmness factors. The index calculation module is used to determine the fatigue index based on the time factor, the posture stiffness factor, the micro-motion factor, and the physiological calm factor. The vehicle control module is used to correct the fatigue index using the driving status data, determine a graded response strategy to prevent fatigued driving, and control the vehicle according to the graded response strategy.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the vehicle control method for preventing fatigue driving as described in any one of claims 1 to 8.

Images