Methods, devices, and computer equipment for determining driver fatigue status

Abstract

This application relates to the field of vehicle technology, and in particular to a method, apparatus, and computer device for determining driver fatigue state. It includes: determining a first influence range of the driving environment on the driver's reaction speed based on driving environment information; wherein the driving environment information includes at least weather and road surface information; determining a second influence range of traffic conditions on the driver's reaction speed based on traffic condition information of the driving route corresponding to the vehicle; determining a third influence range of the driver's physical condition on the driver's reaction speed based on the driver's physical condition information; determining a predicted reaction speed value based on the first, second, and third influence ranges; and determining the driver's fatigue state based on the predicted reaction speed value and the acquired driver's reaction speed monitoring value.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, and computer device for determining driver fatigue state. Background Technology

[0002] Indeed, with the surge in the number of cars, traffic safety has become a major global issue that cannot be ignored. Driver fatigue is a significant contributing factor to traffic accidents, making its monitoring and prevention particularly important.

[0003] While monitoring a driver's physiological signals such as electrocardiogram, blood pressure, and brain waves can reflect the driver's fatigue level to some extent, this method usually requires the driver to wear special monitoring equipment, which may cause discomfort to the driver during actual driving and affect driving operation. In addition, the equipment is expensive and not conducive to popularization.

[0004] Existing fatigue driving monitoring systems often lack real-time performance and cannot quickly and accurately determine the driver's fatigue state, which reduces the effectiveness of the monitoring system to some extent. Therefore, improvements are urgently needed. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, and computer device for determining driver fatigue state that can improve the accuracy of fatigue state identification, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for determining driver fatigue state, including:

[0007] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0008] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0009] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0010] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0011] The driver's fatigue state is determined based on the predicted reaction speed and the obtained driver's reaction speed monitoring values.

[0012] In one embodiment, determining the first influence of the driving environment on the driver's reaction speed based on the vehicle's driving environment information includes:

[0013] Determine the interaction factors between weather and road surface information;

[0014] Based on weather information, interaction factors, and road surface information, the magnitude of the first impact of the driving environment on the driver's reaction speed is determined.

[0015] In one embodiment, traffic condition information includes traffic flow information, traffic accident information, road construction information, traffic control information, and driving behavior information of other vehicles on the driving route; based on the traffic condition information of the driving route corresponding to the vehicle, a second impact of traffic conditions on the driver's reaction speed is determined, including:

[0016] Determine the travel time of the driving route based on the complexity of traffic information;

[0017] Based on the time taken to travel, the second magnitude of the impact of traffic conditions on driver reaction speed is determined.

[0018] In one embodiment, determining the predicted reaction rate value based on a first influence magnitude, a second influence magnitude, and a third influence magnitude includes:

[0019] Determine the driver's basic reaction speed based on the driver's behavioral characteristics;

[0020] Based on the first, second, and third magnitudes of influence, the baseline reaction rate is adjusted to obtain the predicted reaction rate value.

[0021] In one embodiment, determining the driver's fatigue state based on the predicted reaction speed value and the acquired driver's reaction speed monitoring value includes:

[0022] The obtained driver reaction speed monitoring values ​​are compared with the predicted reaction speed values;

[0023] If the reaction speed monitoring value is greater than or equal to the reaction speed prediction value, then the driver is determined to be fatigued.

[0024] If the reaction speed monitoring value is less than the reaction speed prediction value, then the driver's fatigue state is determined to be non-fatigue.

[0025] In one embodiment, after determining the driver's fatigue state, the method further includes:

[0026] Based on the driver's fatigue level, determine the assisted driving strategy and provide feedback on the assisted driving strategy to the driver.

[0027] Secondly, this application also provides a driver fatigue state determination device, comprising:

[0028] The first determining module is used to determine the first impact of the driving environment on the driver's reaction speed based on the driving environment information of the vehicle; wherein, the driving environment information includes at least weather environment information and road surface environment information;

[0029] The second determining module is used to determine the second impact of traffic conditions on the driver's reaction speed based on traffic condition information of the driving route corresponding to the vehicle.

[0030] The third determination module is used to determine the third influence of the driver's status on the driver's reaction speed based on the driver's personnel status information.

[0031] The comprehensive assessment module is used to determine the predicted value of the reaction rate based on the first, second, and third impact magnitudes.

[0032] The fatigue level determination module is used to determine the driver's fatigue state based on the predicted reaction speed value and the acquired driver's reaction speed monitoring value.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0034] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0035] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0036] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0037] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0038] Based on the predicted reaction speed value and the acquired driver reaction speed monitoring value, the driver's fatigue state is determined. Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0039] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0040] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0041] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0042] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0043] Based on the predicted reaction speed value and the acquired driver reaction speed monitoring value, the driver's fatigue state is determined. Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0044] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0045] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0046] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0047] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0048] The driver's fatigue state is determined based on the predicted reaction speed and the obtained driver's reaction speed monitoring values.

[0049] The aforementioned method, apparatus, and computer equipment for determining driver fatigue state, by analyzing weather environment information (such as rain, snow, fog, haze, and sunny days) and road surface environment information (such as dryness, slipperiness, and potholes), can accurately quantify the impact of these factors on driver reaction speed. This helps drivers and vehicle systems better adapt to different driving environments and improves driving safety. By considering traffic conditions along the driving route (such as traffic congestion, accident-prone areas, and construction zones), this scheme can dynamically adjust the expectation of driver reaction speed, thereby more accurately predicting driver behavior under specific traffic conditions. This helps drivers make adjustments in advance and avoid potential safety hazards. By analyzing driver's personal status information (such as age, gender, driving experience, and physiological state), this scheme can more comprehensively assess the driver's reaction ability and thus more accurately predict their performance in actual driving. This helps to personalize the settings of the driver assistance system to better suit the needs of different drivers. By integrating the first, second, and third impact amplitudes, this scheme can derive a predicted reaction speed value. Comparing this predicted value with the actual monitored driver reaction speed can accurately determine whether the driver is fatigued. This helps to remind drivers to rest in a timely manner and prevent traffic accidents caused by fatigue driving. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating a method for determining driver fatigue state in one embodiment;

[0052] Figure 2 This is a flowchart illustrating the steps for determining the first impact of the driving environment on the driver's reaction speed in one embodiment.

[0053] Figure 3 This is a flowchart illustrating the step of determining the second impact of traffic conditions on driver reaction speed in one embodiment;

[0054] Figure 4 This is a flowchart illustrating the steps for determining the predicted reaction rate in one embodiment;

[0055] Figure 5 This is a flowchart illustrating the steps for determining driver fatigue status in one embodiment;

[0056] Figure 6 Here is a block diagram of a driver fatigue state determination system in one embodiment;

[0057] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] In one exemplary embodiment, such as Figure 1 As shown, a method for determining driver fatigue state is provided. Taking the application of this method to a computer device as an example, the method includes the following steps S101 to S105. Wherein:

[0060] S101, based on the driving environment information of the vehicle, determine the first influence of the driving environment on the driver's reaction speed.

[0061] The driving environment information includes at least weather environment information and road surface environment information.

[0062] Understandably, in rainy weather, slippery roads and reduced visibility require drivers to take longer to assess road conditions and react. Snowy or icy roads not only increase the risk of vehicle skidding but also significantly reduce tire-to-road friction, making vehicle control more difficult and naturally extending reaction time. Foggy weather with extremely low visibility limits drivers' vision, making it difficult to accurately judge vehicles and road conditions ahead, severely impacting reaction speed. In good weather conditions such as sunny or cloudy days, drivers have clear vision, good road conditions, and relatively faster reaction times.

[0063] Furthermore, smooth road surfaces help vehicles travel smoothly and allow drivers to react faster. Potholes or uneven surfaces increase vehicle bumps, impair the driver's vision and judgment, and lead to a decrease in reaction time. As before, slippery roads increase the risk of losing vehicle control and reduce driver reaction time. Different types of roads require different levels of driver reaction speed. For example, on highways with high speeds and heavy traffic, drivers need even faster reaction times to handle unexpected situations.

[0064] Based on the above analysis, driver reaction speed is affected by weather and road surface information. In this embodiment, the weather and road surface information are input into the first analysis model to obtain the first influence magnitude output by the first analysis model.

[0065] The first analytical model refers to a mathematical model or algorithmic framework used to assess the impact of the driving environment on the driver's reaction speed. This model can receive specific information about the driving environment as input, such as weather conditions (rain, snow, fog, visibility, etc.), road conditions (slipperiness, potholes), road type (highway, urban road, etc.), etc., and after internal processing and calculation, output a quantitative value representing the magnitude of the first speed impact of the driving environment on the driver's reaction speed.

[0066] S102, based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed.

[0067] Traffic information may include traffic flow, vehicle speed distribution, traffic light frequency, and the behavior of pedestrians and other road users.

[0068] It is understandable that (1) traffic volume: high traffic volume means that drivers need to pay more attention to surrounding vehicles and respond to lane changes, braking and other situations in a timely manner. Increased traffic volume may lead to longer driver reaction time because they need to process more information.

[0069] (2) Speed ​​distribution: When there is a large difference in vehicle speed, the driver needs to judge the speed and intention of other vehicles more quickly in order to avoid a collision. Too fast or too slow speeds can affect the driver's reaction speed because they need to adapt to different speed environments.

[0070] (3) Traffic lights: The frequency and pattern of traffic light changes affect the driver's expectations and reactions. Irregular traffic light changes may increase the driver's reaction burden.

[0071] (4) Pedestrians and other road users: Pedestrians crossing the road and bicycles suddenly changing lanes may require drivers to react quickly. These unpredictable behaviors increase the difficulty of drivers' reactions.

[0072] (5) Road design and layout: Complex road design and layout may increase the cognitive burden on drivers, thereby affecting reaction speed. For example, multi-lane intersections and complex overpasses may require drivers to take longer to react.

[0073] In this embodiment, traffic condition information is input into a second analysis model to obtain the second magnitude of the impact of traffic conditions on driver reaction speed, output by the second analysis model. The second analysis model refers to a mathematical model or algorithmic framework specifically designed to assess the degree of influence of traffic conditions on driver reaction speed. This model can receive specific information about traffic conditions as input, such as traffic flow, vehicle speed distribution, traffic light frequency, and the behavior of pedestrians and other road users. After internal processing and calculation, it outputs a quantitative value representing the second magnitude of the impact of traffic conditions on driver reaction speed.

[0074] The second analytical model provides a deeper understanding of how traffic conditions affect drivers' reaction times, thus offering safer and more efficient driving advice and guidance. For example, in situations of traffic congestion or significant speed differences, the model may output a larger impact value, reminding drivers to be more vigilant and focused.

[0075] S103, based on the driver's personnel status information, determine the third influence magnitude of the personnel status on the driver's reaction speed.

[0076] The personnel status information may include fatigue level, concentration level, emotional state, and health status.

[0077] In this embodiment, the driver's state information is input into the third analysis model to obtain the third influence magnitude of the driver's state on the driver's reaction speed, as output by the third analysis model. The third analysis model refers to a mathematical model or algorithmic framework specifically designed to assess the degree of influence of driver state on the driver's reaction speed. This model is designed to receive specific information about the driver's state as input, such as fatigue level, concentration level, emotional state, health status, driving experience, and age, and through internal processing and calculation mechanisms, output a quantitative value representing the third influence magnitude of the driver's state on the driver's reaction speed.

[0078] S104. Determine the predicted reaction rate value based on the first, second, and third influence amplitudes.

[0079] For example, B0 is the driver's basic reaction speed without any external influences.

[0080] ΔB1 is the first magnitude of influence, representing the impact of a certain external factor (such as weather conditions) on the driver's reaction speed.

[0081] ΔB2 is the second magnitude of influence, representing the impact of traffic conditions on driver reaction speed.

[0082] ΔB3 is the third influence magnitude, representing the impact of the driver's condition on reaction speed.

[0083] These effects can be positive (indicating an increase in reaction rate, i.e., a faster reaction) or negative (indicating a decrease in reaction rate, i.e., a slower reaction).

[0084] In one feasible approach, these influence magnitudes are linearly superimposed to obtain a predicted value for the reaction rate. This method assumes that the influence magnitudes are independent of each other and that their effect on the reaction rate is linear.

[0085] In another possible approach, different magnitudes of influence may interact, causing their combined effect on reaction speed to be more than a simple linear sum. For example, when a driver is highly fatigued, their reaction speed may decrease significantly even in good traffic conditions. To predict reaction speed more accurately, it may be necessary to consider the nonlinear relationships and interactions between these magnitudes of influence. This can be achieved by constructing more complex mathematical models or using machine learning algorithms that can capture the complex relationships between different factors and provide more accurate predictions.

[0086] S105, determine the driver's fatigue state based on the predicted reaction speed value and the obtained driver's reaction speed monitoring value.

[0087] Specifically, the predicted reaction speed is compared with the driver's actual reaction speed monitoring values. A reasonable threshold range is set to determine whether the driver's reaction speed deviates from the normal range. This threshold can be determined based on experience, statistical data, or safety standards.

[0088] If the driver's actual reaction speed is significantly slower than the predicted value, and this difference exceeds the set threshold range, it can be preliminarily determined that the driver may be fatigued.

[0089] In the aforementioned method for determining driver fatigue, this application analyzes weather environment information (such as rain, snow, fog, haze, and sunny days) and road surface environment information (such as dryness, slipperiness, and potholes). This scheme can accurately quantify the impact of these factors on the driver's reaction speed. This helps drivers and vehicles better adapt to different driving environments and improves driving safety. By considering traffic conditions along the driving route (such as traffic congestion, accident-prone areas, and construction zones), this scheme can dynamically adjust the expectation of the driver's reaction speed, thereby more accurately predicting the driver's behavior under specific traffic conditions. This helps drivers make adjustments in advance and avoid potential safety hazards. By analyzing the driver's personal status information (such as age, gender, driving experience, and physiological state), this scheme can more comprehensively assess the driver's reaction ability and thus more accurately predict their performance in actual driving. This helps to personalize the settings of driver assistance to better suit the needs of different drivers. By integrating the first, second, and third impact amplitudes, this scheme can derive a predicted reaction speed value. Comparing this predicted value with the actual monitored driver reaction speed can accurately determine whether the driver is fatigued. This helps to remind drivers to rest in a timely manner and prevent traffic accidents caused by fatigue driving.

[0090] In one exemplary embodiment, such as Figure 2 As shown, based on the driving environment information of the vehicle, the primary influence of the driving environment on the driver's reaction speed is determined, including:

[0091] S201, determine the interaction factors between weather environment information and road surface environment information.

[0092] The interaction factor is a quantitative indicator used to describe how these two environmental factors, under specific weather and road conditions, jointly affect a driver's reaction speed or driving behavior. This factor is typically determined through a comprehensive analysis of the impact of weather and road conditions on driving safety.

[0093] Specifically, the interaction factor considers the interaction between weather conditions (such as sunny, rainy, snowy, and foggy days) and road conditions (such as dry, slippery, snowy, and icy conditions), and how this interaction affects key factors such as the driver's visibility, vehicle handling, and braking distance, thereby affecting the driver's reaction speed.

[0094] For example, in rainy weather with slippery roads, the interaction factor may be larger because rainwater affects the driver's visibility, and the slippery surface increases the vehicle's braking distance, requiring more time for the driver to react. Conversely, in sunny weather with dry roads, the interaction factor may be smaller because these two environmental factors have less impact on the driver's reaction time.

[0095] Specifically, when calculating the interaction factor:

[0096] First, collect historical weather data (such as temperature, humidity, and precipitation), road condition data (such as road type, humidity, and temperature), and relevant traffic accident data or driver behavior data. Clean and organize the collected data to ensure its accuracy and consistency.

[0097] Secondly, different interaction factor levels are defined based on the combination of weather and road conditions. For example, weather can be categorized as sunny, rainy, snowy, etc., and road conditions can be categorized as dry, slippery, snowy, etc., and then an interaction factor can be assigned to each combination.

[0098] Next, the specific factors influencing driver reaction speed, such as obstructed visibility, reduced vehicle handling, and increased braking distance, are analyzed. Each influencing factor is assigned a weight to reflect its importance in affecting driver reaction speed.

[0099] Finally, models for calculating interaction factors are built using statistical analysis, machine learning, or expert methods. These models should be able to account for combinations of different weather and road conditions, and their combined impact on driver reaction speed.

[0100] S202 determines the first magnitude of the impact of the driving environment on the driver's reaction speed based on weather environment information, interaction factors, and road surface environment information.

[0101] First, a baseline reaction speed needs to be determined, typically the average reaction speed of a driver under ideal driving conditions (e.g., sunny days, dry roads). This value can be obtained through historical data, experimental studies, or expert evaluation. Next, current weather and road condition information needs to be collected. This information can be provided by weather stations, environmental monitoring stations, vehicle sensors, or intelligent transportation systems. Based on the collected weather and road information, the corresponding interaction factor needs to be identified or calculated. This factor reflects the degree to which the driver's reaction speed decreases relative to the baseline under specific weather and road conditions. The interaction factor can be obtained through pre-established models, databases, or expert assessments.

[0102] Then, an interaction factor is used to adjust the baseline reaction speed to calculate the predicted reaction speed under the current driving conditions. The first influence magnitude is the difference between the predicted reaction speed and the baseline reaction speed. Finally, the calculated first influence magnitude is output as the result. This result can be used to assess the impact of the driving environment on the driver's reaction speed and to provide the driver with safe driving advice or warnings.

[0103] In one exemplary embodiment, traffic condition information includes traffic flow information, traffic accident information, road construction information, traffic control information, and driving behavior information of other vehicles on the driving route. Based on the traffic condition information of the driving route corresponding to the vehicle, a second impact of traffic conditions on the driver's reaction speed is determined, such as... Figure 3 As shown, it includes:

[0104] S301 determines the travel time of a driving route based on the complexity of traffic information.

[0105] Specifically, real-time traffic information is collected, including traffic flow, traffic accidents, road construction, traffic control, and the driving behavior of other vehicles on the route. This information is then integrated to form a comprehensive traffic picture for subsequent analysis and calculation.

[0106] Complexity assessments are performed on the collected traffic information. This can be achieved by analyzing factors such as traffic flow density, the severity and frequency of traffic accidents, the scope and duration of road construction, the type and intensity of traffic control measures, and the driving behavior patterns of other vehicles. The purpose of the complexity assessment is to quantify the potential impact of traffic conditions on the travel time of driving routes.

[0107] Based on the complexity assessment results, an appropriate algorithm or model is used to calculate the estimated travel time of the driving route under current traffic conditions. This time should take into account all factors that may affect the travel speed.

[0108] S302 determines the second magnitude of the impact of traffic conditions on driver reaction speed based on the duration of passage.

[0109] First, a baseline reaction speed is determined, which is typically the average driver reaction speed under conditions of no traffic interference or low traffic complexity. Using passage time as input, and combining it with the baseline reaction speed, a second magnitude of the impact of traffic conditions on driver reaction speed is calculated.

[0110] One possible approach is to compare the transit time with a certain threshold. If the transit time exceeds the threshold, the traffic situation is considered complex, and the driver's reaction speed may be affected, and the magnitude of the impact is calculated accordingly.

[0111] Another approach is to use regression models or machine learning algorithms to fit historical data on passage time and driver reaction speed to predict the driver's reaction speed under the current passage time and calculate the difference from the baseline reaction speed as the magnitude of the impact.

[0112] The calculated second impact magnitude is output as the result, used to assess the specific impact of traffic conditions on driver reaction speed.

[0113] In an exemplary embodiment, a predicted reaction rate is determined based on a first influence magnitude, a second influence magnitude, and a third influence magnitude, such as... Figure 4 As shown, it includes:

[0114] S401 determines the driver's basic reaction speed based on the driver's behavioral characteristics.

[0115] This process involves collecting drivers' personal information, such as age, gender, and driving experience. It also includes collecting historical driving data, such as average reaction time, accident records, and driving style. Driver behavioral characteristics are analyzed, including reaction time, decision-making ability, and level of concentration. The driver's physiological and psychological state, such as fatigue and emotional state, is also considered, as these factors can affect baseline reaction time. Based on this analysis, appropriate algorithms or models are used to calculate the driver's baseline reaction time under undisturbed conditions.

[0116] S402, based on the first, second, and third influence amplitudes, adjusts the basic reaction rate to obtain the predicted reaction rate value.

[0117] Specifically, the process involves acquiring the previously calculated first influence magnitude (the impact of weather and road conditions on driver reaction speed), the second influence magnitude (the impact of traffic conditions on driver reaction speed), and a possible third influence magnitude (other unspecified influencing factors, such as vehicle performance, driver health, etc.). Using an appropriate mathematical model or algorithm, the first, second, and third influence magnitudes are applied to the baseline reaction speed to calculate the driver's predicted reaction speed under current conditions. This may involve combining the individual influence magnitudes with the baseline reaction speed in a weighted or multiplicative manner. The adjusted reaction speed is then output as a predicted value to assess the driver's reaction ability under current conditions.

[0118] In one exemplary embodiment, such as Figure 5 As shown, based on the predicted reaction speed value and the obtained driver reaction speed monitoring value, the driver fatigue state is determined, including:

[0119] S501 compares the acquired driver reaction speed monitoring value with the predicted reaction speed value.

[0120] Optionally, the driver's reaction speed monitoring value under current driving conditions is acquired. This value can be measured in real time using sensors, cameras, or other monitoring devices built into the vehicle. Simultaneously, a previously calculated predicted reaction speed value is acquired. This value is predicted based on a comprehensive analysis of driver behavior characteristics, external environmental conditions, and other influencing factors. The monitored reaction speed value is compared with the predicted reaction speed value. The purpose of this comparison is to assess whether the driver's actual reaction speed meets expectations.

[0121] S502, if the reaction speed monitoring value is greater than or equal to the reaction speed prediction value, then the driver's fatigue state is determined to be present.

[0122] If the reaction speed monitoring value is greater than or equal to the predicted reaction speed value, it indicates that the driver's actual reaction speed is slower than expected. This could be due to driver fatigue, lack of concentration, or other factors.

[0123] Therefore, in this situation, it is determined that the driver is fatigued, and appropriate measures may need to be taken, such as reminding the driver to rest or adjusting the driving tasks.

[0124] S503, if the reaction speed monitoring value is less than the reaction speed prediction value, then the driver's fatigue state is determined to be non-fatigue.

[0125] Furthermore, after determining the driver's fatigue state, the method also includes: determining an assisted driving strategy based on the driver's fatigue state, and providing feedback on the assisted driving strategy to the driver.

[0126] When driver fatigue is detected, appropriate driver assistance strategies can be activated immediately, such as increasing alert frequency, adjusting vehicle driving modes (e.g., smoother acceleration and deceleration), and even taking automatic deceleration or stopping measures in extreme cases to ensure the safety of the driver and passengers. Driver assistance suggestions or interventions can be customized based on the driver's level of fatigue and personal preferences. For example, a mildly fatigued driver may only need audible or visual alerts, while a severely fatigued driver may require more direct vehicle control assistance. By providing feedback on driver assistance strategies, the driver's awareness of their fatigue level can be enhanced, prompting them to take necessary rest or adjustment measures. This feedback mechanism helps cultivate driver safety awareness and reduce the risks associated with fatigued driving.

[0127] Appropriate driver assistance strategies can not only improve driving safety but also reduce the driver's workload to some extent, especially during long-distance driving or in complex road conditions. This helps improve driver comfort and satisfaction, thereby optimizing the overall driving experience.

[0128] In an exemplary embodiment, as Figure 6 shown, this embodiment provides a driver state recognition system, including:

[0129] The core factor leading to driving fatigue is long-term driving behavior. When the driver always maintains the same posture, concentrates, and continuously processes various traffic information, fatigue is likely to occur. Driving fatigue is also affected by weather changes, traffic conditions, and the driver's emotional fluctuations. Driving on highways or in traffic congestion scenarios will increase the mental burden, bad weather will increase driving pressure, and emotional problems will also consume the driver's physical and mental resources. At the same time, personal factors such as the driver's physiological state and sleep situation will also affect the degree of fatigue. These factors interact and jointly cause driving fatigue.

[0130] When the intelligent monitoring system for drowsy driving state under the SOA architecture works, the cloud system will perform fusion processing and storage on the multi-source data uploaded by the vehicle end and the intelligent bracelet device end, form an effective data set, and perform training and verification through the AI algorithm large model to obtain personalized fatigue thresholds F1 and F2 (F1 < F2) that conform to the driver's physiological state and habits. Then, the data results are deployed on the vehicle to complete the data closed-loop.

[0131] Considering the influence of the driver's personal factors on driving fatigue, the intelligent bracelet device transmits the monitoring data of the driver's physiological state and sleep situation to the cloud system in real time. The cloud system uses the AI algorithm large model to train the monitoring data to obtain the initial fatigue index F0 of the driver before driving the vehicle.

[0132] After the vehicle starts, the weather scenario module starts to collect the wind speed w1, rainfall w2, snowfall w3, etc. in the surrounding area of the vehicle and transmits them to the cloud system. The variable α represents the influence coefficient of the weather condition on the driver's driving time. The cloud system uses the large model to train to obtain that α satisfies the functional relationship . Tw represents the weighted driving time of the driver affected by the weather condition, , i = 1, 2,..., n, where t is the driving duration of the driver, and the same applies hereinafter. This relationship can be expressed as the weighted driving time of the driver under the influence of n weather conditions after the vehicle starts.

[0133] The traffic module collects the road traffic information on the vehicle driving route, including the road congestion duration r1, highway driving duration r2, etc. and transmits them to the cloud system. The variable β represents the influence coefficient of the traffic condition on the driver's driving time. The cloud system uses the large model to train to obtain that β satisfies the functional relationship . Tr represents the weighted driving time of the driver affected by the traffic condition, , j = 1, 2,..., m. This relationship can be expressed as the weighted driving time of the driver under the influence of m traffic conditions after the vehicle starts.

[0134] The in-vehicle camera collects the driver's image data e1, and the voice sensor collects the driver's voice feature data e2, which are transmitted to the cloud system to judge the driver's emotional state. The variable γ represents the influence coefficient of the emotional state on the driver's driving time. The cloud system obtains through large model training that γ satisfies the functional relationship . Te represents the weighted driving time affected by the driver's emotional state, , k = 1, 2, …, p. This relationship can be expressed as the weighted driving time of the driver under the influence of p emotional states after the vehicle starts.

[0135] The variable F represents the driver's comprehensive fatigue state index. Using the comprehensive weighted coefficient method, . Among them, d is the correlation coefficient between the driving time and the fatigue state index, a is the weighted coefficient of Tw, b is the weighted coefficient of Tr, and c is the weighted coefficient of Te.

[0136] The variable L represents the driver's fatigue level. By comparing the comprehensive fatigue state index F with the personalized fatigue thresholds F1, F2 (F1 < F2), the driver's fatigue level is judged, .

[0137] L = 2 indicates that the driver is in a highly fatigued state. At this time, the driver may make driving mistakes and even may fall asleep briefly unconsciously, greatly increasing the risk of traffic accidents. In this state, the cloud system sends a control instruction to the vehicle end, and the vehicle end system controls the instrument to give a fatigue alarm, automatically activates the refreshing mode to help the driver regain a clear state, and at the same time sends a warning message to surrounding vehicles and infrastructure through the V2X communication module to remind other participants in road traffic to pay more attention, enhancing the prevention ability of fatigue driving traffic accidents and contributing an important part to the vehicle networking security system.

[0138] L = 1 indicates that the driver is in a mildly fatigued state. In this state, the cloud system sends a control instruction to the vehicle end, and the vehicle end system controls the instrument to give a fatigue alarm, and the in-vehicle intelligent AI actively communicates with the driver to provide personalized recommendations to help the driver relieve driving fatigue.

[0139] L = 0 indicates that the driver is in a clear state and has not yet developed driving fatigue, and the intelligent monitoring system continues to work.

[0140] After the intelligent monitoring system for fatigue driving state under the SOA architecture gives a fatigue alarm, it will not give an alarm again within 30 minutes, but the system continues to collect monitoring data. After 30 minutes, the cloud system recalculates the driver's fatigue level and sends an instruction to control the vehicle end system to respond in a graded manner.

[0141] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0142] Based on the same inventive concept, this application also provides a driver fatigue state determination device for implementing the driver fatigue state determination method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more driver fatigue state determination device embodiments provided below can be found in the limitations of the driver fatigue state determination method described above, and will not be repeated here.

[0143] In one exemplary embodiment, a driver fatigue state determination device is provided, comprising:

[0144] The first determining module is used to determine the first impact of the driving environment on the driver's reaction speed based on the driving environment information of the vehicle; wherein, the driving environment information includes at least weather environment information and road surface environment information;

[0145] The second determining module is used to determine the second impact of traffic conditions on the driver's reaction speed based on traffic condition information of the driving route corresponding to the vehicle.

[0146] The third determination module is used to determine the third influence of the driver's status on the driver's reaction speed based on the driver's personnel status information.

[0147] The comprehensive assessment module is used to determine the predicted value of the reaction rate based on the first, second, and third impact magnitudes.

[0148] The fatigue level determination module is used to determine the driver's fatigue state based on the predicted reaction speed value and the acquired driver's reaction speed monitoring value.

[0149] The various modules in the aforementioned driver fatigue state determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0150] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for determining driver fatigue. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0151] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0152] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0153] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0154] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0155] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0156] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0157] The driver's fatigue state is determined based on the predicted reaction speed and the obtained driver's reaction speed monitoring values.

[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0159] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0160] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0161] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0162] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0163] The driver's fatigue state is determined based on the predicted reaction speed and the obtained driver's reaction speed monitoring values.

[0164] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0165] Based on the driving environment information of the vehicle, determine the primary impact of the driving environment on the driver's reaction speed; the driving environment information includes at least weather environment information and road surface environment information;

[0166] Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second magnitude of the impact of traffic conditions on the driver's reaction speed;

[0167] Based on the driver's status information, determine the third influence of the driver's status on the driver's reaction speed;

[0168] The predicted reaction rate is determined based on the first, second, and third magnitudes of influence.

[0169] The driver's fatigue state is determined based on the predicted reaction speed and the obtained driver's reaction speed monitoring values.

[0170] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0171] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0173] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A driver state recognition method, characterized in that, The method includes: Determine the interaction factor between weather environment information and road surface environment information in the driving environment information where the vehicle is located, and determine the first influence magnitude of the driving environment on the driver's reaction speed based on the weather environment information, the interaction factor and the road surface environment information; Based on the traffic condition information of the driving route corresponding to the vehicle, determine the second impact of traffic conditions on the driver's reaction speed; Based on the driver's personnel status information, determine the third influence range of personnel status on the driver's reaction speed; The predicted reaction rate is determined based on the first influence magnitude, the second influence magnitude, and the third influence magnitude. The driver's fatigue state is determined based on the predicted reaction speed value and the obtained driver's reaction speed monitoring value.

2. The method according to claim 1, characterized in that, The traffic condition information includes traffic flow information, traffic accident information, road construction information, traffic control information, and driving behavior information of other vehicles on the driving route; determining the second impact of traffic conditions on the driver's reaction speed based on the traffic condition information of the driving route corresponding to the vehicle includes: The duration of the driving route is determined based on the complexity of the traffic condition information. Based on the passage time, a second impact of traffic conditions on driver reaction speed is determined.

3. The method according to claim 1, characterized in that, Determining the predicted reaction rate value based on the first influence magnitude, the second influence magnitude, and the third influence magnitude includes: Based on the driver's behavioral characteristics, determine the driver's basic reaction speed; The base reaction rate is adjusted based on the first influence magnitude, the second influence magnitude, and the third influence magnitude to obtain the predicted reaction rate value.

4. The method according to claim 1, characterized in that, Determining the driver's fatigue state based on the predicted reaction speed value and the obtained driver's reaction speed monitoring value includes: The obtained driver reaction speed monitoring value is compared with the predicted reaction speed value; If the monitored reaction speed value is greater than or equal to the predicted reaction speed value, then the driver is determined to be fatigued. If the monitored reaction speed value is less than the predicted reaction speed value, then the driver's fatigue state is determined to be non-fatigue.

5. The method according to claim 1, characterized in that, After determining the driver's fatigue state, the method further includes: Based on the driver's fatigue state, an assisted driving strategy is determined and fed back to the driver.

6. The method according to claim 1, characterized in that, The personnel status information includes fatigue level, concentration level, emotional state, and health status.

7. A driver status recognition device, characterized in that, The device includes: The first determining module is used to determine the interaction factor between weather environment information and road surface environment information in the driving environment information where the vehicle is located, and to determine the first influence magnitude of the driving environment on the driver's reaction speed based on the weather environment information, the interaction factor and the road surface environment information. The second determining module is used to determine the second influence range of traffic conditions on the driver's reaction speed based on the traffic condition information of the driving route corresponding to the vehicle. The third determining module is used to determine the third influence magnitude of the driver's status on the driver's reaction speed based on the driver's personnel status information. The comprehensive evaluation module is used to determine the predicted value of the reaction speed based on the first influence magnitude, the second influence magnitude, and the third influence magnitude; The fatigue level determination module is used to determine the driver's fatigue state based on the predicted reaction speed value and the obtained driver's reaction speed monitoring value.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images