Driver sleepiness level evaluation method based on sleep deprivation

Abstract

The invention provides a driver sleepiness level evaluation method based on sleep deprivation. The method comprises the following steps: acquiring driver sleepiness level test data after sleep deprivation; according to the driver drowsiness level test data after sleep deprivation, constructing a subjective evaluation index and an objective evaluation index representing the driver drowsiness level; inputting the subjective evaluation indexes and the objective evaluation indexes into a constructed driver sleepiness level multi-dimensional evaluation model, calculating model weights, and storing the model weights to obtain a driver sleepiness level multi-dimensional final evaluation model; and obtaining an objective evaluation index of the drowsiness level of the to-be-detected driver, inputting the objective evaluation index into the driver drowsiness level multi-dimensional final evaluation model, and calculating to obtain the drowsiness level of the driver. According to the method, multi-dimensional evaluation indexes are adopted, the defect that it is difficult to accurately and comprehensively evaluate the driver drowsiness level through a single evaluation index is effectively overcome, and the accuracy and reliability of the driver drowsiness level evaluation method are further improved.

Description

Technical Field

[0001] The invention relates to the field of automobile safety testing, and in particular to a method for evaluating a driver's sleepiness level based on sleep deprivation. Background Art

[0002] In order to reduce the driving risks caused by driver drowsiness, driver status monitoring systems such as driver drowsiness reminders and warning systems have emerged. However, the performance and reliability of these monitoring systems are directly related to whether they can accurately and timely detect abnormal conditions such as driver drowsiness and play a positive warning role. Among them, driver drowsiness level detection, as an important part of verifying the performance and reliability of driver drowsiness reminders and warning systems, has now become a key research direction in the industry. How to comprehensively, accurately and effectively evaluate the driver's drowsiness level is of great practical significance for improving the technical level and product quality of the entire driver status monitoring system industry and reducing traffic accidents caused by poor driver conditions.

[0003] At present, existing patents, papers and other relevant literature have studied the driver's sleepiness level test, but there are still certain shortcomings. On the one hand, the evaluation index of the driver's sleepiness level is single, and it is difficult to obtain accurate and comprehensive evaluation results. On the other hand, during the test, not only is there a lack of consideration of biorhythmia, but the driver's sleepiness level is difficult to be effectively controlled, and it is difficult to obtain scientific and effective evaluation results. In addition, the driver's sleepiness level test mostly relies on driving simulators, which is difficult to accurately reflect the driver's sleepiness level in a real road environment. In general, there is currently a lack of driver sleepiness level evaluation methods for real vehicle testing that take biorhythmia into account. Summary of the invention

[0004] In order to overcome the defect of the above-mentioned prior art that the driver's sleepiness level evaluation index is single and leads to inaccurate evaluation results, the present invention provides a driver's sleepiness level evaluation method based on sleep deprivation.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] The present invention proposes a method for evaluating driver sleepiness level based on sleep deprivation, comprising:

[0007] S1: Obtain driver sleepiness level test data after sleep deprivation;

[0008] S2: Based on the test data of driver sleepiness level after sleep deprivation, construct subjective evaluation index and objective evaluation index to characterize the driver's sleepiness level;

[0009] S3: Input the subjective evaluation index and the objective evaluation index into the constructed multi-dimensional evaluation model of the driver's sleepiness level, calculate the model weight, and save it to obtain the final multi-dimensional evaluation model of the driver's sleepiness level;

[0010] S4: Obtain an objective evaluation index of the sleepiness level of the driver to be tested, input the multi-dimensional final evaluation model of the driver's sleepiness level, and calculate the driver's sleepiness level.

[0011] Preferably, in said S1, the test data of the driver's sleepiness level after sleep deprivation includes the driver's eye movement index, neuroelectrophysiological index and alertness task test results after sleep deprivation.

[0012] Preferably, the S1 includes:

[0013] Karolinska Sleepiness Scale data were obtained;

[0014] The driver wears a calibrated eye tracker and a trunkless ECG recording device, and uses a portable eye tracker and a trunkless ECG recording device to measure eye movement indicators and neuroelectrophysiological indicators respectively;

[0015] Performing attention and alertness task tests on the driver to obtain alertness task test results, which include reaction time and test accuracy.

[0016] Preferably, the S2 includes:

[0017] The Karolinska Sleepiness Scale data were used as subjective evaluation indicators;

[0018] The vigilance decline index was calculated based on reaction time and test accuracy;

[0019] The eye movement index, neuroelectrophysiological index and vigilance decline index were standardized, and the standard Z score of each index was calculated. The T score of the corresponding index was calculated based on the standard Z score.

[0020] The T scores of the eye movement index, the neurophysiological index and the alertness reduction index constitute objective evaluation indicators of the driver's sleepiness level.

[0021] Preferably, calculating the vigilance reduction index based on the reaction time and the test accuracy rate includes:

[0022]

[0023] Among them, A1 represents the alertness decline index, T r S represents the time when the driver responds correctly to the target stimulus. r Indicates the test accuracy.

[0024] Preferably, the eye movement index, the neuroelectrophysiological index and the vigilance reduction index are standardized respectively, the standard Z score of each index is calculated, and the T score of the corresponding index is calculated according to the standard Z score, including:

[0025] For eye movement index, neuroelectrophysiological index and vigilance reduction index, the Z score of the corresponding index is calculated according to the following formula:

[0026]

[0027] Among them, Z represents the Z score, X represents the original value of each indicator, μ represents the mean value of the group of data, and S represents the standard deviation of the group of data;

[0028] The formula for calculating the T score is:

[0029] T=2Z+5.5

[0030] Preferably, in S3, the method for determining the multi-dimensional evaluation model of the driver's sleepiness level includes:

[0031]

[0032] Among them, P d represents the driver's sleepiness level, A1 represents the T score of the vigilance reduction index, B2 represents the T score of the neuroelectrophysiological index, C3 represents the T score of the eye movement index, α, β, and γ represent the weight of the vigilance reduction index, the weight of the neuroelectrophysiological index, and the weight of the eye movement index, respectively.

[0033] Preferably, the weight values ​​are determined by scoring by multiple experts based on their rich experience and knowledge, and ultimately taking the average score, and each weight satisfies the relationship: α+β+γ=1.

[0034] The present invention proposes a driver sleepiness level assessment system based on sleep deprivation, which is used to implement the above method, including:

[0035] A data acquisition module, used for acquiring driver sleepiness level test data after sleep deprivation;

[0036] An index construction module, used to construct subjective evaluation indexes and objective evaluation indexes representing the driver's sleepiness level based on the test data of the driver's sleepiness level after sleep deprivation;

[0037] A model acquisition module is used to input the subjective evaluation index and the objective evaluation index into the constructed multi-dimensional evaluation model of the driver's sleepiness level, calculate the model weight, and save it to obtain the final multi-dimensional evaluation model of the driver's sleepiness level;

[0038] The result acquisition module is used to obtain the objective evaluation index of the sleepiness level of the driver to be detected, input the multi-dimensional final evaluation model of the driver's sleepiness level, and calculate the driver's sleepiness level.

[0039] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0040] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0041] The present invention proposes a method for evaluating the sleepiness level of a driver based on sleep deprivation, and the method comprises: obtaining test data of the sleepiness level of the driver after sleep deprivation; constructing subjective evaluation indexes and objective evaluation indexes to characterize the sleepiness level of the driver according to the test data of the sleepiness level of the driver after sleep deprivation; inputting the subjective evaluation indexes and objective evaluation indexes into the constructed multi-dimensional evaluation model of the sleepiness level of the driver, calculating the model weights, and saving them to obtain the final multi-dimensional evaluation model of the sleepiness level of the driver; obtaining the objective evaluation index of the sleepiness level of the driver to be tested, inputting the final multi-dimensional evaluation model of the sleepiness level of the driver, and calculating the sleepiness level of the driver. The present invention adopts multi-dimensional evaluation indexes, which effectively makes up for the deficiency that a single evaluation index is difficult to accurately and comprehensively evaluate the sleepiness level of the driver, and further improves the accuracy and reliability of the method for evaluating the sleepiness level of the driver. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of the method for evaluating driver sleepiness level based on sleep deprivation described in Example 1;

[0043] Figure 2 A schematic diagram of the design of the attention and vigilance task test platform described in Example 2;

[0044] Figure 3 This is a schematic diagram of the structure of the method for evaluating driver sleepiness level based on sleep deprivation described in Example 3. DETAILED DESCRIPTION

[0045] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0046] In order to better illustrate the present embodiment, some parts in the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0047] It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0048] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0049] Example 1

[0050] This embodiment proposes a method for evaluating driver sleepiness level based on sleep deprivation, such as Figure 1 As shown, including:

[0051] S1: Obtain driver sleepiness level test data after sleep deprivation;

[0052] S2: Based on the test data of driver sleepiness level after sleep deprivation, construct subjective evaluation index and objective evaluation index to characterize the driver's sleepiness level;

[0053] S3: Input the subjective evaluation index and the objective evaluation index into the constructed multi-dimensional evaluation model of the driver's sleepiness level, calculate the model weight, and save it to obtain the final multi-dimensional evaluation model of the driver's sleepiness level;

[0054] S4: Obtain an objective evaluation index of the sleepiness level of the driver to be tested, input the multi-dimensional final evaluation model of the driver's sleepiness level, and calculate the driver's sleepiness level.

[0055] During the specific implementation process, first, a test of the driver's sleepiness level after sleep deprivation is carried out, and the driver's physiological, psychological and behavioral data are collected simultaneously; then, subjective evaluation indicators and objective evaluation indicators are constructed based on the test data of the driver's sleepiness level after sleep deprivation, and the indicators are input into the constructed multidimensional evaluation model of the driver's sleepiness level, and the model weights are calculated; finally, the objective evaluation indicators of the driver's sleepiness level to be tested are input into the final multidimensional evaluation model of the driver's sleepiness level, and the driver's sleepiness level is calculated.

[0056] Example 2

[0057] This embodiment proposes a method for evaluating a driver's sleepiness level based on sleep deprivation, including:

[0058] (1) Conduct a sleepiness test on drivers after sleep deprivation and simultaneously collect physiological, psychological and behavioral data of the drivers, including:

[0059] S11: The tester is responsible for conducting tests, debugging equipment, recording data, and ensuring driving safety during actual vehicle tests; the driver needs to complete a static sleepiness level test and actual vehicle tests; the tester helps the driver wear a calibrated eye tracker and a trunkless ECG recording device.

[0060] S12: The driver completes the Karolinska Sleepiness Scale to self-assess his / her current sleepiness level, and the tester records the test results.

[0061] S13: The driver takes a visual simulation test of drowsiness, and the tester records the test results and obtains physiological and psychological data at the same time.

[0062] S14: The driver performs attention and alertness task tests, and the tester records the test results and obtains physiological and psychological data.

[0063] S15: The driver undergoes a real vehicle test on a closed and safe road. During the real vehicle test, the tester periodically evaluates the driver's sleepiness level, records the test results, and obtains physiological and psychological data.

[0064] In S11, the eye tracker is a portable eye movement device used to record the driver's eyelid closure duration, blinking frequency and pupil diameter during the test; the device needs to be debugged and calibrated before the test.

[0065] In S11, the trunkless ECG recording device can record the time of occurrence of R waves in the ECG signal during the test; and use professional heart rate variability software to perform time domain analysis and frequency domain analysis on the data.

[0066] In S12, the Karolinska Sleepiness Scale divides the sleepiness level into 9 levels, specifically, level 1 indicates extreme alertness; level 2 indicates very alertness; level 3 indicates alertness; level 4 indicates relatively alertness; level 5 indicates not very alert but not sleepy; level 6 indicates some tendency to sleepiness; level 7 indicates sleepiness, but no effort is needed to stay awake; level 8 indicates sleepiness and requires a certain amount of effort to stay awake; level 9 indicates very sleepy and requires great effort to stay awake. Levels 1 to 6 indicate wakefulness, that is, a non-drowsy state. Levels 7 and above indicate a drowsy state, and levels 8 and 9 indicate severe sleepiness.

[0067] In S13, the visual simulation test for drowsiness requires filling in the visual simulation test scale for drowsiness. The scale contains 18 questions, each of which contains a word describing the drowsy state. Each state is set with a subjective grade of 0-100 points, 0 points is the lowest score in this state, and 100 points is the highest score in this state. A sliding bar is set for each item, with 0 on the left side of the sliding bar and 100 on the right side of the sliding bar. The driver drags the mouse to the appropriate position of the sliding bar according to the current subjective experience, and the test is performed every 2 hours. The result of the visual simulation test for drowsiness is the weighted average of the two dimensions of wakefulness and sleepiness. The larger the mean, the higher the driver's sleepiness level. State 1 to state 9 of the visual simulation test scale for drowsiness represent the awake state, which represents: conversation, concentration, moving the body, keeping eyes open, efficiency, vitality, positivity, vitality, and energy. State 10 to state 18 represent a sleepy state, characterized by: lying down, exhausted, tired, exhausted, exhausted, sleepy, tired, closed eyes, and drowsy.

[0068] In S14, the attention and alertness task test refers to: in the test, the driver responds quickly to the detection stimulus on the screen to detect his sleepiness level. The total duration of the attention and alertness task test is 10 minutes. The specific test method is: during the test, the driver sits in front of a computer screen, and the detection stimulus A is displayed on the screen at intervals of 2-10s. The driver responds to the detection stimulus A that appears on the screen as quickly as possible, that is, presses the button to confirm. At the same time, the system records its reaction time and repeats the test until the time is up. When the driver's response is consistent with the detection stimulus A, it is recorded as a correct response. When the driver's response is inconsistent with the detection stimulus A or the driver does not respond within the longest button reaction time, it is an incorrect response. The longer the single correct reaction time, the higher the sleepiness level. The single correct reaction time refers to: the time from the appearance of the detection stimulus A to the driver's correct response to it, that is, the reaction time, in milliseconds (ms). The schematic diagram of the attention and alertness task test platform design is shown below. Figure 2 As shown, the detection stimulus A is displayed on a blank screen at intervals of 2-10s, waiting for the driver to respond with a key. When the driver responds within 500ms (regardless of whether the response is correct or incorrect) or fails to respond after more than 500ms, the current round of testing ends. After the current round of testing ends, the next round of testing should be started immediately, and a new round of detection stimuli will be displayed at intervals of 2-10s again until the time expires. In S15, the driver periodically informs the tester verbally of his or her sleepiness level, and the tester records the test results.

[0069] When conducting the driver's sleepiness level assessment, a sleep deprivation experiment is conducted on the driver. During the sleep deprivation test, the driver needs to complete 12 static sleepiness level tests and 2 actual vehicle tests, both of which are conducted on closed and safe roads; the driver can carry out daily activities during the non-test period, but cannot rest or sleep. Secondly, using steps S11, S12, S13 and S14, a static sleepiness level test is conducted at intervals, the test duration is 20 to 30 minutes, and the test process is the same. Finally, using step S15, a real vehicle test is conducted once during the day and once in the early morning.

[0070] (2) Based on the test data of driver sleepiness level after sleep deprivation, subjective evaluation index and objective evaluation index characterizing the driver's sleepiness level are constructed, including:

[0071] The driver's sleepiness level can be reflected by indicators such as reaction time, heart rate variability, and eye movement indexes. First of all, considering that a single indicator cannot comprehensively evaluate the driver's sleepiness level, in order to better characterize the driver's sleepiness level, a combination of subjective and objective evaluation indicators is used to conduct a multi-dimensional evaluation of the driver's sleepiness level. Secondly, the above indicators are standardized. Finally, the correlation between each indicator and the measurement results of the Karolinska Sleepiness Scale is calculated, and on this basis, a comprehensive sleepiness level indicator is formed. The specific steps are as follows:

[0072] S21: Propose subjective and objective evaluation indicators of the driver's sleepiness level based on the basic parameters obtained in step 1, including: ending the test.

[0073] a) Indicators of decreased alertness

[0074] The vigilance reduction index is used to characterize the driver's alertness and reflects the driver's ability to respond in a timely manner and the level of sleepiness. The parameters involved in this index are obtained from the attention and vigilance task test scores, namely the driver's reaction time to respond correctly to the target stimulus and the test accuracy. The calculation formula is:

[0075]

[0076] Where, represents the alertness reduction index, represents the time when the driver responds correctly to the target stimulus, and represents the test accuracy.

[0077] b) Neurophysiological indicators

[0078] This indicator characterizes the driver's brain activity state. It uses the indicators of heart rate variability and EEG parameters that are sensitive to sleepiness level to assess the driver's sleepiness level. The larger the value, the higher the driver's sleepiness level. It can be measured using a trunkless ECG recording device.

[0079] c) Eye movement indicators

[0080] This indicator represents the eye movement state of the driver's visual concentration. The fixation point is used to represent the driver's visual concentration and is used to evaluate the driver's sleepiness level. The lower the visual concentration, the higher the driver's sleepiness level. It can be measured using a portable eye movement device.

[0081] S22: Considering that a single indicator cannot comprehensively evaluate the driver's sleepiness level, in order to better characterize the driver's sleepiness level, a combination of subjective and objective evaluation indicators is used to evaluate the driver's sleepiness level in multiple dimensions. The above subjective and objective indicators are standardized. According to the mean and standard deviation of the data distribution of each indicator, the standard Z score is taken. The calculation formula of the Z score is:

[0082]

[0083] In the formula, represents the standard score, represents the original value of each indicator, represents the average value of the group of data, and represents the standard deviation of the group of data

[0084] The T score is a statistical method for calculating the number of relative positions, which can avoid decimal points and negative values ​​in the Z score. The above standard Z score is converted into a T score with a value of 1-10. The calculation formula of the T score is:

[0085] T=2Z+5.5 (3)

[0086] In the formula, Z represents the standard score, T represents the T score, and the T score ranges from 1 to 10.

[0087] S23, calculate the correlation between the above indicators and the measurement results of the Karolinska Sleepiness Scale, and calculate the mean score of the significantly correlated indicators. The mean represents the comprehensive sleepiness level, and the higher the score, the higher the sleepiness level.

[0088] (3) Construct a multi-dimensional evaluation model for driver sleepiness level and determine the weights of each evaluation index of driver sleepiness level. Specifically:

[0089] The calculation formula of the multi-dimensional evaluation model of the driver's sleepiness level is:

[0090]

[0091] Among them, P d represents the driver's sleepiness level, A1 represents the T score of the vigilance reduction index, B2 represents the T score of the neuroelectrophysiological index, C3 represents the T score of the eye movement index, α, β, γ represent the vigilance reduction index weight, neuroelectrophysiological index weight, and eye movement index weight respectively. Each weight satisfies the relationship: α+β+γ=1

[0092] The obtained subjective evaluation index and objective evaluation index of the driver are used as input data, the model weight is calculated according to formula (4), and the model weight is saved to obtain the multi-dimensional final evaluation model of the driver's sleepiness level; the objective evaluation index of the sleepiness level of the driver to be tested is obtained, input into the multi-dimensional final evaluation model of the driver's sleepiness level, and the driver's sleepiness level is calculated.

[0093] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0094] Example 3

[0095] This embodiment proposes a driver sleepiness level assessment system based on sleep deprivation, which is used to implement the method described in embodiment 1 or 2. Figure 3 As shown, including:

[0096] A data acquisition module, used for acquiring driver sleepiness level test data after sleep deprivation;

[0097] An index construction module, used to construct subjective evaluation indexes and objective evaluation indexes representing the driver's sleepiness level based on the test data of the driver's sleepiness level after sleep deprivation;

[0098] A model acquisition module is used to input the subjective evaluation index and the objective evaluation index into the constructed multi-dimensional evaluation model of the driver's sleepiness level, calculate the model weight, and save it to obtain the final multi-dimensional evaluation model of the driver's sleepiness level;

[0099] The result acquisition module is used to obtain the objective evaluation index of the sleepiness level of the driver to be detected, input the multi-dimensional final evaluation model of the driver's sleepiness level, and calculate the driver's sleepiness level.

[0100] The same or similar reference numerals correspond to the same or similar components;

[0101] The terms used in the drawings to describe positional relationships are only used for illustrative purposes and should not be construed as limiting this patent;

[0102] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for evaluating driver sleepiness level based on sleep deprivation, characterized in that: include: S1: Obtain driver sleepiness level test data after sleep deprivation; S2: Based on the test data of driver sleepiness level after sleep deprivation, construct subjective evaluation index and objective evaluation index to characterize the driver's sleepiness level; S3: Input the subjective evaluation index and the objective evaluation index into the constructed multi-dimensional evaluation model of the driver's sleepiness level, calculate the model weight, and save it to obtain the final multi-dimensional evaluation model of the driver's sleepiness level; S4: Obtain an objective evaluation index of the sleepiness level of the driver to be tested, input the multi-dimensional final evaluation model of the driver's sleepiness level, and calculate the driver's sleepiness level.

2. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 1, characterized in that: In S1, the sleepiness level test data of the driver after sleep deprivation includes eye movement indexes, neuroelectrophysiological indexes and alertness task test results of the driver after sleep deprivation.

3. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 2, characterized in that: The S1 includes: Karolinska Sleepiness Scale data were obtained; The driver wears a calibrated eye tracker and a trunkless ECG recording device, and uses a portable eye tracker and a trunkless ECG recording device to measure eye movement indicators and neuroelectrophysiological indicators respectively; Performing attention and alertness task tests on the driver to obtain alertness task test results, which include reaction time and test accuracy.

4. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 3, characterized in that: The S2 includes: The Karolinska Sleepiness Scale data were used as subjective evaluation indicators; The vigilance decline index was calculated based on reaction time and test accuracy; The eye movement index, neuroelectrophysiological index and vigilance decline index were standardized, and the standard Z score of each index was calculated. The T score of the corresponding index was calculated based on the standard Z score. The T scores of the eye movement index, the neurophysiological index and the alertness reduction index constitute objective evaluation indicators of the driver's sleepiness level.

5. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 4, characterized in that: Indicators of vigilance decline calculated based on reaction time and test accuracy include: Among them, A1 represents the alertness decline index, T r S represents the time when the driver responds correctly to the target stimulus. r Indicates the test accuracy.

6. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 4, characterized in that: The eye movement index, neuroelectrophysiological index and vigilance reduction index were standardized respectively, and the standard Z score of each index was calculated. The T score of the corresponding index was calculated based on the standard Z score, including: For eye movement index, neuroelectrophysiological index and vigilance reduction index, the Z score of the corresponding index is calculated according to the following formula: Among them, Z represents the Z score, X represents the original value of each indicator, μ represents the mean value of the group of data, and S represents the standard deviation of the group of data; The formula for calculating the T score is: T=2Z+5.

5.

7. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 4, characterized in that: In S3, the method for determining the multi-dimensional evaluation model of the driver's sleepiness level includes: Among them, P d represents the driver's sleepiness level, A1 represents the T score of the vigilance reduction index, B2 represents the T score of the neuroelectrophysiological index, C3 represents the T score of the eye movement index, α, β, and γ represent the weight of the vigilance reduction index, the weight of the neuroelectrophysiological index, and the weight of the eye movement index, respectively.

8. The method for evaluating driver sleepiness level based on sleep deprivation according to claim 7, characterized in that: The weight values ​​are determined by scoring by multiple experts based on their rich experience and knowledge, and ultimately taking the average score, and each weight satisfies the relationship: α+β+γ=1.

9. A driver sleepiness level assessment system based on sleep deprivation, used to implement the method according to any one of claims 1 to 8, characterized in that: include: A data acquisition module, used for acquiring driver sleepiness level test data after sleep deprivation; An index construction module, used to construct subjective evaluation indexes and objective evaluation indexes representing the driver's sleepiness level based on the test data of the driver's sleepiness level after sleep deprivation; A model acquisition module is used to input the subjective evaluation index and the objective evaluation index into the constructed multi-dimensional evaluation model of the driver's sleepiness level, calculate the model weight, and save it to obtain the final multi-dimensional evaluation model of the driver's sleepiness level; The result acquisition module is used to obtain the objective evaluation index of the sleepiness level of the driver to be detected, input the multi-dimensional final evaluation model of the driver's sleepiness level, and calculate the driver's sleepiness level.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images