Driver pre-post detection system and method

Abstract

The invention provides a driver pre-post detection system and method, and relates to the technical field of driver health detection.The system comprises a balance platform, a physiological sign detection device, a data processor and a display screen, and the balance platform measures the pressure value of a driver within set time, calculates the gravity center change frequency, analyzes stability and obtains balance capacity indexes; the physiological sign detection device collects physiological sign data and analyzes the physiological sign data to obtain physiological health indexes, the display screen displays psychological test questions and collects psychological test answers and human eye characteristics, the data processor analyzes the psychological health indexes and sober-up degree indexes to obtain the psychological health indexes and the sober-up degree indexes, and the indexes are comprehensively analyzed to obtain an on-duty permission result; according to the method, the balance ability, the physiological health, the psychological health and the waking degree are comprehensively considered, the one-sidedness of a single index is avoided, the system automatically completes data acquisition, analysis and result output, the detection efficiency is improved, and man-made interference is reduced.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of driver health detection, and in particular to a driver pre-job detection system and method. Background Art

[0002] In the field of pre-job driver testing, existing technologies primarily focus on monitoring a few physiological signs, such as heart rate and blood pressure, to assess a driver's health. These methods suffer from limitations such as a single sensor type, insufficient multimodal data fusion capabilities, neglect of psychological and behavioral factors, lack of personalized assessment, low automation, and inadequate application of deep learning technology. These issues hinder comprehensive and accurate assessment of a driver's pre-job status, thus impacting driving safety. Therefore, a new, multi-dimensional, and comprehensive pre-job driver testing system is urgently needed to overcome the shortcomings of existing technologies and improve detection accuracy and reliability. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a driver pre-job detection system and method in view of the deficiencies in the existing technology.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: a driver pre-job detection system, comprising a balancing platform, a physiological sign detection device, a data processor and a display screen;

[0005] The balancing station is used to measure the pressure value generated by the driver within a set time;

[0006] The physiological sign detection device is used to collect the driver's physiological sign data;

[0007] The display screen is used to display psychological test questions to the driver, obtain psychological test answers input by the driver, and collect the driver's eye characteristics during the test;

[0008] The data processor is configured to obtain a center of gravity change frequency based on the pressure value, and perform stability analysis based on the center of gravity change frequency to obtain a balance capability index;

[0009] Performing physiological health analysis on the physiological sign data to obtain physiological health indicators;

[0010] Performing a psychological health analysis on the answers to the psychological test to obtain a psychological health index;

[0011] Performing a wakefulness analysis on the human eye features to obtain a wakefulness index;

[0012] A comprehensive analysis is conducted based on the balance ability index, the physiological health index, the mental health index and the sobriety index to obtain a work permit result.

[0013] Another technical solution of the present invention to solve the above technical problems is as follows: a driver pre-job detection method, comprising the following steps:

[0014] Measure the pressure generated by the driver within a set time;

[0015] Collecting the driver's physiological data;

[0016] Presenting psychological test questions to the driver, obtaining the driver's input of psychological test answers, and collecting the driver's eye features during the test;

[0017] The center of gravity change frequency is obtained by the pressure value, and stability analysis is performed based on the center of gravity change frequency to obtain a balance ability index;

[0018] Performing physiological health analysis on the physiological sign data to obtain physiological health indicators;

[0019] Performing a psychological health analysis on the answers to the psychological test to obtain a psychological health index;

[0020] Performing a wakefulness analysis based on the human eye characteristics to obtain a wakefulness index;

[0021] A comprehensive analysis is conducted based on the balance ability index, the physiological health index, the mental health index and the sobriety index to obtain a work permit result.

[0022] The beneficial effects of the present invention are: it comprehensively considers multiple dimensions such as the driver's balance ability, physical health, mental health and sobriety, and can comprehensively evaluate the driver's pre-job status, avoiding the one-sidedness brought about by single-indicator evaluation; it collects multiple data through equipment such as balance platforms, physiological signs detection devices, display screens, and analyzes them with the help of data processors, thereby improving the accuracy of the evaluation results; based on the analysis of the driver's individual data, it can give personalized job permit results according to the physical condition and mental state of different drivers, thereby better ensuring driving safety; it has a high degree of automation, and the driver only needs to complete various tests according to the prompts, and the system automatically collects data, analyzes and processes the data and obtains the results, thereby improving detection efficiency and reducing interference from human factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram showing the connections of the components of the driver pre-job detection system provided by an embodiment of the present invention;

[0024] Figure 2 A flowchart of a driver pre-job detection method provided by an embodiment of the present invention.

[0025] In the accompanying drawings, the names of the components represented by the various symbols are as follows:

[0026] 1. Display screen, 2. Physiological sign detection device, 3. Data processor, 4. Balance platform. DETAILED DESCRIPTION

[0027] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0028] Example 1: Figure 1 As shown, an embodiment of the present invention provides a driver pre-job detection system, including a display screen 1, a physiological sign detection device 2, a data processor 3 and a balancing platform 4;

[0029] The balancing station 4 is used to measure the pressure value generated by the driver within a set time;

[0030] The physiological sign detection device 2 is used to collect the driver's physiological sign data;

[0031] The display screen 1 is used to display psychological test questions to the driver, obtain the psychological test answers input by the driver, and collect the driver's eye characteristics during the test;

[0032] The data processor 3 is configured to obtain a center of gravity change frequency based on the pressure value, and perform stability analysis based on the center of gravity change frequency to obtain a balance capability index;

[0033] Performing physiological health analysis on the physiological sign data to obtain physiological health indicators;

[0034] Performing a psychological health analysis on the answers to the psychological test to obtain a psychological health index;

[0035] Performing a wakefulness analysis on the human eye features to obtain a wakefulness index;

[0036] A comprehensive analysis is conducted based on the balance ability index, the physiological health index, the mental health index and the sobriety index to obtain a work permit result.

[0037] In this embodiment, multiple dimensions such as the driver's balance ability, physical health, mental health, and sobriety are comprehensively considered, which can comprehensively assess the driver's pre-job status and avoid the one-sidedness caused by a single indicator evaluation;

[0038] By collecting various data through the balance platform 4, physiological sign detection device 2, display screen 1 and other equipment, and analyzing them with the help of data processor, the accuracy of the evaluation results is improved;

[0039] Based on the analysis of individual driver data, personalized driving permit results can be given according to the physical and psychological conditions of different drivers to better ensure driving safety;

[0040] The system has a high degree of automation. The driver only needs to follow the prompts to complete each test. The system automatically collects data, analyzes and processes it, and draws the results, which improves the detection efficiency and reduces the interference of human factors.

[0041] Preferably, the display screen is also used to capture the driver's facial image;

[0042] The data processor is used to identify the facial image and obtain identity verification information.

[0043] Preferably, in the balancing station, the pressure value generated by the driver within a set time is measured, specifically:

[0044] A pressure sensor is installed inside the balancing platform. When a driver stands on the balancing platform, the pressure sensor measures the pressure value at the driver's position within a set time.

[0045] In this embodiment, the pressure sensor installed inside the balancing platform can accurately measure the pressure value generated by the driver within a set time, providing an accurate data basis for subsequent center of gravity change frequency calculation and balance ability assessment;

[0046] The center of gravity position is updated every time a pressure value is collected within the set time. This can track the changes in the driver's center of gravity in real time and promptly detect abnormal fluctuations in the driver's balance ability.

[0047] Preferably, in the data processor, the center of gravity change frequency is obtained by the pressure value, and stability analysis is performed according to the center of gravity change frequency to obtain a balance ability index, specifically:

[0048] Within the set time, each time the pressure value is collected, the center of gravity position is updated, and the center of gravity position sequence is obtained according to the center of gravity position, wherein the center of gravity position of the driver (x 重心 ,y 重心 ), center of gravity position (x 重心 ,y 重心 ) is expressed as:

[0049]

[0050] Among them, x i and y i is the coordinate position of the pressure sensor, F i is the pressure value measured by the pressure sensor;

[0051] The center of gravity change frequency is obtained according to the center of gravity position change at adjacent moments in the center of gravity position sequence, and the balance ability index B is calculated according to the center of gravity change frequency and the normal center of gravity frequency value. The balance ability index B is expressed as:

[0052]

[0053] Among them, f is the frequency of center of gravity change, f o The normal center of gravity frequency value is the average value of the center of gravity change frequency obtained based on the statistics of normal population data.

[0054] In this embodiment, the center of gravity change frequency is obtained by calculating the center of gravity position changes at adjacent moments in the center of gravity position sequence, and the balance ability index is calculated in combination with the normal center of gravity frequency value. This quantitatively evaluates the driver's balance ability and facilitates comprehensive analysis with other indicators.

[0055] A scientific method is used to analyze the frequency of center of gravity changes, and the balance ability is evaluated based on the difference between the center of gravity change frequency and the normal frequency range, making the evaluation results more scientific and convincing.

[0056] Preferably, the data processor performs physiological health analysis on the physiological sign data to obtain physiological health indicators, specifically:

[0057] Obtaining heart rate, blood pressure, and body temperature from the physiological sign data, and scoring the normality and abnormality of the heart rate, blood pressure, and body temperature based on a status scoring standard to obtain a heart rate health index, a blood pressure health index, and a body temperature health index;

[0058] The heart rate health index, the blood pressure health index, and the body temperature health index are weightedly calculated to obtain a physiological health index P, which is expressed as:

[0059] P=w p1 ×p1+w p2 ×p2+w p3 ×p3,

[0060] Among them, w p1 , w p2 , w p3 , w p4 , w p5 is the weight of each health indicator, the sum of the weights is 1, p1 is the heart rate health indicator, p2 is the blood pressure health indicator, and p3 is the body temperature health indicator.

[0061] In this embodiment, a heart rate health index, a blood pressure health index, and a body temperature health index are obtained from multiple physiological sign data such as heart rate, blood pressure, and body temperature, and then a weighted calculation is performed to obtain a physiological health index. This can comprehensively reflect the driver's physiological health status and avoid the influence of a single physiological sign abnormality on the assessment result.

[0062] Based on the status scoring standards, the normal and abnormal heart rate, blood pressure and body temperature are scored, making the health indicators of different physiological signs comparable and facilitating weighted calculation and comprehensive evaluation.

[0063] Preferably, the data processor performs a psychological health analysis on the psychological test answers to obtain a psychological health index, specifically:

[0064] Obtaining fatigue level test answers, emotional state test answers, concentration test answers, anxiety level test answers, and reaction speed from the psychological test answers, and converting the fatigue level test answers, emotional state test answers, concentration test answers, anxiety level test answers, and reaction speed into corresponding scores based on the psychological test scoring criteria;

[0065] The fatigue level test score, emotional state test score, concentration test score, anxiety level test score and reaction speed score are weighted to obtain the mental health index M, which is expressed as:

[0066] P=w m1 ×m1+w m2 ×m2+w m3 ×m3+w m4 ×m4+w m5 ×m5,

[0067] Among them, w m1 , w m2 , w m3 , w m4 , w m5 is the weight of each score, the sum of the weights is 1, m1 is the fatigue level test score, m2 is the emotional state test score, m3 is the attention concentration test score, m4 is the anxiety level test score, and m5 is the reaction speed score.

[0068] In this embodiment, the driver is evaluated from multiple psychological dimensions such as fatigue level, emotional state, concentration, anxiety level and reaction speed, which can fully understand the driver's psychological state and provide a more sufficient basis for judging whether he is suitable for the job;

[0069] The answers to psychological tests are converted into corresponding scores and weighted calculations are performed to obtain mental health indicators, which enables quantitative assessment of mental health and facilitates comprehensive analysis with other indicators.

[0070] Preferably, the data processor performs a wakefulness analysis on the human eye features to obtain a wakefulness index, specifically:

[0071] Obtaining the degree of eye opening, blinking frequency, and eye movement speed from the human eye characteristics, wherein the degree of eye opening is calculated by the ratio of the vertical height of the eye to the width of the eye, the blinking frequency is obtained by calculating the number of blinks within a set time, and the eye movement speed is obtained by calculating the change in the position of the eye at two consecutive time points;

[0072] The eye opening and closing degree, blinking frequency and eye movement speed are weightedly calculated to obtain the awakeness index S, which is expressed as:

[0073] S=w s1 ×s1+w s2 ×s2+w s3 ×s3,

[0074] Among them, w s1 , w s2 , w s3 is the weight of each feature, the sum of the weights is 1, s1 is the degree of eye opening, s2 is the blinking frequency, and s3 is the eye movement speed.

[0075] In this embodiment, multiple eye features related to wakefulness, such as eye opening degree, blinking frequency, and eye movement speed, are comprehensively considered to enable a more comprehensive assessment of the driver's wakefulness, avoiding the inaccuracy caused by a single feature assessment.

[0076] The degree of eye opening and closing, blinking frequency and eye movement speed are weightedly calculated to obtain the wakefulness index, which realizes the quantitative assessment of the wakefulness level and facilitates comprehensive analysis with other indicators.

[0077] Preferably, the data processor performs a comprehensive analysis based on the balance ability index, the physiological health index, the mental health index, and the sobriety index to obtain a work permit result, specifically:

[0078] The balance ability index, the physiological health index, the mental health index, and the sobriety index are standardized based on a Z-score standardization formula to obtain a driver standardized feature vector. The Z-score standardization formula is:

[0079]

[0080] Among them, x i is the original value of one of the indicators, μ i is the average value of one of the indicators, σ i is the standard deviation of one of the indicators;

[0081] A pre-job comprehensive analysis model is constructed based on a deep learning model. The pre-job comprehensive analysis model includes an input layer, an embedding layer, a feature splicing layer, a hidden layer, and an output layer.

[0082] The input layer is used to input the driver ID and the driver's standardized feature vector;

[0083] The embedding layer is used to map the driver ID into an embedding vector e, which is a low-dimensional dense vector. The embedding vector e is expressed as:

[0084] e=embedding(ID),

[0085] The feature concatenation layer is used to concatenate the embedding vector with the driver's normalized feature vector to obtain a concatenated vector h0, which is expressed as:

[0086] h0=Concat(e,x norm ),

[0087] The hidden layer includes a first fully connected layer containing 128 neurons and a second fully connected layer containing 64 neurons. The first fully connected layer and the second fully connected layer sequentially perform nonlinear transformation on the concatenated vector h0 through the ReLU nonlinear activation function, which is expressed as:

[0088] h1=ReLu(W1h0+b1),

[0089] h2=ReLu(W2h1+b2),

[0090] Where h1 is the output feature of the first fully connected layer, h2 is the output feature of the second fully connected layer, W1 and W2 are weights, and b1 and b2 are biases;

[0091] The output layer is used to map the output feature h2 to the interval (0, 1) through the Sigmoid activation function and output the probability value;

[0092] If the probability value is greater than or equal to 0.5, it is a positive class, that is, the result of the job permit is suitable for the job.

[0093] If the probability value is less than 0.5, it is a negative class, that is, the job permission result is not suitable for the job.

[0094] Before building the pre-job comprehensive analysis model, the steps for training the pre-job comprehensive analysis model are also included, including:

[0095] The binary cross-entropy loss function is used to improve the generalization ability of the model. Binary cross-entropy loss is a common loss function for binary classification problems. It measures the difference between the probability value predicted by the model and the true label. For a sample, its loss function is defined as:

[0096] Loss=-[y true ·log(y pred )+(1-y true )·log(1-y pred )],

[0097] Among them, y pred is the true label (0 or 1), y pred The probability value predicted by the model (between 0 and 1). During training, the goal of the model is to minimize the average loss value over the entire training set.

[0098] L2 regularization is used to avoid model overfitting. L2 regularization (also known as weight decay) constrains the model weights by adding a regularization term to the loss function to prevent the weights from becoming too large, thereby reducing the complexity of the model and avoiding overfitting.

[0099] In this embodiment, a comprehensive analysis based on the balance ability index, physiological health index, mental health index and sobriety index can comprehensively and accurately assess the driver's pre-job status and improve the reliability of the job permit result;

[0100] Using deep learning models to build pre-employment comprehensive analysis models can automatically learn complex patterns and relationships in data, improving the model's generalization ability and prediction accuracy;

[0101] The Z-score standardization process is performed on each indicator to eliminate the dimensional differences and order of magnitude differences between different indicators, so that the model can perform comprehensive analysis more effectively;

[0102] Taking the driver ID as one of the inputs and mapping it into an embedding vector through the embedding layer can achieve personalized evaluation of different drivers and improve the pertinence and accuracy of the evaluation results.

[0103] Example 2: Figure 2 As shown, the embodiment of the present invention also proposes a driver pre-job detection method, comprising the following steps:

[0104] S1. Measure the pressure value generated by the driver within a set time;

[0105] S2. Collecting the driver's physiological data;

[0106] S3. Presenting psychological test questions to the driver, obtaining psychological test answers input by the driver, and collecting the driver's eye features during the test;

[0107] S4. Determine the center of gravity change frequency based on the pressure value, perform a stability analysis based on the center of gravity change frequency to obtain a balance ability index, perform a physiological health analysis on the physiological sign data to obtain a physiological health index, perform a psychological health analysis on the psychological test answers to obtain a psychological health index, and perform a wakefulness analysis based on the human eye characteristics to obtain a wakefulness index;

[0108] S5. Perform a comprehensive analysis based on the balance ability index, the physiological health index, the mental health index, and the sobriety index to obtain a work permit result.

[0109] Preferably, the center of gravity change frequency is obtained by the pressure value, and stability analysis is performed based on the center of gravity change frequency to obtain a balance ability index, specifically:

[0110] Within the set time, each time the pressure value is collected, the center of gravity position is updated, and the center of gravity position sequence is obtained according to the center of gravity position, wherein the center of gravity position of the driver (x 重心 ,y 重心 ), center of gravity position (x 重心 ,y 重心 ) is expressed as:

[0111]

[0112] Among them, x i and y i is the coordinate position of the pressure sensor, F i is the pressure value measured by the pressure sensor;

[0113] The center of gravity change frequency is obtained according to the center of gravity position change at adjacent moments in the center of gravity position sequence, and the balance ability index B is calculated according to the center of gravity change frequency and the normal center of gravity frequency value. The balance ability index B is expressed as:

[0114]

[0115] Among them, f is the frequency of center of gravity change, f o is the normal center of gravity frequency value.

[0116] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another system, or ignoring or not implementing certain features.

[0118] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the embodiments of the present invention.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A driver pre-job detection system, characterized in that: It includes a balance platform, a physiological sign detection device, a data processor and a display screen; The balancing station is used to measure the pressure value generated by the driver within a set time; The physiological sign detection device is used to collect the driver's physiological sign data; The display screen is used to display psychological test questions to the driver, obtain psychological test answers input by the driver, and collect the driver's eye characteristics during the test; The data processor is configured to obtain a center of gravity change frequency based on the pressure value, and perform stability analysis based on the center of gravity change frequency to obtain a balance capability index; Performing physiological health analysis on the physiological sign data to obtain physiological health indicators; Performing a psychological health analysis on the answers to the psychological test to obtain a psychological health index; Performing a wakefulness analysis on the human eye features to obtain a wakefulness index; A comprehensive analysis is conducted based on the balance ability index, the physiological health index, the mental health index and the sobriety index to obtain a work permit result.

2. The driver pre-job detection system according to claim 1, characterized in that: In the balancing station, the pressure value generated by the driver within the set time is measured, specifically: A pressure sensor is installed inside the balancing platform. When a driver stands on the balancing platform, the pressure sensor measures the pressure value at the driver's position within a set time.

3. The driver pre-job detection system according to claim 1, characterized in that: In the data processor, the center of gravity change frequency is obtained by the pressure value, and stability analysis is performed based on the center of gravity change frequency to obtain a balance ability index, specifically: Within the set time, each time the pressure value is collected, the center of gravity position is updated, and the center of gravity position sequence is obtained according to the center of gravity position, wherein the center of gravity position of the driver (x 重心 ,y 重心 ), center of gravity position (x 重心 ,y 重心 ) is expressed as: Among them, x i and y i is the coordinate position of the pressure sensor, F i is the pressure value measured by the pressure sensor; The center of gravity change frequency is obtained according to the center of gravity position change at adjacent moments in the center of gravity position sequence, and the balance ability index B is calculated according to the center of gravity change frequency and the normal center of gravity frequency value. The balance ability index B is expressed as: Among them, f is the frequency of center of gravity change, f o is the normal center of gravity frequency value.

4. The driver pre-job detection system according to claim 1, characterized in that: In the data processor, a physiological health analysis is performed on the physiological sign data to obtain physiological health indicators, specifically: Obtaining heart rate, blood pressure, and body temperature from the physiological sign data, and scoring the normality and abnormality of the heart rate, blood pressure, and body temperature based on a status scoring standard to obtain a heart rate health index, a blood pressure health index, and a body temperature health index; The heart rate health index, the blood pressure health index, and the body temperature health index are weightedly calculated to obtain a physiological health index P, which is expressed as: P=w p1 ×p1+w p2 ×p2+w p3 ×p3, Among them, w p1 , w p2 , w p3 , w p4 , w p5 is the weight of each health indicator, the sum of the weights is 1, p1 is the heart rate health indicator, p2 is the blood pressure health indicator, and p3 is the body temperature health indicator.

5. The driver pre-job detection system according to claim 1, characterized in that: In the data processor, a psychological health analysis is performed on the psychological test answers to obtain a psychological health index, specifically: Obtaining fatigue level test answers, emotional state test answers, concentration test answers, anxiety level test answers, and reaction speed from the psychological test answers, and converting the fatigue level test answers, emotional state test answers, concentration test answers, anxiety level test answers, and reaction speed into corresponding scores based on the psychological test scoring criteria; The fatigue level test score, emotional state test score, concentration test score, anxiety level test score and reaction speed score are weighted to obtain the mental health index M, which is expressed as: P=w m1 ×m1+w m2 ×m2+w m3 ×m3+w m4 ×m4+w m5 ×m5, Among them, w m1 , w m2 , w m3 , w m4 , w m5 is the weight of each score, the sum of the weights is 1, m1 is the fatigue level test score, m2 is the emotional state test score, m3 is the attention concentration test score, m4 is the anxiety level test score, and m5 is the reaction speed score.

6. The driver pre-job detection system according to claim 1, characterized in that: In the data processor, the awakeness analysis is performed on the human eye features to obtain an awakeness index, specifically: Obtaining the degree of eye opening, blinking frequency, and eye movement speed from the human eye characteristics, wherein the degree of eye opening is calculated by the ratio of the vertical height of the eye to the width of the eye, the blinking frequency is obtained by calculating the number of blinks within a set time, and the eye movement speed is obtained by calculating the change in the position of the eye at two consecutive time points; The eye opening and closing degree, blinking frequency and eye movement speed are weightedly calculated to obtain the awakeness index S, which is expressed as: S=w s1 ×s1+w s2 ×s2+w s3 ×s3, Among them, w s1 , w s2 , w s3 is the weight of each feature, the sum of the weights is 1, s1 is the degree of eye opening, s2 is the blinking frequency, and s3 is the eye movement speed.

7. The driver pre-job detection system according to claim 1, characterized in that: The data processor performs a comprehensive analysis based on the balance ability index, the physiological health index, the mental health index, and the sobriety index to obtain a work permit result, specifically: The balance ability index, the physiological health index, the mental health index, and the sobriety index are standardized based on a Z-score standardization formula to obtain a driver standardized feature vector. The Z-score standardization formula is: Among them, x i is the original value of the i-th indicator, μ i is the average value of the i-th indicator, σ i is the standard deviation of the i-th indicator; A pre-job comprehensive analysis model is constructed based on a deep learning model. The pre-job comprehensive analysis model includes an input layer, an embedding layer, a feature splicing layer, a hidden layer, and an output layer. The input layer is used to input the driver ID and the driver's standardized feature vector; The embedding layer is used to map the driver ID into an embedding vector e, which is a low-dimensional dense vector. The embedding vector e is expressed as: e=embedding(ID), The feature concatenation layer is used to concatenate the embedding vector with the driver's normalized feature vector to obtain a concatenated vector h0, which is expressed as: h0=Concat(e,x norm ), The hidden layer includes a first fully connected layer containing 128 neurons and a second fully connected layer containing 64 neurons. The first fully connected layer and the second fully connected layer sequentially perform nonlinear transformation on the concatenated vector h0 through the ReLU nonlinear activation function, which is expressed as: h1=ReLu(W1h0+b1), h2=ReLu(W2h1+b2), Where h1 is the output feature of the first fully connected layer, h2 is the output feature of the second fully connected layer, W1 and W2 are weights, and b1 and b2 are biases; The output layer is used to map the output feature h2 to the interval (0, 1) through the Sigmoid activation function and output the probability value; If the probability value is greater than or equal to 0.5, it is a positive class, that is, the result of the job permit is suitable for the job. If the probability value is less than 0.5, it is a negative class, that is, the job permission result is not suitable for the job.

8. The driver pre-job detection system according to any one of claims 1 to 7, characterized in that: The display screen is also used to collect the driver's facial image; The data processor is used to identify the facial image and obtain identity verification information.

9. A driver pre-job detection method, characterized in that: The steps include: Measure the pressure generated by the driver within a set time; Collecting the driver's physiological data; Presenting psychological test questions to the driver, obtaining the driver's input of psychological test answers, and collecting the driver's eye features during the test; The center of gravity change frequency is obtained by the pressure value, and stability analysis is performed based on the center of gravity change frequency to obtain a balance ability index; Performing physiological health analysis on the physiological sign data to obtain physiological health indicators; Performing a psychological health analysis on the answers to the psychological test to obtain a psychological health index; Performing a wakefulness analysis based on the human eye characteristics to obtain a wakefulness index; A comprehensive analysis is conducted based on the balance ability index, the physiological health index, the mental health index and the sobriety index to obtain a work permit result.

10. The driver pre-job detection method according to claim 9, characterized in that: The center of gravity change frequency is obtained by the pressure value, and stability analysis is performed based on the center of gravity change frequency to obtain the balance ability index, which is specifically: Within the set time, each time the pressure value is collected, the center of gravity position is updated, and the center of gravity position sequence is obtained according to the center of gravity position, wherein the center of gravity position of the driver (x 重心 ,y 重心 ), center of gravity position (x 重心 ,y 重心 ) is expressed as: Among them, x i and y i is the coordinate position of the pressure sensor, F i is the pressure value measured by the pressure sensor; The center of gravity change frequency is obtained according to the center of gravity position change at adjacent moments in the center of gravity position sequence, and the balance ability index B is recalculated according to the center of gravity change frequency and the normal center of gravity frequency value. The balance ability index B is expressed as: Among them, f is the frequency of center of gravity change, f o is the normal center of gravity frequency value.

Images