Testing method, system, electronic equipment and medium for driver status monitoring products

Abstract

The present invention relates to a test method, system, electronic device and medium for a driver status monitoring product. The test method for the driver status monitoring product comprises: obtaining vehicle driving data, vehicle position data, objective physiological data of the driver and subjective physiological data of the driver, and performing data time synchronization and normalization processing on the above data; inputting the processed data into a multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs; determining the alarm time of the tested product according to the alarm image information and alarm sound information of the tested product; determining the alarm response time according to the time when the dangerous driving behavior occurs and the alarm time of the tested product; obtaining the alarm response time of multiple drivers driving at different fatigue levels to determine the alarm response time set; determining the value of the test evaluation index according to the alarm response time set. The method can conduct objective, comprehensive and integrated testing on driver status monitoring products.

Description

Technical Field

[0001] The present invention relates to the field of vehicle active safety, and in particular to a test method, system, electronic equipment and medium for a driver status monitoring product. Background Art

[0002] Abnormal driver status is one of the important reasons for traffic accidents, and about 30% of traffic accidents are related to abnormal driver status. Due to lack of concentration, drivers cannot take normal actions in time when encountering dangerous emergencies, which leads to accidents.

[0003] The driver monitoring function can monitor the driver's driving status in real time and send a prompt message to remind the driver to drive safely when his attention is distracted, so it can effectively reduce the number of accidents caused by driver errors. A series of national and local standards on driver monitoring functions have been formulated and issued at home and abroad, providing a good policy environment for the development of driver monitoring functions. At the same time, driver monitoring is a necessary function for autonomous vehicles, and the rapid development of smart cockpits has also promoted the growth of demand for driver monitoring functions. According to industry research reports, the domestic driver monitoring market space will reach 8.2 billion yuan, providing a good market environment for the development of driver monitoring functions.

[0004] At present, the driver monitoring function is mainly divided into two technical routes: vehicle driving status monitoring and driver physiological status monitoring. Vehicle driving status monitoring mainly monitors and analyzes data such as vehicle speed changes, acceleration changes, lateral distance from the lane line, and driving time to determine whether the driver's status is normal. Driver physiological status monitoring mainly monitors and analyzes the driver's heart rate, eyeballs, brain waves, and posture to determine whether the driving status is normal.

[0005] Since the driver status function has a good policy and market development environment, good development prospects and market demand, and this function has multiple technical routes, it is currently difficult to inspect product quality. Therefore, a set of scientific and reasonable testing methods is urgently needed to evaluate the products produced by enterprises. For products with different technical routes and different architectures, it can not only determine whether the products meet the standard requirements and can be used safely, but also determine the degree of excellence of different products in achieving their functions.

[0006] At present, there are few studies on driver monitoring function test methods, which are mainly through the combination of camera monitoring and manual judgment. The existing test methods are relatively simple, and the test results are greatly affected by the subjective influence of the test personnel; on the other hand, the existing methods mainly focus on testing products of the driver physiological monitoring technology route, and are not suitable for products of the vehicle driving status monitoring technology route, and the scope of application is relatively limited; finally, the current test methods are mainly for the passability test of independent projects, such as closing eyes, yawning and other projects, and there is little research on the overall performance evaluation of the driver monitoring function.

[0007] In view of this, the present invention is proposed. Summary of the invention

[0008] The purpose of the present invention is to provide a test method, system, electronic equipment and medium for a driver status monitoring product, so as to realize an objective, comprehensive and integrated test of the driver status monitoring product.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions:

[0010] In a first aspect, the present invention provides a method for testing a driver status monitoring product, comprising:

[0011] Acquire vehicle driving data, vehicle location data, driver objective physiological data and driver subjective physiological data, and perform data time synchronization and normalization processing on the above data;

[0012] Inputting the processed vehicle driving data, vehicle position data, driver objective physiological data and driver subjective physiological data into a multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs;

[0013] Determine the alarm time of the product under test according to the alarm image information and alarm sound information of the product under test;

[0014] Determine the alarm response time according to the time when the dangerous driving behavior occurs and the time when the tested product alarms;

[0015] Obtaining the alarm response time when multiple drivers are driving at different fatigue levels, and determining an alarm response time set;

[0016] According to the alarm response time set, the value of the test evaluation index is determined.

[0017] In a second aspect, the present invention provides a test system for a driver status monitoring product, comprising:

[0018] Vehicle information collection subsystem, used to obtain vehicle driving data and vehicle location data;

[0019] The driver information collection subsystem is used to obtain the driver's objective physiological data and the driver's subjective physiological data;

[0020] Data synchronization and processing subsystem, used to perform data time synchronization and normalization processing on the above data;

[0021] Acoustic information collection subsystem, used to collect alarm sound information;

[0022] Image information acquisition subsystem, used to collect alarm image information;

[0023] The test evaluation subsystem is used to input the processed vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data into a multi-dimensional dangerous driving model to determine the time when dangerous driving behavior occurs; determine the alarm time of the tested product based on the alarm image information and alarm sound information of the tested product; determine the alarm response time based on the time when the dangerous driving behavior occurs and the alarm time of the tested product; obtain the alarm response time of multiple drivers driving at different fatigue levels to determine an alarm response time set; determine the value of the test evaluation index based on the alarm response time set.

[0024] In a third aspect, the present invention provides an electronic device, comprising:

[0025] at least one processor, and a memory communicatively coupled to at least one of the processors;

[0026] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can perform the above method.

[0027] In a fourth aspect, the present invention provides a medium having computer instructions stored thereon, wherein the computer instructions are used to enable the computer to execute the above method.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The data sources of the test method for the driver status monitoring product provided by the present invention are four dimensions: vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data, and the test method is evaluated through a multi-dimensional dangerous driving model, which greatly improves the objectivity of the test method and can effectively improve the shortcoming of the current test method that it is highly subjective.

[0030] This test method can be applied to driver status monitoring products of two technical routes: vehicle driving status monitoring and driver physiological status monitoring. It can effectively make up for the shortcomings of the current main test methods that can only test products of the driver physiological status monitoring technical route and have a narrow scope of application.

[0031] This test method combines the current status of domestic and international standard research to achieve continuous and overall performance evaluation of driver monitoring products, effectively improving the shortcomings of current test methods that can only be evaluated on a project-by-project basis. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 is a flow chart of a test method for a driver status monitoring product provided in Example 1;

[0034] Figure 2 is a schematic diagram of the structure of the test system of the driver status monitoring product provided in Example 2;

[0035] Figure 3 is a schematic diagram of the structure of the vehicle information collection subsystem in Example 2;

[0036] Figure 4 is a schematic diagram of the structure of the driver information collection subsystem in Example 2;

[0037] Figure 5 is a schematic diagram of the structure of the acoustic information acquisition subsystem in Example 2;

[0038] Figure 6 is a schematic diagram of the structure of the image information acquisition subsystem in Example 2;

[0039] Figure 7 is a schematic diagram of the structure of the data synchronization and processing subsystem in Example 2;

[0040] Figure 8 is a schematic diagram of the structure of the test evaluation subsystem in Example 2;

[0041] Fig. 9 It is a schematic diagram of the structure of the electronic device provided in Example 3. DETAILED DESCRIPTION

[0042] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0043] Example 1

[0044] Figure 1 This is a flow chart of a test method for a driver status monitoring product provided by this embodiment, and this embodiment is applicable to testing aspects such as the monitoring accuracy and timeliness of the driver status monitoring product. The method can be executed by a test system for the driver status monitoring product, which can be composed of software and / or hardware and is generally integrated in an electronic device.

[0045] See also Figure 1 The test method of the above driver status monitoring product includes the following steps:

[0046] S110, obtaining vehicle driving data, vehicle position data, driver objective physiological data and driver subjective physiological data, and performing data time synchronization and normalization processing on the above data.

[0047] Preferably, the vehicle driving data (as shown in Table 1) includes: positive acceleration standard deviation, positive acceleration cumulative ratio, acceleration exceeding 2m / s 2 Duration, acceleration less than -3m / s 2 Duration and acceleration exceeding 3m / s 2 duration, average value of the highest positive acceleration per unit time, standard deviation of negative acceleration, cumulative proportion of negative acceleration, acceleration exceeding 2m / s 2 The number of times the acceleration exceeds 3m / s 2 The number of times, the average maximum speed per unit time, and the acceleration is less than -3m / s 2 The number of times;

[0048] The vehicle position data (as shown in Table 2) includes: the standard deviation of the distance between the right edge of the vehicle and the right lane line, the sum of the number of times the left edge or right edge of the vehicle exceeds the lane edge by 0.3m, and the sum of the duration that the left edge or right edge of the vehicle exceeds the lane edge by 0.3m;

[0049] The objective physiological data of the driver (as shown in Table 3) include: the number of blinks within 1 minute, the number of eye saccades within 1 minute, the frequency of fixation on the target interest area, the fixation time on the target interest area, the relative power ratio of delta brain waves, and the relative power ratio of beta brain waves;

[0050] The driver's subjective physiological data includes: the driver's own fatigue level fed back by the driver after training with the Karolinska Sleepiness Scale.

[0051] According to the existing commonly used test vehicle information collection system, the sampling interval is 0.05s, and the calculation interval is 1 minute (1200 items), and the above vehicle driving data is calculated. After the driver is trained by the Karolinska sleepiness test method, the driver will feedback his fatigue level every 1 minute. KSS , the fatigue classification is shown in Table 4.

[0052] Table 1

[0053]

[0054] Table 2

[0055]

[0056]

[0057] Table 3

[0058]

[0059] Table 4

[0060]

[0061] The data time synchronization and normalization processing methods can be implemented in the art, and this embodiment does not impose any special restrictions on this. For example, GPS time is used for time synchronization, linear normalization is used for normalization, and time synchronization and normalization are achieved through a DEWE-43 data collector.

[0062] S120, inputting the processed vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data into a multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs.

[0063] Preferably, the multi-dimensional dangerous driving model is determined in the following manner:

[0064] A hierarchical analysis method is used to determine the first weight of each indicator in the vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data;

[0065] The entropy weight method is used to determine the second weight of each indicator in the vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data;

[0066] Determine a weight matrix according to the first weight, the second weight and the comprehensive integrated weighting method;

[0067] A multi-dimensional dangerous driving model is determined according to the weight matrix, the processed vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data.

[0068] The multi-dimensional dangerous driving model uses the analytic hierarchy process and the entropy weight method to determine the first weight and the second weight respectively, and then combines the comprehensive integrated weighting method to obtain a weight matrix, which contains the weights corresponding to all data. Finally, the multi-dimensional dangerous driving model is determined based on the weight matrix and the processed data. The comprehensive integrated weighting method refers to a comprehensive method that combines the analytic hierarchy process and the entropy weight method to determine the indicator weights according to different preference coefficients.

[0069] The comprehensive integrated weighting method model and weight calculation method are shown in the following formula:

[0070]

[0071]

[0072] Among them, β1 and β2 are the weight coefficients of the hierarchical analysis method and the entropy weight method, respectively, ω is the weight calculated by the comprehensive integrated weighting method, ω i In , when i is 1, ω1 is the weight calculated by the hierarchical analysis method, and when i is 2, ω2 is the weight calculated by the entropy weight method.

[0073] The above formula can be used to obtain the weight of each indicator, and then the weight matrix can be obtained (see the following formula):

[0074]

[0075] Preferably, the multi-dimensional dangerous driving model is

[0076] Among them, K d is the risky driving coefficient, is the vehicle driving data weight, is the processed vehicle driving data, is the vehicle position data weight, is the processed vehicle position data, is the driver's objective physiological data weight, is the processed objective physiological data of the driver, ω s is the driver's subjective physiological data weight, L s It is the processed driver's subjective physiological data.

[0077] Every time the test system collects data, it can calculate the dangerous driving coefficient corresponding to the current moment. When the calculated dangerous driving coefficient is higher than the preset dangerous driving coefficient threshold, the moment corresponding to the dangerous driving coefficient is the moment when the dangerous driving behavior occurs.

[0078] S130: Determine the alarm time of the tested product according to the alarm image information and alarm sound information of the tested product.

[0079] The alarm image information refers to the vehicle table data image and the driver posture image when the alarm occurs. The alarm sound information refers to the alarm sound data when the alarm occurs, including the alarm sound starting time.

[0080] Optionally, the alarm time of the tested product is determined according to the information of the time when the alarm image and the alarm sound of the tested product appear.

[0081] S140: Determine an alarm response time according to the time when the dangerous driving behavior occurs and the time when the tested product alarms.

[0082] Specifically, the alarm response time = the alarm time of the tested product - the time when the dangerous driving behavior occurs.

[0083] S150, obtaining the alarm response time when multiple drivers drive at different fatigue levels, and determining an alarm response time set. In actual testing, a product should be tested multiple times with multiple drivers at different fatigue levels, so as to maximize the accuracy of the test results and better reflect the monitoring performance of the product.

[0084] S160. Determine the value of the test evaluation index according to the alarm response time set.

[0085] Preferably, the test evaluation index includes: accuracy, true detection rate and average response time. The calculation method of the accuracy, true detection rate and average response time can be implemented in the art, and this embodiment does not impose any special restrictions on this. For example, the true detection rate is the ratio of the number of detected real events to the total number of detected events.

[0086] The data sources of the test method of the above-mentioned driver status monitoring product are four dimensions: vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data. It is evaluated through a multi-dimensional dangerous driving model, which greatly improves the objectivity of the test method and can effectively improve the shortcomings of the current test method that is highly subjective.

[0087] This test method can be applied to driver status monitoring products of two technical routes: vehicle driving status monitoring and driver physiological status monitoring. It can effectively make up for the shortcomings of the current main test methods that can only test products of the driver physiological status monitoring technical route and have a narrow scope of application.

[0088] This test method combines the current status of domestic and international standard research to achieve continuous and overall performance evaluation of driver monitoring products, effectively improving the shortcomings of current test methods that can only be evaluated on a project-by-project basis.

[0089] Furthermore, unlike the above-mentioned continuous and holistic system performance tests, for single behavioral test items such as closing eyes and wearing infrared blocking sunglasses, the test can be carried out according to steps S130-S160, with the time when the dangerous driving behavior occurs as the start time of the item behavior.

[0090] Example 2

[0091] See also Figure 2 , this embodiment provides a test system for a driver status monitoring product, including:

[0092] The vehicle information collection subsystem 101 is used to obtain vehicle travel data and vehicle location data;

[0093] The driver information collection subsystem 102 is used to obtain the driver's objective physiological data and the driver's subjective physiological data;

[0094] The data synchronization and processing subsystem 103 is used to perform data time synchronization and normalization processing on the above data;

[0095] The acoustic information collection subsystem 104 is used to collect alarm sound information;

[0096] The image information acquisition subsystem 105 is used to acquire alarm image information;

[0097] The test evaluation subsystem 106 is used to input the processed vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data into a multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs; determine the alarm time of the tested product based on the alarm image information and alarm sound information of the tested product; determine the alarm response time based on the time when the dangerous driving behavior occurs and the alarm time of the tested product; obtain the alarm response time of multiple drivers driving at different fatigue levels to determine an alarm response time set; determine the value of the test evaluation index based on the alarm response time set.

[0098] Furthermore, if Figure 3 As shown, the vehicle information collection subsystem 101 includes a first vehicle-mounted storage and communication module 1011, and a vehicle speed data collection module 1012, a brake data collection module 1013, a throttle data collection module 1014, a steering data collection module 1015, a lane information collection module 1016, a vehicle position information collection module 1017 and a position data comparison module 1018 respectively connected to the first vehicle-mounted storage and communication module 1011;

[0099] Furthermore, if Figure 4 As shown, the driver information collection subsystem 102 includes a second vehicle-mounted storage and communication module 1021 , and an EEG information collection module 1022 , a pupil information collection module 1023 and a subjective physiological data input module 1024 respectively connected to the second vehicle-mounted storage and communication module 1021 .

[0100] Furthermore, if Figure 5 As shown, the acoustic information collection subsystem 104 includes a sound data collection module 1041 and a third vehicle-mounted storage and communication module 1042 which are connected to each other.

[0101] Furthermore, if Figure 6 As shown, the image information acquisition subsystem 105 includes a fourth vehicle-mounted storage and communication module 1051 , and an instrument data image acquisition module 1052 and a driver posture data acquisition module 1053 respectively connected to the fourth vehicle-mounted storage and communication module 1051 .

[0102] Furthermore, if Figure 7 As shown, the data synchronization and processing subsystem 103 includes a first data receiving module 1031, a data time synchronization module 1032 and a data preprocessing module 1033 which are connected in sequence; the first data receiving module 1031 is also respectively connected to the first vehicle-mounted storage and communication module 1011, the second vehicle-mounted storage and communication module 1021, the third vehicle-mounted storage and communication module 1042, and the fourth vehicle-mounted storage and communication module 1051.

[0103] Furthermore, if Figure 8 As shown, the test evaluation subsystem 106 includes a second data receiving module 1061, a dangerous driving behavior occurrence time extraction module 1062, an alarm time extraction module 1063 and an evaluation index numerical output module 1064. The dangerous driving behavior occurrence time extraction module 1062 and the alarm time extraction module 1063 are both connected to the second data receiving module 1061, and the dangerous driving behavior occurrence time extraction module 1062 and the alarm time extraction module 1063 are also connected to the evaluation index numerical output module 1064; the second data receiving module 1061 is also connected to the data preprocessing module 1033.

[0104] Example 3

[0105] like Fig. 9 As shown, this embodiment provides an electronic device, including:

[0106] at least one processor; and

[0107] a memory communicatively connected to at least one of the processors; wherein,

[0108] The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors to enable at least one of the processors to perform the above method. At least one processor in the electronic device can perform the above method, and thus has at least the same advantages as the above method.

[0109] Optionally, the electronic device also includes an interface for connecting various components, including a high-speed interface and a low-speed interface. Various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on a memory to display the graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to an interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 201 is taken as an example.

[0110] The memory 202 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the test method of the driver status monitoring product in the embodiment of the present invention. The processor 201 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 202, that is, implements the test method of the driver status monitoring product mentioned above.

[0111] The memory 202 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 202 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 202 may further include a memory remotely arranged relative to the processor 201, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0112] The electronic device may further include: an input device 203 and an output device 204. The processor 201, the memory 202, the input device 203 and the output device 204 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0113] The input device 203 can receive input digital or character information, and the output device 204 can include a display device, an auxiliary lighting device (e.g., LED), and a tactile feedback device (e.g., a vibration motor), etc. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0114] Example 4

[0115] This embodiment provides a medium on which computer instructions are stored, and the computer instructions are used to enable the computer to execute the above method. The computer instructions on the medium are used to enable the computer to execute the above method, and thus have at least the same advantages as the above method.

[0116] The medium in the present invention may adopt any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of the medium (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0117] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0118] The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0119] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0120] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0121] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A test method for a driver status monitoring product, characterized in that: include: Acquire vehicle driving data, vehicle location data, driver objective physiological data and driver subjective physiological data, and perform data time synchronization and normalization processing on the above data; The driver's subjective physiological data includes: the driver's own fatigue level feedback after Karolinska sleepiness test training; Inputting the processed vehicle driving data, vehicle position data, driver objective physiological data and driver subjective physiological data into a multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs; Determine the alarm time of the product under test according to the alarm image information and alarm sound information of the product under test; Determine the alarm response time according to the time when the dangerous driving behavior occurs and the time when the tested product alarms; Obtaining the alarm response time when multiple drivers are driving at different fatigue levels, and determining an alarm response time set; Determining the value of the test evaluation index according to the alarm response time set; The multi-dimensional dangerous driving model is determined in the following manner: A hierarchical analysis method is used to determine the first weight of each indicator in the vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data; The entropy weight method is used to determine the second weight of each indicator in the vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data; Determine a weight matrix according to the first weight, the second weight and the comprehensive integrated weighting method; Determining a multi-dimensional dangerous driving model according to the weight matrix, the processed vehicle driving data, the vehicle position data, the driver's objective physiological data, and the driver's subjective physiological data; The model and weight calculation method of the comprehensive integrated weighting method are shown in the following formula: Among them, β1 and β2 are the weight coefficients of the hierarchical analysis method and the entropy weight method, respectively, ω is the weight calculated by the comprehensive integrated weighting method, ω i In , when i is 1, ω1 is the weight calculated by the hierarchical analysis method, and when i is 2, ω2 is the weight calculated by the entropy weight method; The weight matrix is: ； The multi-dimensional dangerous driving model is: ; in, K d is the risky driving coefficient, is the vehicle driving data weight, is the processed vehicle driving data, is the vehicle position data weight, is the processed vehicle position data, is the driver's objective physiological data weight, is the processed objective physiological data of the driver, is the driver's subjective physiological data weight, It is the processed driver's subjective physiological data.

2. The test method of the driver status monitoring product according to claim 1, characterized in that: The vehicle driving data includes: positive acceleration standard deviation, positive acceleration cumulative ratio, acceleration exceeding 2 m / s 2 Duration, acceleration less than -3m / s 2 Duration, acceleration exceeds 3 m / s 2 duration, average value of the highest positive acceleration per unit time, standard deviation of negative acceleration, cumulative proportion of negative acceleration, acceleration exceeding 2 m / s 2 The number of times the acceleration exceeds 3 m / s 2 The number of times, the average maximum speed per unit time, and the acceleration below -3 m / s 2 The number of times; The vehicle position data includes: the standard deviation of the distance between the right edge of the vehicle and the right lane line, the sum of the number of times the left edge or right edge of the vehicle exceeds the lane edge by 0.3 m, and the sum of the duration that the left edge or right edge of the vehicle exceeds the lane edge by 0.3 m; The objective physiological data of the driver include: the number of blinks in 1 minute, the number of eye saccades in 1 minute, the frequency of fixation on the target interest area, the fixation time on the target interest area, the relative power ratio of delta brain waves, and the relative power ratio of beta brain waves.

3. The test method of the driver status monitoring product according to claim 1, characterized in that: The step of inputting the processed vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data into a multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs includes: Inputting the processed vehicle driving data, vehicle position data, driver objective physiological data and driver subjective physiological data into a multi-dimensional dangerous driving model to determine a dangerous driving coefficient; The time when the dangerous driving behavior occurs is determined according to the dangerous driving coefficient and a preset dangerous driving coefficient threshold.

4. The test method for a driver status monitoring product according to any one of claims 1 to 3, characterized in that: The test evaluation indicators include: accuracy, true detection rate and average response time.

5. A test system for a driver status monitoring product, characterized in that: include: Vehicle information collection subsystem, used to obtain vehicle driving data and vehicle location data; The driver information collection subsystem is used to obtain the driver's objective physiological data and the driver's subjective physiological data; The driver's subjective physiological data includes: the driver's own fatigue level feedback after Karolinska sleepiness test training; Data synchronization and processing subsystem, used to perform data time synchronization and normalization processing on the above data; Acoustic information collection subsystem, used to collect alarm sound information; Image information acquisition subsystem, used to collect alarm image information; The test evaluation subsystem is used to input the processed vehicle driving data, vehicle position data, driver's objective physiological data and driver's subjective physiological data into the multi-dimensional dangerous driving model to determine the time when the dangerous driving behavior occurs; determine the alarm time of the tested product according to the alarm image information and alarm sound information of the tested product; determine the alarm response time according to the time when the dangerous driving behavior occurs and the alarm time of the tested product; obtain the alarm response time of multiple drivers driving at different fatigue levels to determine the alarm response time set; determine the value of the test evaluation index according to the alarm response time set; The multi-dimensional dangerous driving model is determined in the following manner: using a hierarchical analysis method to determine the first weight of each indicator in the vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data; The entropy weight method is used to determine the second weight of each indicator in the vehicle driving data, the vehicle position data, the driver's objective physiological data and the driver's subjective physiological data; Determine a weight matrix according to the first weight, the second weight and the comprehensive integrated weighting method; Determining a multi-dimensional dangerous driving model according to the weight matrix, the processed vehicle driving data, the vehicle position data, the driver's objective physiological data, and the driver's subjective physiological data; The model and weight calculation method of the comprehensive integrated weighting method are shown in the following formula: Among them, β1 and β2 are the weight coefficients of the hierarchical analysis method and the entropy weight method, respectively, ω is the weight calculated by the comprehensive integrated weighting method, ω i In , when i is 1, ω1 is the weight calculated by the AHP method, and when i is 2, ω2 is the weight calculated by the entropy weight method; The weight matrix is: ； The multi-dimensional dangerous driving model is: ; in, K d is the risky driving coefficient, is the vehicle driving data weight, is the processed vehicle driving data, is the vehicle position data weight, is the processed vehicle position data, is the driver's objective physiological data weight, is the processed objective physiological data of the driver, is the driver's subjective physiological data weight, It is the processed subjective physiological data of the driver.

6. The test system for the driver status monitoring product according to claim 5, characterized in that: The vehicle information collection subsystem includes a first vehicle-mounted storage and communication module, and a vehicle speed data collection module, a brake data collection module, a throttle data collection module, a steering data collection module, a lane information collection module, a vehicle position information collection module and a position data comparison module respectively connected to the first vehicle-mounted storage and communication module; The driver information collection subsystem includes a second vehicle-mounted storage and communication module, and an EEG information collection module, a pupil information collection module and a subjective physiological data input module respectively connected to the second vehicle-mounted storage and communication module; The acoustic information collection subsystem includes a sound data collection module and a third vehicle-mounted storage and communication module connected to each other; The image information acquisition subsystem includes a fourth vehicle-mounted storage and communication module, and an instrument data image acquisition module and a driver posture data acquisition module respectively connected to the fourth vehicle-mounted storage and communication module; The data synchronization and processing subsystem includes a first data receiving module, a data time synchronization module and a data preprocessing module connected in sequence; the first data receiving module is also connected to the first vehicle-mounted storage and communication module, the second vehicle-mounted storage and communication module, the third vehicle-mounted storage and communication module, and the fourth vehicle-mounted storage and communication module respectively; The test and evaluation subsystem includes a second data receiving module, a dangerous driving behavior occurrence time extraction module, an alarm time extraction module and an evaluation index numerical output module. The dangerous driving behavior occurrence time extraction module and the alarm time extraction module are both connected to the second data receiving module, and the dangerous driving behavior occurrence time extraction module and the alarm time extraction module are also both connected to the evaluation index numerical output module; the second data receiving module is also connected to the data preprocessing module.

7. An electronic device, characterized in that: include: at least one processor, and a memory communicatively coupled to at least one of the processors; The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that the at least one processor can execute the method according to any one of claims 1 to 4.

8. A medium, characterized in that The medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 4.

Images