Helmet wearing tightness testing method and device and computer readable storage medium

Abstract

The invention provides a helmet wearing tightness test method and device, and a computer readable storage medium. The method comprises the following steps: acquiring effective subject data when a subject wears a helmet in different simulation scenes; monitoring pressure distribution of a contact surface between the interior of the helmet and the head of the subject, and generating a pressure distribution diagram; inputting the pressure distribution diagram and the effective subject data into a mode recognition model to obtain a tightness mode; under the condition that the tightness mode is that the helmet is not worn tightly, a self-adaptive adjustment mechanism is used for automatically adjusting helmet wearing parameters; according to the automatically adjusted helmet wearing parameters, obtaining the feeling data of the subject again and verifying the adjustment effect; and under the condition that the adjustment effect is that the adjustment is invalid, data are acquired again, and the helmet is adjusted until the helmet is worn tightly. The problem that in the prior art, the fitting degree of the helmet and the head is difficult to accurately assess due to the fact that the helmet testing result and the actual use condition have deviation is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of helmet tightness testing, and in particular to a helmet wearing tightness testing method, a helmet wearing tightness testing device, a computer-readable storage medium and a computer program product. Background Art

[0002] With the development of science and technology and the improvement of safety awareness, helmets have been widely used as personal protective equipment in many fields. Traditional helmet design mainly relies on static size measurement and simple pressure testing to evaluate the tightness of wearing. However, this test method cannot fully reflect the impact of individual differences, movement status and environmental changes on the tightness of helmet wearing in actual use. In recent years, the progress of sensor technology, EEG signal acquisition technology and deep learning algorithms has provided new possibilities for the precise testing and optimization of helmet wearing tightness.

[0003] Although the existing technology has made certain progress in helmet design and testing, there are still many shortcomings. First, the existing helmet tightness test methods often ignore the diversity of actual usage scenarios, such as climate conditions, sports status, etc., resulting in deviations between the test results and actual usage. Secondly, traditional pressure tests cannot provide comprehensive three-dimensional pressure distribution information, making it difficult to accurately evaluate the fit between the helmet and the head. In addition, the existing technology lacks real-time monitoring of the subject's physiological and psychological state, and cannot perform personalized adaptation of the helmet from a human perspective. Summary of the invention

[0004] The main purpose of the present application is to provide a helmet wearing tightness testing method, a helmet wearing tightness testing device, a computer-readable storage medium and a computer program product, so as to at least solve the problem in the prior art that the deviation between the helmet test results and the actual usage makes it difficult to accurately evaluate the fit between the helmet and the head.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for testing the tightness of helmet wearing is provided, comprising: an acquisition step, acquiring valid subject data when a subject wears a helmet in different simulation scenarios, the valid subject data comprising valid eye tracking data, head micro-movement data and electroencephalogram signals after data processing, the eye tracking data comprising at least the subject's line of sight movement trajectory, gaze point and number of blinks, the head micro-movement data comprising at least the subject's head linear acceleration, velocity and angular velocity data; a generation step, monitoring the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology, and generating a pressure distribution map; a pattern recognition step, inputting the pressure distribution map and the valid subject data into a pattern recognition model to judge the tightness of the helmet wearing, and obtaining the tightness pattern of the helmet wearing of the subject, the tightness pattern being divided into the helmet wearing tight or the head wearing tight. The helmet is not worn tightly; an adjustment step, when the tightness mode is that the helmet is not worn tightly, automatically adjusting the helmet wearing parameters according to the pressure distribution diagram and the valid subject data by using an adaptive adjustment mechanism to make the helmet adapt to the head of the subject; a verification step, according to the automatically adjusted helmet wearing parameters, re-acquiring the subject's feeling data, and verifying the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid adjustment or valid adjustment, the invalid adjustment indicates that the helmet is still not worn tightly, and the valid adjustment indicates that the helmet is worn tightly; when the adjustment effect is that the adjustment is invalid, repeating the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step in sequence at least once until the helmet is worn tightly.

[0006] Optionally, obtaining valid subject data when the subject wears a helmet in different simulation scenarios includes: when the preparation conditions are met, starting the 4D environment simulator and randomly generating different simulation scenarios, the preparation conditions being that the subject cleans his head and wears the helmet as instructed and sits in the simulation environment to prepare for different scenario tests; superimposing a virtual indication of the helmet wearing status in the subject's field of view in real time through AR technology according to the simulation scenario, so that the subject completes the corresponding action according to the virtual indication and obtains original eye tracking data and original head micro-movement data in real time; performing data cleaning operations on the original eye tracking data and the original head micro-movement data to obtain valid eye tracking data and valid head micro-movement data; using a high-resolution EEG signal acquisition system combined with signal processing technology to monitor the subject's original EEG signals in real time; performing preprocessing operations on the original EEG signals to obtain intermediate EEG signals, and extracting characteristic signals in the intermediate EEG signals using Fourier transform to obtain valid EEG signals, the preprocessing operations at least including artifact removal operations.

[0007] Optionally, the original EEG signal is preprocessed to obtain an intermediate EEG signal, and a characteristic signal in the intermediate EEG signal is extracted using Fourier transform to obtain a valid EEG signal, including: performing the artifact removal operation on the original EEG signal according to an artifact removal formula to obtain the intermediate EEG signal, wherein the artifact removal formula is: Among them, Artifact=|e in (t)-μ e |>ασ e , e in (t) is the original EEG signal at time t, μ e is the average value of the original EEG signal, σ e is the standard deviation of the original EEG signal, α is the threshold coefficient, Artifact is a Boolean value, e clean (t) is the intermediate EEG signal after artifact removal, e in (t-1) is the original EEG signal value without artifacts at time t-1, e in (t+1) is the original EEG signal value without artifacts at time t+1; the feature extraction of the intermediate EEG signal is performed according to the Fourier transform formula to obtain the EEG signal, and the Fourier transform formula is: Wherein, F(ω) is the EEG signal obtained by Fourier transform, f(t) is a time domain signal, representing a function of the intermediate EEG signal, t is time, ω is angular frequency, and j is an imaginary unit.

[0008] Optionally, the pressure distribution of the contact surface between the helmet and the subject's head is monitored by 3D pressure mapping technology to generate a pressure distribution map, including: collecting pressure data on the contact surface between the helmet and the head in real time by a 3D pressure mapping sensor, and fixing the 3D pressure mapping sensor inside the helmet; converting the pressure data into the pressure distribution map according to a pressure mapping formula, and the pressure mapping formula is: Where P(x,y) is the pressure value at the coordinate (x,y), (x,y) is the coordinate position on the contact surface inside the helmet, and w i is the weight factor of the ith 3D pressure mapping sensor, p i is the pressure value measured by the i-th 3D pressure mapping sensor, i is a variable index, N is the total number of the 3D pressure mapping sensors, and the expression of the pressure value of each coordinate point in the pressure distribution map is: Among them, p′(x,y) is the interpolated pressure value, (x1,y1) and (x2,y2) are the coordinates of adjacent points with known pressure values, and P(x1,y1), P(x2,y1), P(x1,y2) and P(x2,y2) are the known pressure values ​​at adjacent points.

[0009] Optionally, the pressure distribution map and the valid subject data are input into a pattern recognition model to obtain a tightness pattern of the helmet worn by the subject, including: inputting the pressure distribution map and the valid subject data into the pattern recognition model, using the convolution layer in the pattern recognition model to extract the spatial features of the pressure distribution map and the valid subject data to generate a feature map, performing a dimensionality reduction pooling operation in the pooling layer in the pattern recognition model, converting the feature map into a one-dimensional feature vector in the fully connected layer in the pattern recognition model, and performing feature processing on the one-dimensional feature vector in the output layer in the pattern recognition model to output the tightness pattern, wherein the formula for generating the feature map is: y(n,i,j) is the value of the output nth feature map at position (i,j), n, i, j are variable indexes, W(n,k,l) ​​is the weight of the corresponding nth convolution kernel at position (k,l), x(n,i+k,j+l) is the value of the input data x at position (i+k,j+l), b(n) is the bias coefficient corresponding to the nth convolution kernel, σ is the activation function, x is the input data, representing the pressure distribution map and the valid subject data.

[0010] Optionally, the helmet wearing parameters are automatically adjusted according to the pressure distribution map and the effective subject data using an adaptive adjustment mechanism, including: extracting features from both the pressure distribution map and the effective subject data to obtain corresponding feature data, the feature data corresponding to the pressure distribution map at least including pressure peak value, pressure average value and uniformity of pressure distribution, and the feature data corresponding to the effective subject data at least including gaze point position, gaze duration, blinking frequency, head movement speed, acceleration and movement trajectory; performing feature fusion on all the feature data to obtain a feature vector; and adjusting the helmet wearing parameters according to an adaptive adjustment mechanism formula based on the feature vector, the adaptive adjustment mechanism formula including a pressure adjustment formula and a helmet position adjustment formula, and the pressure adjustment formula is ΔP=K p ·(P desired -P current ), where ΔP is the pressure adjustment amount, K p is the proportional adjustment coefficient, P desired is the desired pressure distribution, P current is the currently monitored pressure distribution, and the helmet position adjustment formula is: θ=θ0+Δθ, where θ is the new position of the helmet, θ0 is the initial position of the helmet, and Δθ is the adjustment amount of the helmet.

[0011] Optionally, verifying the adjustment effect according to the subject's feeling data includes: substituting the feeling data in the subject's feeling data into a first analysis formula to obtain an average value of the feeling data score, wherein the first analysis formula is: in, is the average score of the perception data, S i Score the feeling data of the i-th subject, where i is a variable index and Z is the total number of subjects; substitute the physiological data in the subject's feeling data into a second analysis formula to obtain heart rate variability, where the second analysis formula is: Where HRV is heart rate variability, σ RR is the standard deviation of heart rate, is the average heart rate; the EEG signal data in the subject's perception data is substituted into the third analysis formula to obtain the power of the α wave in the EEG signal. The third analysis formula is: Among them, P α is the power of the α wave, P(f) is the power spectrum density of the EEG signal, and f α,high and f α,low are the upper and lower limits of the frequency range of the α wave respectively; the EEG signal data in the subject's perception data is substituted into the fourth analysis formula to obtain the pressure distribution uniformity index, and the fourth analysis formula is: Wherein, UI is the pressure distribution uniformity index, Pj is the pressure value detected by the jth 3D pressure mapping sensor, j is the variable index, is the average value of the pressure values ​​detected by all the 3D pressure mapping sensors, and V is the total number of the 3D pressure mapping sensors; when the tightness condition is met, the adjustment effect is determined to be the adjustment is valid, and the tightness condition is that the average value of the feeling data score is greater than the first standard value, the heart rate variability is greater than or equal to the second set threshold and less than or equal to the third standard value, the power of the α wave is less than or equal to the fourth standard value, and the pressure distribution uniformity index is less than the fifth standard value; when the tightness condition is not met, the adjustment effect is determined to be the adjustment is invalid.

[0012] According to another aspect of the present application, a helmet wearing tightness testing device is provided, the device comprising: an acquisition unit, for executing an acquisition step, to acquire valid subject data when a subject wears a helmet in different simulation scenarios, the valid subject data comprising valid eye tracking data, head micro-movement data and electroencephalogram signals after data processing, the eye tracking data comprising at least the subject's line of sight movement trajectory, gaze point and number of blinks, the head micro-movement data comprising at least the subject's head linear acceleration, velocity and angular velocity data; a generation unit, for executing a generation step, to monitor the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology, and to generate a pressure distribution map; a pattern recognition unit, for executing a pattern recognition step, to input the pressure distribution map and the valid subject data into a pattern recognition model, to judge the tightness of the helmet wearing, and to obtain the tightness pattern of the helmet wearing of the subject, the tightness pattern being divided into the helmet wearing tight or the head wearing tight. The helmet is not worn tightly; an adjusting unit is used for the adjustment step, when the tightness mode is that the helmet is not worn tightly, automatically adjusting the helmet wearing parameters according to the pressure distribution diagram and the valid subject data by using an adaptive adjustment mechanism to make the helmet adapt to the head of the subject; a verification unit is used to perform the verification step, according to the automatically adjusted helmet wearing parameters, re-acquire the subject's feeling data, and verify the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid adjustment or valid adjustment, the invalid adjustment indicates that the helmet is still not worn tightly, and the valid adjustment indicates that the helmet is worn tightly; a repeating unit is used to, when the adjustment effect is that the adjustment is invalid, sequentially repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once until the helmet is worn tightly.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0014] According to another aspect of the present application, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the methods described above is implemented.

[0015] Applying the technical solution of the present application, in a helmet wearing tightness test method, first, an acquisition step is performed to acquire valid subject data when a subject wears a helmet in different simulation scenarios, the above-mentioned valid subject data includes valid eye tracking data, head micro-movement data and EEG signals after data processing, the above-mentioned eye tracking data at least includes the subject's line of sight movement trajectory, gaze point and number of blinks, and the above-mentioned head micro-movement data at least includes the subject's head linear acceleration, velocity and angular velocity data; then, a generation step is performed to monitor the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology to generate a pressure distribution map; then, a pattern recognition step is performed to input the above-mentioned pressure distribution map and the above-mentioned valid subject data into a pattern recognition model to judge the tightness of the helmet wearing, and obtain the tightness pattern of the helmet wearing of the above-mentioned subject, and the above-mentioned tightness pattern is divided into the helmet wearing tightly or the helmet wearing loosely; After that, an adjustment step, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted according to the pressure distribution map and the effective subject data using an adaptive adjustment mechanism to make the helmet adapt to the head of the subject; after that, a verification step, according to the automatically adjusted helmet wearing parameters, the subject's feeling data is reacquired, and the adjustment effect is verified according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly; finally, when the adjustment effect is invalid, the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step are repeated at least once in sequence until the helmet is worn tightly. This application realizes accurate testing and adaptive adjustment of the tightness of helmet wearing by combining eye tracking, EEG signal acquisition and 3D pressure mapping technology, as well as the developed deep learning pattern recognition algorithm, and recollects the subject's data according to the automatically adjusted helmet wearing parameters, verifies the adjustment effect and analyzes it until the helmet is worn tightly, thereby improving the comfort and protection effect of the helmet. The present application solves the problem in the prior art that the deviation between helmet test results and actual usage makes it difficult to accurately evaluate the fit between the helmet and the head. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for performing a helmet wearing tightness testing method provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic diagram of a process for testing the tightness of a helmet provided in accordance with an embodiment of the present application is shown;

[0018] Figure 3 A structural block diagram of a helmet wearing tightness testing device provided according to an embodiment of the present application is shown.

[0019] The above drawings include the following reference numerals:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background technology, the helmet tightness testing method in the prior art often ignores the diversity of actual usage scenarios, such as climate conditions, motion status, etc., resulting in deviations between the test results and actual usage conditions. In order to solve the problem that the helmet test results in the prior art deviate from the actual usage conditions, making it difficult to accurately evaluate the fit between the helmet and the head, the embodiments of the present application provide a helmet wearing tightness testing method, a helmet wearing tightness testing device, a computer-readable storage medium and a computer program product.

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for executing a helmet wearing tightness test method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the helmet wearing tightness test method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal 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 a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific example of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a method for testing the tightness of helmet wearing is provided, which runs on a mobile terminal, a computer terminal or a similar computing device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 2 FIG. 1 is a flow chart of a method for testing the tightness of helmet wearing according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0030] Step S201, an acquisition step, acquires valid subject data when the subject wears a helmet in different simulation scenarios, the above-mentioned valid subject data includes valid eye tracking data, head micro-movement data and EEG signals after data processing, the above-mentioned eye tracking data at least includes the subject's line of sight movement trajectory, gaze point and number of blinks, and the above-mentioned head micro-movement data at least includes the subject's head linear acceleration, velocity and angular velocity data.

[0031] Specifically, an eye tracking device is used to record the subject's line of sight movement trajectory, fixation point, and number of blinks. The subject's head linear acceleration, velocity, and angular velocity data are collected through sensors. An electroencephalogram (EEG) device is used to record the subject's EEG signals. The collected data is preprocessed to obtain the above-mentioned valid subject data, including filtering, artifact removal, etc., to ensure the validity of the data. Ensure that the collected data accurately reflects the subject's actual state in the simulated scene.

[0032] Step S202, a generating step, monitors the pressure distribution of the contact surface between the inside of the helmet and the head of the subject through 3D pressure mapping technology to generate a pressure distribution map.

[0033] Specifically, 3D pressure mapping technology is used to monitor the pressure distribution of the contact surface between the helmet and the subject's head. A pressure distribution map is generated based on the monitoring results to show the pressure points where the helmet contacts the head. Providing detailed pressure information on the contact between the helmet and the head helps identify problems with the tightness of the helmet.

[0034] Step S203, a pattern recognition step, inputs the pressure distribution diagram and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtains the tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into the helmet wearing tightly or the helmet wearing loosely.

[0035] Specifically, the pressure distribution map and valid subject data are input into the pattern recognition model, which analyzes the data, determines the tightness of the helmet, and outputs the pattern of whether the helmet is worn tightly or loosely. The pattern recognition technology is used to quickly determine the wearing status of the helmet, providing a basis for subsequent adjustments.

[0036] Step S204, an adjustment step, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data to make the helmet adapt to the head of the subject.

[0037] Specifically, when it is identified that the helmet is not worn tightly, the adaptive adjustment mechanism is used to automatically adjust the helmet wearing parameters. According to the adjustment parameters, the position or tightness of the helmet is automatically adjusted to fit the subject's head. The automated adjustment process reduces human intervention and improves the efficiency and accuracy of the adjustment. The helmet is made to better fit the subject's head, improving comfort and functionality.

[0038] Step S205, a verification step, reacquires the subject's perception data according to the automatically adjusted helmet wearing parameters, and verifies the adjustment effect according to the subject's perception data, wherein the subject's perception data includes the subject's perception data, physiological data, EEG signal data and pressure distribution data, and the adjustment effect is invalid or valid. The invalid adjustment indicates that the helmet is still not worn tightly, and the valid adjustment indicates that the helmet is worn tightly.

[0039] Specifically, based on the automatically adjusted helmet wearing parameters, the subject's sensory data, physiological data, EEG signal data, and pressure distribution data are recollected. The recollected data is analyzed to verify the adjustment effect and determine whether the helmet is worn tightly. Ensure that the adjusted helmet wearing state meets the requirements and improve the accuracy and reliability of the simulation test. If the adjustment is ineffective, further adjustments can be made in a timely manner.

[0040] Step S206, when the adjustment effect is that the adjustment is invalid, repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once in sequence until the helmet is worn tightly.

[0041] Specifically, if the verification result shows that the adjustment is invalid, the acquisition step, generation step, pattern recognition step, adjustment step and verification step are repeated until the helmet is worn tightly. The tightness of the helmet is ensured through an iterative process until a satisfactory effect is achieved. The robustness of the system is improved to ensure that the best helmet wearing effect can be achieved under different subjects and different simulation scenarios. The purpose of the entire process is to ensure the tightness of the helmet in the simulation scenario, thereby improving the comfort of the subjects and the accuracy of the test data. Through an automated and intelligent adjustment mechanism, the process can adapt to the head characteristics of different subjects and achieve personalized helmet wearing adjustments.

[0042] In this embodiment, first, an acquisition step is performed to acquire valid subject data when the subject wears the helmet in different simulation scenarios, the valid subject data including valid eye tracking data, head micro-movement data and EEG signals after data processing, the eye tracking data at least including the subject's line of sight movement trajectory, gaze point and number of blinks, the head micro-movement data at least including the subject's head linear acceleration, velocity and angular velocity data; then, a generation step is performed to monitor the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology to generate a pressure distribution map; then, a pattern recognition step is performed to input the pressure distribution map and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing and obtain the tightness mode of the helmet wearing of the subject, the tightness mode is divided into the helmet wearing tightly or the helmet wearing loosely; then, an adjustment step is performed to adjust the pressure distribution map on the upper surface of the helmet. In the case where the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted using the adaptive adjustment mechanism according to the pressure distribution diagram and the effective subject data, so that the helmet adapts to the head of the subject; then, the verification step, according to the automatically adjusted helmet wearing parameters, the subject's feeling data is re-acquired, and the adjustment effect is verified according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the effective adjustment means that the helmet is worn tightly; finally, in the case where the adjustment effect is invalid, the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step are repeated at least once in sequence until the helmet is worn tightly. This application combines eye tracking, EEG signal acquisition and 3D pressure mapping technology, as well as the developed deep learning pattern recognition algorithm, to achieve accurate testing and adaptive adjustment of the tightness of helmet wearing, and re-collects the subject's data according to the automatically adjusted helmet wearing parameters, verifies the adjustment effect and analyzes it until the helmet is worn tightly, thereby improving the comfort and protection effect of the helmet. The present application solves the problem in the prior art that the deviation between helmet test results and actual usage makes it difficult to accurately evaluate the fit between the helmet and the head.

[0043] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the helmet wearing tightness testing method of the present application will be described in detail below in combination with specific embodiments.

[0044] In order to comprehensively evaluate the behavior and physiological response of the subject in the virtual environment, in an optional implementation, the above step S201 includes:

[0045] Step S2011, when the preparation conditions are met, start the 4D environment simulator and randomly generate different simulation scenarios. The preparation conditions are that the subject cleans his head and wears a helmet as instructed and sits in the simulation environment to prepare for different scenario tests.

[0046] Step S2012, superimposing a virtual indication of the helmet wearing status in the field of vision of the subject in real time through AR technology according to the simulated scene, so that the subject can complete the corresponding action according to the virtual indication and obtain the original eye tracking data and the original head micro-movement data in real time;

[0047] Step S2013, performing a data cleaning operation on the original eye tracking data and the original head micro-movement data to obtain valid eye tracking data and valid head micro-movement data;

[0048] Step S2014, using a high-resolution EEG signal acquisition system combined with signal processing technology to monitor the original EEG signals of the above-mentioned subject in real time;

[0049] Step S2015, preprocessing the original EEG signal to obtain an intermediate EEG signal, and using Fourier transform to extract characteristic signals in the intermediate EEG signal to obtain the effective EEG signal. The preprocessing operation at least includes artifact removal.

[0050] In the above embodiment, the subject first needs to clean his head to reduce signal interference and wear a helmet as instructed, which is usually a head-mounted display (HMD) with sensors. The subject sits in a simulated environment and prepares for testing in different scenarios. Start a 4D environment simulator that can generate a virtual environment with multiple sensory stimuli such as vision, hearing, and touch. Randomly generate different simulation scenarios, which may include different environments, tasks, or challenges to test the subject's response. By simulating real or fictional environments, experimental conditions can be controlled and interference from external variables can be reduced. Randomly generated scenarios increase the diversity and unpredictability of the test and help collect more comprehensive data. Using AR technology, virtual instructions are superimposed in the subject's field of view in real time, which may include arrows, cursors, or other visual cues. The subject completes the corresponding actions according to these virtual instructions, such as moving the head, eye tracking, etc. At the same time, the system collects the subject's eye tracking data and head micro-movement data in real time. AR technology provides an intuitive way of interaction, allowing subjects to interact with the virtual environment more naturally. The collected raw eye tracking data and head micro-movement data are cleaned to remove noise and outliers. Invalid data is identified and eliminated through algorithms, and valid data is retained for subsequent analysis. Data cleaning ensures the accuracy and reliability of the data and provides a high-quality data foundation for subsequent analysis. Valid data can more accurately reflect the behavior and response of the subjects. The EEG activity of the subjects is monitored in real time using a high-resolution EEG signal acquisition system. The EEG signal acquisition system may include multiple electrodes distributed on the subject's scalp to capture the electrical activity of different areas of the brain. EEG signal monitoring can provide direct information about the cognitive state and emotional response of the subject. The raw EEG signal is preprocessed, including artifact removal operations, such as removing eye movement artifacts and electromyographic artifacts. The preprocessed signal is Fourier transformed to extract the frequency components, i.e., characteristic signals. These characteristic signals can reflect specific patterns of brain activity, such as alpha waves, beta waves, etc. The preprocessing operation improves the signal-to-noise ratio of the EEG signal, making the signal easier to analyze. By combining multiple technologies and data, the behavior and physiological responses of the subjects in the virtual environment can be comprehensively evaluated, which is of great significance to the development of psychology, cognitive science, neuroscience, and virtual reality technology.

[0051] In order to improve the quality of the EEG signal, in an optional implementation manner, the above step S2015 includes:

[0052] Step S20151, performing the above-mentioned artifact removal operation on the above-mentioned original EEG signal according to the artifact removal formula to obtain the above-mentioned intermediate EEG signal. The above-mentioned artifact removal formula is Among them, Artifact=|e in (t)-μ e |>ασ e , ein (t) is the original EEG signal at time t, μ e is the average value of the original EEG signal, σ e is the standard deviation of the original EEG signal, α is the threshold coefficient, Artifact is a Boolean value, e clean (t) is the above intermediate EEG signal after artifact removal, e in (t-1) is the original EEG signal value without artifacts at time t-1, e in (t+1) is the original EEG signal value without artifacts at time t+1;

[0053] Step S20152, extracting features from the intermediate EEG signal according to the Fourier transform formula to obtain the EEG signal. The Fourier transform formula is: Among them, F(ω) is the above-mentioned EEG signal obtained by Fourier transform, f(t) is a time domain signal, which represents the function of the above-mentioned intermediate EEG signal, t is time, ω is angular frequency, and j is an imaginary unit.

[0054] In the above embodiment, the average value and standard deviation are calculated: the average value μ of the original EEG signal is calculated. e and standard deviation σ e For each time point t, calculate |e in (t)-μ e |, if this absolute value is greater than ασ e , then it is considered that there is an artifact at this point, that is, Artifact=True is satisfied; otherwise, Artifact=False is satisfied. Perform the artifact removal operation according to the above artifact removal formula. Remove artifacts from EEG signals. These artifacts may be caused by eye movements, electromyographic interference, power supply interference, etc., which will interfere with the analysis and interpretation of the signal. By replacing or smoothing the artifact points, the quality of EEG signals is improved, the noise caused by artifacts is reduced, and the signal is clearer, which is helpful for subsequent feature extraction and pattern recognition. Apply the Fourier transform formula to the intermediate EEG signal after artifact removal to obtain the signal obtained by Fourier transform, that is, the amplitude and phase information at different frequencies. Convert the time domain signal to the frequency domain signal to facilitate the analysis of the frequency components of the signal. Extract features from the spectrum, such as power spectral density, frequency band energy, etc. These features are very important for understanding the physiological significance of EEG signals and performing pattern recognition. By extracting key frequency components, the dimension of the data can be reduced, simplifying subsequent data processing and analysis. Improve the quality of EEG signals and extract features that are helpful for analysis and recognition.

[0055] In order to help improve the comfort and safety of the helmet, in an optional implementation, the above step S202 includes:

[0056] Step S2021, collecting pressure data on the contact surface between the helmet and the head in real time through a 3D pressure mapping sensor, and fixing the 3D pressure mapping sensor inside the helmet;

[0057] Step S2022: convert the pressure data into the pressure distribution diagram according to the pressure mapping formula. The pressure mapping formula is: Where P(x,y) is the pressure value at the coordinate (x,y), (x,y) is the coordinate position on the contact surface inside the helmet, and w i is the weight factor of the i-th 3D pressure mapping sensor, p i is the pressure value measured by the i-th 3D pressure mapping sensor, i is the variable index, N is the total number of the 3D pressure mapping sensors, and the expression of the pressure value of each coordinate point in the pressure distribution diagram is: Wherein, p′(x,y) is the interpolated pressure value, (x1,y1) and (x2,y2) are the coordinates of adjacent points with known pressure values, and P(x1,y1), P(x2,y1), P(x1,y2) and P(x2,y2) are the above-mentioned known pressure values ​​at adjacent points.

[0058] In the above embodiment, 3D pressure mapping sensors are evenly distributed on the contact surface inside the helmet. These sensors need to be able to detect small pressure changes. The sensor monitors the pressure on the contact surface inside the helmet in real time and converts it into an electrical signal. The electrical signal is transmitted to the data processing unit through a wire or wirelessly, and the pressure data is processed. Being able to understand the pressure distribution inside the helmet in real time is crucial for adjusting the helmet design to improve wearing comfort. Using a given pressure mapping formula, the pressure data collected from each 3D pressure mapping sensor is converted into coordinate points on the coordinates, and the pressure value of each point on the entire contact surface is calculated using an interpolation formula based on the known pressure value and coordinate position. The interpolation formula uses the known pressure values ​​of four adjacent points to estimate the pressure value of any point. A continuous pressure distribution map is generated based on all the coordinate point positions and the corresponding interpolated pressure values. By analyzing the pressure distribution map, areas with too high or too low pressure can be identified, thereby optimizing the design of the helmet, such as adjusting the thickness or hardness of the lining material. By real-time monitoring and analysis of the pressure distribution inside the helmet, it helps to improve the comfort and safety of the helmet, and also provides important data support for the design and manufacture of the helmet.

[0059] In order to effectively predict the tightness mode of the helmet, in an optional implementation, the above step S203 includes:

[0060] Step S2031, input the pressure distribution map and the valid subject data into the pattern recognition model, use the convolution layer in the pattern recognition model to extract the spatial features of the pressure distribution map and the valid subject data to generate a feature map, perform dimensionality reduction pooling operation in the pooling layer in the pattern recognition model, convert the feature map into a one-dimensional feature vector in the fully connected layer in the pattern recognition model, perform feature processing on the one-dimensional feature vector in the output layer in the pattern recognition model, and output the compactness pattern, wherein the formula for generating the feature map is: y(n,i,j) is the value of the output nth feature map at position (i,j), n, i, j are variable indexes, W(n,k,l) ​​is the weight of the corresponding nth convolution kernel at position (k,l), x(n,i+k,j+l) is the value of the input data x at position (i+k,j+l), b(n) is the bias coefficient corresponding to the nth convolution kernel, σ is the activation function, and x is the input data, which represents the above pressure distribution map and the above valid subject data.

[0061] In the above embodiment, the above training deep learning model includes using convolutional neural network to perform model training, using convolution to extract spatial features of input data, generating feature maps, using activation functions to introduce nonlinearity, reducing data dimensions and performing pooling operations in the pooling layer, and converting the feature maps into one-dimensional feature vectors in the fully connected layer. The formula for generating feature maps is: The loss function formula in the iterative optimization process is: in, is the loss function, Represents the predicted value, y represents the true value, M represents the number of samples, and i is the variable index. The overall process is: first input the pressure distribution map and valid subject data into the pattern recognition model. Then use the convolution layer in the model to extract spatial features. After the convolution operation, an activation function (such as ReLU activation function, Sigmoid activation function or Tanh activation function) is usually applied to introduce nonlinearity and enhance the expressiveness of the model. Pooling layer: After the convolution layer, the pooling layer (such as maximum pooling or average pooling) is used to reduce dimension and extract important features to reduce the amount of calculation. The fully connected layer converts the feature map into a one-dimensional feature vector in preparation for classification or regression tasks. The output layer performs feature processing on the one-dimensional feature vector and outputs a compactness pattern. This enables the model to automatically learn features that distinguish different categories or prediction targets from the input data, and can effectively predict new data.

[0062] In order to improve the comfort and use effect of the helmet, in an optional implementation manner, the above step S204 includes:

[0063] Step S2041, extracting features from the pressure distribution graph and the valid subject data to obtain corresponding feature data, wherein the feature data corresponding to the pressure distribution graph at least includes a pressure peak value, a pressure average value, and uniformity of pressure distribution, and the feature data corresponding to the valid subject data at least includes a gaze point position, a gaze duration, a blinking frequency, a speed of head movement, an acceleration, and a movement trajectory;

[0064] Step S2042, performing feature fusion on all the above feature data to obtain a feature vector;

[0065] Step S2043, based on the above-mentioned feature vector, the above-mentioned helmet wearing parameters are adjusted according to the adaptive adjustment mechanism formula, and the above-mentioned adaptive adjustment mechanism formula includes a pressure adjustment formula and a helmet position adjustment formula. The above-mentioned pressure adjustment formula is ΔP=K p ·(P desired -P current ), where ΔP is the pressure adjustment amount, K p is the proportional adjustment coefficient, P desired is the desired pressure distribution, P current is the currently monitored pressure distribution, and the above helmet position adjustment formula is: θ=θ0+Δθ, where θ is the new position of the helmet, θ0 is the initial position of the helmet, and Δθ is the adjustment amount of the helmet.

[0066] In the above embodiment, by analyzing the pressure distribution diagram, the point with the highest pressure value is found to obtain the pressure peak value. The average of all pressure values ​​in the pressure distribution diagram is calculated to obtain the pressure average value. The uniformity of the pressure distribution is evaluated by statistically analyzing the standard deviation or variance of the pressure values ​​in the pressure distribution diagram. The focus position of the subject's line of sight is obtained by an eye tracking device to obtain the gaze point position. The gaze duration is obtained by recording the length of time the subject keeps gazing at a specific gaze point. The blink frequency is obtained by recording the number of times and time intervals of the subject's blinks by an eye tracking device. The speed of the head movement is measured by a head movement tracking device to obtain the speed of the head movement. The acceleration of the head movement is measured by an accelerometer to obtain the acceleration. The path of the head movement is recorded by the tracking device to obtain the motion trajectory, and the key information that can represent the helmet wearing comfort and the subject's physiological state is extracted from the raw data to provide a basis for subsequent helmet adjustment. All extracted feature data are integrated to form a feature vector. Feature fusion is to merge multiple feature data into a unified data structure for subsequent algorithm processing. This helps to reduce data dimensions, improve algorithm efficiency, and may improve the generalization ability of the model. The above adjustment amount can be a step size set according to the feature vector, or it can be obtained by fine calculation through other algorithms. By adjusting the pressure distribution inside the helmet, the pressure distribution is closer to the expected pressure distribution, thereby improving the comfort and stability of the helmet. By adjusting the position of the helmet, the helmet can fit the user's head more closely, reduce discomfort, and improve the user experience. According to the feature vector, the adaptive adjustment mechanism formula is used to adjust the helmet wearing parameters. Through this process, the system can automatically adjust the helmet wearing parameters to adapt to the physiological and psychological needs of different users, and improve the comfort and use effect of the helmet.

[0067] In order to evaluate the adjustment effect, in an optional implementation manner, the above step S205 includes:

[0068] Step S2051, the feeling data in the subject's feeling data is substituted into the first analysis formula to obtain the average value of the feeling data score. The first analysis formula is: in, is the average score of the above perception data, S i Score the above feeling data of the i-th subject, i is the variable index, and Z is the total number of subjects;

[0069] Step S2052, the physiological data in the subject's feeling data is substituted into a second analysis formula to obtain heart rate variability. The second analysis formula is: Where HRV is heart rate variability, σ RR is the standard deviation of heart rate, is the average heart rate;

[0070] Step S2053, substituting the EEG signal data in the subject's perception data into a third analysis formula to obtain the power of the α wave in the EEG signal. The third analysis formula is: Among them, P α is the power of the α wave, P(f) is the power spectrum density of the EEG signal, and f α,high and f α,low They are the upper and lower limits of the frequency range of the above-mentioned α waves, respectively;

[0071] Step S2054, substituting the EEG signal data in the subject's perception data into a fourth analysis formula to obtain the pressure distribution uniformity index. The fourth analysis formula is: Where UI is the pressure distribution uniformity index, P j is the pressure value detected by the jth 3D pressure mapping sensor, j is the variable index, is the average value of the pressure values ​​detected by all the 3D pressure mapping sensors, and V is the total number of the 3D pressure mapping sensors;

[0072] Step S2055, when the tightness condition is met, determining that the adjustment effect is effective, the tightness condition being that the average value of the feeling data score is greater than the first standard value, the heart rate variability is greater than or equal to the second set threshold and less than or equal to the third standard value, the power of the alpha wave is less than or equal to the fourth standard value, and the pressure distribution uniformity index is less than the fifth standard value;

[0073] Step S2056: When the tightness condition is not satisfied, it is determined that the adjustment effect is invalid.

[0074] In the above embodiment, the feeling data scores of all subjects are collected, and these scores may be based on questionnaires, self-reports or other forms of subjective evaluation. Then, the average value is calculated using the first analysis formula, which provides a general trend of the quantitative feeling data score to help understand the overall feeling of the subject to the adjustment. The average value can be used as one of the benchmark indicators for evaluating the effect of the adjustment. The physiological data of the subject is collected, especially the heart rate data. The heart rate variability is calculated using the second analysis formula. The heart rate variability is an important indicator for measuring the activity of the autonomic nervous system, which can reflect the stress level and emotional state of the subject. By analyzing HRV, the effect of the adjustment on the physiological state of the subject can be understood. The EEG signal data of the subject is collected, and the power of the alpha wave is calculated using the third analysis formula. The alpha wave power is an important indicator for measuring the state of brain relaxation and is related to attention and relaxation. By analyzing the alpha wave power, the effect of the adjustment on the brain activity of the subject can be understood. The pressure value detected by the subject using the 3D pressure mapping sensor is collected, and the pressure distribution uniformity index is calculated using the fourth analysis formula. The pressure distribution uniformity index can reflect the pressure distribution of the subject on the contact surface, which is related to comfort and health risks, and the effect of the adjustment on the pressure distribution of the subject's body can be understood. The results obtained from the first to fourth analysis formulas are compared with the preset standard values ​​to determine whether the tightness condition is met. The key to comprehensively evaluating the adjustment effect is that it combines data from multiple dimensions such as subjective feelings, physiological reactions, brain activity, and body pressure distribution. If the tightness condition is met, the adjustment is considered effective, otherwise it is considered invalid. This helps decision makers understand the actual effect of the adjustment measures and optimize them accordingly. If the adjustment is judged to be invalid, it can prompt researchers or decision makers to reconsider the adjustment strategy and find a more effective solution. By comprehensively analyzing the subjective feelings, physiological reactions, brain activity, and body pressure distribution of the subjects, a comprehensive and scientific basis is provided for evaluating the adjustment effect.

[0075] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0076] The embodiment of the present application also provides a helmet wearing tightness testing device. It should be noted that the helmet wearing tightness testing device of the embodiment of the present application can be used to execute the helmet wearing tightness testing method provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0077] The following is an introduction to the helmet wearing tightness testing device provided in the embodiment of the present application.

[0078] Figure 3 : is a structural block diagram of a helmet wearing tightness testing device according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0079] The acquisition unit 10 is used to execute the acquisition step to acquire valid subject data when the subject wears the helmet in different simulation scenarios, wherein the valid subject data includes valid eye tracking data, head micro-movement data and electroencephalogram signals after data processing, wherein the eye tracking data at least includes the subject's line of sight movement trajectory, gaze point and number of blinks, and the head micro-movement data at least includes the subject's head linear acceleration, velocity and angular velocity data.

[0080] Specifically, an eye tracking device is used to record the subject's line of sight movement trajectory, fixation point, and number of blinks. The subject's head linear acceleration, velocity, and angular velocity data are collected through sensors. An electroencephalogram (EEG) device is used to record the subject's EEG signals. The collected data is preprocessed to obtain the above-mentioned valid subject data, including filtering, artifact removal, etc., to ensure the validity of the data. Ensure that the collected data accurately reflects the subject's actual state in the simulated scene.

[0081] The generating unit 20 is used to execute the generating step, monitor the pressure distribution of the contact surface between the inside of the helmet and the head of the subject through the 3D pressure mapping technology, and generate a pressure distribution map.

[0082] Specifically, 3D pressure mapping technology is used to monitor the pressure distribution of the contact surface between the helmet and the subject's head. A pressure distribution map is generated based on the monitoring results to show the pressure points where the helmet contacts the head. Providing detailed pressure information on the contact between the helmet and the head helps identify problems with the tightness of the helmet.

[0083] The pattern recognition unit 30 is used to perform the pattern recognition step, input the above-mentioned pressure distribution map and the above-mentioned valid subject data into the pattern recognition model to judge the tightness of the helmet wearing, and obtain the tightness pattern of the helmet wearing of the above-mentioned subject, and the above-mentioned tightness pattern is divided into the helmet wearing tightly or the helmet wearing loosely.

[0084] Specifically, the pressure distribution map and valid subject data are input into the pattern recognition model, which analyzes the data, determines the tightness of the helmet, and outputs the pattern of whether the helmet is worn tightly or loosely. The pattern recognition technology is used to quickly determine the wearing status of the helmet, providing a basis for subsequent adjustments.

[0085] The adjustment unit 40 is used to perform the adjustment step. When the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted according to the pressure distribution diagram and the valid subject data using an adaptive adjustment mechanism to make the helmet adapt to the head of the subject.

[0086] Specifically, when it is identified that the helmet is not worn tightly, the adaptive adjustment mechanism is used to automatically adjust the helmet wearing parameters. According to the adjustment parameters, the position or tightness of the helmet is automatically adjusted to fit the subject's head. The automated adjustment process reduces human intervention and improves the efficiency and accuracy of the adjustment. The helmet is made to better fit the subject's head, improving comfort and functionality.

[0087] The verification unit 50 is used to execute the verification step, reacquire the subject's perception data according to the automatically adjusted helmet wearing parameters, and verify the adjustment effect according to the subject's perception data, the subject's perception data includes the subject's perception data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly.

[0088] Specifically, based on the automatically adjusted helmet wearing parameters, the subject's sensory data, physiological data, EEG signal data, and pressure distribution data are recollected. The recollected data is analyzed to verify the adjustment effect and determine whether the helmet is worn tightly. Ensure that the adjusted helmet wearing state meets the requirements and improve the accuracy and reliability of the simulation test. If the adjustment is ineffective, further adjustments can be made in a timely manner.

[0089] The repeating unit 60 is used to repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step in sequence at least once until the helmet is worn tightly when the adjustment effect is invalid.

[0090] Specifically, if the verification result shows that the adjustment is invalid, the acquisition step, generation step, pattern recognition step, adjustment step and verification step are repeated until the helmet is worn tightly. The tightness of the helmet is ensured through an iterative process until a satisfactory effect is achieved. The robustness of the system is improved to ensure that the best helmet wearing effect can be achieved under different subjects and different simulation scenarios. The purpose of the entire process is to ensure the tightness of the helmet in the simulation scenario, thereby improving the comfort of the subjects and the accuracy of the test data. Through an automated and intelligent adjustment mechanism, the process can adapt to the head characteristics of different subjects and achieve personalized helmet wearing adjustments.

[0091] In this embodiment, the acquisition unit is used to execute the acquisition step to acquire valid subject data when the subject wears the helmet in different simulation scenarios, the above-mentioned valid subject data includes valid eye tracking data, head micro-movement data and EEG signals after data processing, the above-mentioned eye tracking data at least includes the subject's line of sight movement trajectory, gaze point and number of blinks, and the above-mentioned head micro-movement data at least includes the subject's head linear acceleration, velocity and angular velocity data; the generation unit is used to execute the generation step to monitor the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology to generate a pressure distribution map; the pattern recognition unit is used to execute the pattern recognition step to input the above-mentioned pressure distribution map and the above-mentioned valid subject data into the pattern recognition model to judge the tightness of the helmet wearing and obtain the tightness mode of the helmet wearing of the above-mentioned subject, and the above-mentioned tightness mode is divided into the helmet wearing tightly or the helmet wearing loosely; the adjustment unit is used to An adjustment step, when the tightness mode is that the helmet is not worn tightly, automatically adjusting the helmet wearing parameters according to the pressure distribution diagram and the valid subject data by using an adaptive adjustment mechanism, so that the helmet adapts to the head of the subject; a verification unit, used to execute the verification step, according to the automatically adjusted helmet wearing parameters, re-acquire the subject's feeling data, and verify the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid or valid, the invalid adjustment indicates that the helmet is still not worn tightly, and the valid adjustment indicates that the helmet is worn tightly; a repeating unit, used to, when the adjustment effect is that the adjustment is invalid, sequentially repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once until the helmet is worn tightly. This application combines eye tracking, EEG signal collection and 3D pressure mapping technology, as well as developed deep learning pattern recognition algorithms, to achieve accurate testing and adaptive adjustment of helmet tightness. According to the automatically adjusted helmet wearing parameters, the data of the subjects is recollected, the adjustment effect is verified and analyzed until the helmet is tightly worn, thereby improving the comfort and protection of the helmet. This application solves the problem in the prior art that the deviation between the helmet test results and the actual usage makes it difficult to accurately evaluate the fit between the helmet and the head.

[0092] In order to comprehensively evaluate the behavior and physiological response of the subject in the virtual environment, in an optional implementation, the acquisition unit includes:

[0093] A simulation module is started, which is used to start the 4D environment simulator and randomly generate different simulation scenarios when the preparation conditions are met. The preparation conditions are that the subject cleans his head and wears a helmet as instructed and sits in the simulation environment to prepare for different scenario tests;

[0094] A virtual indication module, used to superimpose a virtual indication of the helmet wearing status in the field of vision of the subject in real time through AR technology according to the above-mentioned simulation scene, so that the subject can complete the corresponding action according to the above-mentioned virtual indication and obtain the original eye tracking data and the original head micro-movement data in real time;

[0095] A data cleaning module, used for performing a data cleaning operation on the original eye tracking data and the original head micro-movement data to obtain valid eye tracking data and valid head micro-movement data;

[0096] A monitoring module, used to monitor the original EEG signals of the above-mentioned subjects in real time by using a high-resolution EEG signal acquisition system combined with signal processing technology;

[0097] The preprocessing module is used to perform preprocessing operations on the above-mentioned original EEG signals to obtain intermediate EEG signals, and use Fourier transform to extract characteristic signals in the above-mentioned intermediate EEG signals to obtain the effective above-mentioned EEG signals. The above-mentioned preprocessing operations at least include artifact removal operations.

[0098] In the above embodiment, the subject first needs to clean his head to reduce signal interference and wear a helmet as instructed, which is usually a head-mounted display (HMD) with sensors. The subject sits in a simulated environment and prepares for testing in different scenarios. Start a 4D environment simulator that can generate a virtual environment with multiple sensory stimuli such as vision, hearing, and touch. Randomly generate different simulation scenarios, which may include different environments, tasks, or challenges to test the subject's response. By simulating real or fictional environments, experimental conditions can be controlled and interference from external variables can be reduced. Randomly generated scenarios increase the diversity and unpredictability of the test and help collect more comprehensive data. Using AR technology, virtual instructions are superimposed in the subject's field of view in real time, which may include arrows, cursors, or other visual cues. The subject completes the corresponding actions according to these virtual instructions, such as moving the head, eye tracking, etc. At the same time, the system collects the subject's eye tracking data and head micro-movement data in real time. AR technology provides an intuitive way of interaction, allowing subjects to interact with the virtual environment more naturally. The collected raw eye tracking data and head micro-movement data are cleaned to remove noise and outliers. Invalid data is identified and eliminated through algorithms, and valid data is retained for subsequent analysis. Data cleaning ensures the accuracy and reliability of the data and provides a high-quality data foundation for subsequent analysis. Valid data can more accurately reflect the behavior and response of the subjects. The EEG activity of the subjects is monitored in real time using a high-resolution EEG signal acquisition system. The EEG signal acquisition system may include multiple electrodes distributed on the subject's scalp to capture the electrical activity of different areas of the brain. EEG signal monitoring can provide direct information about the cognitive state and emotional response of the subject. The raw EEG signal is preprocessed, including artifact removal operations, such as removing eye movement artifacts and electromyographic artifacts. The preprocessed signal is Fourier transformed to extract the frequency components, i.e., characteristic signals. These characteristic signals can reflect specific patterns of brain activity, such as alpha waves, beta waves, etc. The preprocessing operation improves the signal-to-noise ratio of the EEG signal, making the signal easier to analyze. By combining multiple technologies and data, the behavior and physiological responses of the subjects in the virtual environment can be comprehensively evaluated, which is of great significance to the development of psychology, cognitive science, neuroscience, and virtual reality technology.

[0099] In order to improve the quality of EEG signals, in an optional implementation, the preprocessing module includes:

[0100] The artifact removal submodule is used to perform the above artifact removal operation on the above original EEG signal according to the artifact removal formula to obtain the above intermediate EEG signal. The above artifact removal formula is: Among them, Artifact=|e in (t)-μ e |>ασ e , ein (t) is the original EEG signal at time t, μ e is the average value of the original EEG signal, σ e is the standard deviation of the original EEG signal, α is the threshold coefficient, Artifact is a Boolean value, e clean (t) is the above intermediate EEG signal after artifact removal, e in (t-1) is the original EEG signal value without artifacts at time t-1, e in (t+1) is the original EEG signal value without artifacts at time t+1;

[0101] The feature extraction submodule is used to extract the features of the intermediate EEG signal according to the Fourier transform formula to obtain the EEG signal. The Fourier transform formula is: Among them, F(ω) is the above-mentioned EEG signal obtained by Fourier transform, f(t) is a time domain signal, which represents the function of the above-mentioned intermediate EEG signal, t is time, ω is angular frequency, and j is an imaginary unit.

[0102] In the above embodiment, the average value and standard deviation are calculated: the average value μ of the original EEG signal is calculated. e and standard deviation σ e For each time point t, calculate |e in (t)-μ e |, if this absolute value is greater than ασ e , then it is considered that there is an artifact at this point, that is, Artifact=True is satisfied; otherwise, Artifact=False is satisfied. Perform the artifact removal operation according to the above artifact removal formula. Remove artifacts from EEG signals. These artifacts may be caused by eye movements, electromyographic interference, power supply interference, etc., which will interfere with the analysis and interpretation of the signal. By replacing or smoothing the artifact points, the quality of EEG signals is improved, the noise caused by artifacts is reduced, and the signal is clearer, which is helpful for subsequent feature extraction and pattern recognition. Apply the Fourier transform formula to the intermediate EEG signal after artifact removal to obtain the signal obtained by Fourier transform, that is, the amplitude and phase information at different frequencies. Convert the time domain signal to the frequency domain signal to facilitate the analysis of the frequency components of the signal. Extract features from the spectrum, such as power spectral density, frequency band energy, etc. These features are very important for understanding the physiological significance of EEG signals and performing pattern recognition. By extracting key frequency components, the dimension of the data can be reduced, simplifying subsequent data processing and analysis. Improve the quality of EEG signals and extract features that are helpful for analysis and recognition.

[0103] In order to help improve the comfort and safety of the helmet, in an optional implementation, the generating unit includes:

[0104] A collection module, used to collect pressure data on the contact surface between the helmet and the head in real time through a 3D pressure mapping sensor, and the 3D pressure mapping sensor is fixed inside the helmet;

[0105] A conversion module is used to convert the pressure data into the pressure distribution diagram according to a pressure mapping formula. The pressure mapping formula is: Where P(x,y) is the pressure value at the coordinate (x,y), (x,y) is the coordinate position on the contact surface inside the helmet, and w i is the weight factor of the i-th 3D pressure mapping sensor, p i is the pressure value measured by the i-th 3D pressure mapping sensor, i is the variable index, N is the total number of the 3D pressure mapping sensors, and the expression of the pressure value of each coordinate point in the pressure distribution diagram is: Wherein, p′(x,y) is the interpolated pressure value, (x1,y1) and (x2,y2) are the coordinates of adjacent points with known pressure values, and P(x1,y1), P(x2,y1), P(x1,y2) and P(x2,y2) are the above-mentioned known pressure values ​​at adjacent points.

[0106] In the above embodiment, 3D pressure mapping sensors are evenly distributed on the contact surface inside the helmet. These sensors need to be able to detect small pressure changes. The sensor monitors the pressure on the contact surface inside the helmet in real time and converts it into an electrical signal. The electrical signal is transmitted to the data processing unit through a wire or wirelessly, and the pressure data is processed. Being able to understand the pressure distribution inside the helmet in real time is crucial for adjusting the helmet design to improve wearing comfort. Using a given pressure mapping formula, the pressure data collected from each 3D pressure mapping sensor is converted into coordinate points on the coordinates, and the pressure value of each point on the entire contact surface is calculated using an interpolation formula based on the known pressure value and coordinate position. The interpolation formula uses the known pressure values ​​of four adjacent points to estimate the pressure value of any point. A continuous pressure distribution map is generated based on all the coordinate point positions and the corresponding interpolated pressure values. By analyzing the pressure distribution map, areas with too high or too low pressure can be identified, thereby optimizing the design of the helmet, such as adjusting the thickness or hardness of the lining material. By real-time monitoring and analysis of the pressure distribution inside the helmet, it helps to improve the comfort and safety of the helmet, and also provides important data support for the design and manufacture of the helmet.

[0107] In order to effectively predict the tightness pattern of the helmet, in an optional embodiment, the pattern recognition unit includes:

[0108] The input-output module is used to input the pressure distribution map and the valid subject data into the pattern recognition model, to extract the spatial features of the pressure distribution map and the valid subject data by the convolution layer in the pattern recognition model to generate a feature map, and to perform a dimensionality reduction pooling operation in the pooling layer in the pattern recognition model, to convert the feature map into a one-dimensional feature vector in the fully connected layer in the pattern recognition model, to perform feature processing on the one-dimensional feature vector in the output layer in the pattern recognition model, and to output the compactness pattern, wherein the formula for generating the feature map is: y(n,i,j) is the value of the output nth feature map at position (i,j), n, i, j are variable indexes, W(n,k,l) ​​is the weight of the corresponding nth convolution kernel at position (k,l), x(n,i+k,j+l) is the value of the input data x at position (i+k,j+l), b(n) is the bias coefficient corresponding to the nth convolution kernel, σ is the activation function, and x is the input data, which represents the above pressure distribution map and the above valid subject data.

[0109] In the above embodiment, the above training deep learning model includes using convolutional neural network to perform model training, using convolution to extract spatial features of input data, generating feature maps, using activation functions to introduce nonlinearity, reducing data dimensions and performing pooling operations in the pooling layer, and converting the feature maps into one-dimensional feature vectors in the fully connected layer. The formula for generating feature maps is: The loss function formula in the iterative optimization process is: in, is the loss function, Represents the predicted value, y represents the true value, M represents the number of samples, and i is the variable index. The overall process is: first input the pressure distribution map and valid subject data into the pattern recognition model. Then use the convolution layer in the model to extract spatial features. After the convolution operation, an activation function (such as ReLU activation function, Sigmoid activation function or Tanh activation function) is usually applied to introduce nonlinearity and enhance the expressiveness of the model. Pooling layer: After the convolution layer, the pooling layer (such as maximum pooling or average pooling) is used to reduce dimension and extract important features to reduce the amount of calculation. The fully connected layer converts the feature map into a one-dimensional feature vector in preparation for classification or regression tasks. The output layer performs feature processing on the one-dimensional feature vector and outputs a compactness pattern. This enables the model to automatically learn features that distinguish different categories or prediction targets from the input data, and can effectively predict new data.

[0110] In order to improve the comfort and use effect of the helmet, in an optional implementation, the adjustment unit includes:

[0111] a feature extraction module, configured to extract features from the pressure distribution graph and the valid subject data to obtain corresponding feature data, wherein the feature data corresponding to the pressure distribution graph at least includes a pressure peak value, a pressure average value, and uniformity of pressure distribution, and the feature data corresponding to the valid subject data at least includes a gaze point position, a gaze duration, a blinking frequency, a speed of head movement, an acceleration, and a movement trajectory;

[0112] A feature fusion module is used to fuse all the above feature data to obtain a feature vector;

[0113] The adjustment module is used to adjust the helmet wearing parameters according to the adaptive adjustment mechanism formula based on the feature vector. The adaptive adjustment mechanism formula includes a pressure adjustment formula and a helmet position adjustment formula. The pressure adjustment formula is ΔP=K p ·(P desired -P current ), where ΔP is the pressure adjustment amount, K p is the proportional adjustment coefficient, P desired is the desired pressure distribution, P current is the currently monitored pressure distribution, and the above helmet position adjustment formula is: θ=θ0+Δθ, where θ is the new position of the helmet, θ0 is the initial position of the helmet, and Δθ is the adjustment amount of the helmet.

[0114] In the above embodiment, by analyzing the pressure distribution diagram, the point with the highest pressure value is found to obtain the pressure peak value. The average of all pressure values ​​in the pressure distribution diagram is calculated to obtain the pressure average value. The uniformity of the pressure distribution is evaluated by statistically analyzing the standard deviation or variance of the pressure values ​​in the pressure distribution diagram. The focus position of the subject's line of sight is obtained by an eye tracking device to obtain the gaze point position. The gaze duration is obtained by recording the length of time the subject keeps gazing at a specific gaze point. The blink frequency is obtained by recording the number of times and time intervals of the subject's blinks by an eye tracking device. The speed of the head movement is measured by a head movement tracking device to obtain the speed of the head movement. The acceleration of the head movement is measured by an accelerometer to obtain the acceleration. The path of the head movement is recorded by the tracking device to obtain the motion trajectory, and the key information that can represent the helmet wearing comfort and the subject's physiological state is extracted from the raw data to provide a basis for subsequent helmet adjustment. All extracted feature data are integrated to form a feature vector. Feature fusion is to merge multiple feature data into a unified data structure for subsequent algorithm processing. This helps to reduce data dimensions, improve algorithm efficiency, and may improve the generalization ability of the model. The above adjustment amount can be a step size set according to the feature vector, or it can be obtained by fine calculation through other algorithms. By adjusting the pressure distribution inside the helmet, the pressure distribution is closer to the expected pressure distribution, thereby improving the comfort and stability of the helmet. By adjusting the position of the helmet, the helmet can fit the user's head more closely, reduce discomfort, and improve the user experience. According to the feature vector, the adaptive adjustment mechanism formula is used to adjust the helmet wearing parameters. Through this process, the system can automatically adjust the helmet wearing parameters to adapt to the physiological and psychological needs of different users, and improve the comfort and use effect of the helmet.

[0115] In order to evaluate the adjustment effect, in an optional implementation manner, the verification unit includes:

[0116] The first calculation module is used to bring the above-mentioned feeling data in the above-mentioned subject feeling data into the first analysis formula to obtain the average value of the feeling data score. The above-mentioned first analysis formula is: in, is the average score of the above perception data, S i Score the above feeling data of the i-th subject, i is the variable index, and Z is the total number of subjects;

[0117] The second calculation module is used to bring the above physiological data in the above subject's feeling data into the second analysis formula to obtain the heart rate variability. The above second analysis formula is: Where HRV is heart rate variability, σ RR is the standard deviation of heart rate, is the average heart rate;

[0118] The third calculation module is used to substitute the EEG signal data in the subject's perception data into a third analysis formula to obtain the power of the alpha wave in the EEG signal. The third analysis formula is: Among them, P α is the power of the α wave, P(f) is the power spectrum density of the EEG signal, and f α,high and f α,low They are the upper and lower limits of the frequency range of the above-mentioned α waves, respectively;

[0119] The fourth calculation module is used to substitute the above-mentioned EEG signal data in the above-mentioned subject's feeling data into the fourth analysis formula to obtain the above-mentioned pressure distribution uniformity index. The above-mentioned fourth analysis formula is: Where UI is the pressure distribution uniformity index, P j is the pressure value detected by the jth 3D pressure mapping sensor, j is the variable index, is the average value of the pressure values ​​detected by all the 3D pressure mapping sensors, and V is the total number of the 3D pressure mapping sensors;

[0120] A first determination module is used to determine that the adjustment effect is effective if a tightness condition is met, wherein the tightness condition is that the average value of the feeling data score is greater than a first standard value, the heart rate variability is greater than or equal to a second set threshold and less than or equal to a third standard value, the power of the alpha wave is less than or equal to a fourth standard value, and the pressure distribution uniformity index is less than a fifth standard value;

[0121] The second determination module is configured to determine that the adjustment effect is invalid if the compactness condition is not satisfied.

[0122] In the above embodiment, the feeling data scores of all subjects are collected, and these scores may be based on questionnaires, self-reports or other forms of subjective evaluation. Then, the average value is calculated using the first analysis formula, which provides a general trend of the quantitative feeling data score to help understand the overall feeling of the subject to the adjustment. The average value can be used as one of the benchmark indicators for evaluating the effect of the adjustment. The physiological data of the subject is collected, especially the heart rate data. The heart rate variability is calculated using the second analysis formula. The heart rate variability is an important indicator for measuring the activity of the autonomic nervous system, which can reflect the stress level and emotional state of the subject. By analyzing HRV, the effect of the adjustment on the physiological state of the subject can be understood. The EEG signal data of the subject is collected, and the power of the alpha wave is calculated using the third analysis formula. The alpha wave power is an important indicator for measuring the state of brain relaxation and is related to attention and relaxation. By analyzing the alpha wave power, the effect of the adjustment on the brain activity of the subject can be understood. The pressure value detected by the subject using the 3D pressure mapping sensor is collected, and the pressure distribution uniformity index is calculated using the fourth analysis formula. The pressure distribution uniformity index can reflect the pressure distribution of the subject on the contact surface, which is related to comfort and health risks, and the effect of the adjustment on the pressure distribution of the subject's body can be understood. The results obtained from the first to fourth analysis formulas are compared with the preset standard values ​​to determine whether the tightness condition is met. The key to comprehensively evaluating the adjustment effect is that it combines data from multiple dimensions such as subjective feelings, physiological reactions, brain activity, and body pressure distribution. If the tightness condition is met, the adjustment is considered effective, otherwise it is considered invalid. This helps decision makers understand the actual effect of the adjustment measures and optimize them accordingly. If the adjustment is judged to be invalid, it can prompt researchers or decision makers to reconsider the adjustment strategy and find a more effective solution. By comprehensively analyzing the subjective feelings, physiological reactions, brain activity, and body pressure distribution of the subjects, a comprehensive and scientific basis is provided for evaluating the adjustment effect.

[0123] The helmet wearing tightness test device comprises a processor and a memory. The acquisition unit, the generation unit and the pattern recognition unit are stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0124] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem in the prior art that the helmet test results deviate from the actual usage, making it difficult to accurately evaluate the fit between the helmet and the head.

[0125] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0126] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is running, the device where the computer-readable storage medium is located is controlled to execute the helmet wearing tightness testing method.

[0127] Specifically, the helmet wearing tightness test method includes:

[0128] Step S201, an acquisition step, acquiring valid subject data when the subject wears the helmet in different simulation scenarios, the valid subject data including valid eye tracking data, head micro-movement data and EEG signals after data processing, the eye tracking data at least including the subject's line of sight movement trajectory, fixation point and number of blinks, the head micro-movement data at least including the subject's head linear acceleration, velocity and angular velocity data;

[0129] Step S202, a generating step, monitoring the pressure distribution of the contact surface between the inside of the helmet and the head of the subject by 3D pressure mapping technology, and generating a pressure distribution map;

[0130] Step S203, a pattern recognition step, inputting the pressure distribution map and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtaining a tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely;

[0131] Step S204, an adjustment step, in which, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, so that the helmet fits the head of the subject;

[0132] Step S205, a verification step, reacquiring the subject's feeling data according to the automatically adjusted helmet wearing parameters, and verifying the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, and the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly;

[0133] Step S206, when the adjustment effect is that the adjustment is invalid, repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once in sequence until the helmet is worn tightly.

[0134] An embodiment of the present invention provides a processor, which is used to run a program, wherein the helmet wearing tightness testing method is executed when the program is running.

[0135] Specifically, the helmet wearing tightness test method includes:

[0136] Step S201, an acquisition step, acquiring valid subject data when the subject wears the helmet in different simulation scenarios, the valid subject data including valid eye tracking data, head micro-movement data and EEG signals after data processing, the eye tracking data at least including the subject's line of sight movement trajectory, fixation point and number of blinks, the head micro-movement data at least including the subject's head linear acceleration, velocity and angular velocity data;

[0137] Step S202, a generating step, monitoring the pressure distribution of the contact surface between the inside of the helmet and the head of the subject by 3D pressure mapping technology, and generating a pressure distribution map;

[0138] Step S203, a pattern recognition step, inputting the pressure distribution map and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtaining a tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely;

[0139] Step S204, an adjustment step, in which, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, so that the helmet fits the head of the subject;

[0140] Step S205, a verification step, reacquiring the subject's feeling data according to the automatically adjusted helmet wearing parameters, and verifying the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, and the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly;

[0141] Step S206, when the adjustment effect is that the adjustment is invalid, repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once in sequence until the helmet is worn tightly.

[0142] An embodiment of the present invention provides a helmet, the helmet comprising a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0143] Step S201, an acquisition step, acquiring valid subject data when the subject wears the helmet in different simulation scenarios, the valid subject data including valid eye tracking data, head micro-movement data and EEG signals after data processing, the eye tracking data at least including the subject's line of sight movement trajectory, fixation point and number of blinks, the head micro-movement data at least including the subject's head linear acceleration, velocity and angular velocity data;

[0144] Step S202, a generating step, monitoring the pressure distribution of the contact surface between the inside of the helmet and the head of the subject by 3D pressure mapping technology, and generating a pressure distribution map;

[0145] Step S203, a pattern recognition step, inputting the pressure distribution map and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtaining a tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely;

[0146] Step S204, an adjustment step, in which, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, so that the helmet fits the head of the subject;

[0147] Step S205, a verification step, reacquiring the subject's feeling data according to the automatically adjusted helmet wearing parameters, and verifying the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, and the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly;

[0148] Step S206, when the adjustment effect is that the adjustment is invalid, repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once in sequence until the helmet is worn tightly.

[0149] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0150] Step S201, an acquisition step, acquiring valid subject data when the subject wears the helmet in different simulation scenarios, the valid subject data including valid eye tracking data, head micro-movement data and EEG signals after data processing, the eye tracking data at least including the subject's line of sight movement trajectory, fixation point and number of blinks, the head micro-movement data at least including the subject's head linear acceleration, velocity and angular velocity data;

[0151] Step S202, a generating step, monitoring the pressure distribution of the contact surface between the inside of the helmet and the head of the subject by 3D pressure mapping technology, and generating a pressure distribution map;

[0152] Step S203, a pattern recognition step, inputting the pressure distribution map and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtaining a tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely;

[0153] Step S204, an adjustment step, in which, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, so that the helmet fits the head of the subject;

[0154] Step S205, a verification step, reacquiring the subject's feeling data according to the automatically adjusted helmet wearing parameters, and verifying the adjustment effect according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, and the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly;

[0155] Step S206, when the adjustment effect is that the adjustment is invalid, repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once in sequence until the helmet is worn tightly.

[0156] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0157] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0158] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0161] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0162] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0163] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0165] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0166] 1) The helmet wearing tightness test method of the present application comprises the following steps: first, an acquisition step is performed to acquire valid subject data when a subject wears a helmet in different simulation scenarios, wherein the valid subject data comprises valid eye tracking data, head micro-movement data and EEG signals after data processing, wherein the eye tracking data comprises at least the subject's line of sight movement trajectory, gaze point and blinking times, and the head micro-movement data comprises at least the subject's head linear acceleration, velocity and angular velocity data; then, a generation step is performed to monitor the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology to generate a pressure distribution map; then, a pattern recognition step is performed to input the pressure distribution map and the valid subject data into a pattern recognition model to judge the tightness of the helmet wearing and obtain the tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely; then, an adjustment step is performed to determine the tightness of the helmet wearing and obtain the tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely; then, an adjustment step is performed to determine the tightness of the helmet wearing and obtain the tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely. The whole step, when the tightness mode is that the helmet is not worn tightly, the helmet wearing parameters are automatically adjusted according to the pressure distribution map and the effective subject data by using the adaptive adjustment mechanism to make the helmet adapt to the head of the subject; then, the verification step, according to the automatically adjusted helmet wearing parameters, the subject's feeling data is re-acquired, and the adjustment effect is verified according to the subject's feeling data, the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, the adjustment effect is invalid or valid, the invalid adjustment means that the helmet is still not worn tightly, and the valid adjustment means that the helmet is worn tightly; finally, when the adjustment effect is invalid, the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step are repeated at least once in sequence until the helmet is worn tightly. The present application realizes accurate testing and adaptive adjustment of the tightness of helmet wearing by combining eye tracking, EEG signal acquisition and 3D pressure mapping technology, as well as the developed deep learning pattern recognition algorithm, and re-collects the subject's data according to the automatically adjusted helmet wearing parameters, verifies the adjustment effect and analyzes it until the helmet is worn tightly, thereby improving the comfort and protection effect of the helmet. The present application solves the problem in the prior art that the deviation between helmet test results and actual usage makes it difficult to accurately evaluate the fit between the helmet and the head.

[0167] 2) The helmet wearing tightness testing device of the present application comprises an acquisition unit, which is used to execute an acquisition step to acquire valid subject data when the subject wears the helmet in different simulation scenarios, wherein the valid subject data comprises effective eye tracking data, head micro-movement data and EEG signals after data processing, wherein the eye tracking data comprises at least the subject's line of sight movement trajectory, gaze point and blinking times, and the head micro-movement data comprises at least the subject's head linear acceleration, velocity and angular velocity data; a generation unit, which is used to execute a generation step to monitor the pressure distribution of the contact surface between the inside of the helmet and the subject's head through 3D pressure mapping technology to generate a pressure distribution map; a pattern recognition unit, which is used to execute a pattern recognition step to input the pressure distribution map and the valid subject data into a pattern recognition model to judge the tightness of the helmet wearing and obtain the tightness mode of the helmet wearing of the subject, wherein the tightness mode is divided into whether the helmet is worn tightly or not tightly; an adjustment unit, which is used to execute a pattern recognition step to input the pressure distribution map and the valid subject data into a pattern recognition model to judge the tightness of the helmet wearing and obtain the tightness mode of the helmet wearing of the subject, wherein the tightness mode is divided into whether the helmet is worn tightly or not tightly; The whole unit is used for the adjustment step. When the tightness mode is that the helmet is not tightly worn, the helmet wearing parameters are automatically adjusted according to the pressure distribution diagram and the valid subject data by using an adaptive adjustment mechanism to make the helmet adapt to the head of the subject; the verification unit is used to execute the verification step. According to the automatically adjusted helmet wearing parameters, the subject's feeling data is re-acquired, and the adjustment effect is verified according to the subject's feeling data. The subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data. The adjustment effect is invalid or valid. The invalid adjustment indicates that the helmet is still not tightly worn, and the valid adjustment indicates that the helmet is tightly worn; the repeating unit is used to, when the adjustment effect is that the adjustment is invalid, sequentially repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once until the helmet is tightly worn. This application combines eye tracking, EEG signal collection and 3D pressure mapping technology, as well as developed deep learning pattern recognition algorithms, to achieve accurate testing and adaptive adjustment of helmet tightness. According to the automatically adjusted helmet wearing parameters, the data of the subjects is recollected, the adjustment effect is verified and analyzed until the helmet is tightly worn, thereby improving the comfort and protection of the helmet. This application solves the problem in the prior art that the deviation between the helmet test results and the actual usage makes it difficult to accurately evaluate the fit between the helmet and the head.

[0168] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A helmet wearing tightness testing method, characterized in that: include: an acquisition step, acquiring valid subject data when the subject wears the helmet in different simulation scenarios, wherein the valid subject data includes valid eye tracking data, head micro-movement data and EEG signals after data processing, wherein the eye tracking data at least includes the subject's line of sight movement trajectory, fixation point and blinking times, and the head micro-movement data at least includes the subject's head linear acceleration, velocity and angular velocity data; A generating step, monitoring the pressure distribution of the contact surface between the inside of the helmet and the head of the subject by 3D pressure mapping technology, and generating a pressure distribution map; a pattern recognition step, inputting the pressure distribution map and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtaining a tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely; an adjusting step, when the tightness mode is that the helmet is not worn tightly, automatically adjusting the helmet wearing parameters by using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, so that the helmet fits the head of the subject; a verification step, reacquiring the subject's feeling data according to the automatically adjusted helmet wearing parameters, and verifying the adjustment effect according to the subject's feeling data, wherein the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data and pressure distribution data, and the adjustment effect is invalid or valid, wherein the invalid adjustment indicates that the helmet is still not worn tightly, and the valid adjustment indicates that the helmet is worn tightly; In a case where the adjustment effect is that the adjustment is invalid, the obtaining step, the generating step, the pattern recognition step, the adjusting step and the verifying step are sequentially repeated at least once until the helmet is worn tightly.

2. The method according to claim 1, characterized in that Obtain valid subject data when the subject wears a helmet in different simulation scenarios, including: When the preparation conditions are met, the 4D environment simulator is started and different simulation scenes are randomly generated. The preparation conditions are that the subject cleans his head and wears a helmet as instructed and sits in the simulation environment to prepare for different scene tests; According to the simulation scene, a virtual indication of the helmet wearing status is superimposed in the field of vision of the subject in real time by using AR technology, so that the subject can complete the corresponding action according to the virtual indication and obtain the original eye tracking data and the original head micro-movement data in real time; Performing a data cleaning operation on the original eye tracking data and the original head micro-movement data to obtain valid eye tracking data and valid head micro-movement data; Using a high-resolution EEG signal acquisition system combined with signal processing technology to monitor the original EEG signals of the subject in real time; The original EEG signal is preprocessed to obtain an intermediate EEG signal, and a characteristic signal in the intermediate EEG signal is extracted using Fourier transform to obtain a valid EEG signal. The preprocessing operation at least includes an artifact removal operation.

3. The method according to claim 2, characterized in that The original EEG signal is preprocessed to obtain an intermediate EEG signal, and a characteristic signal in the intermediate EEG signal is extracted by Fourier transform to obtain a valid EEG signal, including: The artifact removal operation is performed on the original EEG signal according to the artifact removal formula to obtain the intermediate EEG signal. The artifact removal formula is: Among them, Artifact=|e in (t)-μ e |>ασ e , e in (t) is the original EEG signal at time t, μ e is the average value of the original EEG signal, σ e is the standard deviation of the original EEG signal, α is the threshold coefficient, Artifact is a Boolean value, e clean (t) is the intermediate EEG signal after artifact removal, e in (t-1) is the original EEG signal value without artifacts at time t-1, e in (t+1) is the original EEG signal value without artifacts at time t+1; The feature extraction of the intermediate EEG signal is performed according to the Fourier transform formula to obtain the EEG signal. The Fourier transform formula is: Wherein, F(ω) is the EEG signal obtained by Fourier transform, f(t) is a time domain signal, representing a function of the intermediate EEG signal, t is time, ω is angular frequency, and j is an imaginary unit.

4. The method according to claim 1, characterized in that The pressure distribution of the contact surface between the helmet and the subject's head is monitored by 3D pressure mapping technology to generate a pressure distribution map, including: The 3D pressure mapping sensor is used to collect the pressure data on the contact surface between the helmet and the head in real time, and the 3D pressure mapping sensor is fixed inside the helmet; All the pressure data are converted into the pressure distribution map according to the pressure mapping formula, and the pressure mapping formula is: Where P(x,y) is the pressure value at the coordinate (x,y), (x,y) is the coordinate position on the contact surface inside the helmet, and w i is the weight factor of the ith 3D pressure mapping sensor, p i is the pressure value measured by the i-th 3D pressure mapping sensor, i is a variable index, N is the total number of the 3D pressure mapping sensors, and the expression of the pressure value of each coordinate point in the pressure distribution map is: Among them, p′(x,y) is the interpolated pressure value, (x1,y1) and (x2,y2) are the coordinates of adjacent points with known pressure values, and P(x1,y1), P(x2,y1), P(x1,y2) and P(x2,y2) are the known pressure values ​​at adjacent points.

5. The method according to claim 1, characterized in that Inputting the pressure distribution map and the valid subject data into a pattern recognition model to obtain a tightness pattern of the subject's helmet wearing, including: The pressure distribution map and the valid subject data are input into the pattern recognition model, so as to use the convolution layer in the pattern recognition model to extract the spatial features of the pressure distribution map and the valid subject data to generate a feature map, and the pooling layer in the pattern recognition model performs a dimensionality reduction pooling operation, and the fully connected layer in the pattern recognition model converts the feature map into a one-dimensional feature vector, and the output layer in the pattern recognition model performs feature processing on the one-dimensional feature vector, and outputs the compactness pattern, wherein the formula for generating the feature map is: y(n,i,j) is the value of the output nth feature map at position (i,j), n, i, j are variable indexes, W(n,k,l) ​​is the weight of the corresponding nth convolution kernel at position (k,l), x(n,i+k,j+l) is the value of the input data x at position (i+k,j+l), b(n) is the bias coefficient corresponding to the nth convolution kernel, σ is the activation function, x is the input data, representing the pressure distribution map and the valid subject data.

6. The method according to claim 1, characterized in that Automatically adjusting the helmet wearing parameters using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, including: Performing feature extraction on both the pressure distribution map and the valid subject data to obtain corresponding feature data, wherein the feature data corresponding to the pressure distribution map at least includes a pressure peak value, a pressure average value, and uniformity of pressure distribution, and the feature data corresponding to the valid subject data at least includes a gaze point position, a gaze duration, a blinking frequency, a speed of head movement, an acceleration, and a movement trajectory; Performing feature fusion on all the feature data to obtain a feature vector; The helmet wearing parameters are adjusted according to the adaptive adjustment mechanism formula based on the characteristic vector, wherein the adaptive adjustment mechanism formula includes a pressure adjustment formula and a helmet position adjustment formula, and the pressure adjustment formula is ΔP=K p ·(P desired -P current ), where ΔP is the pressure adjustment amount, K p is the proportional adjustment coefficient, P desired is the desired pressure distribution, P current is the currently monitored pressure distribution, and the helmet position adjustment formula is: θ=θ0+Δθ, where θ is the new position of the helmet, θ0 is the initial position of the helmet, and Δθ is the adjustment amount of the helmet.

7. The method according to claim 1, characterized in that Verifying the adjustment effect according to the subject's perception data includes: Substitute the feeling data in the subject's feeling data into the first analysis formula to obtain the average feeling data score. The first analysis formula is: in, is the average score of the perception data, S i Score the perception data of the i-th subject, i is the variable index, and Z is the total number of subjects; The physiological data in the subject's feeling data is substituted into a second analysis formula to obtain heart rate variability. The second analysis formula is: Where HRV is heart rate variability, σ RR is the standard deviation of heart rate, is the average heart rate; Substituting the EEG signal data in the subject's perception data into the third analysis formula to obtain the power of the α wave in the EEG signal, the third analysis formula is: Among them, P α is the power of the α wave, P(f) is the power spectral density of the EEG signal, and f α,high and f α,low are the upper and lower limits of the frequency range of the α wave, respectively; Substituting the EEG signal data in the subject's perception data into the fourth analysis formula to obtain the pressure distribution uniformity index, the fourth analysis formula is: Wherein, UI is the pressure distribution uniformity index, P j is the pressure value detected by the jth 3D pressure mapping sensor, j is the variable index, is the average value of the pressure values ​​detected by all the 3D pressure mapping sensors, and V is the total number of the 3D pressure mapping sensors; In the case where a tightness condition is met, determining that the adjustment effect is effective, the tightness condition being that the average value of the feeling data score is greater than a first standard value, the heart rate variability is greater than or equal to a second set threshold and less than or equal to a third standard value, the power of the alpha wave is less than or equal to a fourth standard value, and the pressure distribution uniformity index is less than a fifth standard value; When the tightness condition is not satisfied, the adjustment effect is determined to be invalid.

8. A helmet wearing tightness testing device, characterized in that: The device comprises: an acquisition unit, configured to execute the acquisition step to acquire valid subject data when the subject wears the helmet in different simulation scenarios, wherein the valid subject data includes valid eye tracking data, head micro-movement data and electroencephalogram signals after data processing, wherein the eye tracking data at least includes the subject's line of sight movement trajectory, fixation point and blinking times, and the head micro-movement data at least includes the subject's head linear acceleration, velocity and angular velocity data; A generating unit, configured to execute the generating step, monitor the pressure distribution of the contact surface between the inside of the helmet and the head of the subject through 3D pressure mapping technology, and generate a pressure distribution map; a pattern recognition unit, configured to perform a pattern recognition step, input the pressure distribution diagram and the valid subject data into a pattern recognition model to determine the tightness of the helmet wearing, and obtain a tightness pattern of the helmet wearing of the subject, wherein the tightness pattern is divided into a helmet wearing tightly or a helmet wearing loosely; an adjusting unit, configured to adjust, in a step where, when the tightness mode is that the helmet is not worn tightly, automatically adjust the helmet wearing parameters using an adaptive adjustment mechanism according to the pressure distribution diagram and the valid subject data, so as to adapt the helmet to the head of the subject; a verification unit, configured to execute a verification step, reacquire the subject's feeling data according to the automatically adjusted helmet wearing parameters, and verify the adjustment effect according to the subject's feeling data, wherein the subject's feeling data includes the subject's feeling data, physiological data, EEG signal data, and pressure distribution data, and the adjustment effect is that the adjustment is invalid or valid, wherein the invalid adjustment indicates that the helmet is still not worn tightly, and the valid adjustment indicates that the helmet is worn tightly; A repeating unit is used to, when the adjustment effect is that the adjustment is invalid, sequentially repeat the acquisition step, the generation step, the pattern recognition step, the adjustment step and the verification step at least once until the helmet is worn tightly.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images