A method, system and device for monitoring attention based on EEG

Abstract

The present invention discloses an EEG-based attention monitoring method, system and device, which relate to the technical field of attention monitoring, including: obtaining original EEG data, performing passband filtering and notch filtering on the original EEG data to filter out environmental noise, and obtaining denoised EEG data; performing α, β, and θ filtering on the denoised EEG data, and calculating the α, β, and θ frequency band powers to obtain α, β, and θ frequency band power data, wherein the original EEG data has a timestamp; performing attention initialization processing on the α, β, and θ frequency band power data to obtain baseline values ​​of the attention parameter EI and the α wave desynchronization parameter ASD of each terminal user; normalizing the EI parameter and the ASD parameter relative to the baseline value to obtain an effective attention parameter value, thereby realizing attention monitoring.

Description

Technical Field

[0001] The present invention relates to the field of attention monitoring technology, and in particular to an EEG-based attention monitoring method, system, and device. Background Art

[0002] Brain-computer interface technology uses non-invasive EEG (Electroencephalogram) to monitor the target's attention state, thereby understanding the impact of macro-environment such as teaching methods, work content, and work methods on the target object's learning or work status, and providing a reliable reference for improving work and learning methods.

[0003] With the development of EEG technology, the correlation between various EEG signal bands and brain activity is becoming increasingly clear. EEG signals have become an important research and detection tool for identifying human brain states. The impact of macroscopic conditions in certain scenarios on a group of people is well-suited for monitoring using EEG technology. Attentional state is often of great interest. While assessing this state using attention parameters can provide insights into individual attentional trends, these parameters are relative. The absolute values ​​of these parameters can vary between individuals, and even for the same individual at different times. Effective attention monitoring requires reliable baseline values. Currently, the common practice is to prepare fixed videos, images, or text resources for the monitored subject to watch or read, and then record the corresponding attention parameter values ​​as a baseline. This approach lacks variability, consumes significant network communication resources, and suffers from poor repeatability. Attentional state monitoring systems require a simple and reproducible method to establish an attention baseline for effective monitoring. Summary of the Invention

[0004] In order to address the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide an EEG-based attention monitoring method, system and device.

[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a method for monitoring attention based on EEG, the method comprising the following steps:

[0006] Obtaining raw EEG data, performing passband filtering and notch filtering on the raw EEG data to filter out environmental noise, and obtaining denoised EEG data; performing α, β, and θ filtering on the denoised EEG data, and calculating the α, β, and θ frequency band powers to obtain α, β, and θ frequency band power data, wherein the raw EEG data has a timestamp;

[0007] The α, β, and θ frequency band power data are processed for attention initialization to obtain the baseline values ​​of each terminal user's attention parameter EI and α wave desynchronization parameter ASD; the EI parameter and ASD parameter are normalized relative to the baseline value to obtain the effective attention parameter value, thereby realizing attention monitoring.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the process of acquiring the raw EEG data includes:

[0009] The brain's electrical activity signals are collected by placing electrodes on the scalp. They need to be placed in locations with strong alpha, beta, and theta wave activity, including frontal and parietal electrode areas. Each electrode is connected to an EEG amplifier via a wire for signal amplification. The amplified EEG signal is collected and stored by a computer or recording device. The EEG signal is collected continuously at high frequency with a preset number of sampling points per second. The sampling process is time-stamped by the system to obtain time-stamped raw EEG data.

[0010] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the process of performing passband filtering and notch filtering on the raw EEG data with the timestamp:

[0011] Use infinite impulse response IIR filter for filtering. Let the input signal be x[n] and the output signal be y[n]. The filter formula is:

[0012]

[0013] where b k is the feedforward coefficient of the non-recursive part, a m is the feedback coefficient of the recursive part, M and N are the number of feedforward and feedback coefficients, respectively.

[0014] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: performing α, β, and θ filtering on the denoised EEG data, and calculating the α, β, and θ frequency band powers, wherein the calculation process follows the following formula:

[0015]

[0016] Where N is the moving average window size, x[nk] is the signal value of the corresponding brain wave at time point nk, and the calculation process of the α, β, and θ frequency band power follows the above formula.

[0017] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the process of performing attention initialization processing on the data to be monitored includes: an image feedback process, a sound feedback process, and an event synchronization process;

[0018] The image feedback process changes the parameters of the graphics generation function by calculating the changes in the EI parameters and the ASD parameters, generating different forms of patterns that change between randomness and order, thereby attracting attention. The sound feedback process uses a music programming language to generate sound feedback and provides sound feedback interactive capabilities. The event synchronization process synchronizes external audio and video files by providing timestamps to the outside.

[0019] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: an attention initialization process of the image feedback process is as follows:

[0020] After generating the pattern, the attention parameters are calculated and stored, the maximum value of the attention parameters is selected as the initial benchmark, the data is normalized with the initial benchmark, and an attention competition is conducted, and the maximum value is reselected as the final benchmark.

[0021] In conjunction with the first aspect, in certain implementations of the first aspect, the method further includes: a process of the attention competition is as follows:

[0022] A pattern consisting of line outlines will appear within the preset parameter range of the generated pattern. By focusing attention on the image, the line outline pattern will be maintained. The attention parameter is calculated based on the initial value benchmark. If the parameter is higher than the overall preset average, the line outline pattern will be maintained, while if it is lower than the overall average, the line outline pattern will disappear. The maximum attention value obtained during the competition will become the final attention benchmark.

[0023] The calculation process of pattern generation is as follows:

[0024] Reference rotation function: reference angular frequency ω, rotation function e jωt ;

[0025] Amplitude modulation function:

[0026] Given a time range t, the generating function f(ωt)=A(ωt)e jωt

[0027] Graph drawing: Given a time range t, calculate the function f(ωt), and draw a graph with the real part of the function f(ωt) as the x-coordinate and the imaginary part as the y-coordinate;

[0028] Adjustable parameters: ω,k i Slow change effect: fixed ω, adjusted k i ; In the adjustment parameter k i When , the new amplitude value is imported through the queue to obtain the slow change effect.

[0029] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: a calculation formula for the attention parameter EI is as follows:

[0030]

[0031] Where β and θ represent the frequency band power of β wave and θ wave, respectively.

[0032] The calculation process of the alpha wave desynchronization parameter ASD is as follows:

[0033]

[0034] Among them, α 基准 is the alpha wave band power in the baseline state, α 任务 is the alpha wave band power in the task state.

[0035] In a second aspect, in order to achieve the above-mentioned purpose, the present invention discloses an EEG-based attention monitoring system, comprising:

[0036] A filtering calculation module obtains raw EEG data, performs passband filtering and notch filtering on the raw EEG data to filter out environmental noise, and obtains denoised EEG data; performs α, β, and θ filtering on the denoised EEG data, and calculates the α, β, and θ frequency band power to obtain α, β, and θ frequency band power data, wherein the raw EEG data is timestamped;

[0037] The attention monitoring module performs attention initialization processing on the α, β, and θ frequency band power data to obtain the baseline values ​​of each terminal user's attention parameter EI and α wave desynchronization parameter ASD; the EI parameter and ASD parameter are normalized relative to the baseline value to obtain the effective attention parameter value to realize attention monitoring.

[0038] In another aspect of the present invention, in order to achieve the above-mentioned purpose, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, it adopts the above-mentioned EEG-based attention monitoring method.

[0039] Beneficial effects of the present invention:

[0040] This invention can directly generate mathematically aesthetic, yet variable and unpredictable patterns using simple mathematical formulas, completing the initialization of the attention baseline value, thereby forming an effective attention monitoring system. Compared with existing technologies, it does not require additional video and image resources, does not increase network communication load, and has good consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0042] Figure 1 It is a schematic flow chart of the method of the present invention;

[0043] Figure 2 is the attention initialization flow chart of the present invention;

[0044] Figure 3 It is a pattern effect diagram of the present invention;

[0045] Figure 4 Schematic diagram of the attention baseline values ​​obtained under different batches of the present invention;

[0046] Figure 5 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0048] Example 1:

[0049] like Figure 1 As shown, a method for monitoring attention based on EEG includes the following steps:

[0050] S101: Obtain raw EEG data, add a timestamp to the raw EEG data, and obtain the raw EEG data with the timestamp. In this embodiment, the data is published to a communication agent via a local area network; the raw EEG data is subscribed from the communication agent, the raw EEG data is subjected to passband filtering and notch filtering for denoising, and the denoised EEG data is subjected to α, β, and θ filtering;

[0051] Specifically, IIR filtering is also used to select appropriate filtering parameters to perform passband filtering on the corresponding bands, and the α, β, and θ band powers are calculated;

[0052] The process of acquiring raw EEG data includes: collecting brain electrical activity signals by placing electrodes on the scalp, usually placed in locations with relatively strong alpha, beta, and theta wave activity, such as the frontal and parietal electrode areas. Each electrode is connected to an EEG amplifier via a wire for signal amplification, and the amplified EEG signal is collected and stored by a computer or recording device. EEG signals can be collected continuously, usually at a high frequency of 200 to 1000 sampling points per second to ensure signal accuracy. The sampling process obtains time-stamped raw EEG data by the system affixing a timestamp.

[0053] The process of performing passband filtering and notch filtering on the raw EEG data is as follows: IIR (Infinite Impulse Response) filter is used for filtering. Assuming the input signal is x[n] and the output signal is y[n], the filter formula is:

[0054]

[0055] where b k is the feedforward coefficient (non-recursive part), usually related to the filter's x[n]; a m is the feedback coefficient (recursive part, usually related to the output signal y[n] of the filter; M and N are the number of feedforward and feedback coefficients, respectively.

[0056] As long as the appropriate b k and a m It is also possible to implement passband and notch filtering at once. An example is:

[0057] a m =[1,-5.23226662,13.1412423,-21.3162115,24.68953123,-21.07860679,

[0058] 13.36043405,-6.1932289,1.98264742,-0.39154442,0.03825309]

[0059] b k =[0.03137679,-0.01939192,-0.09413036,0.07756769,0.06275358,

[0060] -0.11635153,0.06275358,0.07756769,-0.09413036,-0.01939192,0.03137679]

[0061] The calculation process of the α, β, and θ band powers is as follows:

[0062]

[0063] Where N is the moving average window size, and x[nk] is the signal value of the corresponding EEG wave at time point nk. The calculation process of α, β, and θ frequency band power all follows the above formula.

[0064] S102: In this embodiment, the α, β, and θ band power data are subscribed to the communication agent to initiate an attention initialization process. First, the subscribed data undergoes a first-stage attention initialization process to obtain initial baseline values ​​for each terminal user's attention parameter, EI, and α wave desynchronization parameter, ASD. After the first-stage initialization process is complete, the attention detection module normalizes each terminal's EI and ASD parameters based on their respective initial baseline values. An attention competition game is then conducted to obtain and save the final baseline values ​​for EI and ASD. The initialization process concludes, and subsequent attention monitoring will utilize the final baseline values ​​for normalization.

[0065] The process of attention initialization processing includes: image feedback process, sound feedback process and event synchronization process;

[0066] The image feedback process changes the parameters of the graphics generation function by calculating the changes in the EI parameters and the ASD parameters, generating different forms of patterns that vary between random and ordered. This graphics generation method is simple to calculate and novel in form, can effectively attract the user's attention, and complete the initialization of the attention parameters.

[0067] The sound feedback process uses a music programming language to generate sound feedback and provides interactive sound feedback capabilities. The event synchronization process synchronizes external audio and video files by providing timestamps to the outside, providing a convenient interface for multimodal data collaboration and data set accumulation.

[0068] The first stage of attention initialization process is as follows:

[0069] By allowing users to observe randomly generated patterns to enter a relatively focused attention state, the absolute value of the attention parameter is calculated and stored, the maximum value of the attention parameter is selected as the initial benchmark, the data is normalized based on the initial benchmark, and an attention competition is conducted.

[0070] The process of the attention competition is as follows:

[0071] A pattern consisting of line outlines will appear within the preset parameter range of the generated pattern. By focusing attention on the image, the line outline pattern will be maintained. The attention parameter is calculated based on the initial value benchmark. If the parameter is higher than the overall preset average, the line outline pattern will be maintained, while if it is lower than the overall average, the line outline pattern will disappear. The maximum attention value obtained during the competition will become the final attention benchmark.

[0072] The calculation process of pattern generation is as follows:

[0073] Reference rotation function: reference angular frequency ω, rotation function e jωt ;

[0074] Amplitude modulation function:

[0075]

[0076] Given a time range t, the generating function f(ωt)=A(ωt)e jωt

[0077] Graph drawing: Given a time range t, calculate the function f(ωt), and draw a graph with the real part of the function f(ωt) as the x-coordinate and the imaginary part as the y-coordinate;

[0078] Adjustable parameters: ω,k i Slow change effect: fixed ω, adjusted k i ; In the adjustment parameter k i When the new amplitude value is imported by queue, the slow change effect is obtained. Usually the parameter k i At least one of them must be an irrational number, such as the natural number e, pi, or other irrational numbers.

[0079] The calculation formula of the attention parameter EI is as follows:

[0080]

[0081] Where β and θ represent the frequency band power of β wave and θ wave, respectively.

[0082] The calculation process of the alpha wave desynchronization parameter ASD is as follows:

[0083]

[0084] Among them, α 基准 is the alpha wave band power in the baseline state, α 任务 is the alpha wave band power in the task state.

[0085] Specifically, alpha wave desynchronization—a decrease in alpha wave (8–13 Hz) activity—is observed when a person is focused on a task or thinking. Alpha waves are typically associated with states of relaxation, such as resting with eyes closed, and are often reduced or desynchronized when the brain is highly engaged, a characteristic of ASD.

[0086] Both ASD and EI parameters reflect brain engagement, but they focus on different aspects:

[0087] ASD parameters focus on a decrease in alpha wave power, which typically occurs when the brain is engaged in cognitive tasks or focusing attention. A decrease in alpha waves often indicates that an individual is engaging in an active mental state.

[0088] The EI metric focuses on the relative balance of beta and theta waves. Beta waves indicate alertness and active thinking, while theta waves are often associated with relaxation, light meditation, or lack of concentration. Increased EI values ​​often indicate increased focus or cognitive load.

[0089] Both ASD parameters and EI parameters are related to individuals. The relative changes in the parameters can reflect the changes in the individual's brain state, but the absolute values ​​depend on the individual situation and vary greatly.

[0090] Specifically, the present invention is further described below through examples:

[0091] like Figure 3 As shown, at a specific reference angular frequency ω, the formula For n = 2, k1 = 2k2 = kπ. The function generates patterns for k values ​​of 3.12, 3.13, 3.14, 3.142, 3.15, and 3.16. It can be seen that the pattern is linear only within a very small range; in all other cases, a two-dimensional dot matrix pattern with mathematical beauty is generated. During the attention initialization phase, the end user first observes the changes in the generated pattern to establish an initial attention baseline. This baseline is then used to calculate the attention parameter before entering the game competition phase. During the competition phase, the end user must focus their attention on the pattern as closely as possible. Those with an attention parameter above the group average will see a linear pattern, while those below the average will see a two-dimensional dot matrix pattern. Games are a dynamic equilibrium state, characterized by unpredictability, which increases interest. The goal in the second phase is to maximize the attention baseline.

[0092] The existing technology usually uses stored video resources or picture resources to allow the end user to observe and enter a focused state, but the repeatability obtained thereby is not good. The attention baseline value generated in the first initialization stage of the present invention can be comparable to the existing technology level. The advantage is that there is no need to store additional resources, and flexible and diverse patterns can be generated using simple formulas. The entire initialization process of the present invention combines the first step initialization process and the process of the attention competition. Through the interactive feedback brought by the attention competition, the repeatability and stability of the attention baseline parameters are significantly improved. Figure 4 The EI parameter baseline values ​​for attention are shown for viewing images alone, viewing videos alone, and after executing the full initialization process. It can be seen that the initialization process significantly improves the repeatability and stability of the baseline values. Please note that the EI parameter is a ratio, without units, and its absolute value is meaningless; only relative trends are meaningful. Therefore, selecting a good baseline value is crucial for effectively monitoring attention. Table 1 below shows the EI baseline values ​​for executing the initialization process, viewing videos, and viewing images. It can be seen that the linear initialization process minimizes the standard deviation, thereby improving the stability of the baseline value.

[0093] Table 1 Mean and standard deviation of EI benchmark values ​​generated by each method

[0094]

[0095] Example 2: The second aspect, as Figure 5 As shown, in order to achieve the above purpose, the present invention discloses an EEG-based attention monitoring system, comprising:

[0096] The filtering calculation module 11 obtains the original EEG data, performs passband filtering and notch filtering on the original EEG data to filter out environmental noise, and obtains denoised EEG data; performs α, β, and θ filtering on the denoised EEG data, and calculates the α, β, and θ frequency band power to obtain α, β, and θ frequency band power data, wherein the original EEG data is timestamped;

[0097] The attention monitoring module 12 performs attention initialization processing on the α, β, and θ frequency band power data to obtain the baseline values ​​of the attention parameter EI and the α wave desynchronization parameter ASD of each terminal user; the EI parameter and the ASD parameter are normalized relative to the baseline value to obtain the effective attention parameter value to realize attention monitoring.

[0098] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0099] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium having a computer program stored thereon, which executes the above method when executed by a processor. The storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0100] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0101] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present disclosure. Various changes and improvements may be made to the present disclosure without departing from the spirit and scope of the present disclosure, and such changes and improvements shall fall within the scope of the present disclosure.

Claims

1. A method for monitoring attention based on EEG, characterized in that: The method comprises the following steps: Obtaining raw EEG data, performing passband filtering and notch filtering on the raw EEG data to filter out environmental noise, and obtaining denoised EEG data; performing α, β, and θ filtering on the denoised EEG data, and calculating the α, β, and θ frequency band powers to obtain α, β, and θ frequency band power data, wherein the raw EEG data has a timestamp; The α, β, and θ frequency band power data are processed for attention initialization to obtain the baseline values ​​of each terminal user's attention parameter EI and α wave desynchronization parameter ASD; the EI and ASD parameters are normalized relative to the baseline values ​​to obtain the effective attention parameter value, thereby realizing attention monitoring; Performing a first-stage attention initialization on the α, β, and θ frequency band power data to obtain initial baseline values ​​for the attention parameter EI and the α wave desynchronization parameter ASD; wherein, after generating the pattern, the attention parameter and the α wave desynchronization parameter are calculated and stored, and the maximum value of the attention parameter and the maximum value of the α wave desynchronization parameter are selected as the initial baseline; After the initialization process of the first stage is completed, the attention detection module will normalize the calculation of the EI and ASD parameters of each terminal based on their respective initial baseline values, and then conduct an attention competition to obtain and save the final baseline values ​​of EI and ASD. After the initialization process is completed, subsequent attention monitoring will use the final baseline values ​​for normalization calculation; The attention initialization process includes: an image feedback process, wherein the image feedback process changes the parameters of the graphic generation function by calculating the changes of the EI parameter and the ASD parameter, thereby generating different forms of patterns that change between randomness and order, thereby attracting attention; The process of the attention competition is as follows: A pattern consisting of line outlines will appear within the preset parameter range of the generated pattern. By focusing attention on the image, the line outline pattern will be maintained. The attention parameter is calculated based on the initial benchmark. If the parameter is higher than the overall preset average, the line outline pattern will be maintained, while if it is lower than the overall average, the line outline pattern will disappear. The maximum attention value obtained during the competition will become the final attention benchmark. The calculation formula of the attention parameter EI is as follows: In the formula, β and θ represent the frequency band power of β wave and θ wave respectively; The calculation process of the alpha wave desynchronization parameter ASD is as follows: Among them, α 基准 is the alpha wave band power in the baseline state, α 任务 is the alpha wave band power in the task state.

2. The method for monitoring attention based on EEG according to claim 1, characterized in that: The process of obtaining the raw EEG data includes: The brain's electrical activity signals are collected by placing electrodes on the scalp. They need to be placed in locations with strong alpha, beta, and theta wave activity, including frontal and parietal electrode areas. Each electrode is connected to an EEG amplifier via a wire for signal amplification. The amplified EEG signal is collected and stored by a computer or recording device. The EEG signal is collected continuously at high frequency with a preset number of sampling points per second. The sampling process is time-stamped by the system to obtain time-stamped raw EEG data.

3. The method for monitoring attention based on EEG according to claim 1, characterized in that: The process of performing passband filtering and notch filtering on the raw EEG data: Use infinite impulse response IIR filter for filtering. Let the input signal be x[n] and the output signal be y[n]. The filter formula is: where b k is the feedforward coefficient of the non-recursive part, a m is the feedback coefficient of the recursive part, M and N are the number of feedforward and feedback coefficients, respectively.

4. The method for monitoring attention based on EEG according to claim 1, characterized in that: The denoised EEG data is subjected to α, β, and θ filtering, and the α, β, and θ frequency band powers are calculated. The calculation process follows the following formula: Where N is the moving average window size, x[nk] is the signal value of the corresponding brain wave at time point nk, and the calculation process of the α, β, and θ frequency band power follows the above formula.

5. The method for monitoring attention based on EEG according to claim 1, characterized in that: The process of performing attention initialization processing on the α, β, and θ frequency band power data further includes: a sound feedback process and an event synchronization process; The sound feedback process generates sound feedback using a music programming language to provide interactive sound feedback capabilities, and the event synchronization process synchronizes external audio and video files by providing timestamps to the outside.

6. The method for monitoring attention based on EEG according to claim 1, characterized in that: The calculation process for generating the pattern is as follows: Reference rotation function: reference angular frequency ω, rotation function e jωt ; Amplitude modulation function: Given a time range t, the generating function f(ωt)=A(ωt)e jωt ; Graph drawing: Given a time range t, calculate the function f(ωt), and draw a graph with the real part of the function f(ωt) as the x-coordinate and the imaginary part as the y-coordinate; Adjustable parameters: ω,k i Slow change effect: fixed ω, adjusted k i ; In the adjustment parameter k i When , the new amplitude value is imported through the queue to obtain the slow change effect.

7. An EEG-based attention monitoring system, characterized in that: include: The filtering calculation module obtains the original EEG data, performs passband filtering and notch filtering on the original EEG data to filter out environmental noise, and obtains the denoised EEG data; Performing α, β, and θ filtering on the denoised EEG data, and calculating the α, β, and θ frequency band power to obtain α, β, and θ frequency band power data, wherein the original EEG data has a timestamp; The attention monitoring module performs attention initialization processing on the α, β, and θ frequency band power data to obtain the baseline values ​​of each terminal user's attention parameter EI and α wave desynchronization parameter ASD; the EI parameter and ASD parameter are normalized relative to the baseline value to obtain the effective attention parameter value to realize attention monitoring; Performing a first-stage attention initialization on the α, β, and θ frequency band power data to obtain initial baseline values ​​for the attention parameter EI and the α wave desynchronization parameter ASD; wherein, after generating the pattern, the attention parameter and the α wave desynchronization parameter are calculated and stored, and the maximum value of the attention parameter and the maximum value of the α wave desynchronization parameter are selected as the initial baseline; After the initialization process of the first stage is completed, the attention detection module will normalize the calculation of the EI and ASD parameters of each terminal based on their respective initial baseline values, and then conduct an attention competition to obtain and save the final baseline values ​​of EI and ASD. After the initialization process is completed, subsequent attention monitoring will use the final baseline values ​​for normalization calculation; The attention initialization process includes: an image feedback process, wherein the image feedback process changes the parameters of the graphic generation function by calculating the changes of the EI parameter and the ASD parameter, thereby generating different forms of patterns that change between randomness and order, thereby attracting attention; The process of the attention competition is as follows: A pattern consisting of line outlines will appear within the preset parameter range of the generated pattern. By focusing attention on the image, the line outline pattern will be maintained. The attention parameter is calculated based on the initial benchmark. If the parameter is higher than the overall preset average, the line outline pattern will be maintained, while if it is lower than the overall average, the line outline pattern will disappear. The maximum attention value obtained during the competition will become the final attention benchmark. The calculation formula of the attention parameter EI is as follows: In the formula, β and θ represent the frequency band power of β wave and θ wave respectively; The calculation process of the alpha wave desynchronization parameter ASD is as follows: Among them, α 基准 is the alpha wave band power in the baseline state, α 任务 is the alpha wave band power in the task state.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: The memory stores a computer program that can be run on the processor. When the processor loads and executes the computer program, it adopts an EEG-based attention monitoring method according to any one of claims 1 to 6.

Images