CN-121996074-A - Electroencephalogram head loop interaction control method and device based on concentration level

CN121996074ACN 121996074 ACN121996074 ACN 121996074ACN-121996074-A

Abstract

The invention discloses an electroencephalogram head loop interaction control method and device based on concentration level, which are characterized in that multi-band electroencephalogram signals and user interaction parameters are collected, spectrum decoupling analysis is implemented to identify concentration characteristic base lines, concentration stability coefficients are derived to establish a cognitive state mapping relation, a high-response frequency band is tracked to verify, frequency band fusion analysis is implemented to form a control channel, concentration fluctuation data are collected to construct an interaction control network, multitask response analysis is implemented to identify intention switching points, cognitive load parameters are extracted to divide a low-load area and a high-load area, recovery rate is extracted in a recognition conversion process to construct an attention toughness index, an optimal trigger position is determined in the low-load area according to the attention toughness index, an electroencephalogram characteristic chain is constructed to be aligned with the concentration stability coefficients to determine a low-interference response window, a self-adaptive threshold group is set, and a redundant brain wave component is extracted by coupling identification false trigger area to execute false trigger inhibition to generate an interaction control instruction, so that teaching intervention and student cognitive state are matched accurately.

Inventors

WEI YANZHAO
SHI XUHUI
FENG YU
DENG MING
GE ZHIJIE
FU YUNFA
HUANG KAIFENG

Assignees

山西脑智科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260127

Claims (10)

1. An electroencephalogram head ring interaction control method based on concentration level is characterized by comprising the following steps: Collecting multi-band electroencephalogram signals of an electroencephalogram head ring and user interaction state parameters, performing frequency spectrum decoupling analysis on the multi-band electroencephalogram signals to identify a concentration characteristic base line, deriving an attention stability coefficient from the user interaction state parameters, and associating the concentration characteristic base line with the attention stability coefficient to establish a cognitive state mapping relation; Tracking and positioning a high-response frequency band core according to the cognitive state mapping relation, performing frequency band fusion analysis on the high-response frequency band core to form a control channel, acquiring concentration fluctuation data along the control channel, and constructing an interaction control network based on the concentration fluctuation data; Performing multi-task response analysis on the interactive control network to identify an intention switching point, extracting cognitive load parameters of the intention switching point, performing grading to generate a low-load area and a high-load area, identifying a conversion process from the high-load area to the low-load area, extracting a recovery rate, and constructing an attention toughness index based on the recovery rate; Determining an optimal trigger position in the low-load area according to the attention toughness index, extracting multi-band electroencephalogram data according to the optimal trigger position to construct an electroencephalogram characteristic chain, aligning the electroencephalogram characteristic chain with the attention stability coefficient to determine a low-interference response window, and setting a self-adaptive threshold value group in the low-interference response window; And coupling the self-adaptive threshold group with the concentration fluctuation data to identify a false triggering area, extracting a redundant brain wave component from the false triggering area, and executing false triggering inhibition on the interaction control network based on the redundant brain wave component to generate an interaction control instruction.
2. The method of claim 1, wherein performing a spectral decoupling analysis on the multi-band electroencephalogram signal identifies a concentration profile baseline, comprising: Constructing a frequency band energy spectrum based on the multi-band electroencephalogram signals; performing peak location on the band energy spectrum to extract dominant frequency components; Expanding the dominant frequency component in a time dimension to form a frequency stability track; and determining a concentration characteristic baseline according to the convergence region of the frequency stability track.
3. The method of claim 1, wherein the band fusion analysis of the high response band verification to form a control channel comprises: extracting the phase consistency of each frequency band from the high-response frequency band core; performing cross-frequency band coupling strength evaluation on the phase consistency to generate a frequency band cooperation map; Identifying a maximum synergy path in the frequency band synergy graph; and determining a control channel along the maximum cooperative path.
4. The method of claim 1, wherein said identifying a transition process of said high load region to said low load region extracts a recovery rate comprising: Extracting forehead lobe activity intensity at the boundary of the high load region and the low load region; performing instantaneous rate of change tracking on the forehead leaf activity intensity to generate an activity decay trajectory; identifying a decay inflection event from the activity decay trajectory; and calibrating the occurrence frequency of the attenuation inflection point event as a recovery rate.
5. The method of claim 1, wherein said constructing an attention toughness index based on said recovery rate comprises: Expanding the recovery rate on a frequency domain to extract recovery spectrum characteristics; performing beta wave attenuation rate tracking on the recovered spectrum characteristics to generate a memory consolidation index; Extracting a maintenance duration parameter from the memory consolidation index; and establishing an attention toughness index according to the maintenance duration parameter.
6. The method of claim 1, wherein said aligning the chain of brain wave features with the attention stabilization factor determines a low interference response window, comprising: performing gamma wave burst detection on the brain wave characteristic chain to construct a candidate event set; Evaluating the candidate event set based on the attention stability factor to generate event confidence; Screening high-credibility events from the event credibility to form an understanding event confirmation set; The time slots of the understanding event confirmation set are identified as low interference response windows.
7. The method of claim 1, wherein said coupling the adaptive threshold set with the focused fluctuation data identifies false trigger zones, comprising: setting the adaptive threshold set as a dynamic envelope boundary; performing out-of-range detection on the concentration fluctuation data based on the dynamic envelope boundary to extract out-of-range time sequences; Identifying a short-time out-of-range event in the out-of-range time sequence; And determining a false triggering area based on the short-time out-of-range event.
8. The method of claim 4, wherein said performing transient rate of change tracking of said forehead lobe activity intensity generates an activity decay trajectory comprising: Extracting asynchronous change segments from the time series of forehead leaf activity intensities; Performing energy difference value accumulation on the asynchronous change segment to obtain a cognitive overload event; generating a detuning strength based on a peak amplitude of the cognitive overload event; and forming an activity attenuation track according to the detuning intensity.
9. The method of claim 6, wherein performing gamma-ray burst detection on the chain of brain wave features constructs a set of candidate events, comprising: extracting a gamma frequency band energy mutation track from the brain wave characteristic chain; identifying rising edges and falling edges in the gamma frequency band energy mutation tracks to form an explosion envelope map; Performing duration screening on the burst envelope map to extract a time window conforming to cognitive integration characteristics; and constructing a candidate event set based on the time window conforming to the cognitive integration characteristic.
10. An electroencephalogram head ring interaction control device based on concentration level, which is characterized by comprising: The signal acquisition module is used for acquiring multi-band electroencephalogram signals of the electroencephalogram head ring and user interaction state parameters, performing frequency spectrum decoupling analysis on the multi-band electroencephalogram signals to identify a concentration characteristic base line, deriving an attention stability coefficient from the user interaction state parameters, and associating the concentration characteristic base line with the attention stability coefficient to establish a cognitive state mapping relation; The channel construction module is used for tracking and positioning a high-response frequency band core according to the cognitive state mapping relation, forming a control channel for the high-response frequency band core through frequency band fusion analysis, collecting concentration fluctuation data along the control channel, and constructing an interactive control network based on the concentration fluctuation data; The toughness evaluation module is used for executing multi-task response analysis to the interactive control network to identify an intention switching point, extracting cognitive load parameters of the intention switching point, carrying out grading to generate a low-load area and a high-load area, identifying a conversion process from the high-load area to the low-load area, extracting a recovery rate, and constructing an attention toughness index based on the recovery rate; The threshold setting module is used for determining an optimal trigger position in the low-load area according to the attention toughness index, extracting multi-band electroencephalogram data according to the optimal trigger position to construct an electroencephalogram characteristic chain, aligning the electroencephalogram characteristic chain with the attention stability coefficient to determine a low-interference response window, and setting an adaptive threshold group in the low-interference response window; the instruction generation module is used for coupling the self-adaptive threshold value group with the concentration fluctuation data to identify a false triggering area, extracting redundant brain wave components from the false triggering area, and executing false triggering inhibition on the interaction control network based on the redundant brain wave components to generate an interaction control instruction.

Description

Electroencephalogram head loop interaction control method and device based on concentration level Technical Field The invention relates to the technical field of brain-computer interface control, in particular to an electroencephalogram head loop interaction control method and device based on concentration level. Background In an intelligent educational scenario, the concentration level and cognitive load status of a student directly affect the learning effect. The traditional teaching system adopts a fixed content pushing rhythm, and is difficult to adapt to the change of the real-time cognitive state of students. Although some systems attempt to adjust teaching strategies through behavior data such as answer accuracy, response time and the like, the surface indexes have hysteresis, and the actual cognitive load state and concentration fluctuation law in the brain cannot be captured. The brain electrical signal is used as a physiological index for reflecting the brain nerve activity, and provides a technical path for monitoring the cognitive state in real time. However, the existing method faces multiple challenges of accurately identifying concentration characteristics from multi-band brain wave data and establishing a mapping relation with a cognitive state, identifying a dynamic conversion process of a cognitive load and implementing intervention at an optimal moment, and effectively inhibiting false triggering caused by physiological noise such as blinking, muscle activity and the like. There is therefore a need for a method to address at least one of the above problems. Disclosure of Invention The invention discloses a brain electrical head loop interaction control method and device based on concentration level, which are characterized in that a concentration characteristic baseline is identified through frequency spectrum decoupling analysis, a high-response frequency band core is tracked to form a control channel, an optimal trigger position is determined based on an attention toughness index, a low-interference response window is determined through alignment of a brain wave characteristic chain and an attention stability coefficient, false triggering interference is restrained to generate an interaction control instruction, and teaching intervention and student cognitive state real-time matching is realized. The invention provides an electroencephalogram head ring interaction control method based on concentration level, which comprises the following steps of: Collecting multi-band electroencephalogram signals of an electroencephalogram head ring and user interaction state parameters, performing frequency spectrum decoupling analysis on the multi-band electroencephalogram signals to identify a concentration characteristic base line, deriving an attention stability coefficient from the user interaction state parameters, and associating the concentration characteristic base line with the attention stability coefficient to establish a cognitive state mapping relation; Tracking and positioning a high-response frequency band core according to the cognitive state mapping relation, performing frequency band fusion analysis on the high-response frequency band core to form a control channel, acquiring concentration fluctuation data along the control channel, and constructing an interaction control network based on the concentration fluctuation data; Performing multi-task response analysis on the interactive control network to identify an intention switching point, extracting cognitive load parameters of the intention switching point, performing grading to generate a low-load area and a high-load area, identifying a conversion process from the high-load area to the low-load area, extracting a recovery rate, and constructing an attention toughness index based on the recovery rate; Determining an optimal trigger position in the low-load area according to the attention toughness index, extracting multi-band electroencephalogram data according to the optimal trigger position to construct an electroencephalogram characteristic chain, aligning the electroencephalogram characteristic chain with the attention stability coefficient to determine a low-interference response window, and setting a self-adaptive threshold value group in the low-interference response window; And coupling the self-adaptive threshold group with the concentration fluctuation data to identify a false triggering area, extracting a redundant brain wave component from the false triggering area, and executing false triggering inhibition on the interaction control network based on the redundant brain wave component to generate an interaction control instruction. The second aspect of the present invention proposes an electroencephalogram head ring interaction control device based on concentration level, comprising: The signal acquisition module is used for acquiring multi-band electroencephalogram signals of the electroencephalogram head ring and use