CN-121971801-A - Real-time cognitive load regulation and control method

CN121971801ACN 121971801 ACN121971801 ACN 121971801ACN-121971801-A

Abstract

The disclosure relates to a cognitive load real-time regulation and control method, a device, electronic equipment and a storage medium. The method comprises the steps of carrying out a preset high-cognition load induction experiment on a preset number of tested persons, collecting brain electrical data of the tested persons, establishing a cognition load monitoring model, identifying a high-cognition load state based on the cognition load monitoring model, generating a model identification result, outputting the model identification result to a transcranial electric stimulation control code, operating the transcranial electric stimulation control code after receiving a high-cognition load identification label, regulating and controlling transcranial direct current stimulation nerves based on the transcranial electric stimulation control code, and if the cognition load monitoring model identification result is in a low-load state, indicating that transcranial direct current stimulation regulation and control is effective. The method and the device can effectively monitor the cognitive load condition in real time, regulate and control the cognitive state in real time through transcranial electric stimulation, control the cognitive load level, and improve or maintain better operation performance.

Inventors

LI JIAXUAN
WU JINTAO
ZHANG LIJIAN
LIU HAO
LIANG JIANXING
CHANG QI
ZHAO JILONG

Assignees

北京机械设备研究所

Dates

Publication Date: 20260505
Application Date: 20251201

Claims (10)

1. The method for regulating and controlling cognitive load in real time is characterized by comprising the following steps of: carrying out a preset high cognitive load induction experiment on a preset number of tested personnel, and collecting brain electricity data of the tested personnel; establishing a cognitive load monitoring model, and identifying a high cognitive load state based on the cognitive load monitoring model to generate a model identification result; Outputting the model identification result to a transcranial electrical stimulation control code; After receiving the high cognitive load identification tag, running a transcranial electric stimulation control code; Regulating and controlling the transcranial direct current stimulation nerve based on the transcranial electric stimulation control code; and if the recognition result output of the cognitive load monitoring model is in a low-load state, indicating that transcranial direct current stimulation regulation and control play a role.
2. The method of claim 1, wherein the method further comprises: 10 testers are selected for carrying out a high cognitive load induction experiment, a simulated flight countermeasure task of 1 aircraft to be controlled and 3 aircraft to be controlled is adopted as an experiment model, the experiment is carried out circularly, and brain electrical data of the testers are collected.
3. The method of claim 1, wherein the method establishes a cognitive load monitoring model and identifies a high cognitive load state based on the cognitive load monitoring model, the generating a model identification result further comprising: The cognitive load contrast experiment and the electroencephalogram data acquisition; the subjective scoring result after the task is collected is combined with the task difficulty to carry out cognitive load level classification; preprocessing an electroencephalogram signal and calculating a power spectrum density index to obtain a training data set; Training data and performing model training and testing by using a machine learning algorithm; high cognitive load state identification.
4. The method of claim 3, wherein the preprocessing of the electroencephalogram signals in the method further comprises: And performing pre-processing of re-referencing, filtering, segmenting, interpolating bad guides, rejecting bad segments and analyzing independent components to remove artifacts on the electroencephalogram signals.
5. The method of claim 3, wherein the electroencephalogram power spectral density index calculation in the method further comprises: Calculating power spectrum densities of different frequency bands in the test time; Respectively averaging the power spectrum densities of the four frequency bands of all the test times; dividing all acquired leads into brain regions with preset quantity according to brain region dividing rules; the power spectrum densities of all the four frequency bands of the leads in each brain region are respectively averaged to obtain the required power spectrum density index; and (5) carrying out standardization or normalization treatment on the extracted features by using a Min-Max normalization method.
6. The method of claim 5, wherein calculating power spectral densities for different frequency bands within a test run in the method further comprises: Dividing a signal with a length of N into L segments, namely, N=LM, adding a hamming window w (N) to each data window, performing Fourier transformation, and calculating a power spectrum of the signal, wherein the formula is as follows: Calculating the power spectrum value of each piece of data, averaging the calculated power spectrum values, And then, estimating the power spectral density of the signal by adopting a Welch method for each segment of the all-lead epoch, and respectively averaging 4 frequency bands (delta frequency band 1-4 Hz, theta frequency band 4-8 Hz, alpha frequency band 8-13 Hz and beta frequency band 13-30 Hz).
7. The method of claim 1, wherein modulating a transcranial direct current stimulation nerve based on the transcranial electrical stimulation control code in the method further comprises: the stimulated brain area is an upper orbit forehead area, the stimulating electrodes are arranged in a mode that the anode is used as a center FP1 cathode electrode to surround, the current rises from 0 to 1.5 milliamperes during stimulation, the rising time is 15s, then the current is kept at 1.5 milliamperes for 15 minutes, and finally the current gradually becomes 0 within 15 s.
8. A device for real-time regulation and control of cognitive load, the device comprising: the electroencephalogram data acquisition module is used for carrying out a preset high cognitive load induction experiment on a preset number of tested personnel and acquiring electroencephalogram data of the tested personnel; the monitoring model building module is used for building a cognitive load monitoring model, and identifying a high cognitive load state based on the cognitive load monitoring model to generate a model identification result; The identification result output module is used for outputting the model identification result to a transcranial electric stimulation control code; the control code running module is used for running the transcranial electric stimulation control code after receiving the high cognitive load identification tag; The stimulation nerve regulation and control module is used for regulating and controlling the transcranial direct current stimulation nerve based on the transcranial electric stimulation control code; and the model result recognition module is used for indicating that transcranial direct current stimulation regulation and control play a role if the recognition result output of the cognitive load monitoring model is in a low-load state.
9. An electronic device, comprising Processor, and A memory having stored thereon computer readable instructions which, when executed by the processor, implement the method according to any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, implements the method according to any of claims 1 to 7.

Description

Real-time cognitive load regulation and control method Technical Field The disclosure relates to the field of cognitive neuroscience, and in particular relates to a method and device for regulating and controlling cognitive load in real time, electronic equipment and a computer readable storage medium. Background In the field of man-machine interaction, a common cognitive load regulation and control method is used for optimizing a man-machine interaction interface from a task, or optimizing information and complexity associated with the task, so that the cognitive load of an operator or a decision maker is reduced or improved, and the method is slow in effect and lacks of real-time performance. The transcranial direct current stimulation technology (TranscranialDirectCurrentStimulation, tDCS) is a non-invasive nerve regulation technology, and by placing electrodes on the surface of the scalp, weak direct current is applied to a specific area of the brain, and the weak direct current directly acts on neuron cell membranes to change excitability of the specific area of the brain, so that the brain nerve activity is regulated, and the functions and behaviors of the brain are influenced, so that the aim of regulating and controlling cognitive load is fulfilled. The technology is a direct physical intervention mode, a specific electric stimulation signal is input to the brain through external equipment, a visual pathway is bypassed, the brain nerve activity is directly and actively regulated, the pertinence and the instantaneity are high, the effect is generally obvious and quick, in some researches, the transcranial direct current stimulation technology can observe the alleviation of symptoms and the improvement of cognitive ability in a relatively short time in the aspect of improving the cognitive function of depression patients. Accordingly, there is a need for one or more approaches to address the above-described problems. It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art. Disclosure of Invention The present disclosure is directed to a method, apparatus, electronic device, and computer-readable storage medium for real-time regulation of cognitive load that, at least in part, overcome one or more of the problems due to the limitations and disadvantages of the related art. According to one aspect of the present disclosure, there is provided a method for real-time regulation of cognitive load, including: carrying out a preset high cognitive load induction experiment on a preset number of tested personnel, and collecting brain electricity data of the tested personnel; establishing a cognitive load monitoring model, and identifying a high cognitive load state based on the cognitive load monitoring model to generate a model identification result; Outputting the model identification result to a transcranial electrical stimulation control code; After receiving the high cognitive load identification tag, running a transcranial electric stimulation control code; Regulating and controlling the transcranial direct current stimulation nerve based on the transcranial electric stimulation control code; and if the recognition result output of the cognitive load monitoring model is in a low-load state, indicating that transcranial direct current stimulation regulation and control play a role. In an exemplary embodiment of the present disclosure, the method further comprises: 10 testers are selected for carrying out a high cognitive load induction experiment, a simulated flight countermeasure task of 1 aircraft to be controlled and 3 aircraft to be controlled is adopted as an experiment model, the experiment is carried out circularly, and brain electrical data of the testers are collected. In an exemplary embodiment of the present disclosure, the method establishes a cognitive load monitoring model, and identifies a high cognitive load state based on the cognitive load monitoring model, and generating a model identification result further includes: The cognitive load contrast experiment and the electroencephalogram data acquisition; the subjective scoring result after the task is collected is combined with the task difficulty to carry out cognitive load level classification; preprocessing an electroencephalogram signal and calculating a power spectrum density index to obtain a training data set; Training data and performing model training and testing by using a machine learning algorithm; high cognitive load state identification. In an exemplary embodiment of the present disclosure, the preprocessing of the electroencephalogram signal in the method further includes: And performing pre-processing of re-referencing, filtering, segmenting, interpolating bad guides, rejecting bad segments and analyzing indepe