Visual cognition training method based on electroencephalogram signal neural feedback

Abstract

The invention belongs to the technical field of visual cognition training, and discloses a visual cognition training method based on electroencephalogram signal neural feedback. Comprising the steps that a computer presents a visual cognition training task, and an electroencephalogram signal collecting device synchronously collects electroencephalogram signals of a user and transmits the electroencephalogram signals to the computer in a data stream mode; the computer extracts electroencephalogram signal features according to the electroencephalogram signal when the user executes the training task, and calculates the ratio of an electroencephalogram signal feature value to an individualized electroencephalogram signal feature reference value; according to a comparison result of the ratio and a preset threshold value, the comparison result is presented in the computer screen in the form of a bar-shaped indicator and a character and is fed back to a user; and adjusting the difficulty of the training task in the next training section according to a comparison result of an average value of the ratio in a certain training section and a preset threshold value. By combining the electroencephalogram signal neural feedback technology and the traditional cognitive training method, the brain response adjustment of the user and the enhancement of the visual cognitive ability are synchronously realized.

Description

Technical Field

[0001] The present invention relates to the technical field of visual cognition training, and in particular to a visual cognition training method based on electroencephalogram signal neural feedback. Background Art

[0002] Practitioners in many industries not only have extraordinary winning abilities and professional skills, but also need to reach a high level of perception and cognition. Cognitive level is a key dimension to measure learning ability and evaluate development potential. How to train cognitive ability is one of the hot topics that cognitive researchers are concerned about. With the rapid development of computer technology, the main presentation form of cognitive training has transitioned from paper-and-pencil tasks to computerized tasks, and the training method is mainly based on specific task-based training.

[0003] In recent years, neurofeedback technology has been considered as one of the effective means to improve cognitive ability. Neurofeedback is a new form of biofeedback. This technology converts the extracted specific brain neural activities into different forms of feedback signals and provides them to the subjects through a closed-loop brain-computer interface. The subjects can realize autonomous regulation of the brain-related neural activities according to the real-time changes of the feedback signals. Combining EEG neurofeedback technology with traditional cognitive training methods can synchronously achieve multi-dimensional regulation of brain state and cognitive ability level, and improve the efficiency of cognitive training.

[0004] At present, visual cognitive training is still mainly based on traditional methods based on repetitive task training, and lacks the combination with new cognitive ability level assessment and enhancement methods. In addition, the current neurofeedback technology is mainly used to regulate the brain response in the resting state, and lacks research on the corresponding regulation effect of the brain in the task-induced state, as well as related research on visual cognitive training methods combined with EEG. Summary of the invention

[0005] The present invention provides a visual cognition training method based on EEG signal neural feedback, which can simultaneously improve the user's visual cognition level and regulate the user's brain activity state through training. In addition, the brain regulation method gradually mastered by the user can keep him in a more active and excited state during the training process, thereby helping to improve the efficiency of visual cognition training.

[0006] The technical solution adopted by the present invention is as follows: a visual cognition training method based on EEG signal neural feedback, comprising:

[0007] The computer presents a visual cognition training task, which is divided into a test part and a formal training part. At the same time, the EEG signal acquisition device synchronously acquires the EEG signals of the user during the training task, and transmits the acquired EEG signals to the computer in the form of a data stream;

[0008] Obtain individualized EEG signal feature baseline values ​​based on the visual cognitive training tasks in the test part;

[0009] In the formal training part, the computer extracts EEG signal features according to the EEG signals of the user when performing the visual cognition training task, and calculates the ratio of the EEG signal feature value to the individualized EEG signal feature reference value;

[0010] According to the comparison result between the ratio and the preset threshold value, the ratio is presented on the computer screen in the form of a bar indicator and text to be fed back to the user, thereby realizing a closed loop of EEG signal collection, processing and feedback presentation.

[0011] The preset threshold is divided into an upper threshold and a lower threshold. The upper threshold is set to 1.2, and the lower threshold is set to 0.8.

[0012] The test part includes no less than five test task modules; the training part includes no less than three training task sections, and each training task section includes no less than fifteen training task modules.

[0013] The average value of the EEG signal features corresponding to the test task modules included in the test part serves as the individualized EEG signal feature benchmark value of the user in the current training.

[0014] The computer extracts EEG features according to the EEG signals of the user when performing the visual cognition training task, and calculates the ratio of the EEG signal feature value to the individualized EEG signal feature reference value, specifically including:

[0015] The computer intercepts the EEG signal data segment corresponding to the user's performance of the visual cognitive training task from the EEG signal data stream according to the timestamp, pre-processes the EEG signal data segment, and extracts the EEG signal features related to concentration, namely, the β-band relative power of the electrode channel in the parietal lobe area, and the β-band relative power is the ratio of the β-band power to the 1-30 Hz wide-band power.

[0016] After the user completes a training task module, the computer calculates the ratio of the EEG signal characteristics corresponding to the training task module to the individualized EEG signal characteristic baseline value, and presents the ratio in the form of a bar indicator on the screen of the computer; the ratio is compared with a preset threshold, and text feedback is presented on the screen of the computer based on the comparison result.

[0017] The text feedback is set as follows: if the ratio is lower than a preset lower threshold, negative feedback is presented in text form on the screen; if the ratio is higher than a preset upper threshold, positive feedback is presented in text form on the screen; if the ratio is between the upper and lower limits of the preset threshold, neutral feedback is presented in text form on the screen.

[0018] Each time the user completes a training task section, the difficulty of the training task in the next training task section is adjusted according to the comparison result of the average value of the ratio in a certain training task section and a preset threshold.

[0019] Each time the user completes a training task section, if the average value of the ratio in a certain training task section is lower than the lower limit of the threshold, the task difficulty of the next training section will be reduced; if the average value is higher than the upper limit of the threshold, the task difficulty of the next training section will be increased; if the average value is between the upper and lower limits of the threshold, the difficulty of the current training task will be maintained.

[0020] Beneficial effects of the present invention:

[0021] First, by integrating neurofeedback technology, the present invention enables the computer to decode in real time the brain feature indicators of the user when performing visual cognitive training tasks, and present the decoded features in a visual form on the screen, so that the user can intuitively perceive the state of his or her own brain activity, thereby establishing a real-time connection between brain activity and external feedback, and effectively improving the interactivity and immediacy of the training process.

[0022] Second, the present invention uses EEG technology to extract physiological characteristic indicators that are highly related to user concentration, namely the relative power of the β band, and uses it as the core training parameter. During the training process, the system presents the changing trend of this indicator through a visual interface, allowing users to accurately grasp their own concentration state, and actively adjust the positive growth of the characteristic value to achieve the improvement of brain concentration.

[0023] Third, the present invention can be used in the visual cognitive ability training of ball game players and e-sports players. The method described in this article can enable the trained users to maintain a higher level of concentration and mental activity when performing visual cognitive tasks, thereby improving the users' visual cognitive abilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1An overall flow chart of a visual cognition training method based on EEG signal neural feedback provided by an embodiment of the present invention, including the overall division of training and the general flow of each component of training;

[0026] Figure 2 It is a module-level flow chart of the training scheme of the present invention, showing the detailed process between the modules in the training and the calculation and presentation method of the EEG signal feature feedback;

[0027] Figure 3 It is a training task subsection-level flow chart of the training program described in the present invention, showing the detailed process between each training task subsection in the training and the specific adjustment plan of the task difficulty of the training task subsection. DETAILED DESCRIPTION

[0028] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0029] To facilitate understanding of the embodiments of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0030] It should be noted that the following embodiments and features in the embodiments may be combined with each other in the absence of conflict; and, based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making any creative work are within the scope of protection of the present disclosure.

[0031] In general, the visual cognition training method based on EEG signal neurofeedback proposed by the present invention is generally divided into a test part and a formal training part, wherein the formal training part is further divided into three training task sections;

[0032] The test section includes five training task modules in total; each training task section includes fifteen training task modules;

[0033] While the user is performing a series of visual cognitive training tasks presented by the computer, the EEG signal acquisition device worn by the user synchronously acquires the user's EEG signals and transmits the EEG signals to the computer in the form of a data stream;

[0034] The computer performs data preprocessing on the received EEG signal data stream, and extracts the required EEG signal features, namely, the relative β-band power of the electrode channel in the parietal lobe area, from the preprocessed data;

[0035] In the test part, the average values ​​of the user's EEG signal features corresponding to the five training task modules are regarded as the user's individualized baseline value in this visual cognition training, which represents the user's brain concentration state at the beginning of the training;

[0036] In any of the training task subsections of the formal training part, after the user completes any of the training task modules, the EEG signal features extracted by the computer are compared with the individualized reference values, and the ratio of the two is presented in the form of a bar indicator on the screen of the computer;

[0037] The EEG signal characteristic ratio also needs to be compared with a preset threshold value to judge the adjustment of the current user's brain state. Specifically, if the EEG signal characteristic ratio is higher than the preset upper threshold value, it is considered that the user's brain concentration has improved, and positive feedback is presented in the form of text in the computer; if the EEG signal characteristic ratio is lower than the preset lower threshold value, it is considered that the user's brain concentration has decreased, and negative feedback is presented in the form of text in the computer; if the EEG signal characteristic ratio is between the lower and upper limits of the preset threshold value, it is considered that the user's brain concentration has not changed significantly, and neutral feedback is presented in the form of text in the computer;

[0038] The user gradually learns to adjust the brain state to improve the brain concentration according to the characteristic ratio of the electroencephalogram signal presented in visual feedback form in the computer and the text feedback;

[0039] At the same time, users improve their visual cognitive ability through repetitive training based on visual cognitive tasks;

[0040] In addition, the average value of the EEG signal features in any of the training task sections is regarded as an average representation of the user's brain concentration state in the training task section, which is used to compare with the individualized EEG feature baseline value and adjust the training task difficulty of the next training task section.

[0041] The overall flow chart of a visual cognition training method based on EEG signal neural feedback provided by an embodiment of the present invention is as follows: Figure 1 As shown, the following steps are included:

[0042] The first step is that before the training begins, the user needs to wear the EEG signal acquisition device and correctly connect the EEG signal acquisition device to the computer;

[0043] The second step is to start training. The user first completes the test part of the training. The computer counts the EEG signal characteristics of the user in the test part and constructs the individualized EEG signal characteristic benchmark value for this training. The specific steps include the following:

[0044] 2.1) The user completes the five modules of visual cognition training tasks included in the test part;

[0045] 2.2) The computer intercepts the EEG signal data segments corresponding to the five module tasks according to the timestamps; the data segments are preprocessed, including 50 Hz notch filtering and 1-30 Hz bandpass filtering;

[0046] 2.3) The computer calculates the power density spectrum of the EEG data corresponding to the electrode channel in the parietal region; calculates the power of the β (13-30 Hz) frequency band and the power of the 1-30 Hz frequency band; calculates the ratio of the β frequency band power to the 1-30 Hz frequency band power to obtain the key EEG signal feature: the relative power of the β frequency band; the β rhythm is generally believed to be highly correlated with the concentration state of the brain and is a key indicator for evaluating the concentration of the brain in the present invention;

[0047] 2.4) The average value of the EEG signal characteristics of the statistical test part of users is the individualized EEG signal characteristic benchmark value of the user in this training.

[0048] In the third step, when the user performs the training tasks in the formal training part, each time the user completes a task module, the computer calculates the EEG signal characteristics corresponding to the user's execution of the module, and gives the user text and graphic feedback based on the comparison result of the characteristic value with the individual EEG signal characteristic benchmark value, including the following: Figure 2 Steps shown:

[0049] 3.1) The user completes the training task of any module in the formal training part;

[0050] 3.2) The computer intercepts the EEG signal data segment corresponding to the module training task according to the timestamp; performs the above-mentioned preprocessing on the data segment; and extracts the above-mentioned EEG signal features from the data segment;

[0051] 3.3) Calculate the ratio of the EEG signal feature value corresponding to the module to the user's individual EEG signal feature baseline value for this training, and present the ratio on the computer screen in the form of a bar indicator, that is, provide visual feedback of the EEG signal feature to the user;

[0052] 3.4) Compare the ratio of the above EEG features to the individualized EEG feature baseline with a preset threshold, and present the corresponding text feedback on the user screen according to the comparison result. Specifically, if the ratio of the two is lower than the preset lower threshold, negative feedback is presented in text on the screen; if the ratio of the two is higher than the preset upper threshold, positive feedback is presented in text on the screen; if the ratio of the two is between the upper and lower limits of the preset threshold, neutral feedback is presented in text on the screen.

[0053] In the fourth step, when the user performs the training tasks in the formal training part, each time the user completes a training task section (including fifteen module training tasks), the computer calculates the EEG signal characteristics corresponding to the user's execution of the training task section, and adjusts the task difficulty of the next training task section based on the comparison result of the characteristic average value and the individual EEG signal characteristic benchmark value, including the following: Figure 3 Steps shown:

[0054] 4.1) The user completes the training task in any training task section of the formal training part;

[0055] 4.2) The computer intercepts the EEG signal data segment corresponding to the training task of the training task section according to the timestamp; performs the above-mentioned preprocessing on the data segment; and extracts the above-mentioned EEG signal features from the data segment;

[0056] 4.3) Calculate the ratio of the EEG signal characteristic value corresponding to the training task subsection to the user's individualized EEG signal characteristic baseline value for this training, and calculate the average value of the ratio between the two within this training task subsection;

[0057] 4.4) Compare the average value of the above-mentioned EEG signal characteristic ratio with a preset threshold value, and adjust the difficulty of the training task in the next training task section according to the comparison result. Specifically, if the average value is lower than the preset lower threshold value, the difficulty of the training task in the next training task section is reduced; if the average value is higher than the preset upper threshold value, the difficulty of the training task in the next training task section is increased; if the average value is between the upper and lower limits of the preset threshold value, the difficulty of the current training task is kept unchanged.

[0058] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A visual cognition training method based on EEG signal neural feedback, characterized in that: include: The computer presents a visual cognition training task, which is divided into a test part and a formal training part. At the same time, the EEG signal acquisition device synchronously acquires the EEG signals of the user during the training task, and transmits the acquired EEG signals to the computer in the form of a data stream; Obtain individualized EEG signal feature baseline values ​​based on the visual cognitive training tasks in the test part; In the formal training part, the computer extracts EEG signal features according to the EEG signals of the user when performing the visual cognition training task, and calculates the ratio of the EEG signal feature value to the individualized EEG signal feature reference value; According to the comparison result between the ratio and the preset threshold value, the ratio is presented on the computer screen in the form of a bar indicator and text to be fed back to the user, thereby realizing a closed loop of EEG signal collection, processing and feedback presentation.

2. The visual cognition training method based on EEG signal neural feedback according to claim 1, characterized in that: The preset threshold is divided into an upper threshold and a lower threshold. The upper threshold is set to 1.2, and the lower threshold is set to 0.

8.

3. The visual cognition training method based on EEG signal neural feedback according to claim 1, characterized in that: The test part includes no less than five test task modules; the training part includes no less than three training task sections, and each training task section includes no less than fifteen training task modules.

4. The visual cognition training method based on EEG signal neural feedback according to claim 3, characterized in that: The average value of the EEG signal features corresponding to the test task modules included in the test part serves as the individualized EEG signal feature benchmark value of the user in the current training.

5. The visual cognition training method based on EEG signal neural feedback according to any one of claims 1 to 4, characterized in that: The computer extracts EEG features according to the EEG signals of the user when performing the visual cognition training task, and calculates the ratio of the EEG signal feature value to the individualized EEG signal feature reference value, specifically including: The computer intercepts the EEG signal data segment corresponding to the user's performance of the visual cognitive training task from the EEG signal data stream according to the timestamp, pre-processes the EEG signal data segment, and extracts the EEG signal features related to concentration, namely, the β-band relative power of the electrode channel in the parietal lobe area, and the β-band relative power is the ratio of the β-band power to the 1-30 Hz wide-band power.

6. The visual cognition training method based on EEG signal neural feedback according to claim 5, characterized in that: After the user completes a training task module, the computer calculates the ratio of the EEG signal characteristics corresponding to the training task module to the individualized EEG signal characteristic baseline value, and presents the ratio in the form of a bar indicator on the screen of the computer; the ratio is compared with a preset threshold, and text feedback is presented on the screen of the computer based on the comparison result.

7. The visual cognition training method based on EEG signal neural feedback according to claim 6, characterized in that: The text feedback is set as follows: if the ratio is lower than a preset lower threshold, negative feedback is presented in text form on the screen; if the ratio is higher than a preset upper threshold, positive feedback is presented in text form on the screen; If the ratio is between the upper and lower limits of the preset threshold, neutral feedback is presented in text form on the screen.

8. The visual cognition training method based on EEG signal neural feedback according to claim 5, characterized in that: Each time the user completes a training task section, the difficulty of the training task in the next training task section is adjusted according to the comparison result of the average value of the ratio in a certain training task section and a preset threshold.

9. The visual cognition training method based on EEG signal neural feedback according to claim 8, characterized in that: Each time the user completes a training task section, if the average value of the ratio in a certain training task section is lower than the lower limit of the threshold, the task difficulty of the next training section is reduced; If the average value is higher than the upper limit of the threshold, the difficulty of the task in the next training section is increased; If the average value is between the upper and lower limits of the threshold, the difficulty of the current training task is maintained.

Images