Intelligent auxiliary training brain-computer system for improving attention

Abstract

The invention relates to the technical field of attention aided training, in particular to an intelligent aided training brain-computer system for improving attention, and the system comprises a data input module which is used for enabling a user to input a plurality of evaluation data of a monitoring subject; the data fitting module is used for outputting an intervention scheme according to the analysis of the evaluation data; the scheme execution module responds to the fitting result of the data fitting module and is used for executing the intervention scheme of the monitoring subject; the analysis module comprises a monitoring unit used for receiving the electroencephalogram signals of the monitored subject in real time and monitoring the completion time and accuracy of the intervention scheme, an analysis unit used for determining the qualification of the intervention scheme and determining whether the evaluation accuracy of the attention level is qualified, and a correction unit used for correcting unqualified conditions. According to the invention, the assessment accuracy of the brain-computer system on the attention level is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of attention-assisted training, and in particular to an intelligent-assisted training brain-computer system for improving attention. Background Art

[0002] Autism spectrum disorder is a common neurodevelopmental disorder in children's development. Children with these disorders often show problems such as inattention, difficulty in social communication, and abnormal behavior. These problems seriously affect children's daily life, social adaptability, and academic performance, and bring huge burdens to children and their families. If children with autism spectrum disorder can be helped to improve their attention level, many benefits can be obtained. Regarding the therapeutic intervention methods to improve attention, traditional methods have many disadvantages. For example: the teaching method is often one-way, teachers impart knowledge and skills, and children passively accept them, lacking interactivity and sense of participation. In terms of teaching content, it is often boring and difficult to stimulate students' interest and motivation. Therefore, problems such as poor learning effects, low student learning efficiency, and slow teaching progress are prone to occur.

[0003] In recent years, with the development of computer technology and neuroscience, brain-computer interface technology is gradually being widely used in auxiliary rehabilitation therapy to improve the attention of children with disorders such as autism spectrum disorders. Brain-computer interface refers to a technology that realizes human-computer interaction by converting brain neural signals into operable command signals. In terms of monitoring and evaluating children's attention, brain-computer interface technology can realize objective monitoring and quantification of attention, thereby more accurately evaluating changes in children's attention. For example, the use of brain-computer interface can record children's EEG signals and judge the children's attention state by analyzing these signals. Compared with traditional methods such as behavioral observation and questionnaire surveys, the use of brain-computer interface technology has the following advantages: (1) Higher objectivity: Brain-computer interface technology can directly record and analyze children's EEG signals, reducing factors of human interference and improving the objectivity of evaluation; (2) Short evaluation time: Brain-computer interface technology can record and analyze children's EEG signals in real time, thereby shortening the evaluation time; (3) Quantifiable: Brain-computer interface technology can convert children's EEG signals into numerical data and conduct objective quantitative evaluation, which can more accurately grasp the subtle changes in children's attention.

[0004] Chinese Patent Publication No.: CN110478593A discloses an EEG attention training system based on VR technology, which includes an EEG acquisition module, a CPU module, a data storage module, and a visual human-computer interaction module. The EEG acquisition module is used to receive a response signal sent by the single-chip microcomputer in the CPU module, and collect data after receiving the response signal, and transmit the EEG signal collected from the scalp to the host computer through serial communication. The data storage module is used to receive the collection information received by the host computer, and share the attention value in the dynamic link library. The invention can realize auxiliary rehabilitation training for patients with attention deficit, place the patient in a virtual environment, and indirectly perform auxiliary treatment on the patient in the form of exploration, which will not cause tension, anxiety and other uneasy emotions, and can provide real-time feedback on the patient's attention training situation, providing a certain reference for subsequent clinical treatment.

[0005] It can be seen that the EEG attention training system based on VR technology has the following problems: the invention collects EEG signals through serial communication to share the attention value in the dynamic link library, and places the patient in a virtual environment to indirectly provide auxiliary treatment to the patient, thereby realizing auxiliary rehabilitation training for patients with attention deficit. However, the invention lacks monitoring of the treatment process of patients with attention deficit, resulting in low accuracy in the assessment of attention level. Summary of the invention

[0006] To this end, the present invention provides an intelligent auxiliary training brain-computer system for improving attention, so as to overcome the problem in the prior art that the lack of monitoring of the auxiliary treatment process of the monitored subject leads to low accuracy in the assessment of the attention level.

[0007] To achieve the above object, the present invention provides an intelligent auxiliary training brain-computer system for improving attention, comprising:

[0008] A data input module, which is used for a user to input a number of evaluation data of a monitored subject, wherein the evaluation data includes scale data and experimental data;

[0009] a data fitting module connected to the data input module, for determining the attention level of the monitored subject based on the comparison between each of the evaluation data and the sample data in the sample database, identifying abnormal data based on the comparison result of the fit between the evaluation data and the sample data of the corresponding attention level and a preset fit, and outputting an intervention plan based on the abnormal data;

[0010] a program execution module, which is connected to the data fitting module and is used to execute the intervention program of the monitored subject in response to the fitting result of the data fitting module;

[0011] An analysis module, which is connected to the data fitting module and the solution execution module respectively, includes:

[0012] A monitoring unit, which is used to receive the EEG signal of the monitoring subject in real time to determine the attention evaluation value, and to monitor the completion time and accuracy of the intervention plan;

[0013] An analysis unit, which is used to construct an effect curve based on the completion time and the accuracy rate to determine the eligibility of the intervention plan based on a first slope of the effect curve, and to construct an evaluation value curve according to the attention evaluation value to determine whether the evaluation accuracy of the attention level is qualified based on a correlation between a second slope of the evaluation value curve and the first slope;

[0014] A correction unit, responsive to the analysis result of the analysis unit, is used to increase the preset fitness for an unqualified intervention plan and to correct the attention evaluation value under the condition that the evaluation accuracy is unqualified.

[0015] Furthermore, the data fitting module determines the mean of the fit between the evaluation data and the sample data and determines the maximum mean of the fit, determines the attention level of the sample data corresponding to the maximum mean of the fit as the attention level of the monitored subject, and determines the intervention plan corresponding to the attention level as the basic intervention plan, wherein a correspondence between the sample data, the intervention plan and the attention level is pre-set.

[0016] Furthermore, the data fitting module compares the single item data in the evaluation data with the corresponding single item sample data to obtain the degree of fit;

[0017] The single item of data is determined to be abnormal data based on a comparison result that the degree of fit is less than a preset degree of fit.

[0018] Furthermore, the data fitting module determines the intervention item corresponding to the abnormal data, and replaces the corresponding intervention item in the basic intervention plan based on the intervention item to output an intervention plan for the monitored subject, wherein the intervention plan includes several intervention items, each intervention item includes several intervention stages, and each intervention stage includes several intervention cycles.

[0019] Furthermore, the analysis unit establishes an effect curve of completion time and accuracy for the intervention cycle of any intervention stage, records the maximum slope of the effect curve as the first slope, and determines to enter the next treatment stage based on the condition that the first slope is greater than or equal to a preset threshold.

[0020] Further, the analysis unit determines that the intervention plan is unqualified based on a comparison result that the first slope is less than a first preset slope.

[0021] Further, the correction unit obtains a slope difference by subtracting the first slope from the first preset slope based on the unqualified intervention scheme.

[0022] Based on the comparison result that the slope difference is greater than the preset slope difference, determining to reduce the preset fitness by a first fitness adjustment coefficient;

[0023] Based on the comparison result that the slope difference is less than or equal to the preset slope difference, it is determined to reduce the preset fitness by a second fitness adjustment coefficient.

[0024] Furthermore, the analysis unit establishes an evaluation value curve of the intervention period and the attention evaluation value for the intervention period of any intervention stage, records the maximum slope of the evaluation value curve as the second slope, and records the ratio of the second slope to the first slope as the correlation degree.

[0025] The evaluation accuracy of the attention level is determined to be unqualified based on the comparison result that the degree of association is less than the first preset degree of association or greater than the second preset degree of association.

[0026] Further, the correction unit determines a first difference between the preset association degree and the association degree, and a second difference between the association degree and the preset association degree under the condition that the evaluation accuracy of the attention level is unqualified,

[0027] Determining to increase the attention evaluation value by a first evaluation value adjustment coefficient based on a comparison result that the first difference is greater than a first preset difference;

[0028] Based on the comparison result that the first difference is less than or equal to the first preset difference, it is determined to use a second evaluation value adjustment coefficient to increase the attention evaluation value.

[0029] Further, the correction unit determines to reduce the attention evaluation value by using a third evaluation value adjustment coefficient based on a comparison result that the second difference is greater than a second preset difference;

[0030] Based on the comparison result that the second difference is less than or equal to the second preset difference, it is determined to use a fourth evaluation value adjustment coefficient to reduce the attention evaluation value.

[0031] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention determines the attention level of the monitored subject based on the comparison between the evaluation data of the monitored subject and the sample data, and the sample data is determined based on big data, thereby improving the objectivity and accuracy of the evaluation of the attention level of the monitored subject; outputs a basic intervention plan according to the attention level, and determines abnormal data based on the comparison between the evaluation data and the sample data, adjusts the basic intervention plan in a targeted manner based on the abnormal data, and outputs a final intervention plan, thereby improving the accuracy of the intervention plan for the individual; establishes an effect curve by monitoring the completion time and accuracy of the intervention plan, and determines the eligibility of the intervention plan based on the slope of the effect curve. The larger the slope, the shorter the time for the monitored subject to complete the intervention plan, the higher the accuracy, and the better the intervention effect of the intervention plan, which also indicates that the improvement effect of the attention level of the monitored subject is better. The better the improvement effect of the attention level is, the larger the attention evaluation value is. Therefore, the evaluation accuracy of the attention level is determined based on the comparison of the slope of the effect curve with the slope of the attention evaluation value, thereby improving the evaluation benchmark of the attention level, and further improving the evaluation accuracy of the attention level.

[0032] Furthermore, the present invention determines the single item fit by comparing any data in the evaluation data with the corresponding single item data in the sample data, and determines the fit mean based on the single item fit. The larger the fit mean, the closer the attention level of the monitored subject is to the attention level corresponding to the sample data as a whole. The intervention plan corresponding to the closest sample data is used as the basic plan, and abnormal data is determined according to the fit of the single item data. The abnormal data indicates that the monitored subject has particularly serious defects in a certain aspect and requires targeted training. Therefore, the intervention items that require targeted training are replaced with the corresponding items in the basic intervention plan, and finally the intervention plan is output, which improves the output benchmark of the intervention plan for the monitored subject. The more accurate the intervention plan is, the more the attention level reflected by the monitored subject completing the intervention plan conforms to the actual level of the monitored subject, thereby further improving the accuracy of the attention level assessment.

[0033] Furthermore, the present invention evaluates the training effect based on the slope of the effect curve. The larger the slope, the shorter the time taken by the monitored subject to complete the intervention plan and the higher the accuracy rate, thereby indicating that the attention improvement effect of the monitored subject is better. When the slope is greater than or equal to the preset threshold, it indicates that the purpose of the intervention stage has been achieved and the next stage can be entered. If the slope is too small, it indicates that the attention improvement effect of the monitored subject is not good, which is due to the fact that the setting of the intervention plan does not meet the specific situation of the monitored subject. The preset fitting degree can be reduced and the evaluation benchmark of abnormal data can be improved, thereby improving the pertinence of the intervention plan of the monitored subject to better meet the individual situation of the monitored subject, thereby further improving the accuracy of the assessment of the attention level.

[0034] Furthermore, the present invention determines the accuracy of attention level assessment based on the comparison of the slopes of the effect curve and the evaluation value curve. The higher the attention level of the monitored subject, the shorter the time to complete the intervention program and the higher the accuracy rate. The attention evaluation value and the training effect are correlated to a certain extent. Too high or too low a correlation between the attention level and the training effect indicates that the accuracy of attention level assessment is unqualified, thereby making targeted adjustments to further improve the accuracy of attention level assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a structural block diagram of an intelligent auxiliary training brain-computer system for improving attention according to an embodiment of the present invention;

[0036] Figure 2 A flowchart for determining abnormal data according to an embodiment of the present invention;

[0037] Figure 3 A flow chart for determining eligibility of an intervention plan for an embodiment of the present invention;

[0038] Figure 4 A flow chart of determining whether the accuracy of the attention level assessment is qualified according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0040] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0041] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0042] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] See also Figure 1-Figure 4 As shown, Figure 1 This is a structural block diagram of an intelligent auxiliary training brain-computer system for improving attention according to an embodiment of the present invention; Figure 2 A flowchart for determining abnormal data according to an embodiment of the present invention; Figure 3 A flow chart for determining eligibility of an intervention plan for an embodiment of the present invention; Figure 4 A flow chart of determining whether the accuracy of the attention level assessment is qualified according to an embodiment of the present invention.

[0044] The embodiment of the present invention provides an intelligent auxiliary training brain-computer system for improving attention, comprising:

[0045] A data input module, which is used for a user to input a number of evaluation data of a monitored subject, wherein the evaluation data includes scale data and experimental data;

[0046] a data fitting module connected to the data input module, for determining the attention level of the monitored subject based on the comparison between each of the evaluation data and the sample data in the sample database, identifying abnormal data based on the comparison result of the fit between the evaluation data and the sample data of the corresponding attention level and a preset fit, and outputting an intervention plan based on the abnormal data;

[0047] a program execution module, which is connected to the data fitting module and is used to execute the intervention program of the monitored subject in response to the fitting result of the data fitting module;

[0048] An analysis module, which is connected to the data fitting module and the solution execution module respectively, includes:

[0049] A monitoring unit, which is used to receive the EEG signal of the monitoring subject in real time to determine the attention evaluation value, and to monitor the completion time and accuracy of the intervention plan;

[0050] An analysis unit, which is used to construct an effect curve based on the completion time and the accuracy rate to determine the eligibility of the intervention plan based on a first slope of the effect curve, and to construct an evaluation value curve according to the attention evaluation value to determine whether the evaluation accuracy of the attention level is qualified based on a correlation between a second slope of the evaluation value curve and the first slope;

[0051] A correction unit, responsive to the analysis result of the analysis unit, is used to increase the preset fitness for an unqualified intervention plan and to correct the attention evaluation value under the condition that the evaluation accuracy is unqualified.

[0052] Specifically, the scales include but are not limited to the Child Autism Rating Scale, the Autism Treatment Evaluation Form, the Autism Screening Questionnaire, the Parenting Stress Scale and the Anxiety Self-Rating Scale; the experiments include but are not limited to conducting social, language, cognitive and behavioral experiments on the monitored subjects to comprehensively evaluate the children's attention level.

[0053] Specifically, when the monitoring subject executes the intervention plan, the program execution module will change color as a correct prompt when the monitoring subject makes a correct response, and will make a sound prompt when the monitoring subject makes an incorrect response.

[0054] Specifically, brain waves have multiple frequency bands, and waves in different frequency bands represent different states of the monitored subject. The frequency range of alpha waves is 8-13Hz, which is usually associated with a wakeful and quiet state. It is the best state for learning and thinking. When the brain is in an alpha wave state, the individual usually feels calm, focused, has a good memory, and a rich imagination; the frequency range of beta waves is 13-30Hz, which is usually associated with active thinking, concentration, or anxiety. When the brain is in a beta wave state, the individual may be engaged in thinking activities and appear busy or nervous; the frequency range of theta waves is 4-8Hz, which mainly appears in light sleep, hypnosis, relaxation, meditation, dreaming, or creative states. The (α×θ) / β ratio can reflect the individual's attention level.

[0055] Specifically, the attention evaluation value is determined based on the α wave, β wave and θ wave of the EEG signal. First, a relationship model between the (α×θ) / β ratio and the attention evaluation value is established based on big data through statistical analysis methods; secondly, the monitoring unit processes the received EEG signal, including but not limited to noise removal, extracts the power of the α wave, β wave and θ wave, and compares the power product of the α wave and the θ wave with the power of the β wave to obtain the (α×θ) / β ratio; finally, the (α×θ) / β ratio is substituted into the relationship model to output the attention evaluation value.

[0056] Specifically, the effect curve and the evaluation value curve are both established in the second quadrant. The horizontal axis of the effect curve is time, the unit is minutes, and the vertical axis is the accuracy, the unit is %; the horizontal axis of the evaluation value curve is a single intervention cycle, the unit is weeks, and the vertical axis is the attention evaluation value, which has no unit.

[0057] Specifically, the data fitting module determines the mean of the fit between the evaluation data and the sample data and determines the maximum mean of the fit, determines the attention level of the sample data corresponding to the maximum mean of the fit as the attention level of the monitored subject, and determines the intervention plan corresponding to the attention level as the basic intervention plan, wherein a correspondence between the sample data, the intervention plan and the attention level is pre-set.

[0058] Specifically, the calculation method of the fit is not limited. For example, the scale data includes a number of scores, and a score scatter plot can be constructed. The fit between the scale data can be the fit between the corresponding score scatter plots;

[0059] There is no limitation on the method for determining the degree of fit between the rating scatter plots. For example, the average difference between corresponding points of two rating scatter plots may be calculated and the average difference may be determined as the degree of fit between the rating scatter plots.

[0060] Specifically, the sample data is obtained in advance, wherein the evaluation data of different monitoring subjects are obtained through big data, and the correspondence between the attention level, intervention plan and the evaluation data is synchronously constructed and stored in the sample database. The correspondence between the attention level, intervention plan and the evaluation data can be one-to-many.

[0061] Specifically, the data fitting module compares the single item data in the evaluation data with the corresponding single item sample data to calculate the degree of fit;

[0062] The single item of data is determined to be abnormal data based on a comparison result that the degree of fit is less than a preset degree of fit.

[0063] Specifically, the preset degree of fit is pre-calculated and is between 0.1 and 0.5 times the maximum degree of fit mean of the sample data corresponding to the attention level of the monitored subject. The embodiment of the present invention preferably has a maximum degree of fit of 0.3 times the mean.

[0064] Specifically, the data fitting module determines the intervention item corresponding to the abnormal data, and replaces the corresponding intervention item in the basic intervention plan based on the intervention item to output an intervention plan for the monitored subject, wherein the intervention plan includes several intervention items, each intervention item includes several intervention stages, and each intervention stage includes several intervention cycles.

[0065] Specifically, the analysis unit establishes an effect curve of completion time and accuracy for the intervention cycle of any intervention stage, records the maximum slope of the effect curve as the first slope, and determines to enter the next treatment stage based on the condition that the first slope is greater than or equal to a preset threshold.

[0066] Specifically, the value range of the preset threshold is set to [3, 6], and 4 is preferred in the embodiment of the present invention.

[0067] Specifically, the analysis unit determines that the intervention plan is unqualified based on the comparison result that the first slope is less than a first preset slope;

[0068] The analysis unit determines that the intervention plan is qualified based on a comparison result that the first slope is greater than or equal to the first preset slope.

[0069] Specifically, the value range of the first preset slope is set to [0.8, 3], and 1 is preferred in the embodiment of the present invention.

[0070] Specifically, the correction unit obtains a slope difference by subtracting the first slope from the first preset slope based on the unqualified intervention scheme.

[0071] Based on the comparison result that the slope difference is greater than the preset slope difference, determining to reduce the preset fitness by a first fitness adjustment coefficient;

[0072] Based on the comparison result that the slope difference is less than or equal to the preset slope difference, it is determined to reduce the preset fitness by a second fitness adjustment coefficient.

[0073] Specifically, the value range of the preset slope difference is set to [0.2, 1.3], and 0.3 is preferred in the embodiment of the present invention; the value range of the first fitness adjustment coefficient is set to [0.7, 0.9], and 0.8 is preferred in the embodiment of the present invention; the value range of the second fitness adjustment coefficient is set to (0.9, 0.98], and 0.95 is preferred in the embodiment of the present invention. For example, the method of adjusting the preset fitness by using the first fitness adjustment coefficient is 0.3 multiplied by 0.8, which is 0.24 times the maximum fitness mean.

[0074] Specifically, the analysis unit establishes an evaluation value curve of the intervention cycle and the attention evaluation value for the intervention cycle of any intervention stage, records the maximum slope of the evaluation value curve as the second slope, and records the ratio of the second slope to the first slope as the correlation degree.

[0075] Determining that the evaluation accuracy of the attention level is unqualified based on a comparison result that the correlation degree is less than a first preset correlation degree or greater than a second preset correlation degree;

[0076] The accuracy of the evaluation of the attention level is determined to be qualified based on a comparison result that the degree of association is greater than or equal to the first preset degree of association and less than or equal to the second preset degree of association.

[0077] Specifically, the value range of the first preset correlation degree is set to [0.4, 0.6], and 0.5 is preferred in the embodiment of the present invention; the value range of the second preset correlation degree is set to [0.7, 0.9], and 0.8 is preferred in the embodiment of the present invention.

[0078] Specifically, the correction unit determines a first difference between the preset association degree and the association degree, and a second difference between the association degree and the preset association degree under the condition that the evaluation accuracy of the attention level is unqualified,

[0079] Determining to increase the attention evaluation value by a first evaluation value adjustment coefficient based on a comparison result that the first difference is greater than a first preset difference;

[0080] Based on the comparison result that the first difference is less than or equal to the first preset difference, it is determined to use a second evaluation value adjustment coefficient to increase the attention evaluation value.

[0081] Specifically, the value range of the first preset difference is set to [0.1, 0.3], and the preferred embodiment of the present invention is 0.2; the value range of the first evaluation value adjustment coefficient is set to [1.06, 1.09], and the preferred embodiment of the present invention is 1.07; the value range of the second evaluation value adjustment coefficient is set to [1.02, 1.05], and the preferred embodiment of the present invention is 1.04.

[0082] Specifically, the correction unit determines to use a third evaluation value adjustment coefficient to reduce the attention evaluation value based on a comparison result that the second difference is greater than a second preset difference;

[0083] Based on the comparison result that the second difference is less than or equal to the second preset difference, it is determined to use a fourth evaluation value adjustment coefficient to reduce the attention evaluation value.

[0084] Specifically, the value range of the second preset difference is set to [0.2, 0.4], and the preferred embodiment of the present invention is 0.3; the value range of the third evaluation value adjustment coefficient is set to [0.92, 0.95], and the preferred embodiment of the present invention is 0.93; the value range of the fourth evaluation value adjustment coefficient is set to [0.96, 0.99], and the preferred embodiment of the present invention is 0.97.

[0085] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An intelligent auxiliary training brain-computer system for improving attention, characterized in that: include: A data input module, which is used for a user to input a number of evaluation data of a monitored subject, wherein the evaluation data includes scale data and experimental data; a data fitting module connected to the data input module, for determining the attention level of the monitored subject based on the comparison between each of the evaluation data and the sample data in the sample database, identifying abnormal data based on the comparison result of the fit between the evaluation data and the sample data of the corresponding attention level and a preset fit, and outputting an intervention plan based on the abnormal data; a program execution module, which is connected to the data fitting module and is used to execute the intervention program of the monitored subject in response to the fitting result of the data fitting module; An analysis module, which is connected to the data fitting module and the solution execution module respectively, includes: A monitoring unit, which is used to receive the EEG signal of the monitoring subject in real time to determine the attention evaluation value, and to monitor the completion time and accuracy of the intervention plan; An analysis unit, which is used to construct an effect curve based on the completion time and the accuracy rate to determine the eligibility of the intervention plan based on a first slope of the effect curve, and to construct an evaluation value curve according to the attention evaluation value to determine whether the evaluation accuracy of the attention level is qualified based on a correlation between a second slope of the evaluation value curve and the first slope; A correction unit, responsive to the analysis result of the analysis unit, is used to reduce the preset fitness for an unqualified intervention plan and to correct the attention evaluation value under the condition that the evaluation accuracy is unqualified.

2. The intelligent auxiliary training brain-computer system for improving attention according to claim 1 is characterized in that: The data fitting module determines the mean of the fit between the evaluation data and the sample data and determines the maximum mean of the fit, determines the attention level of the sample data corresponding to the maximum mean of the fit as the attention level of the monitored subject, and determines the intervention plan corresponding to the attention level as the basic intervention plan, wherein a correspondence between the sample data, the intervention plan and the attention level is pre-set.

3. The intelligent auxiliary training brain-computer system for improving attention according to claim 2 is characterized in that: The data fitting module compares the single item data in the evaluation data with the corresponding single item sample data to calculate the degree of fit; The single item of data is determined to be abnormal data based on a comparison result that the degree of fit is less than a preset degree of fit.

4. The intelligent auxiliary training brain-computer system for improving attention according to claim 3 is characterized in that: The data fitting module determines the intervention item corresponding to the abnormal data, and replaces the corresponding intervention item in the basic intervention plan based on the intervention item to output an intervention plan for the monitored subject, wherein the intervention plan includes several intervention items, each intervention item includes several intervention stages, and each intervention stage includes several intervention cycles.

5. The intelligent auxiliary training brain-computer system for improving attention according to claim 4 is characterized in that: The analysis unit establishes an effect curve of completion time and accuracy for the intervention cycle of any intervention stage, records the maximum slope of the effect curve as the first slope, and determines to enter the next treatment stage based on the condition that the first slope is greater than or equal to a preset threshold.

6. The intelligent auxiliary training brain-computer system for improving attention according to claim 1 is characterized in that: The analysis unit determines that the intervention plan is unqualified based on a comparison result that the first slope is less than a first preset slope.

7. The intelligent auxiliary training brain-computer system for improving attention according to claim 6 is characterized in that: The correction unit obtains a slope difference by subtracting the first slope from the first preset slope based on the unqualified intervention scheme, Based on the comparison result that the slope difference is greater than the preset slope difference, determining to reduce the preset fitness by a first fitness adjustment coefficient; Based on the comparison result that the slope difference is less than or equal to the preset slope difference, it is determined to reduce the preset fitness by a second fitness adjustment coefficient.

8. The intelligent auxiliary training brain-computer system for improving attention according to claim 1, characterized in that: The analysis unit establishes an evaluation value curve of the intervention period and the attention evaluation value for the intervention period of any intervention stage, records the maximum slope of the evaluation value curve as the second slope, and records the ratio of the second slope to the first slope as the correlation degree. The evaluation accuracy of the attention level is determined to be unqualified based on the comparison result that the degree of association is less than the first preset degree of association or greater than the second preset degree of association.

9. The intelligent auxiliary training brain-computer system for improving attention according to claim 8, characterized in that: The correction unit determines a first difference between the preset association degree and the association degree, and a second difference between the association degree and the preset association degree under the condition that the evaluation accuracy of the attention level is unqualified, Determining to increase the attention evaluation value by a first evaluation value adjustment coefficient based on a comparison result that the first difference is greater than a first preset difference; Based on the comparison result that the first difference is less than or equal to the first preset difference, it is determined to use a second evaluation value adjustment coefficient to increase the attention evaluation value.

10. The intelligent auxiliary training brain-computer system for improving attention according to claim 8, characterized in that: The correction unit determines to use a third evaluation value adjustment coefficient to reduce the attention evaluation value based on a comparison result that the second difference is greater than a second preset difference; Based on the comparison result that the second difference is less than or equal to the second preset difference, it is determined to use a fourth evaluation value adjustment coefficient to reduce the attention evaluation value.

Images