Modeling method, monitoring method and system for monitoring cognitive training process

Abstract

The application discloses a modeling method, a monitoring method and a system of a monitoring model of a cognitive training process. The modeling method comprises the following steps: obtaining cognitive training scores of a plurality of patients with cognitive impairment; constructing a plane rectangular coordinate system with the number of training times as the horizontal coordinate and the cognitive training scores as the vertical coordinate; marking coordinate points based on the cognitive training scores of each patient with cognitive impairment; based on all coordinate points in the plane rectangular coordinate system, fitting a plurality of standard learning curves by using a preset function to obtain a plurality of parameter combinations; taking the square root error as an evaluation index of the model fitting effect, and taking the parameter combination with the minimum square root error as the best parameter combination; and applying the best parameter combination to the preset function to form a monitoring model for monitoring the cognitive training process. The standard learning curve drawn by using the monitoring model can monitor the cognitive training process of a single patient, and output the relative standard reaching level and learning progress of the patient.

Description

Technical Field

[0001] This invention relates to a modeling method for a cognitive training process monitoring model, as well as a monitoring method for the cognitive training process and a corresponding monitoring system, belonging to the field of cognitive assessment technology. Background Technology

[0002] Cognitive training is an effective means of delaying cognitive decline, and achieving good cognitive enhancement results relies on continuous training for three months or even a lifetime. How to enhance individuals' interest in cognitive training and enable them to consistently exert effort and take action is an area where continuous innovation and breakthroughs are needed in the design of cognitive training tasks.

[0003] Traditional cognitive training utilizes classic task settings, but due to significant differences in individual cognitive levels, using tasks of uniform difficulty can lead to problems. Some individuals may find the tasks too easy, resulting in decreased interest, reduced focus, and lower training frequency. Others may find the tasks too difficult, causing excessive stress, damaging their confidence, and decreasing their commitment to cognitive training. Therefore, it is essential to monitor patients' cognitive training progress during the training process. This allows for adjustments to the training plan based on individual differences, helping patients better understand their progress and providing them with a clear direction for their cognitive training. Consequently, how to effectively monitor patients' cognitive training progress is a pressing technical challenge that needs to be addressed. Summary of the Invention

[0004] The primary technical problem to be solved by this invention is to provide a modeling method for a monitoring model of the cognitive training process.

[0005] Another technical problem to be solved by the present invention is to provide a method for monitoring the cognitive training process.

[0006] Another technical problem to be solved by the present invention is to provide a monitoring system for the cognitive training process.

[0007] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution: According to a first aspect of the present invention, a method for modeling a monitoring model of a cognitive training process is provided, comprising the following steps: Obtain multiple cognitive training scores from several patients with cognitive impairment; A Cartesian coordinate system is constructed with the number of training sessions as the x-axis and the cognitive training score as the y-axis. Within the Cartesian coordinate system, coordinate points are marked based on the multiple cognitive training scores of each of the patients with cognitive impairment. Based on all coordinate points in the Cartesian coordinate system, a preset function is used to fit the standard learning curve multiple times to obtain multiple sets of parameter combinations. The square root error is used as the evaluation index of the model fitting effect, and the parameter combination with the smallest square root error is taken as the optimal parameter combination. The optimal parameter combination is applied to the preset function to form a monitoring model for monitoring the cognitive training process.

[0008] Preferably, the fitting of the standard learning curve includes: The changes in cognitive training scores with the number of training iterations are fitted using a preset function, which is as follows:

[0009] in, denoted by t, represents the cognitive training score at the t-th training session; a represents the asymptote level; s represents the initial value, with the mean of the first cognitive training score as a fixed parameter; e represents an exponential function with a natural number as the base; t represents the number of training sessions; r represents the learning rate; and d represents the degree to which the learning pattern is followed. After a fitting is completed using the preset function, a set of parameter combinations formed by parameters a, r, and d is obtained.

[0010] Preferably, the cognitive training score is one of a single task score, a single brain ability score, or a total brain ability score. The individual task score is the score for a specific cognitive training task. The individual brain ability score is the average score obtained by averaging the scores of all cognitive training tasks associated with that brain ability. The overall brain ability score is the average score obtained by averaging the scores of each brain ability.

[0011] Preferably, based on the standard learning curve plotted using the optimal parameter combination, the number of training iterations t required to reach the asymptote level a is obtained. N The number of training sessions t1 where the learning rate shows a clear inflection point of increase, and the number of training sessions t2 where the learning rate shows a clear inflection point of decrease; Among them, the training count from 0 to t1 represents the exploratory period for patients with average cognitive impairment, and the training count from t1 to t2 represents the reinforcement period for patients with average cognitive impairment. N This is the fine-tuning period for patients with average cognitive impairment.

[0012] According to a second aspect of the present invention, a method for monitoring the cognitive training process is provided, comprising the following steps: Obtain multiple cognitive training scores of the patients to be monitored; The cognitive training score V of the patient to be monitored at the last time t患 Cognitive training score V corresponding to the number of training iterations of the monitoring model t To compare and obtain the comparison results; Based on the comparison results, the relative achievement level of the monitored patients is output; The monitoring model is constructed using the modeling method described above.

[0013] Preferably, the monitoring method further includes: Based on the changes in the cognitive training scores of the monitored patients over multiple training sessions, the current learning stage of the monitored patients is obtained; wherein, if the cognitive training scores of the monitored patients show a significant inflection point of increase, the monitored patients are determined to be in the reinforcement stage; if the cognitive training scores of the monitored patients have not yet shown an inflection point, the monitored patients are determined to be in the exploration stage; if the cognitive training scores of the monitored patients show a significant inflection point of deceleration, the patients are determined to be in the fine-tuning stage. Based on the standard learning curve plotted using the optimal parameter combination, the number of training iterations t required to reach the asymptote level a is obtained. N The training sessions t1 and t2 represent the number of training sessions where the learning rate shows a significant inflection point of increase and a significant inflection point of decrease, respectively. The training sessions from 0 to t1 represent the exploratory phase for patients with average cognitive impairment, t1 to t2 represent the reinforcement phase, and t2 to t... N This is the fine-tuning period for patients with average cognitive impairment. The last training session of the patient under monitoring is compared with the training session t1 or t2 to output the learning progress status of the patient under monitoring.

[0014] In the better case, if V t患 Close to V t and not exceeding V t If the preset information area is defined, then the relative achievement level of the patient to be monitored is considered to be achieved; If V t患 Higher than V t If the preset information area is defined, then the relative attainment level of the patient to be monitored is considered to be above the standard; If V t患 Below V t If the preset information area is not met, then the relative achievement level of the patient to be monitored is not met.

[0015] Preferably, the monitoring method further includes: Based on the relative achievement level and learning progress of the patients to be monitored, an optimized training plan is output for the patients to be monitored.

[0016] Preferably, the cognitive training score of the patient to be monitored is one of the following: single task score, single brain ability score, or overall brain ability score. If the cognitive training score of the patient to be monitored is a single task score, then the training optimization scheme is to adjust the training cycle of the single training task. If the cognitive training score of the patient to be monitored is a single brain ability score, then the training optimization scheme is to make a structured adjustment to the cognitive training tasks associated with that brain ability. If the cognitive training score of the patient to be monitored is the overall brain ability score, then the training optimization plan is to adjust the overall training frequency and prioritize the cognitive training tasks corresponding to the individual brain abilities that improve the slowest.

[0017] According to a third aspect of the present invention, a monitoring system for a cognitive training process is provided, comprising a processor and a memory, wherein the processor reads a computer program in the memory for executing the monitoring method described above.

[0018] Compared with the prior art, the present invention has the following technical effects: 1. A nonlinear regression fitting model with nonlinear mixed effects is used as the learning model. By constructing a standard learning curve of cognitive training score as a function of training times, the cognitive training process of a single patient can be monitored using this standard learning curve.

[0019] 2. It can be applied to single tasks, single cognitive abilities, or overall cognitive abilities to monitor the patient's learning process, thereby determining the patient's relative achievement level, learning stage, and progress relative to the standard. This provides a more objective indicator, offering feedback on the patient's learning and training progress from multiple dimensions, including horizontal comparisons and longitudinal development. 3. Based on the patient's relative achievement level and learning progress, cognitive training can be optimized, and different adjustment plans can be recommended for single tasks, single cognitive abilities, and overall cognitive abilities. Attached Figure Description

[0020] Figure 1 A flowchart illustrating a modeling method for a cognitive training process monitoring model provided in the first embodiment of the present invention; Figure 2 This is a schematic diagram of fitting a standard learning curve in the first embodiment of the present invention; Figure 3 The overall flowchart of a cognitive training process monitoring method provided in the second embodiment of the present invention; Figure 4 A detailed flowchart of a cognitive training process monitoring method provided in the second embodiment of the present invention; Figure 5This is a monitoring comparison chart of patient 1 in the second embodiment of the present invention; Figure 6 This is a monitoring comparison chart of patient 2 in the second embodiment of the present invention; Figure 7 A schematic diagram of the structure of a cognitive training process monitoring system provided in the third embodiment of the present invention. Detailed Implementation

[0021] The technical content of the present invention will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0022] The technical concept of this invention involves fitting cognitive training data (which can correspond to a single task, a single brain ability, or overall brain ability) of a cognitively impaired group to a nonlinear regression fitting model with nonlinear mixed effects as the learning model. This fits the standard learning curves for a single task, a single brain ability, or overall brain ability during cognitive training. From the fitting interval of the standard learning curve, the total training period required for a single task, a single brain ability, or overall brain ability can be obtained. Furthermore, based on this standard learning curve, the three learning stages of "exploration-reinforcement-fine-tuning" for the average cognitively impaired patient, as well as the time period for each of these three learning stages, can be determined.

[0023] For a single patient, by obtaining the patient's cognitive training scores multiple times, the patient's cognitive training status can be compared with a standard learning curve, which can be used to monitor the relative achievement level and learning progress of new patients.

[0024] First Embodiment like Figure 1 As shown, the modeling method for a cognitive training process monitoring model provided in the first embodiment of the present invention specifically includes steps S1 to S6: S1: Obtain multiple cognitive training scores from multiple patients with cognitive impairment.

[0025] In this embodiment, the cognitive training score is one of the following: a single task score, a single brain ability score, or an overall brain ability score. Specifically, a single task score is the score for a specific cognitive training task. A single brain ability score is the average score obtained by averaging the scores of all cognitive training tasks associated with that brain ability. The overall brain ability score is the average score obtained by averaging the scores of all brain abilities.

[0026] It is understandable that different types of cognitive training scores will lead to different monitoring models. In this embodiment, monitoring models can be constructed for individual task scores, individual brain ability scores, or overall brain ability scores.

[0027] S2: Construct a Cartesian coordinate system.

[0028] Specifically, such as Figure 2 As shown, in this embodiment, a Cartesian coordinate system is constructed with the number of training sessions t as the horizontal axis and the cognitive training score V as the vertical axis.

[0029] S3: In a Cartesian coordinate system, mark coordinate points based on the multiple cognitive training scores of each cognitively impaired patient.

[0030] Specifically, such as Figure 2 As shown, after marking coordinate points based on the multiple cognitive training scores of each cognitively impaired patient, a graph can be formed by connecting all the coordinate points sequentially. Figure 2 A learning curve in the form of a wave.

[0031] S4: Based on all coordinate points in the Cartesian coordinate system, use a preset function to fit the standard learning curve multiple times to obtain multiple sets of parameter combinations.

[0032] Specifically, this includes steps S41 to S43: S41: Use a preset function (in this example, the Weiber function) to fit the change in cognitive training score with the number of training iterations. The preset function is as follows:

[0033] in, denoted by t, represents the cognitive training score at the t-th training session; a represents the asymptote level; s represents the initial value, with the mean of the first cognitive training score as a fixed parameter; e represents an exponential function with a natural number as the base; t represents the number of training sessions; r represents the learning rate; and d represents the degree to which the learning pattern is followed.

[0034] Understandably, a larger 'a' indicates a higher final cognitive training score. A larger 'r' indicates a faster learning speed. A larger 'd' indicates a closer fit to the preset function, and a faster acceleration of learning over time.

[0035] S42: After a fitting is completed using a preset function, a set of parameters a, r, and d are obtained.

[0036] Reference Figure 2 As shown, after completing one fitting using a preset function, a standard learning curve can be obtained (i.e.: Figure 2 (A smooth learning curve). It can be understood that, based on this standard learning curve, the parameters a, r, and d in the preset function can be determined, thus forming a set of parameter combinations (a, r, d).

[0037] S43: Repeat steps S41 to S42 above to fit the standard learning curve multiple times using a preset function, thereby obtaining multiple sets of parameter combinations.

[0038] S5: Select the optimal parameter combination.

[0039] Specifically, in this embodiment, the root square error (RMSE) is used as the evaluation index of the model fitting effect, and the parameter combination with the smallest RMSE is taken as the optimal parameter combination.

[0040] The specific method of evaluating the model fitting effect using the root square error (RMSE) is a conventional technique in this field and will not be elaborated here.

[0041] S6: Apply the optimal parameter combination to the preset function to form a monitoring model for monitoring the cognitive training process.

[0042] Specifically, after selecting the optimal parameter combination based on step S5, this optimal parameter combination is applied to a preset function to form a monitoring model for monitoring the cognitive training process. Furthermore, as... Figure 2 As shown in this embodiment, the standard learning curve is plotted based on the optimal parameter combination, and the number of training iterations t is obtained when the asymptote level a is reached. N The number of training sessions t1 where the learning rate shows a clear inflection point of increase, and the number of training sessions t2 where the learning rate shows a clear inflection point of decrease.

[0043] Among them, the training count from 0 to t1 represents the exploratory period for patients with average cognitive impairment, and the training count from t1 to t2 represents the reinforcement period for patients with average cognitive impairment. N This is the fine-tuning period for patients with average cognitive impairment.

[0044] Second Embodiment like Figure 3 and Figure 4 As shown, based on the first embodiment described above, the second embodiment of the present invention provides a method for monitoring the cognitive training process, specifically including steps S10 to S60: S10: Obtain the cognitive training scores of the patients to be monitored multiple times.

[0045] In this embodiment, the patient's multiple cognitive training scores are one of the following: single task score, single brain ability score, or overall brain ability score. Different types of scores correspond to different monitoring models.

[0046] Understandably, if the patient's multiple cognitive training scores are individual task scores, then the training process needs to be monitored using the monitoring model constructed using individual task scores in the first embodiment. Similarly, if the patient's multiple cognitive training scores are individual brain ability scores, then the training process needs to be monitored using the monitoring model constructed using individual brain ability scores in the first embodiment. If the patient's multiple cognitive training scores are overall brain ability scores, then the training process needs to be monitored using the monitoring model constructed using overall brain ability scores in the first embodiment.

[0047] S20: The cognitive training score V of the patient to be monitored at the last time. t患 Cognitive training score V corresponding to the number of training iterations of the monitoring model t Compare them to obtain the comparison results.

[0048] Specifically, for the patient to be monitored, obtain the patient's current number of training sessions 1…t, and the score V for each training session. 1患 …V t患 The patient's training score V in the t-th training session (i.e., the last training session) is calculated. t患 The cognitive training score V of the monitoring model at the tth time t By comparing them, we can obtain the comparison results.

[0049] S30: Based on the comparison results, output the relative achievement level of the patients to be monitored.

[0050] Specifically, if V t患 Close to V t and not exceeding V t Preset signal area (refer to) Figure 2 If the shaded area in the image represents the relative level of achievement of the patient being monitored, then the patient's relative achievement level is considered to be within the target range. If V t患 Higher than V t If the pre-set information region is specified, the relative target level of the patient to be monitored is considered excessive. If V t患 Below V t If the pre-set information area is not met, the relative achievement level of the patient to be monitored will be considered as not meeting the target.

[0051] like Figure 5 As shown, for patient 1, due to their cognitive training score V in the t-th session... t患 Below V t The pre-set information area indicates that patient 1's current training has not met the target. For example... Figure 6 As shown, for patient 2, due to their cognitive training score V in the t-th session... t患 Higher than V t Based on the pre-set information area, it was determined that patient 2's current training level was excessive.

[0052] S40: Output the current learning stage of the patient to be monitored.

[0053] Specifically, based on the changes in the cognitive training scores of the monitored patients over multiple sessions, the current learning stage of the monitored patients is determined. If the monitored patients' cognitive training scores show a significant inflection point of increase, the monitored patients are determined to be in the reinforcement stage; if the monitored patients' cognitive training scores have not yet shown an inflection point, the monitored patients are determined to be in the exploration stage; if the monitored patients' cognitive training scores show a significant inflection point of deceleration, the monitored patients are determined to be in the fine-tuning stage.

[0054] like Figure 5 As shown, for patient 1, since the curve change shows an inflection point, it is determined that patient 1 is in the exploratory phase. Figure 6 As shown, for patient 2, since the curve change showed a clear inflection point of growth but no clear inflection point of deceleration, it was determined that patient 2 was in the enhancement phase.

[0055] S50: Outputs the learning progress of the patient to be monitored.

[0056] Specifically, in this embodiment, the standard learning curve plotted based on the optimal parameter combination is used to obtain the number of training iterations t required to reach the asymptote level a. N The training sessions t1 and t2 represent the number of training sessions where the learning rate shows a significant inflection point of increase and a significant inflection point of decrease, respectively. The training sessions from 0 to t1 represent the exploratory phase for patients with average cognitive impairment, t1 to t2 represent the reinforcement phase, and t2 to t... N This is the fine-tuning period for patients with average cognitive impairment.

[0057] Therefore, the last training count of the patient to be monitored in step S40 is compared with the training count t1 or training count t2, thereby outputting the learning progress status of the patient to be monitored.

[0058] like Figure 5 As shown, since Patient 1's last training session t > t1 during the current exploratory phase, Patient 1's learning phase is considered lagging. It's understandable that if Patient 1's last training session t ≤ t1 during the current exploratory phase, then Patient 1's learning phase is normal. If Patient 1's last training session t ≤ t1 during the current exploratory phase, and Patient 1's learning curve shows a clear inflection point, then Patient 1's learning phase is considered overdue.

[0059] like Figure 6As shown, since Patient 2 is currently in the intensive training phase and the last training session number t1 < t < t2, Patient 2's learning stage is considered normal. It is understandable that if Patient 2's last training session number t > t2, then Patient 2's learning stage is considered lagging. If Patient 2's last training session number t1 < t < t2, and the curve shows a clear deceleration inflection point, then Patient 2's learning stage is considered advanced.

[0060] S60: Based on the relative achievement level and learning progress of the patients to be monitored, output the training optimization plan for the patients to be monitored.

[0061] In this embodiment, three different training optimization schemes are output for three different types of cognitive training scores (single task score, single brain ability score, or overall brain ability score).

[0062] The following is a detailed explanation of three different training optimization schemes: (1) If the cognitive training score of the patient to be monitored is the score of a single task, then the training optimization plan is to adjust the training cycle of the single training task.

[0063] Specifically, for a single task, the learning rate and relative exploration period for achieving the highest score are calculated. Based on this, a standard training cycle of N times can be established for that task, and the training cycle can be adjusted according to the patient's learning progress and relative achievement level.

[0064] (2) If the cognitive training score of the patient to be monitored is a single brain ability score, then the training optimization plan is to make a structured adjustment to the cognitive training tasks associated with that brain ability.

[0065] Specifically, the brain's ability is calculated as a result of repeated practice, and a standardized learning curve is plotted. Then, based on the individual patient's learning progress and relative achievement level, the difficulty of the corresponding cognitive training task is adjusted by increasing or decreasing it.

[0066] (3) If the cognitive training score of the patient to be monitored is the overall brain ability score, the training optimization plan is to adjust the overall training frequency and prioritize the cognitive training task corresponding to the single brain ability that improves the slowest.

[0067] Specifically, the overall brain ability is calculated daily as the number of training days increases, and an overall learning curve is plotted. This curve is then fitted to individual patients to assess their overall learning progress and relative achievement level, providing overall feedback. The overall training frequency is adjusted, and priority is given to training the individual brain abilities that show the slowest improvement for each patient.

[0068] Third Embodiment like Figure 7 As shown, based on the above-described method for monitoring the cognitive training process, the third embodiment of the present invention further provides a system for monitoring the cognitive training process. This monitoring system includes one or more processors 21 and a memory 22. The memory 22 is coupled to the processors 21 and is used to store one or more programs. When the one or more programs are executed by the one or more processors 21, the one or more processors 21 implement the method for monitoring the cognitive training process as described in the above embodiments.

[0069] The processor 21 controls the overall operation of the monitoring system to complete all or part of the steps of the cognitive training process monitoring method described above. The processor 21 can be a central processing unit (CPU), graphics processing unit (GPU), field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), digital signal processing (DSP) chip, etc. The memory 22 stores various types of data to support the operation of the monitoring system. This data may include, for example, instructions for any application or method operating on the monitoring system, and application-related data. The memory 22 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, etc.

[0070] In one exemplary embodiment, the monitoring system may be implemented by a computer chip or physical entity, or by a product with certain functions, for executing the above-described monitoring method for the cognitive training process and achieving the same technical effect as the described method. A typical embodiment is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, an in-vehicle human-machine interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0071] In another exemplary embodiment, the present invention also provides a computer-readable storage medium including program instructions, which, when executed by a processor, implement the steps of the cognitive training process monitoring method in any of the above embodiments. For example, the computer-readable storage medium may be the memory including the program instructions, which may be executed by the processor of the monitoring system to complete the cognitive training process monitoring method described above and achieve the same technical effects as the method described above.

[0072] In summary, the modeling method, monitoring method, and system for monitoring the cognitive training process provided in this embodiment of the invention have the following beneficial effects: 1. A nonlinear regression fitting model with nonlinear mixed effects is used as the learning model. By constructing a standard learning curve of cognitive training score as a function of training times, the cognitive training process of a single patient can be monitored using this standard learning curve.

[0073] 2. It can be applied to single tasks, single brain abilities, and overall brain abilities to monitor the patient's learning process, determine the patient's relative achievement level, learning stage, and progress relative to the standard. As a more objective indicator, it provides feedback on the patient's learning and training progress from multiple dimensions, including horizontal comparison and longitudinal development.

[0074] 3. Cognitive training for patients can be optimized based on their relative achievement level and learning progress, and different adjustment plans can be recommended for single tasks, single brain abilities, and overall brain abilities.

[0075] It should be noted that the above embodiments are merely illustrative examples, and the technical solutions of each embodiment can be combined, all of which are within the protection scope of this invention.

[0076] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. The modeling method, monitoring method, and system for the cognitive training process monitoring model provided by this invention have been described in detail above. Any obvious modifications made by those skilled in the art without departing from the essence of this invention will constitute an infringement of the patent rights of this invention and will incur corresponding legal liability.

Claims

1. A modeling method for a cognitive training process monitoring model, characterized in that... Includes the following steps: Obtain multiple cognitive training scores from several patients with cognitive impairment; A Cartesian coordinate system is constructed with the number of training sessions as the x-axis and the cognitive training score as the y-axis. Within the Cartesian coordinate system, coordinate points are marked based on the multiple cognitive training scores of each of the patients with cognitive impairment. Based on all coordinate points within the Cartesian coordinate system, a preset function is used to fit a standard learning curve multiple times to obtain multiple sets of parameter combinations; wherein, the fitting of the standard learning curve includes: fitting the change in cognitive training score with the number of training sessions using a preset function, the preset function being as follows: ;in, denoted as t, representing the cognitive training score in the t-th training session; a represents the asymptote level; s represents the starting value, with the mean of the first cognitive training score as a fixed parameter; e represents an exponential function with a natural number as the base; t represents the number of training sessions; r represents the learning rate; d represents the degree to which the learning pattern is followed; after completing one fitting using the preset function, a set of parameters a, r, and d are obtained. The square root error is used as the evaluation index of the model fitting effect, and the parameter combination with the smallest square root error is taken as the optimal parameter combination. The optimal parameter combination is applied to the preset function to form a monitoring model for monitoring the cognitive training process; specifically, this includes: drawing a standard learning curve based on the optimal parameter combination, and obtaining the number of training iterations t when the asymptote level a is reached. N The training sessions t1 and t2 represent the number of training sessions where the learning rate shows a significant inflection point of increase and a significant inflection point of decrease, respectively. The training sessions from 0 to t1 represent the exploratory phase for patients with average cognitive impairment, t1 to t2 represent the reinforcement phase, and t2 to t... N This is the fine-tuning period for patients with average cognitive impairment.

2. The modeling method as described in claim 1, characterized in that: The cognitive training score is one of the following: single task score, single brain ability score, or overall brain ability score. The individual task score is the score for a specific cognitive training task. The individual brain ability score is the average score obtained by averaging the scores of all cognitive training tasks associated with that brain ability. The overall brain ability score is the average score obtained by averaging the scores of each brain ability.

3. A method for monitoring the cognitive training process, characterized in that... Includes the following steps: Obtain multiple cognitive training scores of the patients to be monitored; The cognitive training score V of the patient to be monitored at the last time t患 Cognitive training score V corresponding to the number of training iterations of the monitoring model t The two models are compared to obtain a comparison result; wherein the monitoring model is constructed by the modeling method described in any one of claims 1-2. Based on the comparison results, the relative achievement level of the monitored patients is output; The monitoring method also includes: Based on the changes in the cognitive training scores of the monitored patients over multiple training sessions, the current learning stage of the monitored patients is obtained; wherein, if the cognitive training scores of the monitored patients show a significant inflection point of increase, the monitored patients are determined to be in the reinforcement stage; if the cognitive training scores of the monitored patients have not yet shown an inflection point, the monitored patients are determined to be in the exploration stage; if the cognitive training scores of the monitored patients show a significant inflection point of deceleration, the patients are determined to be in the fine-tuning stage. Based on the standard learning curve plotted using the optimal parameter combination, the number of training iterations t required to reach the asymptote level a is obtained. N The training sessions t1 and t2 represent the number of training sessions where the learning rate shows a significant inflection point of increase and a significant inflection point of decrease, respectively. The training sessions from 0 to t1 represent the exploratory phase for patients with average cognitive impairment, t1 to t2 represent the reinforcement phase, and t2 to t... N This is the fine-tuning period for patients with average cognitive impairment. The last training session of the patient under monitoring is compared with the training session t1 or t2 to output the learning progress status of the patient under monitoring.

4. The monitoring method as described in claim 3, characterized in that: If V t患 Close to V t And not exceeding V t If the preset information area is defined, then the relative achievement level of the patient to be monitored is considered to be achieved; If V t患 Higher than V t If the preset information area is defined, then the relative attainment level of the patient to be monitored is considered to be above the standard; If V t患 Below V t If the preset information area is not met, then the relative achievement level of the patient to be monitored is not met.

5. The monitoring method as described in claim 4, characterized in that... Also includes: Based on the relative achievement level and learning progress of the patients to be monitored, an optimized training plan is output for the patients to be monitored.

6. The monitoring method as described in claim 5, characterized in that: The cognitive training score of the patient to be monitored is one of the following: single task score, single brain ability score, or overall brain ability score. If the cognitive training score of the patient to be monitored is a single task score, then the training optimization scheme is to adjust the training cycle of the single training task. If the cognitive training score of the patient to be monitored is a single brain ability score, then the training optimization scheme is to make a structured adjustment to the cognitive training tasks associated with that brain ability. If the cognitive training score of the patient to be monitored is the overall brain ability score, then the training optimization plan is to adjust the overall training frequency and prioritize the cognitive training tasks corresponding to the individual brain abilities that improve the slowest.

7. A monitoring system for cognitive training process, characterized in that... It includes a processor and a memory, wherein the processor reads a computer program from the memory for executing the monitoring method as described in any one of claims 3 to 6.

Images