Method, device, equipment, medium and product for improving cognitive ability

Abstract

This disclosure relates to a training method, apparatus, device, medium, and product for enhancing cognitive abilities, belonging to the technical field of brain function training. The method includes: in response to a cognitive training request from a trainee, acquiring the trainee's characteristic information; determining the high-level cognitive task indicated by the cognitive training request and the corresponding cognitive ability map; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task; using the cognitive ability map, selecting target basic cognitive tasks that match the high-level cognitive task from a pre-set cognitive map database, and setting the target basic cognitive tasks and the high-level cognitive tasks as a target task group; displaying the target task group to the trainee; and, upon receiving the trainee's output of the final training result for the target task group, determining a target score representing the trainee's cognitive ability based on the final training result.

Description

Technical Field

[0001] This disclosure relates to the technical field of brain function training, and more specifically, to a training method, apparatus, device, medium, and product for improving cognitive abilities. Background Technology

[0002] Currently, cognitive ability, as a core competency for humans to acquire, process, and apply information, encompasses key dimensions such as attention, memory, and reasoning, and is widely used in fields such as psychology, neuroscience, and educational assessment. To train individuals to improve their cognitive abilities, basic cognitive tasks are typically presented, such as spatial-location working memory tasks. However, training cognitive regions with long-distance transfer is difficult, resulting in lower accuracy in cognitive ability training. Summary of the Invention

[0003] One objective of this disclosure is to provide a new technical solution for training to enhance cognitive abilities.

[0004] According to a first aspect of this disclosure, a training method for improving cognitive abilities is provided, the method comprising: In response to a cognitive training request from a trainee, the trainee's characteristic information is obtained; Determine the high-level cognitive task indicated by the cognitive training request and the corresponding cognitive ability map of the high-level cognitive task; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task; Using the cognitive ability graph, in a pre-set cognitive graph database, target basic cognitive tasks that match the advanced cognitive tasks are selected from each basic cognitive task, and the target basic cognitive tasks and the advanced cognitive tasks are taken as a target task group. The target task set is shown to the trainee; Upon receiving the trainer's output of the final training result for the target task group, the target test score characterizing the trainer's cognitive ability is determined based on the final training result.

[0005] Optionally, the step of filtering target basic cognitive tasks that match the advanced cognitive tasks from a pre-set cognitive graph database using the cognitive ability graph includes: Based on the cognitive partitions indicated by the cognitive ability graph, each basic cognitive task is selected and matched in the preset cognitive graph database and formed into multiple basic cognitive task groups; wherein, any two basic cognitive tasks in each basic cognitive task group correspond to different cognitive partitions. Select target basic cognitive tasks from the multiple basic cognitive task groups that match the advanced cognitive task.

[0006] Optionally, the step of filtering the target basic cognitive task that matches the advanced cognitive task from the plurality of basic cognitive task groups includes: The explanatory power of the plurality of basic cognitive task groups for the advanced cognitive task is determined, and the basic cognitive task group with the maximum explanatory power among the plurality of basic cognitive task groups is obtained as the target basic cognitive task matching the advanced cognitive task.

[0007] Optionally, before determining the target test score representing the trainee's cognitive ability based on the final training result, the method further includes: Receive feedback information showing the target task set to the trainee; When the feedback information indicates that the trainee meets the set bridging conditions, the matching recurrent cognitive tasks in the target task group are selected according to the preset screening conditions. For repetitive cognitive tasks, the trainee is shown and the repetitive training results are obtained. If the previous training cycle result indicates that the trainee meets the bridging condition, for the next training cycle result, the steps of performing the recurrent cognitive task, showing the trainee the recurrent training result, and obtaining the recurrent training result are repeated until the next training cycle result does not meet the bridging condition, and the next training cycle result is taken as the final training result.

[0008] Optionally, the cyclical cognitive task is the high-level cognitive task.

[0009] Optionally, the bridging conditions include the duration of all the recurrent cognitive tasks performed being less than or equal to a set duration and the accuracy of the final training result being less than or equal to a set threshold.

[0010] According to a second aspect of this disclosure, a training device for enhancing cognitive abilities is also provided, the device comprising: The response module is used to obtain the trainer's feature information in response to the trainer's cognitive training request; The first determining module is used to determine the high-level cognitive task indicated by the cognitive training request and the cognitive ability map corresponding to the high-level cognitive task; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task; The filtering module is used to filter target basic cognitive tasks that match the advanced cognitive tasks from the various basic cognitive tasks in a preset cognitive graph database through the cognitive ability graph, and to set the target basic cognitive tasks and the advanced cognitive tasks as a target task group. The display module is used to display the target task set to the trainee; The second determining module is used to determine the target test score characterizing the trainee's cognitive ability based on the final training result of the trainee's output for the target task group.

[0011] According to a third aspect of this disclosure, an electronic device is also provided, including a memory and a processor, the memory being used to store a computer program; the processor being used to execute the computer program to implement the method according to a first aspect of this disclosure.

[0012] According to a fourth aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, the computer program implementing the method according to a first aspect of this disclosure when executed by a processor.

[0013] According to a fifth aspect of this disclosure, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the method described according to a first aspect of this disclosure.

[0014] One beneficial effect of this disclosure is that the cognitive ability enhancement training method provided by the present invention can determine the trainee's characteristic information by receiving the trainee's cognitive training request. Based on the advanced cognitive task indicated by the cognitive training request and the corresponding cognitive ability map, the method uses the cognitive ability map to filter target basic cognitive tasks that match the advanced cognitive task from a pre-set cognitive map database. The target basic cognitive task and the advanced cognitive task are then presented to the trainee as a target task group. Furthermore, the method can receive the trainee's final training result and determine the target test score representing the trainee's cognitive ability based on the final training result. This enables training of the trainee's near-transfer and far-transfer cognitive regions, effectively improving the accuracy of cognitive ability enhancement training.

[0015] Other features and advantages of the embodiments of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of the present disclosure and, together with their description, serve to explain the principles of the embodiments of the present disclosure.

[0017] Figure 1 This is a flowchart illustrating a training method for enhancing cognitive abilities according to one embodiment; Figure 2 This is a schematic diagram of a cognitive ability map according to one embodiment; Figure 3 This is a block diagram of a training device for enhancing cognitive abilities according to one embodiment; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to one embodiment. Detailed Implementation

[0018] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the parts and steps set forth in these embodiments do not limit the scope of the invention.

[0019] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0020] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0021] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0022] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0023] <Method Implementation> Figure 1 This is a flowchart illustrating a training method for improving cognitive abilities according to one embodiment. The implementing entity is a smart terminal displayed to the trainee, which can be a mobile phone, tablet, or personal computer, etc., and is not limited thereto.

[0024] like Figure 1 As shown, the training method for improving cognitive abilities in this embodiment may include the following steps S110 to S140: Step S110: In response to the cognitive training request of the trainee, obtain the trainee's feature information.

[0025] In this embodiment, the feature information may include the trainer's age, gender, cognitive level, or cognitive task preference type, etc.

[0026] Step S120: Determine the high-level cognitive task indicated by the cognitive training request and the corresponding cognitive ability map of the high-level cognitive task; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task.

[0027] In this embodiment, there are multiple advanced cognitive tasks, and different advanced cognitive tasks can be adapted to the different training needs of trainees. Each different advanced cognitive task can correspond to a cognitive ability map.

[0028] In some examples, such as Figure 2 The cognitive ability map shown has a cognitive region corresponding to each basic cognitive task. These regions correspond to the Dorsal Attention (DA), Frontoparietal (FP), Sensorimotor (SM), Visual Attention (VA), Ventral Stream (VS), and Dorsomedial Prefrontal (DM) regions, respectively. Each basic cognitive task has different explanatory power for different higher-level cognitive tasks. For example, the explanatory power of basic cognitive task A1 for higher-level cognitive task B1 is 50%, and the explanatory power of basic cognitive task A2 for higher-level cognitive task B1 is 70%. Furthermore, in this cognitive ability map, the cognitive regions establish corresponding linear relationships. For example, the Dorsal Attention region has corresponding linear relationships with the Ventral Stream, Visual Attention, and Frontoparietal regions, respectively.

[0029] Step S130: Using the cognitive ability graph, select target basic cognitive tasks that match advanced cognitive tasks from the pre-set cognitive graph database, and group the target basic cognitive tasks and advanced cognitive tasks into a target task group.

[0030] In some embodiments, step S130 may include the following steps S210 to S240: Step S210: Determine the associated cognitive task configuration identifier based on each cognitive region indicated by the cognitive ability map.

[0031] Step S220: Based on the cognitive partitions indicated by the cognitive ability map, select matching basic cognitive tasks from the preset cognitive map database and form multiple basic cognitive task groups; wherein, any two basic cognitive tasks in each basic cognitive task group correspond to different cognitive partitions.

[0032] Step S230: Select target basic cognitive tasks that match advanced cognitive tasks from multiple basic cognitive task groups.

[0033] In this embodiment, by distinguishing between basic cognitive tasks and advanced cognitive tasks, the cognitive tasks for training trainees to improve their cognitive abilities can be further optimized, thereby enhancing the comprehensiveness of the training.

[0034] In some embodiments, step S230 may include the following step S310: Step S310: Determine the explanatory power of multiple basic cognitive task groups for the advanced cognitive task, and obtain the basic cognitive task group with the maximum explanatory power among the multiple basic cognitive task groups, so as to serve as the target basic cognitive task to match the advanced cognitive task.

[0035] In this embodiment, the cognitive graph database can be pre-built. The smart terminal uses existing correlation and regression algorithms to filter and match various basic cognitive tasks from the pre-built cognitive graph database. Existing regression analysis algorithms are used to determine the explanatory power of each basic cognitive task. Basic cognitive tasks corresponding to different cognitive partitions are then combined, and the differences in explanatory power among the various combinations are compared. The basic cognitive task group with the highest explanatory power is determined as the target basic cognitive task to match the advanced cognitive task. This target basic cognitive task is then displayed to the trainee, ensuring that the target basic cognitive task extracted from the cognitive graph database better meets the trainee's training needs.

[0036] In some embodiments, the basic cognitive tasks in the cognitive graph database may include object-location short-term memory cognitive tasks, spatial sequence short-term memory cognitive tasks, object-location working memory cognitive tasks, object working memory cognitive tasks, two-choice reaction time cognitive tasks, three-choice reaction time cognitive tasks, temporal order judgment cognitive tasks, visual search cognitive tasks, spatial breadth cognitive tasks, symmetry breadth cognitive tasks, adapted symmetry breadth cognitive tasks, object-location binding cognitive tasks, spatial short-term memory cognitive tasks, multiple-choice reaction time cognitive tasks, discrimination reaction time cognitive tasks, length discrimination cognitive tasks, visual pattern completion cognitive tasks, and single-task cognitive tasks.

[0037] This object-location short-term memory cognitive task can assess the ability to associate object features (car color / style) with locations (parking spaces). In each trial, the trainee sequentially encodes the locations of multiple unique cars within a displayed grid; after a car disappears, the trainee selects its original location based on the presented car features. The difficulty can be adjusted by increasing the grid size, the number of cars, and decreasing the encoding time. Each training session consists of 20 trials, lasting 5-8 minutes.

[0038] This spatial sequence short-term memory cognitive task can be: requiring participants to recall spatial locations in sequence. In each trial, visual cues (such as tiles) are presented at different locations within a grid; after the sequence disappears, participants must click on the grid locations in the correct order. The difficulty can be adjusted by changing the grid dimensions (3×3 to 5×5), sequence length, and cue presentation duration. Each training session consists of 20 trials, lasting 5-8 minutes.

[0039] This object-location working memory cognitive task can be: training the maintenance and updating of object positions. The trainee first encodes unique visual stimuli (such as animals or geometric shapes) presented in a grid; after the stimuli are hidden, a target category (such as "animals") is presented, and the trainee must select all tiles initially belonging to that category from a grid of tiles with similar appearances. The difficulty is adjusted by increasing the number of stimuli, shortening the viewing time, and spatially reorganizing the tiles (rotating / moving / swapping) within a holding interval. Each training session consists of 15 trials and lasts 5-8 minutes.

[0040] The object working memory cognitive task can be: assessing the dynamic updating ability of object features in working memory. Two to three "magic hats" are presented to the trainees, who then raise the hats one by one. The participants must judge whether the revealed object matches the object previously presented with that hat (a button press response). All participants use the same difficulty level (2 or 3 hats), as this task is already challenging enough for the target age group, making it difficult to set a smoothly increasing difficulty gradient. Each training session consists of 96 trials and lasts approximately 4 minutes.

[0041] This binary choice reaction time cognitive task can measure rapid perceptual discrimination ability. Trainees are presented with a series of red and green butterfly stimuli, and must quickly choose one of two buttons to press (e.g., press the left arrow for red, the right arrow for green), with accuracy feedback provided. The stimulus characteristics and timing remain constant, with a single level of difficulty throughout. Each training session lasts 3 minutes.

[0042] This three-choice reaction time cognitive task can be: requiring discrete choice responses under time pressure. The trainee controls a simulated aircraft moving along three horizontal lanes, switching to an air lane via buttons to avoid randomly appearing obstacles (such as hot air balloons). The difficulty is adjusted by increasing obstacle density, aircraft speed (shortening the reaction window), and limiting the number of error corrections. Each training session consists of 5 modules, with a total duration of 7.5 minutes.

[0043] This temporal sequence judgment cognitive task can be: judging the presentation order of two stimuli (auditory thunder, visual raindrop image). The stimuli are presented sequentially, and the initial asynchrony difference (SOA) is variable; the difficulty can be adjusted by decreasing the SOA and increasing the advanced accuracy threshold. Each training session consists of 30 trials and lasts 5-8 minutes.

[0044] This visual search cognitive task can be: requiring visual scanning and pattern recognition within a time limit. Trainees are shown multiple tangled wires (connecting a light bulb and a switch), and must identify the unique, complete connection and select the corresponding switch before the time limit expires. The difficulty is adjusted by increasing the visual complexity of the tangled wires (e.g., the number of bends, the degree of overlap) and shortening the maximum reaction time. Each training session consists of 50 trials and lasts 5-8 minutes.

[0045] This spatial span cognitive task can be adapted from the standardized Corsi block-tapping test to measure visuospatial working memory capacity. Trainees are shown a circular matrix, with some circles lit sequentially (each stimulus 500ms, interval 500ms). Participants must tap the circles in the same order. An adaptive ladder procedure is used to adjust the difficulty: the matrix size (length / width) and sequence length each increase by 1 after a correct response; the difficulty remains unchanged after an incorrect response; the difficulty decreases after two consecutive errors. The initial sequence length is 3, the matrix is ​​2×3, and there are 14 trials. Performance is quantified as average capacity K: K = M - 0.5 + Σ (i = 1 to n)Pi, where Pi is the average accuracy for different sequence lengths, and M is the minimum sequence length.

[0046] This symmetry span cognitive task can be adapted from the symmetry span task to assess spatial working memory under concurrent processing load. Trainees are shown a fixed 3×4 circular array. In each trial, participants first determine whether the butterfly presented in the center is symmetrical (with a 2-second reaction time limit, providing feedback); the butterfly then moves to a specific circle (presented after 500ms, visible for 800ms, then disappears). After a series of symmetry judgment / movement events, participants must click on the circles in the order the butterfly lands (positions are not repeated within the same trial). The difficulty is adjusted per trial (consistent with the spatial span task), with an initial sequence length of 3, a total of 14 trials, and a maximum sequence length of 10. Performance is quantified as average capacity K (calculated in the same way as the spatial span task).

[0047] This adapted symmetry span cognitive task can be: adapted from the symmetry span paradigm of Study 1, combining an individual presentation processing cognitive task (judging whether the centrally presented butterfly is symmetrical) and a spatial memory cognitive task. After each symmetry judgment, the butterfly moves to a unique cell in a 3×4 grid; after a series of trials, participants need to recall the spatial position of the butterfly according to four preset rules (e.g., symmetrical butterflies first, asymmetrical butterflies first, forward / reverse order). The difficulty is adjusted by increasing the number of butterflies in the sequence and using more complex recall rules. Each training session consists of 20 trials and lasts 5-8 minutes.

[0048] This object-location binding cognitive task can assess the ability to remember object-location bindings in a spatial context. Trainees are shown an animation in which a character walks on a city map, collecting items at specific locations; they then need to drag each item back to its original location on a blank map from a central inventory. The difficulty is adjusted by increasing the number of items, expanding their spatial distribution on the map, and shortening the encoding time for each collection. Each training session consists of 20 trials and lasts 5-8 minutes.

[0049] This spatial short-term memory cognitive task can assess the ability to remember object-location associations. Trainees are shown a sequence of unique visual stimuli (such as animal pattern cards) presented at specific locations within a grid; they then need to drag each stimulus back to its original position on a blank grid from a central stimulus library. The difficulty is adjusted by increasing the grid size (matrix dimension), the number of stimuli (set size), and shortening the encoding time for each stimulus. Each training session consists of 25 trials and lasts 5-8 minutes.

[0050] This multiple-choice reaction time cognitive task can be as follows: A central button is shown to the trainee, who clicks and holds the button to initiate a trial; after a variable delay, the target ("groundhog") appears in one of several holes nearby, and the participant must release the central button and quickly click the target. The difficulty can be adjusted by increasing the number of holes, shortening the target presentation time, lengthening the delay before the target appears, and increasing the number of trials per set. Each training session consists of 90 trials and lasts 5-8 minutes.

[0051] This discrimination-based reaction time cognitive task can involve target-distractor discrimination and reaction inhibition. Trainees are presented with a controllable character that moves along two lanes, collecting targets and avoiding distractions based on explicit cues (such as shape / color) using directional keys. The difficulty is adjusted by increasing the character's speed (shortening the reaction window), increasing error penalties (such as time loss), and increasing the frequency of rule-switching cues. Each training session consists of 5 trials, with a total duration of 7.5 minutes.

[0052] This length discrimination cognitive task can assess visual length estimation and perceptual-motor matching ability. Trainees are shown a white dotted line (of a specific length) connecting two pitons on a rock face. They must use the mouse to "cut" a virtual rope to match that length. The difficulty can be adjusted by changing the spatial orientation of the reference pitons, reducing the allowable error range (tolerance) for rope cutting, increasing the number of pitons that need to be connected consecutively in a single pass, and increasing the curvature of the reference line. Each training session consists of 30 trials and lasts 5-8 minutes.

[0053] This visual pattern completion exercise can be designed to achieve perceptual closure through observation and mental manipulation. Trainees are shown an incomplete image on one side and a set of pattern fragments on the other. They must mentally rotate and translate the fragments to precisely fill in the corresponding gaps in the image. The difficulty is adjusted by increasing the number of fragments, requiring adjustments to dependencies between fragments (placing one fragment affects the fit of others), and increasing the tolerance requirements for position and rotation alignment. Each training session consists of 40 trials and lasts 5-8 minutes.

[0054] This single-task cognitive task can be: completing three symmetry span cognitive tasks using different stimulus materials with varying degrees of symmetry. Trainees need to determine whether each stimulus (butterfly pattern, flower, abstract shape) is symmetrical and then recall its position. All tasks use a "one step forward, two steps back" step-up procedure to adjust difficulty. Each training session consists of two trials for each task, with a total duration of approximately 10 minutes.

[0055] In this embodiment, by setting these basic cognitive tasks, the standardization and comparability of the training are ensured, which effectively improves the accuracy of training trainees to improve their cognitive abilities.

[0056] In some embodiments, the advanced cognitive tasks in the cognitive graph database include digit 3 backtracking cognitive task, adaptive digit n backtracking task, nonverbal reasoning task, multi-domain cognitive task, multi-task processing cognitive task, multi-object tracking cognitive task, continuous recognition cognitive task, and control group cognitive task.

[0057] The 3-backtracking cognitive task can be adapted from Kirchner's n-backtracking paradigm to measure update ability. Trainees are presented with a fixed queue of four card positions. In each trial, the card enters from the leftmost position, briefly displays the number (≤3 seconds), and then flips and hides. Participants must determine whether the current number matches the numbers presented three positions prior (the 3-backtracking rule). There is a 500ms interval between stimuli, consisting of four sets of 23 trials each (20 requiring a response), with a 5-second rest between sets. The number of "same" and "different" trials in the stimulus sequence is balanced. Performance is quantified as a discrimination index d': d' = Z (hit rate) - Z (false alarm rate).

[0058] This adaptive digit n-backtracking cognitive task can be an adapted digit 3-backtracking task. Trainees are presented with a horizontal card position queue, the queue length varying with difficulty. In each trial, the cards enter from the leftmost position, briefly displaying the number (≤3 seconds) before being flipped and hidden. Participants must determine if the current number matches the numbers presented n positions prior. There is a 500ms interval between stimuli, comprising 8 sets, each with 20+n trials, with a 5-second rest between sets. Difficulty starts with 1-backtracking and is adjusted by module: n increases if there are <3 errors, decreases if there are >5 errors, otherwise n remains unchanged. The number of "same" and "different" trials in the stimulus sequence is balanced. Performance is quantified as the average n level of the last 5 sets (the first 3 sets are excluded as practice).

[0059] The nonverbal reasoning cognitive task (NVR) can be as follows: Trainees are presented with graphical questions using the Sandia Matrix, an open-source alternative to the Raven's Progressive Matrix, to assess their reasoning abilities. Each question is a 3×3 matrix with a missing bottom-right cell; participants choose the correct answer from eight options. There are six parallel sets of 40 questions each, with similar difficulty; participants complete one set per assessment session, with a 10-minute time limit. Performance is measured by average accuracy.

[0060] The multi-domain cognitive task (MD) can be: including three adaptive cognitive tasks targeting different cognitive domains (working memory, attention allocation, inhibition), where cognitive tasks can include symmetric breadth tasks, single-task cognitive tasks, and single-domain cognitive tasks.

[0061] The multitasking cognitive task can be: showing the trainee three consecutive tasks to be performed simultaneously: (1) monitoring and replenishing a periodically evaporating soup pot (soup pot task); (2) identifying and responding to a high-pitched target sound from an oven within 2 seconds (oven task); (3) monitoring up to 6 pancakes with changing colors and performing the corresponding operations (pancake task). Failure to respond in time will result in a deduction of points. The difficulty is adjusted by increasing the evaporation rate, increasing the frequency of the target sound, and increasing the number of active pancakes to be monitored. Each training session consists of 2 trial cycles, with a total duration of 10 minutes. ; Spatial Simon task: assessing reaction inhibition ability. A flock of birds facing a specific direction is presented on the screen; the flock either moves in the direction it is facing (consistent trial) or moves in the opposite direction (inconsistent trial); the subject needs to quickly and accurately determine the direction of movement (left / right). The maximum allowable reaction time (deadline) is adjusted by module: if the accuracy of the previous module is >85%, the deadline is shortened; if it is <60%, it is extended; if it is 60%-85%, it remains unchanged. Each training session consists of 2 modules (240 trials in total), with a total duration of approximately 10 minutes.

[0062] This multi-object tracking cognitive task (MOT) can be adapted from a classic multi-object tracking paradigm to assess visual attentional capacity (the ability to dynamically track multiple identical moving objects). At the start of each trial, the trainee is shown a set of identical objects ("fireflies"); some objects (targets) flash three times (on / off every 250ms) to mark them; then all objects become visually identical, move randomly for 8 seconds, and then stop; the participant must select all initial targets from the final static array. A tiered procedure is used to adjust the difficulty per trial: the number of targets increases by 1 after a correct response, remains unchanged after an incorrect response, and decreases by 1 after two consecutive errors. Performance is quantified as average tracking capacity K, calculated based on the accuracy at each target load level: K = M - 0.5 + Σ (i = 1 to n)Pi, where M is the minimum load and Pi is the accuracy sorted by increasing load.

[0063] The sequential recognition cognitive task (CRT) can be adapted from the standard sequential recognition paradigm to assess visual episodic memory. Trainees are presented with a long sequence of images (each image presented for 2000 ms, for a total of 256 trials); they must click a response button when an image is repeated, and not respond to new images (not repeated). To avoid the practice effect of repeated assessment, six parallel versions are designed, each using a unique set of images. Performance is quantified as a discrimination index d' based on hit rate and false alarm rate. To control for material differences between versions, each participant's raw d' is converted to a Z-score (standardized)—based on the mean and standard deviation of the control group included in the core analysis—to minimize the potential transfer effect of working memory training on the baseline distribution.

[0064] The control group's cognitive task can be: completing three adaptive training tasks for task transitions, adapted from a task transition program developed by Rogers and Monsell. All task transition training tasks require a response within a time limit, which is adjusted according to a preset time limit: if the accuracy of the previous module is >85%, the time limit is shortened; if <60%, it is extended; otherwise, it remains unchanged. Each training session completes two modules for each task: Task 1 contains 260 trials, and Tasks 2 and 3 each contain 300 trials, with a total duration of approximately 10 minutes. Tasks 1-3 can include color rule transition tasks, spatial rule transition tasks, and gender rule transition tasks.

[0065] The color rule conversion task here can be as follows: In each trial, 1-6 circles are distributed in the four quadrants of the smart terminal screen; the circle color (red / green) prompt task rules are as follows: for red, the total number of circles in the left and right halves of the field of vision must be compared, and for green, the total number of circles in the upper and lower halves of the field of vision must be compared; the subject must press the corresponding button within the time limit to report the judgment result (such as "left / right" or "up / down").

[0066] The spatial rule transformation task here could be: in each trial, number-letter pairs (such as "3G") are presented on the upper or lower half of the screen of the smart terminal; the presentation location prompt task: the upper half needs to determine the parity (even / odd) of the numbers, and the lower half needs to determine the vowel / consonant attribute of the letters; the subject responds to the prompt rules of each trial by pressing the corresponding button.

[0067] The gender rule switching task here could be: in each trial, a portrait photo is displayed in the center of the smart terminal screen; gender cues are categorized according to rules: for male faces, it is necessary to determine whether the subject is wearing glasses, and for female faces, it is necessary to determine whether the subject's expression is happy; the subject presses the corresponding button to respond to the perceptual characteristics of the cues.

[0068] In this embodiment, by setting up advanced cognitive tasks, the training of trainees' cognitive abilities is achieved by combining basic cognitive tasks with advanced cognitive tasks, thereby further improving the accuracy of training trainees to improve their cognitive abilities.

[0069] Step S140: Upon receiving the trainer's output of the final training result for the target task group, determine the target test score representing the trainer's cognitive ability based on the final training result.

[0070] In this embodiment, the target assessment score can be the total number of times the trainee completes the target task group and the cyclic cognitive task. For example, if the trainee's final training result is that the accuracy of the target task group or the cyclic cognitive task reaches 80%, the total number of times the trainee completes the target task group or the cyclic cognitive task can reflect the trainee's cognitive ability.

[0071] In some embodiments, prior to step S140, the method further includes the following steps S310 to S340: Step S310: Receive feedback information on the target task set shown to the trainee.

[0072] Step S320: If the feedback information indicates that the trainee meets the set bridging conditions, select matching recurrent cognitive tasks from the target task group according to the preset screening conditions.

[0073] Step S330: For the cyclic cognitive task, show the trainee the cyclic training results and obtain them.

[0074] Step S340: If the previous training cycle result indicates that the trainee meets the bridging condition, for the next training cycle result, repeat the steps of showing the training cycle result to the trainee and obtaining the training cycle result for the recurrent cognitive task until the next training cycle result does not meet the bridging condition, and take the next training cycle result as the final training result.

[0075] In this embodiment, after the trainer performs input operations on the target task group, the feedback information received by the smart terminal may include the training accuracy and the number of correct reactions in the target task group.

[0076] In some instances, the recurrent cognitive task is a high-level cognitive task. A recurrent cognitive task can also be a specific basic cognitive task, or it can include both high-level and basic cognitive tasks; this is not limited here. Recurrent training can be performed by mixing high-level and basic cognitive tasks to suit various training scenarios.

[0077] In this embodiment, the previous training cycle and the next training cycle can correspond to different training difficulties. The training difficulty can be adjusted according to the trainee's accuracy in the previous cognitive task.

[0078] In some embodiments, to ensure the readability of the trainee's final training results, bridging conditions may include the duration of all repetitive cognitive tasks performed being less than or equal to a set duration and the accuracy of the final training result being less than or equal to a set threshold. The accuracy of the final training result may be that the training accuracy of the next repetition is less than or equal to a set threshold, or that the number of correct reaction times is less than or equal to a set number.

[0079] In this embodiment, the filtering condition can be to filter out the advanced cognitive tasks in the target task group. If the feedback information indicates that the trainee meets the set bridging conditions, the advanced cognitive tasks in the target task group are re-exposed to the trainee for the next cycle training result, and the trainee's cycle training results for the advanced cognitive tasks in the target task group are obtained.

[0080] In this embodiment, by setting filtering conditions to select a portion of the target task group and retraining the trainees, the accuracy of training the trainees to improve their cognitive abilities can be further improved.

[0081] <Equipment Example 1> Figure 3 This is a schematic diagram of a training device for enhancing cognitive abilities according to one embodiment. Figure 3 As shown, the cognitive enhancement training device 300 may include: The response module 310 is used to obtain the trainer's feature information in response to the trainer's cognitive training request; The first determining module 320 is used to determine the high-level cognitive task indicated by the cognitive training request and the cognitive ability map corresponding to the high-level cognitive task; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task. The filtering module 330 is used to filter target basic cognitive tasks that match advanced cognitive tasks in a pre-set cognitive graph database through a cognitive ability graph, and to group the target basic cognitive tasks and advanced cognitive tasks as target task groups. Display module 340 is used to display the target task set to the trainee; The second determining module 350 is used to determine the target test score representing the trainee's cognitive ability based on the final training result of the trainee's output for the target task group.

[0082] In some embodiments, the filtering module 330 is further configured to filter matching basic cognitive tasks in a preset cognitive graph database according to each cognitive partition indicated by the cognitive ability graph, and form multiple basic cognitive task groups; wherein any two basic cognitive tasks in each basic cognitive task group correspond to different cognitive partitions; and filter target basic cognitive tasks that match advanced cognitive tasks in multiple basic cognitive task groups.

[0083] In some embodiments, the filtering module 330 is further configured to determine the explanatory power of multiple basic cognitive task groups for the advanced cognitive task, and obtain the basic cognitive task group with the highest explanatory power among the multiple basic cognitive task groups, as the target basic cognitive task matching the advanced cognitive task. In some embodiments, the cognitive enhancement training device 300 further includes a loop module for receiving feedback information on displaying a target task group to the trainee; when the feedback information indicates that the trainee meets the set bridging conditions, filtering matching loop cognitive tasks in the target task group according to preset filtering conditions; for the loop cognitive task, displaying and obtaining loop training results to the trainee; when the previous loop training result indicates that the trainee meets the bridging conditions, for the next loop training result, re-executing the steps of displaying and obtaining loop training results to the trainee for the loop cognitive task, until the next loop training result does not meet the bridging conditions, and taking the next loop training result as the final training result.

[0084] <Equipment Example 2> Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to another embodiment.

[0085] like Figure 4 As shown, the electronic device 400 includes a processor 410 and a memory 420, the memory 420 for storing an executable computer program, and the processor 410 for executing methods as described in any of the above method embodiments under the control of the computer program.

[0086] Each module of the cognitive ability enhancement training device 300 described above can be implemented by the processor 410 executing the computer program stored in the memory 420 in this embodiment, or it can be implemented by other structures, which are not limited here.

[0087] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for causing a processor to implement any of the methods in the foregoing embodiments of this disclosure. A computer-readable storage medium may be a tangible device capable of holding and storing instructions used by an instruction execution device. For example, a computer-readable storage medium may include an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), compact disc-read-only memory (CD-ROM), digital versatile disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any combination thereof. Computer-readable storage media as used herein is not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires. The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include one or more of copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media in the respective computing / processing device.The computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object programs written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Smalltalk, C++, etc.) and conventional procedural programming languages ​​(such as the "C" language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network (e.g., a local area network or a wide area network), or it may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays, or programmable logic arrays, may be customized by utilizing state information from the computer-readable program instructions to execute the computer-readable program instructions, thereby implementing various aspects of the embodiments of this disclosure. Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It should be noted that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are all equivalent. Various embodiments of the present disclosure have been described above; the above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this disclosure is defined by the appended claims.

Claims

1. A training method for improving cognitive abilities, characterized in that, The method includes: In response to a cognitive training request from a trainee, the trainee's characteristic information is obtained; Determine the high-level cognitive task indicated by the cognitive training request and the corresponding cognitive ability map of the high-level cognitive task; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task; Using the cognitive ability graph, in a pre-set cognitive graph database, target basic cognitive tasks that match the advanced cognitive tasks are selected from each basic cognitive task, and the target basic cognitive tasks and the advanced cognitive tasks are taken as a target task group. The target task set is shown to the trainee; Upon receiving the trainer's output of the final training result for the target task group, the target test score characterizing the trainer's cognitive ability is determined based on the final training result.

2. The method according to claim 1, characterized in that, The step of using the cognitive ability graph to filter target basic cognitive tasks that match the advanced cognitive tasks from a pre-set cognitive graph database includes: Based on the cognitive partitions indicated by the cognitive ability graph, each basic cognitive task is selected and matched in the preset cognitive graph database and formed into multiple basic cognitive task groups; wherein, any two basic cognitive tasks in each basic cognitive task group correspond to different cognitive partitions. Select target basic cognitive tasks from the multiple basic cognitive task groups that match the advanced cognitive task.

3. The method according to claim 2, characterized in that, The step of selecting the target basic cognitive task that matches the advanced cognitive task from the plurality of basic cognitive task groups includes: The explanatory power of the plurality of basic cognitive task groups for the advanced cognitive task is determined, and the basic cognitive task group with the maximum explanatory power among the plurality of basic cognitive task groups is obtained as the target basic cognitive task matching the advanced cognitive task.

4. The method according to claim 1, characterized in that, Before determining the target score representing the trainee's cognitive ability based on the final training result, the method further includes: Receive feedback information showing the target task set to the trainee; When the feedback information indicates that the trainee meets the set bridging conditions, the matching recurrent cognitive tasks in the target task group are selected according to the preset screening conditions. For repetitive cognitive tasks, the trainee is shown and the repetitive training results are obtained. If the previous training cycle result indicates that the trainee meets the bridging condition, for the next training cycle result, the steps of performing the recurrent cognitive task, showing the trainee the recurrent training result, and obtaining the recurrent training result are repeated until the next training cycle result does not meet the bridging condition, and the next training cycle result is taken as the final training result.

5. The method according to claim 4, characterized in that, The cyclical cognitive task is the advanced cognitive task.

6. The method according to claim 5, characterized in that, The bridging conditions include the duration of all the recurrent cognitive tasks performed being less than or equal to a set duration and the accuracy of the final training result being less than or equal to a set threshold.

7. A training device for enhancing cognitive abilities, characterized in that, The device includes: The response module is used to obtain the trainer's feature information in response to the trainer's cognitive training request; The first determining module is used to determine the high-level cognitive task indicated by the cognitive training request and the cognitive ability map corresponding to the high-level cognitive task; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task; The filtering module is used to filter target basic cognitive tasks that match the advanced cognitive tasks from the various basic cognitive tasks in the preset cognitive graph database through the cognitive ability graph, and to set the target basic cognitive tasks and the advanced cognitive tasks as a target task group. The display module is used to display the target task set to the trainee; The second determining module is used to determine the target test score characterizing the trainee's cognitive ability based on the final training result of the trainee's output for the target task group.

8. An electronic device, characterized in that, The system includes a memory and a processor, the memory being used to store a computer program; the processor being used to execute the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images