A cognitive function training intelligent push system and method based on multi-dimensional capability value

Abstract

The present invention belongs to the technical field of cognitive function training, and specifically relates to an intelligent push system and method for cognitive function training based on multi-dimensional ability values. The invention can more accurately evaluate the user's cognitive state and training effect by collecting real-time feedback from the user during cognitive function training. Through intelligent push, the training content and difficulty can be dynamically adjusted according to the user's actual needs and ability level, thereby improving the personalization and effectiveness of training. In addition, by continuously monitoring and updating the training list, it can ensure that the user is always trained in the best state, avoiding the problem of overtraining or undertraining. It aims to help users improve their cognitive ability and improve their quality of life by providing a comprehensive, dynamic and personalized cognitive function training program.

Description

Technical Field

[0001] The present invention belongs to the technical field of cognitive function training, and in particular relates to a cognitive function training intelligent push system and method based on multi-dimensional ability values. Background Art

[0002] With the rapid development of science and technology, the application of artificial intelligence technology in various fields has become more and more extensive, especially in the field of cognitive function training. The intelligent push system can provide corresponding learning resources and training content according to the user's learning situation and ability level, so that the user's cognitive ability can be improved.

[0003] However, in previous training, it was necessary to manually formulate individual training plans, which not only required a large workload but was also affected by individual abilities. The training was not targeted and could not quickly find the dimensions in which individuals were weaker in ability, provide training areas suitable for individuals, generate individualized training plans, and achieve accurate and effective treatment. Based on this, this solution provides an intelligent push method for cognitive function training based on multi-dimensional ability values ​​to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent push system and method for cognitive function training based on multi-dimensional ability values, which can quickly find the dimensions in which individual abilities are weak, provide training areas suitable for individuals, and generate individualized training plans.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A method for intelligently pushing cognitive function training based on multi-dimensional capability values, comprising:

[0007] Acquiring a multi-dimensional ability value of a user for cognitive function training, wherein the multi-dimensional ability value includes visual perception, auditory perception, sensory perception, working memory, organizational planning, and inhibitory control;

[0008] Determine the ability level score of the user's cognitive ability value in each dimension according to the multi-dimensional ability value, and determine the cognitive state of each dimension according to the ability level score, wherein the cognitive state includes a normal state and an abnormal state;

[0009] Collecting the difference between the user's cognitive ability value and a preset standard ability value under the abnormal state, and recording it as an abnormal cognitive difference;

[0010] Outputting the abnormal level of each of the cognitive ability values ​​according to the abnormal cognitive difference, and determining the order of pushing each of the cognitive ability values ​​according to the abnormal level;

[0011] Generate a cognitive function training list according to the push sequence, and push the cognitive function training contents one by one according to the cognitive function training list;

[0012] The user feedback parameters after the cognitive function training list is executed are collected, and the cognitive function training list is updated according to the user feedback parameters.

[0013] In a preferred embodiment, when obtaining the multi-dimensional ability value of the user for cognitive function training, training is performed in the directions of attention, memory, logical thinking, spatial perception and emotional regulation;

[0014] The attention corresponds to visual perception and auditory perception, memory corresponds to working memory, logical thinking corresponds to organizational planning, spatial perception corresponds to sensory perception, and emotional regulation corresponds to inhibitory control;

[0015] After the multi-dimensional capability value is output, pre-processing is performed synchronously, and the pre-processing includes:

[0016] Performing data cleaning on the multi-dimensional capability values ​​to remove invalid data and outliers;

[0017] The cleaned multi-dimensional capability values ​​are standardized to unify the data formats of all the multi-dimensional capability values.

[0018] In a preferred embodiment, the step of determining the ability level score of the user's cognitive ability value in each dimension based on the multi-dimensional ability value includes:

[0019] Obtain the cognitive ability values ​​of users trained in various dimensions;

[0020] quantifying the cognitive ability value, and recording the quantified cognitive ability value as an allocation condition parameter;

[0021] Get the scoring criteria for each dimension;

[0022] Compare the user's cognitive ability value with the corresponding scoring criteria to match the ability level scores of the cognitive ability values ​​in each dimension.

[0023] In a preferred embodiment, the step of determining the cognitive status of each dimension according to the ability level score includes:

[0024] Constructing a monitoring period and setting a plurality of sampling nodes within the monitoring period;

[0025] Collecting the ability level scores of the user's cognitive ability values ​​in each dimension at each sampling node and recording them as evaluation condition parameters;

[0026] Obtaining an evaluation function, inputting the evaluation condition parameter into the evaluation function, and recording the output result of the evaluation function as a state evaluation parameter;

[0027] Obtaining the evaluation threshold corresponding to the cognitive ability value under each dimension, and comparing the evaluation threshold with the state evaluation parameter;

[0028] If the state evaluation parameter is greater than the evaluation threshold, it indicates that the user's cognitive ability value in the corresponding dimension tends to be abnormal, and the cognitive state of the user's cognitive ability value in the corresponding dimension is set to an abnormal state;

[0029] If the state evaluation parameter is less than or equal to the evaluation threshold, it indicates that the user's cognitive ability value in this dimension is within the normal range, and the cognitive state of the user's cognitive ability value in the corresponding dimension is set to a normal state.

[0030] In a preferred embodiment, the step of outputting the abnormal level of each cognitive ability value according to the abnormal cognitive difference comprises:

[0031] Obtain the abnormal cognitive difference of cognitive ability values ​​in each dimension under abnormal conditions;

[0032] Obtaining an evaluation interval, wherein a plurality of evaluation intervals are provided, and each evaluation interval corresponds to an abnormality level;

[0033] The abnormal cognitive difference is matched with the evaluation interval, and the abnormal level of cognitive ability value in each dimension is output.

[0034] In a preferred embodiment, the push rounds of the cognitive function training content in the cognitive function training list are 5 to 8 rounds, and in the cognitive function training list, the push duration of the cognitive function training content is proportional to the ranking of the cognitive function training content.

[0035] In a preferred embodiment, the step of collecting user feedback parameters after the cognitive function training list is executed includes:

[0036] Obtaining the real-time abnormal cognitive difference of each cognitive ability value after the cognitive function training list is executed, and recording it as a feedback condition parameter;

[0037] Sorting the feedback condition parameters according to the execution order of the push rounds of the cognitive function training list;

[0038] According to the arrangement order of the feedback condition parameters, the feedback condition parameters in adjacent positions are compared to obtain the recovery amount of the user's cognitive function and record it as the user feedback parameter.

[0039] In a preferred embodiment, the step of updating the cognitive function training list according to the user feedback parameter includes:

[0040] Obtaining all the user feedback parameters;

[0041] According to the value of the user feedback parameter, the user feedback parameter is classified into a positive parameter and a negative parameter, wherein under the positive parameter, the user's cognitive ability tends to recover, and under the negative parameter, the user's cognitive ability tends to decline;

[0042] Counting the number of the reverse parameters under the same cognitive ability value, and calculating the proportion of cognitive decline after cognitive function training according to the number of the reverse parameters, and synchronously outputting them as the first-level update condition parameter;

[0043] Counting the positive parameters of the same cognitive ability when the first-level update condition parameter takes a value of zero, and recording them as the second-level update condition parameter;

[0044] updating the cognitive function training list according to the primary update condition parameters and the secondary update condition parameters;

[0045] Wherein, when the cognitive function training list is updated, the sorting of cognitive ability values ​​under the primary update condition parameters is performed first, and then the sorting of cognitive ability values ​​under the secondary update condition parameters is performed.

[0046] The present invention also provides a system for intelligently pushing cognitive function training based on multi-dimensional capability values, using the above-mentioned intelligent pushing method for cognitive function training based on multi-dimensional capability values, including:

[0047] A data acquisition module, the acquisition module is used to acquire the multi-dimensional ability value of the user for cognitive function training, wherein the multi-dimensional ability value includes visual perception, auditory perception, sensory perception, working memory, organizational planning and inhibitory control;

[0048] A state classification module, the state classification module is used to determine the ability level score of the user's cognitive ability value in each dimension according to the multi-dimensional ability value, and determine the cognitive state of each dimension according to the ability level score, wherein the cognitive state includes a normal state and an abnormal state;

[0049] A difference output module, the difference output module is used to collect the difference between the user's cognitive ability value and a preset standard ability value in the abnormal state, and record it as an abnormal cognitive difference;

[0050] A level assessment module, the level assessment module is used to output the abnormal level of each cognitive ability value according to the abnormal cognitive difference, and determine the push order of each cognitive ability value according to the abnormal level;

[0051] A push module, the push module is used to generate a cognitive function training list according to the push sequence, and push the cognitive function training content one by one according to the cognitive function training list;

[0052] A list updating module is used to collect user feedback parameters after the cognitive function training list is executed, and update the cognitive function training list according to the user feedback parameters.

[0053] And, an electronic device, the electronic device comprising:

[0054] at least one processor;

[0055] and a memory communicatively coupled to the at least one processor;

[0056] Among them, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned intelligent push method based on multi-dimensional ability value cognitive function training.

[0057] The technical effects achieved by the present invention are:

[0058] By collecting real-time feedback from users during cognitive function training, the present invention can more accurately evaluate the user's cognitive state and training effect. Through intelligent push, the training content and difficulty can be dynamically adjusted according to the user's actual needs and ability level, thereby improving the personalization and effectiveness of training. In addition, by continuously monitoring and updating the training list, it can ensure that the user is always trained in the best state to avoid the problem of overtraining or undertraining. The purpose is to help users improve their cognitive ability and enhance their quality of life by providing a comprehensive, dynamic and personalized cognitive function training program. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic flow chart of the method of the present invention;

[0060] Figure 2 It is a schematic diagram of the system module of the present invention;

[0061] Figure 3 It is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0064] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0065] See also Figure 1 As shown, the present invention provides an intelligent push method for cognitive function training based on multi-dimensional capability values, comprising:

[0066] S1. Obtaining the multi-dimensional ability value of the user for cognitive function training, wherein the multi-dimensional ability value includes visual perception, auditory perception, sensory perception, working memory, organizational planning, and inhibitory control;

[0067] S2. Determine the ability level score of the user's cognitive ability value in each dimension based on the multi-dimensional ability value, and determine the cognitive state of each dimension based on the ability level score, wherein the cognitive state includes a normal state and an abnormal state;

[0068] S3, collecting the difference between the user's cognitive ability value and the preset standard ability value under abnormal conditions, and recording it as abnormal cognitive difference;

[0069] S4. Outputting the abnormal level of each cognitive ability value according to the abnormal cognitive difference, and determining the order of pushing each cognitive ability value according to the abnormal level;

[0070] S5. Generate a cognitive function training list according to the push order, and push the cognitive function training contents one by one according to the cognitive function training list;

[0071] S6. Collect user feedback parameters after the cognitive function training list is executed, and update the cognitive function training list according to the user feedback parameters.

[0072] As described in the above steps S1-S6, with the continuous development of information technology, the intelligent push method can more accurately meet the personalized needs of users. By real-time monitoring and analyzing the changes in the user's cognitive ability, the push order of the training content can be dynamically adjusted. In this embodiment, the multi-dimensional ability values ​​of the user during cognitive function training will be first obtained. These multi-dimensional ability values ​​cover multiple aspects such as visual perception, auditory perception, sensory perception, working memory, organizational planning, and inhibitory control. Through multi-dimensional evaluation, the user's performance in cognitive function can be fully understood. Then, based on these multi-dimensional ability values, the ability level of the user's cognitive ability value in each dimension will be scored. The scoring results will help determine the user's cognitive ability level score in each dimension. According to the ability level score, the cognitive state of each dimension can be further judged. The cognitive state is mainly divided into two types: normal state and abnormal state. After determining the cognitive state, for the dimension of the abnormal state, the difference between the user's cognitive ability value and the preset standard ability value will be collected, and the difference will be recorded as the abnormal cognitive difference. The abnormal cognitive difference reflects the difference between the user and the standard level in a specific dimension. The difference in level provides a basis for subsequent training. According to the abnormal cognitive difference, the abnormal level of each cognitive ability value will be output. The level of abnormality will directly affect the push order of each cognitive ability value, that is, according to the level of abnormality, the cognitive ability value with a higher abnormal level will be pushed first to ensure that the user can get targeted training first. Then, a cognitive function training list will be generated according to the push order. The cognitive function training list will guide the user to perform the corresponding cognitive function training content. After that, the cognitive function training content will be pushed one by one according to the cognitive function training list to ensure that the user can perform training in the established order and priority. The push rounds of cognitive function training content in the cognitive function training list are 5 to 8 rounds, and in the cognitive function training list, the push duration of cognitive function training content is proportional to the ranking of cognitive function training content. Finally, the feedback parameters provided by the user after completing the cognitive function training list will be collected. The user feedback parameters are used to reflect the user's training effect. The cognitive function training list will also be updated according to the user feedback parameters to ensure that the training content can better meet the needs of the user and improve the training effect.

[0073] In a preferred embodiment, when obtaining the multi-dimensional ability value of the user for cognitive function training, training is performed in the directions of attention, memory, logical thinking, spatial perception and emotional regulation;

[0074] Attention corresponds to visual and auditory perception, memory corresponds to working memory, logical thinking corresponds to organizational planning, spatial perception corresponds to sensory perception, and emotional regulation corresponds to inhibitory control;

[0075] Among them, after the multi-dimensional capability values ​​are output, preprocessing is performed synchronously, and the preprocessing includes:

[0076] Perform data cleaning on multi-dimensional capability values ​​to remove invalid data and outliers;

[0077] The cleaned multi-dimensional capability values ​​are standardized to unify the data format of all multi-dimensional capability values.

[0078] In this implementation, during the process of user cognitive function training, the user is committed to comprehensively evaluating and improving the user's multi-dimensional ability values, covering multiple aspects such as attention, memory, logical thinking, spatial perception and emotional regulation. Specifically, attention training aims to improve the user's visual and auditory attention, memory training focuses on enhancing the user's working memory ability, logical thinking exercises the user's thinking order and planning ability by organizing and planning tasks, spatial perception improves the user's spatial cognitive ability through perceptual training, and emotional regulation helps users better manage their emotional responses through inhibitory control training. In order to ensure accurate evaluation of the training effect , it is necessary to record and analyze the user's multi-dimensional ability values ​​in detail. After the user's cognitive ability values ​​are output, they need to go through a series of preprocessing steps to ensure the accuracy and availability of the data. The first step of preprocessing is to clean the multi-dimensional ability values, including eliminating invalid or incomplete data, and identifying and excluding outliers. Outliers may be caused by technical failures or user errors. After data cleaning is completed, the cleaned data will be standardized. The purpose is to unify all multi-dimensional ability values ​​into a standardized data format for subsequent analysis and comparison, to ensure the accuracy and reliability of subsequent analysis, and thus provide users with more accurate cognitive function training programs.

[0079] In a preferred embodiment, the step of determining the ability level score of the user's cognitive ability value in each dimension according to the multi-dimensional ability value includes:

[0080] S201, obtaining the cognitive ability values ​​trained by the user in various dimensions;

[0081] S202, quantifying the cognitive ability value, and recording the quantified cognitive ability value as an allocation condition parameter;

[0082] S203, obtaining scoring criteria under each dimension;

[0083] S204: Compare the user's cognitive ability value with the corresponding scoring standard to match the ability level score of the cognitive ability value in each dimension.

[0084] As described in the above steps S201-S204, in order to accurately evaluate the user's cognitive ability level scores in different dimensions, it is first necessary to obtain the cognitive ability values ​​demonstrated by the user after training in each dimension, and at the same time, it is necessary to quantify these cognitive ability values. The purpose of quantification is to convert the user's cognitive ability value into a numerical form that can be compared and analyzed, which usually involves comparing the user's test results with a standardized scoring system, so as to convert the user's actual performance into a quantitative score. The quantified cognitive ability value will be recorded and used as an allocation condition parameter for subsequent analysis. After the quantification, it is necessary to obtain the scoring criteria under each dimension. The scoring criteria is a key reference for evaluating the user's cognitive ability level. A clear scoring range and grade division are set for each dimension. The scoring criteria are usually formulated by an expert team based on a large amount of research and practical experience to ensure its scientificity and accuracy. Finally, the user's cognitive ability value is compared with the corresponding scoring criteria, and the ability level score of the user's cognitive ability value in each dimension can be matched, thereby reflecting the user's specific performance level in each dimension, thereby providing the user with a comprehensive and detailed cognitive ability assessment report.

[0085] In a preferred embodiment, the step of determining the cognitive status of each dimension according to the ability level score includes:

[0086] S205, constructing a monitoring period, and setting a plurality of sampling nodes within the monitoring period;

[0087] S206, collecting the ability level scores of the user's cognitive ability values ​​in each dimension at each sampling node, and recording them as evaluation condition parameters;

[0088] S207, obtaining an evaluation function, inputting the evaluation condition parameters into the evaluation function, and recording the output result of the evaluation function as a state evaluation parameter;

[0089] S208, obtaining the evaluation threshold corresponding to the cognitive ability value in each dimension, and comparing the evaluation threshold with the state evaluation parameter;

[0090] If the state evaluation parameter is greater than the evaluation threshold, it indicates that the user's cognitive ability value in the corresponding dimension tends to be abnormal, and the cognitive state of the user's cognitive ability value in the corresponding dimension is set as an abnormal state;

[0091] If the state evaluation parameter is less than or equal to the evaluation threshold, it indicates that the user's cognitive ability value in this dimension is within the normal range, and the cognitive state of the user's cognitive ability value in the corresponding dimension is set to a normal state.

[0092] As described in the above steps S205-S208, in order to determine the cognitive status of each dimension according to the ability level score, first, a monitoring period needs to be constructed. During the monitoring period, multiple sampling nodes are also set. The sampling nodes will serve as key time points for collecting data. At each sampling node, the ability level score of the user in each dimension will be collected and recorded as an evaluation condition parameter. Next, a preset evaluation function is introduced to analyze and process the evaluation condition parameters we collected, where the expression of the evaluation function is: , where represents the state evaluation parameter, Represents the evaluation condition parameters under the last sampling node, Indicates the predicted duration based on the current node sequence offset. The purpose is to intervene in the calculation of whether the user's cognitive ability value will be abnormal in the future. Indicates the length of the monitoring period, Indicates the number of evaluation condition parameters, and It represents the evaluation condition parameters under adjacent sampling nodes. By inputting the evaluation condition parameters into the evaluation function and recording the output results of the function as state evaluation parameters, it can help understand the user's cognitive state in each dimension. Specifically, it is necessary to obtain the evaluation threshold corresponding to the cognitive ability value in each dimension. The evaluation threshold is a pre-set standard value used to determine whether the user's cognitive ability in each dimension is within the normal range. The evaluation threshold is compared with the state evaluation parameter. If the state evaluation parameter is greater than the evaluation threshold, it means that the user's cognitive ability value in the corresponding dimension tends to be abnormal. In this case, the cognitive state of the user's cognitive ability value in the corresponding dimension is marked as an abnormal state. On the contrary, if the state evaluation parameter is less than or equal to the evaluation threshold, it indicates that the user's cognitive ability value in this dimension is within the normal range. At this time, the cognitive state of the user's cognitive ability value in the corresponding dimension is marked as a normal state. In this way, the user's cognitive state in each dimension can be accurately determined according to the ability level score, thereby providing a scientific basis for subsequent intervention and guidance.

[0093] In a preferred embodiment, the step of outputting the abnormal level of each cognitive ability value according to the abnormal cognitive difference includes:

[0094] Obtain the abnormal cognitive difference of cognitive ability values ​​in each dimension under abnormal conditions;

[0095] Obtain an evaluation interval, wherein a plurality of evaluation intervals are set, and each evaluation interval corresponds to an abnormality level;

[0096] Match the abnormal cognitive difference with the evaluation interval and output the abnormal level of cognitive ability value in each dimension.

[0097] In this embodiment, in order to accurately evaluate the abnormal level of each cognitive ability value under abnormal conditions, it is first necessary to obtain the abnormal cognitive difference of the cognitive ability value in each dimension under abnormal conditions, that is, the difference between each cognitive dimension (such as attention, memory, logical thinking, etc.) and that under normal conditions, and then introduce a preset evaluation interval. The evaluation interval includes multiple different interval segments, each interval segment corresponds to a specific abnormal level. For example, an abnormal level from low to high can be set, such as slight abnormality, moderate abnormality, severe abnormality, etc. Each level has a corresponding numerical range for matching and evaluation. Finally, the acquired abnormal cognitive difference is matched with the set evaluation interval. By comparing the numerical range of the abnormal cognitive difference with the range of each evaluation interval, the abnormal level of the cognitive ability value in each dimension can be determined. For example, if the cognitive difference of a certain dimension falls within the severe abnormal interval, then it can be concluded that the cognitive ability value of the dimension belongs to the severe abnormal level. Based on this, the abnormal level of each cognitive ability value under abnormal conditions can be systematically evaluated.

[0098] In a preferred embodiment, the step of collecting user feedback parameters after the cognitive function training list is executed includes:

[0099] S601, obtaining the real-time abnormal cognitive difference of each cognitive ability value after the cognitive function training list is executed, and recording it as a feedback condition parameter;

[0100] S602, sorting the feedback condition parameters according to the execution order of the push rounds of the cognitive function training list;

[0101] S603: Compare the feedback condition parameters in adjacent positions according to the arrangement order of the feedback condition parameters to obtain the recovery amount of the user's cognitive function and record it as the user feedback parameter.

[0102] As described in the above steps S601-S603, in order to ensure the accuracy of the user feedback parameters collected after the execution of the cognitive function training list is completed, it is first necessary to obtain the real-time abnormal cognitive difference of each cognitive ability value after the execution of the cognitive function training list is completed, and record it as a feedback condition parameter, and then the feedback condition parameters need to be sorted according to the execution order of the push round of the cognitive function training list, that is, the feedback condition parameters are sorted according to the execution time sequence of each training item in the training list. This sorting process helps us better understand the user's performance at different training stages, so as to more accurately evaluate the user's cognitive function recovery. Finally, the feedback condition parameters under adjacent positions will be compared according to the arrangement order of the feedback condition parameters. Through this comparison, the recovery amount of the user's cognitive function can be obtained. Specifically, the changes in the user's cognitive ability values ​​at different training stages will be analyzed to evaluate the user's cognitive function recovery. These recovery amounts will be recorded as user feedback parameters to provide a corresponding basis for subsequent training adjustments and optimizations.

[0103] In a preferred embodiment, the step of updating the cognitive function training list according to the user feedback parameter includes:

[0104] Get all user feedback parameters;

[0105] According to the value of the user feedback parameter, the user feedback parameter is classified into positive parameters and negative parameters. Under the positive parameter, the user's cognitive ability tends to recover, and under the negative parameter, the user's cognitive ability tends to decline.

[0106] Count the number of reverse parameters under the same cognitive ability value, and calculate the proportion of cognitive decline after cognitive function training according to the number of reverse parameters, and output them synchronously as the first-level update condition parameters;

[0107] The positive parameters of the same cognitive ability when the first-level update condition parameter is zero are counted and recorded as the second-level update condition parameter;

[0108] The cognitive function training list is updated according to the primary updating condition parameter and the secondary updating condition parameter;

[0109] Among them, when the cognitive function training list is updated, the sorting of cognitive ability values ​​under the first-level update condition parameters is performed first, and then the sorting of cognitive ability values ​​under the second-level update condition parameters is performed.

[0110] In order to ensure that the cognitive function training list can be effectively updated according to the actual feedback of users, it is necessary to first obtain all user feedback parameters to reflect the changes in the user's cognitive ability during the training process. Then, the user feedback parameters will be classified according to the values ​​of the user feedback parameters. Specifically, the user feedback parameters will be divided into two categories: positive parameters and reverse parameters. The positive parameters indicate that the user's cognitive ability has recovered or improved after training, while the reverse parameters indicate that the user's cognitive ability has declined or decreased after training. After the classification is completed, it is necessary to count the reverse parameters under the same cognitive ability value. By calculating the number of reverse parameters, the proportion of cognitive ability decline after cognitive function training can be evaluated. This proportion will be used as the first-level update condition parameter for subsequent update processing. At the same time, it is also necessary The number of positive parameters under the same cognitive ability value and when the first-level update condition parameter is zero is counted. The number of positive parameters will be recorded as the second-level update condition parameter for further refining the conditions for the update process. Finally, the cognitive function training list will be updated based on the first-level update condition parameter and the second-level update condition parameter. During the update process, the cognitive ability values ​​under the first-level update condition parameter will be sorted first to ensure that the cognitive ability values ​​with more obvious cognitive decline can be given priority attention and adjustment. Subsequently, the cognitive ability values ​​under the second-level update condition parameter will be sorted to further optimize and refine the cognitive function training list, ensuring that the cognitive function training list can be effectively updated based on the actual feedback of users, so as to better meet the personalized needs of users and improve the effect of cognitive function training.

[0111] See also Figure 2 , a multi-dimensional capability value based cognitive function training intelligent push system, using the above-mentioned multi-dimensional capability value based cognitive function training intelligent push method, including:

[0112] A data acquisition module, the acquisition module is used to obtain the multi-dimensional ability values ​​of the user for cognitive function training, wherein the multi-dimensional ability values ​​include visual perception, auditory perception, sensory perception, working memory, organizational planning and inhibitory control;

[0113] A state classification module, which is used to determine the ability level score of the user's cognitive ability value in each dimension based on the multi-dimensional ability value, and determine the cognitive state of each dimension based on the ability level score, wherein the cognitive state includes a normal state and an abnormal state;

[0114] The difference output module is used to collect the difference between the user's cognitive ability value and the preset standard ability value under abnormal conditions, and record it as abnormal cognitive difference;

[0115] The level assessment module is used to output the abnormal level of each cognitive ability value according to the abnormal cognitive difference, and determine the push order of each cognitive ability value according to the abnormal level;

[0116] A push module, which is used to generate a cognitive function training list according to a push order, and push the cognitive function training content one by one according to the cognitive function training list;

[0117] The list updating module is used to collect user feedback parameters after the cognitive function training list is executed, and update the cognitive function training list according to the user feedback parameters.

[0118] In the above, the system includes a data acquisition module, a state classification module, a differential output module, a grade assessment module, a push module and a list update module. The data acquisition module is responsible for collecting the multi-dimensional ability values ​​of the user when conducting cognitive function training. The multi-dimensional ability values ​​cover visual perception, auditory perception, sensory perception, working memory, organizational planning and inhibitory control. Based on this, the system can fully understand the user's performance in various cognitive dimensions. The state classification module scores the user's cognitive ability values ​​in each dimension according to the collected multi-dimensional ability values. Based on the ability level score, the user's cognitive state in each dimension can be judged. The cognitive state can be divided into two categories: normal state and abnormal state. The differential output module focuses on users in abnormal states, and will record the difference between the user's cognitive ability value in abnormal states and the preset standard ability value, and define these differences as abnormal cognitive differentials. The grade assessment module is based on the abnormal cognitive differentials. , evaluate the abnormal level of each cognitive ability value. In this way, the system can determine the push order of each cognitive ability value to ensure that the ability values ​​that need to be trained are pushed first. The push module generates a cognitive function training list according to the determined push order. The list contains the cognitive ability values ​​and related content that users need to train. The push module will push the cognitive function training content one by one according to this list to ensure that users can train according to the established priority. After the user completes the task in the cognitive function training list, the list update module will collect the user's feedback parameters. The user feedback parameters include the user's training effect on the training content, etc. The list update module will dynamically adjust the cognitive function training list according to these feedback parameters to ensure that the training content always meets the user's actual needs and progress, and provide users with personalized cognitive function training plans to help users make progress in various cognitive dimensions, thereby improving overall cognitive ability.

[0119] See also Figure 3 , an electronic device, the electronic device comprising:

[0120] at least one processor;

[0121] and a memory communicatively coupled to the at least one processor;

[0122] Among them, the memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned intelligent push method based on multi-dimensional ability value cognitive function training.

[0123] The processor of the above electronic device can be a central processing unit (CPU) or a graphics processing unit (GPU), which can efficiently process large amounts of data and complex computing tasks. The memory includes an internal memory and an external memory. The internal memory can be a random access memory (RAM), and the external memory can be a hard disk drive (HDD) or a solid-state drive (SSD), which together provide sufficient storage space and fast data access speed for the electronic device. In addition, the electronic device can also include an arithmetic unit and an input-output device. The arithmetic unit can perform complex mathematical operations, while the input-output device allows the user to interact with the system, provide training data, and receive training results.

[0124] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0125] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A method for intelligently pushing cognitive function training based on multi-dimensional capability values, characterized in that: include: Acquiring a multi-dimensional ability value of a user for cognitive function training, wherein the multi-dimensional ability value includes visual perception, auditory perception, sensory perception, working memory, organizational planning, and inhibitory control; Determine the ability level score of the user's cognitive ability value in each dimension according to the multi-dimensional ability value, and determine the cognitive state of each dimension according to the ability level score, wherein the cognitive state includes a normal state and an abnormal state; Collecting the difference between the user's cognitive ability value and a preset standard ability value under the abnormal state, and recording it as an abnormal cognitive difference; According to the abnormal cognitive difference, the abnormal level of each cognitive ability value is output, and the order of pushing each cognitive ability value is determined according to the abnormal level; according to the abnormal level, the cognitive ability value with a higher abnormal level is pushed first to ensure that the user can get targeted training first, and then a cognitive function training list is generated according to the push order. The cognitive function training list will guide the user to perform the corresponding cognitive function training content, and then the cognitive function training content is pushed one by one according to the cognitive function training list to ensure that the user can perform training according to the established order and priority; Collecting user feedback parameters after the cognitive function training list is executed, and updating the cognitive function training list according to the user feedback parameters; The step of collecting user feedback parameters after the cognitive function training list is executed includes: Obtaining the real-time abnormal cognitive difference of each cognitive ability value after the cognitive function training list is executed, and recording it as a feedback condition parameter; Sorting the feedback condition parameters according to the execution order of the push rounds of the cognitive function training list; According to the arrangement order of the feedback condition parameters, the feedback condition parameters in adjacent positions are compared to obtain the recovery amount of the user's cognitive function and record it as the user feedback parameter; The step of updating the cognitive function training list according to the user feedback parameters includes: Obtaining all the user feedback parameters; According to the value of the user feedback parameter, the user feedback parameter is classified into a positive parameter and a negative parameter, wherein under the positive parameter, the user's cognitive ability tends to recover, and under the negative parameter, the user's cognitive ability tends to decline; Counting the number of the reverse parameters under the same cognitive ability value, and calculating the proportion of cognitive decline after cognitive function training according to the number of the reverse parameters, and synchronously outputting them as the first-level update condition parameter; Counting the positive parameters of the same cognitive ability when the first-level update condition parameter takes a value of zero, and recording them as the second-level update condition parameter; updating the cognitive function training list according to the primary update condition parameters and the secondary update condition parameters; Wherein, when the cognitive function training list is updated, the sorting of cognitive ability values ​​under the primary update condition parameters is performed first, and then the sorting of cognitive ability values ​​under the secondary update condition parameters is performed.

2. The intelligent push method for cognitive function training based on multi-dimensional ability values ​​according to claim 1 is characterized by: When obtaining the multi-dimensional ability value of the user for cognitive function training, training is performed in the directions of attention, memory, logical thinking, spatial perception and emotional regulation; The attention corresponds to visual perception and auditory perception, memory corresponds to working memory, logical thinking corresponds to organizational planning, spatial perception corresponds to sensory perception, and emotional regulation corresponds to inhibitory control; After the multi-dimensional capability value is output, pre-processing is performed synchronously, and the pre-processing includes: Performing data cleaning on the multi-dimensional capability values ​​to remove invalid data and outliers; The cleaned multi-dimensional capability values ​​are standardized to unify the data formats of all the multi-dimensional capability values.

3. The intelligent push method for cognitive function training based on multi-dimensional ability value according to claim 1 is characterized by: The step of determining the ability level score of the user's cognitive ability value in each dimension based on the multi-dimensional ability value includes: Obtain the cognitive ability values ​​of users trained in various dimensions; quantifying the cognitive ability value, and recording the quantified cognitive ability value as an allocation condition parameter; Get the scoring criteria for each dimension; Compare the user's cognitive ability value with the corresponding scoring criteria to match the ability level scores of the cognitive ability values ​​in each dimension.

4. The intelligent push method for cognitive function training based on multi-dimensional ability value according to claim 1 is characterized by: The step of determining the cognitive status of each dimension according to the ability level score comprises: Constructing a monitoring period and setting a plurality of sampling nodes within the monitoring period; Collecting the ability level scores of the user's cognitive ability values ​​in each dimension at each sampling node and recording them as evaluation condition parameters; Obtaining an evaluation function, inputting the evaluation condition parameter into the evaluation function, and recording the output result of the evaluation function as a state evaluation parameter; Obtaining the evaluation threshold corresponding to the cognitive ability value under each dimension, and comparing the evaluation threshold with the state evaluation parameter; If the state evaluation parameter is greater than the evaluation threshold, it indicates that the user's cognitive ability value in the corresponding dimension tends to be abnormal, and the cognitive state of the user's cognitive ability value in the corresponding dimension is set to an abnormal state; If the state evaluation parameter is less than or equal to the evaluation threshold, it indicates that the user's cognitive ability value in this dimension is within the normal range, and the cognitive state of the user's cognitive ability value in the corresponding dimension is set to a normal state.

5. The intelligent push method for cognitive function training based on multi-dimensional ability value according to claim 1 is characterized by: The step of outputting the abnormal level of each of the cognitive ability values ​​according to the abnormal cognitive difference comprises: Obtain the abnormal cognitive difference of cognitive ability values ​​in each dimension under abnormal conditions; Obtaining an evaluation interval, wherein a plurality of evaluation intervals are provided, and each evaluation interval corresponds to an abnormality level; The abnormal cognitive difference is matched with the evaluation interval, and the abnormal level of cognitive ability value in each dimension is output.

6. The intelligent push method for cognitive function training based on multi-dimensional ability value according to claim 1 is characterized by: The push rounds of the cognitive function training content in the cognitive function training list are 5 to 8 rounds, and in the cognitive function training list, the push duration of the cognitive function training content is proportional to the ranking of the cognitive function training content.

7. An intelligent push system for cognitive function training based on multi-dimensional capability values, characterized by: The method for intelligently pushing cognitive function training based on multi-dimensional capability values ​​according to any one of claims 1 to 6 comprises: A data acquisition module, the acquisition module is used to acquire the multi-dimensional ability value of the user for cognitive function training, wherein the multi-dimensional ability value includes visual perception, auditory perception, sensory perception, working memory, organizational planning and inhibitory control; A state classification module, the state classification module is used to determine the ability level score of the user's cognitive ability value in each dimension according to the multi-dimensional ability value, and determine the cognitive state of each dimension according to the ability level score, wherein the cognitive state includes a normal state and an abnormal state; A difference output module, the difference output module is used to collect the difference between the user's cognitive ability value and a preset standard ability value in the abnormal state, and record it as an abnormal cognitive difference; A level assessment module, the level assessment module is used to output the abnormal level of each cognitive ability value according to the abnormal cognitive difference, and determine the push order of each cognitive ability value according to the abnormal level; A push module, the push module is used to generate a cognitive function training list according to the push sequence, and push the cognitive function training content one by one according to the cognitive function training list; A list updating module is used to collect user feedback parameters after the cognitive function training list is executed, and update the cognitive function training list according to the user feedback parameters.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent push method for cognitive function training based on multi-dimensional ability values ​​as described in any one of claims 1 to 6.

Images