Memory training method, system and equipment based on artificial intelligence and storage medium

Abstract

The invention relates to a memory training method, system and device based on artificial intelligence and a storage medium, and the method comprises the steps: determining an initial multi-dimensional memory training scheme based on collected user data, and carrying out the memory training of a user based on the initial multi-dimensional memory training scheme, and obtaining first memory training data; based on the first memory training data, performing iterative adjustment on the initial multi-dimensional memory training scheme, and determining a personalized multi-dimensional memory training scheme; based on the personalized multi-dimensional memory training scheme, performing multi-dimensional evaluation processing on the memory of the user to obtain a multi-dimensional evaluation score; compared with the prior art, according to the technical scheme, the memory training scheme can be dynamically adjusted based on the user performance, and the effectiveness of memory training is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a memory training method, system, device and storage medium based on artificial intelligence. Background Art

[0002] With the development of cognitive science, memory, concentration, cognitive flexibility and neuroplasticity have become core elements in the field of education and brain training. These abilities are essential to improving individuals' learning efficiency, adaptability and innovation. However, most existing memory training tools are limited to single cognitive tasks, such as simple forward or reverse digital memory tasks. These tools often cannot provide personalized multi-dimensional training, nor can they dynamically adjust the training difficulty according to the user's actual ability level.

[0003] In view of the limitations of existing technologies, there is an urgent need for a new memory training method and system in the market. Summary of the invention

[0004] The present application provides a memory training method, system, device and storage medium based on artificial intelligence, which dynamically adjusts the memory training program based on user performance to ensure the effectiveness of memory training.

[0005] In a first aspect, the present application provides an artificial intelligence-based memory training method, comprising: determining an initial multidimensional memory training plan based on collected user data, and performing memory training on the user based on the initial multidimensional memory training plan to obtain first memory training data; iteratively adjusting the initial multidimensional memory training plan based on the first memory training data to determine a personalized multidimensional memory training plan; performing multidimensional evaluation processing on the user's memory based on the personalized multidimensional memory training plan to obtain a multidimensional evaluation score.

[0006] Furthermore, based on the collected user data, an initial multidimensional memory training program is determined, specifically including: obtaining a pre-constructed standard multidimensional memory training program library, wherein the standard multidimensional memory training program library includes multiple standard multidimensional memory training programs, and standard two-dimensional arrays corresponding to each of the multiple standard multidimensional memory training programs; collecting user data input by the user, wherein the user data includes age and gender; associating the age and the gender to generate a two-dimensional array, matching the two-dimensional array with all standard two-dimensional arrays in the standard multidimensional memory training program library, determining a target standard two-dimensional array, and using the standard multidimensional memory training program corresponding to the target standard two-dimensional array as the user's initial multidimensional memory training program.

[0007] Furthermore, based on the initial multidimensional memory training program, memory training is performed on the user to obtain first memory training data, which specifically includes: the initial multidimensional memory training program includes multiple memory training programs; when it is detected that the initial multidimensional memory training program is triggered, the task data of a single memory training program in the initial multidimensional memory training program is sent to the user in turn, and the task data sending time of the task data is recorded, and after receiving the valid training data fed back by the user based on the task data, the task data feedback time is recorded; based on the task data sending time and the task data feedback time, the training reaction time is determined, and the task data and the valid training data are compared to determine the training accuracy, and the training reaction time and the training accuracy are used as the training result data of a single memory training program; the training result data corresponding to all memory training programs are integrated to obtain the first memory training data.

[0008] Furthermore, before integrating the training result data corresponding to all memory training programs to obtain the first memory training data, it also includes: obtaining the program type corresponding to a single memory training program in the initial multidimensional memory training program sent to the user; when the program type is a complex program, calculating the ratio between the training accuracy rate corresponding to the single memory training program and the standard training accuracy rate, and determining the anti-interference rate based on the ratio; using the training reaction time, the training accuracy rate and the anti-interference rate as the training result data of a single memory training program.

[0009] Furthermore, based on the first memory training data, the initial multidimensional memory training plan is iteratively adjusted to determine a personalized multidimensional memory training plan, specifically including: obtaining the training result threshold data corresponding to each memory training plan in the initial multidimensional memory training plan, and based on the first memory training data, obtaining the training result data corresponding to each memory training plan, respectively comparing the training result data with the training result threshold data, and based on the comparison result, iteratively adjusting the difficulty coefficient corresponding to each memory training plan in the initial multidimensional memory training plan to obtain a multidimensional memory training adjustment plan, wherein the multidimensional memory training adjustment plan includes multiple memory training adjustment plans; based on the multidimensional memory training adjustment plan, determining the personalized multidimensional memory training plan.

[0010] Furthermore, based on the multidimensional memory training adjustment plan, the personalized multidimensional memory training plan is determined, specifically including: respectively obtaining the triggering number of each memory training adjustment plan in the multidimensional memory training adjustment plan within the target time period, and using the triggering number as the training frequency corresponding to each memory training adjustment plan; respectively obtaining the target training result data of each memory training adjustment plan in the multidimensional memory training adjustment plan within the target time period, and calculating the progress based on the target training result data; based on the user data, the training frequency and the progress value, the multidimensional memory training adjustment plan is adjusted to determine a personalized multidimensional memory training plan.

[0011] Furthermore, based on the personalized multidimensional memory training program, a multidimensional evaluation process is performed on the user's memory to obtain a multidimensional evaluation score, specifically including: based on the personalized multidimensional memory training program, the user is subjected to memory training to obtain second memory training data; based on the second memory training data, the user's score value in each dimension is calculated respectively; wherein each dimension includes a memory dimension, a concentration dimension, a cognitive flexibility dimension and a neural plasticity dimension; and the score values ​​in all dimensions are integrated to obtain a multidimensional evaluation score.

[0012] In a second aspect, the present application provides an artificial intelligence-based memory training system, comprising: an initial evaluation module, a personalized program generation module and a multidimensional evaluation module; wherein the initial evaluation module is used to determine an initial multidimensional memory training program based on collected user data, and based on the initial multidimensional memory training program, perform memory training on the user to obtain first memory training data; the personalized program generation module is used to iteratively adjust the initial multidimensional memory training program based on the first memory training data to determine a personalized multidimensional memory training program; the multidimensional evaluation module is used to perform multidimensional evaluation processing on the user's memory based on the personalized multidimensional memory training program to obtain a multidimensional evaluation score.

[0013] In a third aspect, the present application provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is used to implement the artificial intelligence-based memory training method described in any one of the above items of the present application when executing a program stored in the memory.

[0014] In a fourth aspect, the present application also provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the artificial intelligence-based memory training method described in any one of the above items of the present application.

[0015] The above-mentioned technical solution provided by the embodiment of the present application has the following advantages compared with the prior art: the method provided by the embodiment of the present application, by collecting the basic data of the user, is used to determine a suitable initial multidimensional memory training program, and can set a relatively personalized starting point for different users, so as to avoid the user from performing overly difficult or overly simple training without understanding his or her own cognitive ability; subsequently, based on the initial multidimensional memory training program, the user is subjected to memory training to obtain first memory training data; based on the first memory training data, the initial multidimensional memory training program is iteratively adjusted to determine a personalized multidimensional memory training program; in this process, as the user training progresses, the system can dynamically adjust the initial multidimensional memory training program according to the user's performance, which helps to continuously stimulate the user's cognitive potential, and based on the generated personalized multidimensional memory training program, the user's memory is multidimensionally evaluated to obtain a multidimensional evaluation score, which can more comprehensively evaluate the user's cognitive ability progress and provide a basis for further training adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0019] Figure 1 It is a flowchart of an embodiment of a memory training method based on artificial intelligence provided by the present application;

[0020] Figure 2 It is a structural schematic diagram of an embodiment of a memory training system based on artificial intelligence provided by the present application;

[0021] Figure 3 It is a structural schematic diagram of an electronic device provided by this application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0023] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0024] Example 1, see Figure 1 , Figure 1 : is a flow chart of an embodiment of a memory training method based on artificial intelligence provided by the present application, such as Figure 1 As shown, the method includes steps 101 to 103, which are specifically as follows:

[0025] Step 101: Determine an initial multidimensional memory training program based on collected user data, and perform memory training on the user based on the initial multidimensional memory training program to obtain first memory training data.

[0026] In one embodiment, since the cognitive ability and memory level exhibited by each user at different ages are not the same, by collecting basic user data, such as age, gender, etc., and determining a suitable initial multi-dimensional memory training program based on the user data, a relatively personalized starting point can be set for different users to avoid users performing overly difficult or overly simple training without understanding their own cognitive abilities.

[0027] In one embodiment, a pre-constructed standard multi-dimensional memory training program library is obtained, wherein the standard multi-dimensional memory training program library includes multiple standard multi-dimensional memory training programs and standard two-dimensional arrays corresponding to each of the multiple standard multi-dimensional memory training programs.

[0028] Specifically, in order to quickly match the corresponding initial multidimensional memory training plan for the user; by pre-constructing a standard multidimensional memory training plan library, wherein the standard multidimensional memory training plan library includes multiple standard multidimensional memory training plans, and the multiple standard multidimensional memory training plans are training plans executed according to the average cognitive ability and memory level demonstrated by users of different age stages, and according to the corresponding user data such as user age and gender, corresponding standard two-dimensional arrays are set for the multiple standard multidimensional memory training plans, wherein the standard two-dimensional array is composed of age and gender.

[0029] Preferably, the plurality of standard multidimensional memory training programs have different corresponding task difficulties for different annual stages.

[0030] In one embodiment, user data input by a user is collected, wherein the user data includes age and gender; the age and the gender are associated to generate a two-dimensional array, the two-dimensional array is matched with all standard two-dimensional arrays in the standard multi-dimensional memory training program library, a target standard two-dimensional array is determined, and the standard multi-dimensional memory training program corresponding to the target standard two-dimensional array is used as the initial multi-dimensional memory training program for the user.

[0031] Specifically, the user data can be collected based on the user inputting according to the user data filling prompt when the user logs in for the first time or registers at the client.

[0032] Specifically, the age in the user data is used as the first key name, and the gender in the user data is used as the first key value, and the first key name and the first key value are associated to obtain a two-dimensional array; preferably, the two-dimensional array is age-gender.

[0033] Specifically, when performing two-dimensional array matching processing, the similarity between the two-dimensional array and all standard two-dimensional arrays in the standard multidimensional memory training program library is calculated based on a similarity algorithm, and the target standard two-dimensional array in the standard multidimensional memory training program library is determined based on the highest similarity value.

[0034] In one embodiment, the initial multi-dimensional memory training program includes a plurality of memory training programs, wherein the plurality of memory training programs include a forward sequence number training program, a reverse sequence data training program, and a complex number training program.

[0035] Specifically, the positive sequence number training program is to display or play a set of number sequences consisting of target digits to the user visually or auditorily, and the user repeats or inputs the set of number sequences seen or heard in positive order.

[0036] Specifically, the reverse number training program is to display or play a set of number sequences consisting of target digits to the user visually or auditorily, and the user repeats or inputs the set of number sequences seen or heard in reverse order.

[0037] Specifically, the complex digital training program is through a combination of visual and auditory means, such as playing a number sequence consisting of a target number of digits to the user, and the user inputs the number sequence on the display in ascending or descending order based on the heard number sequence; or showing a number sequence consisting of a target number of digits to the user, and the user repeats the number sequence in ascending or descending order based on the seen number sequence; at the same time, visual interference elements and auditory interference elements are added in the training process to exercise the user's multi-tasking ability and anti-interference ability.

[0038] Preferably, for a digital sequence consisting of a target number of digits, the target number of digits is determined by the task difficulty corresponding to different age stages; preferably, for a 5-year-old user, the corresponding initial multidimensional memory training program has an initial task difficulty of: for the positive sequence number training program, the target number of digits is 5, and for the reverse order number training program, the target number of digits is 4; for a 10-year-old user, the corresponding initial multidimensional memory training program has an initial task difficulty of: for the positive sequence number training program, the target number of digits is 8, and for the reverse order number training program, the target number of digits is 6.

[0039] In one embodiment, when it is detected that the initial multidimensional memory training program is triggered, the task data of a single memory training program in the initial multidimensional memory training program is sent to the user in sequence, and the task data sending time of the task data is recorded. After receiving the valid training data fed back by the user based on the task data, the task data feedback time is recorded.

[0040] Specifically, the initial multi-dimensional memory training program is loaded on a mobile terminal, and the mobile terminal is connected to a user terminal where the user is located, so that the user can interact with the initial multi-dimensional memory training program based on the user terminal.

[0041] Specifically, whether the initial multi-dimensional memory training program is triggered is determined by detecting whether a target area on a display device of the user terminal is clicked or pressed.

[0042] Specifically, after the initial multidimensional memory training program is triggered, the system will send task data of a single memory training program to the user in sequence according to the initial multidimensional memory training program, wherein the task data is a digital sequence, and the array sequence is composed of a target number of digits.

[0043] Preferably, when sending the task data of a single memory training program to the user, the sending can be performed via a microphone device or a display device.

[0044] Specifically, after the task data is sent, the system automatically records the current time and determines the task data sending time.

[0045] Specifically, after receiving the task data, the user needs to complete the memory training task according to the instructions and feed back the effective training data to the system; wherein, the effective training data can be obtained by collecting the user's audio data and converting the audio data into effective training data; or by collecting the order in which the user clicks on relevant numbers on the display, and generating effective training data based on the order.

[0046] Specifically, the system automatically records the time when the user submits feedback and uses it as the task data feedback time.

[0047] In one embodiment, the training reaction time is determined based on the task data sending time and the task data feedback time, and the task data and the effective training data are compared to determine the training accuracy, and the training reaction time and the training accuracy are used as the training result data of a single memory training program.

[0048] Specifically, the time interval between the task data feedback time and the task data sending time is calculated, the time difference between the preset maximum reaction time and the time interval is calculated, and the time difference is used as the training reaction time.

[0049] Specifically, the correct number of digits in the effective training data is determined by comparing the task data with the effective training data, a first ratio of the correct number of digits to the target number of digits corresponding to the task data is calculated, and the training accuracy is determined based on the first ratio.

[0050] In one embodiment, the program type corresponding to a single memory training program in the initial multidimensional memory training program sent to the user is obtained; when the program type is a complex program, the ratio between the training accuracy rate corresponding to the single memory training program and the standard training accuracy rate is calculated, and based on the ratio, the anti-interference rate is determined.

[0051] Specifically, the scheme types corresponding to the positive sequence number training scheme and the reverse sequence data training scheme in the initial multi-dimensional memory training scheme are set to non-complex schemes, and the scheme type corresponding to the complex number training scheme is set to complex scheme.

[0052] Preferably, multiple training accuracy rates corresponding to when the user executes the forward sequence digital training program and the reverse sequence data training program are obtained, and the average of the multiple training accuracy rates is calculated to obtain a standard training accuracy rate.

[0053] In one embodiment, the training reaction time, the training accuracy rate and the anti-interference rate are used as training result data of a single memory training program.

[0054] In one embodiment, the training result data corresponding to all memory training programs are integrated to obtain the first memory training data.

[0055] Step 102: Based on the first memory training data, iteratively adjust the initial multidimensional memory training program to determine a personalized multidimensional memory training program.

[0056] In one embodiment, the training result threshold data corresponding to each memory training scheme in the initial multidimensional memory training scheme is obtained, and based on the first memory training data, the training result data corresponding to each memory training scheme is obtained, and the training result data and the training result threshold data are compared respectively; based on the comparison result, the difficulty coefficient corresponding to each memory training scheme in the initial multidimensional memory training scheme is iteratively adjusted to obtain a multidimensional memory training adjustment scheme; based on the multidimensional memory training adjustment scheme, the personalized multidimensional memory training scheme is determined; wherein the multidimensional memory training adjustment scheme includes multiple memory training adjustment schemes.

[0057] Specifically, an expected training result threshold data set is defined for each memory training program; the training result threshold data set can be based on standardized tests and the average performance of a large number of users, representing the benchmark performance of different age stages at different task difficulty levels; for example, for a sequential digit training program, the corresponding training result threshold data set includes the training accuracy threshold and training reaction time threshold corresponding to user groups of different ages and genders.

[0058] By comparing the user's training result data with the preset threshold data and analyzing whether the user's performance reaches or exceeds the threshold, the user's performance in each training program can be evaluated.

[0059] Specifically, when comparing the user's training result data with the preset training result threshold data, the training accuracy in the training result data is compared with the training accuracy threshold in the training result threshold data, and the training reaction time in the training result data is compared with the training reaction time threshold in the training result threshold data. If the training accuracy in the training result data is greater than the training accuracy threshold in the training result threshold data, and the training reaction time in the training result data is not greater than the training reaction time threshold in the training result threshold data, then the difficulty coefficient corresponding to each memory training scheme in the initial multidimensional memory training scheme is increased.

[0060] Example description: Based on the user's training accuracy and training reaction time, the system gradually increases the difficulty of the task; when the user performs well, the target number of digits corresponding to the forward digit training program and the target number of digits corresponding to the reverse digit training program are further improved.

[0061] Specifically, if the training accuracy in the training result data is not greater than the training accuracy threshold in the training result threshold data, and the training reaction time in the training result data is greater than the training reaction time threshold in the training result threshold data, then the difficulty coefficient corresponding to each memory training scheme in the initial multidimensional memory training scheme is reduced.

[0062] Preferably, within the target time period, the initial multidimensional memory training program is iteratively adjusted based on the first memory training data to determine a more optimal multidimensional memory training adjustment program.

[0063] In one embodiment, when determining the personalized multidimensional memory training plan based on the multidimensional memory training adjustment plan, the triggering number of each memory training adjustment plan in the multidimensional memory training adjustment plan within the target time period is obtained respectively, and the triggering number is used as the training frequency corresponding to each memory training adjustment plan; the target training result data of each memory training adjustment plan in the multidimensional memory training adjustment plan within the target time period is obtained respectively, and the progress amplitude is calculated based on the target training result data; based on the user data, the training frequency and the progress amplitude, the multidimensional memory training adjustment plan is adjusted to determine the personalized multidimensional memory training plan.

[0064] Specifically, the number of times each memory training adjustment plan is triggered within the target time period is analyzed. The number of triggers reflects the user's participation in each training plan. For example, if a memory training adjustment plan is triggered 5 times within a week, then this number represents the training frequency corresponding to the memory training adjustment plan.

[0065] Specifically, during the target time period, the user's training result data in each memory training adjustment plan is also collected, such as training accuracy, training reaction time, etc., and the user's progress over a period of time is measured using the improvement calculation method, such as the improvement coefficient evaluation method.

[0066] Specifically, when the multidimensional memory training adjustment plan is adjusted based on user data, training frequency and improvement rate, a first multidimensional memory training adjustment plan with a high training frequency and a large improvement rate is selected from all multidimensional memory training adjustment plans, and the training weight of the first multidimensional memory training adjustment plan in the multidimensional memory training adjustment plan is reduced, and the training weights of the remaining multidimensional memory training adjustment plans in the multidimensional memory training adjustment plan are increased; conversely, a second multidimensional memory training adjustment plan with a low training frequency and a small improvement rate is selected from all multidimensional memory training adjustment plans, and the training weight of the second multidimensional memory training adjustment plan in the multidimensional memory training adjustment plan is increased to obtain a personalized multidimensional memory training plan.

[0067] Example description: If the training frequency of a certain memory training adjustment plan is high and the improvement is large, it may indicate that the user performs well on this memory training adjustment plan. The training weight of this memory training adjustment plan can be appropriately reduced, thereby increasing the corresponding training weights of other memory training adjustment plans. On the contrary, if the improvement is small or the training frequency is low, the training weight of this memory training adjustment plan may need to be appropriately increased.

[0068] Step 103: Based on the personalized multidimensional memory training program, a multidimensional evaluation process is performed on the user's memory to obtain a multidimensional evaluation score.

[0069] In one embodiment, based on the personalized multi-dimensional memory training program, memory training is performed on the user to obtain second memory training data.

[0070] Specifically, the personalized multidimensional memory training program includes multiple personalized memory training programs; when it is detected that the personalized multidimensional memory training program is triggered, the first task data of a single personalized memory training program in the personalized multidimensional memory training program is sent to the user in turn, and the first task data sending time of the first task data is recorded. After receiving the first valid training data fed back by the user based on the task data, the first task data feedback time is recorded; based on the first task data sending time and the first task data feedback time, the first training reaction time is determined, and the first task data and the first valid training data are compared to determine the first training accuracy rate, and the first reaction time and the first training accuracy rate are used as the first training result data of a single personalized memory training program; the first training result data corresponding to all personalized memory training programs are integrated to obtain second memory training data.

[0071] Specifically, the second memory training data includes the forward training accuracy, forward training reaction time and forward target number of digits corresponding to the personalized forward digit training plan, and includes the reverse training accuracy, reverse training reaction time and reverse target number of digits corresponding to the personalized reverse digit training plan; and also includes the complex training accuracy, complex training reaction time and complex anti-interference rate corresponding to the personalized complex digit training plan.

[0072] Preferably, the second memory training data also includes the first task data feedback time and the first task data sending time corresponding to each personalized memory training program in the personalized multi-dimensional memory training program.

[0073] Preferably, the second memory training data also includes the degree of improvement corresponding to each personalized memory training program in the personalized multi-dimensional memory training program.

[0074] Preferably, the process of performing memory training on the user based on the personalized multidimensional memory training program to obtain the second memory training data is the same as the process of performing memory training on the user based on the initial multidimensional memory training program to obtain the first memory training data, and will not be described in detail here.

[0075] In one embodiment, based on the second memory training data, the user's score value in each dimension is calculated respectively; wherein each dimension includes a memory dimension, a concentration dimension, a cognitive flexibility dimension, and a neuroplasticity dimension;

[0076] Specifically, the score values ​​under each dimension include but are not limited to the score value of the memory dimension, the score value of the concentration dimension, the score value of the cognitive flexibility dimension and the score value of the neuroplasticity dimension.

[0077] Specifically, for the memory dimension score value: obtain the forward training accuracy, forward training reaction time and forward target number of digits corresponding to the forward digit training scheme from the second memory training data; and the reverse training accuracy, reverse training reaction time and reverse target number of digits corresponding to the reverse digit training scheme; by setting a corresponding first weight value for the forward training accuracy, the forward training reaction time and the forward target number of digits, respectively multiply the forward training accuracy, the forward training reaction time and the forward target number of digits with the corresponding first weight value, and add the parameters obtained by the multiplication , and obtain the forward training score; similarly, set corresponding second weight values ​​for the reverse training accuracy, the reverse training reaction time and the reverse target number of digits, respectively multiply the reverse training accuracy, the reverse training reaction time and the reverse target number of digits with the corresponding second weight values, and add the multiplied parameters to obtain the reverse training score; obtain the corresponding scheme weight values ​​of the forward digital training scheme and the reverse digital training scheme, multiply and add the forward training score and the reverse training score with the corresponding scheme weight values, respectively, to obtain the memory dimension score value.

[0078] Specifically, for the concentration dimension score: obtain the complex training accuracy, complex training reaction time and complex anti-interference rate corresponding to the complex digital training plan from the second memory training data; set the corresponding third weight value for the complex training accuracy, complex training reaction time and complex anti-interference rate, and multiply and add the complex training accuracy, complex training reaction time and complex anti-interference rate with the corresponding third weight value to obtain the concentration dimension score.

[0079] Specifically, for the cognitive flexibility dimension score: based on the second memory training data, obtain the first task data feedback time and the first task data sending time corresponding to each personalized memory training scheme in the personalized multidimensional memory training scheme, calculate the first task data feedback time corresponding to the first personalized memory training scheme in two adjacent personalized memory training schemes and the first task data sending time corresponding to the second personalized memory training scheme in two adjacent personalized memory training schemes, and determine the scheme switching speed; and determine the scheme switching accuracy based on the first training accuracy rate corresponding to the first personalized memory training scheme in the two adjacent personalized memory training schemes and the second training accuracy rate corresponding to the second personalized memory training scheme in the two adjacent personalized memory training schemes; by setting corresponding fourth weight values ​​for the scheme switching speed and the scheme switching accuracy, multiply and add the scheme switching speed and the scheme switching accuracy with the corresponding fourth weight values, respectively, to obtain the cognitive flexibility dimension score.

[0080] Specifically, for the neuroplasticity dimension score value: obtain the first forward-sequence training accuracy and the first forward-sequence training reaction time of the personalized forward-sequence digital training program corresponding to the first time; simultaneously obtain the second forward-sequence training accuracy and the second forward-sequence training reaction time of the personalized forward-sequence digital training program corresponding to the second time, and calculate the time interval between the first time and the second time; calculate the training accuracy difference between the first forward-sequence training accuracy and the second forward-sequence training accuracy, and calculate a first ratio of the training accuracy difference to the time interval, and use the first ratio as the slope of the accuracy learning curve; calculate the training reaction time difference between the first forward-sequence training reaction time and the second forward-sequence training reaction time, and calculate the training reaction time. A second ratio of the difference to the time interval, and using the second ratio as the slope of the reaction time learning curve; by setting a corresponding fifth weight value for the slope of the accuracy learning curve and the slope of the reaction time learning curve, respectively multiplying and adding the slope of the accuracy learning curve and the slope of the reaction time learning curve with the corresponding fifth weight value, to obtain the slope of the learning curve; obtaining the corresponding degree of improvement of each personalized memory training program in the personalized multidimensional memory training program; setting a corresponding sixth weight value for the program switching accuracy, the degree of improvement and the slope of the learning curve, respectively multiplying and adding the program switching accuracy, the degree of improvement and the slope of the learning curve with the corresponding sixth weight value, to obtain a neuroplasticity dimension score.

[0081] In one embodiment, the rating values ​​under all dimensions are integrated to obtain a multi-dimensional evaluation score.

[0082] Example 2, see Figure 2 , Figure 2 is a structural diagram of an embodiment of a memory training system based on artificial intelligence provided by the present application, such as Figure 2 As shown, the system includes an initial evaluation module 201 , a personalized solution generation module 202 and a multi-dimensional evaluation module 203 .

[0083] The initial evaluation module 201 is used to determine an initial multidimensional memory training program based on the collected user data, and perform memory training on the user based on the initial multidimensional memory training program to obtain first memory training data.

[0084] The personalized program generation module 202 is used to iteratively adjust the initial multidimensional memory training program based on the first memory training data to determine a personalized multidimensional memory training program.

[0085] The multidimensional evaluation module 203 is used to perform a multidimensional evaluation process on the user's memory based on the personalized multidimensional memory training program to obtain a multidimensional evaluation score.

[0086] In one embodiment, the initial evaluation module 201 is used to determine an initial multidimensional memory training program based on the collected user data, specifically including: obtaining a pre-constructed standard multidimensional memory training program library, wherein the standard multidimensional memory training program library includes multiple standard multidimensional memory training programs, and standard two-dimensional arrays corresponding to each of the multiple standard multidimensional memory training programs; collecting user data input by the user, wherein the user data includes age and gender; associating the age and the gender to generate a two-dimensional array, matching the two-dimensional array with all standard two-dimensional arrays in the standard multidimensional memory training program library, determining a target standard two-dimensional array, and using the standard multidimensional memory training program corresponding to the target standard two-dimensional array as the user's initial multidimensional memory training program.

[0087] In one embodiment, the initial evaluation module 201 is used to perform memory training on the user based on the initial multidimensional memory training program to obtain first memory training data, specifically including: the initial multidimensional memory training program includes multiple memory training programs; when it is detected that the initial multidimensional memory training program is triggered, the task data of a single memory training program in the initial multidimensional memory training program is sent to the user in sequence, and the task data sending time of the task data is recorded, and after receiving the valid training data fed back by the user based on the task data, the task data feedback time is recorded; based on the task data sending time and the task data feedback time, the training reaction time is determined, and the task data and the valid training data are compared to determine the training accuracy, and the training reaction time and the training accuracy are used as the training result data of a single memory training program; the training result data corresponding to all memory training programs are integrated to obtain the first memory training data.

[0088] In one embodiment, the initial evaluation module 201 is used to integrate the training result data corresponding to all memory training schemes, and before obtaining the first memory training data, it also includes: obtaining the scheme type corresponding to a single memory training scheme in the initial multidimensional memory training scheme sent to the user; when the scheme type is a complex scheme, calculating the ratio between the training accuracy rate corresponding to the single memory training scheme and the standard training accuracy rate, and determining the anti-interference rate based on the ratio; using the training reaction time, the training accuracy rate and the anti-interference rate as the training result data of a single memory training scheme.

[0089] In one embodiment, the personalized scheme generation module 202 is used to iteratively adjust the initial multidimensional memory training scheme based on the first memory training data to determine a personalized multidimensional memory training scheme, specifically including: obtaining the training result threshold data corresponding to each memory training scheme in the initial multidimensional memory training scheme, and based on the first memory training data, obtaining the training result data corresponding to each memory training scheme, respectively comparing the training result data with the training result threshold data, and based on the comparison result, iteratively adjusting the difficulty coefficient corresponding to each memory training scheme in the initial multidimensional memory training scheme to obtain a multidimensional memory training adjustment scheme, wherein the multidimensional memory training adjustment scheme includes multiple memory training adjustment schemes; based on the multidimensional memory training adjustment scheme, determining the personalized multidimensional memory training scheme.

[0090] In one embodiment, the personalized program generation module 202 is used to determine the personalized multidimensional memory training program based on the multidimensional memory training adjustment program, specifically including: respectively obtaining the triggering number of each memory training adjustment program in the multidimensional memory training adjustment program within the target time period, and using the triggering number as the training frequency corresponding to each memory training adjustment program; respectively obtaining the target training result data of each memory training adjustment program in the multidimensional memory training adjustment program within the target time period, and calculating the progress based on the target training result data; adjusting the multidimensional memory training adjustment program based on the user data, the training frequency and the progress value to determine the personalized multidimensional memory training program.

[0091] In one embodiment, the multidimensional evaluation module 203 is used to perform multidimensional evaluation processing on the user's memory based on the personalized multidimensional memory training program to obtain a multidimensional evaluation score, specifically including: based on the personalized multidimensional memory training program, performing memory training on the user to obtain second memory training data; based on the second memory training data, calculating the user's score value in each dimension respectively; wherein each dimension includes a memory dimension, a concentration dimension, a cognitive flexibility dimension and a neural plasticity dimension; integrating the score values ​​in all dimensions to obtain a multidimensional evaluation score.

[0092] The above-mentioned memory training system based on artificial intelligence can implement the memory training method based on artificial intelligence in the above-mentioned method embodiment. The options in the above-mentioned method embodiment are also applicable to this embodiment and will not be described in detail here.

[0093] like Figure 3 As shown, Figure 3It is a structural diagram of an electronic device provided by the present application; it includes a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114, and the memory 113 is used to store computer programs.

[0094] In one embodiment of the present application, the processor 111 is used to implement the artificial intelligence-based memory training method provided by any one of the aforementioned method embodiments when executing the program stored in the memory 113.

[0095] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the artificial intelligence-based memory training method provided in any of the aforementioned method embodiments are implemented.

[0096] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0098] It should be understood that the terms used in the text are only for the purpose of describing specific example embodiments, and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0099] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A memory training method based on artificial intelligence, characterized in that: include: Determining an initial multidimensional memory training program based on the collected user data, and performing memory training on the user based on the initial multidimensional memory training program to obtain first memory training data; Iteratively adjusting the initial multidimensional memory training program based on the first memory training data to determine a personalized multidimensional memory training program; Based on the personalized multidimensional memory training program, a multidimensional evaluation process is performed on the user's memory to obtain a multidimensional evaluation score.

2. The method according to claim 1, characterized in that Based on the collected user data, determine the initial multi-dimensional memory training program, including: Obtaining a pre-built standard multi-dimensional memory training program library, wherein the standard multi-dimensional memory training program library includes a plurality of standard multi-dimensional memory training programs and a standard two-dimensional array corresponding to each of the plurality of standard multi-dimensional memory training programs; Collecting user data input by a user, wherein the user data includes age and gender; The age and the gender are associated to generate a two-dimensional array, and the two-dimensional array is matched with all standard two-dimensional arrays in the standard multi-dimensional memory training program library to determine the target standard two-dimensional array, and the standard multi-dimensional memory training program corresponding to the target standard two-dimensional array is used as the initial multi-dimensional memory training program for the user.

3. The method according to claim 1, characterized in that: Based on the initial multi-dimensional memory training program, memory training is performed on the user to obtain first memory training data, which specifically includes: The initial multi-dimensional memory training program includes a plurality of memory training programs; When it is detected that the initial multidimensional memory training program is triggered, the task data of a single memory training program in the initial multidimensional memory training program is sent to the user in sequence, and the task data sending time of the task data is recorded, and after receiving the effective training data fed back by the user based on the task data, the task data feedback time is recorded; Based on the task data sending time and the task data feedback time, determine the training reaction time, compare the task data with the effective training data, determine the training accuracy, and use the training reaction time and the training accuracy as the training result data of a single memory training program; The training result data corresponding to all memory training programs are integrated to obtain the first memory training data.

4. The method according to claim 3, characterized in that Before integrating the training result data corresponding to all memory training programs to obtain the first memory training data, the method further includes: Acquire a program type corresponding to a single memory training program in the initial multi-dimensional memory training program sent to the user; When the scheme type is a complex scheme, calculating the ratio between the training accuracy rate corresponding to the single memory training scheme and the standard training accuracy rate, and determining the anti-interference rate based on the ratio; The training reaction time, the training accuracy rate and the anti-interference rate are used as training result data of a single memory training program.

5. The method according to claim 1, characterized in that: Based on the first memory training data, iteratively adjusting the initial multidimensional memory training program to determine a personalized multidimensional memory training program specifically includes: Acquire the training result threshold data corresponding to each memory training scheme in the initial multidimensional memory training scheme, and based on the first memory training data, acquire the training result data corresponding to each memory training scheme, respectively compare the training result data with the training result threshold data, and iteratively adjust the difficulty coefficient corresponding to each memory training scheme in the initial multidimensional memory training scheme based on the comparison result to obtain a multidimensional memory training adjustment scheme, wherein the multidimensional memory training adjustment scheme includes a plurality of memory training adjustment schemes; Based on the multidimensional memory training adjustment plan, the personalized multidimensional memory training plan is determined.

6. The method according to claim 5, characterized in that Based on the multidimensional memory training adjustment plan, determining the personalized multidimensional memory training plan specifically includes: Respectively obtain the number of times each memory training adjustment scheme in the multidimensional memory training adjustment scheme is triggered within the target time period, and use the number of times as the training frequency corresponding to each memory training adjustment scheme; Respectively obtaining target training result data of each memory training adjustment scheme in the multidimensional memory training adjustment scheme within a target time period, and calculating the improvement range based on the target training result data; Based on the user data, the training frequency and the improvement amplitude, the multidimensional memory training adjustment plan is adjusted to determine a personalized multidimensional memory training plan.

7. The method according to claim 1, characterized in that: Based on the personalized multi-dimensional memory training program, a multi-dimensional evaluation process is performed on the user's memory to obtain a multi-dimensional evaluation score, specifically including: Based on the personalized multi-dimensional memory training program, the user is trained in memory to obtain second memory training data; Based on the second memory training data, respectively calculate the user's score value in each dimension; wherein each dimension includes a memory dimension, a concentration dimension, a cognitive flexibility dimension, and a neuroplasticity dimension; The rating values ​​under all dimensions are integrated to obtain a multi-dimensional evaluation score.

8. A memory training system based on artificial intelligence, characterized in that: include: Initial assessment module, personalized solution generation module and multidimensional assessment module; The initial evaluation module is used to determine an initial multidimensional memory training program based on the collected user data, and perform memory training on the user based on the initial multidimensional memory training program to obtain first memory training data; The personalized program generation module is used to iteratively adjust the initial multidimensional memory training program based on the first memory training data to determine a personalized multidimensional memory training program; The multidimensional evaluation module is used to perform a multidimensional evaluation process on the user's memory based on the personalized multidimensional memory training program to obtain a multidimensional evaluation score.

9. An electronic device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is used to implement the artificial intelligence-based memory training method described in any one of claims 1-7 when executing the program stored in the memory.

10. A computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the artificial intelligence-based memory training method described in any one of claims 1 to 7 of the present application.

Images