Brain Training System and Method Based on Big Data

Abstract

The present invention provides a brain-training system and method based on big data. The system includes: a data storage module, which is used to obtain and store user data, and the user data at least includes basic data and game data; a task push module, which responds to the login instruction of a target user, retrieves the user data corresponding to the target user stored in the data storage module, calculates the rehabilitation index of the target user, generates a predicted value of the rehabilitation index based on an autoregressive moving average model, generates a push strategy according to the difference between the rehabilitation index and the predicted value of the rehabilitation index; a game loading module, which is used to store a variety of candidate games and push at least one target game in response to the push strategy. It solves the problem in the prior art that it is impossible to customize a physiotherapy plan and push multiple games after big data analysis and prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of cognitive training, and particularly to a brain-building training system and method based on big data. Background Art

[0002] Brain training has been used to improve users' memory and cognitive skills. Training the brains of the elderly can improve the overall cognitive function and daily living ability of users with mild cognitive impairment (MCI) and dementia, and training the brains of children can develop children's potential.

[0003] However, the physical therapy programs recommended by existing scientific brain-building programs to users are all manually added by rehabilitation therapists or automatically recommended according to simple rules, and cannot intelligently formulate personalized treatment plans according to the user's own situation. At the same time, the formulated physical therapy programs are not fine-grained enough, with a relatively large granularity. The subdivision of the recommended physical therapy games is not enough, and it cannot be well combined with the user's own disease conditions for recommendation and treatment. The physical therapy programs lack pertinence. Moreover, the games in existing technical brain-building programs are relatively divorced from life and lack fun, making users feel that they are playing games for treatment, and it is easy for users to generate boredom. And during the game push process, it is very easy to push repetitive physical therapy games or games with substantially the same gameplay to users, which is very easy for users to generate a rebellious psychology and affect the use effect of users.

[0004] In view of this, a brain-building training system and method based on big data are provided, in order to solve the problems in the prior art that physical therapy program customization and multiple game pushes cannot be performed through big data analysis and prediction. Summary of the Invention

[0005] The present invention provides a brain-building training system and method based on big data, in order to perform physical therapy program customization and multiple game pushes through big data analysis and prediction, thereby improving the customization effect of physical therapy programs and the game push effect, and further improving the use effect of the brain-building training system.

[0006] The present invention provides a brain-building training system based on big data, and the system includes:

[0007] A data storage module, which is used to obtain and store user data, and the user data at least includes basic data and game data;

[0008] A task push module, which, in response to the login instruction of a target user, retrieves the user data corresponding to the target user stored in the data storage module;

[0009] Calculate the rehabilitation index of the target user, and generate a predicted value of the rehabilitation index based on the autoregressive moving average model;

[0010] Generate a push strategy according to the difference degree between the rehabilitation index and the predicted value of the rehabilitation index;

[0011] A game loading module, which is used to store a variety of candidate games and push at least one target game in response to the push strategy.

[0012] In some embodiments, the system further includes:

[0013] A payment module, which is used to generate payment data according to a preset payment strategy in response to the physiotherapy package selected by the target user, and the payment data at least includes a bill and payment information.

[0014] In some embodiments, calculating the rehabilitation index of the target user and generating a predicted value of the rehabilitation index based on the autoregressive moving average model specifically includes:

[0015] Based on the obtained sample data, obtain the endogenous relationship between various games and the scores of various patients at different stages;

[0016] Optimize the game type and recommendation rules through sample data with good curative effects;

[0017] According to the patient's rehabilitation situation, combine the mental ability value and the results of the cognitive impairment battery test, and perform weighted averaging to obtain the patient's rehabilitation index, and generate a predicted value of the rehabilitation index based on the autoregressive moving average model.

[0018] In some embodiments, generating a push strategy according to the difference degree between the rehabilitation index and the predicted value of the rehabilitation index specifically includes:

[0019] If the difference degree between the rehabilitation index and the predicted value of the rehabilitation index is less than the threshold, then use the historical game type as the pushed game;

[0020] If the difference degree between the rehabilitation index and the predicted value of the rehabilitation index is greater than or equal to the threshold, then replace it with a new game type and use the new game type as the pushed game.

[0021] In some embodiments, the task push module is further used to generate a push strategy according to the user portrait, specifically including:

[0022] Obtain the cognitive domain of the target user based on the user portrait;

[0023] Calculate the basic mental ability value of the target user according to the cognitive domain;

[0024] Determine the cognitive impairment level according to the basic mental ability value;

[0025] Based on the cognitive impairment level and the educational level of the target user, determine the game level.

[0026] The present invention also provides a brain - strengthening training method based on big data, and the method includes:

[0027] Obtain and store user data, where the user data at least includes basic data and game data;

[0028] In response to a login instruction of a target user, retrieve the user data corresponding to the target user stored in the data storage module, calculate the rehabilitation index of the target user, and generate a predicted value of the rehabilitation index based on an autoregressive moving average model; generate a push strategy according to the difference between the rehabilitation index and the predicted value of the rehabilitation index;

[0029] Push at least one target game in response to the push strategy.

[0030] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above - described method is implemented.

[0031] In some embodiments, the electronic device includes:

[0032] A user terminal, where the user terminal includes a PAD, a self - service machine, and a PC;

[0033] A doctor terminal, where the doctor terminal includes a doctor's PC.

[0034] The present invention also provides a non - transitory computer - readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above - described method is implemented.

[0035] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the above - described method is implemented.

[0036] In one or several specific embodiments, the brain - strengthening training system and method provided by the present invention at least have the following technical effects:

[0037] The game loading module of the brain - strengthening training system provided by the present invention includes games with multiple training dimensions, enabling users to receive more scientific and professional cognitive training. Moreover, for each training dimension, there are multiple games with different styles and different difficulties, and the gameplay is more diverse. Some games can even train multiple cognitive fields, enabling users to play one game and achieve the effect of training multiple cognitive abilities, making the field more vertical and specific, and bringing a higher physical therapy experience to users. Thus, the problem of unclear game domain division in the prior art is solved, and the user experience is improved;

[0038] The brain training system provided by the present invention can, through the task push module, recommend suitable customized solutions according to the multi-dimensional indicators of the target user and the target user's own situation, thus solving the problem in the prior art that physical therapy programs cannot be customized and a variety of games cannot be pushed after big data analysis and prediction;

[0039] The brain training system provided by the present invention integrates multiple games into the game loading module. Combining the user's perspective, it subdivides cognitive abilities in multiple dimensions and adopts diverse gameplay and themes, featuring being easy, interesting, and creative; and most of them are common games in real life, such as "finding and putting things in place", classifying and storing different daily necessities, enabling users to enjoy the fun of the game in a pleasant and relaxed state, and gradually restoring cognitive abilities during the game, thus solving the problem in the prior art that games are divorced from life and lack interestingness;

[0040] The brain training system provided by the present invention can, through the different styles of games stored in the task push module and the game loading module, as well as the playability (easy, interesting, easy to start, and fresh in creativity), flexibly set how long it takes before the same game is not recommended again, so that users can always maintain a sense of freshness and interestingness during the physical therapy process, thus solving the problem in the prior art that a large number of repetitive games or games with generally the same gameplay are generated due to the lack of intelligent recommendation, which easily causes users to have a rebellious psychology and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 is a structural block diagram of a brain training system based on big data provided by the present invention;

[0043] Figure 2 is a flowchart of a brain training method based on big data provided by the present invention;

[0044] Figure 3 is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] To solve the problems existing in the prior art, the present invention provides a brain fitness training system and method based on big data. Through big data analysis and prediction, a physiotherapy plan is customized and multiple games are pushed, thereby improving the customization effect of the physiotherapy plan and the pushing effect of the games, and further improving the usage effect of the brain fitness training system.

[0047] In a specific embodiment, as Figure 1 shown, the brain fitness training system based on big data provided by the present invention includes:

[0048] A data storage module 110, which is used to obtain and store user data. The user data at least includes basic data and game data. In a specific usage scenario, the data storage module uses NoSQL for big data storage. The main data stored includes game scores of users, game levels of users, and other business data related to games. The database has complete index and sharding support, and the query performance is very high. The data stored in the data storage module is used to provide data support for the task pushing module and the additional report service module.

[0049] A task pushing module 120, which responds to the login instruction of the target user, retrieves the user data corresponding to the target user stored in the data storage module; calculates the rehabilitation index of the target user, and generates a predicted value of the rehabilitation index based on the autoregressive moving average model; generates a pushing strategy according to the difference between the rehabilitation index and the predicted value of the rehabilitation index; the task pushing module 120 can also be used to generate a user portrait of the target user according to the user data of the target user, and generate a pushing strategy according to the user portrait; specifically, the user portrait at least includes indicators such as physiotherapy scores, age, education level, diagnosis results, and assessment scores.

[0050] A game loading module 130, which is used to store a variety of candidate games and push at least one target game in response to the pushing strategy. The game loading module 130 is a game loading engine, which dynamically loads games on OSS storage in combination with the binding relationship between the system and the user. The game loading module is also used to load parameters corresponding to the target game while dynamically loading the target game, such as sound effects, illustrations, the score of the user's most recent play, the level of the user's most recent play, and the optimal score of this game.

[0051] The cognitive games stored in the game loading module 130 are divided into orientation, memory, execution, attention, language, calculation, perception, etc. according to the cognitive domain. All physical therapy games are based on the physical therapy experience of medical staff in reality to form physical therapy scripts, and finally developed into games. Most of the game scenes come from life to increase the fun of the game, such as "finding objects and returning them to their original places" and "going around the supermarket", so that users can get physical therapy in real life scenes. In specific usage scenarios, games can be deployed in the cloud. At the same time, in order to ensure the smooth experience of multiple users on the PAD end, CDN acceleration can be turned on.

[0052] In the task push module, the rehabilitation index of the target user is calculated, and a predicted value of the rehabilitation index is generated based on an autoregressive moving average model, specifically including:

[0053] Based on the sample data obtained, the endogenous relationship between various types of games and the scores of various types of patients at different stages was obtained;

[0054] Optimize game types and recommended rules through sample data with good therapeutic effects;

[0055] According to the patient's recovery status, combined with the brain power value and cognitive dysfunction test results, a weighted average is taken to obtain the patient's recovery index, and the predicted value of the recovery index is generated based on the autoregressive moving average model.

[0056] According to the difference between the rehabilitation index and the predicted value of the rehabilitation index, a push strategy is generated, which specifically includes:

[0057] When the difference between the rehabilitation index and the predicted rehabilitation index value is less than a threshold, the historical game type is used as the pushed game;

[0058] When the difference between the rehabilitation index and the predicted value of the rehabilitation index is greater than or equal to a threshold, a new game type is replaced and the new game type is used as a pushed game.

[0059] That is to say, in the algorithm, the patient's own real recovery index is calculated and obtained, and the predicted value of the rehabilitation index is generated by the autoregressive moving average model through a large amount of patient data that has achieved good therapeutic effects. The direct difference between the patient's rehabilitation index and the predicted value of the rehabilitation index is compared to generate or modify the push strategy.

[0060] In a specific usage scenario, the system uses big data technology and can perform big data analysis based on a large number of patient usage situations. The endogenous relationship between various types of games and the scores of various types of patients at different stages can be obtained. The system can summarize the data of patients who have achieved good therapeutic effects and continuously improve the game types and recommendation rules. The system regularly performs weighted averaging based on the patient's recovery status, combined with the brain power value and cognitive dysfunction test results, to obtain the patient's recovery index. According to the patient's recovery index, the system can use the autoregressive moving average model (ARMA) to predict the recovery index of patients undergoing treatment.

[0061] ARMA is a statistical model widely used in time series analysis, especially in the analysis of stationary series. The basic characteristics of time series include: trend, serial correlation, and randomness. Trend refers to the monotonicity of the sequence as a whole. The ARMA model is a stationary time series model, and the trend must be removed before modeling. Serial correlation refers to the linear correlation between the current sequence value and one or some previous sequence values. Randomness means that the sequence is uncertain to a certain extent. Since the model cannot capture all the characteristics of the real world, there will always be some noise, which is called white noise.

[0062] Model form: The ARMA (p, q) model contains p autoregressive terms and q moving average terms. The ARMA (p, q) model can be expressed as:

[0063]

[0064] Among them, p and q are the autoregressive order and moving average order of the model; φ and θ are non-zero unknown coefficients; ε t Independent error term; X t is a stationary, normal, zero-mean time series.

[0065] If the predicted result is consistent with the expected recovery situation, the previously recommended rules game will continue to be used. If the recovery situation is significantly different from the expected situation, other similar games will be recommended until a game that is more suitable for the patient is found. Through this big data recommendation, we can effectively find the game type that is suitable for the patient and achieve a more satisfactory treatment effect.

[0066] Furthermore, in order to facilitate user payment, the system also includes:

[0067] Payment module 140. The payment module is used to generate payment data according to a preset payment strategy in response to a physiotherapy package selected by a target user. The payment data includes at least a bill and payment information. Specifically, the payment module 140 is connected to a third-party payment platform for payment, which belongs to the auxiliary service of the system. It mainly solves the problem that users who have physiotherapy at home can flexibly select corresponding physiotherapy packages. There are various ways for physiotherapy packages, such as monthly payment, quarterly payment, annual payment, etc.

[0068] In a specific usage scenario, the system uses Internet microservices as the underlying framework. The service planning includes: "Cognitive game service", "Payment service", "Data warehouse big data analysis service", "Live broadcast service", "Recommendation service", "Financial service", etc. The services are deployed in the cloud.

[0069] In the task push module 120, a push strategy is generated according to the user profile, specifically including:

[0070] Based on the user profile, obtain the cognitive domain of the target user; according to the user's cognitive impairment, reasonably recommend a physiotherapy plan to achieve the purpose of cognitive training. Among them, the cognitive domain includes orientation, memory, executive ability, attention, language ability, calculation ability, perception, etc.;

[0071] Calculate the basic mental ability value of the target user according to the cognitive domain;

[0072] Determine the cognitive impairment level according to the basic mental ability value;

[0073] Based on the cognitive impairment level and the educational level of the target user, determine the game level.

[0074] The task push module 120 forms a user profile by analyzing a large amount of user data, analyzing the user's game scores, and identifying the user's behavioral defects. The task push module 120 recommends a group of physiotherapy tasks for the user every day. The specific indicators of the user profile include: user physiotherapy score, user age, user education level, user diagnosed condition, user assessment score, and other factors. The recommendation service targets and divides the domain according to the user profile, and pushes games to users according to different difficulties. To prevent the recommendation of repeated games, the system will dynamically form a rule that a certain game will not be recommended within xx days according to the recommendation history. For example, the same game will not be recommended within 2 days or within a week, or a game that has been rejected by the user more than 2 times will not be recommended. The recommendation rules can be specifically:

[0075] 1. Recommend according to user tags: When the user enters the system, corresponding tags will be added to the user's cognitive domain;

[0076] 2. Recommendation based on the user's mental ability: Through professional system evaluations (MMSE, MOCA), the user's basic mental ability will be calculated. Those with a mental ability score from 0 to 158 belong to severe cognitive impairment, and the recommended games are all simple games at the first level. For those with a medium to high mental ability, recommendations are made according to the established algorithm of the program. For example, divide the mental ability value by the total number of game levels, and round the obtained value to recommend the game level.

[0077] 3. Recommendation based on the user's education level: According to the education level entered by the user into the system, the difficulty level of the games is recommended accordingly.

[0078] It should be understood that various recommendation rules can be used alone or in combination.

[0079] The game loading module of the brain training system provided by the present invention includes games with multiple training dimensions, enabling users to receive more scientific and professional cognitive training. Moreover, each training dimension has multiple games with different styles and different difficulties, and has more diverse gameplay. Some games can even train multiple cognitive fields, enabling users to play one game and achieve the effect of training multiple cognitive abilities, making the fields more vertical and specific, and bringing a higher physical therapy experience to users. Thus, the problem of unclear game domain division in the prior art is solved, and the user experience is improved.

[0080] The brain training system provided by the present invention can, through the task push module, recommend suitable customized solutions according to the multi-dimensional indicators of the target user and the target user's own situation, thus solving the problem in the prior art that it is impossible to customize physical therapy solutions and push multiple games after big data analysis and prediction.

[0081] The brain training system provided by the present invention integrates multiple games into the game loading module. From the user's perspective, it subdivides cognitive abilities into multiple dimensions, adopts diverse gameplay and themes, and has the characteristics of being relaxed, interesting, and creative. Moreover, most of them are common games in real life, such as "finding and putting things in place", classifying and storing different daily necessities, enabling users to enjoy the fun of the game in a pleasant and relaxed state, and gradually recovering their cognitive abilities during the game. Thus, the problem in the prior art that games are divorced from life and lack fun is solved.

[0082] Through the different styles of games stored in the task push module and the game loading module of the brain training system provided by the present invention, as well as the playability (easy and interesting gameplay, easy to start, fresh creativity), it is possible to flexibly set how long it takes not to repeat the recommended games, so that users can always maintain a sense of freshness and interest during the physical therapy process. Thus, the problem in the prior art that a large number of repetitive games or games with similar gameplay are generated due to the lack of intelligent recommendation, which easily causes users to have a rebellious mentality, is solved, and the user experience is improved.

[0083] In addition to the above system, the present invention also provides a brain training method based on big data, such as Figure 2 shown, the method comprising the following steps:

[0084] S210: Obtain and store user data, the user data including at least basic data and game data;

[0085] S220: In response to a login instruction of a target user, retrieve the user data corresponding to the target user stored in the data storage module, calculate the rehabilitation index of the target user, and generate a rehabilitation index prediction value based on an autoregressive moving average model; generate a push strategy according to the difference degree between the rehabilitation index and the rehabilitation index prediction value;

[0086] S230: Push at least one target game in response to the push strategy.

[0087] In some embodiments, the method further comprises:

[0088] In response to a physiotherapy package selected by a target user, generate payment data according to a preset payment strategy, the payment data including at least a bill and payment information.

[0089] In some embodiments, calculating the rehabilitation index of the target user and generating a rehabilitation index prediction value based on an autoregressive moving average model specifically comprises:

[0090] Based on the obtained sample data, obtain the endogenous relationship between various games and the scores of various patients at different stages;

[0091] Optimize the game types and recommendation rules through sample data with good curative effects;

[0092] According to the rehabilitation situation of the patient, combine the brain power value and the results of the cognitive dysfunction battery test, and perform weighted averaging to obtain the rehabilitation index of the patient, and generate a rehabilitation index prediction value based on an autoregressive moving average model.

[0093] In some embodiments, generating a push strategy according to the difference degree between the rehabilitation index and the rehabilitation index prediction value specifically comprises:

[0094] In the case where the difference degree between the rehabilitation index and the rehabilitation index prediction value is less than a threshold, use the historical game type as the pushed game;

[0095] In the case where the difference degree between the rehabilitation index and the rehabilitation index prediction value is greater than or equal to the threshold, replace with a new game type and use the new game type as the pushed game.

[0096] In some embodiments, the game loading module is further configured to load parameters corresponding to the target game while dynamically loading the target game.

[0097] In some embodiments, the task push module is further configured to generate a push strategy based on the user profile, specifically including:

[0098] Obtain the cognitive domain of the target user based on the user profile;

[0099] Calculate the basic mental ability value of the target user according to the cognitive domain;

[0100] Determine the cognitive impairment level according to the basic mental ability value;

[0101] Based on the cognitive impairment level and the educational level of the target user, determine the game level.

[0102] The game loading module of the brain training method provided by the present invention includes games with multiple training dimensions, enabling users to receive more scientific and professional cognitive training. Moreover, each training dimension has multiple games with different styles and different difficulties, and has more diverse gameplay. Some games can even train multiple cognitive fields, enabling users to play one game and achieve the effect of training multiple cognitive abilities, making the field more vertical and specific, and bringing a higher physical therapy experience to users. Thus, the problem that the game domain is not clear enough in the prior art is solved, and the user experience is improved.

[0103] The brain training method provided by the present invention can, through the task push module, recommend a suitable customized solution according to the multi-dimensional indicators of the target user and the target user's own situation, thus solving the problem in the prior art that it is impossible to customize a physical therapy plan and push multiple games after big data analysis and prediction.

[0104] The brain training method provided by the present invention integrates multiple games into the game loading module, combines the user perspective, subdivides the cognitive abilities in multiple dimensions, and adopts diverse gameplay and themes, which are easy, interesting, and creative. Moreover, most of them are common games in real life, such as "finding and putting things in place", classifying and storing different daily necessities, enabling users to enjoy the fun of the game in a pleasant and relaxed state, and gradually recovering their cognitive abilities in the game. Thus, the problem that games in the prior art are divorced from life and lack interest is solved.

[0105] The brain-training method provided by the present invention can flexibly set how long games are not recommended repeatedly through games of different styles stored in the task push module and the game loading module, as well as playability (easy and interesting gameplay, easy to get started, fresh creativity), so that users can always maintain a sense of freshness and fun during physical therapy, thereby solving the problem in the prior art that a large number of repetitive games or games with substantially the same gameplay are generated due to the lack of intelligent recommendation, which easily causes users to have a rebellious psychology and improving the user experience.

[0106] Figure 3 An example of the physical structure diagram of an electronic device is shown as Figure 3 shown. The electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the above method.

[0107] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the part of the technical solution of the present invention that essentially contributes to the prior art, or the part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0108] In some embodiments, the electronic device includes:

[0109] A user terminal, which includes a PAD, a self-service machine, and a PC terminal;

[0110] A doctor terminal, which includes a doctor's PC terminal.

[0111] In a specific usage scenario, the entire platform task scheduling adopts xxl-job distributed scheduling tasks. For large amounts of data such as user physiotherapy data and scores, sharding logic is used for scheduling. The sharding method adopts modulo sharding. For example, Service A processes data with an odd modulo, and Server B processes data with an even modulo. Sharding reduces the server pressure and improves the computing power of the program.

[0112] The electronic device can be regarded as the product system of the brain training system. This product system includes the user PAD terminal, the user PC self-service machine, the user large-screen machine, and the doctor's PC computer terminal. Among them, the user PAD terminal is developed based on Android, and the system is changed from the bottom layer to set the brain training system to start automatically when the device boots up. The user large-screen machine is developed based on Android. This device is used to test the user's cognitive impairment. The user large-screen machine contains the complete question banks of MOCA and MMSE, and can also customize a variety of cognitive question banks. After the test is completed, the user does not need to wait for the test report to be generated instantly, allowing the user to understand their own situation in real time. The user PC self-service machine is developed based on Android. The self-service machine is placed in the hospital's rehabilitation room for users to log in and study and complete cognitive training tasks. The doctor's PC computer terminal facilitates the doctor to log in to set the cognitive game parameters and pay attention to the user's recovery situation in real time.

[0113] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the above method.

[0114] The device embodiments described above are merely illustrative. 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing 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.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A brain training system based on big data, characterized in that, The system comprises: A data storage module, the data storage module is used to obtain and store user data, the user data at least includes basic data and game data; A task pushing module, wherein the task pushing module retrieves user data corresponding to the target user stored in the data storage module in response to a login instruction of the target user; The task push module is also used to generate push strategies based on user portraits, including: Obtaining a cognitive domain of a target user based on the user portrait; Calculate the basic brainpower value of the target user according to the cognitive domain; Determining the level of cognitive impairment according to the basic brain power value; Determining a game level based on the cognitive impairment level and the educational level of the target user; Calculating the rehabilitation index of the target user and generating a predicted value of the rehabilitation index based on an autoregressive moving average model; specifically including: Based on the sample data obtained, the endogenous relationship between various types of games and the scores of various types of patients at different stages was obtained; Optimize game types and recommended rules through sample data with good therapeutic effects; According to the patient's recovery situation, combined with the brain power value and the cognitive dysfunction test results, a weighted average is performed to obtain the patient's recovery index, and a predicted value of the recovery index is generated based on the autoregressive moving average model; the patient's own real recovery index is calculated and obtained, and the predicted value of the recovery index is generated based on the autoregressive moving average model through a large number of patient data that have achieved good therapeutic effects. The difference between the patient's recovery index and the predicted value of the recovery index is compared directly to generate or modify the push strategy; According to the difference between the rehabilitation index and the predicted value of the rehabilitation index, a push strategy is generated; specifically including: If the predicted result is consistent with the expected recovery, continue to use the previously recommended rules game; if the recovery situation is significantly different from the expected situation, recommend other similar games until a game that is more suitable for the patient is found; A game loading module is used to store a plurality of games to be selected and push at least one target game in response to the push strategy.

2. The brain training system based on big data according to claim 1, wherein, The system further comprises: A payment module is used to generate payment data according to a preset payment strategy in response to the physiotherapy package selected by the target user, and the payment data at least includes a bill and payment information.

3. The brain training system based on big data according to claim 2, characterized in that According to the difference between the rehabilitation index and the predicted value of the rehabilitation index, a push strategy is generated, which specifically includes: When the difference between the rehabilitation index and the predicted rehabilitation index value is less than a threshold, the historical game type is used as the pushed game; When the difference between the rehabilitation index and the predicted value of the rehabilitation index is greater than or equal to a threshold, a new game type is replaced and the new game type is used as a pushed game.

4. A brain-training method based on big data, based on the method described in any one of claims 1-3, characterized in that, The method comprises: Acquire and store user data, wherein the user data includes at least basic data and game data; In response to a login instruction of a target user, retrieve the user data corresponding to the target user stored in the data storage module, calculate the rehabilitation index of the target user, and generate a predicted value of the rehabilitation index based on an autoregressive moving average model; and generate a push strategy according to the degree of difference between the rehabilitation index and the predicted value of the rehabilitation index; Push at least one target game in response to the push policy.

5. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, the method described in claim 4 is implemented.

6. The electronic device according to claim 5, characterized in that, Including: A client, which includes a PAD, a self-service machine, and a PC; A doctor's end, which includes a doctor's PC.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method described in claim 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the method described in claim 4 is implemented.

Images