Intelligent control method and system for upper and lower limb active and passive training device

Abstract

The invention discloses an upper and lower limb active and passive trainer intelligent control method and system, and the method comprises the steps: obtaining the information data of a user and the use feature data of an upper and lower limb active and passive trainer, calling the information data and use feature data of the user in a target data set through an AI large model, and carrying out the intelligent analysis of the function demands of the user, aI analysis result data of the user is generated and output, personalized recommendation rehabilitation information is formed and pushed to the user, and in other words, the trainer can conduct evaluation analysis on the rehabilitation effect of the user and conduct correlation analysis through the server side; the AI analysis result of the user is generated based on the control parameter information and in combination with the AI large model, the rehabilitation training result can be intelligently evaluated, the machine intelligent evaluation function is achieved, the personalized recommendation rehabilitation function is added and improved, and the use effect, efficiency and function richness of the trainer equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to an intelligent control method and system for an upper and lower limb active and passive trainer. Background Art

[0002] The upper and lower limb rehabilitation trainer is suitable for limb dysfunction caused by a variety of diseases and injuries, including but not limited to sequelae of stroke, spinal cord injury, multiple sclerosis, Parkinson's disease, postoperative recovery of fractures, muscle atrophy, and postoperative recovery of joint replacement.

[0003] However, the evaluation of the training effects of existing upper and lower limb active and passive trainers often relies on manual questionnaires, which are difficult to associate and match with the control parameters, functional modes and training categories of upper and lower limb rehabilitation trainers. The intelligence is relatively general, there is no intelligent analysis of user information and usage characteristics, and it is unable to generate training effect evaluation. In addition, there is still a lack of intelligent control of upper and lower limb active and passive trainers. At the same time, it is difficult to provide users with diversified personalized recommended rehabilitation needs. For this reason, in view of the shortcomings of its relatively single functions and difficulty in intelligent evaluation and selection of training categories, intelligent control modes and parameters at this stage, we propose an intelligent control method and system for upper and lower limb active and passive trainers. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing upper and lower limb active and passive training devices, the present invention is proposed.

[0005] Therefore, one of the objects of the present invention is to provide an intelligent control method and system for upper and lower limb active and passive trainers, which utilize the trainer equipment to obtain the user's information data and usage characteristic data, and generate the user's AI analysis results based on the control parameter information and combined with the AI ​​big model. It can not only intelligently evaluate the rehabilitation training results with machine intelligent evaluation function, but also increase and improve the personalized recommended rehabilitation function, thereby improving the use effect, efficiency and functional richness of the trainer equipment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In one aspect, the present invention provides an intelligent control method for an upper and lower limb active and passive training device, comprising the following steps: Acquire user information data and usage characteristic data of upper and lower limb active and passive trainers, and form a target data set of upper and lower limb active and passive trainers after data clustering; Through the AI ​​big model and calling the information data and usage characteristic data of the user in the target data set, an intelligent analysis of the user's functional requirements is performed, and after matching the user, an intelligent control mode and training strategy data of the upper and lower limb active and passive trainer are generated, and the control parameter information of the upper and lower limb active and passive trainer is matched according to the intelligent control mode and training strategy data, and the user's AI analysis result data is generated according to the control parameter information and output; The upper and lower limb active and passive trainer receives and responds to the user's AI analysis result data, recommends the intelligent control mode and training strategy data in the AI ​​analysis result data to the user for selection to form personalized recommended rehabilitation information, and visualizes the personalized recommended rehabilitation information to present the detailed functions of the intelligent control mode and the detailed contents of the training strategy and training function parameters; The upper and lower limb active and passive trainer completes the electrical control signal matching of the main control drive system according to the control parameter information, and waits for the user to confirm to start.

[0007] As a preferred solution of the present invention, the intelligent control mode includes an active mode, a passive mode, and an active-passive mode, and the intelligent control mode switching of different users and usage characteristics is completed through the intelligent control mode; The passive mode is the default startup mode of the upper and lower limb active and passive trainer. The passive mode is configured as a commonly used training mode function selection after matching through AI intelligent analysis and processing based on the user's usage characteristic data; at the same time, when the sensor of the upper and lower limb active and passive trainer detects that the motor speed is 2r / min higher than the preset speed value for 3 consecutive seconds during operation, the upper and lower limb active and passive trainer automatically switches from the passive mode to the active mode; The active mode is a training mode function selection configuration performed according to the user's current output information by matching and determining the user's current output information; at the same time, when the training mode is the active mode, when the sensor of the upper and lower limb active and passive trainer detects that the motor speed is less than 9r / min for 2 consecutive seconds, it automatically switches from the active mode to the passive mode; The active-passive mode is used for intelligent switching between the active mode and the passive mode.

[0008] As a preferred solution of the present invention, wherein: the active and passive modes are intelligently switched between active mode and passive mode after analyzing the user's information data and the matching usage feature data; The intelligent switching between the active mode and the passive mode is specifically that when the user exerts more force than a preset threshold matched by the intelligent switching, the upper and lower limb active and passive training device enters the active mode, and when the user does not exert force and does not exceed the preset threshold matched by the intelligent switching, the upper and lower limb active and passive training device automatically switches to the passive mode; The parameter values ​​of the passive mode, active passive mode and active passive mode are all set as default values. During the training process, the user's current usage feature data is obtained, and the generated AI analysis results are responded to and recommended to the user for the user to select and confirm before modification.

[0009] As a preferred solution of the present invention, the training strategy data includes lower limb training control strategy data, upper limb training control strategy data, and spasticity function training control strategy data; The lower limb training control includes: forward rotation training control and reverse rotation training control with changing direction; The upper limb training control includes: horizontal training, vertical cross and vertical parallel upper limb training control.

[0010] As a preferred embodiment of the present invention, the strategy data of the lower limb training control and the upper limb training control are specifically the training parameters of the lower limbs and upper limbs, and the training parameters of the lower limbs and upper limbs include: duration, control resistance and running speed parameter information.

[0011] As a preferred solution of the present invention, the spasticity function training control is set to an on state by default, and after being turned on, the user's characteristic data of spasticity is intelligently identified, and the movement direction is automatically reversed to relieve the spasticity after the spasticity is identified, and after deceleration and stopping, the upper and lower limb active and passive training device slowly returns to the original training direction and speed; If the upper and lower limb active and passive trainer detects spasm again after reversal, reactivate the spasm protection. The number of consecutive reactivations of spasm protection shall not exceed 5 times, otherwise the upper and lower limb active and passive trainer stops output; At the same time, after the spasm protection is turned on for the upper and lower limb active and passive trainers, the spasm recognition sensitivity is divided into low, medium and high, and has a sensitivity adjustment function. Among them, the low sensitivity corresponds to a trigger time of 4.5s; the medium sensitivity corresponds to a trigger time of 2.5s; the high sensitivity corresponds to a trigger time of 1.5s, with an error of ±0.5s. When the spasm recognition sensitivity conditions are met, it is identified as the corresponding degree of spasm.

[0012] As a preferred solution of the present invention, it also includes: after the user completes the rehabilitation training using the upper and lower limb active and passive trainer, at least one graphical interface is provided, and a pop-up questionnaire survey message and a machine score of the upper and lower limb active and passive trainer are used to give the current rehabilitation training effect based on the currently completed rehabilitation training, and a scoring operation of 1-10 points for different categories of rehabilitation training effects is performed, and statistics of the rehabilitation training results are performed, and after matching the user's information data and usage feature data, the user's rehabilitation training result data is generated; The rehabilitation training effects include functional assessment, activity ability assessment, quality of life assessment, electromyographic signal analysis, spasticity level assessment, training data record assessment, and training trend change assessment.

[0013] As a preferred solution of the present invention, the AI ​​analysis result of the user is generated, specifically by obtaining the control parameter information of the user, and establishing a training control evaluation expert library of upper and lower limb active and passive trainers based on the AI ​​big model, and by building a big model expert group, the control parameters of the user in the training control evaluation expert library and the information data of the user are evaluated and analyzed for the rehabilitation effect of the user; At the same time, LSTM long short-term memory network analysis is used to generate corresponding rehabilitation training program information, and association analysis is performed based on the rehabilitation training program information. Then, user information data belonging to the upper and lower limb active and passive trainers and weight data using feature data are generated. According to the control parameter information of the upper and lower limb active and passive trainers, the rehabilitation training program information currently associated with the user is determined, and output as the rehabilitation training information output result of the deep learning network of the upper and lower limb active and passive trainers.

[0014] In one aspect, the present invention provides an intelligent control system for an upper and lower limb active and passive training device, comprising: The trainer acquisition module is used to acquire the user's information data and the usage characteristic data of the upper and lower limb active and passive trainers, and to form a target data set of the upper and lower limb active and passive trainers after data clustering; The server data processing module is used to perform intelligent analysis of user functional requirements through the AI ​​big model and calling the information data and usage characteristic data of the user in the target data set, generate intelligent control modes and training strategy data of the upper and lower limb active and passive trainers after matching the users, match the control parameter information of the upper and lower limb active and passive trainers according to the intelligent control mode and training strategy data, generate and output the user's AI analysis result data according to the control parameter information; The trainer data receiving module is used for the upper and lower limb active and passive trainers to receive and respond to the user's AI analysis result data, recommend the intelligent control mode and training strategy data in the AI ​​analysis result data to the user to select to form personalized recommended rehabilitation information, and visualize the personalized recommended rehabilitation information to present the detailed functions of the intelligent control mode and the detailed content of the training strategy and the training function parameters; The trainer electronic control module is used for the upper and lower limb active and passive trainers to complete the electronic control signal matching of the main control drive system according to the control parameter information, and wait for the user to confirm the start; The rehabilitation training result statistics module is used to give the current rehabilitation training effect based on the currently completed rehabilitation training through pop-up questionnaire information, and to score different categories of rehabilitation training effects with a score of 1-10. After matching the user's information data and usage feature data, the user's rehabilitation training result data is generated.

[0015] As a preferred solution of the present invention, it also includes a main control drive system for controlling the upper and lower limb active and passive trainers by electrical signals, and the main control drive system includes: a touch display unit, an upper limb Hall detection unit, a lower limb Hall detection unit, an emergency switch, a rehabilitation analysis unit, an upper limb motor encoder, a lower limb motor encoder, an upper limb DC brush motor, an upper limb and lower limb switching circuit, and a lower limb DC brush motor.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the intelligent control method of the upper and lower limb active and passive trainers of the present invention utilizes the trainer equipment to obtain the user's information data and usage characteristic data, and generates the user's AI analysis results based on the control parameter information and combined with the AI ​​big model. It can not only intelligently evaluate the rehabilitation training results with machine intelligent evaluation function, but also increase and improve the personalized recommended rehabilitation function, thereby improving the use effect, efficiency and functional richness of the trainer equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 It is a flow chart of the intelligent control method of the upper and lower limb active and passive training device in an embodiment of the present invention; Figure 2 It is a schematic diagram of the lower limb training operation interface of the intelligently controlled upper and lower limb active and passive training device in an embodiment of the present invention; Figure 3 It is a schematic diagram of an upper limb training function selection interface of the intelligent control of the upper and lower limb active and passive training device in an embodiment of the present invention; Figure 4 A schematic diagram of an active mode parameter setting operation interface of an upper and lower limb active and passive training device according to an embodiment of the present invention; Figure 5 It is a schematic diagram of the modular structure of the intelligent control system of the upper and lower limb active and passive training device in an embodiment of the present invention; Figure 6 It is a schematic diagram of the modular structure of the main control drive system in the intelligent control system of the upper and lower limb active and passive training device in an embodiment of the present invention; Numbers in the figure: 100, trainer acquisition module; 101, server data processing module; 102, trainer data receiving module; 103, trainer electronic control module; 104, rehabilitation training result statistics module. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0019] Reference Figure 1-Figure 4 , is an embodiment of the present invention, which provides an intelligent control method for upper and lower limb active and passive training devices, such as Figure 1 As shown, the following steps are included: Step 1, obtaining user information data and usage characteristic data of upper and lower limb active and passive trainers, and performing data clustering to form a target data set of upper and lower limb active and passive trainers; Step 2: Use the AI ​​big model and call the user's information data and usage feature data in the target data set to perform intelligent analysis of the user's functional requirements, generate intelligent control modes and training strategy data of the upper and lower limb active and passive trainers after matching the users, match the control parameter information of the upper and lower limb active and passive trainers according to the intelligent control mode and training strategy data, generate the user's AI analysis result data according to the control parameter information and output it; Step 3: The upper and lower limb active and passive trainer receives and responds to the user's AI analysis result data, recommends the intelligent control mode and training strategy data in the AI ​​analysis result data to the user for selection to form personalized recommended rehabilitation information, and visualizes the personalized recommended rehabilitation information to present the detailed functions of the intelligent control mode, the detailed content of the training strategy, and the training function parameters; Step 4: The upper and lower limb active and passive training device completes the electrical control signal matching of the main control drive system according to the control parameter information, and waits for the user to confirm the start; Step five also includes providing at least one graphical interface after the user completes rehabilitation training using the upper and lower limb active and passive trainer, and using pop-up questionnaire messages and machine scoring of the upper and lower limb active and passive trainer to give the current rehabilitation training effect based on the currently completed rehabilitation training, and scoring different categories of rehabilitation training effects with a score of 1-10 points, and performing statistics on the rehabilitation training results. After matching the user's information data and usage characteristic data, the user's rehabilitation training result data is generated; wherein the rehabilitation training effects include functional assessment, activity ability assessment, quality of life assessment, electromyography signal analysis, spasticity level assessment, training data record assessment, and training trend change assessment.

[0020] This embodiment further illustrates that the functional assessment is to assess the patient's physical strength, flexibility, balance ability and other functions during the rehabilitation training to understand the changes before and after the rehabilitation training.

[0021] Activity assessment: Assess the patient's ability in daily activities, including walking, going up and down stairs, sitting and standing transfers, and other common activities. The effect of rehabilitation training is evaluated by recording the changes in the patient's activity ability before and after rehabilitation training.

[0022] Quality of life assessment: The goal of rehabilitation training is to improve the patient's quality of life, so it is also very important to assess the patient's quality of life. Some quality of life questionnaires, such as SF-36, can be used to understand the changes in the patient's quality of life before and after rehabilitation training.

[0023] EMG signal analysis: By collecting surface EMG signals of designated parts of the human body during rehabilitation training, and performing denoising and effective signal extraction, the effective EMG signals corresponding to the rehabilitation movements of the human body can be extracted from the collected EMG signals.

[0024] Spasm level assessment: Assess the spasm level, adjustable from 1 to 6 levels. The higher the level, the higher the spasm sensitivity and the easier it is to trigger spasm protection.

[0025] Training data record: After training, all training records of the patient can be automatically saved and a training report can be generated. The training report includes basic information (name, number, gender, age, height, weight, cause of disease), training parameters (game name, training mode, spasm level, training part, game difficulty), training status (game score, average power, average speed, energy consumption, number of spasms, training mileage, training time, symmetry ratio).

[0026] Changes in training trends: The training report must reflect changes in training trends, including power change trend graphs and resistance / speed change trend graphs, so that the clinician can have a clear and comprehensive grasp of the patient's training situation each time.

[0027] It should be emphasized in this embodiment that when generating the AI ​​analysis results of the user, the user's control parameter information is obtained, and a training control evaluation expert library of upper and lower limb active and passive trainers is established based on the AI ​​big model. By building a big model expert group, the user's control parameters and user information data in the training control evaluation expert library are evaluated and analyzed to determine the user's rehabilitation effect; at the same time, the LSTM long short-term memory network analysis is used to generate corresponding rehabilitation training program information, and association analysis is performed based on the rehabilitation training program information. Then, the user information data of the upper and lower limb active and passive trainers and the weight data of the feature data are generated, and according to the control parameter information of the upper and lower limb active and passive trainers, the rehabilitation training program information currently associated with the user is determined, and output as the rehabilitation training information output result of the deep learning network of the upper and lower limb active and passive trainers.

[0028] Specifically, in this embodiment, the intelligent control mode includes: active mode, passive mode, and active-passive mode, and the intelligent control mode switching of different users and usage characteristics is completed through the intelligent control mode; Passive mode is the default startup mode of the upper and lower limb active and passive trainer. The passive mode is configured based on the user's usage characteristic data, and is matched to the commonly used training mode function selection after AI intelligent analysis and processing; at the same time, when the sensor of the upper and lower limb active and passive trainer detects that the motor speed is 2r / min higher than the preset speed value for 3 consecutive seconds during operation, the upper and lower limb active and passive trainer automatically switches from passive mode to active mode; The active mode is a training mode function selection configuration based on the user's current output information, after matching and determining the user's current output information; at the same time, when the training mode is active mode, when the sensor of the upper and lower limb active and passive trainer detects that the motor speed is less than 9r / min for 2 consecutive seconds, it will automatically switch from active mode to passive mode; Active and passive modes are used for intelligent switching between active mode and passive mode.

[0029] Specifically, in this embodiment, the active and passive modes are intelligently switched between the active mode and the passive mode after analyzing the user's information data and the matching usage feature data; The intelligent switching between active mode and passive mode is specifically that when the user exerts more force than the preset threshold matched by the intelligent switching, the upper and lower limb active and passive trainer enters the active mode, and when the user does not exert force and does not exceed the preset threshold matched by the intelligent switching, the upper and lower limb active and passive trainer automatically switches to the passive mode; The parameter values ​​of passive mode, passive mode, and active-passive mode are all set as default values. During the training process, the user's current usage feature data is obtained, and the generated AI analysis results are recommended to the user for the user to select and confirm before modification.

[0030] like Figure 2 and Figure 3 As shown, in this embodiment, when the mode and function are selected, the training strategy data of the functional training specifically includes: lower limb training control strategy data, upper limb training control strategy data, and spasticity function training control strategy data; Lower limb training control includes: forward rotation training control and reverse rotation training control with changing direction; Upper limb training control includes: horizontal training, vertical cross and vertical parallel upper limb training control.

[0031] Specifically, in this embodiment, the strategy data for lower limb training control and upper limb training control are specifically the training parameters of the lower limbs and upper limbs. The training parameters of the lower limbs and upper limbs include: duration, control resistance and running speed parameter information.

[0032] like Figure 4 As shown in the figure, the parameter settings are specifically: the sound setting button can control the voice on and off. The training time setting can set the training time, up to 99 minutes. When the user's training time is reached, it will automatically power off and standby. The spasm button can control the spasm monitoring on and off. The spasm level can be set to high, medium and low. The speed setting is the default speed value in passive mode. The resistance setting is the default resistance value in active mode. The steering time is the switching time between forward and reverse in passive mode.

[0033] Upper limb training is different from lower limb training. This training function has three movement modes. They correspond to "horizontal training", "vertical cross", and "vertical parallel" in Figure 5. In the upper limb horizontal training mode, the user's upper limbs can be trained in a horizontal direction. In this mode, the user's upper limbs can be trained in a vertical cycle on the same plane at the same time, and the switching function of the two vertical training modes can be realized; the training object holds the upper limb training handle with both hands. Directly select the "upper limb training" button, and then select "horizontal training", "vertical cross", and "vertical parallel" according to the training mode required. Three training modes can be selected: "active and passive" mode, "active" mode, and "passive" mode. In the "active and passive" mode, the product can automatically detect the user's status and determine whether to enter the active mode or the passive mode. When the user exerts force, the product enters the active mode, and when the user does not exert force, the device automatically switches to the passive mode. The active and passive parameter values ​​are the default values, and the training process can be manually modified.

[0034] Specifically, in this embodiment, the spasticity function training control is turned on by default, and after being turned on, the user's characteristic data of spasticity is intelligently identified, and the movement direction is automatically reversed to relieve the spasticity after the spasticity is identified, and after the deceleration stops, the upper and lower limb active and passive training device slowly returns to the original training direction and speed; If the upper and lower limb active and passive trainer detects spasm again after reversal, reactivate the spasm protection. The number of consecutive reactivations of spasm protection shall not exceed 5 times, otherwise the upper and lower limb active and passive trainer stops output; At the same time, after the spasm protection is turned on for the upper and lower limb active and passive trainers, the spasm recognition sensitivity is divided into low, medium and high, and has a sensitivity adjustment function. Among them, the low sensitivity corresponds to a trigger time of 4.5s; the medium sensitivity corresponds to a trigger time of 2.5s; the high sensitivity corresponds to a trigger time of 1.5s, with an error of ±0.5s. When the spasm recognition sensitivity conditions are met, it is identified as the corresponding degree of spasm.

[0035] The intelligent control method and system of the upper and lower limb active and passive trainer of this embodiment are applied to the upper and lower limb active and passive trainer. The upper and lower limb active and passive trainer is a circular motion training device, and its working principle is: according to the set parameters, a given signal is output or the patient's own muscle strength is relied on to make the patient's limb extremities move in a circular motion along a fixed axis, driving the entire limbs of unilateral or bilateral upper limbs and / or lower limbs (including shoulders, elbows, wrists, fingers, hips, knees, ankle joints and related muscle groups) to perform comprehensive motion training to enhance the patient's joint mobility and muscle strength.

[0036] When the patient is in a sitting or lying position, he or she can stably fix the upper and / or lower limbs on the motion platform of this product, and set the training mode and parameters through the touch screen according to the type of functional impairment of the patient to complete active or passive training. During the entire training process, the product always performs circular motion training, and the real-time monitoring feedback protection system identifies the patient's muscle strength state (spasm identification) and automatically switches the training mode. The intelligent control method and system of the upper and lower limb active and passive trainer of this embodiment have the following main functions: active mode, passive mode, and automatic switching between active and passive modes.

[0037] refer to Figure 5 and Figure 6 The present invention provides an intelligent control system for upper and lower limb active and passive training devices, comprising: The trainer acquisition module 100 is used to acquire the user's information data and the usage characteristic data of the upper and lower limb active and passive trainers, and to form a target data set of the upper and lower limb active and passive trainers after data clustering; The server data processing module 101 is used to perform intelligent analysis of user functional requirements through the AI ​​big model and calling the information data and usage characteristic data of the user in the target data set, generate intelligent control modes and training strategy data of the upper and lower limb active and passive trainers after matching the users, match the control parameter information of the upper and lower limb active and passive trainers according to the intelligent control mode and training strategy data, generate the user's AI analysis result data according to the control parameter information and output it; The trainer data receiving module 102 is used for the upper and lower limb active and passive trainer to receive and respond to the user's AI analysis result data, recommend the intelligent control mode and training strategy data in the AI ​​analysis result data to the user to select to form personalized recommended rehabilitation information, and visualize the personalized recommended rehabilitation information to present the detailed functions of the intelligent control mode and the detailed content of the training strategy and the training function parameters; The trainer electronic control module 103 is used for the upper and lower limb active and passive trainers to complete the electronic control signal matching of the main control drive system according to the control parameter information, and wait for the user to confirm the start; The rehabilitation training result statistics module 104 is used to give the current rehabilitation training effect based on the currently completed rehabilitation training through a pop-up questionnaire survey message, and to perform a scoring operation of 1-10 points for different categories of rehabilitation training effects, and to generate the user's rehabilitation training result data after matching the user's information data and usage feature data.

[0038] like Figure 6 As shown, the system of this embodiment also includes a main control drive system for controlling the upper and lower limb active and passive trainers with electrical signals, and the main control drive system includes: a touch display unit, an upper limb Hall detection unit, a lower limb Hall detection unit, an emergency switch, a rehabilitation analysis unit, an upper limb motor encoder, a lower limb motor encoder, an upper limb DC brush motor, an upper limb and lower limb switching circuit, and a lower limb DC brush motor.

[0039] Based on the above, the intelligent control method can monitor the user's training performance in real time and perform intelligent evaluation according to the preset rehabilitation goals. The system provides instant feedback to help users adjust the intensity and method of training to achieve the best rehabilitation effect. Based on the user's training data and AI analysis results, the intelligent control system can recommend personalized rehabilitation training plans. These recommended plans include exercise type, intensity, frequency and duration to adapt to the user's specific situation and rehabilitation needs. Through intelligent control methods, trainer equipment can provide a more scientific and efficient training experience, thereby improving the user's rehabilitation effect. It can also dynamically adjust the training plan based on user feedback and progress to ensure the continuity and effectiveness of the training. The functional richness of the equipment has been improved, and it can provide users with more comprehensive and in-depth rehabilitation support.

[0040] To sum up, this embodiment can generate AI analysis results for users based on control parameter information and combined with the AI ​​big model. It can not only intelligently evaluate the rehabilitation training results with machine intelligent evaluation function, but also increase and improve the personalized rehabilitation recommendation function, thereby improving the use effect, efficiency and functional richness of the training equipment.

[0041] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0042] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0043] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0044] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0045] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0046] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0047] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent control method for upper and lower limb active and passive training devices, characterized in that: The following steps are involved: Acquire user information data and usage characteristic data of upper and lower limb active and passive trainers, and form a target data set of upper and lower limb active and passive trainers after data clustering; Through the AI ​​big model and calling the information data and usage characteristic data of the user in the target data set, an intelligent analysis of the user's functional requirements is performed, and after matching the user, an intelligent control mode and training strategy data of the upper and lower limb active and passive trainer are generated, and the control parameter information of the upper and lower limb active and passive trainer is matched according to the intelligent control mode and training strategy data, and the user's AI analysis result data is generated according to the control parameter information and output; The upper and lower limb active and passive trainer receives and responds to the user's AI analysis result data, recommends the intelligent control mode and training strategy data in the AI ​​analysis result data to the user for selection to form personalized recommended rehabilitation information, and visualizes the personalized recommended rehabilitation information to present the detailed functions of the intelligent control mode and the detailed contents of the training strategy and training function parameters; The upper and lower limb active and passive trainer completes the electrical control signal matching of the main control drive system according to the control parameter information, and waits for the user to confirm to start.

2. The intelligent control method of the upper and lower limb active and passive training device according to claim 1, characterized in that: The intelligent control modes include: active mode, passive mode, and active-passive mode, through which intelligent control mode switching for different users and usage characteristics is completed; The passive mode is the default startup mode of the upper and lower limb active and passive trainer. The passive mode is configured as a commonly used training mode function selection after matching through AI intelligent analysis and processing based on the user's usage characteristic data; at the same time, when the sensor of the upper and lower limb active and passive trainer detects that the motor speed is 2r / min higher than the preset speed value for 3 consecutive seconds during operation, the upper and lower limb active and passive trainer automatically switches from the passive mode to the active mode; The active mode is a training mode function selection configuration performed according to the user's current output information by matching and determining the user's current output information; at the same time, when the training mode is the active mode, when the sensor of the upper and lower limb active and passive trainer detects that the motor speed is less than 9r / min for 2 consecutive seconds, it automatically switches from the active mode to the passive mode; The active-passive mode is used for intelligent switching between the active mode and the passive mode.

3. The intelligent control method of the upper and lower limb active and passive training device as claimed in claim 2, characterized in that: The active and passive modes are intelligently switched between active mode and passive mode after analyzing the user's information data and the matching usage feature data; The intelligent switching between the active mode and the passive mode is specifically that when the user exerts more force than a preset threshold matched by the intelligent switching, the upper and lower limb active and passive training device enters the active mode, and when the user does not exert force and does not exceed the preset threshold matched by the intelligent switching, the upper and lower limb active and passive training device automatically switches to the passive mode; The parameter values ​​of the passive mode, active passive mode and active passive mode are all set as default values. During the training process, the user's current usage feature data is obtained, and the generated AI analysis results are responded to and recommended to the user for the user to select and confirm before modification.

4. The intelligent control method for upper and lower limb active and passive training device according to claim 1, characterized in that: The training strategy data includes: lower limb training control strategy data, upper limb training control strategy data, and spasticity function training control strategy data; The lower limb training control includes: forward rotation training control and reverse rotation training control with changing direction; The upper limb training control includes: horizontal training, vertical cross and vertical parallel upper limb training control.

5. The intelligent control method of the upper and lower limb active and passive training device as claimed in claim 4, characterized in that: The strategy data of the lower limb training control and the upper limb training control are specifically the training parameters of the lower limbs and the upper limbs. The training parameters of the lower limbs and the upper limbs include: duration, control resistance and running speed parameter information.

6. The intelligent control method for upper and lower limb active and passive training device according to claim 4, characterized in that: The spasticity function training control is turned on by default, and after being turned on, it intelligently identifies the user's characteristic data of spasticity, automatically reverses the movement direction after identifying the spasticity to relieve the spasticity, and after deceleration and stopping, the upper and lower limb active and passive training device slowly returns to the original training direction and speed; If the upper and lower limb active and passive trainer detects spasm again after reversal, reactivate the spasm protection. The number of consecutive reactivations of spasm protection shall not exceed 5 times, otherwise the upper and lower limb active and passive trainer stops output; At the same time, after the spasm protection is turned on for the upper and lower limb active and passive trainers, the spasm recognition sensitivity is divided into low, medium and high, and has a sensitivity adjustment function. Among them, the low sensitivity corresponds to a trigger time of 4.5s; the medium sensitivity corresponds to a trigger time of 2.5s; the high sensitivity corresponds to a trigger time of 1.5s, with an error of ±0.5s. When the spasm recognition sensitivity conditions are met, it is identified as the corresponding degree of spasm.

7. The intelligent control method for upper and lower limb active and passive training devices according to claim 1, characterized in that: It also includes providing at least one graphical interface after the user completes rehabilitation training using the upper and lower limb active and passive training device, and providing a current rehabilitation training effect based on the currently completed rehabilitation training through a pop-up questionnaire survey message and a machine score of the upper and lower limb active and passive training device, and scoring different categories of rehabilitation training effects with a score of 1-10, and performing statistics on the rehabilitation training results, and generating rehabilitation training result data for the user after matching the user's information data and usage feature data; The rehabilitation training effects include functional assessment, activity ability assessment, quality of life assessment, electromyographic signal analysis, spasticity level assessment, training data record assessment, and training trend change assessment.

8. The intelligent control method for upper and lower limb active and passive training device according to claim 7, characterized in that: Generate AI analysis results for users, specifically by obtaining control parameter information of users, and establishing a training control evaluation expert database for upper and lower limb active and passive trainers based on the AI ​​big model, and by building a big model expert group, conduct evaluation and analysis of user rehabilitation effects on the control parameters of users in the training control evaluation expert database and the information data of the users; At the same time, LSTM long short-term memory network analysis is used to generate corresponding rehabilitation training program information, and association analysis is performed based on the rehabilitation training program information. Then, user information data belonging to the upper and lower limb active and passive trainers and weight data using feature data are generated. According to the control parameter information of the upper and lower limb active and passive trainers, the rehabilitation training program information currently associated with the user is determined, and output as the rehabilitation training information output result of the deep learning network of the upper and lower limb active and passive trainers.

9. An intelligent control system for an upper and lower limb active and passive training device, applied to an intelligent control method for an upper and lower limb active and passive training device as claimed in claim 8, characterized in that: include: The trainer acquisition module is used to acquire the user's information data and the usage characteristic data of the upper and lower limb active and passive trainers, and to form a target data set of the upper and lower limb active and passive trainers after data clustering; The server data processing module is used to perform intelligent analysis of user functional requirements through the AI ​​big model and calling the information data and usage characteristic data of the user in the target data set, generate intelligent control modes and training strategy data of the upper and lower limb active and passive trainers after matching the users, match the control parameter information of the upper and lower limb active and passive trainers according to the intelligent control mode and training strategy data, generate and output the user's AI analysis result data according to the control parameter information; The trainer data receiving module is used for the upper and lower limb active and passive trainers to receive and respond to the user's AI analysis result data, recommend the intelligent control mode and training strategy data in the AI ​​analysis result data to the user to select to form personalized recommended rehabilitation information, and visualize the personalized recommended rehabilitation information to present the detailed functions of the intelligent control mode and the detailed content of the training strategy and the training function parameters; The trainer electronic control module is used for the upper and lower limb active and passive trainers to complete the electronic control signal matching of the main control drive system according to the control parameter information, and wait for the user to confirm the start; The rehabilitation training result statistics module is used to give the current rehabilitation training effect based on the currently completed rehabilitation training through pop-up questionnaire information, and to score different categories of rehabilitation training effects with a score of 1-10. After matching the user's information data and usage feature data, the user's rehabilitation training result data is generated.

10. An intelligent control system for active and passive training devices for upper and lower limbs as claimed in claim 9, characterized in that: It also includes a main control drive system for controlling the upper and lower limb active and passive trainers with electrical signals, and the main control drive system includes: a touch display unit, an upper limb Hall detection unit, a lower limb Hall detection unit, an emergency switch, a rehabilitation analysis unit, an upper limb motor encoder, a lower limb motor encoder, an upper limb DC brush motor, an upper limb and lower limb switching circuit, and a lower limb DC brush motor.

Images