Gas-electricity-heat combined control method and platform for pneumatic rehabilitation gloves

Abstract

The invention discloses a gas-electricity-heat combined control method and platform for a pneumatic rehabilitation glove, and relates to the related field of rehabilitation equipment control, and the method comprises the steps: carrying out the state capture of a finger of a user through the pneumatic rehabilitation glove, and obtaining a finger state data set before training; a finger health state evaluation model is constructed to analyze the finger state data set, and a rehabilitation training scheme is output; and the control module is connected with the motion control module and performs gas-electricity-heat combined control training on the pneumatic system, the electrical stimulation system and the thermal therapy system according to the rehabilitation training scheme. According to the finger rehabilitation training method and device, the technical problems that existing finger rehabilitation training is insufficient in pertinence and effectiveness, and consequently the training precision and efficiency are low are solved, and the technical effects that the pertinence and effectiveness are improved, and then the finger rehabilitation training precision and efficiency are improved are achieved.

Description

Technical Field

[0001] The present application relates to the field related to rehabilitation equipment control, and in particular to a gas-electric-heat combined control method and platform for pneumatic rehabilitation gloves. Background Art

[0002] Finger rehabilitation training is of great significance for promoting the recovery of hand function and improving the quality of life of users. At present, the main method to solve the problem of finger rehabilitation training is to use single or simple combined rehabilitation equipment, such as relying only on pneumatic systems or electrical stimulation systems for training. These methods lack comprehensive capture of finger status and the formulation of personalized training plans, resulting in limited training effects, and it is difficult to meet the specific needs of different patients at different stages of rehabilitation. There are problems such as long rehabilitation cycles and uneven effects.

[0003] Among the current related technologies, finger rehabilitation training lacks pertinence and effectiveness, which leads to technical problems such as low training accuracy and efficiency. Summary of the invention

[0004] The present application provides a combined air-electric-thermal control method and platform for pneumatic rehabilitation gloves. It uses pneumatic rehabilitation gloves to capture finger status data, analyzes the data through a finger health status assessment model to output a personalized rehabilitation training plan, and uses a motion control module to perform combined control training on the pneumatic, electrical stimulation and thermal therapy systems. This achieves the technical effect of improving the targeting and effectiveness, thereby improving the accuracy and efficiency of finger rehabilitation training.

[0005] The present application provides a combined air-electric-thermal control method for pneumatic rehabilitation gloves, comprising: capturing the state of a user's fingers through pneumatic rehabilitation gloves to obtain a finger state data group before training, wherein the pneumatic rehabilitation gloves are provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data; constructing a finger health state assessment model to analyze the finger state data group, and outputting a rehabilitation training plan, wherein the rehabilitation training plan includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value, and a thermal therapy temperature parameter value; connecting a motion control module, and the motion control module performs combined air-electric-thermal control training on a pneumatic system, an electrical stimulation system, and a thermal therapy system according to the rehabilitation training plan.

[0006] In a possible implementation, a finger health status assessment model is constructed to analyze the finger status data group, and the following processing is performed: the finger health status assessment model determines whether the historical finger status data group of the user is included by querying the data memory library. If the historical finger status data group is not included, a rehabilitation training plan is output according to the finger status data group; if the historical finger status data group is included, a rehabilitation training plan is output by combining the finger status data group and the historical finger status data group.

[0007] In a possible implementation, a rehabilitation training plan is output according to the finger state data group, and the following processing is performed: the constraint values ​​corresponding to the pneumatic system, the electrical stimulation system and the thermal therapy system are configured respectively; a rehabilitation joint training function is constructed, and the data of the finger state data group is calculated using the rehabilitation joint training function under the condition of the constraint values ​​to obtain a rehabilitation training plan.

[0008] In a possible implementation, the rehabilitation training plan is output in combination with the finger state data group and the historical finger state data group, and the following processing is performed: identifying the historical record days of the historical finger state data group; assigning weight coefficients to the historical finger state data group according to the historical record days to obtain a weight coefficient group; under the condition of the constraint value, the rehabilitation joint training function calculates the data of the finger state data group and the historical finger state data group according to the weight coefficient group to obtain a rehabilitation training plan.

[0009] In a possible implementation, before the finger state data group is input into the finger health status assessment model for analysis, the finger state data group is subjected to error elimination through a limiting filtering algorithm, and the following processing is performed: a preset difference is set, and each sampling value in the finger state data group is compared according to the preset difference; if the difference between the current sampling value and the previous valid value is greater than the preset difference, the previous sampling value is retained as the valid value of the current sampling value; if the difference between the current sampling value and the previous valid value is less than or equal to the preset difference, the current sampling value is retained as the valid value, and the filtered finger state data group is obtained.

[0010] In a possible implementation, the following processing is performed: error elimination is performed on the finger state data set by using a limiting filtering algorithm, and the expression is as follows: ; in, is the effective value at the current sampling time point, is the sampling value at the current sampling time point, is the effective value of the previous sampling time point, is the difference between the current sampling value and the previous valid value, and A is the preset difference.

[0011] In a possible implementation, the following processing is performed: after sending the rehabilitation training program to the motion control module for gas-electric-heat joint control analysis, the finger state data group after training is recorded; the finger state data group before training and the finger state data group after training of the user are stored in the data memory.

[0012] In a possible implementation, the following processing is performed: the motion control module is also connected to the HIM interaction module, and the HIM interaction module includes a display module and a prompt module; wherein the display module is used to display the user's training, and the prompt module is used to provide training guidance to the user according to the stored rehabilitation training plan.

[0013] The present application also provides an air-electric-thermal joint control platform for pneumatic rehabilitation gloves, including: a finger state capture module, used to capture the state of the user's fingers through the pneumatic rehabilitation gloves, and obtain a finger state data group before training, wherein the pneumatic rehabilitation gloves are provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data; a finger health state evaluation module, used to construct a finger health state evaluation model to analyze the finger state data group, and output a rehabilitation training plan, wherein the rehabilitation training plan includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value and a thermal therapy temperature parameter value; an air-electric-thermal joint control training module, used to connect a motion control module, and the motion control module performs air-electric-thermal joint control training on the pneumatic system, the electrical stimulation system and the thermal therapy system according to the rehabilitation training plan.

[0014] The proposed pneumatic, electric and thermal joint control method and platform for pneumatic rehabilitation gloves in this application firstly captures the state of the user's fingers through the pneumatic rehabilitation gloves to obtain the finger state data group before training, wherein the pneumatic rehabilitation gloves are provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data, then constructs a finger health state assessment model to analyze the finger state data group, and outputs a rehabilitation training program, wherein the rehabilitation training program includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value and a thermal therapy temperature parameter value, and finally connects a motion control module, and the motion control module performs pneumatic, electric and thermal joint control training on the pneumatic system, the electrical stimulation system and the thermal therapy system according to the rehabilitation training program. The technical effect of improving the pertinence and effectiveness, and thus improving the accuracy and efficiency of finger rehabilitation training is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in this application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic flow chart of a combined gas-electric-heat control method for pneumatic rehabilitation gloves provided in an embodiment of the present application.

[0017] Figure 2 A schematic diagram of a flow chart for outputting rehabilitation training programs according to different situations in the air-electric-heat combined control method for pneumatic rehabilitation gloves provided in an embodiment of the present application.

[0018] Figure 3 Schematic diagram of the combined air-electric-heat control platform for pneumatic rehabilitation gloves provided in an embodiment of the present application.

[0019] Figure 4 A schematic diagram of the structure of a gas-electric-heat combined control platform for pneumatic rehabilitation gloves provided in an embodiment of the present application.

[0020] Explanation of the reference numerals: finger status capturing module 10 , finger health status assessing module 20 , gas-electric-heat combined control training module 30 . DETAILED DESCRIPTION

[0021] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0022] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0023] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0024] The present application embodiment provides a combined air-electric-heat control method for pneumatic rehabilitation gloves, such as Figure 1 As shown, the method includes: Step S100, capturing the state of the user's fingers through the pneumatic rehabilitation gloves to obtain a finger state data group before training, wherein the pneumatic rehabilitation gloves are provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data.

[0025] Specifically, each finger of the pneumatic rehabilitation glove is equipped with a flexible film sensor, which fits tightly on the user's fingers. The flexible film sensor has high sensitivity and good fit, and can sense the bending and extension movements of the fingers in real time. When the fingers are flexed or extended, the flexible film sensor will generate corresponding electrical signal changes according to the degree of bending and extension of the fingers. These electrical signals are collected and converted into digital data through the circuit system inside the glove. The collected data is organized into finger state data groups, including finger flexion state data and finger extension state data. These data include the flexion angle, extension angle and corresponding duration of each finger at different time points.

[0026] For example, when the user uses the gloves for the first time every day, the user's hand is evaluated. Each finger of the pneumatic rehabilitation gloves worn by the user is equipped with a flexible film sensor. The corresponding relationship between the resistance value and curvature of the flexible film sensor can be used to calculate the current bending angle of each finger joint. Taking the hand straight extension as 0° as the benchmark, the normal hand range of motion is -20° to 260°, and the maximum range of motion that the gloves can measure is -50° to 300°. The measurement will perform maximum and minimum measurements, and a set of angle value data will be collected for each fist or stretch. The user actively exerts force to drive the gloves to evaluate the curvature. The user first clenched his fingers for 10 seconds according to the voice prompt, and then stretched his fingers for 10 seconds following the voice prompt. During this period, the data only took the last 5 seconds of each activity as a reference.

[0027] Step S200, constructing a finger health status assessment model to analyze the finger status data group and output a rehabilitation training program, wherein the rehabilitation training program includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value and a thermal therapy temperature parameter value.

[0028] Specifically, a finger health status assessment model is constructed using machine learning or deep learning technology. The model learns the correlation between the finger health status and the finger status data group by training a large amount of finger status data.

[0029] The construction process is as follows: A large number of finger state data sets are obtained from the flexible film sensor of the pneumatic rehabilitation glove, including finger flexion state data and finger extension state data. At the same time, other information related to the health status of the fingers, such as the user's age, gender, medical history, rehabilitation stage, etc., are collected as auxiliary features. The collected data is cleaned to remove noise data and outliers. For example, the finger state data set is error-eliminated by the limit filter algorithm, a reasonable preset difference is set, each sample value is compared according to the preset difference, the valid value is retained, and the filtered finger state data set is obtained. According to the evaluation of professional doctors or rehabilitation therapists, the data is labeled to clarify the health status of the fingers, such as normal, mildly impaired, moderately impaired, severely impaired, etc., as a supervisory signal for model training. Features related to the health status of the fingers are extracted from the finger state data set, such as the maximum angle, average angle, angle change rate, duration, etc. of finger flexion and extension. At the same time, other information of the user, such as age, gender, etc., is combined as part of the features. Through correlation analysis, feature importance evaluation and other methods, features that have an important impact on the evaluation of the health status of the fingers are selected, redundant features are removed, and the performance and efficiency of the model are improved. According to the characteristics of the finger health status assessment task, select the machine learning or deep learning model architecture. For example, traditional machine learning models such as decision trees, random forests, and support vector machines can be used, or deep learning models such as convolutional neural networks (CNNs), recurrent neural networks (RNNs) and their variants (such as long short-term memory networks LSTM, gated recurrent units GRU) can be used. For time series data (such as finger status data at different time points), RNNs and their variants are more suitable. The cleaned and labeled data are divided into training sets and test sets. Use the training set to train the selected model and optimize the performance of the model by adjusting the model's hyperparameters (such as learning rate, number of layers, number of neurons, etc.). During the training process, use methods such as cross-validation to avoid overfitting and underfitting problems. Use the test set to evaluate the trained model. The evaluation indicators may include accuracy, recall rate, F1 value, etc. Based on the evaluation results, further optimize the structure and parameters of the model to improve the generalization ability and accuracy of the model. Deploy the trained finger health status assessment model into the pneumatic rehabilitation glove system. When the user uses the pneumatic rehabilitation gloves, the finger status data group is obtained in real time and input into the model. The model analyzes the input data and evaluates the health status of the fingers, including the flexibility and coordination of the fingers. According to the output results of the finger health status evaluation model, combined with other information of the user (such as historical finger status data groups, etc.), a personalized rehabilitation training plan is formulated, including the pneumatic training range of activity value (i.e., the maximum flexion and extension angles that the fingers should reach under the action of the pneumatic system), the electrical stimulation training intensity value (i.e., the current intensity that the electrical stimulation system should apply), and the thermal therapy temperature parameter value (i.e., the temperature that the thermal therapy system should reach).

[0030] like Figure 2 As shown, in a possible implementation, a finger health status assessment model is constructed to analyze the finger state data group, and step S200 further includes step S210, wherein the finger health status assessment model determines whether the user's historical finger state data group is included by querying the data memory library, and if the historical finger state data group is not included, a rehabilitation training program is output according to the finger state data group. Specifically, the finger health status assessment model first accesses a pre-established data memory library, which stores the historical finger state data groups of multiple users, each of which contains the user's finger flexion state data and finger extension state data at different time points, and is used to provide data support for the finger health status assessment model. The model uses certain features (such as user ID, biometric information, etc.) in the current user's finger state data group to identify the current user. After identifying the user, the model traverses the records in the data memory library, compares the user identification information in the records, and searches for the historical finger state data group related to the user. If a historical finger state data set matching the current user is found, the model will enter step S220; if not found, it will enter the subsequent part of step S210, that is, output a rehabilitation training plan based on the current finger state data set.

[0031] Step S220, if the historical finger state data group is included, the rehabilitation training program is output in combination with the finger state data group and the historical finger state data group. Specifically, if the historical finger state data group is included, the model will integrate the current finger state data group with the historical finger state data group after each training to form a more comprehensive data set. This data set contains the user's finger state information at different training end time points and before the current training, providing richer data support for the formulation of personalized rehabilitation training programs. By performing trend analysis on the integrated data set, the model can understand the changing trend of the user's finger state, including the improvement or degradation of the finger flexion and extension ability. Based on the results of the trend analysis, the model will formulate a more personalized rehabilitation training program. This program not only takes into account the current finger state, but also takes into account the user's historical data, so it is more in line with the user's actual needs. Finally, the model will output the formulated rehabilitation training program to the motion control module for subsequent gas-electric-heat joint control training. In addition, after generating the rehabilitation training program, the user can directly train according to the program, or ask the therapist for advice, appropriately adjust the training parameters, and then train. By combining historical data, the model can more accurately understand the changing trend of the user's finger status, thereby developing a rehabilitation training program that better meets the user's actual needs. Personalized rehabilitation training programs can better adapt to the user's physical condition and recovery needs, thereby improving training effects and promoting the recovery of finger function.

[0032] In a possible implementation, a rehabilitation training program is output according to the finger state data group, and step S210 further includes step S211, configuring the constraint values ​​corresponding to the pneumatic system, the electrical stimulation system, and the thermal therapy system, respectively. Specifically, according to the physiological structure of the finger and the safe training range, the pressure upper limit, the pressure change rate and other parameters of the pneumatic system are set. For example, the maximum inflation pressure is set not to exceed a certain safety threshold to avoid excessive compression of the finger joints. According to the safety standards of nerve stimulation and the response characteristics of the finger muscles, the pulse width, frequency, intensity and other parameters of the electrical stimulation are set. These parameters need to ensure that while stimulating muscle contraction, no pain or discomfort is caused. According to the temperature effect and safety of thermal therapy, the heating temperature range (such as 26°C-42°C), heating rate and duration of the thermal therapy system are set to provide a comfortable temperature environment and promote blood circulation and muscle relaxation of the fingers. Among them, the pneumatic system refers to a system that uses gas pressure to passively train the fingers, and realizes the flexion and extension of the fingers by controlling the filling and discharge of gas, and is composed of air bags, air pressure pumps and other components. The electrical stimulation system is a system that applies electrical signals to the finger muscles through electrodes to stimulate muscle contraction and achieve active or auxiliary training. It is composed of electrodes, power supplies and other components. The thermal therapy system is a system that applies heat to the fingers through a heating device to promote local blood circulation and relieve pain and muscle tension. It is composed of heating elements, temperature controllers and other components. The configuration constraints are to ensure that each system can function effectively while ensuring the safety and comfort of the user when performing rehabilitation training. These constraints are set based on physiological and medical knowledge to avoid injuries that may result from overtraining or improper stimulation.

[0033] Step S212, construct a rehabilitation joint training function, and use the rehabilitation joint training function to calculate the data of the finger state data group under the condition of the constraint value to obtain a rehabilitation training plan. Specifically, the rehabilitation joint training function integrates the parameters of the three training methods of pneumatic, electrical stimulation and thermal therapy, and finds the training plan that best suits the current finger state through calculation. The function input includes a finger state data group (such as flexion angle, extension speed, etc.). Under the limitation of the constraint value, the rehabilitation joint training function is used to calculate the input finger state data group and output a rehabilitation training plan. The plan includes specific parameters of pneumatic training (such as inflation pressure, time, etc.), parameters of electrical stimulation training (such as pulse intensity, frequency, etc.) and parameters of thermal therapy (such as heating temperature, time, etc.). This implementation method not only ensures the safety and effectiveness of training, but also improves the user's rehabilitation experience and effect through personalized training plans.

[0034] A possible example is as follows: The rehabilitation joint training function is as follows: ; in, Indicates the maximum position of aerodynamic training, Indicates the maximum position that the user can move in the finger state data group. represents the intensity of electrical stimulation, Indicates the grip-extension difference in the finger state data set, Indicates the temperature of the hot compress. The intensity of electrical stimulation is stronger when the user's voluntary muscle strength is low, and the intensity of electrical stimulation will decrease as the user's muscle strength gradually recovers. The thermal therapy system relaxes muscles by heating, and its heating temperature is inversely proportional to the user's muscle strength.

[0035] In a possible implementation, the rehabilitation training program is output in combination with the finger state data group and the historical finger state data group, and step S220 further includes step S221, identifying the number of days of historical records of the historical finger state data group. Specifically, extract the timestamp information of each record from the historical finger state data group. The timestamp is a specific time mark when the data is recorded, including detailed time information such as year, month, day, hour, minute, and second. Taking the current date (the date when the data is analyzed or the training program is formulated) as the base date, for each record in the historical data set, compare the date part of its timestamp with the base date. For each historical record, calculate the difference in days between it and the base date through a date operation function, which can directly calculate the difference in days between two dates. Collect the day differences of all historical records to form a set or array, which represents the number of days of historical records of the historical finger state data group.

[0036] Step S222, assigning weight coefficients to the historical finger state data group according to the number of days of historical records to obtain a weight coefficient group. Specifically, a weight function is designed, which outputs a weight coefficient according to the number of days of historical records. The weight function can be a linear function, an exponential function, or a function in other forms, depending on the importance attached to the historical data. For example, an exponential decay function can be used so that the more recent data has a greater weight, and the more distant data has a smaller weight. For each record in the historical finger state data group, the corresponding weight coefficient is calculated using the weight function according to the number of days of historical records. All the calculated weight coefficients are combined into a weight coefficient group for data calculation.

[0037] Step S223, under the condition of the constraint value, the rehabilitation joint training function calculates the data of the finger state data group and the historical finger state data group according to the weight coefficient group to obtain a rehabilitation training plan. Specifically, the current finger state data group and the historical finger state data group are fused according to the weight coefficient, which can be achieved by weighted summation, that is, multiplying each data point by its corresponding weight coefficient, and then adding the weighted data points. Based on the fused data, the rehabilitation joint training function is used for calculation, and a rehabilitation training plan that meets the constraint conditions is output, including pneumatic training activity range values, electrical stimulation training stimulation intensity values, and thermal therapy temperature parameter values. Historical data often contain rich information. This implementation method can make more reasonable use of these data through weight coefficient allocation, making the training plan more accurate and effective.

[0038] A possible example is as follows: Taking the maximum position of pneumatic training as an example, the electrical stimulation intensity and heat compress temperature are substituted into the hand grip and extension difference after combining the historical training data, and the calculation method is the same as that of pneumatic training. When there is a historical training plan, the pneumatic training range threshold calculation will refer to the evaluation data after the end of each day, and the reference coefficient will gradually decrease. Suppose the maximum position of pneumatic training is Y, and there are now n days of data. These n data are , , ,…… , and their reference ratio is in accordance with the ratio p (p= ) decreases, that is: = *p; = *p= *p 2 ;......; = *p= *p n-1 . Y is the sum of these data, that is, Y= + + +…+ = * (1+p+p 2 +…+p n-1 ).

[0039] In one possible implementation, before the finger state data group is input into the finger health status assessment model for analysis, the finger state data group is subjected to error elimination through a limiting filtering algorithm, including: setting a preset difference, and comparing each sampling value in the finger state data group according to the preset difference; if the difference between the current sampling value and the previous valid value is greater than the preset difference, retaining the previous sampling value as the valid value of the current sampling value; if the difference between the current sampling value and the previous valid value is less than or equal to the preset difference, retaining the current sampling value as the valid value, and obtaining the filtered finger state data group.

[0040] Specifically, a reasonable difference range is predefined, and this range is determined based on the comprehensive consideration of the sensor accuracy, data acquisition frequency and finger motion characteristics of the pneumatic rehabilitation gloves. The preset difference is a threshold value used to determine whether the difference between the current sampled value and the previous valid value is within an acceptable range. Each newly collected sampled value is compared with the previous valid value to determine the difference between them. The sampled value is each data point in the finger state data group, representing the state of the finger at a certain moment (such as the degree of flexion or extension). When the difference is greater than the preset difference, the previous sampled value is retained as the current valid value; when the difference is less than or equal to the preset difference, the current sampled value is retained as the valid value. The valid value is a data point that is considered to more truly reflect the finger state after filtering. After the above comparison and retention process, a new data group is obtained, and each data point in this data group is a valid value after processing by the limiting filter algorithm. This implementation method pre-processes the original finger state data group through a limiting filtering algorithm, which can significantly reduce abnormal values ​​caused by factors such as sensor noise and data acquisition errors, thereby improving the accuracy and reliability of the data, and ultimately ensuring the effectiveness of the entire pneumatic rehabilitation glove air-electric-heat combined control method.

[0041] In a possible implementation, the finger state data set is subjected to error elimination by using a limiting filtering algorithm, and the expression is as follows: ; in, is the effective value at the current sampling time point, is the sampling value at the current sampling time point, is the effective value of the previous sampling time point, is the difference between the current sampling value and the previous valid value, and A is the preset difference.

[0042] Step S300, connecting a motion control module, wherein the motion control module performs pneumatic, electrical and thermal joint control training on a pneumatic system, an electrical stimulation system and a thermal therapy system according to the rehabilitation training program.

[0043] Specifically, the pneumatic rehabilitation gloves are equipped with a motion control module inside or outside, which is connected to the pneumatic system, electrical stimulation system and thermal therapy system by wired or wireless means. According to the pneumatic training activity range value, electrical stimulation training stimulation intensity value and thermal therapy temperature parameter value in the rehabilitation training program, the motion control module sets the parameters of the pneumatic system, electrical stimulation system and thermal therapy system. During the training process, the motion control module starts the pneumatic system, electrical stimulation system and thermal therapy system in sequence or simultaneously according to the preset training program, and performs air-electric-thermal combined control training on the fingers. The pneumatic system performs flexion and extension training on the fingers through airbags, the electrical stimulation system stimulates the finger muscles through electrodes to enhance muscle strength, and the thermal therapy system applies hot compresses to the fingers through heating elements to promote blood circulation.

[0044] A possible process of combined air-electric-thermal control training is: first, the pneumatic rehabilitation glove drives the hand to stretch while the electrical stimulation is performed to stimulate the wrist, and then the electrical stimulation stops when the wrist is flexed, and the hot compress continues to heat during the entire training period. The embodiment of the present application uses pneumatic rehabilitation gloves to capture finger status data, analyzes the data through a finger health status assessment model to output a personalized rehabilitation training plan, and the motion control module uses this to perform combined control training on the pneumatic, electrical stimulation and thermal therapy systems, etc., to achieve the technical effect of improving the pertinence and effectiveness, and then improving the accuracy and efficiency of finger rehabilitation training.

[0045] In a possible implementation, after sending the rehabilitation training program to the motion control module for gas-electric-heat joint control analysis, the post-training finger state data group is recorded; the user's finger state data group before training and the finger state data group after training are stored in the data memory.

[0046] Specifically, after the rehabilitation training program is sent to the motion control module for gas-electric-heat joint control analysis, the flexible film sensor in the pneumatic rehabilitation glove is used to capture the state of the user's fingers again, including finger flexion state data and finger extension state data. The captured post-training finger state data group and the previously recorded pre-training finger state data group are stored together in the data memory library to save the user's finger state data at different time points for subsequent analysis and comparison. This implementation method stores the user's historical data (including pre-training and post-training data) to form the user's personal rehabilitation history record. These records can help more accurately evaluate the user's rehabilitation progress and adjust the rehabilitation training program according to actual conditions, thereby achieving personalized rehabilitation treatment.

[0047] In a possible implementation, the motion control module is also connected to a HIM interaction module, and the HIM interaction module includes a display module and a prompt module; wherein the display module is used to display the user's training, and the prompt module is used to provide training guidance to the user according to the stored rehabilitation training plan.

[0048] Specifically, the motion control module is connected to the HIM interaction module through a physical connection (such as a cable) or a wireless connection (such as Bluetooth, Wi-Fi) to ensure that the data between them can be transmitted in real time. The HIM interaction module is a module used to realize the interaction between humans and machines. It can display the status and information of the machine in a human-understandable way and receive human instructions or input. The display module is the part of the HIM interaction module responsible for displaying information. It can convert digital or analog signals into human-readable visual information and display the user's training status in real time through a screen (such as LCD, LED, etc.), including the degree of flexion and extension of the fingers, training progress, remaining time, etc. The prompt module is the part of the HIM interaction module responsible for providing user guidance or feedback. It provides training guidance to the user according to the stored rehabilitation training plan through sound (such as voice prompts), text (such as text prompts on the screen) or vibration. For example, when the user needs to increase the strength of finger flexion, the prompt module will issue a corresponding prompt. The motion control module sends the relevant data of the rehabilitation training program (such as the range of activity of pneumatic training, the intensity of electrical stimulation training, the temperature parameter value of thermal therapy, etc.) to the HIM interaction module, and the HIM interaction module generates corresponding display and prompt information based on these data. This is a two-way data interaction process. The motion control module is responsible for controlling the operation of the pneumatic, electrical stimulation and thermal therapy systems, and sending relevant data to the HIM interaction module in real time; while the HIM interaction module is responsible for displaying these data in a user-understandable way and providing corresponding training guidance. This implementation method realizes real-time display of the user's training status and training guidance by introducing the HIM interaction module, thereby improving the user experience, enhancing the training effect and promoting human-computer interaction.

[0049] A specific example is as follows. Taking user Zhang San as an example, it is assumed that the hand evaluation data of user Zhang San when using the device for the first time is shown in Table 1: Table 1: Parameters for the initial hand assessment The equipment gives the recommended training parameters for the day based on the data in Table 1 as shown in Table 2: Table 2: Recommended training parameters for the first day After the user's training on the day is over, the hand status is measured again to obtain the data shown in Table 3: Table 3: Hand evaluation parameters at the end of the first day of training The next day, the user's hand parameters were evaluated again before training to obtain the data shown in Table 4: Table 4: Hand assessment parameters before training the next day After the evaluation is completed, the background data has two sets of data from the first day and the next day. The gas, electricity and heat combined training plan output on the next day will refer to the data from the first day and the next day, as shown in Table 5: Table 5: Recommended training parameters for the next day In the above, refer to Figure 1 and Figure 2 The gas-electric-heat combined control method for pneumatic rehabilitation gloves according to an embodiment of the present invention is described in detail. Figure 3 and Figure 4 The invention describes an air-electric-thermal joint control platform for pneumatic rehabilitation gloves according to an embodiment of the invention.

[0050] The gas-electric-heat joint control platform for pneumatic rehabilitation gloves according to the embodiment of the present invention is used to solve the technical problems of insufficient pertinence and effectiveness of existing finger rehabilitation training, resulting in low training accuracy and efficiency, so as to achieve the technical effect of improving pertinence and effectiveness, and then improving the accuracy and efficiency of finger rehabilitation training. The gas-electric-heat joint control platform for pneumatic rehabilitation gloves includes: a finger state capture module 10, a finger health state assessment module 20, and a gas-electric-heat joint control training module 30.

[0051] The finger state capture module 10 is used to capture the state of the user's fingers through pneumatic rehabilitation gloves to obtain a finger state data group before training, wherein the pneumatic rehabilitation gloves are provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data; the finger health state evaluation module 20 is used to construct a finger health state evaluation model to analyze the finger state data group and output a rehabilitation training plan, wherein the rehabilitation training plan includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value and a thermal therapy temperature parameter value; the gas-electric-thermal joint control training module 30 is used to connect the motion control module, and the motion control module performs gas-electric-thermal joint control training on the pneumatic system, the electrical stimulation system and the thermal therapy system according to the rehabilitation training plan.

[0052] The specific configuration of the finger health status assessment module 20 will be described in detail below. As described above, a finger health status assessment model is constructed to analyze the finger status data group, and the finger health status assessment module 20 may further include: a rehabilitation training program judgment output unit is used for the finger health status assessment model to determine whether the user's historical finger status data group is included by querying the data memory library, if the historical finger status data group is not included, the rehabilitation training program is output according to the finger status data group, if the historical finger status data group is included, the rehabilitation training program is output in combination with the finger status data group and the historical finger status data group.

[0053] Among them, a rehabilitation training plan is output according to the finger state data group, and the rehabilitation training plan judgment output unit may further include: a constraint value configuration subunit is used to configure the constraint values ​​corresponding to the pneumatic system, the electrical stimulation system and the thermal therapy system respectively; a data calculation subunit is used to construct a rehabilitation joint training function, and the rehabilitation joint training function is used to calculate the data of the finger state data group under the condition of the constraint value to obtain a rehabilitation training plan.

[0054] Among them, a rehabilitation training plan is output in combination with the finger state data group and the historical finger state data group, and the rehabilitation training plan judgment output unit may further include: a historical record days identification subunit is used to identify the historical record days of the historical finger state data group; a weight coefficient allocation subunit is used to allocate weight coefficients to the historical finger state data group according to the historical record days to obtain a weight coefficient group; a data calculation subunit is used to calculate the data of the finger state data group and the historical finger state data group according to the weight coefficient group under the condition of the constraint value, and obtain a rehabilitation training plan.

[0055] Among them, before the finger state data group is input into the finger health status assessment model for analysis, the error of the finger state data group is eliminated by a limiting filtering algorithm, and the platform may further include: a data comparison module is used to set a preset difference, and compare each sampling value in the finger state data group according to the preset difference; a filtering module is used to retain the previous sampling value as the valid value of the current sampling value if the difference between the current sampling value and the previous valid value is greater than the preset difference, and retain the current sampling value as the valid value if the difference between the current sampling value and the previous valid value is less than or equal to the preset difference, so as to obtain the filtered finger state data group.

[0056] The error elimination of the finger state data group is performed by a limiting filtering algorithm, and the filtering module may further include: an expression building unit for building an expression, and the expression is as follows: ; in, is the effective value at the current sampling time point, is the sampling value at the current sampling time point, is the effective value of the previous sampling time point, is the difference between the current sampling value and the previous valid value, and A is the preset difference.

[0057] Among them, after sending the rehabilitation training plan to the motion control module for gas-electric-heat joint control analysis, the platform may further include: a finger state data group recording module for recording the finger state data group after training; a data storage module for storing the user's finger state data group before training and the finger state data group after training in the data memory.

[0058] The specific configuration of the gas-electric-heat combined control training module 30 will be described in detail below. As described above, the gas-electric-heat combined control training module 30 may further include: an interactive unit for connecting the motion control module to a HIM interactive module, the HIM interactive module including a display module and a prompt module, wherein the display module is used to display the training of the user, and the prompt module is used to provide training guidance to the user according to the stored rehabilitation training program.

[0059] The gas-electric-heat combined control platform for pneumatic rehabilitation gloves provided in the embodiments of the present invention can execute the gas-electric-heat combined control method for pneumatic rehabilitation gloves provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0060] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0061] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A combined air-electric-heat control method for pneumatic rehabilitation gloves, characterized in that: The method comprises: The state of the user's fingers is captured by a pneumatic rehabilitation glove to obtain a finger state data group before training, wherein the pneumatic rehabilitation glove is provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data; Constructing a finger health status assessment model to analyze the finger status data group and output a rehabilitation training program, wherein the rehabilitation training program includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value and a thermal therapy temperature parameter value; A motion control module is connected, and the motion control module performs gas-electric-thermal joint control training on the pneumatic system, the electrical stimulation system and the thermal therapy system according to the rehabilitation training program.

2. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 1, characterized in that: Constructing a finger health status assessment model to analyze the finger status data set, the method further includes: The finger health status assessment model determines whether the user's historical finger status data group is included by querying the data memory library, and if the historical finger status data group is not included, outputs a rehabilitation training program according to the finger status data group; If the historical finger state data group is included, a rehabilitation training program is output by combining the finger state data group and the historical finger state data group.

3. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 2, characterized in that: Outputting a rehabilitation training program according to the finger state data group, the method comprises: configuring constraint values ​​corresponding to the pneumatic system, the electrical stimulation system, and the thermal therapy system respectively; A rehabilitation joint training function is constructed, and the data of the finger state data group is calculated using the rehabilitation joint training function under the condition of the constraint value to obtain a rehabilitation training program.

4. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 3, characterized in that: Outputting a rehabilitation training program in combination with the finger state data group and the historical finger state data group, the method comprising: Identify the historical record days of the historical finger state data group; Allocating weight coefficients to the historical finger state data group according to the number of days of the historical records to obtain a weight coefficient group; Under the condition of the constraint value, the rehabilitation joint training function calculates the data of the finger state data group and the historical finger state data group according to the weight coefficient group to obtain a rehabilitation training program.

5. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 1, characterized in that: Before inputting the finger state data group into the finger health state assessment model for analysis, error elimination is performed on the finger state data group by using a limiting filtering algorithm, the method comprising: Setting a preset difference, and comparing each sample value in the finger state data group according to the preset difference; If the difference between the current sampling value and the previous valid value is greater than the preset difference, the previous sampling value is retained as the valid value of the current sampling value; if the difference between the current sampling value and the previous valid value is less than or equal to the preset difference, the current sampling value is retained as the valid value, and the filtered finger state data group is obtained.

6. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 5, characterized in that: The error of the finger state data group is eliminated by the limiting filtering algorithm, and the expression is as follows: ； in, is the effective value at the current sampling time point, is the sampling value at the current sampling time point, is the effective value of the previous sampling time point, is the difference between the current sampling value and the previous valid value, and A is the preset difference.

7. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 2, characterized in that: After sending the rehabilitation training program to the motion control module for gas-electric-heat joint control analysis, a finger state data group after training is recorded; The finger state data set before the user training and the finger state data set after the training are stored in the data memory.

8. The air-electric-heat combined control method for pneumatic rehabilitation gloves according to claim 1, characterized in that: The motion control module is also connected to the HIM interaction module, and the HIM interaction module includes a display module and a prompt module; The display module is used to display the training of the user, and the prompt module is used to provide training guidance to the user according to the stored rehabilitation training program.

9. The gas-electric-heat combined control platform for pneumatic rehabilitation gloves is characterized by: The platform is used to implement the gas-electric-heat combined control method for pneumatic rehabilitation gloves according to any one of claims 1 to 8, and the platform comprises: A finger state capturing module, used to capture the state of the user's fingers through a pneumatic rehabilitation glove to obtain a finger state data group before training, wherein the pneumatic rehabilitation glove is provided with a flexible film sensor, and the finger state data group includes finger flexion state data and finger extension state data; A finger health status assessment module is used to construct a finger health status assessment model to analyze the finger status data group and output a rehabilitation training program, wherein the rehabilitation training program includes a pneumatic training activity range value, an electrical stimulation training stimulation intensity value and a thermal therapy temperature parameter value; The gas-electric-thermal combined control training module is used to connect to the motion control module, and the motion control module performs gas-electric-thermal combined control training on the pneumatic system, the electric stimulation system and the thermal therapy system according to the rehabilitation training program.

Images