Intelligent walking aid method, device and equipment for sarcopenia rehabilitation and readable storage medium

Abstract

The invention discloses an intelligent walking aid method, device and equipment for sarcopenia rehabilitation and a readable storage medium, and relates to the technical field of medical rehabilitation. Comprising the steps of firstly obtaining body data of a rehabilitation person; the body data comprises grip data, pressure data, exercise duration data and image data; adjusting the wheel resistance of the sarcopenia rehabilitation intelligent walking aid on the basis of the grip strength data, the pressure data and the movement duration data; and finally, based on the image data, identifying a human body posture and a falling risk of the rehabilitation person, and based on the human body posture and the falling risk, outputting an adjustment suggestion for the rehabilitation person. According to the method, rehabilitation personnel can be helped to recover more timely and effectively.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical rehabilitation, in particular to a sarcopenia rehabilitation intelligent walking aid method, device, equipment and readable storage medium. BACKGROUND

[0002] With the intensification of social aging, it is estimated that the proportion of the elderly population will exceed 20% in 2035, and the elderly are prone to sarcopenia, which will seriously affect the quality of life of the elderly. Sarcopenia patients usually show insufficient muscle strength, difficulty walking, and decreased balance ability, increasing the risk of falling.

[0003] And studies have shown that long-term regular rehabilitation training can effectively improve the muscle strength and walking balance ability of elderly sarcopenia patients. In view of this demand, it is necessary to develop an intelligent walking aid system suitable for sarcopenia rehabilitation. However, the general rehabilitation walking aid frame solution has the problems of complex structure and inconvenient operation for elderly sarcopenia patients, therefore, it is urgent to reduce the impact of sarcopenia on the quality of life of the elderly, and an intelligent walking aid method for sarcopenia rehabilitation is needed to overcome the above defects. SUMMARY

[0004] The purpose of the present application is to provide a sarcopenia rehabilitation intelligent walking aid method, device, equipment and readable storage medium, by collecting the body data of the rehabilitation personnel, and then being able to grasp the real-time recovery situation of the rehabilitation personnel, adjusting the sarcopenia rehabilitation intelligent walking aid and outputting adjustment suggestions according to the recovery situation of the rehabilitation personnel, and realizing more timely and effective help for the rehabilitation of the rehabilitation personnel.

[0005] To achieve the above purpose, the present application provides the following technical scheme: In a first aspect, the present application provides a sarcopenia rehabilitation intelligent walking aid method, which comprises: obtaining body data of a rehabilitation personnel; the body data includes grip strength data, pressure data, exercise duration data and image data; adjusting the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the grip strength data, pressure data and exercise duration data; identifying the body posture and fall risk of the rehabilitation personnel based on the image data, and outputting adjustment suggestions for the rehabilitation personnel based on the body posture and fall risk.

[0006] In some embodiments, adjusting the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the grip strength data, pressure data and exercise duration data comprises: calculating the exercise ability value of the rehabilitation personnel based on the grip strength data, pressure data and exercise duration data; Adjust wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on a difference between the motor ability value and a target value.

[0007] In some embodiments, the human posture and the fall risk of the rehabilitation personnel are identified based on the image data, including: The image data is input into a pre-trained human posture recognition model to obtain the human posture of the rehabilitation personnel. The fall risk of the rehabilitation personnel is determined based on the human posture of the rehabilitation personnel, the grip data and the pressure data.

[0008] In some embodiments, the image data is input into a pre-trained human posture recognition model to obtain the human posture of the rehabilitation personnel, including: The image data is input into an SFB module of the pre-trained human posture recognition model to obtain first features. The first features are input into a TAU module of the pre-trained human posture recognition model to enhance the first features and output the human posture of the rehabilitation personnel.

[0009] In some embodiments, the fall risk of the rehabilitation personnel is determined based on the human posture of the rehabilitation personnel, the grip data and the pressure data, including: The human posture of the rehabilitation personnel, the grip data and the pressure data are multi-modal fused to obtain fused data. The fused data is input into a Transformer architecture to output the fall risk of the rehabilitation personnel through an encoder-decoder structure.

[0010] In some embodiments, the method further includes: It is judged whether the rehabilitation personnel is in an abnormal state based on the grip data, the pressure data and the human posture. If the rehabilitation personnel is in an abnormal state, surface electromyography signals of a lower leg part of the rehabilitation personnel are collected. Training suggestions are generated based on the surface electromyography signals.

[0011] In a second aspect, the present application further provides a sarcopenia rehabilitation intelligent walking device, which includes: A data acquisition module is configured to acquire body data of rehabilitation personnel; the body data includes grip data, pressure data, motion duration data and image data. A wheel adjustment module is configured to adjust wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the grip data, the pressure data and the motion duration data. The suggestion output module is configured to identify a body posture and a falling risk of the rehabilitation person based on the image data, and output an adjustment suggestion for the rehabilitation person based on the body posture and the falling risk.

[0012] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the muscle atrophy rehabilitation intelligent walking aid method in the first aspect.

[0013] In a fourth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the muscle atrophy rehabilitation intelligent walking aid method in the first aspect.

[0014] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the muscle atrophy rehabilitation intelligent walking aid method in the first aspect.

[0015] The muscle atrophy rehabilitation intelligent walking aid method provided by the present application comprises the following steps: acquiring body data of a rehabilitation person; the body data comprises grip strength data, pressure data, exercise duration data, and image data; adjusting wheel resistance of the muscle atrophy rehabilitation intelligent walking aid based on the grip strength data, the pressure data, and the exercise duration data; and identifying a body posture and a falling risk of the rehabilitation person based on the image data, and outputting an adjustment suggestion for the rehabilitation person based on the body posture and the falling risk. By collecting the body data of the rehabilitation person, the real-time recovery condition of the rehabilitation person can be grasped, the muscle atrophy rehabilitation intelligent walking aid can be adjusted in real time according to the recovery condition of the rehabilitation person, and an adjustment suggestion can be output, so that the rehabilitation of the rehabilitation person is more timely and effective.

[0016] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, and to implement the content of the description, the following will be described in detail with reference to the preferred embodiments of the present application and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 FIG. 1 is a flowchart of a muscle atrophy rehabilitation intelligent walking aid method according to an embodiment of the present application; Figure 2 FIG. 2 is a structural schematic diagram of a muscle atrophy rehabilitation intelligent walking aid according to an embodiment of the present application; Figure 3 FIG. 3 is a partial structural schematic diagram of a muscle atrophy rehabilitation intelligent walking aid according to an embodiment of the present application; Figure 4Another partial structure schematic view of a sarcopenia rehabilitation intelligent walking aid device according to an embodiment of the present application is shown in the figure. Figure 5 Another partial structure schematic view of a sarcopenia rehabilitation intelligent walking aid device according to an embodiment of the present application is shown in the figure. Figure 6 A flowchart of a sarcopenia rehabilitation intelligent walking method according to an embodiment of the present application is shown in the figure. Figure 7 A structure schematic view of a sarcopenia rehabilitation intelligent walking device according to an embodiment of the present application is shown in the figure. Figure 8 An electronic device structure schematic view according to an embodiment of the present application is shown in the figure. The figure shows the following reference signs: support frame body 1, grip sensor 2, detachable display screen 3, height adjustment hole 4, wheel 5, connecting rod 6, pressure sensing assembly 7, SOS emergency button 8, LED three-color indicator light 9, buzzer 10, detachable weight-bearing frame 11, main control unit 12, camera module 13, impact ball 14, spring 15, pressure sensing block 16, lower half pipe body 17, pressure sensing block 18, button 19, upper surface 20, lower surface 21, knob 22, damping adjuster 23. DETAILED DESCRIPTION

[0018] The technical solutions of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application. It should be noted that the description of "one embodiment", "embodiment", "example embodiment" and the like in the specification means that the described embodiment can include specific features, structures or characteristics, but not every embodiment must include these specific features, structures or characteristics. In addition, such expressions do not mean the same embodiment. Furthermore, when a specific feature, structure or characteristic is described in connection with an embodiment, it is shown that such a feature, structure or characteristic is combined with other embodiments within the knowledge of those skilled in the art, whether or not it is explicitly described.

[0019] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as there is no conflict.

[0020] In some embodiments, as shown in Figure 1 A flowchart of a sarcopenia rehabilitation intelligent walking method according to an embodiment of the present application is shown in the figure. The method is applied to a sarcopenia rehabilitation intelligent walking aid device, and the specific method includes the following steps. S101, obtaining body data of a rehabilitation person.

[0021] The body data includes grip data, pressure data, exercise duration data and image data.

[0022] Specifically, the sarcopenia rehabilitation intelligent walking aid is provided with a grip sensor, grip data of the rehabilitation personnel can be acquired through the grip sensor, the handle of the sarcopenia rehabilitation intelligent walking aid is provided with a pressure sensor, pressure data of the rehabilitation personnel can be acquired through the pressure sensor, exercise duration data of the rehabilitation personnel is acquired by using a timer after the sarcopenia rehabilitation intelligent walking aid is started, and image data of the rehabilitation personnel is acquired by using a camera.

[0023] It should be noted that, as shown in Figure 2 , Figure 2 is a structural schematic diagram of the sarcopenia rehabilitation intelligent walking aid, the sarcopenia rehabilitation intelligent walking aid comprises a support frame body 1, which is made of light-weight aluminum alloy material and has a foldable structure; the support frame body 1 is provided with a grip sensor 2 at a handle for reflecting hand strength change of the rehabilitation personnel, and is also provided with an SOS button 8 for emergency call; a main control unit 12 is arranged at a left handle for receiving data transmitted by a Bluetooth module; the support frame body 1 is provided with an LED three-color indicator lamp 9, a buzzer 10 and a detachable display screen 3 on a cross beam, a camera module 13 is embedded beside the screen for shooting road conditions in front; a connecting rod 6 is used to connect structures at a lower part of the walking frame, a detachable weight-bearing frame 11 is arranged in a middle part of the connecting rod, and weights can be appropriately added when weight training is needed; a pressure sensing assembly 7 is arranged at an upper and lower joint of the support frame body 1 for posture and gravity center detection; a damping adjuster 23 is arranged at a bottom of the support frame body 1 to control resistance of a lower wheel 5.

[0024] Referring to Figure 3 , Figure 3 is a partial structural schematic diagram of the sarcopenia rehabilitation intelligent walking aid, in order to reduce interference on the rehabilitation personnel caused by surface-mounted sensors, the invention is provided with an impact ball 14 arranged in an upper half pipe body 16 of the support frame body 1, when the rehabilitation personnel exerts force downward, a pressure sensor 18 button 19 in a lower half pipe body 17 will be triggered, when the downward pressure disappears, a spring 15 will be bounced up and restored to an initial state.

[0025] Referring to Figure 4 , Figure 4 is a partial structural schematic diagram of the sarcopenia rehabilitation intelligent walking aid, the grip sensor is embedded in a handle, when the rehabilitation personnel holds a handle upper surface 20 and a handle lower surface 21 at positions where the grip sensor 2 is arranged and simultaneously exerts pressure, the grip sensor 2 will record detailed data of the grip.

[0026] Referring to Figure 5 , Figure 5The schematic view of part structure of the sarcopenia rehabilitation intelligent walking aid, the damping adjuster 23 is connected with the wheel 5 and the support frame body, the resistance is generated by adjusting the knob 22 of the damping adjuster clockwise to meet the training needs of the rehabilitation personnel at different stages.

[0027] The master control unit has user data receiving and storage functions, can display the data obtained from the sensor on the display screen, and can continuously track the training effect of the patient and generate a rehabilitation report.

[0028] S102, based on the grip data, pressure data and exercise duration data, adjusting the wheel resistance of the sarcopenia rehabilitation intelligent walking aid.

[0029] Optionally, the exercise capacity value of the rehabilitation personnel can be calculated based on the grip data, pressure data and exercise duration data first; and then the wheel resistance of the sarcopenia rehabilitation intelligent walking aid is adjusted based on the difference between the exercise capacity value and the target value.

[0030] Specifically, the grip data, pressure data and exercise duration data are normalized first, and then the normalized grip data, pressure data and exercise duration data are weighted and summed to obtain the exercise capacity value of the rehabilitation personnel. For example, the weight of the grip data can be set to 0.3, the weight of the pressure data can be set to 0.4, and the weight of the exercise duration data can be set to 0.3. When the exercise capacity value is lower than the target value, the wheel resistance can be increased, and vice versa.

[0031] Exemplarily, the wheel resistance can also be adjusted according to the current wheel resistance, the resistance of the wheel at this time is obtained , and , the exercise capacity value of the rehabilitation personnel is calculated every five seconds, the difference between the target capacity value and the exercise capacity value is obtained, and the difference between the last exercise capacity value and the exercise capacity value is obtained, a reward coefficient is set, the difference obtained in the last step and the number of wheel resistance sizes are combined to obtain a new resistance size, and the resistance is adjusted according to the result.

[0032] The calculation formula of the exercise capacity value of the rehabilitation personnel in the process is shown in formula (1): (1) and the resistance size that needs to be updated is obtained as shown in formula (2): (2) S103, identifying the human posture and the fall risk of the rehabilitation personnel based on the image data, and outputting the adjustment suggestion for the rehabilitation personnel based on the human posture and the fall risk.

[0033] Optionally, the image data can be input into a pre-trained human posture recognition model to obtain the human posture of the rehabilitation personnel; and the fall risk of the rehabilitation personnel is determined based on the human posture of the rehabilitation personnel, the grip strength data and the pressure data.

[0034] Specifically, the image data is input into an SFB module of the pre-trained human posture recognition model to obtain first features; the first features are input into a TAU module of the pre-trained human posture recognition model to enhance the first features and output the human posture of the rehabilitation personnel. The human posture of the rehabilitation personnel, the grip strength data and the pressure data are fused in a multi-modal manner to obtain fusion data; and the fusion data is input into a Transformer architecture to output the fall risk of the rehabilitation personnel through an encoder-decoder structure.

[0035] The human posture includes positions of a left shoulder, a right shoulder, a shoulder midpoint, a left hip, a right hip, a hip midpoint, a left elbow, a right elbow and a spine midpoint.

[0036] For example, the SFB module first performs a Conv operation with a kernel size of 3 and a step size of 1, and then obtains features input into a depth separable convolution (DW Conv) including a depth convolution operation with a kernel size of 3 and a step size of 1 and a point convolution operation with a kernel size of 1 and a step size of 1, and again performs a Conv operation with a kernel size of 3 and a step size of 1 to obtain the final output, while introducing a residual structure to reduce the probability of learning errors by the model. Compared with a traditional scheme, the SFB module can reduce the parameters and the calculation amount of the model and improve the frame rate of real-time inference.

[0037] Before the model outputs, a TAU module is added. The module first reduces the feature map information (dimension size of 64*64*64) to a lower dimension, and the vector dimension becomes 64 after the dimension reduction, and then performs a layer normalization operation (LayerNorm) on the group of vectors. The normalized information enters two branches for feature enhancement, and the two branches perform a full connection operation (Linear) respectively. The output of the first branch is nonlinearized by using a ReLU function, and the output of the second branch is nonlinearized by using a Sigmoid function. ​​​​​​The function operation obtains the importance degree of each channel. The output results of the two paths are multiplied, and finally the module output is obtained through the full connection layer. Compared with the traditional visual Transformer module, the TAU module can avoid introducing a large number of parameters, and can also analyze the importance degree of different channels of the features through the multi-branch structure.

[0038] The output layer of the final pre-trained human posture recognition model outputs the human posture of the rehabilitation personnel.

[0039] The sarcopenia rehabilitation intelligent walking aid method in the above embodiment first acquires the body data of the rehabilitation personnel; the body data includes grip data, pressure data, exercise duration data and image data; then adjusts the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the grip data, the pressure data and the exercise duration data; finally, the image data is used to identify the human posture and the falling risk of the rehabilitation personnel, and the adjustment suggestion for the rehabilitation personnel is output based on the human posture and the falling risk. By collecting the body data of the rehabilitation personnel, the real-time recovery situation of the rehabilitation personnel can be grasped, and the sarcopenia rehabilitation intelligent walking aid and the adjustment suggestion are adjusted in real time according to the recovery situation of the rehabilitation personnel, so that the rehabilitation of the rehabilitation personnel is more timely and effective.

[0040] In another embodiment, after acquiring the human posture of the rehabilitation personnel, it can also be judged whether the rehabilitation personnel is in an abnormal state based on the grip data, the pressure data and the human posture; if the rehabilitation personnel is in an abnormal state, the surface electromyogram signal of the lower leg part of the rehabilitation personnel is collected; and a training suggestion is generated based on the surface electromyogram signal.

[0041] Specifically, a multi-modal input data can be constructed based on the human posture, the grip data and the pressure data, and a fall probability prediction can be realized through an improved Transformer. For the two-dimensional human posture information obtained by the algorithm, the information matrix size is , which is first reduced to one-dimensional data with a size of , and then the one-dimensional data is spliced with the grip sensor data (data dimension ) and the pressure sensor data (data dimension ) as the input of the model (data dimension ). The input information is first encoded for position information, and then passes through the encoder and decoder modules. The encoder and decoder have the same structure, and both include a multi-head attention mechanism (five heads), a normalization operation and a feedforward network. The formula of the multi-head attention mechanism of is as shown in formula (3): (3) Wherein, is the output of the th head, is the input vector, is a single-head attention operation, is an activation operation, , , is a parameter matrix of query, key, value vectors respectively, is a dimension, is a coefficient matrix, is a concatenation operation, is a total output. Then, a layer normalization and a superposition operation are performed to obtain an output , and the specific steps are shown in equation (4): (4) In the formula, represents a layer normalization operation. The result will enter the feedforward network, which is implemented using a multi-layer perceptron, and the formula is shown in equation (5): (5) In the formula, z is the output of the feedforward network, ReLu is an activation operation to realize nonlinearity, is the weight matrix, is the bias parameter matrix. Then, a superposition and layer normalization operation are performed again to obtain the comprehensive output of the encoder, and the formula is shown in equation (6): (6) The structure of the decoder is consistent with that of the encoder. The obtained encoder output will also be subjected to similar operations as shown in equations (3)-(6), and the output feature dimension after the decoder is . The last two dimensions are combined, and a fully connected operation is performed to reduce the dimension to 2. Then, the classification probability is obtained through the Softmax function. After passing through the network, the probability value of the rehabilitation personnel falling is obtained. If the value is greater than the threshold value of 65%, it is determined that the rehabilitation personnel is in an abnormal state, and an alarm information is given through the buzzer, so as to facilitate the intervention of doctors and family members. At this time, the surface electromyographic signal of the lower leg part of the rehabilitation personnel can also be collected by using the electromyographic signal detection module. The electromyographic signal detection module is installed on the lower leg part of the rehabilitation personnel, and is used to collect the surface electromyographic signal and transmit it to the main control unit. The main control unit is used to evaluate whether the lower limb muscle force is in place according to the electromyographic signal, and stores data information, which provides a reference for subsequent evaluation of doctors.

[0042] Exemplary, in the use of the sarcopenia rehabilitation intelligent walking aid by the rehabilitation personnel, the rehabilitation personnel first needs to fully unfold the folded lightweight aluminum alloy support frame body 1, and ensure the stability of the structure. Then according to the rehabilitation stage and physical condition of oneself, first adjust the height through the height adjusting hole 4, and then adjust the rolling resistance of the wheel 5 through the rotating knob 22 of the bottom damping adjuster 23, clockwise rotation increases the resistance, counterclockwise reduces the resistance. If weight training is needed, appropriate weight can be placed on the detachable weight frame 11 in the middle position of the connecting rod 6.

[0043] After preparation, the main control unit 12 at the left handle is turned on, and the detachable display screen 3 on the cross beam will light up, showing the initial parameters. The rehabilitation personnel holds the handles on both sides of the walking aid with both hands, and the fingers and palms will contact the upper surface 20 and the lower surface 21 of the grip force sensor 2 at the same time, and the system starts to record the grip force data.

[0044] When the rehabilitation personnel starts to push the walking aid to walk, the weight of the body will be transmitted downward through the support frame body 1. At this time, the pressure sensing assembly 7 at the upper and lower junctions starts to work, and the impact ball 14 in the upper half of the pipe body 16 is compressed by the downward pressure, and the springs 15 at both ends are compressed, thereby triggering the buttons 19 on the pressure sensing block 18 in the lower half of the pipe body 17, and the system monitors the posture and center of gravity changes of the user in real time through this way. When the pressure disappears, the spring 15 will pop the impact ball 14 back to the original position.

[0045] During walking, the grip force sensor 2 continuously collects the grip force data of both hands, which is transmitted to the main control unit 12 in real time through the Bluetooth module for analysis and processing. At the same time, the camera module 13 embedded beside the detachable display screen 3 continuously shoots the road conditions in front, helping the rehabilitation personnel to discover and avoid obstacles in time, and in case of emergency, the SOS emergency button 8 can be pressed to trigger the buzzer 10 to seek help.

[0046] The system will provide real-time feedback to the rehabilitation personnel in various ways: the LED three-color indicator light 9 uses different colors to represent the current training state and physical condition, the buzzer 10 will issue a warning sound when an abnormal situation is detected, and the detachable display screen 3 displays detailed rehabilitation data such as walking speed, grip size, center of gravity deviation degree, walking distance, etc. in real time.

[0047] If the rehabilitation personnel feels uncomfortable or encounters an emergency during training, the SOS button 8 at the handle can be pressed immediately, and the system will automatically send a distress signal to inform the medical staff or family members.

[0048] After the training, the main control unit 12 will save all the data of the entire training process for doctors and physiotherapists to analyze the rehabilitation progress. The user needs to remove the weights on the weight frame 11, remove the detachable display screen 3 for charging, and finally fold up the support frame body 1 for storage. The whole system provides scientific, safe and effective rehabilitation training support for sarcopenia patients through intelligent monitoring and feedback.

[0049] In order to more comprehensively show the present scheme, the embodiment gives an optional way of the muscle atrophy rehabilitation intelligent walking aid method, as shown in Figure 6 S201, obtain the body data of the rehabilitation personnel.

[0050] Among them, the body data includes grip data, pressure data, exercise duration data and image data.

[0051] S202, calculate the exercise ability value of the rehabilitation personnel based on the grip data, the pressure data and the exercise duration data.

[0052] S203, adjust the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the difference between the exercise ability value and the target value.

[0053] S204, input the image data into the SFB module of the pre-trained human posture recognition model to obtain the first feature.

[0054] S205, input the first feature into the TAU module of the pre-trained human posture recognition model, enhance the first feature and output the human posture of the rehabilitation personnel.

[0055] S206, multi-modal fusion is performed on the human posture of the rehabilitation personnel, the grip data and the pressure data to obtain fusion data.

[0056] S207, input the fusion data into the Transformer architecture and output the fall risk of the rehabilitation personnel through the encoder-decoder structure.

[0057] S208, output adjustment suggestions for the rehabilitation personnel based on the human posture and the fall risk.

[0058] S209, judge whether the rehabilitation personnel is in an abnormal state based on the grip data, the pressure data and the human posture.

[0059] S210, if the rehabilitation personnel is in an abnormal state, collect the surface electromyogram signal of the lower leg part of the rehabilitation personnel.

[0060] S211, generate training suggestions based on the surface electromyogram signal.

[0061] ​The specific process of S201-S211 can be referred to the description of the method embodiments, and the implementation principle and technical effects are similar, which will not be described here.

[0062] Based on the same inventive concept, the embodiments of the present application also provide a sarcopenia rehabilitation intelligent walking aid device for implementing the above-mentioned method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more sarcopenia rehabilitation intelligent walking aid device embodiments provided below can be referred to the limitations of the sarcopenia rehabilitation intelligent walking aid method described above, which will not be described here.

[0063] In one embodiment, as shown in Figure 7 , a sarcopenia rehabilitation intelligent walking aid device is provided, which comprises: a data acquisition module 30 for acquiring body data of a rehabilitation person; the body data includes grip data, pressure data, exercise duration data and image data; a wheel adjustment module 31 for adjusting the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the grip data, pressure data and exercise duration data; a suggestion output module 32 for identifying the body posture and fall risk of the rehabilitation person based on the image data, and outputting adjustment suggestions for the rehabilitation person based on the body posture and fall risk.

[0064] In another embodiment, the wheel adjustment module 31 in the above Figure 7 is specifically configured to: calculate the exercise ability value of the rehabilitation person based on the grip data, pressure data and exercise duration data; and adjust the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the difference between the exercise ability value and a target value.

[0065] In another embodiment, the suggestion output module 32 in the above Figure 7 comprises: a posture determination unit for inputting the image data into a pre-trained human body posture recognition model to obtain the body posture of the rehabilitation person; a risk prediction unit for determining the fall risk of the rehabilitation person based on the body posture, grip data and pressure data of the rehabilitation person.

[0066] In another embodiment, the posture determination unit in the above embodiment is specifically configured to: input the image data into an SFB module of the pre-trained human body posture recognition model to obtain first features; and input the first features into a TAU module of the pre-trained human body posture recognition model to enhance the first features and output the body posture of the rehabilitation person.

[0067] In another embodiment, the risk prediction unit in the above embodiments is specifically configured to: perform multi-modal fusion on the human posture, grip data and pressure data of the rehabilitation personnel to obtain fusion data; input the fusion data into a Transformer architecture, and output the fall risk of the rehabilitation personnel through an encoder-decoder structure.

[0068] In another embodiment, the muscle atrophy rehabilitation intelligent walking aid device in the above Figure 7 is further configured to: determine whether the rehabilitation personnel is in an abnormal state based on the grip data, pressure data and the human posture; if the rehabilitation personnel is in an abnormal state, collect a surface electromyogram signal of a lower leg part of the rehabilitation personnel; and generate a training suggestion based on the surface electromyogram signal.

[0069] Embodiments of the present application also provide an electronic device. In some embodiments, referring to FIG. 7, the electronic device 700 includes an input unit 710, a memory 720, a processor 730 and an output unit 740. The memory 720 stores program instructions executable on the processor 730, and the processor 730 invokes the program instructions to perform the muscle atrophy rehabilitation intelligent walking aid method and / or technical solutions in the foregoing embodiments. The electronic device 700 can be a mobile terminal device such as a mobile phone or a computer. Figure 8

[0070] In addition, embodiments of the present application also provide a computer-readable storage medium for storing a computer program for executing the muscle atrophy rehabilitation intelligent walking aid method. For example, computer program instructions, when executed by a computer, can invoke or provide the method and / or technical solutions according to the present application through the operation of the computer. The program instructions for invoking the method of the present application can be stored in a fixed or removable storage medium, and / or transmitted and / or stored in a storage medium according to the program instructions for execution.

[0071] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be realized by a general computing device, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Alternatively, they can be realized by program codes executable by a computing device, so that they can be stored in a storage device for execution by a computing device, or they can be respectively manufactured into individual integrated circuit modules, or a plurality of modules or steps among them can be manufactured into a single integrated circuit module to realize. Thus, the present application is not limited to any specific combination of hardware and software.

[0072] ​The technical features of the above embodiments can be integrated in any manner. In order to make the description simple, all possible integrations of the technical features in the above embodiments are not described, however, as long as the integration of the technical features does not exist contradictions, it should be considered that it is within the scope of the description.

[0073] The above embodiments only express several implementation manners of the present application, the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A sarcopenia rehabilitation intelligent walking stick method, characterized in that, The method is applied to a sarcopenia rehabilitation intelligent walking aid, and comprises the following steps: acquiring body data of a rehabilitation person; the body data comprises grip data, pressure data, exercise duration data and image data; adjusting wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on the grip data, the pressure data and the exercise duration data; identifying a body posture and a falling risk of the rehabilitation person based on the image data, and outputting an adjustment suggestion for the rehabilitation person based on the body posture and the falling risk.

2. The sarcopenia rehabilitation intelligent walking stick method of claim 1, wherein, The method further comprises the following steps: calculating a movement ability value of the rehabilitation person based on the grip data, the pressure data and the exercise duration data; adjusting the wheel resistance of the sarcopenia rehabilitation intelligent walking aid based on a difference between the movement ability value and a target value.

3. The sarcopenia rehabilitation intelligent walking stick method of claim 2, wherein, The method further comprises the following steps: inputting the image data into a pre-trained body posture recognition model to obtain the body posture of the rehabilitation person; determining the falling risk of the rehabilitation person based on the body posture of the rehabilitation person, the grip data and the pressure data.

4. The sarcopenia rehabilitation intelligent walking stick method of claim 3, wherein, The method further comprises the following steps: inputting the image data into an SFB module of the pre-trained body posture recognition model to obtain first features; inputting the first features into a TAU module of the pre-trained body posture recognition model to enhance the first features and output the body posture of the rehabilitation person.

5. The sarcopenia rehabilitation smart walker method of claim 3, wherein, The method further comprises the following steps: performing multi-modal fusion on the body posture of the rehabilitation person, the grip data and the pressure data to obtain fusion data; inputting the fusion data into a Transformer architecture to output the falling risk of the rehabilitation person through an encoder-decoder structure.

6. The sarcopenia rehabilitation smart walker method of claim 5, wherein, The method further comprises the following steps: judging whether the rehabilitation person is in an abnormal state based on the grip data, the pressure data and the body posture; if the rehabilitation person is in an abnormal state, collecting surface electromyography signals of a lower leg part of the rehabilitation person; generating a training suggestion based on the surface electromyography signals.

7. A sarcopenia rehabilitation intelligent walking aid device, characterized in that, The device comprises: a data acquisition module configured to acquire body data of a rehabilitation person; the body data comprises grip data, pressure data, exercise duration data and image data; a wheel adjustment module configured to adjust wheel resistance of a sarcopenia rehabilitation intelligent walking aid based on the grip data, the pressure data and the exercise duration data; a suggestion output module configured to identify a body posture and a falling risk of the rehabilitation person based on the image data, and output an adjustment suggestion for the rehabilitation person based on the body posture and the falling risk.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The processor implements the sarcopenia rehabilitation intelligent walking method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the sarcopenia rehabilitation intelligent walking stick method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the sarcopenia rehabilitation intelligent walking stick method in any one of claims 1 to 6.

Images