Automatic alignment method and system of medical displacement machine

Abstract

The invention discloses an automatic alignment method and system for a medical displacement machine. Information of a patient is collected through a laser sensor, a monocular camera and a depth camera; inputting medical record data of the patient into a deep neural network, and using the deep neural network to perform fusion processing on information acquired by the laser sensor, the monocular camera and the depth camera and the medical record data; using a convolutional neural network and a recurrent neural network to train the position information, the joint angle information, the skeleton model and the inconvenient-to-move part, and outputting a predicted human body posture; and dynamically adjusting the position of the shifting machine according to the predicted human body posture. By training the position information, the joint angle information, the skeleton model and the inconvenient-to-move parts, the human body posture can be predicted more accurately, the recognition capability and accuracy of the system are greatly improved, the position of the displacement machine is dynamically adjusted according to the predicted human body posture, and the comfort and safety of a patient in the transfer process can be ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment alignment, and in particular to an automatic alignment method and system for a medical transfer machine. Background Art

[0002] In the medical field, with the development of technology, there are higher requirements for patient care and treatment efficiency. As an auxiliary device, medical transfer machines play an important role in helping patients with limited mobility to transfer positions. Ensuring that patients are safely and efficiently transferred from one location to another is a vital task, especially in large hospitals or nursing homes. The frequent demand for patient transfers has brought considerable pressure to medical staff.

[0003] For the elderly or patients with limited mobility, a transfer machine is needed for transportation, so the transfer from the bed to the transfer machine becomes more and more important. However, in the process of transferring the patient from the bed to the transfer machine, the accurate positioning of the transfer machine is particularly important. Each patient has different inconvenient parts to move. During the positioning process, once the patient's position changes, it is easy to cause inaccurate transfer. Summary of the invention

[0004] The present application provides an automatic alignment method and system for a medical transfer machine, which solves the technical problem in the prior art that when a patient is transferred by a transfer machine, a change in position of the patient easily leads to inaccurate transfer.

[0005] The present application provides an automatic alignment method for a medical lift, comprising the following steps:

[0006] Step S1: measuring the distance between the lift and the target position by at least one laser sensor, collecting two-dimensional image information of the patient by at least one monocular camera, and collecting three-dimensional spatial information of the patient by at least one depth camera, and performing time synchronization processing on the information collected by the laser sensor, the monocular camera and the depth camera;

[0007] Step S2: Input the patient's medical record data into the deep neural network, and use the deep neural network to fuse the information collected by the laser sensor, the monocular camera, the depth camera and the medical record data to obtain the patient's position information, joint angle information, bone model and inconvenient moving parts;

[0008] Step S3: Use convolutional neural network and recurrent neural network to train the position information, joint angle information, skeleton model and inconvenient moving parts, and output the predicted human posture;

[0009] Step S4: dynamically adjusting the position of the transfer machine according to the predicted human body posture.

[0010] In some embodiments, in step S2, the deep neural network includes a convolutional neural network branch, a long short-term memory network branch and a case data branch, the convolutional neural network branch is used to process image data, the long short-term memory network branch is used to process time series data, and the medical record data branch is used to process the patient's medical record data to identify parts that are inconvenient to move and display the parts that are inconvenient to move in the skeletal model.

[0011] In some embodiments, in step S3, the correlation between the predicted human posture and the inconveniently movable part is calculated, and it is determined whether the predicted human posture will affect the inconveniently movable part, and a correlation threshold is set.

[0012] When the correlation degree is greater than the threshold, it means that the inconvenient moving part affects the predicted human body posture, the predicted human body posture is corrected, and the corrected human body posture is output.

[0013] When the correlation degree is less than or equal to the threshold, it means that the inconveniently movable part does not affect the predicted human body posture, and the predicted human body posture is output.

[0014] In some embodiments, the calculation predicts the correlation between the human body posture and the inconvenient moving part.

[0015] The correlation degree A is calculated by the following formula:

[0016]

[0017] Among them, p i represents the predicted i-th posture, I is the set of inconveniently moved parts, and w j is the weight of the inconveniently moved part j, θ j (p i ) is the posture p i The joint angle of the middle part j, f(θ j (p i )) represents the degree of influence on the inconvenient moving parts calculated based on the joint angle.

[0018]

[0019] θ 0 is the angle of the joint in its natural state, and c is a constant.

[0020] In some embodiments, the correcting the predicted human body posture and outputting the corrected human body posture includes:

[0021] Adjust the angles of adjacent joints. If a joint j is in the inconvenient moving part set I, then adjust the angle of the joint k adjacent to j so that θ k The change in A(p i ,I);

[0022] Corrected posture p'i Obtained in the following ways:

[0023] p' i =argmin p' A(p',I)

[0024] Calculate the predicted pose p i The initial correlation degree A(p i ,I);

[0025] Check whether the correlation exceeds the threshold, set the threshold to T, if A(p i ,I)≥T, then enter the posture correction stage;

[0026] Adjust the posture according to the correction strategy until the correlation is below the threshold or the optimal solution is reached;

[0027] Output the corrected posture p' i .

[0028] In some embodiments, the maximum range of motion of each joint j is set to [θ min ,θ max ], ensuring that all joint angles θ j All fall within the maximum activity range, i.e., θ min ≤θ j ≤θ max .

[0029] In some embodiments, step S2 further includes step S21:

[0030] Obtain the patient's weight information and use pressure sensors to measure pressure information in different parts of the body;

[0031] Draw a pressure distribution map, calculate the patient's center of gravity based on the patient's weight and posture, and analyze the proportion of weight borne by each part of the body;

[0032] Adjust the position of the lift so that the patient's center of gravity is away from the inconvenient part to move;

[0033] The pressure distribution is recalculated after adjusting the posture of the transfer machine until the pressure of the inconveniently moved part is less than the threshold.

[0034] In some embodiments, in step S21, the center of gravity position may be calculated by the following formula:

[0035]

[0036] P i is the pressure value of the ith part, x i and i are the coordinates of the ith part.

[0037] An automatic alignment system for a medical transfer machine, applying the method described in any one of the above technical solutions, the system comprises:

[0038] A data collection module is used to collect patient information;

[0039] A data fusion module is used to fuse the information collected by the data collection module with the medical record data;

[0040] The posture prediction module trains the fused data and outputs the predicted human posture;

[0041] A control system is used to adjust the posture of the lift.

[0042] In some embodiments, the system further comprises:

[0043] A correlation calculation module is used to calculate the correlation between the predicted human body posture and the inconveniently movable parts;

[0044] A posture correction module, used to correct the predicted human posture;

[0045] The weight and pressure monitoring module is used to obtain the patient's weight information and pressure information of various parts of the body.

[0046] The beneficial effects of this application are as follows:

[0047] By fusing multi-source data through deep neural networks, it is not only possible to identify the patient's position information, joint angle information, and skeletal model, but also to intelligently identify the inconvenient parts to move. Using convolutional neural networks (CNN) and recurrent neural networks (RNN) to train position information, joint angle information, skeletal models, and inconvenient parts to move, it is possible to more accurately predict human posture, greatly improving the recognition ability and accuracy of the system. The position of the transfer machine is dynamically adjusted according to the predicted human posture, which can ensure the comfort and safety of the patient during the transfer process and avoid causing additional pressure or damage to the inconvenient parts to move. Through the above technical means, nursing staff can complete the patient's transfer work more efficiently.

[0048] By calculating the correlation between the predicted human posture and the inconveniently movable parts, it is possible to accurately assess whether a certain predicted posture will increase the pressure or discomfort of the inconveniently movable parts, and ensure that the predicted posture will not have a negative impact on the inconveniently movable parts. By adjusting the angles of adjacent joints to reduce the correlation, posture correction is performed to ensure that all joint angles fall within the safe range during the posture adjustment process. The human posture and the transfer machine movements are comprehensively adjusted to avoid any problems during the patient transfer process and reduce the risk of joint injury or overstretching.

[0049] Recalculate the pressure distribution after adjusting the position of the transfer machine. Adjust the position of the transfer machine and the position of the patient's center of gravity through the pressure distribution diagram and the center of gravity position calculation to ensure that the patient is in a more natural and comfortable state during the transfer process and reduce the pressure on the inconveniently moved parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention.

[0051] Figure 1 A flowchart of an automatic alignment method for a medical lift provided in the present application;

[0052] Figure 2 A schematic structural diagram of an automatic alignment system for a medical lift provided in this application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0055] In addition, the descriptions of "first", "second", etc. in this application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0056] The embodiments of the present application provide an automatic alignment method and system for a medical lift, thereby solving the technical problem in the prior art that when a patient is transferred by a lift, a change in position of the patient may easily lead to inaccurate positioning.

[0057] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0058] like Figure 1 As shown, the present application provides an automatic alignment method for a medical lift, comprising the following steps:

[0059] Step S1: Collect environmental information through laser sensors, monocular cameras and depth cameras. Specifically, at least one laser sensor is used to measure the distance between the lift and the target position, at least one monocular camera is used to collect two-dimensional image information of the patient, and at least one depth camera is used to collect three-dimensional spatial information of the patient. The information collected by the laser sensor, the monocular camera and the depth camera is time-synchronized.

[0060] Step S2: Input the patient's medical record data into the deep neural network, and use the deep neural network to fuse the information collected by the laser sensor, the monocular camera, the depth camera and the medical record data to obtain the patient's position information, joint angle information, bone model and inconvenient moving parts;

[0061] Step S3: Use convolutional neural network and recurrent neural network to train the position information, joint angle information, skeleton model and inconvenient moving parts, and output the predicted human posture;

[0062] Step S4: dynamically adjusting the position of the transfer machine according to the predicted human body posture.

[0063] By fusing multi-source data through deep neural networks, not only can the patient's position information, joint angle information and bone model be identified, but also the parts that are inconvenient to move can be intelligently identified. Using convolutional neural networks (CNN) and recurrent neural networks (RNN) to train position information, joint angle information, bone models and parts that are inconvenient to move can more accurately predict human posture, greatly improving the recognition ability and accuracy of the system. Dynamically adjusting the position of the transfer machine according to the predicted human posture can ensure the patient's comfort and safety during the transfer process and avoid causing additional pressure or damage to the parts that are inconvenient to move. Through the above technical means, nursing staff can complete the patient's transfer work more efficiently.

[0064] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0065] Specifically, in step S2, the deep neural network includes a convolutional neural network branch, a long short-term memory network branch and a case data branch. The convolutional neural network branch is used to process image data, such as real-time video streams from cameras or stored historical images, which can be used to identify the patient's posture, body contour and any external factors that may affect movement (the environment around the patient, such as the location of the bed). The long short-term memory network branch is used to process time series data and process the patient's movement history data, such as movement patterns, frequencies, etc. The medical record data branch is used to process the patient's medical record data, including but not limited to the patient's diagnosis records, treatment history, drug usage, etc. By combining the time series analysis of image data with medical record information, the system can identify parts that are inconvenient to move and display the inconveniently movable parts in the skeletal model.

[0066] Suppose a patient needs to be transferred from a hospital bed to a lift. Due to the recovery period after surgery, some parts of the body (such as the left leg) are temporarily inconvenient to move. The system processes the patient's case data and combines it with the time series analysis of the image data to identify that the part that is inconvenient to move is the left leg, and displays it in the skeletal model. The subsequent prediction of the human body posture takes into account that the left leg is an inconvenient part to move, and the predicted human body posture does not plan the movement of the left leg, making the predicted human body posture more accurate.

[0067] Preferably, in step S3, the correlation between the predicted human posture and the inconveniently movable part is calculated, whether the predicted human posture will affect the inconveniently movable part is determined, and a correlation threshold is set.

[0068] When the correlation degree is greater than the threshold, it means that the inconvenient moving part affects the predicted human body posture, the predicted human body posture is corrected, and the corrected human body posture is output.

[0069] When the correlation degree is less than or equal to the threshold, it means that the inconveniently movable part does not affect the predicted human body posture, and the predicted human body posture is output.

[0070] The calculation predicts the correlation between the human body posture and the inconvenient moving parts,

[0071] The correlation degree A is calculated by the following formula:

[0072]

[0073] Among them, p i represents the predicted i-th posture, I is the set of inconveniently moved parts, and w j is the weight of the inconveniently moved part j, θ j (p i ) is the posture p i The joint angle of the middle part j, f(θ j (p i)) represents the degree of influence on the inconvenient moving parts calculated based on the joint angle.

[0074]

[0075] θ 0 is the angle of the joint in its natural state, and c is a constant.

[0076] The method of correcting the predicted human body posture and outputting the corrected human body posture comprises:

[0077] Adjust the angles of adjacent joints. If a joint j is in the inconvenient moving part set I, then adjust the angle of the joint k adjacent to j so that θ k The change in A(p i ,I);

[0078] Corrected posture p' i Obtained in the following ways:

[0079] p' i =argmin p' A(p',I)

[0080] Calculate the predicted pose p i The initial correlation degree A(p i ,I);

[0081] Check whether the correlation exceeds the threshold, set the threshold to T, if A(p i ,I)≥T, then enter the posture correction stage;

[0082] Adjust the posture according to the correction strategy until the correlation is below the threshold or the optimal solution is reached;

[0083] Output the corrected posture p' i .

[0084] By calculating the correlation, the system can accurately identify which postures will have an adverse effect on the inconveniently moving parts, and can automatically correct the predicted postures to reduce the pressure on the inconveniently moving parts, improve the patient's comfort and safety, and formulate personalized care plans based on the inconveniently moving parts of each patient to ensure that each patient can receive the most suitable care for themselves, provide real-time correlation monitoring and posture correction feedback, and help nursing staff understand the patient's status at any time.

[0085] Furthermore, the natural range of motion of the joints is determined based on the human skeleton model, and the information about the range of motion of the joints is read from the patient's medical records to set the maximum range of motion of each joint j [θ min ,θ max ], if there is no specific medical record data, the default range of joint motion is used to ensure that all joint angles θj All fall within the maximum activity range, i.e., θ min ≤θ j ≤θ max , which can prevent the joint from over-extension or contraction during the displacement process, thereby reducing the risk of joint injury and reducing the patient's pain and discomfort during the displacement process.

[0086] If it is found that the angle of a joint j exceeds the maximum range of motion, the angle of the joint or its adjacent joints is adjusted to return it to the safe range. If one adjustment cannot bring all joints back to the safe range, multiple iterative adjustments are performed until all joints meet the range of motion requirements. Different patients may have different joint motion restrictions. The maximum range of motion of the joints is set according to the actual situation of each patient, making the nursing plan more personalized and more suitable for the needs of each patient, thereby improving the safety and comfort of the patient, while reducing the workload of nursing staff and improving the efficiency and quality of nursing work.

[0087] In step S2, step S21 is also included:

[0088] Obtain the patient's weight information, install multiple pressure sensors on the transfer machine or bed, covering the patient's main supporting parts such as back, buttocks, legs, etc., use the pressure sensors to measure the pressure information of different parts of the body, clean the collected pressure data, remove abnormal values, and map the pressure values ​​to the corresponding body part coordinates;

[0089] Use drawing tools to draw pressure distribution diagrams, use different color codes to represent different pressure levels, and use graphics to intuitively display the pressure distribution of various parts of the patient's body. Based on the patient's weight and posture, calculate the patient's center of gravity and analyze the weight ratio of each part of the body.

[0090] Adjust the posture of the transfer machine according to the position of the inconveniently moved part, so that the patient's center of gravity avoids the inconveniently moved part. After adjusting the posture of the transfer machine, re-collect pressure data and calculate the new pressure distribution. If the pressure of the inconveniently moved part is still greater than the threshold after multiple adjustments, continue to adjust the posture of the transfer machine until the pressure is lower than the threshold or reaches the optimal solution, ensuring that each patient can get the transfer care that suits him best. By continuously collecting and analyzing pressure distribution data, a large amount of data can be accumulated for further optimizing system performance. The accumulated data can be used to optimize the center of gravity position calculation model and posture adjustment strategy to improve the accuracy and reliability of the system.

[0091] In some embodiments, in step S21, the center of gravity position may be calculated by the following formula:

[0092]

[0093] P i is the pressure value of the ith part, x i and i are the coordinates of the ith part.

[0094] like Figure 2 As shown, an automatic alignment system for a medical transfer machine, applying the method described in any one of the above technical solutions, the system includes:

[0095] A data acquisition module is used to collect information about the patient. The data acquisition module includes a laser sensor for measuring the distance between the lift and the target position, a monocular camera for collecting two-dimensional image information of the patient, and a depth camera for collecting three-dimensional spatial information of the patient.

[0096] The data fusion module is used to fuse the information collected by the data collection module with the medical record data for use by subsequent modules;

[0097] Posture prediction module: trains the fused data and outputs predicted human posture. Convolutional neural network (CNN): processes image data and identifies the patient's posture and body contour. Long short-term memory network (LSTM): processes time series data and analyzes the patient's movement pattern. Medical record data branch: combines medical record data to identify parts that are inconvenient to move.

[0098] A control system, used to adjust the posture of the transfer machine according to the output result of the posture prediction module to adapt to the specific situation of the patient;

[0099] A correlation calculation module calculates the correlation between the predicted human body posture and the inconveniently movable part, and determines whether the predicted posture will affect the inconveniently movable part;

[0100] The posture correction module is responsible for correcting the predicted human posture when the correlation exceeds the threshold, ensuring that the pressure of the inconveniently movable part is lower than the threshold;

[0101] The weight and pressure monitoring module is used to obtain the patient's weight information and pressure information of various parts of the body. The patient's weight information can be obtained through a weight scale. Multiple pressure sensors are installed on the transfer machine or bed to cover the patient's main supporting parts such as the back, buttocks, legs, etc. The pressure sensors are used to measure the pressure information of different parts of the body.

[0102] The automatic alignment system of the medical lift collects the patient's position, two-dimensional image and three-dimensional spatial information through integrated laser sensors, monocular cameras and depth cameras, and combines them with medical record data for fusion processing. It uses convolutional neural networks (CNN) and long short-term memory networks (LSTM) to process image data and analyze motion patterns, and outputs predicted human postures. The system uses the correlation calculation module to determine whether the predicted posture will affect the inconveniently moved parts. If the correlation exceeds the threshold, the posture correction module corrects the posture to ensure that the pressure of the inconveniently moved parts is lower than the threshold. At the same time, the weight and pressure monitoring module obtains the patient's weight information and pressure information of various parts of the body in real time. By drawing a pressure distribution map and calculating the center of gravity position, it guides the control system to adjust the posture of the lift to adapt to the patient's specific situation, so as to achieve accurate output of predicted human postures based on pressure information and inconveniently moved parts, thereby improving the patient's comfort and safety during the shifting process, reducing the workload of nursing staff, and improving nursing efficiency and quality.

[0103] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0104] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An automatic alignment method for a medical lift, characterized in that: The following steps are involved: Step S1: measuring the distance between the lift and the target position by at least one laser sensor, collecting two-dimensional image information of the patient by at least one monocular camera, and collecting three-dimensional spatial information of the patient by at least one depth camera, and performing time synchronization processing on the information collected by the laser sensor, the monocular camera and the depth camera; Step S2: Input the patient's medical record data into the deep neural network, and use the deep neural network to fuse the information collected by the laser sensor, the monocular camera, the depth camera and the medical record data to obtain the patient's position information, joint angle information, bone model and inconvenient moving parts; Step S3: Use convolutional neural network and recurrent neural network to train the position information, joint angle information, skeleton model and inconvenient moving parts, and output the predicted human posture; Step S4: dynamically adjusting the position of the transfer machine according to the predicted human body posture.

2. The automatic alignment method of a medical lift according to claim 1, characterized in that: In step S2, the deep neural network includes a convolutional neural network branch, a long short-term memory network branch and a case data branch, the convolutional neural network branch is used to process image data, the long short-term memory network branch is used to process time series data, and the medical record data branch is used to process the patient's medical record data to identify parts that are inconvenient to move and display the parts that are inconvenient to move in the skeletal model.

3. The automatic alignment method of a medical lift according to claim 1, characterized in that: In step S3, the correlation between the predicted human posture and the inconveniently movable part is calculated, and it is determined whether the predicted human posture will affect the inconveniently movable part, and a correlation threshold is set. When the correlation degree is greater than the threshold, it means that the inconvenient moving part affects the predicted human body posture, the predicted human body posture is corrected, and the corrected human body posture is output. When the correlation degree is less than or equal to the threshold, it means that the inconveniently movable part does not affect the predicted human body posture, and the predicted human body posture is output.

4. The automatic alignment method of a medical lift as claimed in claim 3, characterized in that: The calculation predicts the correlation between the human body posture and the inconvenient moving parts. The correlation degree A is calculated by the following formula: A(p i ,I)=∑ j∈I w j ·f(θ j (p i )) Among them, p i represents the predicted i-th posture, I is the set of inconveniently moved parts, and w j is the weight of the inconveniently moved part j, θ j (p i ) is the posture p i The joint angle of the middle part j, f(θ j (p i )) represents the degree of influence on the inconvenient moving parts calculated based on the joint angle. θ 0 is the angle of the joint in its natural state, and c is a constant.

5. The automatic alignment method of a medical lift according to claim 4, characterized in that: The method of correcting the predicted human body posture and outputting the corrected human body posture comprises: Adjust the angles of adjacent joints. If a joint j is in the inconvenient moving part set I, then adjust the angle of the joint k adjacent to j so that θ k The change in A(p i , I); Corrected posture p' i Obtained in the following ways: p’ i =argmin p' A(p',I) Calculate the predicted pose p i The initial correlation degree A(p i , I); Check whether the correlation exceeds the threshold, set the threshold to T, if A(p i ,)≥T, then enter the posture correction stage; Adjust the posture according to the correction strategy until the correlation is below the threshold or the optimal solution is reached; Output the corrected posture p' i .

6. The automatic alignment method of a medical lift according to claim 5, characterized in that: Set the maximum range of motion of each joint j [θ min ,θ max ], ensuring that all joint angles θ j All fall within the maximum activity range, that is, θ min ≤θ j ≤θ max .

7. The automatic alignment method of a medical lift according to claim 1, characterized in that: In step S2, step S21 is also included: Obtain the patient's weight information and use pressure sensors to measure pressure information in different parts of the body; Draw a pressure distribution map, calculate the patient's center of gravity based on the patient's weight and posture, and analyze the proportion of weight borne by each part of the body; Adjust the position of the lift so that the patient's center of gravity is away from the inconvenient part to move; After adjusting the posture of the transfer machine, the pressure distribution is recalculated until the pressure of the inconveniently moved part is less than the threshold.

8. The automatic alignment method of a medical lift according to claim 7, characterized in that: In step S21, the center of gravity position can be calculated by the following formula: P i is the pressure value of the ith part, x i and i are the coordinates of the ith part.

9. An automatic alignment system for a medical lift, characterized in that: The method according to any one of claims 1 to 8 is applied, wherein the system comprises: A data collection module is used to collect patient information; A data fusion module is used to fuse the information collected by the data collection module with the medical record data; The posture prediction module trains the fused data and outputs the predicted human posture; A control system is used to adjust the posture of the lift.

10. The automatic alignment method of a medical lift according to claim 9, characterized in that: The system further comprises: A correlation calculation module is used to calculate the correlation between the predicted human body posture and the inconveniently movable parts; A posture correction module, used to correct the predicted human posture; The weight and pressure monitoring module is used to obtain the patient's weight information and pressure information of various parts of the body.

Images