A kind of rehabilitation physiotherapy equipment and nursing process monitoring method
Through real-time acquisition and machine learning, analyzing the operating parameters of the dynamic trajectory trainer, identifying and correcting potential anomalies, the problem of ineffectiveness or inefficiency in gait training is solved, and the rehabilitation effect and equipment reliability are improved.
Patent Information
- Application Number
- CN202410913633.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-09
AI Technical Summary
The existing power trajectory trainers cannot intelligently perceive potential abnormalities during the nursing process, resulting in ineffective or inefficient gait training, which may form wrong gait patterns, affecting the rehabilitation effect and prolonging the rehabilitation cycle.
By collecting the operating parameter information of the dynamic trajectory trainer in real time, using machine learning models to perform abnormal analysis, identify potential abnormalities, and generate deviation indexes through gait data comparison, issuing early warnings and adjusting training plans to ensure the effectiveness of gait training.
Improves the accuracy of the power track trainer in gait guidance and support, reduces the risk of wrong gait mode, improves rehabilitation effect and efficiency, and ensures the reliability and service life of the equipment.
Smart Images

Figure CN118673442B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of rehabilitation physiotherapy and nursing, and in particular to a rehabilitation physiotherapy device and a method for monitoring a nursing process. Background Art
[0002] Monitoring the nursing process of rehabilitation physiotherapy equipment refers to real-time tracking and recording of equipment usage, patient's physiological response and treatment effect in the process of using rehabilitation physiotherapy equipment to treat and care for patients. This process includes not only the operation record of the equipment, but also the monitoring of various physiological indicators of the patient (such as heart rate, blood pressure, respiratory rate, etc.). Through the collection and analysis of these data, medical staff can timely understand the patient's recovery status, adjust the treatment plan, improve the rehabilitation effect and reduce the occurrence of complications. At the same time, the accumulation of these data also provides valuable reference for future treatment.
[0003] The main function of the dynamic track trainer is to assist patients with lower limb weakness or partial paralysis in gait training. By reducing the weight of the patient's body, the device enables patients to perform gait exercises in a safe and stable environment. Its core function is to support the patient's body through a sling system, thereby reducing the load on the lower limbs and allowing patients to maintain balance and stability during walking training. This method not only improves the safety of training, but also allows patients to perform longer and more intense gait exercises at an earlier stage of rehabilitation. The dynamic track trainer is particularly important for patients with lower limb dysfunction caused by stroke, spinal cord injury, brain trauma, etc. Through repeated and regular gait training, neural plasticity can be promoted, gait and lower limb function can be improved, and patients can be helped to relearn and restore their walking ability. In addition, the real-time feedback function of the device can record and analyze the patient's gait parameters to help physical therapists develop and adjust personalized rehabilitation plans. This systematic gait training can not only accelerate the rehabilitation process, but also significantly improve the patient's quality of life and self-confidence.
[0004] The existing technology has the following deficiencies: During the process of caring for patients with the power trajectory trainer, the power trajectory trainer has potential abnormalities. The existing technology is usually unable to intelligently perceive them. When this happens, it may not be able to provide correct gait guidance and support, and the patient's gait training may become ineffective or inefficient, or even form an incorrect gait pattern. This will seriously affect the rehabilitation effect, making it impossible for patients to achieve the expected rehabilitation goals, prolonging the rehabilitation cycle, and increasing treatment costs.
[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0006] The purpose of the present invention is to provide a monitoring method for rehabilitation physiotherapy equipment and nursing process, which can intelligently identify potential abnormalities by collecting the operating parameters of the power trajectory trainer in real time and using a machine learning model for abnormal analysis, thereby improving the accuracy of the equipment in gait guidance and support, ensuring the effectiveness of gait training, reducing the risk of erroneous gait patterns, and ultimately improving the rehabilitation effect. When an abnormality is identified and has an impact on gait training, the system issues an early warning and notifies for timely processing to avoid ineffective training. If the abnormality does not affect the training, regular inspection and maintenance can be used to improve the reliability and service life of the equipment, ensure patient safety and rehabilitation effects, and solve the problems in the above-mentioned background technology.
[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for monitoring the nursing process of rehabilitation physiotherapy equipment, comprising the following steps:
[0008] During the operation of the dynamic trajectory trainer, the operating parameter information of the dynamic trajectory trainer is collected in real time, and the collected information is pre-processed to improve the data quality;
[0009] After the preprocessed operating parameter information is processed for abnormality analysis, it is input into the trained machine learning model to identify potential abnormalities of the power trajectory trainer;
[0010] After identifying the potential abnormality of the powered trajectory trainer, the actual gait data of the patient during gait training on the powered trajectory trainer is collected in real time, and the actual gait data is recorded and processed using the data acquisition system and gait analysis software to generate the actual gait training pattern map of the patient;
[0011] Conduct detailed comparison and analysis of the actual gait training pattern and the expected gait training pattern, and identify the deviation between the actual gait and the expected gait through data comparison;
[0012] Based on the results of the comparative analysis, it was evaluated whether the potential abnormalities of the dynamic trajectory trainer had an impact on the patient's gait training.
[0013] Preferably, the operating parameter information of the powered trajectory trainer includes the smoothness information of the robot arm motion and the center of gravity movement trajectory information, wherein the smoothness information of the robot arm motion refers to the continuity and stability of the motion trajectory of the robot arm in the powered trajectory trainer during gait guidance, and the center of gravity movement trajectory information refers to the trajectory changes of the patient's body center of gravity during movement when the powered trajectory trainer performs gait training.
[0014] Preferably, after the preprocessed robot arm motion smoothness information is subjected to abnormal analysis processing, a robot arm motion smoothness abnormality index is generated, and after the preprocessed center of gravity movement trajectory information is subjected to abnormal analysis processing, a center of gravity movement trajectory abnormality index is generated, and the robot arm motion smoothness abnormality index and the center of gravity movement trajectory abnormality index generated after the abnormal analysis processing are input into the trained machine learning model to generate a gait training evaluation coefficient, and the gait training evaluation coefficient is used to perform an intelligent evaluation of the gait training situation of the power trajectory trainer.
[0015] Preferably, the gait training evaluation coefficient generated within the fixed detection window when the power trajectory trainer is caring for the patient is compared and analyzed with a preset gait training evaluation coefficient reference threshold to identify potential abnormalities of the power trajectory trainer. The results of the comparison and analysis are as follows:
[0016] If the gait training evaluation coefficient is greater than or equal to the gait training evaluation coefficient reference threshold, an efficient nursing signal is generated, indicating that the power trajectory trainer can provide efficient nursing care for the patient;
[0017] If the gait training evaluation coefficient is less than the gait training evaluation coefficient reference threshold, an inefficient care signal is generated, indicating that there are potential abnormal risks when the power trajectory trainer provides care for the patient.
[0018] Preferably, after identifying a potential abnormality of the power trajectory trainer, that is, when the power trajectory trainer generates an inefficient care signal for caring for the patient, an actual gait training pattern map of the patient is generated, and the specific steps are as follows:
[0019] Real-time collection of patients’ gait data during gait training;
[0020] The collected gait data is transmitted to a central database or cloud storage system via wired or wireless means;
[0021] Gait parameters were extracted from the preprocessed data using gait analysis software;
[0022] The extracted gait parameters are input into the gait analysis software for analysis and processing. Through comprehensive analysis of various gait parameters, an actual gait training pattern map of the patient is generated.
[0023] Preferably, the actual gait training pattern is compared and analyzed in detail with the expected gait training pattern, and a deviation index is generated through data comparison. The steps for generating the deviation index are as follows:
[0024] Gait parameters are extracted from the actual gait training data and the expected gait training data. Let the actual gait parameter vector be A = {a1, a2, a3, ..., a n}, the expected gait parameter vector is B = {b1, b2, b3, ..., bn}, where n is the number of gait parameters;
[0025] Calculate the cosine similarity between the actual gait parameter vector A and the expected gait parameter vector B. The calculation expression is: Where A·B represents the dot product of vector A and vector B, ‖A‖ and ‖B‖ represent the Euclidean lengths of the two vectors, Cos Sim represents the cosine similarity between the actual gait parameter vector A and the expected gait parameter vector B;
[0026] The deviation index is calculated by the cosine similarity of the actual gait parameter vector A and the expected gait parameter vector B. The calculation expression is: Deviation Index =1-Cos Sim , where Deviation Inde Represents the deviation index.
[0027] Preferably, after identifying the potential abnormality of the powered trajectory trainer, the deviation index generated by the powered trajectory trainer when caring for the patient is compared and analyzed with a preset deviation index reference threshold to evaluate whether the potential abnormality of the powered trajectory trainer has an impact on the patient's gait training. The results of the comparison and analysis are as follows:
[0028] If the deviation index is greater than or equal to the deviation index reference threshold, an impact signal is generated, indicating that the potential abnormality of the power trajectory trainer has affected the patient's gait training, and an early warning prompt is issued for the impact signal to inform the patient and relevant medical personnel;
[0029] If the deviation index is less than the deviation index reference threshold, a non-impact signal is generated, indicating that the potential abnormality of the powered trajectory trainer has no impact on the patient's gait training.
[0030] Preferably, after the pre-processed robot arm motion smoothness information is subjected to abnormal analysis, the specific steps of generating the robot arm motion smoothness abnormality index are as follows:
[0031] In a fixed detection window, the motion trajectory data of the robot arm in the power trajectory trainer is collected in real time, and the motion trajectory data is represented by p(t), wherein p(t) represents the three-dimensional position vector of the robot arm at time t, p(t) = [x(t), y(t), z(t)], x(t) represents the position of the robot arm along the X-axis at time t, y(t) represents the position of the robot arm along the Y-axis at time t, and z(t) represents the position of the robot arm along the Z-axis at time t;
[0032] Calculate the trajectory difference vector of each time step, and the calculation expression is: Δp(t)=p(t)-p(t-1), where Δp(t) represents the position change vector within the time step Δt;
[0033] Calculate the curvature of the trajectory at each time step, using the second-order derivative and first-order derivative of the trajectory for calculation. The calculation expression is: Among them, κ(t) represents the curvature of the trajectory, v(t) represents the velocity vector at time t, a(t) represents the acceleration vector at time t, ‖v(t)×a(t)‖ represents the modulus of the product of velocity and acceleration, and ‖v(t)‖ represents the modulus of the velocity vector;
[0034] The trajectory smoothness evaluation index is calculated using the trajectory curvature and its first-order difference. The calculation expression is: Among them, S(t) represents the trajectory smoothness evaluation index, It represents the first-order derivative of the trajectory curvature, t0 represents the starting time of the fixed detection window, and T represents the total duration of the fixed detection window;
[0035] Based on the trajectory smoothness evaluation index S(t), the robot motion smoothness abnormality index is calculated, and the calculation expression is: In the formula, Robotic Arm Indicates the abnormal index of smoothness of robot movement, S ref It is the reference smoothness evaluation index.
[0036] Preferably, after the preprocessed center of gravity movement trajectory information is subjected to abnormal analysis, the specific steps of generating the center of gravity movement trajectory abnormality index are as follows:
[0037] The patient's center of gravity movement trajectory data is collected in real time within a fixed detection window. T represents the detection window size. N data points are collected per second. Therefore, there will be T×N center of gravity movement data points in each detection window, which are recorded as Where (x i ,y i ) represents the centroid position of the i-th data point;
[0038] Calculate the curvature of the center of gravity moving trajectory, the calculation expression is: In the formula, K i The curvature of the trajectory of the center of gravity is K. i Used to describe the curvature of a trajectory at a certain point;
[0039] Calculate the velocity and acceleration of the center of gravity moving trajectory. The calculation expression is: Where V i and Ai They represent the velocity and acceleration of the center of gravity moving trajectory, respectively. The velocity V i Indicates the speed at which the center of gravity moves between two adjacent data points, acceleration A i Indicates the rate of change of speed;
[0040] Calculate the volatility of the center of gravity moving trajectory, the calculation expression is: Where W i represents the volatility of the moving trajectory of the center of gravity, j represents the offset relative to the current data point, k represents the half-width of the window, and it means taking k points before and after the current data point, for a total of 2k+1 points. The volatility of the moving trajectory of the center of gravity is W i Measures the variation of the center of gravity within a small range;
[0041] Calculate the abnormal index of the center of gravity movement trajectory, and the calculation expression is: Where α, β, γ, and δ are the curvature K of the trajectory of the center of gravity respectively. i , velocity of center of gravity moving trajectory V i Acceleration A of the center of gravity moving trajectory i And the center of gravity moving trajectory volatility W i The weight of Center Mass Indicates the abnormal index of center of gravity movement trajectory.
[0042] A rehabilitation therapy device includes a power trajectory trainer. The specific process of caring for a patient through the power trajectory trainer is as follows:
[0043] Initialize patient information, specifically input patient information including name, age, medical history, and rehabilitation goals;
[0044] Set the parameters of the dynamic trajectory trainer according to the patient's specific situation;
[0045] The parameters of the dynamic trajectory trainer include force, speed, angle, frequency, etc.;
[0046] Check the status of the powered track trainer to ensure that the equipment is intact, all parts are properly connected, and any necessary calibrations are performed;
[0047] Install the patient on the powered trajectory trainer and adjust the straps and support equipment to ensure the patient is safe and comfortable;
[0048] Start the trainer for initial testing, observe patient response, and adjust device parameters to suit patient abilities and needs;
[0049] Start the formal training program, conduct strength, speed, angle, frequency and other aspects of training according to the set parameters, monitor the patient's status in real time, and collect data through sensors and monitoring systems;
[0050] Collect and record data from each training session, including the patient's movement trajectory, strength output, heart rate, blood pressure, etc., analyze the data, evaluate the patient's progress, and adjust subsequent training plans;
[0051] Provide training feedback to patients to inform them of their progress and adjust the parameters of the trainer and training plan based on the data analysis results;
[0052] At the end of each training session, gradually reduce the intensity of the training, allow the patient to slowly return to a resting state, assist the patient in removing from the equipment, and check their physical condition;
[0053] Clean and inspect equipment to ensure it is ready for the next use.
[0054] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0055] The present invention can intelligently identify potential abnormalities of the powered trajectory trainer by collecting the operating parameter information of the powered trajectory trainer in real time and using a machine learning model to perform abnormality analysis and processing. This intelligent evaluation method greatly improves the accuracy of the device in the gait guidance and support process, ensures the effectiveness of the patient's gait training, reduces the risk of forming an erroneous gait pattern, and ultimately improves the rehabilitation effect and efficiency.
[0056] After identifying the potential abnormality, the present invention compares the actual gait training pattern with the expected gait training pattern, generates a deviation index based on data comparison, and accurately evaluates the impact of the abnormality on the patient's gait training through the deviation index. When it is found that the powered trajectory trainer has a potential abnormality and affects the gait training, an impact signal is generated and an early warning prompt is issued to notify the patient and medical staff to take timely measures. This can avoid invalid or inefficient gait training caused by failure or abnormality of the powered trajectory trainer and prevent patients from forming wrong gait patterns. In addition, when the potential abnormality of the powered trajectory trainer does not affect the patient's gait training, regular inspection and maintenance can be used to improve the reliability and service life of the powered trajectory trainer, reduce the incidence of sudden problems, ensure that the powered trajectory trainer is always in good working condition, and ensure the safety of the patient and the rehabilitation effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0058] Figure 1The present invention is a method flow chart of a rehabilitation therapy device and a method for monitoring a nursing process.
[0059] Figure 2 The present invention is a flow chart of caring for a patient through a power trajectory trainer. DETAILED DESCRIPTION
[0060] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.
[0061] The present invention provides Figure 1 A rehabilitation therapy device and a method for monitoring the nursing process are shown, comprising the following steps:
[0062] During the operation of the dynamic trajectory trainer, the operating parameter information of the dynamic trajectory trainer is collected in real time, and the collected information is pre-processed to improve the data quality;
[0063] The operating parameter information of the dynamic trajectory trainer includes the smoothness information of the robot arm movement and the center of gravity movement trajectory information. The smoothness information of the robot arm movement refers to the continuity and stability of the movement trajectory of the robot arm in the dynamic trajectory trainer during the gait guidance process. The center of gravity movement trajectory information refers to the trajectory changes of the patient's body center of gravity during the movement process when the dynamic trajectory trainer performs gait training.
[0064] Preprocessing the collected information is a key step to improve data quality. Preprocessing includes (but is not limited to) the following aspects:
[0065] Data cleaning: Remove noise and outliers from the data to ensure data accuracy and reliability. Noise and outliers may come from sensor failure, data transmission errors, or environmental interference. Cleaning can improve the accuracy of data analysis.
[0066] Data normalization: Converting data of different dimensions to the same dimension, usually scaling the data to a specific range (such as between 0 and 1). Normalization helps eliminate differences between different units and magnitudes, making subsequent analysis and machine learning model processing more consistent and effective.
[0067] Data smoothing: Through moving average method, low-pass filtering and other technologies, random fluctuations in data are reduced to make data smoother and more stable. Smoothing helps to highlight the real trends in the data, suppress the impact of random noise, and improve the interpretability of data.
[0068] Missing value processing: fill or delete missing values in the data set. Common methods include mean filling, interpolation, regression filling, etc. Missing value processing can effectively avoid analysis bias caused by incomplete data and improve data integrity and reliability.
[0069] Data standardization: Transform the data into a standard normal distribution so that the data has zero mean and unit variance. Standardization helps improve the convergence speed and performance of the model for some machine learning algorithms (such as support vector machines and k-means clustering).
[0070] Feature extraction: Extract useful features from raw data to reduce data dimensions and retain information that is meaningful for analysis and modeling. Feature extraction can improve model training efficiency, reduce computational overhead, and avoid the dimensionality curse problem.
[0071] Data transformation: Perform mathematical transformations on data (such as logarithmic transformation and differential transformation) to make the data more consistent with the assumptions of analysis and modeling. The transformed data can reveal hidden patterns and laws in the original data and improve the performance of the model.
[0072] Through the above preprocessing steps, the data quality is improved, making it more suitable for subsequent analysis and modeling. This not only improves the accuracy and consistency of the data, but also enhances the interpretability and application value of the data, thereby obtaining more reliable and effective results in anomaly detection and gait analysis of the powered trajectory trainer.
[0073] After the preprocessed operating parameter information is processed for abnormality analysis, it is input into the trained machine learning model (the machine learning model is built and trained based on historical operating data and abnormal data) to identify potential abnormalities of the power trajectory trainer;
[0074] After the preprocessed robot arm motion smoothness information is subjected to abnormal analysis, a robot arm motion smoothness abnormality index is generated. After the preprocessed center of gravity movement trajectory information is subjected to abnormal analysis, a center of gravity movement trajectory abnormality index is generated. The robot arm motion smoothness abnormality index and the center of gravity movement trajectory abnormality index generated after the abnormal analysis are input into the trained machine learning model to generate a gait training evaluation coefficient. The gait training evaluation coefficient is used to perform an intelligent evaluation of the gait training situation of the power trajectory trainer.
[0075] During the operation of the powered trajectory trainer, if the smoothness of the movement of the robotic arm is abnormal, the powered trajectory trainer will not be able to provide correct gait guidance and support, and the patient's gait training may become ineffective or inefficient, or even form an incorrect gait pattern. The reason is that the main function of the robotic arm is to simulate and guide the patient's natural gait movement through a precise and stable motion trajectory to ensure that the patient maintains the correct posture and gait rhythm during training. If the movement of the robotic arm is not smooth, and there is a jam, jitter or irregular movement, it will directly affect the patient's gait continuity and stability, making it impossible for them to obtain uniform and continuous gait guidance. This irregular guidance will not only increase the patient's discomfort during training, but may also interfere with the neuromuscular remodeling process, causing the patient to form an incorrect gait pattern, thereby prolonging the rehabilitation cycle and reducing the rehabilitation effect. Therefore, the smoothness of the robotic arm's movement is crucial to the success of gait training.
[0076] After the preprocessed robot arm motion smoothness information is subjected to abnormal analysis, the specific steps for generating the robot arm motion smoothness abnormality index are as follows:
[0077] In a fixed detection window, the motion trajectory data of the robot arm in the power trajectory trainer is collected in real time, and the motion trajectory data is represented by p(t), wherein p(t) represents the three-dimensional position vector of the robot arm at time t, p(t) = [x(t), y(t), z(t)], x(t) represents the position of the robot arm along the X-axis at time t, y(t) represents the position of the robot arm along the Y-axis at time t, and z(t) represents the position of the robot arm along the Z-axis at time t;
[0078] Calculate the trajectory difference vector of each time step, and the calculation expression is: Δp(t)=p(t)-p(t-1), where Δp(t) represents the position change vector within the time step Δt;
[0079] It should be noted that when analyzing the running data of the dynamic trajectory trainer, the "time step" refers to the time interval between data recording during the sampling process. This time step is a fixed time period, which represents the time difference between consecutive sampling points. In gait training and robotic arm motion monitoring, this time step is critical because it determines the frequency and precision of data collection.
[0080] Calculate the curvature of the trajectory at each time step, using the second-order derivative (acceleration) and first-order derivative (acceleration) of the trajectory for calculation. The calculation expression is: Among them, κ(t) represents the curvature of the trajectory, v(t) represents the velocity vector at time t, a(t) represents the acceleration vector at time t, ‖v(t)×a(t)‖ represents the modulus of the product of velocity and acceleration, and ‖v(t)‖ represents the modulus of the velocity vector;
[0081] The trajectory smoothness evaluation index is calculated using the trajectory curvature and its first-order difference. The calculation expression is: Among them, S(t) represents the trajectory smoothness evaluation index, It represents the first-order derivative of the trajectory curvature, t0 represents the starting time of the fixed detection window, and T represents the total duration of the fixed detection window;
[0082] Based on the trajectory smoothness evaluation index S(t), the robot motion smoothness abnormality index is calculated, and the calculation expression is: In the formula, Robotic Arm Indicates the abnormal index of smoothness of robot movement, S ref It is a reference smoothness evaluation index (calculated based on normal operation data).
[0083] The greater the performance value of the robot arm motion smoothness abnormality index, the greater the hidden danger of potential abnormalities during the operation of the dynamic trajectory trainer. Specifically, when the abnormality index is high, it means that the smoothness of the robot arm's motion is poor, and there may be problems such as stuttering, jitter or irregular movement. These problems will affect the gait guidance and support functions of the device, and thus affect the patient's gait training effect. On the contrary, when the abnormality index is low, it means that the smoothness of the robot arm's motion is good, the device is in a stable operating state, the hidden dangers of potential abnormalities are small, and it can provide more accurate and reliable gait guidance and support.
[0084] During the operation of the dynamic trajectory trainer, if the trajectory of the center of gravity movement is abnormal, the trainer will not be able to provide correct gait guidance and support, making the patient's gait training ineffective or inefficient, and may even form an incorrect gait pattern. This is because the trajectory of the center of gravity movement is one of the key parameters in gait training, reflecting the balance and stability of the patient's body during walking. An abnormal center of gravity trajectory may indicate that the patient has an incorrect posture or unbalanced force distribution during gait training, and the trainer cannot effectively adjust the support force to compensate for these problems. This not only affects the effectiveness of the training, but may also cause the patient to develop incorrect gait habits, increase the risk of falling and injury, and prolong the rehabilitation period. Therefore, ensuring the normal trajectory of the center of gravity movement is the basis for achieving efficient and correct gait training.
[0085] After the preprocessed center of gravity movement trajectory information is subjected to abnormal analysis, the specific steps of generating the center of gravity movement trajectory abnormality index are as follows:
[0086] The patient's center of gravity movement trajectory data is collected in real time within a fixed detection window. T represents the detection window size. N data points are collected per second. Therefore, there will be T×N center of gravity movement data points in each detection window, which are recorded as Where (x i ,y i ) represents the centroid position of the i-th data point;
[0087] Calculate the curvature of the center of gravity moving trajectory, the calculation expression is: In the formula, K i The curvature of the trajectory of the center of gravity is K. i It is used to describe the curvature of the trajectory at a certain point, which can reflect the change of the trajectory of the center of gravity. i ,y i ) to evaluate the smoothness and stability of the trajectory;
[0088] Calculate the velocity and acceleration of the center of gravity moving trajectory. The calculation expression is: Where V i and A i They represent the velocity and acceleration of the center of gravity moving trajectory, respectively. The velocity V i Indicates the speed at which the center of gravity moves between two adjacent data points, acceleration A i Indicates the rate of change of velocity, speed and acceleration can help identify unusual violent movements or irregular trajectory changes;
[0089] Calculate the volatility of the center of gravity moving trajectory, the calculation expression is: Where W i represents the volatility of the moving trajectory of the center of gravity, j represents the offset relative to the current data point, which is used to select multiple adjacent data points in a small range for calculation, k represents the half-width of the window, which means that k points are taken before and after the current data point, for a total of 2k+1 points, and the volatility of the moving trajectory of the center of gravity W i It measures the variation of the center of gravity within a small range and is used to detect the stability of the center of gravity movement.
[0090] Calculate the abnormal index of the center of gravity movement trajectory, and the calculation expression is: Where α, β, γ, and δ are the curvature K of the trajectory of the center of gravity respectively. i , velocity of center of gravity moving trajectory V i Acceleration A of the center of gravity moving trajectory i And the center of gravity moving trajectory volatility W i The weights reflect the contribution of each parameter to the overall anomaly index. These weights can be tuned based on historical data and expert experience. MassIndicates the abnormal index of center of gravity movement trajectory.
[0091] The larger the performance value of the center of gravity movement trajectory abnormality index, the greater the potential abnormality risk of the dynamic trajectory trainer during operation. The center of gravity movement trajectory abnormality index reflects the smoothness and consistency of the trajectory by comprehensively evaluating the parameters such as the curvature, speed, acceleration and volatility of the center of gravity movement trajectory. When the abnormality index is high, it means that there are large irregularities or fluctuations in the center of gravity movement trajectory, which may cause the device to be unable to provide correct gait guidance and support, thereby affecting the patient's gait training effect. On the contrary, when the abnormality index is small, it means that the trajectory is relatively stable and normal, the operation of the equipment is more reliable, the potential abnormality risk is smaller, and the patient's gait training effect is more guaranteed.
[0092] The selection of machine learning models is not specifically limited here, and can achieve the Robotic index of the robot arm motion smoothness abnormality Arm and the center of gravity movement trajectory abnormality index Center Mass Perform comprehensive analysis to generate gait training evaluation coefficient gait training In order to realize the technical solution of the present invention, the present invention provides a specific implementation method;
[0093] Gait training evaluation coefficient gait training The generated calculation formula is: training =ln(u1*Robotic Arm -1 +u2*Center Mass -1 +1), where u1 and u2 are the robot motion smoothness anomaly index Robotic Arm and the center of gravity movement trajectory abnormality index Center Mass The preset proportional coefficient, and u1 and u2 are both greater than 0.
[0094] It can be seen from the gait training evaluation coefficient that, within the fixed detection window, the greater the performance value of the robotic arm motion smoothness abnormality index generated after the pre-processed robotic arm motion smoothness information is subjected to abnormal analysis processing, the greater the performance value of the center of gravity movement trajectory abnormality index generated after the pre-processed center of gravity movement trajectory information is subjected to abnormal analysis processing, that is, the smaller the performance value of the gait training evaluation coefficient generated within the fixed detection window, the greater the hidden danger of potential abnormality in the powered trajectory trainer's care for patients, and vice versa.
[0095] The gait training evaluation coefficient generated within the fixed detection window when the powered trajectory trainer is caring for the patient is compared with the pre-set gait training evaluation coefficient reference threshold to identify potential abnormalities of the powered trajectory trainer. The results of the comparison and analysis are as follows:
[0096] If the gait training evaluation coefficient is greater than or equal to the gait training evaluation coefficient reference threshold, an efficient nursing signal is generated, indicating that the power trajectory trainer can provide efficient nursing care for the patient;
[0097] If the gait training evaluation coefficient is less than the gait training evaluation coefficient reference threshold, an inefficient care signal is generated, indicating that there are potential abnormal risks when the power trajectory trainer provides care for the patient.
[0098] After identifying the potential abnormality of the powered trajectory trainer, the actual gait data of the patient during gait training on the powered trajectory trainer is collected in real time, and the actual gait data is recorded and processed using the data acquisition system and gait analysis software to generate the actual gait training pattern map of the patient;
[0099] After identifying a potential abnormality of the powered trajectory trainer, that is, when the powered trajectory trainer generates an inefficient care signal for the patient, the actual gait training pattern map of the patient is generated, and the specific steps are as follows:
[0100] Real-time collection of patients’ gait data during gait training;
[0101] These data include parameters such as cadence, stride, gait cycle, foot contact angle, center of gravity movement trajectory, etc. Sensors and acquisition devices synchronously transmit these data to the data acquisition system to ensure the real-time and integrity of the data.
[0102] The collected gait data is transmitted to a central database or cloud storage system via wired or wireless means;
[0103] The accuracy and integrity of data must be ensured during data transmission to avoid data loss or transmission errors. The storage system should have efficient data management and retrieval functions for subsequent processing and analysis.
[0104] Gait parameters were extracted from the preprocessed data using gait analysis software;
[0105] Gait parameters include gait cycle, cadence, stride, time ratio of support phase and swing phase, center of gravity movement trajectory, etc. These parameters reflect the patient's gait characteristics and movement state, and are an important basis for generating gait pattern maps. Gait analysis software is a tool specifically used to extract and analyze gait parameters from preprocessed gait data. Commonly used software includes Vicon Nexus, Motion Analysis Cortex, Qualisys Track Manager (QTM), GAITRite, Delsys EMGworks, and Noraxon MyoResearch. These software use advanced motion capture technology and data processing algorithms to accurately extract key gait parameters such as cadence, stride, gait cycle, time ratio of support phase and swing phase, center of gravity movement trajectory, etc. Through these software, medical staff can understand the patient's gait characteristics and movement state in detail, providing a scientific basis for formulating personalized rehabilitation plans.
[0106] The extracted gait parameters are input into the gait analysis software for analysis and processing, and the actual gait training pattern map of the patient is generated through comprehensive analysis of each gait parameter;
[0107] The graph shows the patient's detailed gait information for each step during the training process, including changes in the gait cycle, stability of stride, trajectory of center of gravity movement, etc.
[0108] Conduct detailed comparison and analysis of the actual gait training pattern and the expected gait training pattern, and identify the deviation between the actual gait and the expected gait through data comparison;
[0109] The actual gait training pattern is compared and analyzed in detail with the expected gait training pattern. Through data comparison, a deviation index is generated. The steps for generating the deviation index are as follows:
[0110] Gait parameters are extracted from the actual gait training data and the expected gait training data. Let the actual gait parameter vector be A = {a1, a2, a3, ..., a n}, the expected gait parameter vector is B = {b1, b2, b3, ..., b n}, where n is the number of gait parameters, such as cadence, stride length, gait cycle, etc.;
[0111] Calculate the cosine similarity between the actual gait parameter vector A and the expected gait parameter vector B. The calculation expression is: Where A·B represents the dot product of vector A and vector B, ‖A‖ and ‖B‖ represent the Euclidean lengths of the two vectors, Cos Sim represents the cosine similarity between the actual gait parameter vector A and the expected gait parameter vector B;
[0112] It should be noted that the expected gait training model refers to the ideal gait parameters and motion trajectory set based on the standard gait data of healthy people, the patient's personal rehabilitation goals and the experience of clinical experts. These parameters include cadence, stride, gait cycle, support phase and swing phase time ratio, etc. The expected gait training model can be determined by analyzing the gait data of a large number of healthy people to determine the baseline value, and then personalized adjustment is made based on the patient's specific situation (such as age, gender, condition, etc.) to develop an ideal gait pattern that meets the patient's rehabilitation needs. In this way, a clear goal can be set for the patient's rehabilitation training to guide and evaluate the effectiveness of gait training.
[0113] The deviation index is calculated by the cosine similarity of the actual gait parameter vector A and the expected gait parameter vector B. The calculation expression is: Deviation Index =1-Cos Sim , where Deviation Index Represents the deviation index.
[0114] The deviation index indicates the degree of difference between the actual gait training pattern and the expected gait training pattern. The closer the cosine similarity is to 1, the more similar the two vectors are and the smaller the deviation index is; conversely, the smaller the cosine similarity is, the greater the difference between the two vectors is and the larger the deviation index is.
[0115] Based on the results of the comparative analysis, evaluate whether the potential abnormalities of the dynamic trajectory trainer have affected the patient's gait training;
[0116] After identifying the potential abnormality of the powered trajectory trainer, the deviation index generated by the powered trajectory trainer when caring for the patient was compared and analyzed with the pre-set deviation index reference threshold to evaluate whether the potential abnormality of the powered trajectory trainer had an impact on the patient's gait training. The results of the comparison and analysis are as follows:
[0117] If the deviation index is greater than or equal to the deviation index reference threshold, an impact signal is generated, indicating that the potential abnormality of the power trajectory trainer has affected the patient's gait training, and an early warning prompt is issued for the impact signal to inform the patient and relevant medical personnel, and the operation of the power trajectory trainer is immediately suspended, and professional technicians conduct a detailed inspection of the power trajectory trainer to find out the specific cause of the potential abnormality;
[0118] If the deviation index is less than the deviation index reference threshold, a non-impact signal is generated, indicating that the potential abnormality of the powered trajectory trainer has no impact on the patient's gait training. The powered trajectory trainer should be inspected and maintained regularly to ensure that it is always in good working condition. Regular inspections can prevent potential failures of the equipment, reduce the incidence of sudden problems, and improve the reliability and service life of the equipment.
[0119] The present invention can intelligently identify potential abnormalities of the powered trajectory trainer by collecting the operating parameter information of the powered trajectory trainer in real time and using a machine learning model to perform abnormality analysis and processing. This intelligent evaluation method greatly improves the accuracy of the device in the gait guidance and support process, ensures the effectiveness of the patient's gait training, reduces the risk of forming an erroneous gait pattern, and ultimately improves the rehabilitation effect and efficiency.
[0120] After identifying the potential abnormality, the present invention compares the actual gait training pattern with the expected gait training pattern, generates a deviation index based on data comparison, and accurately evaluates the impact of the abnormality on the patient's gait training through the deviation index. When it is found that the powered trajectory trainer has a potential abnormality and affects the gait training, an impact signal is generated and an early warning prompt is issued to notify the patient and medical staff to take timely measures. This can avoid invalid or inefficient gait training caused by failure or abnormality of the powered trajectory trainer and prevent patients from forming wrong gait patterns. In addition, when the potential abnormality of the powered trajectory trainer does not affect the patient's gait training, regular inspection and maintenance can be used to improve the reliability and service life of the powered trajectory trainer, reduce the incidence of sudden problems, ensure that the powered trajectory trainer is always in good working condition, and ensure the safety of the patient and the rehabilitation effect.
[0121] The present invention provides Figure 2 A rehabilitation therapy device shown includes a power trajectory trainer. The specific process of caring for a patient through the power trajectory trainer is as follows:
[0122] Initialize patient information, specifically input patient information including name, age, medical history, and rehabilitation goals;
[0123] Set the parameters of the dynamic trajectory trainer according to the patient's specific situation;
[0124] The parameters of the dynamic trajectory trainer include force, speed, angle, frequency, etc.;
[0125] Check the status of the powered track trainer to ensure that the equipment is intact, all parts are properly connected, and any necessary calibrations are performed;
[0126] Install the patient on the powered trajectory trainer and adjust the straps and support equipment to ensure the patient is safe and comfortable;
[0127] Start the trainer for initial testing, observe patient response, and adjust device parameters to suit patient abilities and needs;
[0128] Start the formal training program, conduct strength, speed, angle, frequency and other aspects of training according to the set parameters, monitor the patient's status in real time, and collect data through sensors and monitoring systems;
[0129] Collect and record data from each training session, including the patient's movement trajectory, strength output, heart rate, blood pressure, etc., analyze the data, evaluate the patient's progress, and adjust subsequent training plans;
[0130] Provide training feedback to patients to inform them of their progress and adjust the parameters of the trainer and training plan based on the data analysis results;
[0131] At the end of each training session, gradually reduce the intensity of the training, allow the patient to slowly return to a resting state, assist the patient in removing from the equipment, and check their physical condition;
[0132] Clean and inspect equipment to ensure it is ready for the next use.
[0133] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0134] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0135] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0136] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0137] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0139] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0140] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for monitoring the nursing process of rehabilitation physiotherapy equipment, characterized in that: The following steps are involved: During the operation of the dynamic trajectory trainer, the operating parameter information of the dynamic trajectory trainer is collected in real time, and the collected information is pre-processed to improve the data quality; The operating parameter information of the dynamic trajectory trainer includes the mechanical arm motion smoothness information and the center of gravity movement trajectory information, wherein the mechanical arm motion smoothness information refers to the coherence and stability of the motion trajectory of the mechanical arm in the dynamic trajectory trainer during the gait guidance process, and the center of gravity movement trajectory information refers to the trajectory change of the patient's body center of gravity during the movement process when the dynamic trajectory trainer performs gait training; After the preprocessed operating parameter information is processed for abnormality analysis, it is input into the trained machine learning model to identify potential abnormalities of the power trajectory trainer; After the preprocessed robot arm motion smoothness information is subjected to abnormal analysis, the robot arm motion smoothness abnormality index is generated. After the preprocessed center of gravity movement trajectory information is subjected to abnormal analysis, the center of gravity movement trajectory abnormality index is generated. The robot arm motion smoothness abnormality index and the center of gravity movement trajectory abnormality index generated after the abnormal analysis are input into the trained machine learning model to generate a gait training evaluation coefficient. The gait training evaluation coefficient is used to perform an intelligent evaluation of the gait training situation of the power trajectory trainer: After the preprocessed robot arm motion smoothness information is subjected to abnormal analysis, the specific steps for generating the robot arm motion smoothness abnormality index are as follows: In a fixed detection window, the motion trajectory data of the robot arm in the power trajectory trainer is collected in real time, and the motion trajectory data is represented by p(t), wherein p(t) represents the three-dimensional position vector of the robot arm at time t, p(t) = |x(t), y(t), z(t)], x(t) represents the position of the robot arm along the X-axis at time t, y(t) represents the position of the robot arm along the Y-axis at time t, and z(t) represents the position of the robot arm along the Z-axis at time t; Calculate the trajectory difference vector of each time step, and the calculation expression is: Δp(t)=p(t)-p(t-1), where Δp(t) represents the position change vector within the time step Δt; Calculate the curvature of the trajectory at each time step, using the second-order derivative and first-order derivative of the trajectory for calculation. The calculation expression is: Among them, K(t) represents the curvature of the trajectory, v(t) represents the velocity vector at time t, a(t) represents the acceleration vector at time t, ||v(t)×a(t)|| represents the modulus of the product of velocity and acceleration, ||v(t)|| represents the modulus of the velocity vector; The trajectory smoothness evaluation index is calculated using the trajectory curvature and its first-order difference. The calculation expression is: Among them, S(t) represents the trajectory smoothness evaluation index, It represents the first-order derivative of the trajectory curvature, t0 represents the starting time of the fixed detection window, and T represents the total duration of the fixed detection window; Based on the trajectory smoothness evaluation index S(t), the robot motion smoothness abnormality index is calculated, and the calculation expression is: In the formula, Robotic Arm Indicates the abnormal index of smoothness of robot movement, S ref is the reference smoothness evaluation index; After identifying the potential abnormality of the powered trajectory trainer, the actual gait data of the patient during gait training on the powered trajectory trainer is collected in real time, and the actual gait data is recorded and processed using the data acquisition system and gait analysis software to generate the actual gait training pattern map of the patient; Conduct detailed comparison and analysis of the actual gait training pattern and the expected gait training pattern, and identify the deviation between the actual gait and the expected gait through data comparison; The actual gait training pattern is compared and analyzed in detail with the expected gait training pattern. Through data comparison, a deviation index is generated. The steps for generating the deviation index are as follows: Gait parameters are extracted from the actual gait training data and the expected gait training data. Let the actual gait parameter vector be A = {a1, a2, a3, ..., a n }, the expected gait parameter vector is B = {b1, b2, b3, ..., b n }, where n is the number of gait parameters; Calculate the cosine similarity between the actual gait parameter vector A and the expected gait parameter vector H. The calculation expression is: Where A·B represents the dot product of vector A and vector B, ||A|| and ||B|| represent the Euclidean lengths of the two vectors, and Cos Sim represents the cosine similarity between the actual gait parameter vector A and the expected gait parameter vector B; The deviation index is calculated by the cosine similarity of the actual gait parameter vector A and the expected gait parameter vector B. The calculation expression is: Deviation Index =1-Cos Sim , where Deviation Index represents the deviation index; Based on the results of the comparative analysis, evaluate whether the potential abnormalities of the dynamic trajectory trainer have affected the patient's gait training; After identifying the potential abnormality of the powered trajectory trainer, the deviation index generated by the powered trajectory trainer when caring for the patient was compared and analyzed with the pre-set deviation index reference threshold to evaluate whether the potential abnormality of the powered trajectory trainer had an impact on the patient's gait training. The results of the comparison and analysis are as follows: If the deviation index is greater than or equal to the deviation index reference threshold, an impact signal is generated, indicating that the potential abnormality of the power trajectory trainer has affected the patient's gait training, and an early warning prompt is issued for the impact signal to inform the patient and relevant medical personnel; If the deviation index is less than the deviation index reference threshold, a non-impact signal is generated, indicating that the potential abnormality of the powered trajectory trainer has no impact on the patient's gait training.
2. A method for monitoring the nursing process of rehabilitation physiotherapy equipment according to claim 1, characterized in that: The gait training evaluation coefficient generated within the fixed detection window when the powered trajectory trainer is caring for the patient is compared with the pre-set gait training evaluation coefficient reference threshold to identify potential abnormalities of the powered trajectory trainer. The results of the comparison and analysis are as follows: If the gait training evaluation coefficient is greater than or equal to the gait training evaluation coefficient reference threshold, an efficient nursing signal is generated, indicating that the power trajectory trainer can provide efficient nursing care for the patient; If the gait training evaluation coefficient is less than the gait training evaluation coefficient reference threshold, an inefficient care signal is generated, indicating that there are potential abnormal risks when the power trajectory trainer provides care for the patient.
3. A method for monitoring the nursing process of rehabilitation physiotherapy equipment according to claim 2, characterized in that: After identifying a potential abnormality of the powered trajectory trainer, that is, when the powered trajectory trainer generates an inefficient care signal for the patient, the actual gait training pattern map of the patient is generated, and the specific steps are as follows: Real-time collection of patients’ gait data during gait training; The collected gait data is transmitted to a central database or cloud storage system via wired or wireless means; Gait parameters were extracted from the preprocessed data using gait analysis software; The extracted gait parameters are input into the gait analysis software for analysis and processing. Through comprehensive analysis of various gait parameters, an actual gait training pattern map of the patient is generated.
