A method for obtaining and reproducing the trajectory of moxibustion manipulation

Abstract

The present invention discloses a method for obtaining and reproducing the trajectory of moxibustion manipulation, which relates to the technical field of moxibustion treatment. The method includes installing sensors and patient feedback devices, collecting moxibustion environment data and patient information, and dynamically adjusting initial parameters; according to the initial parameters, collecting the moxibustion manipulation trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient, and performing multi-modal data fusion to generate a high-quality trajectory data set, training a machine learning model to obtain a trajectory learning result; combining the trajectory learning result with the moxibustion environment data and patient information to control the moxibustion robot to perform the reproduction of the manipulation trajectory; and evaluating the moxibustion effect and generating a moxibustion report. By integrating a variety of sensors and combining the moxibustion environment data and patient personalized information, the present invention greatly improves the consistency and safety of the moxibustion effect. At the same time, it can automatically adjust the moxibustion parameters according to the real-time feedback of the patient, further improving the comfort of the patient and optimizing the treatment experience.

Description

Technical Field

[0001] The present invention relates to the technical field of moxibustion treatment, and in particular to a method for obtaining and reproducing the trajectory of moxibustion techniques. Background Art

[0002] With the wide application of moxibustion therapy, how to standardize and individualize moxibustion techniques has become an urgent technical problem to be solved. Traditional moxibustion therapy mainly relies on the experience and techniques of moxibustion practitioners. Factors such as the accuracy of techniques, the intensity of moxibustion application, and the duration of moxibustion have a direct impact on the treatment effect. However, the instability of techniques, the interference of environmental factors, and individual differences among patients often lead to inconsistent moxibustion effects.

[0003] Firstly, the current moxibustion technique capture technologies are relatively single, usually relying on single-sensor data and unable to fully reflect the multi-dimensional changes during the moxibustion process. Secondly, the existing moxibustion robots for reproducing techniques usually do not have the ability of dynamic adjustment and cannot be adjusted in a timely manner according to real-time environmental changes and patient feedback, resulting in inflexible operations. In addition, the existing machine learning algorithms have limitations in the accuracy of technique trajectory reproduction and the capture of timing characteristics, especially with weak reproduction ability for complex techniques. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for obtaining and reproducing the trajectory of moxibustion techniques, which solves the problems of high-precision acquisition and reproduction of moxibustion technique trajectories.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for obtaining and reproducing the trajectory of moxibustion techniques, which includes installing sensors and patient feedback devices, collecting moxibustion environment data and patient information, and dynamically adjusting initial parameters;

[0008] According to the initial parameters, perform moxibustion, collect the moxibustion technique trajectory of the moxibustion practitioner, the changes in the moxibustion environment, and the real-time feedback of the patient, and perform multi-modal data fusion to generate a high-quality trajectory data set;

[0009] Utilize the high-quality trajectory data set to train a machine learning model to obtain a trajectory learning result;

[0010] Combine the trajectory learning result with the moxibustion environment data and patient information to control the moxibustion robot to perform technique trajectory reproduction;

[0011] Collect the real-time data during the process of the moxibustion robot performing technique trajectory reproduction, evaluate the moxibustion effect, and generate a moxibustion report.

[0012] As a preferred solution of the method for obtaining and reproducing the moxibustion manipulation trajectory of the present invention, wherein: the sensors include an infrared motion capture instrument, a temperature sensor, a humidity sensor, and a pressure sensor;

[0013] The moxibustion environment data includes temperature and humidity;

[0014] The patient information includes age and skin sensitivity;

[0015] The initial parameters include the burning speed of the moxa stick, the moxibustion time, the manipulation strength, and the distance.

[0016] As a preferred solution of the method for obtaining and reproducing the moxibustion manipulation trajectory of the present invention, wherein: according to the moxibustion environment data and the patient information, the burning time of the moxa stick is dynamically adjusted, expressed as,

[0017]

[0018] wherein, t b represents the adjusted burning time of the moxa stick, t d represents the basic burning time, T t represents the target moxibustion temperature, T e represents the current ambient temperature;

[0019] According to the ambient humidity, the burning speed of the moxa stick is dynamically adjusted, expressed as,

[0020] v b = v d ·exp(-k2·(H e - H o ));

[0021] wherein, v b represents the adjusted burning speed of the moxa stick, v d represents the basic burning speed, k2 represents the humidity adjustment coefficient, H e represents the current ambient humidity, H o represents the optimal humidity range;

[0022] According to the skin sensitivity of the patient, the moxibustion strength is dynamically adjusted, expressed as,

[0023]

[0024] wherein, F a represents the adjusted moxibustion strength, F b represents the basic moxibustion strength, k3 represents the strength adjustment coefficient, S pt represents the skin sensitivity level of the patient, S n represents the standard skin sensitivity;

[0025] According to the patient's age, dynamically adjust the moxibustion distance, expressed as,

[0026] d a = d b + k4·ln(1 + A pt – A n );

[0027] Among them, d a represents the adjusted moxibustion distance, d b represents the basic moxibustion distance, k4 represents the distance adjustment coefficient, A pt represents the patient's age, A n represents the standard age.

[0028] As a preferred solution of the method for obtaining and reproducing the moxibustion manipulation trajectory of the present invention, wherein: according to the initial parameters, perform moxibustion, and collect the moxibustion manipulation trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient, including the following steps,

[0029] When the moxibustion therapist performs moxibustion, use an infrared motion capture device to record the motion trajectory of the moxibustion therapist's hand and the moxa stick in three-dimensional coordinates, and calculate the speed and acceleration of the manipulation according to the position changes;

[0030] Collect environmental data through temperature and humidity sensors, and monitor the temperature change on the skin surface and the change in the burning speed of the moxa stick;

[0031] Receive the patient's subjective feelings of temperature and pain in real time through the feedback device installed on the patient.

[0032] As a preferred solution of the method for obtaining and reproducing the moxibustion manipulation trajectory of the present invention, wherein: perform multi-modal data fusion on the collected moxibustion manipulation trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient to generate a high-quality trajectory data set, including the following steps,

[0033] Use a time synchronization mechanism to align the data collected by different sensors according to the time stamps;

[0034] Through multi-modal data fusion technology, fuse the motion trajectory of the moxibustion therapist's hand and the moxa stick, calculate the speed and acceleration of the manipulation, the temperature change on the skin surface, the change in the burning speed of the moxa stick, and the patient's feedback on temperature and pain, and output a high-quality trajectory data set.

[0035] As a preferred solution of the method for obtaining and reproducing the moxibustion manipulation trajectory of the present invention, wherein: use the high-quality trajectory data set to train a machine learning model to obtain a trajectory learning result, including the following steps,

[0036] Use the outlier detection method based on standard deviation to remove outliers from the high-quality trajectory dataset;

[0037] Use the Kalman filter algorithm to smooth the high-quality trajectory dataset;

[0038] Format the processed high-quality trajectory dataset to obtain multi-dimensional feature vectors;

[0039] Select the long short-term memory network model, input the multi-dimensional feature vectors, use the multi-layer long short-term memory network units to process the time series data, connect the output of the long short-term memory network layer to the fully connected layer to generate predicted trajectory points, and the output layer provides the predicted values for future trajectory points;

[0040] Use the mean squared error as the loss function to calculate the error between the predicted trajectory and the true trajectory of the long short-term memory network model;

[0041] Use the Adam optimizer to train the long short-term memory network model, automatically adjust the learning rate to accelerate convergence, obtain the trained long short-term memory network model, and output the trajectory learning result.

[0042] As a preferred solution of the method for obtaining and reproducing the moxibustion manipulation trajectory described in the present invention, wherein: combine the trajectory learning result with the moxibustion environment data and patient information, and control the moxibustion robot to perform the manipulation trajectory reproduction, including the following steps,

[0043] Load the patient's personalized parameters including skin temperature sensitivity, pain threshold, body part characteristics, and health status parameters;

[0044] Real-time collect the current environmental parameters through the temperature and humidity sensor;

[0045] Combine the patient's personalized parameters and the current environmental parameters with the trajectory learning result to generate three-dimensional coordinates and moxibustion intensity;

[0046] Start the moxibustion robot, control the movement of the moxa stick according to the three-dimensional trajectory, and through the pressure sensor, the moxibustion robot can sense the force applied to the patient's skin surface in real time and adjust according to the patient's feedback and skin temperature;

[0047] During the moxibustion process, monitor the skin temperature and environmental temperature of the moxibustion point through the temperature sensor, and dynamically adjust the height and moxibustion time of the moxa stick according to the temperature change;

[0048] Monitor the patient's real-time subjective feedback through the feedback device, and adjust the manipulation parameters according to the feedback data;

[0049] Monitor the deviation between the trajectory executed by the moxibustion robot in real time and the trajectory predicted by the long short-term memory network model, define a deviation threshold, and detect abnormal situations of the moxibustion robot. When the deviation threshold is exceeded, an alarm will be triggered and the operation will be paused. According to the real-time environmental parameters, personalized parameters, and patient feedback, regenerate the three-dimensional coordinates and moxibustion application intensity, and the moxibustion robot will execute the operation again.

[0050] As a preferred solution of the method for obtaining and reproducing the moxibustion technique trajectory of the present invention, the method includes: collecting real-time data during the reproduction process of the moxibustion robot's technique trajectory, evaluating the moxibustion effect, and generating a moxibustion report, including the following steps.

[0051] After the moxibustion operation is completed, collect various sensor data and patient feedback data during the moxibustion process.

[0052] By comparing the difference between the skin temperature and the target temperature, evaluate whether the temperature during the moxibustion process remains within the ideal range.

[0053] Compare the moxibustion duration with the ideal moxibustion time to evaluate whether the time during the moxibustion process remains within the ideal range.

[0054] According to the patient's pain feedback data, evaluate the patient's pain perception during the moxibustion process.

[0055] Generate a moxibustion report based on the evaluation results of temperature, time, pain perception, and the real-time trajectory of the moxibustion robot.

[0056] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the method for obtaining and reproducing the moxibustion technique trajectory as described in the first aspect of the present invention is implemented.

[0057] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the method for obtaining and reproducing the moxibustion technique trajectory as described in the first aspect of the present invention is implemented.

[0058] The beneficial effects of the present invention are as follows: By integrating an infrared motion capture device, a temperature sensor, a humidity sensor, and a pressure sensor, multi-modal data acquisition of moxibustion techniques can be achieved, covering multi-dimensional factors such as temperature, humidity, and pressure during the moxibustion process. Through the fusion processing of multi-modal data, a high-quality dataset of manipulation trajectories is generated and trained using machine learning algorithms, which can accurately capture the temporal characteristics and dynamic changes of the manipulation. In addition, by combining moxibustion environment data, patient personalized information, and real-time feedback, the present invention can dynamically adjust parameters such as moxibustion intensity, time, and trajectory, ensuring personalization and precision during the moxibustion process, and greatly improving the consistency and safety of the moxibustion effect. At the same time, it can automatically adjust moxibustion parameters according to the patient's real-time feedback, further improving the patient's comfort and optimizing the treatment experience. Brief Description of the Drawings

[0059] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0060] Figure 1 It is a flowchart of the method for obtaining and reproducing the moxibustion manipulation trajectory in Embodiment 1.

[0061] Figure 2 It is a flowchart of the reproduction of the moxibustion robot in Embodiment 1. Detailed Embodiments

[0062] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0063] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0064] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments.

[0065] Embodiment 1, referring to Figure 1 and Figure 2, which is the first embodiment of the present invention. This embodiment provides a method for obtaining and reproducing the trajectory of moxibustion manipulation, including the following steps:

[0066] S1. Install sensors and patient feedback devices, collect moxibustion environment data and patient information, and dynamically adjust initial parameters, including the following steps.

[0067] S1.1. The sensors include an infrared motion capture device, a temperature sensor, a humidity sensor, and a pressure sensor.

[0068] The infrared motion capture device is installed above the moxibustion operation table to ensure that it can cover the entire activity area of the moxibustion therapist's arm. The Mark points of the capture device should be installed on the back of the moxibustion therapist's hand and part of the moxa stick to monitor the three-dimensional motion of the manipulation trajectory.

[0069] The temperature sensor is installed near the moxibustion operation area, preferably in the area close to the patient's skin, so as to be able to monitor the temperature change on the patient's skin surface in real time. Especially near the moxibustion acupoints, this sensor can help the system judge whether the moxibustion temperature is appropriate, and the data will be transmitted to the system in real time.

[0070] The humidity sensor is installed at a suitable position in the moxibustion environment to ensure that it can monitor the change of air humidity in real time. Humidity is an important factor affecting the burning speed of the moxa stick and the moxibustion effect. The system needs to adjust the burning speed of the moxa stick according to the humidity.

[0071] The pressure sensor is installed in the tactile feedback device on the patient's skin surface to monitor the pressure exerted by the moxa stick on the patient's skin. The main function of this sensor is to ensure that the force exerted during moxibustion is not too large to avoid damaging the patient's skin or causing discomfort.

[0072] The patient feedback device is used to monitor the patient's pain perception and temperature perception in real time. The device is installed on the patient's finger or other suitable positions. The patient can feedback pain or discomfort through a slight pressing force, and the feedback data will be transmitted to the system in real time to adjust the moxibustion parameters.

[0073] The moxibustion environment data includes temperature and humidity.

[0074] The patient information includes age and skin sensitivity.

[0075] The initial parameters include the burning speed of the moxa stick, the moxibustion time, the manipulation force, and the distance.

[0076] S1.2. Dynamically adjust the burning time of the moxa stick according to the moxibustion environment data and patient information, expressed as

[0077]

[0078] where tb Denote the burning time of the adjusted moxa stick as t d Denote the basic burning time (such as 10 minutes) as T t Denote the target moxibustion temperature (such as 40 °C) as T e Denote the current ambient temperature

[0079] Dynamically adjust the burning speed of the moxa stick according to the ambient humidity, expressed as

[0080] v b = v d · exp(-k2·(H e - H o ));

[0081] Wherein, v b Denote the adjusted burning speed of the moxa stick as v d Denote the basic burning speed (such as burning 1 gram of moxa stick per minute), k2 denotes the humidity adjustment coefficient (constant value, unit: 1 / %), H e Denote the current ambient humidity as H o Denote the optimal humidity range (such as 40%);

[0082] Dynamically adjust the moxibustion intensity according to the patient's skin sensitivity, expressed as

[0083]

[0084] Wherein, F a Denote the adjusted moxibustion intensity as F b Denote the basic moxibustion intensity (such as 1 Newton), k3 denotes the intensity adjustment coefficient (constant value, dimensionless), S pt Denote the patient's skin sensitivity level (such as a score of 1 - 10) as S n Denote the standard skin sensitivity (such as 5 as the standard value);

[0085] Dynamically adjust the moxibustion distance according to the patient's age, expressed as

[0086] d a = d b + k4·ln(1 + A pt – A n ));

[0087] Wherein, d a Denote the adjusted moxibustion distance as d b Denote the basic moxibustion distance (such as 3 cm), k4 denotes the distance adjustment coefficient (constant value, unit: cm), A pt Denote the patient's age as A n Denote the standard age (such as 30 years);

[0088] Furthermore, the moxibustion distance can also be dynamically adjusted according to the skin surface temperature of the patient, expressed as,

[0089]

[0090] where k1 represents the distance adjustment coefficient (constant value, unit: cm / °C), and T s represents the skin surface temperature of the patient.

[0091] It should be noted that by installing sensors and patient feedback devices, collecting moxibustion environment data and patient information, and dynamically adjusting the initial parameters, multi-dimensional data during the moxibustion process can be obtained, including the moxibustion environment (temperature, humidity, etc.) and patient personalized information (skin sensitivity, age, etc.), and the initial parameters (such as the height of the moxa stick, burning speed, and moxibustion intensity) can be dynamically adjusted according to these data. The environmental data and patient information collected by the sensors provide personalized and real-time basic data support for subsequent moxibustion, ensuring that the parameter settings during the moxibustion process are more accurate and meet the individual needs of the patient. By dynamically adjusting the initial parameters, the system can adapt to the individual differences of different patients and the changes in the moxibustion environment, greatly improving the accuracy and safety of moxibustion, and avoiding discomfort or insufficient curative effect caused by improper manual parameter setting.

[0092] S2. According to the initial parameters, perform moxibustion, collect the moxibustion technique trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient, and perform multi-modal data fusion to generate a high-quality trajectory dataset, including the following steps:

[0093] S2.1. When the moxibustion therapist performs moxibustion, use an infrared motion capture device to record the movement trajectory of the moxibustion therapist's hand and the moxa stick in three-dimensional coordinates, and calculate the speed and acceleration of the technique according to the position changes;

[0094] By calculating the speed and acceleration of the moxibustion therapist's technique, ensure that the dynamic characteristics of the technique can be restored in the machine learning model;

[0095] Furthermore, if the moxibustion technique involves complex rotation or tilt angles, the rotation angle and rotation speed of the moxa stick also need to be recorded;

[0096] Collect environmental data through temperature and humidity sensors to ensure that the impact of environmental changes during moxibustion on the trajectory data can be recorded, and monitor the temperature changes on the skin surface and the changes in the burning speed of the moxa stick;

[0097] Receive the patient's subjective feelings about temperature and pain in real time through the feedback device installed on the patient;

[0098] It should be noted that through the feedback device, patients can feedback at any time whether they feel the moxibustion is too hot or too cold. The temperature perception data feedback by patients will be recorded in real time and compared with the actual skin temperature to ensure that the moxibustion technique is within the comfortable range of patients. Patients can also feedback the pain during the moxibustion process, and the moxibustion intensity or distance will be adjusted according to the pain feedback.

[0099] S2.2. Use the time synchronization mechanism to align the data collected by different sensors according to the timestamps to ensure the temporal consistency of multi-modal data;

[0100] Through the multi-modal data fusion technology, fuse the movement trajectories of the moxibustion therapist's hand and the moxa stick, calculate the speed and acceleration of the technique, the temperature change on the skin surface, the change in the burning speed of the moxa stick, and the patient's feedback on temperature and pain, and output a high-quality trajectory data set.

[0101] It should be noted that multi-sensors are used to simultaneously collect the technique trajectory of the moxibustion therapist, the changes in the moxibustion environment (such as temperature and humidity), and the real-time feedback of patients (such as pain perception), and through the multi-modal data fusion technology, a high-quality moxibustion technique trajectory data set is generated. The multi-modal data fusion technology ensures that data in different dimensions (such as technique trajectory, environmental parameters, and patient feedback) can be synchronized in time and fused to form a multi-dimensional and dynamic trajectory data set. It can not only capture the key techniques during the moxibustion process but also take into account the influence of the environment and patient feedback, making the generated trajectory data set more comprehensive and accurate. This provides a high-quality data basis for the subsequent training of machine learning models to ensure that the model can accurately reproduce the moxibustion technique.

[0102] S3. Use the high-quality trajectory data set to train a machine learning model to obtain the trajectory learning result, including the following steps:

[0103] Use the outlier detection method based on standard deviation to remove the outliers in the high-quality trajectory data set;

[0104] Use the Kalman filter or moving average filter algorithm to smooth the high-quality trajectory data set to reduce noise;

[0105] Format the processed high-quality trajectory data set to obtain a multi-dimensional feature vector;

[0106] Select the long short-term memory network model, input the multi-dimensional feature vector, and use multiple long short-term memory network units to process the time series data to capture the temporal characteristics of the technique trajectory. The output of each long short-term memory network unit is expressed as:

[0107] h t = LSTM(X(t), h t-1 );

[0108] Among them, h t represents the hidden state at the current time step, X(t) represents the multi-dimensional feature vector at time point t, and h t-1 represents the hidden state at the previous time step, and LSTM represents the LSTM layer in the long short-term memory network model;

[0109] The output of the long short-term memory network layer is connected to the fully connected layer to generate the predicted trajectory point, denoted as,

[0110] P pred (t) = W h ·h t + b h ;

[0111] Among them, P pred (t) represents the predicted trajectory point, W h represents the weight matrix of the fully connected layer, and b h represents the bias term;

[0112] The output layer provides the predicted value of the future trajectory point, denoted as,

[0113] P pred (t) = (x pred (t), y pred (t), z pred (t));

[0114] Among them, x pred (t) represents the x-axis coordinate of the trajectory point predicted by the long short-term memory network model at time point t, y pred (t) represents the y-axis coordinate of the trajectory point predicted by the long short-term memory network model at time point t, and z pred (t) represents the z-axis coordinate of the trajectory point predicted by the long short-term memory network model at time point t;

[0115] The mean squared error is used as the loss function to calculate the error between the trajectory predicted by the long short-term memory network model and the true trajectory, denoted as,

[0116]

[0117] Among them, L represents the loss value, P pred (t) represents the trajectory point predicted by the long short-term memory network model at time point t, T represents the total number of time steps, P(t) represents the true trajectory point at time point t, that is, the trajectory point actually collected by the sensor, and ||P pred (t) - P(t)|| represents the Euclidean distance between two points, which is used to measure the spatial distance between the trajectory point predicted by the long short-term memory network model and the true trajectory point;

[0118] The long short-term memory network model is trained using the Adam optimizer (Adaptive Moment Estimation optimizer), which automatically adjusts the learning rate to accelerate convergence, resulting in a trained long short-term memory network model that outputs the trajectory learning result.

[0119] It should be noted that a high-quality dataset generated using multi-modal data is used to train a machine learning model (such as a long short-term memory network, LSTM) to learn the temporal characteristics of the moxibustion manipulation trajectory. After training, the model can predict the trajectory points that conform to the actual moxibustion manipulation. Through the training of the machine learning model, the system can learn the complex manipulation trajectories of moxibustion therapists, including the speed, strength, and variation patterns of the manipulation. This process ensures that the model can extract the optimal trajectory patterns from a large amount of historical data. It can achieve the automated reproduction of moxibustion manipulations and can dynamically adjust the trajectory to ensure ideal moxibustion effects under different moxibustion conditions. The machine learning model can also improve the accuracy of trajectory reproduction through continuous training and optimization, ensuring the standardization and personalization of moxibustion manipulations.

[0120] S4. Combine the trajectory learning result with the moxibustion environment data and patient information to control the moxibustion robot to perform the manipulation trajectory reproduction, including the following steps:

[0121] Load the patient's personalized parameters including skin temperature sensitivity, pain threshold, body part characteristics, and health status parameters;

[0122] Real-time collect the current environmental parameters through a temperature and humidity sensor;

[0123] Combine the patient's personalized parameters and the current environmental parameters with the trajectory learning result to generate three-dimensional coordinates and moxibustion strength;

[0124] Furthermore, the most suitable type of moxibustion manipulation can be selected by evaluating the environmental parameters and personalized parameters. Common manipulations include suspended moxibustion, pecking moxibustion, and wagging moxibustion. Suspended moxibustion is suitable for cases where the skin is sensitive, the pain threshold is low, or the skin of the moxibustion site is relatively thin, with a relatively stable trajectory pattern and small strength control; pecking moxibustion is suitable for parts with a high pain threshold and thick skin, with the characteristics of rapid and frequent contact, a complex trajectory pattern, and large strength; wagging moxibustion is suitable for cases where the skin thickness is medium and the patient's tolerance is high, with the characteristic of a large swing in the trajectory, moderate strength, and is suitable for moxibustion over a large area.

[0125] Start the moxibustion robot, control the movement of the moxa stick according to the three-dimensional trajectory, and through a pressure sensor, the moxibustion robot can continuously sense the force applied to the patient's skin surface and adjust according to the patient's feedback and skin temperature;

[0126] During moxibustion, the skin temperature and ambient temperature at the moxibustion point are monitored through a temperature sensor, and the height of the moxa stick and the moxibustion time are dynamically adjusted according to the temperature change;

[0127] The real-time subjective feedback of the patient (such as temperature perception and pain perception) is monitored through a feedback device, and the manipulation parameters are adjusted according to the feedback data. If the patient feedbacks that the temperature is too high, the distance between the moxa stick and the skin will be automatically increased or the moxibustion time will be shortened. If the patient feedbacks that the pain is strong, the moxibustion intensity will be reduced or the moxibustion trajectory will be changed to avoid sensitive areas;

[0128] The deviation between the trajectory actually executed by the moxibustion robot and the trajectory predicted by the long short-term memory network model is monitored, a deviation threshold is defined, and the moxibustion robot is detected for abnormal situations. When the deviation threshold is exceeded, an alarm will be triggered and the operation will be paused. According to the real-time environmental parameters, personalized parameters and patient feedback, three-dimensional coordinates and moxibustion intensity will be regenerated, and the moxibustion robot will execute the operation again.

[0129] It should be noted that the trajectory learning results are combined with the real-time moxibustion environment data and patient personalized information to generate three-dimensional coordinates and moxibustion intensity, and the manipulation trajectory is reproduced through the moxibustion robot. It can generate personalized three-dimensional trajectories and moxibustion intensity, ensuring that when the moxibustion robot reproduces the moxibustion manipulation, it can be dynamically adjusted according to the real-time feedback of the patient. It ensures that the moxibustion robot can flexibly respond to the changes in the environment and the patient's state during moxibustion, and avoids poor moxibustion effects caused by a single manipulation. By tracking real-time data, the height, intensity and moxibustion time of the moxa stick can be automatically adjusted, greatly improving the personalization and accuracy of moxibustion.

[0130] S5. Collect the real-time data during the reproduction process of the moxibustion robot's manipulation trajectory, evaluate the moxibustion effect, and generate a moxibustion report, including the following steps:

[0131] After the moxibustion operation is completed, collect various sensor data and patient feedback data during moxibustion;

[0132] According to the patient's skin temperature sensitivity level, judge the patient's tolerance to temperature changes, define the target temperature, and evaluate whether the temperature during moxibustion remains within the ideal range by comparing the difference between the skin temperature and the target temperature. If the difference is large (for example, greater than the set tolerance threshold, such as ±2°C), it means that the temperature control is not ideal enough, and the height of the moxa stick or the moxibustion time may need to be adjusted during the next moxibustion;

[0133] Set an ideal moxibustion time according to the patient's personalized parameters, compare the duration of moxibustion with the ideal moxibustion time, and evaluate whether the time during the moxibustion process remains within the ideal range. If the time deviation is too large, adjust the moxibustion strategy according to different situations. When the time is too long, automatically shorten the preset time for the next moxibustion, or end the moxibustion in advance according to the real-time temperature during the moxibustion process. When the time is too short, extend the preset time for the next moxibustion, or extend the burning time of the moxa stick according to the real-time temperature during the moxibustion process;

[0134] According to the patient's pain feedback data, evaluate the patient's pain perception during the moxibustion process to ensure that the manipulation and strength are appropriate, and quantify the feedback into a numerical value (such as a scale of 1-10). If the pain feedback score is low (such as 1-3), it indicates that the moxibustion strength is moderate and the patient feels comfortable. If the pain feedback score is high (such as 7-10), it indicates that the moxibustion strength is too large or the temperature is too high, which may cause discomfort or pain. According to the patient's pain feedback, the moxibustion strength or manipulation trajectory will be adjusted in real time;

[0135] Generate a moxibustion report based on the evaluation results of temperature, time, pain perception, and the real-time trajectory of the moxibustion robot.

[0136] It should be noted that during the process of the moxibustion robot performing manipulation reproduction, a variety of sensor data and the patient's feedback data are collected in real time, and the moxibustion effect is evaluated. Finally, the system generates a detailed moxibustion report. Through real-time data collection, the system can comprehensively monitor and evaluate the temperature, time, moxibustion strength, and patient feedback during the moxibustion process to ensure that the moxibustion effect meets the expectations. In addition, the moxibustion report provides a detailed record of the moxibustion process, which is convenient for subsequent analysis and optimization. It ensures the safety and effectiveness during the moxibustion process and also provides a basis for subsequent treatment. Through the evaluation of the moxibustion process, the system can continuously optimize future moxibustion operations, improve the curative effect, and at the same time provide personalized treatment suggestions for patients, enhancing the patients' trust.

[0137] This embodiment also provides a computer device applicable to the situation of the method for obtaining and reproducing the moxibustion manipulation trajectory, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for obtaining and reproducing the moxibustion manipulation trajectory as proposed in the above embodiment.

[0138] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0139] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for obtaining and reproducing the moxibustion manipulation trajectory as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0140] In summary, by integrating an infrared motion capture device, temperature sensors, humidity sensors, and pressure sensors, the present invention can achieve multi-modal data collection of moxibustion techniques, covering multi-dimensional factors such as temperature, humidity, and pressure during the moxibustion process. Through the fusion processing of multi-modal data, a high-quality dataset of manipulation trajectories is generated and trained using machine learning algorithms, enabling accurate capture of the temporal characteristics and dynamic changes of the manipulation. In addition, by combining moxibustion environment data, patient-specific information, and real-time feedback, the present invention can dynamically adjust parameters such as moxibustion intensity, time, and trajectory to ensure personalization and precision during the moxibustion process, greatly improving the consistency and safety of the moxibustion effect. At the same time, the system can automatically adjust moxibustion parameters based on the patient's real-time feedback, further improving the patient's comfort and optimizing the treatment experience.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for obtaining and reproducing the moxibustion manipulation trajectory; The method for obtaining and reproducing the moxibustion manipulation trajectory includes the following steps, Install sensors and patient feedback devices, collect moxibustion environment data and patient information, and dynamically adjust the initial parameters; The moxibustion environment data includes temperature and humidity; According to the moxibustion environment data and patient information, dynamically adjust the burning time of the moxa stick, expressed as, Among them, t b represents the burning time of the adjusted moxa stick, and t d represents the basic burning time, and T t represents the target moxibustion temperature, and T e represents the current ambient temperature; According to the environmental humidity, dynamically adjust the burning speed of the moxa stick, expressed as, v b = v d · exp(-k2·(H e - H o )); Among them, v b represents the burning speed of the adjusted moxa stick, v d represents the basic burning speed, k2 represents the humidity adjustment coefficient, H e represents the current ambient humidity, H o represents the optimal humidity range; According to the initial parameters, perform moxibustion, collect the moxibustion manipulation trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient, and perform multi-modal data fusion to generate a high-quality trajectory dataset; Use the high-quality trajectory dataset to train a machine learning model to obtain a trajectory learning result; Combine the trajectory learning result with the moxibustion environment data and patient information to control the moxibustion robot to perform manipulation trajectory reproduction; Collect the real-time data during the process of the moxibustion robot performing manipulation trajectory reproduction, evaluate the moxibustion effect, and generate a moxibustion report.

2. The computer device according to claim 1, characterized in that: The sensors include an infrared motion capture device, a temperature sensor, a humidity sensor, and a pressure sensor; The patient information includes age and skin sensitivity; The initial parameters include the burning speed of the moxa stick, the moxibustion time, the manipulation force, and the distance.

3. The computer device according to claim 2, characterized in that: According to the skin sensitivity of the patient, dynamically adjust the moxibustion force, expressed as, Among them, F a represents the adjusted moxibustion intensity, F b represents the basic moxibustion intensity, k3 represents the intensity adjustment coefficient, S pt represents the patient's skin sensitivity level, S n represents the standard skin sensitivity; According to the patient's age, dynamically adjust the moxibustion distance, expressed as, d a = d b + k4·ln(1 + A pt - A n ); Among them, d a represents the adjusted moxibustion distance, d b represents the basic moxibustion distance, k4 represents the distance adjustment coefficient, A pt represents the age of the patient, A n represents the standard age.

4. The computer device according to claim 3, wherein: According to the initial parameters, perform moxibustion, collect the moxibustion manipulation trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient, including the following steps, When the moxibustion therapist performs moxibustion, use the infrared motion capture device to record the motion trajectory of the moxibustion therapist's hand and the moxa stick in three-dimensional coordinates, and calculate the speed and acceleration of the manipulation according to the position changes; Collect environmental data through temperature and humidity sensors, and monitor the temperature changes on the skin surface and the changes in the burning speed of the moxa stick; Through the feedback device installed on the patient, receive the patient's subjective feelings about temperature and pain in real time.

5. The computer device according to claim 4, characterized in that: Perform multi-modal data fusion on the collected moxibustion manipulation trajectory of the moxibustion therapist, the changes in the moxibustion environment, and the real-time feedback of the patient to generate a high-quality trajectory dataset, including the following steps, Use a time synchronization mechanism to align the data collected by different sensors according to timestamps; Through multi-modal data fusion technology, fuse the motion trajectory of the moxibustion therapist's hand and the moxa stick, the calculated speed and acceleration of the manipulation, the temperature changes on the skin surface, the changes in the burning speed of the moxa stick, and the patient's feedback on temperature and pain, and output a high-quality trajectory dataset.

6. The computer device according to claim 5, characterized in that: Use the high-quality trajectory dataset to train a machine learning model to obtain a trajectory learning result, including the following steps, Use an outlier detection method based on standard deviation to remove outliers in the high-quality trajectory dataset; Use the Kalman filter algorithm to smooth the high-quality trajectory dataset; Format the processed high-quality trajectory dataset to obtain a multi-dimensional feature vector; Select a long short-term memory network model, input a multi-dimensional feature vector, use multiple layers of long short-term memory network units to process time series data, connect the output of the long short-term memory network layer to a fully connected layer to generate predicted trajectory points, and the output layer provides predicted values for future trajectory points; Use the mean squared error as the loss function to calculate the error between the predicted trajectory of the long short-term memory network model and the true trajectory; Use the Adam optimizer to train the long short-term memory network model, automatically adjust the learning rate to accelerate convergence, obtain the trained long short-term memory network model, and output the trajectory learning result.

7. The computer device according to claim 6, characterized in that: Combine the trajectory learning result with the moxibustion environment data and patient information to control the moxibustion robot to perform manual trajectory reproduction, including the following steps Load the patient's personalized parameters including skin temperature sensitivity, pain threshold, body part characteristics, and health status parameters; Through the temperature and humidity sensor, collect the current environmental parameters in real time; Combine the patient's personalized parameters and the current environmental parameters with the trajectory learning result to generate three-dimensional coordinates and moxibustion intensity; Start the moxibustion robot, control the movement of the moxa stick according to the three-dimensional trajectory, and through the pressure sensor, the moxibustion robot can sense the force applied to the patient's skin surface in real time and adjust according to the patient's feedback and skin temperature; During moxibustion, monitor the skin temperature and environmental temperature at the moxibustion point through the temperature sensor, and dynamically adjust the height of the moxa stick and the moxibustion time according to the temperature change; Monitor the patient's real-time subjective feedback through the feedback device and adjust the manual parameters according to the feedback data; Monitor the deviation between the trajectory actually executed by the moxibustion robot and the trajectory predicted by the long short-term memory network model, define a deviation threshold, detect abnormal conditions of the moxibustion robot, and when the deviation threshold is exceeded, an alarm will be triggered and the operation will be paused. According to the real-time environmental parameters, personalized parameters and patient feedback, regenerate the three-dimensional coordinates and moxibustion intensity, and the moxibustion robot will execute the operation again.

8. The computer device according to claim 7, characterized in that: Collect the real-time data during the process of the moxibustion robot performing manual trajectory reproduction, evaluate the moxibustion effect, and generate a moxibustion report, including the following steps After the moxibustion operation is completed, collect various sensor data and patient feedback data during moxibustion; By comparing the difference between the skin temperature and the target temperature, evaluate whether the temperature during moxibustion remains within the ideal range; Compare the moxibustion duration with the ideal moxibustion time to evaluate whether the time during moxibustion remains within the ideal range; According to the patient's pain feedback data, evaluate the patient's pain perception during moxibustion; Generate a moxibustion report according to the evaluation results of temperature, time, pain perception and the real-time trajectory of the moxibustion robot.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method for obtaining and reproducing the moxibustion manipulation trajectory described in claim 1.

Images