CN113470820A - Intelligent control method for moxibustion robot - Google Patents
Intelligent control method for moxibustion robot Download PDFInfo
- Publication number
- CN113470820A CN113470820A CN202110979799.3A CN202110979799A CN113470820A CN 113470820 A CN113470820 A CN 113470820A CN 202110979799 A CN202110979799 A CN 202110979799A CN 113470820 A CN113470820 A CN 113470820A
- Authority
- CN
- China
- Prior art keywords
- moxibustion
- patient
- tongue
- temperature
- acupuncture point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H39/00—Devices for locating or stimulating specific reflex points of the body for physical therapy, e.g. acupuncture
- A61H39/02—Devices for locating such points
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H39/00—Devices for locating or stimulating specific reflex points of the body for physical therapy, e.g. acupuncture
- A61H39/06—Devices for heating or cooling such points within cell-life limits
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/16—Physical interface with patient
- A61H2201/1657—Movement of interface, i.e. force application means
- A61H2201/1659—Free spatial automatic movement of interface within a working area, e.g. Robot
Landscapes
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Rehabilitation Therapy (AREA)
- Epidemiology (AREA)
- Engineering & Computer Science (AREA)
- Physical Education & Sports Medicine (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Pain & Pain Management (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Finger-Pressure Massage (AREA)
Abstract
The invention discloses an intelligent control method of a moxibustion robot, S1, a camera special for an instrument is used for shooting face and tongue images of a patient at a specified shooting position, a radio device is used for sampling sound signals of the patient, according to a diagnosis model, the face and tongue images and the difference of the sound signals under different body conditions are analyzed, and by combining mobile phone code scanning or man-machine interaction, the patient is subjected to inspection, tongue diagnosis, auscultation and inquiry according to the obtained face and tongue image samples, the obtained sound signals and the result of man-machine interaction questionnaire survey, so that the body health condition information of the patient is obtained; s2, according to the health condition information of the patient, the position and posture information of the moxibustion acupuncture points is determined through a depth camera and an automatic acupuncture point searching algorithm, and the moxibustion robot is controlled to grab the moxibustion box and move to the moxibustion acupuncture points to perform moxibustion; s3, the temperature of the acupuncture point of the human body receiving moxibustion is monitored in real time in the moxibustion process, and the temperature of the acupuncture point of the moxibustion is controlled within a set range.
Description
Technical Field
The invention relates to a moxibustion robot, in particular to an intelligent control method of a moxibustion robot.
Background
At present, moxibustion modes at home and abroad can be divided into manual moxibustion and semi-automatic moxibustion, wherein the manual moxibustion refers to that medical workers hold moxa sticks by hands or use moxibustion boxes to perform moxibustion by moxibustion techniques (mild moxibustion, sparrow pecking moxibustion, rotary moxibustion and the like). Semi-automatic refers to medical personnel and uses moxibustion instrument, manual adjustment moxibustion instrument or arm, makes it carry out the moxa-moxibustion treatment at appointed yu acupuncture point. The moxibustion instrument appearing on the market at present lacks the functions of inspection, inquiry and auscultation, and the function of moxibustion by automatically searching acupuncture points without manual intervention, and also needs to rely on the experience of doctors in the aspect of temperature control, so that the moxibustion robot has a great development space in the technology.
Machine learning and deep learning techniques are developed increasingly, a computer summarizes rules from data to generate a model through steps of collecting data, preprocessing the data, learning characteristic engineering, training and testing the model, the model is used for predicting the data, and the computer can be applied to automatic diagnosis and automatic acupoint searching in the research.
Disclosure of Invention
The invention aims to provide an intelligent control method of a moxibustion robot.
In order to achieve the purpose, the invention can adopt the following technical scheme:
the intelligent control method of the moxibustion robot comprises the following steps:
s1, using a camera special for an instrument to shoot face and tongue images of a patient at a designated shooting position, using a radio to sample sound signals of the patient, analyzing the difference of the face and tongue images and the sound signals under different body conditions according to a diagnosis model, combining mobile phone code scanning or man-machine interaction (voice + touch display screen function), and performing inspection, tongue inspection, auscultation and inquiry on the patient according to the acquired face and tongue image samples, the acquired sound signals and the results of the man-machine interaction questionnaire so as to acquire the body health condition information of the patient;
s2, determining the pose information of moxibustion acupuncture points through a depth camera and an automatic acupuncture point finding algorithm according to the health condition information of the patient and combining with the Chinese medicine acupuncture point theory, and controlling the mechanical arm of the moxibustion robot to grab the moxibustion box and move to the moxibustion acupuncture points for moxibustion;
s3, the temperature of the acupuncture point of the human body receiving moxibustion is monitored in real time in the moxibustion process, and the mechanical arm is controlled to adjust the distance between the moxibustion box and the acupuncture point of the human body, so that the temperature of the acupuncture point of the moxibustion is controlled within a set range.
In step S1, the training method of the diagnostic model establishes a use file for each user by using the identification number as a feature; when a user swipes a card for use, firstly, judging whether the user is a new user, newly building an archive for the new user, calling an original archive for an old user, and then, carrying out the following steps:
s1.1, the inspection analysis method comprises the following steps:
s1.1.1, extracting a color feature RGB (red, green and blue) graph of the face image sample, converting the RGB graph into a YCbCr graph, determining a distribution area of naked skin on the face, calculating an average RGB value, converting the RGB graph into an HSV (hue, saturation, value) graph and a lip color feature YIQ (hue, saturation, lightness) graph, and judging the face color feature in an auxiliary manner;
s1.1.2, analyzing data characteristics of the RGB map, the HSV map and the YIQ map by using a deep learning method, and then training by using a BP neural network sample to obtain various face color information models;
s1.2, the tongue diagnosis analysis method comprises the following steps:
s1.2.1, separating tongue pictures by adopting an edge detection algorithm, designating effective edges, and separating tongue pictures by using traversal and recursion;
s1.2.2, acquiring RGB information of the tongue image, processing the RGB information into HSV information, and determining the tongue color type according to HSV value;
s1.2.3, calculating texture features by using a multiple reference model, and measuring the small tongue image area and the large roughness of the texture elements so as to distinguish cracks, old tender and smooth tongues;
s1.2.4, outputting a tongue color and texture result;
s1.2.5, combining the theory of traditional Chinese medicine, and using the cluster analysis method to give the Chinese medicine symptoms of the testee according to the obtained characteristics of the facial diagnosis and the tongue diagnosis.
S1.3, the auscultation analysis method comprises the following steps:
s1.3.1, recording sound signal of specific content under health condition after user establishes file;
s1.3.2, recording the sound signal of the user with specific content, comparing with the sound signal recorded under health condition, and extracting the tone and tone attribute by inductive analysis;
s1.3.3, judging corresponding Chinese medicine symptoms based on a clustering analysis method by combining the Chinese medicine theory according to different tone and tone attribute characteristics;
s1.4, the method for inquiry analysis comprises the following steps:
s1.4.1, using mobile phone code scanning or man-machine interaction, the user expresses specific symptoms of physical discomfort or health care requirements in the form of questionnaires;
s1.4.2, according to the user responses, combining with the inquiry of traditional Chinese medicine, judging traditional Chinese medicine symptoms, and based on traditional Chinese medicine symptoms obtained by facial diagnosis, tongue diagnosis, auscultation and inquiry, adopting a cluster analysis method to give specific moxibustion application method of moxibustion, target acupuncture points, moxibustion application temperature and moxibustion time parameters, and sending the parameters to the moxibustion robot, thereby realizing the autonomous moxibustion treatment of the moxibustion robot.
In step S2, the step of determining the position of the moxibustion acupuncture point of the patient includes:
s2.1.1, according to the diagnosis result and the requirement of the patient, the moxibustion robot plans the target moxibustion acupuncture point, and uses voice + touch display screen to display and guide the user to take off clothes, and uses screen display to display the appointed posture to prepare the moxibustion treatment;
s2.1.2, scanning the three-dimensional posture of the human skeleton by using a depth camera, determining a target moxibustion acupoint group, and positioning the moxibustion acupoint group;
the automatic acupoint searching algorithm comprises the following steps:
s2.2.1, dividing the human body acupuncture point distribution into seven acupuncture point groups by using a skeleton model: 1, head and upper back; 2, lower back and waist; 3, chest and abdomen; 4, the front surfaces of the left arm and the right arm; 5, back surfaces of the left arm and the right arm; 6, the front surfaces of the left leg and the right leg; 7, back surfaces of the left leg and the right leg;
s2.2.2, designing different characteristic algorithms for each acupoint group, determining two to three characteristic points in the acupoint group, then determining the positions of the acupoints according to the distribution relationship of the selected characteristic points and the acupoints, adjusting the positioning position in real time along with the micromotion of the patient, and transmitting the coordinates of the positioning position back to the mechanical arm control system;
s2.2.3, the mechanical arm searches for acupuncture points according to the returned positioning position coordinates, updates moxibustion positions according to the returned refreshing coordinates which are refreshed continuously, and performs moxibustion of a rotary moxibustion method, a spiral moxibustion method, a suspension moxibustion method and a sparrow-pecking moxibustion method on the acupuncture points according to the designed motion trail of the mechanical arm;
s2.2.4, when the moxibustion robot finishes moxibustion on the target acupoints, the robot reminds the patient with voice and moxibustion the next target acupoints in turn, and after the treatment is finished, the treatment record is written into the file.
In step S3, the real-time monitoring of the temperature of the moxibustion acupoint during moxibustion includes the following steps:
s3.1, based on the determined health requirements of the patient and the target acupuncture points, setting a temperature range for moxibustion application of the moxibustion acupuncture points by the user through a touch display screen;
s3.2, measuring the temperature of the moxibustion acupuncture points of the patient in real time by using an infrared temperature measuring device arranged beside the moxibustion box at the front end of the mechanical arm, and transmitting the measured real-time acupuncture point temperature to a mechanical arm control system after the temperature of the moxibustion reaches a preset temperature interval for a period of time;
s3.3, when the infrared temperature detector detects that the temperature of the moxibustion acupuncture point is higher than the upper limit of the preset centigrade, the mechanical arm control system controls the mechanical arm to slightly leave away from the moxibustion acupuncture point; when the infrared temperature detector detects that the temperature of the moxibustion acupuncture point is lower than the lower limit of the preset temperature, the mechanical arm control system controls the mechanical arm to be slightly close to the moxibustion acupuncture point, so that the temperature of the moxibustion treatment part is controlled within a preset temperature range;
and S3.4, monitoring and measuring the distance between the moxibustion box and the skin of the human body in real time through the camera, and ensuring the moxibustion application safety of the moxibustion robot.
According to the invention, facial features of various different complexions are trained, the trained complexion diagnosis model can identify the complexion of the patient, the complexion of the patient is analyzed, common health problems corresponding to the different complexions are displayed on a screen, the health condition of the patient is inquired through voice, a target treatment acupoint is selected, and targeted moxibustion treatment is performed on the patient. And guides the patient to make a treatment posture, the positions of acupuncture points in a three-dimensional space are determined through the distribution positions of the acupuncture points in different previously trained treatment postures, and the mechanical arms of the moxibustion robot automatically find acupuncture points according to the positioning to start moxibustion. In the moxibustion treatment process, the temperature detection system works to detect the temperature of moxibustion acupuncture points in real time, and the distance between the moxibustion box and the acupuncture points to be treated is adjusted by the mechanical arm, so that the temperature of the acupuncture points to be treated is kept within a set temperature range.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a flow chart of the inspection analysis method of the present invention.
FIG. 3 is a flow chart of the tongue analysis method of the present invention.
Fig. 4 is a flow chart of the auscultation analysis method of the present invention.
FIG. 5 is a flow chart of an interrogation analysis method according to the present invention.
Fig. 6 is a schematic view of the moxibustion robot of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. It should be noted that all the directional indicators (such as up, down, left, right, front, and rear … …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicator is changed accordingly.
As shown in fig. 1-6, the intelligent control method of the moxibustion robot of the invention comprises the following steps:
s1, operating the special instrument camera 3 on the mechanical arm 2 of the moxibustion robot 1 to shoot the face and tongue images of the patient at the appointed shooting position, and performing inspection, tongue diagnosis, auscultation and inquiry on the patient according to the acquired face and tongue image sample model of the Chinese by analyzing the face and tongue images and the functions of voice and touch display screen according to the face color diagnosis model to acquire the health condition information of the patient;
s2, determining the position of a moxibustion acupuncture point through a depth camera and an automatic acupuncture point searching algorithm according to the health condition information of the patient, and controlling the mechanical arm 2 of the moxibustion robot 1 to grab the moxibustion box 4 and move to the moxibustion acupuncture point for moxibustion;
and S3, monitoring the temperature of the moxibustion acupuncture points in real time in the moxibustion process, and controlling the mechanical arm 2 to adjust the moxibustion distance so that the temperature of the moxibustion acupuncture points is controlled within a set temperature range.
In step S1, the training method of the diagnostic model establishes a use file for each user by using the identification number as a feature; when a user swipes a card for use, firstly, judging whether the user is a new user, newly building an archive for the new user, calling an original archive for an old user, and then, carrying out the following steps:
s1.1, the inspection analysis method, as shown in figure 2, comprises the following steps:
s1.1.1, extracting a color feature RGB (red, green and blue) graph of the face image sample, converting the RGB graph into a YCbCr graph, determining a distribution area of naked skin on the face, calculating an average RGB value, converting the RGB graph into an HSV (hue, saturation, value) graph and a lip color feature YIQ (hue, saturation, lightness) graph, and judging the face color feature in an auxiliary manner;
s1.1.2, analyzing data characteristics of the RGB map, the HSV map and the YIQ map by using a deep learning method, and then training by using a BP neural network sample to obtain various face color information models;
s1.2, the tongue diagnosis analysis method comprises the following steps as shown in figure 3:
s1.2.1, separating tongue pictures by adopting an edge detection algorithm, designating effective edges, and separating tongue pictures by using traversal and recursion;
s1.2.2, acquiring RGB information of the tongue image, processing the RGB information into HSV information, and determining the tongue color type according to HSV value;
s1.2.3, calculating texture features by using a multiple reference model, and measuring the small tongue image area and the large roughness of the texture elements so as to distinguish cracks, old tender and smooth tongues;
s1.2.4, outputting a tongue color and texture result;
s1.2.5, combining the theory of traditional Chinese medicine, and using the cluster analysis method to give the Chinese medicine symptoms of the testee according to the obtained characteristics of the facial diagnosis and the tongue diagnosis.
S1.3, the auscultation analysis method, as shown in FIG. 4, comprises the following steps:
s1.3.1, recording sound signal of specific content under health condition after user establishes file;
s1.3.2, recording the sound signal of the user with specific content, comparing with the sound signal recorded under the health condition, and extracting the tone and tone attribute by inductive analysis method;
s1.3.3, judging corresponding Chinese medicine symptoms based on a clustering analysis method by combining the Chinese medicine theory according to different tone and tone attribute characteristics;
s1.4, the method for the inquiry analysis, as shown in FIG. 5, comprises the following steps:
s1.4.1, using mobile phone code scanning or man-machine interaction, the user expresses specific symptoms of physical discomfort or health care requirements in the form of questionnaires;
s1.4.2, according to the user responses, combining with the inquiry of traditional Chinese medicine, judging traditional Chinese medicine symptoms, and based on traditional Chinese medicine symptoms obtained by facial diagnosis, tongue diagnosis, auscultation and inquiry, adopting a cluster analysis method to give specific moxibustion application method of moxibustion, target acupuncture points, moxibustion application temperature and moxibustion time parameters, and sending the parameters to the moxibustion robot, thereby realizing the autonomous moxibustion treatment of the moxibustion robot.
In step S2, the step of determining the position of the moxibustion acupuncture point of the patient includes:
s2.1.1, according to the diagnosis result and the requirement of the patient, the moxibustion robot 1 plans the target moxibustion acupuncture point, and uses voice + touch display screen to display and guide the user to take off clothes, and uses the screen to display the appointed posture to prepare the moxibustion treatment;
s2.1.2, scanning the three-dimensional posture of the human skeleton by using a depth camera, determining a target moxibustion acupoint group, and positioning the moxibustion acupoint group;
the automatic acupoint searching algorithm comprises the following steps:
s2.2.1, dividing the human body acupuncture point distribution into seven acupuncture point groups by using a skeleton model: 1, head and upper back; 2, lower back and waist; 3, chest and abdomen; 4, the front surfaces of the left arm and the right arm; 5, back surfaces of the left arm and the right arm; 6, the front surfaces of the left leg and the right leg; 7, back surfaces of the left leg and the right leg;
s2.2.2, designing different characteristic algorithms for each acupoint group, determining two to three characteristic points in the acupoint group, then determining the positions of the acupoints according to the distribution relationship of the selected characteristic points and the acupoints, adjusting the positioning position in real time along with the micromotion of the patient, and transmitting the coordinates of the positioning position back to the mechanical arm control system;
s2.2.3, the mechanical arm 2 searches for acupuncture points according to the returned positioning position coordinates, updates moxibustion positions according to the returned refreshing coordinates which are refreshed continuously, and executes moxibustion of rotating moxibustion, spiral moxibustion, suspension moxibustion and sparrow-pecking moxibustion techniques on the acupuncture points according to the designed motion track of the mechanical arm 2;
s2.2.4, after the moxibustion robot 1 finishes moxibustion on the target acupoints, it will remind the user with voice and moxibustion the next target acupoints in turn, and after the treatment is finished, the record of treatment will be written into the file.
In step S3, the real-time monitoring of the temperature of the moxibustion acupoint during moxibustion includes the following steps:
s3.1, based on the determined health requirements of the patient and the target acupuncture points, setting a temperature range for moxibustion application of the moxibustion acupuncture points by the user through a touch display screen;
s3.2, measuring the temperature of the moxibustion acupuncture points of the patient in real time by using an infrared temperature measuring device 5 arranged beside a moxibustion box 4 at the front end of the mechanical arm 2, and transmitting the measured real-time acupuncture point temperature to a mechanical arm control system after the temperature of the moxibustion reaches a preset temperature interval for a period of time;
s3.3, when the infrared temperature detector 5 detects that the temperature of the moxibustion acupuncture points is higher than the preset upper temperature limit, the mechanical arm control system controls the mechanical arm 2 to slightly keep away from the moxibustion acupuncture points; when the infrared temperature detector 5 detects that the temperature of the moxibustion acupuncture point is lower than the preset lower temperature limit, the mechanical arm control system controls the mechanical arm 2 to be slightly close to the moxibustion acupuncture point, so that the temperature of the moxibustion treatment part is controlled within a preset temperature interval;
and S3.4, monitoring and measuring the distance between the moxibustion box 4 and the skin of the human body in real time through a camera, and ensuring the moxibustion safety of the moxibustion robot 1.
Claims (5)
1. An intelligent control method for a moxibustion robot is characterized by comprising the following steps:
s1, using a camera special for an instrument to shoot the face and tongue images of the patient at the appointed shooting position and using radio equipment to sample the sound signals of the patient, analyzing the difference of the shown face and tongue images and the sound signals under different body conditions according to a diagnosis model, combining mobile phone code scanning or man-machine interaction, and carrying out inspection, tongue inspection, auscultation and inquiry on the patient according to the obtained face and tongue image samples, the obtained sound signals and the results of the man-machine interaction questionnaire survey of Chinese people to obtain the body health condition information of the patient;
s2, determining the pose information of moxibustion acupuncture points through a depth camera and an automatic acupuncture point finding algorithm according to the health condition information of the patient and combining with the Chinese medicine acupuncture point theory, and controlling the mechanical arm of the moxibustion robot to grab the moxibustion box and move to the moxibustion acupuncture points for moxibustion;
s3, the temperature of the acupuncture point of the human body receiving moxibustion is monitored in real time in the moxibustion process, and the mechanical arm is controlled to adjust the distance between the moxibustion box and the acupuncture point of the human body, so that the temperature of the acupuncture point of the moxibustion is controlled within a set range.
2. An intelligent control method for moxibustion robot as claimed in claim 1, wherein in S1, the diagnostic model training method is characterized by identity card number and establishes a usage file for each user; when a user swipes a card for use, firstly, judging whether the user is a new user, newly building an archive for the new user, calling an original archive for an old user, and then, carrying out the following steps:
s1.1, the inspection analysis method comprises the following steps:
s1.1.1, extracting a color feature RGB (red, green and blue) graph of the face image sample, converting the RGB graph into a YCbCr graph, determining a distribution area of naked skin on the face, calculating an average RGB value, converting the RGB graph into an HSV (hue, saturation, value) graph and a lip color feature YIQ (hue, saturation, lightness) graph, and judging the face color feature in an auxiliary manner;
s1.1.2, analyzing the data characteristics of the RGB map, HSV map and YIQ map by using a deep learning method, and then training by using a BP neural network sample to obtain various face color information models;
s1.2, the tongue diagnosis analysis method comprises the following steps:
s1.2.1, separating tongue pictures by adopting an edge detection algorithm, designating effective edges, and separating tongue pictures by using traversal and recursion;
s1.2.2, acquiring RGB information of the tongue image, processing the RGB information into HSV information, and determining the tongue color type according to HSV value;
s1.2.3, calculating texture features by using a multiple reference model, and measuring the small tongue image area and the large roughness of the texture elements so as to distinguish cracks, old tender and smooth tongues;
s1.2.4, outputting a tongue color and texture result;
s1.2.5, combining the theory of traditional Chinese medicine, and using the cluster analysis method to give the Chinese medicine symptoms of the testee according to the obtained characteristics of the facial diagnosis and the tongue diagnosis.
3. The moxibustion robot intelligent control method according to claim 1,
s1.3, the auscultation analysis method comprises the following steps:
s1.3.1, recording sound signal of specific content under health condition after user establishes file;
s1.3.2, recording the sound signal of the user with specific content, comparing with the sound signal recorded under health condition, and extracting the tone and tone attribute by inductive analysis;
s1.3.3, judging corresponding Chinese medicine symptoms based on a clustering analysis method by combining the Chinese medicine theory according to different tone and tone attribute characteristics;
s1.4, the method for inquiry analysis comprises the following steps:
s1.4.1, using mobile phone code scanning or man-machine interaction, the user expresses specific symptoms of physical discomfort or health care requirements in the form of questionnaires;
s1.4.2, according to the user responses, combining with the inquiry of traditional Chinese medicine, judging traditional Chinese medicine symptoms, and based on traditional Chinese medicine symptoms obtained by facial diagnosis, tongue diagnosis, auscultation and inquiry, adopting a cluster analysis method to give specific moxibustion application method of moxibustion, target acupuncture points, moxibustion application temperature and moxibustion time parameters, and sending the parameters to the moxibustion robot, thereby realizing the autonomous moxibustion treatment of the moxibustion robot.
4. The moxibustion robot intelligent control method of claim 1, wherein in S2, the step of determining the position of the moxibustion acupoint on which the patient is subjected comprises:
s2.1.1, according to the diagnosis result and the requirement of the patient, the moxibustion robot plans the target moxibustion acupuncture point, and uses voice + touch display screen to display and guide the user to take off clothes, and uses screen display to display the appointed posture to prepare the moxibustion treatment;
s2.1.2, scanning the three-dimensional posture of the human skeleton by using a depth camera, determining a target moxibustion acupoint group, and positioning the moxibustion acupoint group;
the automatic acupoint searching algorithm comprises the following steps:
s2.2.1, dividing the human body acupuncture point distribution into seven acupuncture point groups by using a skeleton model: 1, head and upper back; 2, lower back and waist; 3, chest and abdomen; 4, the front surfaces of the left arm and the right arm; 5, back surfaces of the left arm and the right arm; 6, the front surfaces of the left leg and the right leg; 7, back surfaces of the left leg and the right leg;
s2.2.2, designing different characteristic algorithms for each acupoint group, determining two to three characteristic points in the acupoint group, then determining the positions of the acupoints according to the distribution relationship of the selected characteristic points and the acupoints, adjusting the positioning position in real time along with the micromotion of the patient, and transmitting the coordinates of the positioning position back to the mechanical arm control system;
s2.2.3, the mechanical arm searches for acupuncture points according to the returned positioning position coordinates, updates moxibustion positions according to the returned refreshing coordinates which are refreshed continuously, and performs moxibustion of a rotary moxibustion method, a spiral moxibustion method, a suspension moxibustion method and a sparrow-pecking moxibustion method on the acupuncture points according to the designed motion trail of the mechanical arm;
s2.2.4, when the moxibustion robot finishes moxibustion on the target acupoints, the robot reminds the patient with voice and moxibustion the next target acupoints in turn, and after the treatment is finished, the treatment record is written into the file.
5. The intelligent control method of moxibustion robot of claim 1, wherein in step S3, the real-time monitoring of the temperature at the moxibustion acupoint during moxibustion comprises the following steps:
s3.1, based on the determined health requirements of the patient and the target acupuncture points, setting a temperature range for moxibustion application of the moxibustion acupuncture points by the user through a touch display screen;
s3.2, measuring the temperature of the moxibustion acupuncture points of the patient in real time by using an infrared temperature measuring device arranged beside the moxibustion box at the front end of the mechanical arm, and transmitting the measured real-time acupuncture point temperature to a mechanical arm control system after the temperature of the moxibustion reaches a preset temperature interval for a period of time;
s3.3, when the infrared temperature detector detects that the temperature of the moxibustion acupuncture point is higher than the upper limit of the preset centigrade, the mechanical arm control system controls the mechanical arm to slightly leave away from the moxibustion acupuncture point; when the infrared temperature detector detects that the temperature of the moxibustion acupuncture point is lower than the lower limit of the preset temperature, the mechanical arm control system controls the mechanical arm to be slightly close to the moxibustion acupuncture point, so that the temperature of the moxibustion treatment part is controlled within a preset temperature range;
and S3.4, monitoring and measuring the distance between the moxibustion box and the skin of the human body in real time through the camera, and ensuring the moxibustion application safety of the moxibustion robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110979799.3A CN113470820A (en) | 2021-08-25 | 2021-08-25 | Intelligent control method for moxibustion robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110979799.3A CN113470820A (en) | 2021-08-25 | 2021-08-25 | Intelligent control method for moxibustion robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113470820A true CN113470820A (en) | 2021-10-01 |
Family
ID=77868001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110979799.3A Pending CN113470820A (en) | 2021-08-25 | 2021-08-25 | Intelligent control method for moxibustion robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113470820A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114504492A (en) * | 2021-12-28 | 2022-05-17 | 深圳市倍轻松科技股份有限公司 | Automatic moxibustion device and method |
| CN115910281A (en) * | 2023-03-02 | 2023-04-04 | 江西原科中医药智能装备有限公司 | Control method and system of thermosensitive moxibustion robot, storage medium and terminal |
| CN116072262A (en) * | 2023-03-08 | 2023-05-05 | 江西原科中医药智能装备有限公司 | Acupoint alignment and motion following method, system, computer and readable storage medium |
| CN116301116A (en) * | 2023-05-18 | 2023-06-23 | 北京航空航天大学 | Self-adaptive temperature control system of moxibustion instrument |
| CN116549287A (en) * | 2023-07-11 | 2023-08-08 | 深圳市朴硕健康文化科技有限公司 | Moxibustion device control method, device, equipment and medium |
| CN116705278A (en) * | 2023-03-29 | 2023-09-05 | 东莞欧森隆科技发展有限公司 | Electronic moxibustion control system and method |
| CN117899374A (en) * | 2024-01-30 | 2024-04-19 | 沈阳工业大学 | Physiotherapy probe integrated in cooperative robot and control method thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200120A (en) * | 2014-09-18 | 2014-12-10 | 上海中医药大学 | System and method for health status monitoring based on traditional Chinese medicine diagnosis information |
| CN106462926A (en) * | 2014-04-30 | 2017-02-22 | 柯尼卡美能达株式会社 | Health degree assessing device and health degree assessing system |
| CN109994175A (en) * | 2019-01-09 | 2019-07-09 | 上海正太网络科技有限公司 | Health detecting method and system based on artificial intelligence |
| US20190343717A1 (en) * | 2017-03-21 | 2019-11-14 | Yun Kyoung YIM | Device and method for three-dimensionally mapping acupuncture points |
| CN211301135U (en) * | 2019-12-30 | 2020-08-21 | 深圳市汉伟智能技术有限公司 | Moxibustion therapy robot |
| CN112669371A (en) * | 2020-12-11 | 2021-04-16 | 深圳市大富智慧健康科技有限公司 | Moxibustion robot control device, system, equipment and storage medium |
-
2021
- 2021-08-25 CN CN202110979799.3A patent/CN113470820A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106462926A (en) * | 2014-04-30 | 2017-02-22 | 柯尼卡美能达株式会社 | Health degree assessing device and health degree assessing system |
| CN104200120A (en) * | 2014-09-18 | 2014-12-10 | 上海中医药大学 | System and method for health status monitoring based on traditional Chinese medicine diagnosis information |
| US20190343717A1 (en) * | 2017-03-21 | 2019-11-14 | Yun Kyoung YIM | Device and method for three-dimensionally mapping acupuncture points |
| CN109994175A (en) * | 2019-01-09 | 2019-07-09 | 上海正太网络科技有限公司 | Health detecting method and system based on artificial intelligence |
| CN211301135U (en) * | 2019-12-30 | 2020-08-21 | 深圳市汉伟智能技术有限公司 | Moxibustion therapy robot |
| CN112669371A (en) * | 2020-12-11 | 2021-04-16 | 深圳市大富智慧健康科技有限公司 | Moxibustion robot control device, system, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| KUN-CHAN LAN等: "Robot-Controlled Acupuncture—An Innovative Step towards Modernization of the Ancient Traditional Medical Treatment Method", 《MEDICINES》 * |
| 张振球等: "《实用中医诊断学》", 31 January 2013 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114504492A (en) * | 2021-12-28 | 2022-05-17 | 深圳市倍轻松科技股份有限公司 | Automatic moxibustion device and method |
| CN115910281A (en) * | 2023-03-02 | 2023-04-04 | 江西原科中医药智能装备有限公司 | Control method and system of thermosensitive moxibustion robot, storage medium and terminal |
| CN116072262A (en) * | 2023-03-08 | 2023-05-05 | 江西原科中医药智能装备有限公司 | Acupoint alignment and motion following method, system, computer and readable storage medium |
| CN116705278A (en) * | 2023-03-29 | 2023-09-05 | 东莞欧森隆科技发展有限公司 | Electronic moxibustion control system and method |
| CN116301116A (en) * | 2023-05-18 | 2023-06-23 | 北京航空航天大学 | Self-adaptive temperature control system of moxibustion instrument |
| CN116301116B (en) * | 2023-05-18 | 2023-08-08 | 北京航空航天大学 | Self-adaptive temperature control system of moxibustion instrument |
| CN116549287A (en) * | 2023-07-11 | 2023-08-08 | 深圳市朴硕健康文化科技有限公司 | Moxibustion device control method, device, equipment and medium |
| CN116549287B (en) * | 2023-07-11 | 2023-11-21 | 深圳市朴硕健康文化科技有限公司 | Moxibustion device control method, device, equipment and medium |
| CN117899374A (en) * | 2024-01-30 | 2024-04-19 | 沈阳工业大学 | Physiotherapy probe integrated in cooperative robot and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113470820A (en) | Intelligent control method for moxibustion robot | |
| US20220331028A1 (en) | System for Capturing Movement Patterns and/or Vital Signs of a Person | |
| US10004410B2 (en) | System and methods for measuring physiological parameters | |
| CN110269600B (en) | Non-contact video heart rate detection method based on multivariate empirical mode decomposition and combined blind source separation | |
| CN111839489B (en) | Non-contact physiological and psychological health detection system | |
| CN110197169A (en) | A kind of contactless learning state monitoring system and learning state detection method | |
| CN110930374A (en) | Acupoint positioning method based on double-depth camera | |
| CN106901741A (en) | A kind of respiratory rate detection method suitable for environment round the clock | |
| CN109002846B (en) | Image recognition method, device and storage medium | |
| CN109044314A (en) | A kind of contactless rhythm of the heart method based on Euler's video amplifier | |
| CN106618481A (en) | Traditional Chinese medicine intelligent diagnosis expert system | |
| CN109993068A (en) | A kind of contactless human emotion's recognition methods based on heart rate and facial characteristics | |
| KR20080005798A (en) | A cognitive and conduct disorder rehabilitation therapy systems using mothion tracking technologies and augmented reality | |
| CN114642586A (en) | Moxibustion physiotherapy intelligent robot system and operation method thereof | |
| CN115761212A (en) | Human body state early warning system based on infrared image | |
| CN106599821A (en) | Controller fatigue detection method and system based on BP neural network | |
| CN109528217A (en) | A kind of mood detection and method for early warning based on physiological vibrations analysis | |
| CN112232256A (en) | Non-contact motion and body measurement data acquisition system | |
| Gaber et al. | Automated grading of facial paralysis using the Kinect v2: a proof of concept study | |
| CN105844096B (en) | Functional evaluation method based on image processing techniques | |
| Chang et al. | Automatic location of facial acupuncture-point based on facial feature points positioning | |
| US11931166B2 (en) | System and method of determining an accurate enhanced Lund and Browder chart and total body surface area burn score | |
| Niemann et al. | Towards a multimodal multisensory cognitive assessment framework | |
| CN107256390B (en) | Hand function evaluation device and method based on change of each part of hand in three-dimensional space position | |
| CN110673721B (en) | Robot nursing system based on vision and idea signal cooperative control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |