CN-121971035-A - Remote bionic pulse feeling system based on movement intention recognition

CN121971035ACN 121971035 ACN121971035 ACN 121971035ACN-121971035-A

Abstract

The disclosure relates to intelligent traditional Chinese medicine diagnosis and treatment, in particular to a remote bionic pulse-taking system based on movement intention recognition, which is used for solving the problem that the traditional remote pulse-taking system and method cannot support doctors to remotely, real-time and autonomously adjust pulse-taking pressure and position, so that the core diagnosis method and the personalized dialectical process of traditional Chinese medicine are difficult to implement. According to the scheme, the doctor presses the arm model to generate the arm electromyographic signals, the remote control manipulator synchronously applies pressure, and the tactile feedback is carried out through the arm model to reproduce the pulse of the patient.

Inventors

LI XIANGXIN
LIU YAN
ZHU YALONG
JIN HENG
TIAN LAN
ZHENG YUE
LI GUANGLIN

Assignees

深圳先进技术研究院

Dates

Publication Date: 20260505
Application Date: 20251215

Claims (10)

1. The remote bionic pulse feeling system based on movement intention recognition is characterized by comprising an arm model module, a myoelectricity acquisition device, a movement intention sensing module and a manipulator module; The arm model module is configured to comprise an arm model, wherein a pressure sensor and a vibrator with adjustable frequency and amplitude are arranged in the arm model, the pressure sensor collects the pressing pressure of each finger of a doctor, and the vibrator reproduces the pulse characteristics of a patient when the doctor presses the vibrator; The myoelectricity acquisition device is configured to acquire myoelectricity signals of the arm of a doctor; the motion intention perception module is configured to identify finger motion intention to generate a control command based on the collected electromyographic signals, wherein the finger motion intention comprises determining a specific bent finger and a bending angle of the finger; The manipulator module is configured to drive the manipulator to execute the movement intention of the fingers of the doctor based on the control command, each finger of the manipulator applies the pressing pressure corresponding to each finger of the doctor, and pulse information of the patient is acquired.
2. The remote bionic pulse-taking system of claim 1, wherein the pulse characteristics are obtained based on pulse information, the pulse characteristics including main wave amplitude, main wave frequency, dicrotic wave time of occurrence, tidal wave arrival time, rising branch slope, falling front branch slope, falling back branch slope.
3. The remote bionic pulse-taking system of claim 1, wherein the electromyographic signals are subjected to 50Hz notch filtering and 20-500Hz band-pass filtering noise reduction prior to use for identification.
4. The remote bionic pulse-taking system of claim 1, wherein a machine learning algorithm for identifying electromyographic signals is provided in the motor intention perception module.
5. The remote bionic pulse-taking system of claim 1, wherein the myoelectricity acquisition device acquires myoelectricity of a doctor's arm through a surface electrode.
6. The remote bionic pulse-taking system of claim 1, further comprising a real-time visual positioning module comprising a camera, the real-time visual positioning module configured to assist the manipulator in precisely positioning the pressing position of the arm of the patient.
7. The remote bionic pulse-taking system according to claim 1, wherein the finger tip of the manipulator is provided with a pressure sensor, and errors of the pressure exerted by the finger corresponding to the pressure sensor and the pressure exerted by the finger of the corresponding doctor are checked in real time, so that the errors are within an error preset value range.
8. The remote bionic pulse taking system of claim 1, wherein the manipulator is capable of being remotely manually controlled in motion.
9. A computer readable storage medium, characterized in that a computer program is stored that can be loaded by a processor and that executes the system according to any one of claims 1 to 8.
10. A remote bionic pulse-taking method, comprising the steps of: The method comprises the steps that a doctor presses an arm model, pressure sensors in the arm model collect pressing pressure of each finger of the doctor, surface electrodes on the arm of the doctor collect electromyographic signals of the arm of the doctor, finger movement intentions of the doctor are identified based on the electromyographic signals, and a control command is generated, wherein the finger movement intentions comprise specific bent fingers and bending angles of the fingers are determined; The mechanical arm receives the control command, executes the movement intention of the fingers of the doctor, applies pressing pressure corresponding to the fingers of the doctor, collects pulse information of the patient, and reproduces pulse characteristics of the patient by the vibrator with adjustable frequency and amplitude in the arm model when the doctor presses the arm model.

Description

Remote bionic pulse feeling system based on movement intention recognition Technical Field The disclosure relates to the field of rehabilitation engineering, intelligent traditional Chinese medicine diagnosis and treatment equipment and man-machine interaction, in particular to a remote bionic pulse-taking system based on movement intention recognition. Background Traditional Chinese medicine pulse diagnosis is highly dependent on dynamic touch pressure sensing of a doctor on wrist radial artery of a patient (comprehensive judgment of lifting, pressing, searching finger-method, pulse position depth, pulse potential deficiency and excess and the like), and remodelling faces essential obstacle. Under the prior art framework, remote pulse diagnosis does not realize the core element of traditional Chinese medicine palpation, namely the dynamic regulation of the fingertip pressure of a doctor and the real-time bidirectional interaction of multidimensional feedback of the pulse condition of a patient, so that the 'underscore feeling' necessary for dialectical treatment is difficult to reproduce. Therefore, it is highly desirable to construct a closed-loop interactive immersive remote pulse-taking platform that supports palpation of pressure pulse-condition feedback physicians to actively adjust fingering. Disclosure of Invention The existing remote pulse diagnosis system and method can not support doctors to remotely and automatically adjust pulse diagnosis pressure and position in real time, so that the traditional Chinese medicine 'lifting, pressing and searching' core diagnosis method and personalized dialectical process are difficult to reproduce. The invention aims to design a remote bionic pulse feeling system based on movement intention recognition, which realizes remote pulse feeling of a simulated human hand by remotely controlling a mechanical arm and synchronously and repeatedly carrying out pressure and touch feedback in real time. The remote bionic pulse feeling system based on movement intention recognition comprises an arm model module, an electromyographic acquisition device, a movement intention sensing module and a manipulator module, wherein the arm model module is configured to comprise an arm model, a pressure sensor and a vibrator with adjustable frequency and amplitude are arranged in the arm model module, the pressure sensor acquires the pressing pressure of each finger of a doctor, the vibrator reproduces pulse characteristics of a patient when the doctor presses, the electromyographic acquisition device is configured to acquire electromyographic signals of the arm of the doctor, the movement intention sensing module is configured to recognize finger movement intention to generate a control command based on the acquired electromyographic signals, the finger movement intention comprises a specific bending finger and a bending angle of the finger, and the manipulator module is configured to drive the manipulator to execute the movement intention of the finger of the doctor based on the control command, and each finger of the manipulator applies the pressing pressure corresponding to each finger of the doctor and acquires pulse information of the patient. In an embodiment of the foregoing technical solution, the pulse characteristic is acquired based on pulse information, and the pulse characteristic includes a main wave amplitude, a main wave frequency, a dicrotic wave occurrence time, a tide wave arrival time, an ascending branch slope, a descending front branch slope, and a descending rear branch slope. In one embodiment of the above technical solution, the electromyographic signal is subjected to a notch filtering of 50Hz and a band-pass filtering of 20-500Hz noise reduction before being used for identification. In an implementation manner of the foregoing technical solution, a machine learning algorithm for identifying electromyographic signals is set in the motion intention sensing module. In one embodiment of the foregoing technical solution, the myoelectricity acquiring device acquires myoelectricity of a doctor's arm through a surface electrode. In an implementation manner of the above technical solution, the remote bionic pulse-taking system further includes a real-time visual positioning module, the real-time visual positioning module includes a camera, and the real-time visual positioning module is configured to assist the manipulator to accurately position the pressing position of the arm of the patient. In one embodiment of the foregoing technical solution, a fingertip of the manipulator has a pressure sensor, and errors between a pressure applied by a finger corresponding to the pressure sensor and a pressure applied by a finger of a corresponding doctor are checked in real time, so that the errors are within an error preset value range. In one embodiment of the above solution, the manipulator is capable of being remotely and manually controlled in motion. Based on the above-d