Remote bionic pulse feeling system based on motion intention recognition

Abstract

The invention relates to intelligent traditional Chinese medicine diagnosis and treatment, in particular to a remote bionic pulse feeling system based on motion intention recognition, which is used for solving the problem that the traditional remote pulse diagnosis system and method cannot support doctors to remotely, real-timely and autonomously adjust the pulse feeling pressure and position, so that the traditional Chinese medicine'lifting, pressing and searching 'core diagnosis method and the personalized dialectical process are difficult to implement. According to the scheme, the arm electromyographic signals generated when a doctor presses the arm model are used for remotely controlling the mechanical arm to synchronously apply pressure, tactile feedback is conducted through the arm model, and the pulse of a patient is reproduced.

Description

Technical Field

[0001] This disclosure relates to the fields of rehabilitation engineering, intelligent TCM diagnostic and treatment equipment, and human-computer interaction, and in particular to a remote bionic pulse diagnosis system based on motion intention recognition. Background Technology

[0002] Traditional Chinese medicine pulse diagnosis relies heavily on the physician's dynamic tactile perception of the radial artery at the patient's wrist (a comprehensive judgment based on "lifting, pressing, and searching" finger techniques, pulse depth, and pulse strength). Its remote application faces fundamental obstacles. Under current technological frameworks, remote pulse diagnosis has not yet achieved the core element of traditional Chinese medicine palpation—the real-time two-way interaction between the physician's dynamic adjustment of fingertip pressure and the patient's multidimensional feedback on the pulse. This makes it difficult to reproduce the "feeling under the fingers" essential for diagnosis and treatment. Therefore, there is an urgent need to construct a closed-loop, interactive, immersive remote pulse diagnosis platform that supports pressure pulse feedback and allows physicians to actively adjust their finger techniques. Summary of the Invention

[0003] Existing remote pulse diagnosis systems and methods cannot support physicians to remotely and autonomously adjust the pulse pressure and position in real time, making it difficult to reproduce the core diagnostic methods of traditional Chinese medicine, such as "lifting, pressing, and searching," and the personalized diagnosis process.

[0004] The purpose of this invention is to design a remote bionic pulse diagnosis system based on motion intention recognition, which realizes remote pulse diagnosis by remotely controlling a robotic hand and synchronizing and reproducing pressure and tactile feedback in real time.

[0005] To achieve the aforementioned technical objectives, this disclosure proposes a remote bionic pulse diagnosis system based on motion intention recognition, comprising an arm model module, an electromyography (EMG) acquisition device, a motion intention sensing module, and a robotic arm module. The arm model module is configured to include an arm model containing a pressure sensor and a vibrator with adjustable frequency and amplitude. The pressure sensor acquires the pressure applied by each of the doctor's fingers, and the vibrator reproduces the patient's pulse characteristics when the doctor applies pressure. The EMG acquisition device is configured to acquire EMG signals from the doctor's arm. The motion intention sensing module is configured to recognize finger motion intentions based on the acquired EMG signals and generate control commands, wherein the finger motion intentions include determining the specific bent finger and the bending angle of the finger. The robotic arm module is configured to drive the robotic arm to execute the doctor's finger motion intentions based on the control commands, with each finger of the robotic arm applying the corresponding pressure applied by the doctor's fingers and acquiring the patient's pulse information.

[0006] In one embodiment of the above technical solution, the pulse characteristics are obtained based on pulse information, and the pulse characteristics include the amplitude of the main wave, the frequency of the main wave, the time of appearance of the dicrotic wave, the time of arrival of the tidal wave, the slope of the ascending branch, the slope of the descending branch before descending, and the slope of the descending branch after descending.

[0007] In one embodiment of the above technical solution, the electromyographic signal is subjected to noise reduction processing with a 50Hz notch filter and a 20-500Hz bandpass filter before it is used for recognition.

[0008] In one embodiment of the above technical solution, the motion intention perception module is equipped with a machine learning algorithm for recognizing electromyographic signals.

[0009] In one embodiment of the above technical solution, the electromyography (EMG) acquisition device collects EMG data from a doctor's arm via surface electrodes.

[0010] In one embodiment of the above technical solution, the remote bionic pulse diagnosis system further includes a real-time visual positioning module, which includes a camera and is configured to assist the robotic arm in accurately positioning the pressure position of the patient's arm.

[0011] In one embodiment of the above technical solution, the fingertips of the robotic hand are equipped with pressure sensors to verify in real time the error between the pressure applied by the corresponding finger and the pressure applied by the corresponding doctor's finger, so that the error is within the preset error range.

[0012] In one embodiment of the above technical solution, the robotic arm can be remotely and manually controlled to move.

[0013] Based on the above technical solutions, a computer-readable storage medium can be obtained, storing a computer program that can be loaded by a processor and executed as described in any of the above-mentioned systems.

[0014] Based on the above technical solution, a remote bionic pulse diagnosis method can be obtained, the steps of which include: when the doctor presses the arm model, the pressure sensor inside the arm model collects the pressing pressure of each finger of the doctor, the surface electrode on the doctor's arm collects the electromyographic signals of the doctor's arm, and the doctor's finger movement intention is identified based on the electromyographic signals, and a control command is generated. The finger movement intention includes determining the specific bent finger and the bending angle of the finger; the robotic arm receives the control command, executes the doctor's finger movement intention, applies the pressing pressure corresponding to each finger of the robotic arm, the robotic arm collects the patient's pulse information, and when the doctor presses the arm model, the frequency and amplitude adjustable vibrator inside the arm model reproduces the patient's pulse characteristics.

[0015] The beneficial technical effects of this invention are as follows: This solution enables doctors to remotely control the robotic arm at the patient's end to accurately locate the pulse point, apply pressure synchronously through biomimetic materials, acquire and reproduce the patient's pulse characteristics in real time, and finally complete a high-precision "pulse diagnosis" in a cross-space scenario, breaking through the technical bottleneck of traditional telemedicine lacking tactile interaction. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic block diagram of a remote bionic pulse diagnosis system in one embodiment.

[0018] Figure 2 This is a schematic diagram of the operation flow of a remote bionic pulse diagnosis system in one embodiment. Detailed Implementation

[0019] To address the technical problems of lack of tactile perception, insufficient operational precision, and disconnection between two-way feedback in telemedicine, this application designs a remote bionic pulse diagnosis system based on motion intention recognition. The system remotely controls the patient's mechanical hand to accurately locate the pulse point in real time through electromyographic signals from the doctor's side. Simultaneously, the doctor applies pressure from bionic materials to the fingers of the mechanical hand and provides real-time feedback of the patient's pulse data to the doctor's side, thus reproducing the tactile sensation and replicating the doctor's technique as closely as possible to achieve remote pulse diagnosis that simulates a real human hand.

[0020] The following description, in conjunction with the accompanying drawings, clearly and completely describes how the technical solution of this case is implemented. Obviously, the described embodiments are only a part of the embodiments of this case, and not all of them. Based on the embodiments in this case, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0021] In Traditional Chinese Medicine, doctors use three fingers to press on three points on the patient's wrist: cun, guan, and chi. Each point has three pulse characteristics: superficial, middle, and deep, collectively known as the three pulse positions, for a total of nine positions. In this application, the doctor demonstrates pulse-taking on the arm model.

[0022] In one method of using a remote bionic pulse diagnosis system, a doctor presses on an arm model, and the remote bionic pulse diagnosis system controls a robotic arm to remotely locate the patient's pulse point and apply pressure synchronously. Simultaneously, the robotic arm acquires the patient's pulse characteristics in real time and reproduces them on the doctor's arm model, ultimately achieving a high-precision pulse diagnosis across spatial scenarios, overcoming the technical bottleneck of traditional telemedicine lacking tactile interaction.

[0023] A remote bionic pulse diagnosis system is designed, comprising a first subsystem (doctor) and a second subsystem (patient). The first subsystem, used by the doctor, is configured to collect electromyographic (EMG) signals from the doctor's arm when the doctor presses on the arm model, decode the finger movement intention based on the collected EMG signals, and then generate and send control commands to drive the robotic arm; and to reproduce the patient's pulse sensation based on received pulse data. The second subsystem, used by the patient, is configured to drive the robotic arm to position itself at the pressing location and perform the pressing action according to the received control commands; and to collect and transmit pulse data.

[0024] In one embodiment, to achieve precise positioning of the compression point by the robotic arm, the remote bionic pulse diagnosis system is equipped with a real-time visual positioning module. The real-time visual positioning module may include a binocular camera, positioned above the patient's wrist to assist the doctor in observing the compression point. The binocular camera records and transmits video of the robotic arm's movement in real time, aiding the doctor in observing the compression point. The robotic arm supports remote manual fine-tuning by the doctor to precisely position it at the target compression point.

[0025] In another embodiment, the real-time visual positioning module has a call function so that the patient can cooperate in adjusting the position of their arm.

[0026] In one embodiment, pressure sensors are installed at the corresponding positions of the cun, guan, and chi points on the wrist of the arm model. These pressure sensors collect the pressing pressure of each of the doctor's fingers in real time, which is synchronously transmitted and converted into the pressing pressure control of the robotic arm via control commands. It can be understood that the fingers of the robotic arm correspond to the doctor's, the fingers performing the pressing action correspond to the doctor's pressing fingers, and the pressing pressure of each finger corresponds to the doctor's pressing pressure. For example, if the doctor applies x Newtons of pressure to the cun point with their index finger, the robotic arm's index finger also applies x Newtons of pressure to the cun point. The doctor's real-time pressing pressure is transmitted to the patient side and used to adjust the torque of the robotic arm's motor, causing each finger of the robotic arm to apply the corresponding collected pressing pressure. Pulse information is acquired through the robotic arm on the patient side and transmitted back to the doctor side. The pulse information includes the pulse frequency and amplitude. The doctor's pressing pressure can be adjusted in real time. The pulse information is collected by pressure sensors at the fingers of the robotic arm.

[0027] In one implementation, the pressure sensor in the arm model covers an area that is close to the location of the pulse in the real arm.

[0028] In one embodiment, the first subsystem is configured to integrate a motion intention perception module, an arm model module, and a first control module. The first control module includes a host computer that sends control commands via a serial communication interface. The motion intention perception module is configured to identify the doctor's finger movement intention based on electromyographic signals from the doctor's arm when taking the pulse and generate control commands. The motion intention perception module includes a machine learning algorithm that takes the electromyographic signals as input and the control commands as output. The machine learning algorithm may be a CNN-LSTM model. The doctor's finger movements refer to the doctor's pulse-taking action. The finger movement intention includes determining the specific bent finger and the bending angle. The arm model module includes an arm model whose outer surface is made of a biomimetic material to facilitate pulse-taking by the doctor. The arm model also reproduces the frequency and amplitude of the patient's pulse to the doctor; therefore, a vibrator with adjustable frequency and amplitude is incorporated into the arm model. The vibrator reproduces the pulse information acquired by the robotic arm. Furthermore, the frequency and amplitude-adjustable vibrator reproduces the patient's pulse information when the doctor presses the arm, but does not reproduce the pulse information when the doctor does not press the arm.

[0029] To accurately identify finger movement intentions, the acquired electromyographic signals were processed by a 50Hz notch filter and a 20-500Hz bandpass filter to reduce noise.

[0030] The electromyography (EMG) signals from the doctor's arm are collected using surface electrodes, one end of which is positioned on the doctor's arm, and the other end is located on a wireless EMG acquisition device. The more areas covered by the surface electrodes, the more accurate the motion recognition. Preferably, the surface electrodes cover the flexor and extensor muscles of the forearm to accurately identify bent fingers and their bending angles.

[0031] The vibrator reproduces the pulse information acquired by the robotic arm, generating corresponding vibration waveforms based on pulse characteristics. These pulse characteristics include the amplitude of the main wave, the frequency of the main wave, the time of appearance of the dicrotic wave, the time of arrival of the tidal wave, the slope of the ascending limb, the slope of the first descending limb, and the slope of the second descending limb. The amplitude of the main wave (or amplitude) refers to the height of the main peak in the pulse wave, representing the maximum value of systolic arterial pressure. The frequency of the main wave usually refers to the frequency of the main peak in the pulse wave, directly related to heart rate, i.e., the number of cardiac cycles per unit time. The dicrotic wave is a small wave following the descending limb of the pulse wave, formed by the rebound of blood after the aortic valve closes, and usually occurs during diastole. The tidal wave is the second peak after the main peak, formed by the reflection of blood impacting peripheral arteries. The slope of the ascending limb refers to the steepness of the ascending limb of the pulse wave, reflecting the ventricular ejection velocity. The first descending limb refers to the waveform portion from the peak of systolic pressure to the dicrotic notch (descending isthmus), and its slope reflects the hemodynamic state before the aortic valve closes. The slope of the waveform between the depressor notch and the diastolic trough after the descent is related to blood volume and peripheral resistance.

[0032] In one embodiment, the second subsystem includes a robotic arm module and a second control module. The second control module includes a host computer configured to transmit the collected pulse and / or pressure information applied by the robotic arm via a serial communication interface. The robotic arm module includes a robotic arm, which includes a receiving unit, a driving unit, and a data acquisition unit. The driving unit is configured to control the movement, bending, and pressure adjustment of the robotic arm's fingers. The data acquisition unit is configured to acquire the patient's pulse information. The robotic arm communicates with the second control module, receiving control commands and / or pressure data from the doctor forwarded by the second control module, and also sending its own pressure data and / or collected pulse data to the second control module. The control commands forwarded by the second control module are control commands generated based on the electromyographic signals of the doctor's arm, and / or control commands from the doctor for fine-tuning the robotic arm. When the robotic arm dynamically adjusts the torque of the hand motor according to the doctor's pressure using a PID algorithm, a fingertip pressure sensor performs real-time verification to ensure that the error between the pressure applied by the corresponding finger and the corresponding pressure applied by the doctor's finger is less than or equal to a preset error value. The preset error value is, for example, 5%.

[0033] In one implementation, a dedicated third subsystem is provided for patient-doctor interactive control. This third subsystem includes a synchronization module configured to bidirectionally synchronize control commands from the doctor's side with sensor data from the patient's side; and error control. The sensor data includes pulse and pressure data. The doctor's control commands include control commands generated based on electromyographic signals from the doctor's arm, and control commands for fine-tuning the robotic arm. The errors include pressure matching error and pulse reproduction accuracy. The pressure matching error is the difference between the pressure applied by the patient-side robotic arm and the pressure applied by the doctor. The pulse reproduction accuracy is a measure of the correlation coefficient between the pulse waveform acquired from the patient's side and the pulse waveform reproduced by the doctor.

[0034] In one implementation, if the pressure matching error is greater than a preset error value (e.g., 5%) or the control command execution delay is greater than a preset time (e.g., 100ms), the remote bionic pulse diagnosis system automatically switches to manual mode and triggers an alarm, allowing the doctor to manually calibrate or adjust the operation based on the error.

[0035] In one implementation, the third subsystem further includes a secure communication module, the secure communication model being configured for network communication and encryption.

[0036] In one embodiment, the remote bionic pulse diagnosis system includes an electromyography (EMG) acquisition device, a motion intention sensing module, an arm model module, and a robotic hand module. The EMG acquisition device includes surface electrodes for EMG acquisition, which are fixed to the doctor's arm; the fixing method can be wearable, adhesive, or strapped on. The arm model module includes an arm model. When the doctor presses on the arm model, the EMG acquisition device processes the EMG signals collected by the surface electrodes through a 50Hz notch filter and a 20-500Hz bandpass filter to reduce noise. The noise-reduced EMG signals are then transmitted to the motion intention sensing module for processing. The motion intention sensing module is equipped with a machine learning algorithm to decode the EMG signals, identify the specific fingers the doctor bends and the bending angle of those fingers, and generate control commands to drive the robotic hand, which is part of the robotic hand module. Simultaneously, pressure sensors in the arm model collect the pressure from the doctor's fingers in real time; this pressure information is synchronously transmitted and converted into pressure control for the robotic hand. When the robotic hand presses on the patient's pulse based on the doctor's finger movements and pressure, it collects the patient's pulse information, including the pulse frequency and amplitude. The arm model is equipped with a vibrator with adjustable frequency and amplitude, which synchronously reproduces the patient's pulse information when the doctor presses it.

[0037] In the above implementation, the remote bionic pulse diagnosis system forms a closed-loop tactile interaction through an electromyography acquisition device, a motion intention perception module, an arm model module, and a robotic hand module, so as to reproduce the doctor's technique as much as possible and restore the frequency and amplitude characteristics of the patient's pulse, thereby realizing remote pulse diagnosis.

[0038] To improve pulse diagnosis, a real-time visual positioning module can be added to the above implementation method. This allows for real-time video calibration when the robotic arm cannot accurately locate the pressure point on the patient's arm. The real-time visual positioning module includes a camera. It may also have a communication function.

[0039] To improve real-time performance, a synchronization module can be set up based on the above implementation method. The doctor's pressure data is transmitted to the robotic arm via the network. At the same time, the torque of the robotic arm motor is dynamically adjusted through a PID algorithm and verified in real time by a fingertip pressure sensor to ensure that the pressure error with the doctor's end is less than or equal to a preset error threshold.

[0040] To improve the positioning accuracy of the robotic arm, it allows doctors to remotely fine-tune it to precisely locate the target position. Simultaneously, it also allows doctors to manually fine-tune or adjust the operation if the robotic arm's movement delay exceeds a preset time.

[0041] In one implementation, the remote bionic pulse diagnosis system operates through the first subsystem, the second subsystem, and the third subsystem to achieve remote pulse diagnosis. For example... Figure 1As shown in the diagram. The first subsystem is configured with a motion intention perception module, an arm model module, and a first control module. The third subsystem is configured with a real-time visual positioning module, a secure communication module, and a synchronization module. The second subsystem is configured with a robotic arm module and a second control module. The arm model module includes an arm model, and the robotic arm module includes a robotic arm. When a doctor performs a pulse diagnosis, the first subsystem collects the doctor's pressure data. Simultaneously, the motion intention perception module identifies the finger movement intention based on the doctor's arm's electromyographic signals and generates control commands. These commands and pressure data are then sent to the third subsystem via the first control module. The third subsystem forwards the control commands and pressure data to the second subsystem. The second subsystem drives the robotic arm to perform pulse compression on the patient according to the control commands, applying appropriate pressure based on the pressure data. During compression, the robotic arm collects the patient's pulse information and sends this information, along with the applied pressure, to the third subsystem. The third subsystem then forwards the pulse information back to the first subsystem, which reproduces the pulse information for the doctor through the arm model. The third subsystem calculates pressure matching error based on the pressure data of the robotic arm and the doctor under the same pressing action, and calculates pulse fidelity based on pulse information for error feedback. The pressure matching error is the difference between the pressure applied by the robotic arm on the patient's side and the pressure applied by the doctor. The pulse fidelity is measured by the correlation coefficient between the pulse waveform collected on the patient's side and the pulse waveform reproduced on the doctor's side. When the pressure matching error exceeds a preset error threshold, the doctor is prompted to remotely fine-tune the robotic arm. When the pulse fidelity exceeds a preset fidelity threshold, the doctor is prompted to determine the reliability of the reproduced pulse wave, so that the doctor can decide whether to make a diagnosis based on the reproduced pulse wave. The real-time video positioning module includes a camera and a microphone. When the doctor remotely fine-tunes the robotic arm, the real-time visual positioning module can be used for assisted positioning. The secure communication module ensures the security of data transmission and video / voice communication. The synchronization module can coordinate data streams at different rates on the doctor's and patient's sides to ensure stable and uninterrupted data transmission. Simultaneously, the synchronization module is configured for error control.

[0042] In one implementation, the method of using a remote bionic pulse-taking system based on motion intention recognition is as follows: Figure 2The process includes: system startup, doctor and patient donning the device and connecting to the video feed. The doctor selects a mode. If automatic mode is selected, it executes automatically with a single click. If manual mode is selected, first, electromyography (EMG) control and positioning are performed. When the doctor presses the arm model, the robotic arm's pressing position and fingers are synchronized with the doctor's based on the collected EMG signals from the doctor's arm. Next, pressure synchronization is performed, synchronizing the pressure of the robotic arm's fingers on the patient with the pressure of the doctor's fingers. Finally, tactile feedback is provided, transmitting the patient's pulse information to the doctor through the arm model. The system status is displayed in real time on the doctor's side. A normal system status is defined as a pressure error between the robotic arm and the doctor's end being less than or equal to a preset error threshold, and a robotic arm movement delay time being less than or equal to a preset time. If the system status is normal, the diagnosis is completed. Otherwise, the doctor manually adjusts the robotic arm's movement to complete the diagnosis.

[0043] This invention can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the invention.

[0044] A remote bionic pulse diagnosis method includes the following steps: when a doctor presses on an arm model, pressure sensors inside the arm model collect the pressing pressure of each of the doctor's fingers, and surface electrodes on the doctor's arm collect electromyographic signals of the doctor's arm. Based on the electromyographic signals, the doctor's finger movement intention is identified, and a control command is generated. The finger movement intention includes determining the specific bent finger and the bending angle of the finger. A robotic arm receives the control command, executes the doctor's finger movement intention, applies pressing pressure corresponding to each of the doctor's fingers, collects the patient's pulse information, and when the doctor presses on the arm model, a vibrator with adjustable frequency and amplitude inside the arm model reproduces the patient's pulse characteristics.

[0045] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0046] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0047] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, Python, etc., and conventional procedural programming languages ​​such as "C" or similar languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0048] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0049] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0050] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0051] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It will be well known to those skilled in the art that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are equivalent.

[0052] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A remote bionic pulse diagnosis system based on motion intention recognition, characterized in that, The system includes an arm model module, an electromyography (EMG) acquisition device, a motion intention sensing module, and a robotic arm module. The arm model module is configured to include an arm model, which contains a pressure sensor and a vibrator with adjustable frequency and amplitude. The pressure sensor collects the pressure of each finger pressed by the doctor, and the vibrator reproduces the patient's pulse characteristics when the doctor presses. The electromyography (EMG) acquisition device is configured to acquire EMG signals from the doctor's arm; The motion intention perception module is configured to recognize finger motion intentions based on collected electromyographic signals and generate control commands, wherein the finger motion intentions include determining the specific bent finger and the bending angle of the finger. The robotic arm module is configured to drive the robotic arm to execute the doctor's finger movement intentions based on control commands, apply the corresponding pressing pressure of the doctor's fingers to each finger of the robotic arm, and collect the patient's pulse information.

2. The remote bionic pulse diagnosis system according to claim 1, characterized in that, The pulse characteristics are obtained based on pulse information and include the amplitude of the main wave, the frequency of the main wave, the time of appearance of the diphthong wave, the time of arrival of the tidal wave, the slope of the ascending branch, the slope of the descending branch before the descent, and the slope of the descending branch after the descent.

3. The remote bionic pulse diagnosis system according to claim 1, characterized in that, Before being used for identification, the electromyographic signals are subjected to noise reduction processing with a 50Hz notch filter and a 20-500Hz bandpass filter.

4. The remote bionic pulse diagnosis system according to claim 1, characterized in that, The motion intention perception module is equipped with a machine learning algorithm that identifies electromyographic signals.

5. The remote bionic pulse diagnosis system according to claim 1, characterized in that, The electromyography (EMG) acquisition device collects EMG data from the doctor's arm using surface electrodes.

6. The remote bionic pulse diagnosis system according to claim 1, characterized in that, The remote bionic pulse diagnosis system also includes a real-time visual positioning module, which includes a camera and is configured to assist the robotic arm in accurately positioning the pressure point on the patient's arm.

7. The remote bionic pulse diagnosis system according to claim 1, characterized in that, The robotic hand has pressure sensors at its fingertips, which verify in real time the error between the pressure applied by the corresponding finger and the pressure applied by the corresponding doctor's finger, ensuring that the error is within a preset range.

8. The remote bionic pulse diagnosis system according to claim 1, characterized in that, The robotic arm can be remotely and manually controlled to move.

9. A computer-readable storage medium, characterized in that: The system stores a computer program that can be loaded by a processor and executed by the system as described in any one of claims 1 to 8.

10. A remote bionic pulse diagnosis method, characterized in that the steps include... include: The doctor presses on an arm model, and pressure sensors inside the arm model collect the pressure of each finger. Surface electrodes on the doctor's arm collect electromyographic signals from the arm. Based on the electromyographic signals, the doctor's finger movement intentions are identified, and control commands are generated. The finger movement intentions include determining the specific finger to bend and the bending angle of the finger. The robotic arm receives control commands and executes the doctor's finger movement intentions. Each finger of the robotic arm applies pressure corresponding to the doctor's finger. The robotic arm collects the patient's pulse information, and when the doctor presses the arm model, the frequency and amplitude adjustable vibrator inside the arm model reproduces the patient's pulse characteristics.

Images