Surgical robot control information generation method, apparatus and storage medium

Abstract

The application relates to a surgical robot control information generation method, system and device. The method comprises the following steps: acquiring a physiological signal of an operator, and performing feature extraction on the physiological signal to obtain a to-be-processed feature; acquiring each reference feature generated in advance, each reference feature corresponding to an operator motion type; comparing the to-be-processed feature with each reference feature to obtain the motion type of the operator; and generating surgical robot control information corresponding to the motion type of the operator, the surgical robot control information being used for controlling the surgical robot. The method can improve the control sensitivity of the surgical robot.

Description

Technical Field

[0001] This application relates to the field of intelligent medical technology, and in particular to a method, apparatus and storage medium for generating control information for a surgical robot. Background Technology

[0002] Minimally invasive surgery is a new technique that uses endoscopes such as laparoscopy and thoracoscopy to perform surgery inside the human body. It has advantages such as less trauma, less pain, and less bleeding, which can effectively reduce the patient's long recovery time and discomfort, and avoid some of the harmful side effects of traditional surgery.

[0003] Minimally invasive surgical robot systems enable doctors to observe the tissue characteristics inside the patient's body through two-dimensional or three-dimensional display devices at the main control console, and remotely control the robotic arms and surgical instruments on the operating robot to complete the surgical operation.

[0004] Currently, when doctors perform robot-assisted surgery, the surgeon operates multiple robotic arms to perform the operation. During the operation, the surgeon controls the surgical robot through physical buttons, such as switching between robotic arms by using foot pedals. This method of controlling the operation through physical foot pedals is easily affected by the position of the hardware. Without direct visual guidance, it is prone to deviations and has low sensitivity. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, system, device, computer equipment, computer-readable storage medium, and computer program product for generating control information of a surgical robot that can improve the control sensitivity of the surgical robot, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for generating control information for a surgical robot, the method comprising:

[0007] Acquire the collected physiological signals of the operator, and extract features from the physiological signals to obtain the features to be processed;

[0008] Acquire pre-generated reference features, each of which corresponds to an operator's motion type;

[0009] The feature to be processed is compared with each of the reference features to obtain the operator's movement type;

[0010] Generate surgical robot control information corresponding to the operator's movement type, the surgical robot control information being used to control the surgical robot;

[0011] The generation of surgical robot control information corresponding to the operator's movement type includes:

[0012] Generate at least one of the following: robotic arm switching control information, clutch control information, endoscope control information, target electrocoagulation control information, target electrosurgery control information, and stop operation information, corresponding to the operator's movement type;

[0013] The operator's physiological signals include: electromyographic signals of the target site of the operator; and / or the operator's heart rate signal.

[0014] In one embodiment, the electromyographic signals of the operator's target site include:

[0015] Electromyographic signals from the operator's feet; or

[0016] Electromyographic (EMG) signals from the operator's feet and knee joint; or

[0017] Electromyographic (EMG) signals from the operator's arm and foot; or

[0018] The electromyographic (EMG) signals from the operator's feet, knees, and arms.

[0019] In one embodiment, the features to be processed include at least one of the time-domain features and frequency-domain features of muscle contraction, and heart rate features.

[0020] In one embodiment, the physiological signal is an electromyographic signal; the step of extracting features from the physiological signal to obtain the features to be processed includes:

[0021] The electromyographic signal is filtered.

[0022] Obtain a reference frequency, and perform a Fourier transform on the filtered electromyographic signal using the reference frequency to obtain the features to be processed; or

[0023] The physiological signal is a heart rate signal; the feature extraction of the physiological signal to obtain the features to be processed includes:

[0024] The heart rate signal is filtered to obtain the features to be processed.

[0025] In one embodiment, the physiological signal includes at least two different types of physiological signals; the feature extraction of the physiological signal to obtain the feature to be processed includes:

[0026] By performing frequency band transformation on different types of physiological signals, different types of physiological signals under the same frequency band can be obtained;

[0027] Different types of physiological signals in the same frequency band are combined to obtain composite signals;

[0028] The composite signal is filtered to obtain the feature to be processed.

[0029] In one embodiment, prior to obtaining the pre-generated reference features, the method further includes:

[0030] Obtain the pre-set motion types for each operator;

[0031] Standard physiological signals corresponding to the operator's movement type were collected from each operator.

[0032] Feature extraction is performed on each of the standard physiological signals to obtain reference features corresponding to each operator;

[0033] Establish the association between the reference features of each operator and the movement type of the operator.

[0034] In one embodiment, prior to acquiring the physiological signals of the operator being collected, the process includes:

[0035] Obtain the foot position of the operator being monitored;

[0036] Obtain the status information of the surgical robot;

[0037] When the foot position is the target position and the status information is the target status information, the first information of the physiological signal acquisition operator is sent to the physiological signal acquisition device.

[0038] In one embodiment, after generating surgical robot control information corresponding to the operator's movement type, the method further includes:

[0039] A second message to stop collecting the operator's physiological signals is sent to the physiological signal acquisition device, which is used to stop collecting the operator's physiological signals based on the second message;

[0040] After controlling the surgical robot based on the surgical robot control information, the process includes:

[0041] A third message is sent to the physiological signal acquisition device to restart the acquisition of the operator's physiological signals based on the third message.

[0042] Secondly, this application also provides a surgical robot control information generation system, the system comprising:

[0043] Physiological signal acquisition device, used to collect the operator's physiological signals;

[0044] The processor is used to execute the above-described surgical robot control information generation method to process the physiological signals and obtain surgical robot control information;

[0045] A motion control device is used to control the surgical robot based on the surgical robot control information.

[0046] In one embodiment, the physiological signal acquisition device includes at least one of the following:

[0047] An electromyography (EMG) signal acquisition device is used to acquire EMG signals from the target area of ​​the operator by means of electrode pads placed on the target area of ​​the operator.

[0048] Millimeter-wave radar device used to collect the operator's heart rate signal.

[0049] In one embodiment, the system further includes:

[0050] A position acquisition device for acquiring the position of the operator's feet;

[0051] The processor is also used to acquire the status information of the surgical robot; when the foot position is the target position and the status information is the target status information, it sends the first information of acquiring the operator's physiological signals to the physiological signal acquisition device.

[0052] Thirdly, this application also provides a surgical robot control information generation device, the device comprising:

[0053] The feature extraction module is used to acquire the physiological signals of the operator being collected, and to extract features from the physiological signals to obtain the features to be processed.

[0054] The reference feature acquisition module is used to acquire pre-generated reference features, each of which corresponds to an operator's motion type.

[0055] The comparison module is used to compare the feature to be processed with each of the reference features to obtain the movement type of the operator;

[0056] The control information generation module is used to generate surgical robot control information corresponding to the operator's movement type, and the surgical robot control information is used to control the surgical robot.

[0057] Fourthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the above embodiments.

[0058] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0059] Sixthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0060] The aforementioned surgical robot control information generation method, system, device, computer equipment, storage medium, and computer program product acquire the collected physiological signals of the operator, extract features from the physiological signals to obtain the features to be processed, and compare the features to be processed with the pre-generated reference features to obtain the operator's movement type, thereby generating surgical robot control information corresponding to the operator's movement type. This software-based control is more accurate and more sensitive than physical buttons. Attached Figure Description

[0061] Figure 1 This is a schematic diagram of a surgical robot system in one embodiment;

[0062] Figure 2 This is a schematic diagram of a doctor's cart and an operating cart in one embodiment;

[0063] Figure 3 This is a schematic diagram of the foot pedals of a doctor's trolley in one embodiment;

[0064] Figure 4 This is a system block diagram of a surgical robot control information generation system in one embodiment;

[0065] Figure 5 This is a schematic diagram of the acquisition system corresponding to the electromyography signal acquisition device in one embodiment;

[0066] Figure 6 This is a schematic diagram of the acquisition system corresponding to the electromyography signal acquisition device in another embodiment;

[0067] Figure 7 This is a schematic diagram of a millimeter-wave radar device in one embodiment;

[0068] Figure 8 This is a flowchart illustrating a method for generating control information for a surgical robot in one embodiment;

[0069] Figure 9 This is a schematic diagram of an electromyography signal acquisition system in one embodiment;

[0070] Figure 10 This is a schematic diagram of a heart rate signal acquisition system in one embodiment;

[0071] Figure 11 This is a schematic diagram of an electromyography and heart rate signal acquisition system in one embodiment;

[0072] Figure 12This is a force analysis diagram of the foot in one embodiment;

[0073] Figure 13 This is a schematic diagram of the original electromyographic signal in one embodiment;

[0074] Figure 14 This is a schematic diagram of a signal filtered by a Butterworth filter in one embodiment.

[0075] Figure 15 This is a schematic diagram illustrating the extraction of electromyographic signal features using Fourier transform in one embodiment.

[0076] Figure 16 The waveform diagram shows the electromyographic signal processing in one embodiment.

[0077] Figure 17 This is a schematic diagram of a radar measurement principle in one embodiment;

[0078] Figure 18 Here is a waveform diagram of heart rate signal processing in one embodiment;

[0079] Figure 19 Here is a waveform diagram corresponding to the signal superposition method in one embodiment;

[0080] Figure 20 This is a structural block diagram of a surgical robot control information generation device in one embodiment;

[0081] Figure 21 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0082] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0083] This application provides a surgical robot system, such as... Figure 1As shown, the device can include a surgeon's cart 100, a surgical cart 200, and an image display terminal 300. Preoperatively, the machine undergoes a self-test to determine its initial position and status. Different machine positions are used depending on the patient's surgical procedure. Holes are drilled according to the location of the lesion, typically five holes: four for installing instruments and endoscopes, and the fifth for auxiliary surgical procedures. After installing the puncture card, instruments, endoscope, and sterile bag, the system can enter the master-slave surgical operation mode. The operator controls the left and right master arms via the control panel of the surgeon's cart 100, thereby controlling two of the four arms of the surgical cart 200 for surgical or endoscopic control. Operation signals are triggered via foot pedals; side pedals are used for arm switching, and corresponding pedals on the left and right sides directly below are used for clutch, endoscopic control, and energy triggering. However, due to factors such as the physical characteristics, reliability, and lifespan of the pedals, their ease of use and stability can affect the efficiency and safety of the surgery. Therefore, this application collects the operator's physiological signals, extracts features from these signals to obtain the features to be processed, and compares the features to be processed with reference features to obtain the operator's movement type. This allows the surgical robot's control information, i.e., the control information corresponding to the signals triggered by the pedals, to be determined based on the operator's movement type. This avoids problems caused by physical control triggering, such as delays, difficulty in controlling foot strength, and unstable buttons, thereby greatly improving surgical efficiency, safety, and service life.

[0084] Combination Figure 2 As shown, the doctor's carriage 100 and operating carriage 20 involved in this application are illustrated. The operator controls the movement of arm 1 (22) or arm 23 (23) of the operating carriage 200 via the left master hand (25), and controls the movement of arm 4 (24) via the right master hand (26). The lower part (21) of the doctor's control panel in the doctor's carriage 10 is the doctor's foot pedal, with an arm switching button on the left. The operator presses the trigger signal switch with the side of their left foot, receives a signal from their hand, and switches between arm 1 (22) and arm 23. The activated arm can be remotely controlled by the master hand. The foot pedal of the doctor's control panel also has physical buttons for clutch, endoscope control, and energy activation.

[0085] Specifically, in combination Figure 3 The foot pedal 31, as a component of the doctor's control console, is located below the console and is operated by the user through foot movements. The foot pedal 31 is equipped with multiple physical buttons to trigger switch signals, which are sent to the motion control device. The motion control device processes these signals logically and then issues further instructions. The arm switching button 32 is located on the left side of the pedal. The user needs to apply pressure with the outside of their left foot. The button is triggered by external pressure, but the size, position, contact point, and sensitivity of the button can all affect the efficiency of the operator's operation and patient safety.

[0086] Therefore, in combination Figure 4 This application provides a surgical robot control information generation system. In this embodiment, the surgical robot control information generation system includes a physiological signal acquisition device 410, a processor 420, and a motion control device 430. The physiological signal acquisition device 410 is used to acquire the operator's physiological signals. The processor 420 is used to extract features from the physiological signals to obtain features to be processed, and compares the features to be processed with reference features to obtain the operator's motion type. Based on the operator's motion type, the surgical robot control information is determined. The motion control device 430 is used to control the surgical robot based on the surgical robot control information.

[0087] The physiological signal acquisition device 410 may include at least one of an electromyography (EMG) signal acquisition device and a millimeter-wave radar device. The EMG signal acquisition device acquires EMG signals from the target site of the operator through electrode pads placed on the target site, and the millimeter-wave radar device acquires the operator's heart rate signal.

[0088] Specifically, in combination Figure 5 As shown, where Figure 5 This is a schematic diagram of the acquisition system corresponding to the electromyography (EMG) signal acquisition device in one embodiment. The processor can be the processor in the host computer 74. The EMG signal acquisition device 71 communicates with the host computer 74 via a serial port. At least one electrode pad 72, 73 is attached to the operator's foot. Figure 5 The diagram shows three electrode pads, which are respectively attached to the sides of the operator's ankle and the middle of the foot to collect three electromyographic (EMG) signals. The EMG signal acquisition device 71 collects the three EMG signals through the three electrode pads and sends them to the processor. Optionally, the EMG signal acquisition device 71 includes a signal receiver, a signal amplifier, a digital-to-analog converter, and a data preprocessing module, used to receive the EMG signals collected by the electrode pads, amplify the EMG signals, perform simple preprocessing after digital-to-analog conversion, and send them to the host computer 74.

[0089] Among them, the combination Figure 6 As shown, the electromyography (EMG) signal acquisition device is a portable wearable device. This device includes three epidermal electrodes 91, 92, and 93, positioned at the front and sides respectively. When worn, the front electrode is placed on the back of the foot, and the side electrodes are placed on either side of the ankle. The wearable device is equipped with a Bluetooth module 94, which can transmit signals to a host computer 95 in real time via Bluetooth. The processor acquires the EMG signals from the wearable device, performs superposition, filtering, and time-frequency feature extraction on the three EMG signals, and sends the surgical robot control signals to the motion control device.

[0090] Specifically, in combination Figure 7As shown, Figure 7 This is a schematic diagram of a millimeter-wave radar device in one embodiment. The millimeter-wave radar device can be installed on a doctor's trolley, for example, on the lifting column of the trolley. The height of the trolley column is adjusted so that the radar height is level with the operator's chest, thereby enabling the acquisition of the operator's heart rate signal. The millimeter-wave radar device includes a transmitter, a receiver, an antenna, and a signal processor. A single signal transmitter and antenna 402 are used to generate millimeter-wave signals. The millimeter-wave signals generated by the transmitter have a high frequency and a short wavelength, providing high resolution and detection capability. The transmission direction 406 of the millimeter-wave signals generated by the transmitter is as follows: Figure 7 As shown; two different antennas and receiving circuits 401 are responsible for receiving millimeter-wave signals reflected from the target object, used for receiving and amplifying the reflected signals, with the echo signal receiving direction 404 as shown. Figure 7 As shown, signal processor 402 processes and analyzes the received millimeter-wave signal. Signal processor 405 typically includes components such as an analog-to-digital converter, a digital signal processor, and an algorithm processing unit, used to extract features and information of the target object. Wireless communication mode 403 sends the acquired data signal to the processor for further processing. The processor can calculate the relative angle between the target and the radar through two different receiving antennas.

[0091] Optionally, the surgical robot control information generation system further includes a position acquisition device for acquiring the operator's foot position. The position acquisition device can be a laser positioning device. The processor is also used to acquire the status information of the surgical robot. When the foot position is the target position and the status information is the target status information, the system sends the first information for acquiring the operator's physiological signals to the physiological signal acquisition device.

[0092] In one embodiment, such as Figure 8 As shown, a method for generating control information for a surgical robot is provided, which can be applied to... Figure 4 Taking the processor in the example, the explanation includes the following steps:

[0093] S802: Acquire the collected physiological signals of the operator and extract features from the physiological signals to obtain the features to be processed.

[0094] Optionally, the physiological signals include electromyographic signals from the target site of the operator and / or the operator's heart rate signal. The physiological signals are acquired through at least one of the following methods: acquiring electromyographic signals from the target site of the operator using an electromyographic signal acquisition device; or acquiring the operator's heart rate signal using a millimeter-wave radar device.

[0095] The electromyography signal acquisition device can be, for example, as follows: Figure 5 The electromyography signal acquisition device shown can also be as follows: Figure 6 The portable wearable device shown is not specifically limited here, nor is the number of electrode pads specifically limited. Figure 5 and Figure 6 The device typically uses three electrode pads. In other embodiments, one, two, or more than four electrode pads may be used; no specific limitation is made here. This electromyography (EMG) signal acquisition device can be installed on different parts of the operator's body to acquire EMG signals from different locations. Optionally, if using… Figure 5 The electromyography (EMG) signal acquisition device in the system acquires EMG signals from different parts of the operator's body by adjusting the position of the electrode pads. If using... Figure 6 The electromyography (EMG) signal acquisition device can be worn on different parts of the body.

[0096] Millimeter-wave radar devices, such as Figure 7 As shown, it should be noted that this embodiment uses a millimeter-wave radar device to collect the operator's heart rate signal. Other embodiments may use other methods, which are not specifically limited here. For accuracy, the millimeter-wave radar device is installed on the doctor's trolley, for example, on the lifting column of the doctor's trolley. The height of the doctor's trolley column is adjusted so that the radar height is level with the operator's chest, thereby enabling the collection of the operator's heart rate signal.

[0097] Optionally, the target area can be the foot, knee, or arm. The electromyographic (EMG) signals from the target area include: EMG signals from the operator's foot; or EMG signals from the operator's foot and knee; or EMG signals from the operator's arm and foot; or EMG signals from the operator's foot, knee, and arm. All of the above EMG signals can be acquired using the EMG signal acquisition device described above.

[0098] For convenience, combined Figures 9 to 11 As shown, Figure 9 This is a schematic diagram of an electromyography (EMG) signal acquisition system in one embodiment. Figure 10 This is a schematic diagram of a heart rate signal acquisition system in one embodiment. Figure 11 This is a schematic diagram of an electromyography and heart rate signal acquisition system in one embodiment.

[0099] exist Figure 9 In this process, the electromyography (EMG) signal acquisition device collects EMG signals from the operator's feet and sends them to the processor. The processor then determines the corresponding control information for the surgical robot. Optionally, the EMG signal acquisition device can also collect EMG signals from the operator's arms. Since the emergency stop button on the doctor's trolley is located at the far right end of the armrest, the emergency stop operation is triggered by monitoring the EMG signals of rapid, large-amplitude movements of the operator's right upper arm.

[0100] exist Figure 10 In this process, millimeter-wave radar collects the operator's heart rate signal and sends it to the processor. The processor then determines the corresponding control information for the surgical robot. Optionally, this embodiment may also include an electromyography (EMG) signal acquisition device. This device can collect EMG signals from the operator's arm. Since the emergency stop button on the doctor's trolley is located at the far right end of the armrest, the emergency stop operation is triggered by monitoring the EMG signals of rapid, large-amplitude movements of the operator's right upper arm.

[0101] exist Figure 11 In this process, the electromyography (EMG) signal acquisition device collects EMG signals from the operator's feet and knee joints and sends them to the processor. The processor then determines the corresponding control information for the surgical robot. Optionally, the EMG signal acquisition device can also collect EMG signals from the operator's arms. Since the emergency stop button on the doctor's trolley is located at the far right end of the armrest, the emergency stop operation is triggered by monitoring the EMG signals of rapid, large-amplitude movements of the operator's right upper arm.

[0102] In other embodiments, it can be achieved through Figure 9 The electromyography (EMG) signal acquisition device in the middle collects the EMG signals of the operator's feet and then... Figure 10 The millimeter-wave radar in the system collects the operator's heart rate signal. In other embodiments, it can be used... Figure 9 The electromyography (EMG) signal acquisition device collects EMG signals from the operator's feet and knee joint, and then... Figure 10 The millimeter-wave radar in the system collects the operator's heart rate signal. In other embodiments, the operator's physiological signals can be collected in other ways, which are not specifically limited here.

[0103] The process of extracting features from physiological signals to obtain the features to be processed can involve filtering the physiological signals to obtain useful features. In other embodiments, after filtering the physiological signals, a Fourier transform can be performed on the filtered physiological signals to obtain the corresponding features to be processed. The features to be processed include at least one of the time-domain features and frequency-domain features of muscle contraction, and heart rate features. The time-domain features of muscle contraction can include the amplitude and frequency of muscle contraction. In other embodiments, the time-domain features of muscle contraction can also be other features, which will not be elaborated here. The features to be processed can refer to the features to be processed when the leg muscles contract, the features to be processed when the arm contracts, or the features to be processed when the muscles near the knee joint contract.

[0104] S804: Obtain the pre-generated reference features, each of which corresponds to the operator's motion type.

[0105] Specifically, the reference features are pre-generated and can be based on multiple operators or a single operator. Optionally, each operator has their own reference features, which differ between operators, thus making the acquisition of operator movement types more accurate. These reference features are obtained by pre-executing the corresponding movement type by the operator, then collecting physiological signals from these signals using a physiological signal acquisition device, and performing feature extraction on these signals. Optionally, the processor pre-associates and stores the reference features with the movement type.

[0106] Optionally, obtaining the reference features may involve obtaining the reference features corresponding to the operator.

[0107] S806: Compare the feature to be processed with each reference feature to obtain the operator's movement type.

[0108] Specifically, the feature to be processed is compared with the corresponding reference feature, that is, the feature to be processed is compared with the reference feature associated with each motion type.

[0109] Optionally, the reference feature corresponding to each movement type may include at least one. For example, when physiological signals are acquired through at least one electrode, the physiological signals acquired by different electrodes correspond to one reference feature. In other embodiments, the physiological signals acquired by different electrodes may correspond to only one reference feature, which is not specifically limited here. The comparison of the feature to be processed with each reference feature can be performed sequentially or in parallel with the reference features corresponding to each movement type. When multiple physiological signals are acquired through multiple electrodes and multiple features to be processed are extracted, the extracted features to be processed are compared with the corresponding reference features, that is, the features to be processed and reference features of the corresponding electrodes are compared to obtain the operator's movement type.

[0110] S808: Generates surgical robot control information corresponding to the operator's movement type. The surgical robot control information is used to control the surgical robot.

[0111] In one embodiment, generating surgical robot control information corresponding to the operator's movement type includes generating at least one of the following: robotic arm switching control information, clutch control information, endoscope control information, target electrocoagulation control information, target electroresection control information, and stop operation information corresponding to the operator's movement type.

[0112] Specifically, the processor pre-stores the association between motion type and surgical robot control information. The processor queries the surgical robot control information based on the motion type and sends the queried surgical robot control information to the motion control device, so that the motion control device controls the surgical robot based on the surgical robot control information.

[0113] The above-mentioned method for generating surgical robot control information acquires the physiological signals of the operator, extracts features from the physiological signals to obtain the features to be processed, and compares the features to be processed with the pre-generated reference features to obtain the operator's movement type, thereby generating surgical robot control information corresponding to the operator's movement type. This software-based control is more accurate and more sensitive than physical buttons.

[0114] In one embodiment, the physiological signal is an electromyographic (EMG) signal; feature extraction of the physiological signal to obtain the features to be processed includes: filtering the EMG signal; obtaining a reference frequency; and performing a Fourier transform on the filtered EMG signal using the reference frequency to obtain the features to be processed.

[0115] Among them, the combination Figure 12 As shown, Figure 12 This is a force analysis diagram of the foot in one embodiment. The operator's foot is usually in a static state, and the force situation is as follows. Figure 12 In the static state, the foot is in equilibrium, with low muscle activation and low frequency domain characteristics of electromyography (EMG). When the foot triggers the pedal with the outer side, it experiences a lateral force Fu. This force disappears when the foot leaves the pedal. Simultaneously, during arm switching, the heel remains stationary while the forefoot moves, causing the ankle joint to deflect at approximately 20 degrees. When the foot is pressed down, it experiences a counterforce in the vertical direction, effective only on the rising edge. Therefore, the frequency and time domain characteristics of its EMG signal are quite pronounced. For this purpose, this embodiment employs a Butterworth filtering algorithm, characterized by a maximally flat frequency response curve within the passband, without fluctuations, while gradually decreasing to zero in the stopband.

[0116] Specifically, in combination Figure 13 and Figure 14 As shown, where Figure 13 This is a schematic diagram of the original electromyographic signal. Figure 14 This is a schematic diagram of the signal after filtering by a Butterworth filter. The Butterworth filter can be used to filter and denoise electromyography (EMG) signals. The formula for the squared magnitude of the frequency response of an nth-order low-pass Butterworth filter is:

[0117]

[0118] Where n is the filter order, the larger n is, the better the approximation between the passband and the stopband, and the steeper the transition band will be, H is the amplitude, ω is the operating frequency, and ωc is the cutoff frequency, which is the frequency at which the amplitude drops to -3 dB. Figure 13 The diagram in the middle is a schematic of the original electromyographic signal, where δ1 is the passband tolerance, i.e., the allowable passband deviation, and δ2 is the stopband tolerance, i.e., the allowable stopband deviation.

[0119] Among them, the combination Figure 15 As shown, Figure 15 This is a schematic diagram illustrating the extraction of electromyographic signal features using Fourier transform in one embodiment, where the formula for Fourier transform is:

[0120]

[0121] Where f(t) is a non-periodic function, i.e., an electromyographic signal, and F(ω) is the frequency domain representation of this function, e -iωt It is a complex exponential function, ω is the angular frequency of 2πf. f is the reference frequency of the basis function. Low-frequency and high-frequency reference functions are obtained by changing the magnitude of the frequency. The reference signal is multiplied by the time-domain signal f(t) to obtain an eigenvalue. Figure 15 In the diagram, 201 represents the original electromyographic signal, 202 represents the reference function, and 203 represents the electromyographic signal characteristics obtained after Fourier transform.

[0122] Combination Figure 16 As shown, Figure 16 This is a waveform diagram of the electromyography (EMG) signal processing in this embodiment. In this embodiment, EMG signals are acquired using three electrode pads to obtain three channels of EMG signals. The three channels of EMG signals are processed separately, or optionally in parallel. First, the EMG signals of the three channels are filtered separately, and then Fourier transforms are performed on the filtered EMG signals to obtain three sets of EMG signal features.

[0123] It should be noted that the feature extraction process of standard physiological signals also involves the feature extraction steps mentioned above. If the standard physiological signal is processed, the reference features, motion type and reference frequency need to be associated and stored after processing. After obtaining the physiological signal of the corresponding operator, the corresponding feature to be processed is extracted through the reference frequency and compared with the corresponding reference feature to determine the motion type.

[0124] In one embodiment, the physiological signal is a heart rate signal; feature extraction of the physiological signal to obtain the features to be processed includes: filtering the heart rate signal to obtain the features to be processed.

[0125] There is a certain relationship between foot movement and heart rate. When the feet move, the body's muscles require more oxygen and nutrients for energy, which necessitates the heart to increase the rate of blood and oxygen delivery, thus increasing the heart rate. When switching arms, the foot moves from a stationary state to a leftward rotation with the heel as the fulcrum, requiring the foot muscles to contract and relax, generating power and propelling the body. When muscles contract, the demand for oxygen and nutrients increases, requiring the heart to increase the rate of blood and oxygen delivery to meet the muscles' needs, resulting in changes in the heart rate waveform. When switching arms, the operator stops the master-slave operation, and only foot movement occurs, eliminating interference from other operations on the heart rate signal. In this embodiment, the heart rate signal is extracted by irradiating the human body with electromagnetic waves and analyzing the amplitude and phase relationship between the micro-movements of the human body and the echo in the reflected waves, thereby establishing a mapping relationship between the operator's movement type and the heart rate signal.

[0126] Combination Figure 17 As shown, according to the radar measurement principle, when the receiving and transmitting electromagnetic wave modules are at the same position as the target, their phase angle and wavelength have the following relationship: ω = 4πΔd / λ. When two receiving antennas are used to receive signals, the relative angle between the target and the radar can be measured. Assuming the angle between the target and the antenna direction is θ, and the distance between the two receiving antennas is d, then according to the properties of right-angle trigonometric functions, we have Δd = dsin(θ). Since ω = 2πΔd / λ, where ω is the phase difference, λ is the wavelength, and Δd is the distance difference between the two waves, we can deduce that the relative angle between the target and the radar is θ = sin^-1(λω / 2πd).

[0127] Specifically, in combination Figure 18 The processor separates the heart rate signal from the original signal, filters the signal, and obtains the heart rate frequency domain result. Let the error threshold be δ, and the amplitude of the real-time heart rate signal be P. с The reference characteristic amplitude is P о Then we have: when |P с -P о When |≤δ, obtain the corresponding motion type; when |P с -P о When |>δ, maintain the current state.

[0128] In one embodiment, the physiological signal includes at least two different types of physiological signals; feature extraction of the physiological signal to obtain the feature to be processed includes: performing frequency band transformation on each different type of physiological signal to obtain different types of physiological signals in the same frequency band; merging the different types of physiological signals in the same frequency band to obtain a composite signal; and filtering the composite signal to obtain the feature to be processed.

[0129] Specifically, in combination Figure 19As shown, in the time domain, signal superposition can be achieved by adding the sample values ​​of each signal. Let the electromyography signal and the heart rate signal be X1(n) and X2(n) respectively, and their sample values ​​be X1(0), X1(1), X1(2), ..., X2(0), X2(1), X2(2), ..., then their superimposed signal is Y(n) = X1(n) + X2(n), as shown. Figure 19 The superposition of signals in the frequency domain produces a new spectrum. Specifically, their spectra are added together, i.e., Y(ω) = X1(ω) + X2(ω). This means that in the frequency domain, the spectra of two or more signals can be superimposed to obtain their combined spectrum. When performing arm switching, assuming that the operator's foot movements and heart rate changes occur simultaneously, time-domain signal superposition can achieve more effective signal filtering and noise reduction. By superimposing two signals, more information can be obtained, and the characteristics and behavior of the signals can be better understood.

[0130] It should be noted that the different types of physiological signals that can be superimposed in this embodiment are for the same body part, such as the feet. Different types of physiological signals from different body parts cannot be superimposed. Specifically, the type of foot movement is characterized by electromyography (EMG) signals and heart rate signals from the foot, so the two can be superimposed. However, the EMG signals from the foot and the arm cannot be superimposed because the EMG signals from the foot are used to characterize foot movement, while the EMG signals from the arm are used to characterize hand movement.

[0131] In the above embodiments, by extracting features from physiological signals using different methods to obtain the features to be processed, a better understanding of the signal's characteristics and behavior can be achieved. Furthermore, it should be noted that the feature extraction process for the reference signal is similar to the feature extraction process for the physiological signal when generating reference features.

[0132] In one embodiment, before acquiring the pre-generated reference features, the method further includes: acquiring pre-set operator movement types; collecting standard physiological signals corresponding to the operator movement types of each operator; extracting features from each standard physiological signal to obtain reference features corresponding to each operator; and establishing the association between the reference features of each operator and the operator movement type.

[0133] This embodiment mainly introduces the generation of reference features. To facilitate the association between reference features and operator movement types, the data model is used to combine the reference features and movement types. First, the operator's movement types are classified, and the association between the operator's movement types and surgical robot control information is determined. Then, the association between the operator's movement types and the operator's reference features is determined. This yields the association between the operator's reference features, operator movement types, and surgical robot control information. Subsequently, after obtaining the operator's features to be processed, the operator's movement type can be determined based on the data model. Then, based on the association between the operator's movement type and surgical robot control information, the corresponding surgical robot control information can be obtained. The acquisition of the association between the operator's movement type and the operator's reference features is illustrated using foot movement as an example:

[0134] Left and right feet still Surgical preparation no No signal Move your left and right feet left and right Position adjustment no No signal Left foot outside press arm switch pedal Arm switching External compressive force Arm switching control information Move your left and right feet forward and backward Position adjustment no No signal Step forward with your left foot past the endoscope pedal and press down. Depress the clutch Upward reaction force Clutch control information Left foot forward to the endoscope pedal but not the clutch pedal and then press down. Step on endoscope Upward reaction force Endoscopic control information Move your right foot forward and to the left and step on the pedal (in conjunction with the laser). Step on left electrocoagulation / electrocuting Upward reaction force Left electrocoagulation / electrocuting control information Move your right foot forward and to the right and step on the pedal (in conjunction with the laser). Step on right electrocoagulation / electrocuting Upward reaction force Right electrocoagulation / electrocuting control information

[0135] The processor collects standard physiological signals of the operator under corresponding foot movements, extracts reference features from the standard physiological signals according to the feature extraction method described above, and then establishes the association between the operator's reference features and the operator's movement type.

[0136] The association between the operator's movement type and the surgical robot's control information is pre-set, and can be either a one-to-one correspondence or a non-one-to-one correspondence. In one optional embodiment, the operator's movement type corresponds to a single piece of surgical robot control information only when it includes at least two movements. Specifically, the left electrocoagulation or left electrosurgical resection control information is triggered only when the operator's movement type includes a first movement of moving the right foot forward to the left and a second movement of pressing down with the right foot. In other embodiments, a single piece of surgical robot control information can correspond to different movement types of different parts of the operator's body, such as a single piece of surgical robot control information corresponding to the operator's foot movement and arm movement. In this embodiment, the association between the operator's movement type and the surgical robot's control information can be set according to actual circumstances and is not limited to the specific association given in this embodiment.

[0137] It should be noted that if the standard physiological signal is a multi-channel signal, the extracted reference features also include multiple channels, thereby establishing the correlation between the reference features of multiple channels and the operator's movement type.

[0138] Optionally, when extracting reference features through Fourier transform, the corresponding reference frequency is also stored, so that in actual processing, the physiological signal can be used to extract features to be processed through the reference frequency.

[0139] When the script actions are represented by heart rate signals, the above data model can be:

[0140]

[0141] The intention refers to the control intention of the surgical robot. Based on this intention, the corresponding surgical robot control information is obtained. Similarly, the relationship between the surgical robot control information and the operator's movement type in this embodiment is also preset and is not limited to the relationship between foot movements and intentions in the table above.

[0142] Optionally, each operator has their own reference features, and the reference features of different operators are different, so as to make the acquisition of the operator's motion type more accurate.

[0143] In the above embodiments, reference features corresponding to the operator are generated in advance, so that each operator has its own reference features, which makes the results more accurate.

[0144] In one embodiment, before acquiring the physiological signals of the operator, the process includes: acquiring the foot position of the operator; acquiring the state information of the surgical robot; and when the foot position is the target position and the state information is the target state information, sending the first information of the physiological signals of the operator to the physiological signal acquisition device.

[0145] In this embodiment, the operator's foot position can be obtained using a laser positioning device. This position is then sent to the processor. The processor determines that the foot position is the target position and that the surgical robot is in the target state, such as a master-slave state. The processor then sends the first information for collecting the operator's physiological signals to the physiological signal acquisition device, causing the device to begin collecting these signals. The state of the surgical robot can be obtained by the processor from the motion control device.

[0146] In the above embodiments, to avoid accidental triggering, the physiological signal acquisition device is activated by determining the operator's foot position and the state of the surgical robot, making it more intelligent.

[0147] In one embodiment, after generating surgical robot control information corresponding to the operator's movement type, the method further includes: sending second information to stop collecting the operator's physiological signals to the physiological signal acquisition device, wherein the physiological signal acquisition device is used to stop collecting the operator's physiological signals based on the second information; and after controlling the surgical robot based on the surgical robot control information, the method further includes: sending third information to restart collecting the operator's physiological signals to the physiological signal acquisition device, wherein the physiological signal acquisition device is used to restart collecting the operator's physiological signals based on the third information.

[0148] To avoid the repeated generation of surgical robot control information, after generating the control information corresponding to the operator's movement type, the processor sends a second message to the physiological signal acquisition device to stop physiological signal acquisition. After the surgical robot is controlled based on the control information, the processor resends a third message to the physiological signal acquisition device to resume physiological signal acquisition. This avoids generating new, identical control information during the control process, thus preventing consistently high processor resource utilization.

[0149] For ease of understanding, the surgical robot control information generation method in this application is illustrated using the following four embodiments:

[0150] In the first embodiment, when the operator's foot is in the target position and the surgical robot is in a master-slave state, electromyography (EMG) signals from the operator's foot are collected by an EMG signal acquisition device. Feature extraction is performed on these EMG signals to obtain the features to be processed. These features are then compared with pre-generated reference features to determine the movement type. Based on the movement type, control information is determined and sent to a motion control device. The motion control device controls the movement of the surgical robot. After the movement is completed, for example, after the robotic arm switch is completed, the system continues to determine whether the operator's foot is in the target position and whether the surgical robot is in a master-slave state, until the surgery ends. The reference features are generated preoperatively. Before surgery, the operator's foot movements are classified, and the corresponding EMG signals for each category are obtained and processed to obtain the reference features. The association between these reference features and foot movements is stored. Furthermore, before feature extraction, the collected EMG signals can be filtered, amplified, and denoised to improve signal quality and stability.

[0151] Optionally, the physiological signal acquisition device can be a wearable device. When the laser signal detects that the foot has been placed in the correct position, it sends the signal to the processor. At the same time, the processor obtains the current state of the surgical robot from the motion control device. If it is in master-slave state, it starts to receive electromyographic signals sent by the wearable device through the Bluetooth module.

[0152] In the second embodiment, the clutch, endoscope, left and right electrocoagulation, and electrocautery control method involves moving the foot forward and then stepping down. The fore-and-aft position of the foot needs to be determined by the electromyographic signal of the knee joint movement distance. Therefore, electrode pads are placed on the surgeon's ankle, instep, and knee. The electromyographic features of the ankle and instep determine whether a stepping motion has occurred, while the knee joint signal features are used to determine the fore-and-aft distance of foot movement. Therefore, when establishing the data model preoperatively, multiple electromyographic signals need to be collected and feature extracted. The data model is generated based on the reference features extracted from the electromyographic signals of different locations and the corresponding movement types.

[0153] When the operator's feet are in the target position and the surgical robot is in master-slave mode, electromyography (EMG) signals from the operator's feet and knee joints are collected by an EMG signal acquisition device. Feature extraction is performed on these EMG signals to obtain features to be processed. These features are then compared with pre-generated corresponding reference features. For example, the features to be processed for the knee joint are compared with the reference features for the knee joint, and the features to be processed for the feet are compared with the reference features for the feet. Based on the comparison results, control information for the surgical robot is obtained and sent to the motion control device. The motion control device controls the movement of the surgical robot. After the movement is completed, such as clutch engagement, endoscopy, left and right electrocoagulation, or electrocautery, the surgical robot continues to determine whether the operator's feet are in the target position and whether the surgical robot is in master-slave mode until the surgery is completed.

[0154] In the third embodiment, a millimeter-wave radar device is mounted on the lifting column of the surgical trolley. The height of the trolley column is adjusted so that the radar height is level with the operator's chest. The operator's scripted movements are characterized by heart rate signals. Before surgery, heart rate signals are collected when the feet are stationary and during different movement types. Reference features are extracted, and a data model is established. During surgery, when the operator's feet are in the target position and the surgical robot is in a master-slave state, the millimeter-wave radar device collects the operator's heart rate signal. Feature extraction is performed on this heart rate signal to obtain the features to be processed. These features are compared with the pre-generated reference features to determine the movement type. Based on the movement type, control information is determined and sent to the motion control device. The motion control device controls the movement of the surgical robot. After the movement is completed, such as after the robotic arm switch is completed, it continues to determine whether the operator's feet are in the target position and whether the surgical robot is in a master-slave state until the surgery ends.

[0155] In the fourth embodiment, the surgical robot is controlled by superimposing electromyography (EMG) signals and heart rate signals. EMG signals from the ankle are acquired when the foot is stationary, moving, or in an arm-switching state; radar echo signals are acquired and heart rate signals are calculated when the foot is stationary, moving, or in an arm-switching state; the EMG and heart rate signals are frequency-converted; the two signals are superimposed in the same frequency band; the composite signal is filtered; and superimposed feature signals of different foot states are extracted to establish a data model. During the surgery, the current EMG and heart rate signals of the foot are acquired in real time, and the EMG and heart rate signals are superimposed and feature extracted to obtain the current feature to be processed. The current feature to be processed is compared with the model data to determine whether it meets the arm-switching position conditions; the processor generates an arm-switching control signal and sends it to the motion control device; the motion control device issues a command to the patient carriage to perform arm switching; after the arm switching is completed, a prompt message is given, and the next signal detection cycle begins. Similarly, other types of movement and control information of the surgical robot can also be implemented in this way, which will not be elaborated further here.

[0156] In the above embodiments, arm switching via electromyography (EMG) signal recognition avoids the influence of the physical location of the hardware on the arm switching foot pedal trigger signal, reducing deviations caused by operation without direct visual guidance. The operator triggers arm switching with slight foot movements, reducing the control force applied to the side of the foot and improving ease of use. The operator does not need to move their feet extensively to find the arm switching pedal position, reducing the switching process between foot pedals and improving surgical efficiency. EMG signals replace the physical buttons on the arm switching foot pedal, avoiding the sensitivity degradation problem caused by long-term use of the physical foot pedal and increasing surgical safety.

[0157] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0158] Based on the same inventive concept, this application also provides a surgical robot control information generation device for implementing the surgical robot control information generation method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the surgical robot control information generation device provided below can be found in the limitations of the surgical robot control information generation method described above, and will not be repeated here.

[0159] In one embodiment, such as Figure 20 As shown, a surgical robot control information generation device is provided, including: a feature extraction module 2001, a reference feature acquisition module 2002, a comparison module 2003, and a control information generation module 2004, wherein:

[0160] The feature extraction module 2001 is used to acquire the physiological signals of the operator and extract features from the physiological signals to obtain the features to be processed.

[0161] The reference feature acquisition module 2002 is used to acquire pre-generated reference features, each of which corresponds to the operator's motion type.

[0162] The comparison module 2003 is used to compare the feature to be processed with each reference feature to obtain the operator's movement type;

[0163] The control information generation module 2004 is used to generate surgical robot control information corresponding to the operator's movement type. The surgical robot control information is used to control the surgical robot.

[0164] In one embodiment, the feature extraction module 2001 acquires the collected physiological signals of the operator by at least one of the following methods: acquiring electromyographic signals of the target part of the operator acquired by an electromyographic signal acquisition device; or acquiring the heart rate signal of the operator acquired by a millimeter-wave radar device.

[0165] In one embodiment, the feature extraction module 2001 is further configured to acquire electromyographic signals of the operator's feet collected by the electromyographic signal acquisition device; or acquire electromyographic signals of the operator's feet and knee joints collected by the electromyographic signal acquisition device; or acquire electromyographic signals of the operator's arms and feet collected by the electromyographic signal acquisition device; or acquire electromyographic signals of the operator's feet, knee joints and arms collected by the electromyographic signal acquisition device.

[0166] In one embodiment, the physiological signal is an electromyographic signal; the feature extraction module 2001 is also used to filter the electromyographic signal; obtain a reference frequency, and perform a Fourier transform on the filtered electromyographic signal using the reference frequency to obtain the features to be processed.

[0167] In one embodiment, the physiological signal is a heart rate signal; the feature extraction module 2001 is also used to filter the heart rate signal to obtain the features to be processed.

[0168] In one embodiment, the physiological signal includes at least two different types of physiological signals; the feature extraction module 2001 is further used to perform frequency band transformation on each different type of physiological signal to obtain different types of physiological signals in the same frequency band; merge the different types of physiological signals in the same frequency band to obtain a composite signal; and filter the composite signal to obtain the feature to be processed.

[0169] In one embodiment, the surgical robot control information generation device further includes: a reference feature generation module, used to acquire pre-set movement types of each operator; collect standard physiological signals corresponding to the movement types of each operator; extract features from each standard physiological signal to obtain reference features corresponding to each operator; and establish the association between the reference features of each operator and the movement type of each operator.

[0170] In one embodiment, the control information generation module 2004 is further configured to generate at least one of the following: robotic arm switching control information, clutch control information, endoscope control information, target electrocoagulation control information, target electrocautery control information, and stop operation information, corresponding to the operator's movement type.

[0171] In one embodiment, the surgical robot control information generation device further includes:

[0172] The foot position acquisition module is used to acquire the foot position of the operator being collected.

[0173] The status information acquisition module is used to acquire the status information of the surgical robot;

[0174] The first information sending module is used to send the first information of the physiological signal of the operator to the physiological signal acquisition device when the foot position is the target position and the status information is the target status information.

[0175] In one embodiment, the surgical robot control information generation device further includes:

[0176] The second information sending module is used to send a second information to stop collecting the operator's physiological signals to the physiological signal acquisition device, and the physiological signal acquisition device is used to stop collecting the operator's physiological signals based on the second information.

[0177] The third information sending module is used to send third information to the physiological signal acquisition device to restart the acquisition of the operator's physiological signals. The physiological signal acquisition device is used to restart the acquisition of the operator's physiological signals based on the third information.

[0178] Each module in the aforementioned surgical robot control information generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0179] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 21 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for generating control information for a surgical robot. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0180] Those skilled in the art will understand that Figure 21 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0181] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0182] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0183] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0184] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0185] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0186] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A surgical robot control information generation method characterized by comprising: The method includes: Acquire the collected physiological signals of the operator, and extract features from the physiological signals to obtain the features to be processed; Acquire pre-generated reference features, each of which corresponds to an operator's motion type; The feature to be processed is compared with each of the reference features to obtain the operator's movement type; Generate surgical robot control information corresponding to the operator's movement type, the surgical robot control information being used to control the surgical robot; The generation of surgical robot control information corresponding to the operator's movement type includes: Generate at least one of the following: robotic arm switching control information, clutch control information, endoscope control information, target electrocoagulation control information, target electrosurgery control information, and stop operation information, corresponding to the operator's movement type; The operator's physiological signals include: electromyographic signals of the target area of ​​the operator and the operator's heart rate signal; The step of extracting features from the physiological signal to obtain the features to be processed includes: Frequency band transformation is performed on the electromyographic signals of the target area and the heart rate signals of the operator to obtain different types of physiological signals in the same frequency band; Different types of physiological signals in the same frequency band are combined to obtain composite signals; The composite signal is filtered to obtain the feature to be processed.

2. The method of claim 1, wherein, The electromyographic signals of the operator's target site include: Electromyographic signals from the operator's feet; or Electromyographic (EMG) signals from the operator's feet and knee joint; or Electromyographic (EMG) signals from the operator's arm and foot; or The electromyographic (EMG) signals from the operator's feet, knees, and arms.

3. The method of claim 1, wherein, The features to be processed include at least one of the time-domain features and frequency-domain features of muscle contraction, and heart rate features.

4. The method of claim 1, wherein, The physiological signal is an electromyographic signal; the feature extraction of the physiological signal to obtain the features to be processed includes: The electromyographic signal is filtered. A reference frequency is obtained, and the filtered electromyographic signal is subjected to a Fourier transform using the reference frequency to obtain the feature to be processed; or the physiological signal is a heart rate signal.

5. The method of claim 1, wherein, The physiological signals include at least two different types of physiological signals.

6. The method of claim 1, wherein, Before obtaining the pre-generated reference features, the process also includes: Obtain the pre-set motion types of each operator; Standard physiological signals corresponding to the operator's movement type were collected from each operator. Feature extraction is performed on each of the standard physiological signals to obtain reference features corresponding to each operator; Establish the association between the reference features of each operator and the movement type of the operator.

7. The method according to any one of claims 1 to 6, characterized in that, Before acquiring the collected physiological signals of the operator, the process includes: Obtain the foot position of the operator being monitored; Obtain the status information of the surgical robot; When the foot position is the target position and the status information is the target status information, the first information of the physiological signal acquisition operator is sent to the physiological signal acquisition device.

8. The method according to any one of claims 1 to 6, characterized in that, After generating surgical robot control information corresponding to the operator's movement type, the method further includes: A second message to stop collecting the operator's physiological signals is sent to the physiological signal acquisition device, which is used to stop collecting the operator's physiological signals based on the second message; After controlling the surgical robot based on the surgical robot control information, the process includes: A third message is sent to the physiological signal acquisition device to restart the acquisition of the operator's physiological signals based on the third message.

9. A surgical robot control information generation device, characterized in that, The device includes: The feature extraction module is used to acquire the operator's physiological signals, including electromyography (EMG) signals from the target area and the operator's heart rate signal. The module then performs feature extraction on these physiological signals to obtain features to be processed. This includes: performing frequency band transformation on the EMG signals from the target area and the operator's heart rate signal to obtain different types of physiological signals within the same frequency band; merging these different types of physiological signals within the same frequency band to obtain a composite signal; and filtering the composite signal to obtain the features to be processed. The reference feature acquisition module is used to acquire pre-generated reference features, each of which corresponds to an operator's motion type. The comparison module is used to compare the feature to be processed with each of the reference features to obtain the movement type of the operator; The control information generation module is used to generate surgical robot control information corresponding to the operator's movement type, including: generating at least one of the following: robotic arm switching control information, clutch control information, endoscope control information, target electrocoagulation control information, target electroresection control information, and stop operation information corresponding to the operator's movement type; the surgical robot control information is used to control the surgical robot.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

Images