Control method of staple cartridge, electric anastomat and storage medium

Abstract

The invention belongs to the technical field of medical instruments, and provides a control method of a nail bin, an electric anastomat and a storage medium, and the control method comprises the following steps: if it is determined that a connecting rod is connected, entering a to-be-identified nail bin state; if the nail bin is identified, judging the nail bin; if the nail bin is to be used and is not matched with the electric anastomat, waiting to replace another matched nail bin; if yes, playing staple cartridge information corresponding to the staple cartridge; the voice enhancement method based on the improved first-order differential microphone array identifies user voice features to obtain voice feedback information, and judges whether the staple cartridge information meets the anastomosis requirement or not; if yes, motion parameters of a driving motor are set based on the staple cartridge stroke; if a user presses down the control button, the driving motor is controlled to rotate forwards to complete nail discharging and anastomosis work, and if the driving motor reaches a preset stroke, the driving motor is controlled to rotate backwards to complete tool retracting; the situation that the nail bin is mistakenly installed due to manual judgment and nail bin replacement is avoided; and the accuracy and efficiency of speech recognition are improved.

Description

Technical Field

[0001] The present application belongs to the field of medical device technology, and in particular relates to a control method for a staple cartridge, an electric stapler, and a storage medium. Background Art

[0002] An electric stapler is a medical device frequently used during surgical operations on physiological tissues. In general surgical treatments, electric staplers are often used to complete tissue anastomosis. Depending on the needs of different surgeries, the corresponding gun body stapler of the electric stapler needs to be equipped with working components of different lengths and models. The stapler is disposable and cannot be reused. With current electric staplers, the operator manually determines whether the stapler matches the surgical requirements and then changes the stapler model. It is easy for the operator to make errors in judgment and operation, resulting in the installation and use of the wrong stapler. The misinstalled stapler increases the cost of the surgery and increases the risk of the surgery. There is also a method of confirming the replacement of the stapler with an electric stapler through voice interaction, but there is a problem of inaccurate voice recognition in the operating room environment, which introduces additional risks.

[0003] The existing technology has the problem of manual judgment and replacement of the nail magazine resulting in misinstallation or inaccurate recognition of the replacement nail magazine during voice interaction confirmation operation, resulting in misinstallation. Summary of the Invention

[0004] The present application provides a control method for a staple cartridge, an electric stapler, and a storage medium, which can solve the problem of misinstallation caused by manual judgment and replacement of the staple cartridge or misinstallation caused by inaccurate recognition of the replacement staple cartridge during voice interaction confirmation operation.

[0005] In a first aspect, the present application provides a method for controlling a stapler, which is applied to an electric stapler. The electric stapler includes a connecting rod, a fixing rod, a radio frequency identification module, an anvil, a voice module, a control module, a control button assembly, and a drive motor. The stapler is movably connected to the anvil. Control methods include: If the control module determines that the connecting rod is connected, the radio frequency identification module enters the nail magazine waiting for identification state; If the RFID module has identified the staple cartridge, the control module determines whether the staple cartridge is ready for use and whether the staple cartridge is compatible with the electric stapler; If the staple cartridge is ready for use and does not match the electric stapler, wait for replacement with another staple cartridge that matches the electric stapler; if the staple cartridge is ready for use and matches the electric stapler, the voice module plays the staple cartridge information corresponding to the staple cartridge, which includes the staple cartridge model, staple cartridge stroke, and titanium staple height; After playing the nail magazine information, the voice module identifies the user's voice features based on the improved first-order differential microphone array voice enhancement method to obtain voice feedback information corresponding to the user's voice features. The control module determines whether the nail magazine information meets the work requirements based on the voice feedback information. If the stapler information meets the requirements of the stapler work, the control module sets the motion parameters of the drive motor based on the stapler stroke, and the voice module prompts the electric stapler to enter the work-ready state; If the user presses the control button in the control button assembly, the control module controls the drive motor to rotate forward to complete the nail removal and anastomosis work. If the drive motor has reached the preset stroke, the control module controls the drive motor to reverse to complete the knife retraction.

[0006] In one embodiment, the control module determines that the connecting rod is engaged, including: If the connecting rod is screwed into the barrel connection port of the fixed rod, a connection signal of the connecting rod is triggered, and the control module obtains the connection signal to determine that the connecting rod is connected.

[0007] In one embodiment, a method for improving speech enhancement using a first-order differential microphone array includes: Acquire initial continuous speech of any duration using two microphones, where the angle formed by the line connecting the two microphones and the direction of the sound source is greater than or equal to an angle threshold; Removing a DC component from the continuous speech to obtain a first continuous speech signal; framing the first continuous speech signal to obtain a framed first continuous speech signal; A speech beam is formed by iterating the signal weights corresponding to the two channels in the first continuous speech signal after frame division until the mean square error between the output signal synthesized by the continuous speech signals of the two channels and the expected signal is minimized; After performing short-time Fourier transform on the speech beam, the noise spectrum of each frame is determined using the noise spectrum calculation formula; Divide the noise spectrum into a preset number of sub-bands, and determine the sub-band average speech spectrum for each sub-band using the corresponding spectrum subtraction formula; The phase difference determined by the improved phase difference calculation formula is used to perform phase correction on the sub-band average speech spectrum and signal reconstruction to determine the reconstructed speech spectrum; The reconstructed speech spectrum is subjected to inverse short-time Fourier transform to obtain a pure speech enhancement signal.

[0008] In one embodiment, a speech beam is formed by iterating the signal weights corresponding to the two channels in the first continuous speech signal after frame division until the mean square error between the output signal synthesized by the continuous speech signals of the two channels and the desired signal is minimized, including: The signal weights corresponding to the two channels in the first continuous speech signal after framing are iterated using a weight iterative calculation formula, and the weight values ​​of the two-channel microphones are dynamically adjusted by gradient descent until the mean square error between the output signal synthesized by the continuous speech signal of the two channels and the expected signal is minimized. Then, the speech beam is synthesized through the signal model.

[0009] In one embodiment, the weight iterative calculation formula is:

[0010] in, For the i microphones n The weight of the speech signal at time +1; For the i microphones n The weight of the speech signal at each moment; is the step length; is the error signal, i.e., the difference between the reference signal and the output signal, where the reference signal is the main axis channel signal of the microphone array and the output signal is the signal of the speech beamformation; For the i microphones n The voice signal at the moment.

[0011] In one embodiment, the noise spectrum is calculated as:

[0012] in, For the m Frame No. k Noise spectrum of the frequency point; For the m- Frame 1 k Noise spectrum of the frequency point; is the proportionality coefficient; For the m Frame No. k Power spectrum of frequency points; For the m Frame No. k The probability of speech existence at a frequency point.

[0013] In one embodiment, the spectrum subtraction calculation formula is:

[0014] in, is the sub-band average speech spectrum; Sub-band m Frame No. k Power spectrum of noisy speech at each frequency point; is the over-reduction factor of the sub-band; is the spectrum lower limit factor of the sub-band; For the k Noise spectrum of noisy speech at certain frequency points.

[0015] In one embodiment, the improved phase difference calculation formula is:

[0016] in, is the signal phase mask; is the average value of the pure speech signal; Sub-band m Frame No. k Power spectrum of noisy speech at each frequency point; is the phase of pure speech signal; is the phase of the noisy speech signal.

[0017] In a second aspect, the present application provides an electric stapler comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the contents of the first aspect when executing the computer program.

[0018] In a third aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method as described in any one of the contents of the first aspect.

[0019] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0020] Compared with the prior art, the present invention has the following beneficial effects: A control method for a nail magazine of the present application is applied to an electric stapler, which includes a connecting rod, a fixing rod, a radio frequency identification module, a nail support, a voice module, a control module, a control button assembly and a driving motor, and the nail magazine is movably connected to the nail support; if the control module determines that the connecting rod is connected, the radio frequency identification module enters a nail magazine state to be identified; if the radio frequency identification module has identified the nail magazine, the control module determines whether the nail magazine is ready for use and whether the nail magazine matches the electric stapler; if the nail magazine is ready for use and the nail magazine does not match the electric stapler, then wait for replacement with another nail magazine that matches the electric stapler; if the nail magazine is ready for use and the nail magazine matches the electric stapler, the voice module plays the nail magazine information corresponding to the nail magazine, and the nail magazine information includes the nail magazine model, nail magazine stroke and titanium nail height; after playing the nail magazine information, the voice module recognizes the user's voice features based on the voice enhancement method of the improved first-order difference microphone array to obtain voice feedback information corresponding to the user's voice features, and the control module determines whether the nail magazine information meets the requirements of the stapler based on the voice feedback information. requirements; if the stapler information meets the stapling work requirements, the control module sets the motion parameters of the drive motor based on the stapler stroke, and the voice module prompts the electric stapler to enter the working ready state; if the user presses the control button in the control button assembly, the control module controls the drive motor to rotate forward to complete the staple removal and stapling work. If the drive motor has reached the preset stroke, the control module controls the drive motor to reverse to complete the retraction; compared with the existing technology, since the present application identifies the stapler through the radio frequency identification module, the control module determines whether the stapler is to be used and whether the stapler matches the electric stapler, thereby avoiding the situation where the stapler is misinstalled due to manual judgment and replacement of the stapler; in addition, since the speech enhancement method of the improved first-order differential microphone array is used to identify the user's voice features and obtain voice feedback information corresponding to the user's voice features, the environmental noise such as the instrument movement in the operating room environment is filtered out, and the accuracy of the speech recognition of the user's voice features and the voice feedback information is improved, and the accuracy and efficiency of the correct replacement of the stapler are further improved, and the additional risk of misinstallation of the stapler is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 1 is a schematic structural diagram of an electric stapler to which a control method for a staple cartridge provided in one embodiment of the present application is applied; Figure 2 1 is a schematic top view of the structure of an electric stapler to which a control method for a staple cartridge provided in one embodiment of the present application is applicable; Figure 3 This is a flow chart of a method for controlling a staple cartridge provided in one embodiment of the present application; Figure 4 1 is a flow chart of a method for speech enhancement using an improved first-order differential microphone array according to an embodiment of the present application; Figure 5 This is a time domain diagram of the channel 1 speech signal in the initial continuous speech with a duration of 3.5 seconds obtained according to an embodiment of the present application; Figure 6 This is a time domain diagram of the channel 2 speech signal in the initial continuous speech with a duration of 3.5 seconds provided in an embodiment of the present application; Figure 7 Schematic diagram of the angle formed by the line connecting two microphones and the direction of the sound source provided by an embodiment of the present application; Figure 8 Schematic diagram of the voiceprint of the initial continuous speech provided in one embodiment of the present application; Figure 9 This is a schematic diagram of a voiceprint completed by extracting speech features using a speech enhancement method using an improved first-order differential microphone array provided in an embodiment of the present application.

[0023] Reference numerals: 1. Gun body; 2. Fixing rod; 3. Connecting rod; 4. Anvil; 5. Protective cover assembly; 6. Steering knob; 7. Voice module; 8. Barrel connection port; 121. Control button assembly; 122. Safety button assembly; 13. Radio frequency identification module. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0025] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0026] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0027] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0029] Current electric staplers require operators to manually determine whether the staple cartridge matches the surgical requirements before replacing the cartridge. This can easily lead to the wrong cartridge being installed due to operator error, increasing surgical costs and risks. Alternatively, electric staplers can use voice interaction to confirm cartridge changes, but this can be subject to inaccurate voice recognition in operating room environments, creating additional risks.

[0030] In order to partially solve the above technical problems, the present application provides a control method for a staple cartridge, which is applied to an electric stapler, such as Figure 1 、 Figure 2As shown, the electric stapler includes a connecting rod 3, a fixing rod 2, a radio frequency identification module 13, a nail holder 4, a voice module 7, a control module (not shown in the figure), a control button assembly 121 and a drive motor (not shown in the figure), and the nail magazine is movably connected to the nail holder 4; the control method includes: if the control module determines that the connecting rod 3 is connected, the radio frequency identification module 13 enters a nail magazine state to be identified; if the radio frequency identification module 13 has identified the nail magazine, the control module determines whether the nail magazine is ready for use and whether the nail magazine matches the electric stapler; if the nail magazine is ready for use and the nail magazine does not match the electric stapler, wait for replacement of another nail magazine that matches the electric stapler; if the nail magazine is ready for use and the nail magazine matches the electric stapler, the voice module 7 plays the nail corresponding to the nail magazine. The stapler information includes the stapler model, stapler stroke and titanium staple height; after playing the stapler information, the voice module 7 identifies the user's voice features based on the voice enhancement method of the improved first-order differential microphone array to obtain voice feedback information corresponding to the user's voice features, and the control module determines whether the stapler information meets the stapling work requirements based on the voice feedback information; if the stapler information meets the stapling work requirements, the control module sets the motion parameters of the drive motor based on the stapler stroke, and the voice module 7 prompts the electric stapler to enter the work-ready state; if the user presses the control button in the control button assembly 121, the control module controls the drive motor to rotate forward to complete the staple removal and stapling work. If the drive motor has reached the preset stroke, the control module controls the drive motor to reverse to complete the knife retraction. Compared with the prior art, since the present application identifies the nail magazine through the radio frequency identification module 13, the control module determines whether the nail magazine is ready for use and whether the nail magazine matches the electric stapler, thereby avoiding the situation where the nail magazine is misinstalled due to manual judgment and replacement of the nail magazine; in addition, since the speech enhancement method of the improved first-order differential microphone array is used to identify the user's voice features and obtain voice feedback information corresponding to the user's voice features, the environmental noise such as the instrument movement in the operating room environment is filtered out, the accuracy of the speech recognition of the user's voice features and the voice feedback information is improved, and the accuracy and efficiency of the correct replacement of the nail magazine are further improved, and the additional risk of misinstallation of the nail magazine is reduced.

[0031] It should be noted that if Figure 1 、 Figure 2 As shown, the electric stapler also includes a gun body 1, a protective cover assembly 5, a steering knob 6, a barrel connection port 8, and a safety button assembly 122. The voice module 7 includes two microphones, the connection between which forms an angle with the sound source to enhance the voice signal from the user's direction. The stapler information also includes disinfection records, usage counts, and expiration dates. The radio frequency identification module 13 obtains the corresponding stapler information by identifying the unique code of the RFID electronic chip on the stapler clamp, which is used to track disinfection records, usage counts, and expiration dates.

[0032] The technical solution of this application is described below through specific embodiments.

[0033] The first aspect of the present application provides a control method for a staple cartridge, which is applied to an electric stapler, such as Figure 3 As shown, the control method includes: S1, if the control module determines that the connecting rod is connected, the radio frequency identification module enters the state of the nail magazine to be identified.

[0034] In one embodiment, after the electric stapler is powered on and initialized, the control module includes a microcontroller chip (MCU), which detects whether the connecting rod is correctly connected. After the control module of the electric stapler determines that the connecting rod is connected, it turns on the radio frequency identification module, and the radio frequency identification module enters the state of the stapler to be identified, that is, the radio frequency identification module transmits a first radio frequency signal and enters the state of searching for the stapler to be identified.

[0035] In one embodiment, the control module determines that the connecting rod is engaged, including: If the connecting rod is screwed into the barrel connection port of the fixed rod, a connection signal of the connecting rod is triggered, and the control module obtains the connection signal to determine that the connecting rod is connected.

[0036] S2, if the radio frequency identification module has identified the staple cartridge, the control module determines whether the staple cartridge is ready for use and whether the staple cartridge matches the electric stapler.

[0037] In one embodiment, after the RFID tag of the staple magazine holder enters the recognition range of the radio frequency identification module, the radio frequency identification module receives the second radio frequency signal emitted by the identification module in the RFID electronic chip, and identifies the RFID electronic chip of the staple magazine holder within the recognition range. If the radio frequency identification module has identified the staple magazine, the RFID electronic chip sends the staple magazine information to the radio frequency identification module through the energy of the induced current, and the radio frequency identification module then sends the staple magazine information to the control module. The control module determines whether the staple magazine is ready for use and whether the staple magazine matches the electric stapler.

[0038] S3, if the staple cartridge is ready for use and the staple cartridge does not match the electric stapler, wait for replacement with another staple cartridge that matches the electric stapler; if the staple cartridge is ready for use and the staple cartridge matches the electric stapler, the voice module plays the staple cartridge information corresponding to the staple cartridge.

[0039] In one embodiment, the nail magazine information includes the nail magazine model, nail magazine stroke and titanium nail height. If the nail magazine is ready for use and the nail magazine does not match the electric stapler, the voice module plays that the nail magazine does not match the electric stapler, and then wait to replace another nail magazine that matches the electric stapler; if the nail magazine is ready for use and the nail magazine matches the electric stapler, the voice module plays the nail magazine information corresponding to the nail magazine.

[0040] S4, after playing the nail warehouse information, the voice module identifies the user's voice features based on the improved first-order differential microphone array voice enhancement method to obtain voice feedback information corresponding to the user's voice features. The control module determines whether the nail warehouse information meets the work requirements based on the voice feedback information.

[0041] In one embodiment, since the electric stapler requires extremely high voice recognition accuracy in the operating room, the MCU of the electric stapler of the present application is an embedded system based on the STM32 series, which integrates a voice enhancement method of an improved first-order differential microphone array. After the voice module plays the stapler information, the voice module recognizes the user's voice features through the voice enhancement method of the improved first-order differential microphone array, and obtains voice feedback information corresponding to the user's voice features. The control module determines whether the stapler information meets the stapling work requirements based on the voice feedback information; the data processing efficiency under the STM32 series embedded system is improved, and the voice processing performance of the MCU is improved while maintaining low complexity.

[0042] S5, if the stapler information meets the requirements of the stapler work, the control module sets the motion parameters of the drive motor based on the stapler stroke, and the voice module prompts the electric stapler to enter the work ready state.

[0043] In one embodiment, if the stapler information meets the requirements of the stapler work, the control module sets the motion parameters of the drive motor based on the stapler stroke, and the voice module prompts the electric stapler to enter the working ready state, waiting for the user to press the safety button in the safety button assembly to be activated.

[0044] S6, if the user presses the control button in the control button assembly, the control module controls the drive motor to rotate forward to complete the nail removal and anastomosis work. If the drive motor has reached the preset stroke, the control module controls the drive motor to rotate reversely to complete the knife retraction.

[0045] In one embodiment, after the user presses the safety button in the safety button assembly to activate the working ready state, if the user presses the control button in the control button assembly, the MCU of the control module controls the drive motor to move forward in the forward direction (i.e., away from the gun body) to complete the nail removal and anastomosis work. If the drive motor has reached the preset stroke, the MCU of the control module controls the drive motor to move in the reverse direction to the starting position to complete the knife retraction; the user does not need to rely on manual visual judgment to determine whether the preset stroke has been reached.

[0046] This application combines RFID radio frequency identification method, voice broadcast, and voice recognition method to verify the nail magazine when the electric stapler is installed, preventing the risks of repeated use of the nail magazine and the inability to assemble and affect the surgical operation due to mismatch between the nail magazine and the stapler. Through voice broadcast and voice recognition, the user can eliminate the risk of incorrect installation of the nail magazine in advance, and automatically complete the operation by driving the motor with the MCU, thereby improving the accuracy of the operation, greatly reducing the risk of misuse of the nail magazine during stapler surgery, and improving the efficiency and accuracy of the operation.

[0047] The spectral subtraction of the first-order difference (or frequency domain) microphone array in the existing technology (i.e., the FDM-SS algorithm) has certain defects in terms of real-time requirements, computational complexity, microphone position calibration, and non-stationarity of environmental noise, which causes the electric stapler to reduce the accuracy of recognizing user voice in the operating room environment and increase the delay of voice recognition. Therefore, this application provides a speech enhancement method for improving the first-order difference microphone array to partially solve the above technical problems.

[0048] In one embodiment, Figure 4 As shown, the speech enhancement method of improving the first-order differential microphone array includes: S41: Acquire initial continuous speech of any duration through two microphones, where an angle formed by a line connecting the two microphones and a direction of a sound source is greater than or equal to an angle threshold.

[0049] In one embodiment, two microphones are used to obtain an initial continuous speech of any duration, for example, two microphones are used to obtain an initial continuous speech of 3.5 seconds, such as Figure 5 、 Figure 6 As shown, Figure 5 This is the time domain diagram of the channel 1 speech signal in the initial continuous speech with a duration of 3.5 seconds. Figure 6 This is a time domain diagram of the channel 2 speech signal in the initial continuous speech with a duration of 3.5 seconds.

[0050] The two-microphone differential array of the existing FDM-SS algorithm requires a fixed direction (e.g. θ =0°, that is, the angle formed by the line between the two microphones and the direction of the sound source θ =0°), if the user's sound source moves or the direction of the sound source changes, the effect of adaptive beamforming will be reduced, and thus the effect of speech recognition will be reduced; in this embodiment, if Figure 7 As shown, the angle formed by the line between the two microphones and the direction of the sound source θ The angle is greater than or equal to the angle threshold, and 90°≥angle threshold≥10°, and the distance d between the two microphones is ≤4 cm, thereby improving the ability to track the sound source.

[0051] S42: Remove the DC component from the continuous speech to obtain a first continuous speech signal.

[0052] In this embodiment, various medical equipment noises in the operating room environment, such as the prompt sounds of anesthetics and monitors, are low-frequency signals. By removing the DC component of the collected initial continuous voice signal to obtain the first continuous voice signal, the impact of environmental noise on voice recognition is reduced, and the accuracy of voice recognition is improved.

[0053] S43: Divide the first continuous speech signal into frames to obtain a framed first continuous speech signal.

[0054] S44, forming a speech beam by iterating the signal weights corresponding to the two channels in the first continuous speech signal after frame division until the mean square error between the output signal synthesized by the continuous speech signals of the two channels and the expected signal is minimized.

[0055] In one embodiment, a speech beam is formed by iterating the signal weights corresponding to the two channels in the first continuous speech signal after framing until the mean square error between the output signal synthesized from the two-channel continuous speech signal and the desired signal is minimized. This includes: iterating the signal weights corresponding to the two channels in the first continuous speech signal after framing using a weight iteration calculation formula, dynamically adjusting the weight values ​​of the two-channel microphones through gradient descent until the mean square error between the output signal synthesized from the two-channel continuous speech signal and the desired signal is minimized, and then synthesizing the speech beam using a signal model to reduce the synthesized beam error caused by sound source movement or noise direction changes. That is, first, a single-channel speech signal in the first continuous speech signal after framing is adaptively filtered using a minimum mean square error method, the weight of the single-channel speech signal is recursively updated in real time, and the microphone weights are adjusted in real time using a weight iteration calculation formula until the mean square error between the output signal synthesized from the two-channel continuous speech signal and the desired signal is minimized, thereby achieving sound source tracking; then, the two single-channel speech signals from the two microphones are beamsynthesized using the signal model to form a speech beam.

[0056] In one embodiment, the signal model of the speech beam is:

[0057] in, for n The speech signal of dual-microphone beamforming at all times; is the weight of the first microphone speech signal; is the weight of the second microphone speech signal; For the first microphone n Voice signal at each moment; For the second microphonen The voice signal at the moment.

[0058] In one embodiment, the weight iterative calculation formula is:

[0059] in, For the i microphones n The weight of the speech signal at time +1; For the i microphones n The weight of the speech signal at each moment; is the step size, which is used to control the adaptive filtering speed, that is, to control the speed of gradient descent to balance convergence and stability; is the error signal, i.e., the difference between the reference signal and the output signal, where the reference signal is the main axis channel signal of the microphone array and the output signal is the signal of the speech beamformation; For the i microphones n The voice signal at the moment.

[0060] S45, after performing short-time Fourier transform on the speech beam, the noise spectrum of each sub-frame is determined using a noise spectrum calculation formula.

[0061] The existing FDM-SS algorithm detects speech signals in silent segments on the premise that the noise is a stationary signal, and its effect is relatively poor in a non-stationary noise environment.

[0062] In this embodiment, after performing a short-time Fourier transform (STFT) on the speech beam, the beam power spectrum of each frame is calculated frame by frame, the minimum power of each frequency band within the time window is tracked, and the probability of speech presence is determined based on the preset ratio threshold of the power spectrum to the minimum power. , then recursively updates the noise spectrum of each frame in real time using the noise spectrum calculation formula. This enhances voice detection and improves speech recognition accuracy even in the unstable noise environment of the operating room. Specifically, before Fourier transforming the signal, a window function, such as a Hamming window, is applied to the frames (e.g., 256 points per frame) to prevent spectrum leakage.

[0063] In one embodiment, determining the probability of speech presence includes: First determine the local energy S(k,m) = |Y(k,m)| 2 , and then track the historical minimum S min(k,m) (for example, the time window length is 256 points), and then calculate the ratio I(k,m) = S(k,m) / S min (k, m), where I is the signal-to-noise ratio. When the signal-to-noise ratio is large enough, it is considered that a speech signal exists. Then a ratio threshold is set. If I(k, m) > the ratio threshold δ (the ratio threshold δ is 2-5), it is marked as a candidate for speech. Finally, by comparing it with the prior signal-to-noise ratio, the probability of speech existence I(k, m) is obtained, which is equivalent to a table lookup operation to determine the probability of speech existence.

[0064] In one embodiment, the noise spectrum is calculated as:

[0065] in, For the m Frame No. k Noise spectrum of the frequency point; For the m- Frame 1 k Noise spectrum of the frequency point; is the proportionality coefficient; For the m Frame No. k Power spectrum of frequency points; For the m Frame No. k The probability of speech existence at a frequency point.

[0066] S46, dividing the noise spectrum into a preset number of sub-bands, and determining the sub-band average speech spectrum for each sub-band using a corresponding spectrum subtraction calculation formula.

[0067] After obtaining the noise spectrum, the spectral subtraction method in the existing FDM-SS algorithm adjusts the size of the noise spectrum by controlling the global over-subtraction factor and the spectrum floor factor. However, for noise of different frequencies, the over-subtraction factor and the spectrum floor factor are not adjusted accordingly, resulting in high-frequency distortion or residual noise.

[0068] In this embodiment, the noise spectrum is divided into a preset number of sub-bands, and the sub-band average speech spectrum is determined for each sub-band by a corresponding spectral subtraction formula. The preset number is 3 to 10, that is, a corresponding over-subtraction factor and spectral floor factor are set for each sub-band in a different frequency range, thereby suppressing broadband noise.

[0069] In one embodiment, the spectral subtraction calculation formula is:

[0070] in, is the sub-band average speech spectrum; Sub-band m Frame No. k Power spectrum of noisy speech at each frequency point; is the over-reduction factor of the sub-band; is the spectrum lower limit factor of the sub-band; For the k The noise spectrum of the noisy speech at the frequency point, max () is the maximum value of the two equations in the brackets.

[0071] In one embodiment, when the first sub-band is a low frequency band of 0-2 kHz, is 1.0~1.2, is 0.01~0.015; and when the second sub-band is the high frequency band 4~8kHz, 1.5~2.0, is 0.02~0.025; when the third sub-band is the mid-frequency band 2~4kHz, is 1.5, is 0.015; thus, a corresponding over-subtraction factor and spectrum floor factor are set for each sub-band in a different frequency range, thereby suppressing broadband noise and avoiding user voice distortion.

[0072] S47, using the phase difference determined by the improved phase difference calculation formula to perform phase correction and signal reconstruction on the sub-band average speech spectrum to determine a reconstructed speech spectrum.

[0073] In the prior art FDM-SS algorithm, the phase of the noisy signal is used as the phase of the reconstructed speech spectrum signal, resulting in distortion of the reconstructed speech spectrum signal.

[0074] In this embodiment, the phase difference determined by the improved phase difference calculation formula is used to perform phase correction and signal reconstruction on the sub-band average speech spectrum to determine the reconstructed speech spectrum of each sub-band, wherein the phase difference determined by the improved phase difference calculation formula is the phase difference between the average value of the pure speech signal and the noisy speech signal, thereby reducing the distortion degree of the reconstructed speech spectrum signal.

[0075] In one embodiment, the improved phase difference calculation formula is:

[0076] in, is the signal phase mask; is the average value of the pure speech signal, is the average value of the average speech spectra of multiple sub-bands; Sub-band m Frame No. kPower spectrum of noisy speech at each frequency point; is the phase of pure speech signal; is the phase of the noisy speech signal.

[0077] In one embodiment, when the phase of the noise signal used to reconstruct the speech spectrum signal is independent of the phase of the speech signal, the improved phase difference calculation formula can be simplified to an amplitude ratio, which is:

[0078] in, is the signal phase mask; is the average value of the pure speech signal; Sub-band m Frame No. k Power spectrum of noisy speech at a certain frequency point.

[0079] S48, performing an inverse short-time Fourier transform on the reconstructed speech spectrum to obtain a pure speech enhancement signal.

[0080] In one embodiment, the improved first-order differential microphone array speech enhancement method is applied on an MCU based on an STM32 series embedded system. The real-time data obtained are shown in Table 1. The actual measurement results of the existing FDM-SS algorithm and the improved first-order differential microphone array speech enhancement method (i.e., improved FDM-SS) in the same environment are compared and shown in Table 2. The improved first-order differential microphone array speech enhancement method of the present application achieves more robust speech enhancement on the same embedded platform. That is, after adopting the improved FDM-SS method, the speech enhancement method is more robust when the steady-state noise rises (e.g., from 8.2dB to 11.5dB) and the non-steady-state noise rises (e.g., from 6.1dB to 9. 8dB), it also improves the naturalness of the user's synthesized speech signal (for example, from 3.4 to 4.0), thereby further improving the accuracy of speech recognition when the ambient noise rises; in addition, since the human brain requires 150~300ms of processing time to recognize and understand speech content, and the national cochlear implant registration standard stipulates that the speech conversion time is ≤150ms, although the end-to-end delay of the improved FDM-SS in this application has increased by 5ms, the end-to-end delay is only 50ms, which is much less than the human brain processing time and the standard speech conversion time, so it still meets the real-time requirements, provides a reliable solution for far-field voice interaction of low-resource devices, and is more suitable for use in operating room environments. This embodiment also performs MFCC (Mel Frequency Cepstral Coefficient) on the enhanced speech to extract speech features and complete voiceprint comparison, such as Figure 8 、 Figure 9 As shown, Figure 8 is a schematic diagram of the voiceprint of the original speech signal. Figure 9Schematic diagram of voiceprint comparison completed by extracting speech features using the improved first-order differential microphone array speech enhancement method (i.e., improved FDM-SS).

[0081] Table 1 Real-time performance data of the speech enhancement method based on the improved first-order differential microphone array on the MCU of the STM32 series embedded system

[0082] Table 2 Comparison of the measured results of the existing FDM-SS algorithm and the improved first-order differential microphone array speech enhancement method in the same environment

[0083] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0084] In a second aspect, the present application provides an electric stapler comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the contents of the first aspect when executing the computer program.

[0085] In a third aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method as described in any one of the contents of the first aspect.

[0086] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0087] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form.

[0088] The computer-readable medium may include at least any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunications signals, and software distribution media. Examples include USB flash drives, external hard drives, magnetic disks, or optical disks. In some jurisdictions, due to legislation and patent practice, computer-readable media cannot include electric carrier signals or telecommunications signals.

[0089] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0090] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0091] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0092] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0093] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for controlling a nail magazine, characterized in that: Applied to an electric stapler, the electric stapler includes a connecting rod, a fixing rod, a radio frequency identification module, an anvil, a voice module, a control module, a control button assembly and a drive motor, and the staple cartridge is movably connected to the anvil; Control methods include: If the control module determines that the connecting rod is connected, the radio frequency identification module enters the nail magazine waiting for identification state; If the RFID module has identified the staple cartridge, the control module determines whether the staple cartridge is ready for use and whether the staple cartridge is compatible with the electric stapler; If the staple cartridge is ready for use and does not match the electric stapler, wait for replacement with another staple cartridge that matches the electric stapler; if the staple cartridge is ready for use and matches the electric stapler, the voice module plays the staple cartridge information corresponding to the staple cartridge, which includes the staple cartridge model, staple cartridge stroke, and titanium staple height; After playing the nail magazine information, the voice module identifies the user's voice features based on the improved first-order differential microphone array voice enhancement method to obtain voice feedback information corresponding to the user's voice features. The control module determines whether the nail magazine information meets the work requirements based on the voice feedback information. If the stapler information meets the requirements of the stapler work, the control module sets the motion parameters of the drive motor based on the stapler stroke, and the voice module prompts the electric stapler to enter the work-ready state; If the user presses the control button in the control button assembly, the control module controls the drive motor to rotate forward to complete the nail removal and anastomosis work. If the drive motor has reached the preset stroke, the control module controls the drive motor to reverse to complete the knife retraction.

2. The method for controlling a staple cartridge according to claim 1, wherein: The control module determines the connecting rod engagement, including: If the connecting rod is screwed into the barrel connection port of the fixed rod, a connection signal of the connecting rod is triggered, and the control module obtains the connection signal to determine that the connecting rod is connected.

3. The method for controlling a staple cartridge according to claim 1, wherein: The speech enhancement method for improving the first-order difference microphone array includes: Acquire initial continuous speech of any duration using two microphones, where the angle formed by the line connecting the two microphones and the direction of the sound source is greater than or equal to an angle threshold; Removing a DC component from the continuous speech to obtain a first continuous speech signal; framing the first continuous speech signal to obtain a framed first continuous speech signal; A speech beam is formed by iterating the signal weights corresponding to the two channels in the first continuous speech signal after frame division until the mean square error between the output signal synthesized by the continuous speech signals of the two channels and the expected signal is minimized; After performing short-time Fourier transform on the speech beam, the noise spectrum of each frame is determined using the noise spectrum calculation formula; Divide the noise spectrum into a preset number of sub-bands, and determine the sub-band average speech spectrum for each sub-band using the corresponding spectrum subtraction formula; The phase difference determined by the improved phase difference calculation formula is used to perform phase correction on the sub-band average speech spectrum and signal reconstruction to determine the reconstructed speech spectrum; The reconstructed speech spectrum is subjected to inverse short-time Fourier transform to obtain a pure speech enhancement signal.

4. The method for controlling a staple cartridge according to claim 3, wherein: A speech beam is formed by iterating the signal weights corresponding to the two channels in the first continuous speech signal after frame division until the mean square error between the output signal synthesized by the continuous speech signals of the two channels and the desired signal is minimized, including: The signal weights corresponding to the two channels in the first continuous speech signal after framing are iterated using a weight iterative calculation formula, and the weight values ​​of the two-channel microphones are dynamically adjusted by gradient descent until the mean square error between the output signal synthesized by the continuous speech signal of the two channels and the expected signal is minimized. Then, the speech beam is synthesized through the signal model.

5. The method for controlling a staple cartridge according to claim 4, wherein: The weight iterative calculation formula is: in, For the i microphones n The weight of the speech signal at time +1; For the i microphones n The weight of the speech signal at each moment; is the step length; is the error signal, i.e., the difference between the reference signal and the output signal, where the reference signal is the main axis channel signal of the microphone array and the output signal is the signal of the speech beamformation; For the i microphones n The voice signal at the moment.

6. The method for controlling a staple cartridge according to claim 3, wherein: The noise spectrum calculation formula is: in, For the m Frame No. k Noise spectrum of the frequency point; For the m- Frame 1 k Noise spectrum of the frequency point; is the proportionality coefficient; For the m Frame No. k Power spectrum of frequency points; For the m Frame No. k The probability of speech existence at a frequency point.

7. The method for controlling a staple cartridge according to claim 3, wherein: The calculation formula for spectral subtraction is: in, is the sub-band average speech spectrum; Sub-band m Frame No. k Power spectrum of noisy speech at each frequency point; is the over-reduction factor of the sub-band; is the spectrum lower limit factor of the sub-band; For the k Noise spectrum of noisy speech at certain frequency points.

8. The method for controlling a staple cartridge according to claim 3, wherein: The improved phase difference calculation formula is: in, is the signal phase mask; is the average value of the pure speech signal; Sub-band m Frame No. k Power spectrum of noisy speech at each frequency point; is the phase of pure speech signal; is the phase of the noisy speech signal.

9. An electric stapler comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images