A global oral instrument voice intelligent control method and system

Abstract

The application relates to a global oral cavity instrument voice intelligent control method and system, which comprises the following steps: acquiring the device type, working state, executable function, parameter adjustment range and safety limit condition of the current oral cavity instrument, and calling the corresponding special instruction domain; collecting a diagnosis and treatment environment sound signal, identifying an oral cavity diagnosis and treatment noise type and carrying out noise reduction processing to obtain a target voice signal; identifying a preset wake-up word and a function instruction in an offline state to generate a to-be-executed control instruction; verifying the special instruction domain, the working state, the executable function, the parameter adjustment range and the safety limit condition, converting into a device control parameter after verification, and performing a corresponding operation; and performing conflict processing according to multi-channel control input during the execution process, and outputting a feedback prompt. Therefore, the compatibility, anti-interference and safety of the oral cavity instrument voice control are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology for dental medical devices, and in particular to a voice-based intelligent control method and system for all-domain dental devices. Background Technology

[0002] Dental treatment typically involves the use of various dental instruments, such as light-cured tube machines, root canal motors, periodontal treatment devices, implant machines, micro-power systems, and dental laser treatment devices. Different dental instruments have different operating modes, output power, speed, torque, irrigation status, and program calling methods, requiring dentists to frequently adjust parameters, switch modes, or control the start and stop of treatments according to the stage of the procedure.

[0003] Most existing dental instruments are controlled by buttons, knobs, touch panels, or foot switches. For handheld dental instruments, the number of buttons that can be set on the device surface is limited to meet the requirements of waterproofing, sterilization, and miniaturization, making multi-level menu switching or combination button operation relatively complicated. For large dental instruments such as implant machines, micro-power systems, and dental laser treatment devices, doctors usually need to operate them through foot pedals or control panels, which results in low efficiency of intraoperative adjustments and easily interrupts the continuous treatment process.

[0004] Meanwhile, the dental treatment environment is filled with complex noises such as motor sounds, water flow sounds, suction sounds, air jet sounds, instrument collision sounds, and conversations. Conventional voice control methods are prone to inaccurate recognition or false triggering. Directly applying conventional voice recognition technology to dental instrument control, especially for high-risk operations such as start / stop, power adjustment, speed adjustment, torque adjustment, or laser output, could compromise equipment safety. Furthermore, some voice recognition solutions rely on network processing, which is not conducive to meeting the requirements of real-time response, data security, and offline use in medical settings.

[0005] Therefore, existing dental instrument control methods suffer from problems such as inconvenient operation, insufficient compatibility with all types of equipment, weak anti-interference capability of intraoperative voice recognition, insufficient safety against accidental touch, and poor coordination capability of multiple control channels. Summary of the Invention

[0006] To at least partially overcome the problems in related technologies where the control of dental instruments relies on button, foot pedal, or touch operation, resulting in inconvenience during operation, insufficient compatibility with all types of equipment, poor accuracy of voice recognition under complex diagnostic and treatment noise, and easy mis-triggering of high-risk control commands, this application provides a full-domain intelligent voice control method and system for dental instruments.

[0007] The proposed solution is as follows:

[0008] According to a first aspect of the embodiments of this application, a method for intelligent voice control of a full-domain dental instrument is provided, comprising: The system obtains the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety restrictions. Based on the device type and executable functions, it calls the dedicated instruction field corresponding to the current dental instrument from the preset global instruction library. The dedicated instruction field only contains the mode switching instructions, parameter adjustment instructions, start / stop control instructions, and program call instructions that the current dental instrument is allowed to execute. Collect sound signals from the treatment environment, identify the types of oral treatment noise in the sound signals, and perform corresponding noise reduction processing according to the types of oral treatment noise to obtain the target speech signal; In offline mode, speech recognition is performed on the target speech signal. When the target speech signal contains a preset wake word and a function instruction in sequence, a control instruction to be executed is generated according to the function instruction. When the preset wake word or the function instruction is missing, the generation of the control instruction to be executed is prohibited. Based on the dedicated instruction field, the working status, the executable function, the parameter adjustment range, and the safety restrictions, the legality and security of the control instruction to be executed are verified. If the verification is successful, the control instruction to be executed is converted into device control parameters, and the current dental instrument is controlled to perform the corresponding operation. If the verification fails, execution is rejected and a prompt is output. During the execution of the corresponding operation, at least one control input is received from voice input, key input, foot pedal input, and swing input, and conflict is handled according to the preset safety priority, with emergency stop control input having the highest priority. Obtain the execution feedback information of the current dental instrument, and output feedback prompts based on the execution feedback information.

[0009] Preferably, identifying the type of oral treatment noise in the sound signal of the treatment environment, and performing corresponding noise reduction processing according to the type of oral treatment noise, includes: Sound features are extracted from the sound signals of the treatment environment to determine the type of oral treatment noise; When the type of oral diagnosis and treatment noise includes at least one of motor noise, water flow noise, saliva suction noise, air jet noise, instrument collision noise, background conversation noise and environmental echo, the noise reduction strategy corresponding to the type of oral diagnosis and treatment noise is invoked. The noise reduction strategy is used to suppress the noise in the diagnostic environment to obtain the target speech signal.

[0010] Preferably, performing speech recognition on the target speech signal offline includes: Upon recognizing the preset wake word, the current dental instrument enters the command receiving state; In the instruction receiving state, the function instruction is identified, and it is determined whether the function instruction belongs to the dedicated instruction domain; If the function instruction belongs to the dedicated instruction domain, then the control instruction to be executed is generated; If the function instruction does not belong to the dedicated instruction domain, the control instruction to be executed will not be generated and an invalid instruction prompt will be output.

[0011] Preferably, the legality verification includes: Determine whether the control instruction to be executed belongs to the dedicated instruction domain; Determine whether the control object corresponding to the control instruction to be executed belongs to the executable function; Determine whether the target parameter corresponding to the control instruction to be executed is within the parameter adjustment range; When all of the above judgment results are satisfied, the control instruction to be executed is determined to have passed the legality check.

[0012] Preferably, the security verification includes: Determine the risk level of the control instruction to be executed; When the control instruction to be executed is a start / stop control instruction, power increase instruction, speed increase instruction, torque increase instruction, program call instruction or laser output instruction, the control instruction to be executed is identified as a high-risk control instruction. For the high-risk control command, determine whether the current dental instrument meets the execution conditions based on the working status and the safety constraints; If the execution conditions are not met, the high-risk control instruction will be refused to be executed.

[0013] Preferably, converting the control command to be executed into device control parameters includes: The control category corresponding to the control instruction to be executed is determined based on the device type; When the control category is mode switching, mode switching parameters are generated; When the control category is parameter adjustment, a target parameter value or parameter increase / decrease amount is generated; When the control category is start-stop control, start parameters, stop parameters, or pause parameters are generated. When the control category is program call, preset program call parameters are generated.

[0014] Preferably, conflict handling is performed according to a preset security priority, including: When different control inputs correspond to control intentions Figure 1When the control intent is reached, the operation corresponding to the control intent is executed; When different control inputs correspond to inconsistent control intentions, compare the safety priorities corresponding to each control input; If any control input is an emergency stop control input, then the current output of the current dental instrument is immediately stopped; If no emergency stop control input is available, a control input with lower safety risk is executed, or the current dental instrument is put into a pause state and a conflict warning is output.

[0015] Preferably, obtaining the execution feedback information of the current dental instrument and outputting feedback prompts based on the execution feedback information includes: The actual execution state of the current dental instrument is obtained, and the actual execution state is compared with the target execution state corresponding to the device control parameters; If the actual execution status matches the target execution status, then an execution success message will be output. If the actual execution state is inconsistent with the target execution state, an execution exception prompt will be output, and the current operation will be stopped, restricted, or maintained depending on the exception type. The feedback prompts include at least one of light prompts, sound prompts, vibration prompts, and interface prompts.

[0016] Preferably, based on the device type and the executable function, a dedicated instruction domain corresponding to the current dental instrument is called from a preset global instruction library, including: Based on the device type, the current dental instrument is determined to be either a handheld dental instrument or a large dental instrument; Based on the executable function, candidate control instructions that match the current dental instrument are selected from the preset global instruction library; Based on the parameter adjustment range and the safety constraints, the candidate control commands are filtered to obtain the dedicated command domain.

[0017] According to a second aspect of the embodiments of this application, a full-domain dental instrument voice intelligent control system is provided, including: a device information acquisition unit, a command domain calling unit, a sound acquisition unit, a noise reduction processing unit, an offline speech recognition unit, a command verification unit, a control execution unit, a multi-channel input unit, a conflict handling unit, and a feedback prompting unit; The device information acquisition unit is used to acquire the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety restrictions; The instruction domain calling unit is used to call a dedicated instruction domain corresponding to the current dental instrument from a preset global instruction library based on the device type and the executable function. The dedicated instruction domain only contains mode switching instructions, parameter adjustment instructions, start / stop control instructions and program calling instructions that the current dental instrument is allowed to execute. The sound acquisition unit is used to acquire sound signals from the medical environment. The noise reduction processing unit is used to identify the type of oral diagnosis noise in the sound signal of the diagnosis environment, and perform corresponding noise reduction processing according to the type of oral diagnosis noise to obtain the target speech signal; The offline speech recognition unit is used to perform speech recognition on the target speech signal in an offline state, and when the target speech signal contains a preset wake word and a function instruction in sequence, it generates a control instruction to be executed according to the function instruction. The instruction verification unit is used to perform legality verification and security verification on the control instruction to be executed based on the dedicated instruction field, the working state, the executable function, the parameter adjustment range, and the security restrictions. The control execution unit is used to convert the control instruction to be executed into device control parameters after the legality verification and security verification are passed, and to control the current dental instrument to perform the corresponding operation. The multi-channel input unit is used to receive at least one control input among voice input, key input, foot pedal input, and swing input; The conflict handling unit is used to handle conflicts of different control inputs according to preset safety priorities, wherein emergency stop control inputs have the highest priority. The feedback prompting unit is used to obtain the execution feedback information of the current dental instrument and output feedback prompts based on the execution feedback information.

[0018] The technical solution provided in this application may include the following beneficial effects: The technical solution provided in this application obtains the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety constraints, and calls a dedicated command domain accordingly. This enables voice control commands to match the actual functions and safety boundaries of the current dental instrument, preventing inappropriate commands from being executed and improving the compatibility and control safety of dental instruments across the entire range.

[0019] By identifying the types of oral treatment noise in the treatment environment and performing corresponding noise reduction processing for different noise types, the target speech signal can be extracted in complex noise environments such as motor noise, water flow noise, saliva suction noise, air jet noise, instrument collision noise, and background conversation noise, thereby improving the accuracy and stability of intraoperative speech recognition.

[0020] By recognizing target voice signals in offline mode and generating control commands to be executed by sequentially triggering preset wake words and function commands, the system can complete voice control without relying on external networks. At the same time, it can avoid directly triggering device actions after misrecognizing a single voice word, reducing the risk of false triggering.

[0021] By combining a dedicated instruction domain, operating status, executable functions, parameter adjustment range, and safety restrictions, the legality and safety of the control instructions to be executed are verified. This can eliminate control operations that exceed the scope, privileges, or safety conditions before the instructions are executed, which is particularly beneficial for improving the safety of operations such as start-stop control, power regulation, speed regulation, torque regulation, and program calls.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0024] Figure 1 This is a flowchart illustrating a full-domain oral instrument voice intelligent control method according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a full-domain oral instrument voice intelligent control system provided in one embodiment of this application.

[0025] Reference numerals: Device information acquisition unit-21; Command field call unit-22; Sound acquisition unit-23; Noise reduction processing unit-24; Offline speech recognition unit-25; Command verification unit-26; Control execution unit-27; Multi-channel input unit-28; Conflict handling unit-29; Feedback prompt unit-30. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] Example 1 Figure 1 This is a flowchart illustrating a full-domain oral instrument voice intelligent control method according to an embodiment of this application, with reference to... Figure 1 A method for intelligent voice control of dental instruments across the entire field of vision, comprising: S11. Obtain the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety restrictions. Based on the device type and executable functions, call the dedicated instruction field corresponding to the current dental instrument from the preset global instruction library. The dedicated instruction field only contains the mode switching instructions, parameter adjustment instructions, start / stop control instructions, and program call instructions that the current dental instrument is allowed to execute. S12. Collect the sound signal of the treatment environment, identify the type of oral treatment noise in the sound signal of the treatment environment, and perform corresponding noise reduction processing according to the type of oral treatment noise to obtain the target speech signal; S13. Perform speech recognition on the target speech signal in offline mode. When the target speech signal contains a preset wake-up word and a function command in sequence, generate a control command to be executed according to the function command. When the preset wake-up word or function command is missing, the generation of the control command to be executed is prohibited. S14. Based on the dedicated instruction domain, working status, executable functions, parameter adjustment range and safety restrictions, perform legality and safety checks on the control instructions to be executed. If the checks pass, convert the control instructions to be executed into equipment control parameters and control the current dental instrument to perform the corresponding operation. If the checks fail, refuse to execute and output a prompt. S15. During the execution of the corresponding operation, receive at least one control input from voice input, key input, foot pedal input and swing input, and handle conflicts according to preset safety priorities, among which emergency stop control input has the highest priority; S16. Obtain the execution feedback information of the current dental instrument and output feedback prompts based on the execution feedback information.

[0028] For ease of understanding, the following explains some key terms in this embodiment: A global command library is a comprehensive database containing all known dental instruments and all their possible control commands. This library is used to provide a complete set of control commands for different types of dental instruments.

[0029] A dedicated command domain refers to a subset of control commands selected from the global command library specifically for a given dental instrument, containing only those commands that the instrument is permitted to execute. This dedicated command domain ensures the specificity and safety of control commands, preventing attempts at incompatible or prohibited operations.

[0030] Dental clinic noise types refer to various sound interferences commonly found in dental clinic environments, such as motor noise, water flow noise, saliva suction sound, air jet sound, instrument collision sound, background conversation sound, and environmental echo. Identifying these noise types helps in targeted noise reduction processing to improve the accuracy of speech recognition.

[0031] A preset wake-up word is a specific word or phrase used in a voice control system to activate the command reception state. Only after recognizing the wake-up word will the system begin listening for and processing subsequent function commands, thus avoiding accidental triggering.

[0032] Function commands are specific operation instructions issued by the user after the wake word, such as "mode switching," "power adjustment," "start," or "stop." These function commands are the basis for the system to perform specific operations.

[0033] Control instructions to be executed refer to control instructions that are initially generated based on the identified function instructions and have not yet been verified. Only after the instructions have undergone legality and security verification will they be converted into device control parameters and executed.

[0034] Legality verification refers to the process of checking the validity of generated control instructions to be executed. This verification ensures that the instructions conform to the current device's dedicated instruction domain, executable functions, and parameter adjustment range, preventing the issuance of unreasonable or invalid instructions.

[0035] Safety verification refers to the process of assessing the risks and determining the safety of generated control instructions to be executed. This verification pays particular attention to high-risk operations, ensuring that specific safety constraints are met before execution to protect the safety of patients and operators.

[0036] Device control parameters refer to the low-level parameters that are converted into control commands that have been verified and confirmed to be safe for execution, and can be directly recognized and executed by dental instruments. These parameters directly drive the instruments to perform corresponding operations, such as mode switching parameters, target parameter values, and startup parameters.

[0037] Preset safety priorities refer to the execution order set for different control inputs (such as voice, buttons, foot pedals, and swinging). When multiple conflicting control inputs exist, the system will process them according to this priority to ensure timely response and safety of critical operations.

[0038] Emergency stop control inputs are those with the highest safety priority, designed to immediately halt the current operation of dental instruments under any circumstances. Examples include emergency stop buttons or specific voice commands.

[0039] Execution feedback information refers to the status or result information returned by dental instruments after an operation has been performed. This information is used to determine whether the operation was successful, whether any abnormalities occurred, and to provide feedback prompts to the user accordingly.

[0040] In this embodiment, the device type, operating status, executable functions, parameter adjustment range, and safety restrictions of the current dental instrument are first obtained. Specifically, this device information can be pre-stored in a local database, and the operator can manually select the model of the dental instrument being used when the system starts. The system then loads the corresponding device information based on the selected model. Based on the obtained device type and executable functions, a dedicated instruction field corresponding to the current dental instrument can be called from a preset global instruction library. For example, the global instruction library can contain general instructions for all dental instruments, while the dedicated instruction field is selected through manual configuration or a simple database query to filter out the mode switching instructions, parameter adjustment instructions, start / stop control instructions, and program call instructions that are allowed to be executed by the specific instrument.

[0041] Furthermore, the system collects sound signals from the treatment environment. Sound signal acquisition can be achieved through microphone arrays integrated into dental instruments or the treatment environment. After acquiring the sound signals, the type of dental treatment noise in the environmental sound signal needs to be identified, and corresponding noise reduction processing is performed based on this noise type to obtain the target speech signal. For example, a general spectral subtraction algorithm can be used to denoise the acquired sound signal to suppress background noise, thereby improving speech clarity.

[0042] Based on this, after obtaining the target speech signal, the system performs speech recognition on the target speech signal offline. This recognition process can use a pre-trained local speech recognition model. When the target speech signal sequentially contains a preset wake word and a function command, the system generates a control command to be executed based on the function command. For example, the system can use simple keyword matching technology to identify "Hello, assistant" as the wake word, then identify "start" as the function command, and generate a "start" control command to be executed accordingly. If the target speech signal lacks the preset wake word or function command, the system prohibits the generation of the control command to be executed to avoid accidental operation.

[0043] Subsequently, after generating the control command to be executed, it is necessary to perform legality and safety checks on the command based on the dedicated command domain, the operating status, the executable function, the parameter adjustment range, and the safety restrictions. Legality checks simply determine whether the command is within the dedicated command domain of the current instrument and whether the operation corresponding to the command matches the executable function of the current instrument. Safety checks can make a preliminary judgment based on the type of command; for example, all commands involving power adjustment can be marked as requiring extra attention. If the checks pass, the control command to be executed is converted into device control parameters, and the current dental instrument is controlled to perform the corresponding operation. For example, a "start" command is converted into a start signal for the instrument. If the checks fail, the system will refuse to execute the command and may issue a general prompt tone.

[0044] During the execution of corresponding operations, the system can receive various control inputs, including at least one of voice input, button input, foot pedal input, and swing input. When multiple control inputs exist, the system needs to handle conflicts according to preset safety priorities. For example, button input can be set to have higher priority than voice input. Among them, emergency stop control inputs are given the highest priority. For example, when the emergency stop button is detected to be pressed, the device will immediately stop the current operation regardless of any other input.

[0045] Finally, the system will obtain the execution feedback information of the current dental instrument. This feedback information may include the instrument's current operating status, parameter settings, etc. Based on this execution feedback information, the system will output feedback prompts. For example, if the instrument starts successfully, the system can issue a "operation successful" prompt tone.

[0046] The technical solution provided in this application obtains the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety constraints, and calls a dedicated command domain accordingly. This enables voice control commands to match the actual functions and safety boundaries of the current dental instrument, preventing inappropriate commands from being executed and improving the compatibility and control safety of dental instruments across the entire range.

[0047] By identifying the types of oral treatment noise in the treatment environment and performing corresponding noise reduction processing for different noise types, the target speech signal can be extracted in complex noise environments such as motor noise, water flow noise, saliva suction noise, air jet noise, instrument collision noise, and background conversation noise, thereby improving the accuracy and stability of intraoperative speech recognition.

[0048] By recognizing target voice signals in offline mode and generating control commands to be executed by sequentially triggering preset wake words and function commands, the system can complete voice control without relying on external networks. At the same time, it can avoid directly triggering device actions after misrecognizing a single voice word, reducing the risk of false triggering.

[0049] By combining a dedicated instruction domain, operating status, executable functions, parameter adjustment range, and safety restrictions, the legality and safety of the control instructions to be executed are verified. This can eliminate control operations that exceed the scope, privileges, or safety conditions before the instructions are executed, which is particularly beneficial for improving the safety of operations such as start-stop control, power regulation, speed regulation, torque regulation, and program calls.

[0050] Example 2 In one possible implementation of this embodiment, identifying the type of oral treatment noise in the sound signal of the treatment environment, and performing corresponding noise reduction processing according to the type of oral treatment noise, includes: Sound features are extracted from the sound signals of the treatment environment to determine the type of oral treatment noise. When the type of oral diagnosis and treatment noise includes at least one of motor noise, water flow noise, saliva suction noise, air jet noise, instrument collision noise, background conversation noise and environmental echo, the noise reduction strategy corresponding to the type of oral diagnosis and treatment noise is invoked. The noise reduction strategy is used to process the sound signal of the diagnosis and treatment environment to obtain the target speech signal.

[0051] To accurately identify noise types in the treatment environment, the system first extracts acoustic features from the acquired ambient sound signals. This may include extracting acoustic features such as Mel-frequency cepstral coefficients (MFCCs), linear predictive coding (LPC) coefficients, zero-crossing rate, short-time energy, spectral centroid, and spectral bandwidth. These features effectively characterize the spectral and temporal properties of the sound signal. Subsequently, a pre-trained classification model, such as a support vector machine (SVM), a Gaussian mixture model (GMM), or a deep neural network (DNN), is used to analyze the extracted features to determine the main types of oral treatment noise in the current ambient sound signal. This classification model is obtained through learning and training on a large number of samples of different noise types.

[0052] Once the specific type of oral diagnosis noise is identified, the system will retrieve the most suitable noise reduction strategy from a pre-defined noise reduction strategy library. For example, for motor noise, strategies based on spectral subtraction or Wiener filtering can be used, combined with their periodic or harmonic characteristics for suppression; for water flow noise and saliva suction noise, statistical model-based noise reduction methods, such as nonnegative matrix factorization (NMF) or deep learning models, can be used to effectively separate speech from continuous noise; for transient impact noise such as jet exhaust and instrument collision noise, transient noise suppression algorithms or wavelet transform-based methods can be used; for background conversation noise, speech activity detection (VAD) technology combined with a deep learning speech enhancement model can be used for separation; and for environmental echoes, dereverberation algorithms, such as cepstral analysis-based or deep learning-based dereverberation networks, can be used. Each strategy is optimized for the specific physical characteristics and acoustic performance of the noise.

[0053] After invoking the corresponding noise reduction strategy, the system will perform noise suppression processing on the original clinical environment sound signal according to the strategy. The specific implementation of the noise suppression processing depends on the selected strategy. For example, if spectral subtraction is used, the power spectrum of the noise will be estimated and subtracted from the power spectrum of the noisy speech, and then the time-domain signal will be reconstructed through inverse Fourier transform. If a deep learning model is used, the noisy speech will be input into a pre-trained neural network, and the network will directly output the denoised speech signal. Through this targeted noise suppression processing, speech information can be preserved to the maximum extent while effectively suppressing various types of oral clinical noise, thereby obtaining a target speech signal with a higher signal-to-noise ratio and better speech clarity, providing high-quality input for subsequent speech recognition.

[0054] In one possible implementation of this embodiment, speech recognition of the target speech signal in an offline state includes: Upon recognizing the preset wake word, the current dental instrument enters the command receiving state; In the instruction receiving state, identify the function instruction and determine whether the function instruction belongs to the dedicated instruction domain; If the function instruction belongs to a dedicated instruction domain, then a control instruction to be executed is generated; If the function instruction does not belong to the dedicated instruction domain, no control instruction to be executed will be generated and an invalid instruction prompt will be output.

[0055] Specifically, when the system continuously monitors the sound signals of the treatment environment, it first identifies a preset wake-up word. This preset wake-up word is a specific voice command pre-set by the user, such as "Hello, assistant," "Dental assistant," or "Start device," used to clearly inform the system that it is ready to receive subsequent functional commands. Once the preset wake-up word is successfully recognized, the system puts the current dental instrument into command receiving mode. This command receiving mode is a specific operating mode in which the system focuses more intently on listening to and processing subsequent voice input, treating it as a potential functional command rather than ordinary background dialogue or noise. This state switching helps improve the accuracy of subsequent command recognition and avoids unnecessary processing of irrelevant voice in non-command states.

[0056] While the dental instrument is in command receiving mode, the system further identifies the function commands issued by the user. These commands are the specific operations the user wants the instrument to perform, such as "increase power" or "switch modes." Upon identifying a command, the system immediately determines whether it belongs to a dedicated command domain. A dedicated command domain is a pre-defined set of commands based on the instrument's type and executable functions, containing only mode switching, parameter adjustment, start / stop control, and program call commands permitted for that instrument. This determination process is crucial for ensuring the validity and safety of the commands.

[0057] If the system determines that the function instruction belongs to a dedicated instruction domain (meaning it is a valid instruction that the current dental instrument can understand and is allowed to execute), it will generate a control instruction to be executed. This control instruction is the basis for subsequent control of the current dental instrument to perform the corresponding operation. Conversely, if the system determines that the function instruction does not belong to a dedicated instruction domain (meaning it is an invalid instruction that the current dental instrument cannot understand, is not allowed to execute, or is unrelated to the current instrument), it will not generate a control instruction to be executed and will output an invalid instruction prompt to the user. This prompt can inform the user of the invalid instruction through sound, light, or interface display, guiding the user to reissue the correct instruction.

[0058] In one possible implementation of this embodiment, the validity check includes: Determine whether the control instruction to be executed belongs to a special instruction domain; Determine whether the control object corresponding to the control instruction to be executed is an executable function; Determine whether the target parameter corresponding to the control instruction to be executed is within the parameter adjustment range; If all of the above judgment results are satisfied, the control instruction to be executed is determined to have passed the legality check.

[0059] Specifically, the first step is to determine whether the control command to be executed belongs to a dedicated command domain. A dedicated command domain is predefined based on the device type and executable functions of the current dental instrument, and only includes mode switching commands, parameter adjustment commands, start / stop control commands, and program call commands that the instrument is allowed to execute. This determination aims to ensure that the command corresponding to the speech recognition result is a valid command that the current instrument can understand and execute. For example, the system can maintain a command whitelist associated with the current dental instrument and verify the validity of the control command to be executed by querying this whitelist.

[0060] Secondly, it is determined whether the control object corresponding to the control instruction to be executed is an executable function. An executable function refers to the various operational capabilities that the dental instrument possesses in its current working state. This determination is to prevent instructions from attempting to control functions that the instrument does not possess. For example, if the current instrument does not have a water spray function, any control instruction involving water spraying will be considered illegal. This can be achieved by comparing the control object in the control instruction to be executed with the currently updated list of executable functions of the dental instrument.

[0061] Furthermore, it is determined whether the target parameter corresponding to the control command to be executed is within the parameter adjustment range. The parameter adjustment range refers to the allowable value range of various adjustable parameters of the current dental instrument (such as rotation speed, power, water flow rate, etc.). This determination is to prevent commands from requiring the instrument to perform parameter settings beyond its physical or safety limits. For example, if the maximum rotation speed of an instrument is 30,000 rpm, but the command requires it to be set to 40,000 rpm, the command will be deemed illegal. This can be achieved by checking the upper and lower limits of the numerical parameters contained in the command.

[0062] Ultimately, only when all the above judgment results are satisfied is the control instruction to be executed determined to have passed the legality check, thus allowing it to be further converted into equipment control parameters and executed.

[0063] In one possible implementation of this embodiment, the security verification includes: Determine the risk level of the control instructions to be executed; When the control command to be executed is a start / stop control command, power increase command, speed increase command, torque increase command, program call command or laser output command, the control command to be executed will be identified as a high-risk control command. For high-risk control instructions, determine whether the current dental instrument meets the execution conditions based on its working status and safety constraints; If the execution conditions are not met, the high-risk control instruction will be refused.

[0064] Specifically, upon receiving a control command to be executed, the system first assesses the risk level of the command to determine its potential danger. For example, commands can be classified into different risk levels based on factors such as the type of command, the magnitude of parameter changes involved, and the potential impact on dental instruments or patients. For instance, commands that change the instrument's operating mode or adjust key parameters (such as power and speed) are generally considered high-risk, while commands that query instrument status or display information are considered low-risk.

[0065] Furthermore, this application explicitly defines the types of high-risk control instructions. When the control instruction to be executed belongs to any of the following categories: start / stop control instruction, power increase instruction, speed increase instruction, torque increase instruction, program call instruction, or laser output instruction, the system directly identifies the instruction as a high-risk control instruction. For example, instructions such as "start the high-speed drill bit," "increase laser output power," and "call the root canal treatment program" are classified as high-risk because they directly affect the critical operating status of the instrument or have a direct effect on the patient. The system can maintain a preset list or set of high-risk instructions internally to quickly and accurately identify these instructions.

[0066] For control commands identified as high-risk, the system performs a more rigorous and detailed judgment on execution conditions. This judgment process comprehensively considers the real-time operating status of the dental instrument and preset safety constraints. Operating status includes, but is not limited to, whether the instrument is in standby, operating, paused, or malfunctioning state, and whether other operations are in progress. For example, if the instrument is currently in maintenance mode, the treatment procedure is not allowed to be executed. Safety constraints refer to preset parameters and regulations that ensure operational safety, such as maximum power, maximum speed, minimum working distance, whether the patient is in position, and whether necessary attachments are connected. These conditions can be rigid regulations or dynamically adjusted according to the specific treatment plan. For example, if no water mist cooling is detected in the patient's oral cavity, the system will prohibit the activation of the high-speed drill. The system comprehensively analyzes these conditions through preset logic gates or an expert system to determine whether the current dental instrument meets the conditions for executing the high-risk command.

[0067] If, based on the above assessment, the current dental instrument does not meet the conditions for executing a high-risk control command, the system will immediately refuse to execute the command. Simultaneously, the system can output appropriate prompts, such as through sound, screen display, or indicator lights, to inform the user of the reason for the refusal, such as "instrument not ready" or "out of safe range," thereby effectively preventing potentially dangerous operations.

[0068] In one possible implementation of this embodiment, converting the control instruction to be executed into device control parameters includes: Determine the control category corresponding to the control instruction to be executed based on the equipment type; When the control category is mode switching, generate mode switching parameters; When the control category is parameter adjustment, generate target parameter values ​​or parameter increase / decrease amounts; When the control category is start-stop control, generate start parameters, stop parameters, or pause parameters; When the control category is program call, preset program call parameters are generated.

[0069] In practice, the system first determines the control category of a control instruction based on the type of the dental instrument (e.g., dental treatment machine, implant machine, scaler, etc.) and the semantic content of the instruction to be executed. This is achieved through a pre-established mapping table between device types and instruction categories. This table stores the control categories supported by each device type (e.g., mode switching, parameter adjustment, start / stop control, program call) and how to parse the corresponding control category from the instruction to be executed. For example, the system can analyze keywords in the instruction to be executed (e.g., "mode," "speed," "start," "program") in conjunction with the current device type to determine its control category.

[0070] When the control category is determined to be mode switching, the system will generate the corresponding mode switching parameters. For example, if the voice command is "switch to cleaning mode", after recognizing it as a mode switching category, the system will look up the device mode parameter (such as "MODE_CLEAN" or the value "01") corresponding to "cleaning mode" and generate the parameter to instruct the device to switch to the preset cleaning working mode.

[0071] When the control category is determined to be parameter adjustment, the system generates a target parameter value or parameter increment / decrement. For example, for the voice command "increase the speed by 100," the system parses "speed" as the adjustment object, "increase by 100" as an incremental operation, and calculates the increment "+100" relative to the current speed value. For the voice command "set the speed to 3000," the system extracts the specific value "3000" and combines it with the parameter unit (such as rpm) to generate a complete parameter value, ensuring that the equipment can accurately adjust its operating parameters.

[0072] When the control category is determined to be start-stop control, the system generates start parameters, stop parameters, or pause parameters. These parameters are instructions for the device to perform basic operations (such as starting work, completely stopping, or temporarily interrupting). For example, the voice command "start" generates the "START" parameter, the voice command "stop" generates the "STOP" parameter, and the voice command "pause" generates the "PAUSE" parameter. These parameters directly correspond to the start-stop control logic inside the device.

[0073] When the control category is determined to be a program call, the system generates preset program call parameters. Many modern dental instruments support pre-programmed treatment procedures. The system looks up the corresponding preset program identifier or parameter based on the program name or number mentioned in the voice command (e.g., "call program one", "execute whitening program") and generates the parameter. For example, the voice command "call program one" will be converted into the "PROGRAM_CALL_01" parameter, thereby simplifying the operation process.

[0074] In one possible implementation of this embodiment, conflict handling is performed according to a preset security priority, including: When different control inputs correspond to control intentions Figure 1 When the control intent is reached, the corresponding operation is executed; When different control inputs correspond to inconsistent control intentions, compare the safety priorities corresponding to each control input; If any control input is an emergency stop control input, the current output of the current dental instrument will be stopped immediately; If no emergency stop control input exists, execute a control input with lower safety risk, or put the current dental instrument into a pause state and output a conflict warning.

[0075] When different control inputs correspond to control intentions Figure 1 When the voice command is "stop" and the foot pedal also emits a stop signal, the system executes the operation corresponding to the control intent. This means the system first determines whether the operation intent expressed by all received control inputs is the same. For example, if the voice command is "stop" and the foot pedal also emits a stop signal, the system recognizes that both intents are the same. Figure 1 If the input fails, a stop operation will be executed immediately. This measure aims to improve operational redundancy and user experience, ensuring that consistent instructions can be reliably executed under multi-channel input.

[0076] When different control inputs correspond to inconsistent control intentions, the system compares the safety priorities of each input. If the system detects a conflict between the control intentions expressed by multiple inputs—for example, a voice command requesting "increase RPM" while a button input requests "decrease RPM"—the system will not execute either command directly but will instead enter a priority comparison phase. In this phase, the system queries preset priority rules, which assign a safety priority to each type of control input or specific control intention. These priorities are typically set based on factors such as the risk level of the operation, ease of user operation, and urgency, and are stored in the system's configuration module.

[0077] If any control input is an emergency stop control input, the current output of the dental instrument is immediately stopped. This is the highest level of conflict resolution mechanism. Emergency stop control inputs typically refer to instructions designed to immediately interrupt all instrument operation, such as triggering a physical emergency stop button, a specific foot pedal emergency stop action, or a preset voice emergency stop command. Once the system recognizes any such input, regardless of the intent of other control inputs, it will unconditionally and immediately cut off the current output of the dental instrument, such as stopping motor rotation, shutting off water and gas supply, or interrupting laser output, to maximize the safety of the patient and operator.

[0078] If no emergency stop control input exists, the system will execute the control input with lower safety risk, or pause the current dental instrument and output a conflict warning. For non-emergency stop conflicts, the system will compare the safety risk levels of each operation in the conflicting command based on a preset risk assessment model. For example, in a conflict between "increase rotation speed" and "decrease rotation speed," "decrease rotation speed" is usually considered a lower-risk operation, and the system may prioritize it. If the conflicting commands have similar risk levels, or the system cannot clearly determine which operation has a lower risk, to avoid potential misoperation, the system will pause the current dental instrument, temporarily stopping all operations, and simultaneously output a conflict warning through light, sound, or interface prompts to inform the operator that there is a command conflict and that manual intervention or re-entry of the command is required.

[0079] In one possible implementation of this embodiment, obtaining the execution feedback information of the current dental instrument and outputting feedback prompts based on the execution feedback information includes: Obtain the current actual execution status of the dental instrument and compare the actual execution status with the target execution status corresponding to the equipment control parameters; If the actual execution status matches the target execution status, then output a success message. If the actual execution status is inconsistent with the target execution status, an execution exception message will be output, and the current operation will be stopped, restricted, or maintained depending on the exception type. Feedback prompts include at least one of the following: light prompts, sound prompts, vibration prompts, and interface prompts.

[0080] Specifically, the process involves acquiring the actual operating state of the dental instrument and comparing it with the target operating state corresponding to the device's control parameters. The actual operating state refers to the current real-time operational status reported by the instrument's internal sensors, controllers, or software modules after receiving and attempting to execute a control command. Examples include the instrument's on / off status, current mode, rotation speed, power, water flow rate, air pressure, laser intensity, or program execution progress. The target operating state corresponding to the device's control parameters refers to the device state expected to be achieved by the system based on the control parameters generated from the voice command. For example, if the command is "adjust the rotation speed to 20,000 rpm," the target operating state is a rotation speed of 20,000 rpm. The comparison process aims to determine whether the actual state matches the target state. This can be achieved through numerical comparison, status flag comparison, or range judgment, such as determining whether the actual rotation speed is within the allowable error range of the target rotation speed.

[0081] If the actual execution status matches the target execution status, a success message will be output. When the comparison between the actual and target execution statuses shows a match, it indicates that the instruction has been completed as expected. At this point, the system will generate an "execution successful" signal or message and output it as part of the feedback message.

[0082] If the actual execution state differs from the target execution state, an execution exception message will be output, and the current operation will be stopped, restricted, or maintained depending on the exception type. When the actual execution state differs from the target execution state, it indicates a problem occurred during instruction execution, failing to achieve the expected goal. In this case, the system will output an execution exception message. Exception types may include equipment failure, parameters exceeding the adjustment range, execution timeout, conflict with other operations, or abnormal sensor readings. Depending on the severity and type of the exception, the system will take different measures: Stopping the current operation means immediately terminating all ongoing operations, typically used in severe exception situations; Restricting the current operation means reducing equipment performance (such as reducing speed or power) or disabling certain functions to prevent further risks, while allowing some operations to continue; Maintaining the current operation means maintaining the current operating state of the equipment in some minor or acceptable exception situations, and alerting the user.

[0083] Feedback prompts include at least one of the following: light prompts, sound prompts, vibration prompts, and interface prompts. Feedback prompts are the way the system communicates device status and command execution results to the operator. Light prompts provide visual feedback through indicator lights on the device, changes in screen backlight color, etc. Sound prompts provide auditory feedback through buzzers, speakers playing preset sound effects, or voice announcements. Vibration prompts provide tactile feedback by generating vibrations using a built-in vibration motor, especially suitable for handheld dental instruments. Interface prompts display text, icons, progress bars, and other information on the device's display screen or the connected control terminal interface. The system can select one or more prompt methods and combine them for output based on actual needs and device configuration.

[0084] In one possible implementation of this embodiment, based on the device type and executable function, a dedicated instruction domain corresponding to the current dental instrument is called from a preset global instruction library, including: Determine whether the current dental instrument is a handheld dental instrument or a large dental instrument based on the type of equipment. Based on the executable functions, candidate control commands that match the current dental instrument are selected from the preset global command library; Based on the parameter adjustment range and safety constraints, candidate control commands are filtered to obtain a dedicated command domain.

[0085] The system categorizes dental instruments based on their type, classifying them as either handheld or large-scale instruments. Dental instruments are typically classified into handheld instruments (e.g., high-speed turbine handpieces, low-speed handpieces, ultrasonic scalers) and large-scale instruments (e.g., dental treatment units, dental X-ray machines, laser treatment units) based on their shape, function, and usage scenario. This classification forms the basis for constructing a dedicated instruction domain, as different types of instruments differ significantly in their operational logic, executable functions, and safety requirements. For example, handheld instruments usually emphasize fine-tuning parameters such as rotation speed, torque, and water mist, while large-scale instruments may involve more complex program calls, position control, or image acquisition functions. By clearly identifying the instrument type, the system can load corresponding preset rule sets and instruction templates, providing direction for subsequent instruction screening and filtering.

[0086] After determining the instrument type, candidate control commands matching the current dental instrument are filtered from a pre-defined global command library based on the executable functions. This step further filters commands related to the instrument's function from a pre-defined global command library containing all possible commands, based on the specific executable functions of the current dental instrument. The pre-defined global command library can be a structured database storing various dental instrument mode switching commands, parameter adjustment commands, start / stop control commands, and program call commands, and associating them with the corresponding instrument type and function. For example, if the current instrument is an ultrasonic scaler with teeth cleaning function, the system will filter commands such as "teeth cleaning mode switching," "power adjustment," and "start / stop"; if the instrument is a dental treatment unit, it may filter commands such as "chair position adjustment," "lighting switch," and "instrument position call." This filtering process ensures that the set of commands processed subsequently is related to the current instrument's function, avoiding interference from irrelevant commands.

[0087] Subsequently, candidate control commands are filtered based on parameter adjustment ranges and safety constraints to obtain a dedicated command domain. This step is crucial in constructing the dedicated command domain, ensuring that the final command domain is both legal and safe. After initial screening to obtain candidate control commands, the system further refines the filtering by combining the actual parameter adjustment range of the current dental instrument with preset safety constraints. The parameter adjustment range refers to the upper and lower limits of various parameters allowed by the instrument under normal operating conditions, such as rotational speed, power, temperature, and flow rate. Safety constraints may include specific operational contraindications of the instrument, restrictions on interaction with other instruments, and special requirements of the patient. For example, if a candidate control command involves adjusting the instrument's power beyond its maximum allowable range, or is prohibited from execution in a specific safety mode, that command will be filtered out. Through this dual filtering mechanism, the final dedicated command domain not only includes the functional commands that the instrument can execute, but also ensures that all commands are within the physical limitations and safety specifications of the instrument.

[0088] Example 3 Figure 2 This is a schematic diagram of the structure of a full-domain dental instrument voice intelligent control system according to an embodiment of this application, with reference to... Figure 2 A full-domain oral instrument voice intelligent control system includes: an equipment information acquisition unit 21, an instruction domain calling unit 22, a sound acquisition unit 23, a noise reduction processing unit 24, an offline speech recognition unit 25, an instruction verification unit 26, a control execution unit 27, a multi-channel input unit 28, a conflict handling unit 29, and a feedback prompting unit 30. The equipment information acquisition unit 21 is used to acquire the current dental instrument's equipment type, working status, executable functions, parameter adjustment range, and safety restrictions; The instruction domain calling unit 22 is used to call the dedicated instruction domain corresponding to the current dental instrument from the preset global instruction library based on the device type and executable functions. The dedicated instruction domain only contains the mode switching instruction, parameter adjustment instruction, start / stop control instruction and program calling instruction that the current dental instrument is allowed to execute. The sound acquisition unit 23 is used to acquire sound signals from the treatment environment; The noise reduction processing unit 24 is used to identify the type of oral diagnosis noise in the sound signal of the diagnosis environment, and perform corresponding noise reduction processing according to the type of oral diagnosis noise to obtain the target speech signal; The offline speech recognition unit 25 is used to perform speech recognition on the target speech signal in an offline state, and when the target speech signal contains a preset wake-up word and a function command in sequence, it generates a control command to be executed according to the function command. Instruction verification unit 26 is used to perform legality verification and security verification on the control instruction to be executed based on the dedicated instruction field, working status, executable function, parameter adjustment range and security restrictions. The control execution unit 27 is used to convert the control command to be executed into equipment control parameters after the legality and security verification are passed, and to control the current dental instrument to perform the corresponding operation. The multi-channel input unit 28 is used to receive at least one control input among voice input, key input, foot pedal input and swing input; The conflict handling unit 29 is used to handle conflicts of different control inputs according to preset safety priorities, wherein emergency stop control inputs have the highest priority; The feedback prompt unit 30 is used to obtain the execution feedback information of the current dental instrument and output feedback prompts based on the execution feedback information.

[0089] The system first dynamically invokes dedicated instruction domains based on device type and executable functions, ensuring that only control commands compatible with the current dental instruments are allowed to be executed, thus resolving compatibility issues across all device categories. Simultaneously, it addresses complex noises in the dental treatment environment, such as motor sounds, water flow sounds, and suction sounds, by identifying noise types and matching noise reduction strategies, significantly improving voice signal quality. Furthermore, the offline voice recognition mechanism avoids network dependence, ensuring real-time response and data security, and prevents accidental triggering through dual verification of preset wake words and function commands. Further, the instruction verification unit performs legality and security checks based on dedicated instruction domains, operating status, and safety restrictions, especially judging the execution conditions of high-risk control commands to effectively avoid safety hazards. In addition, the multi-channel input unit and conflict handling unit work together to handle conflicts between voice, button, foot pedal, and swing inputs according to preset safety priorities, ensuring priority response for emergency stop operations. Finally, the feedback unit outputs execution status information, forming a closed-loop control. In summary, this system, through multi-dimensional technological collaboration, comprehensively optimizes the ease of operation, environmental adaptability, and safety of dental instrument control, providing reliable technical support for complex treatment scenarios.

[0090] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0091] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0092] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0093] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0094] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0095] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0096] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0097] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0098] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A voice-controlled intelligent method for full-range dental instruments, characterized in that, include: The system obtains the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety restrictions. Based on the device type and executable functions, it calls the dedicated instruction field corresponding to the current dental instrument from the preset global instruction library. The dedicated instruction field only contains the mode switching instructions, parameter adjustment instructions, start / stop control instructions, and program call instructions that the current dental instrument is allowed to execute. Collect sound signals from the treatment environment, identify the types of oral treatment noise in the sound signals, and perform corresponding noise reduction processing according to the types of oral treatment noise to obtain the target speech signal; In offline mode, speech recognition is performed on the target speech signal. When the target speech signal contains a preset wake word and a function instruction in sequence, a control instruction to be executed is generated according to the function instruction. When the preset wake word or the function instruction is missing, the generation of the control instruction to be executed is prohibited. Based on the dedicated instruction field, the working status, the executable function, the parameter adjustment range, and the safety restrictions, the legality and security of the control instruction to be executed are verified. If the verification is successful, the control instruction to be executed is converted into device control parameters, and the current dental instrument is controlled to perform the corresponding operation. If the verification fails, execution is rejected and a prompt is output. During the execution of the corresponding operation, at least one control input is received from voice input, key input, foot pedal input, and swing input, and conflict is handled according to the preset safety priority, with emergency stop control input having the highest priority. Obtain the execution feedback information of the current dental instrument, and output feedback prompts based on the execution feedback information.

2. The method according to claim 1, characterized in that, Identify the type of oral treatment noise in the sound signal of the treatment environment, and perform corresponding noise reduction processing according to the type of oral treatment noise, including: Sound features are extracted from the sound signals of the treatment environment to determine the type of oral treatment noise; When the type of oral diagnosis and treatment noise includes at least one of motor noise, water flow noise, saliva suction noise, air jet noise, instrument collision noise, background conversation noise and environmental echo, the noise reduction strategy corresponding to the type of oral diagnosis and treatment noise is invoked. The noise reduction strategy is used to suppress the noise in the diagnostic environment to obtain the target speech signal.

3. The method according to claim 1, characterized in that, Performing speech recognition on the target speech signal in an offline state includes: Upon recognizing the preset wake word, the current dental instrument enters the command receiving state; In the instruction receiving state, the function instruction is identified, and it is determined whether the function instruction belongs to the dedicated instruction domain; If the function instruction belongs to the dedicated instruction domain, then the control instruction to be executed is generated; If the function instruction does not belong to the dedicated instruction domain, the control instruction to be executed will not be generated and an invalid instruction prompt will be output.

4. The method according to claim 1, characterized in that, The legality verification includes: Determine whether the control instruction to be executed belongs to the dedicated instruction domain; Determine whether the control object corresponding to the control instruction to be executed belongs to the executable function; Determine whether the target parameter corresponding to the control instruction to be executed is within the parameter adjustment range; When all of the above judgment results are satisfied, the control instruction to be executed is determined to have passed the legality check.

5. The method according to claim 1, characterized in that, The security verification includes: Determine the risk level of the control instruction to be executed; When the control instruction to be executed is a start / stop control instruction, power increase instruction, speed increase instruction, torque increase instruction, program call instruction or laser output instruction, the control instruction to be executed is identified as a high-risk control instruction. For the high-risk control command, determine whether the current dental instrument meets the execution conditions based on the working status and the safety constraints; If the execution conditions are not met, the high-risk control instruction will be refused to be executed.

6. The method according to claim 1, characterized in that, Converting the control command to be executed into device control parameters includes: The control category corresponding to the control instruction to be executed is determined based on the device type; When the control category is mode switching, mode switching parameters are generated; When the control category is parameter adjustment, a target parameter value or parameter increase / decrease amount is generated; When the control category is start-stop control, start parameters, stop parameters, or pause parameters are generated. When the control category is program call, preset program call parameters are generated.

7. The method according to claim 1, characterized in that, Conflict handling is performed according to preset security priorities, including: When different control inputs correspond to the same control intent, the operation corresponding to the control intent is executed; When different control inputs correspond to inconsistent control intentions, compare the safety priorities corresponding to each control input; If any control input is an emergency stop control input, then the current output of the current dental instrument is immediately stopped; If no emergency stop control input is available, a control input with lower safety risk is executed, or the current dental instrument is put into a pause state and a conflict warning is output.

8. The method according to claim 1, characterized in that, Obtain the execution feedback information of the current dental instrument, and output feedback prompts based on the execution feedback information, including: The actual execution state of the current dental instrument is obtained, and the actual execution state is compared with the target execution state corresponding to the device control parameters; If the actual execution status matches the target execution status, then an execution success message will be output. If the actual execution state is inconsistent with the target execution state, an execution exception prompt will be output, and the current operation will be stopped, restricted, or maintained depending on the exception type. The feedback prompts include at least one of light prompts, sound prompts, vibration prompts, and interface prompts.

9. The method according to claim 1, characterized in that, Based on the device type and the executable functions, the dedicated instruction domain corresponding to the current dental instrument is called from the preset global instruction library, including: Based on the device type, the current dental instrument is determined to be either a handheld dental instrument or a large dental instrument; Based on the executable function, candidate control instructions that match the current dental instrument are selected from the preset global instruction library; Based on the parameter adjustment range and the safety constraints, the candidate control commands are filtered to obtain the dedicated command domain.

10. A voice-intelligent control system for all-domain dental instruments, characterized in that, include: The device information acquisition unit, command domain calling unit, sound acquisition unit, noise reduction processing unit, offline speech recognition unit, command verification unit, control execution unit, multi-channel input unit, conflict handling unit, and feedback prompt unit are all included. The device information acquisition unit is used to acquire the current dental instrument's device type, working status, executable functions, parameter adjustment range, and safety restrictions; The instruction domain calling unit is used to call a dedicated instruction domain corresponding to the current dental instrument from a preset global instruction library based on the device type and the executable function. The dedicated instruction domain only contains mode switching instructions, parameter adjustment instructions, start / stop control instructions and program calling instructions that the current dental instrument is allowed to execute. The sound acquisition unit is used to acquire sound signals from the medical environment. The noise reduction processing unit is used to identify the type of oral diagnosis noise in the sound signal of the diagnosis environment, and perform corresponding noise reduction processing according to the type of oral diagnosis noise to obtain the target speech signal; The offline speech recognition unit is used to perform speech recognition on the target speech signal in an offline state, and when the target speech signal contains a preset wake word and a function instruction in sequence, it generates a control instruction to be executed according to the function instruction. The instruction verification unit is used to perform legality verification and security verification on the control instruction to be executed based on the dedicated instruction field, the working state, the executable function, the parameter adjustment range, and the security restrictions. The control execution unit is used to convert the control instruction to be executed into device control parameters after the legality verification and security verification are passed, and to control the current dental instrument to perform the corresponding operation. The multi-channel input unit is used to receive at least one control input among voice input, key input, foot pedal input, and swing input; The conflict handling unit is used to handle conflicts of different control inputs according to preset safety priorities, wherein emergency stop control inputs have the highest priority. The feedback prompting unit is used to obtain the execution feedback information of the current dental instrument and output feedback prompts based on the execution feedback information.

Images