Wireless identification method, device and equipment for molars masticatory muscle activity and medium

Abstract

The invention provides a wireless identification method and device for molars masticatory muscle activity, equipment and a medium, and effectively solves the problems that a wired surface electromyography machine is inconvenient to use in a specific occasion and cannot accurately identify the molars masticatory muscle activity of a user. The method comprises the steps that real-time electromyographic signals of masticatory muscles of a user are collected in real time based on an electrode unit, and the real-time electromyographic signals are preprocessed through a microprocessor to obtain electromyographic signals; the method comprises the following steps: receiving an electromyographic signal, sampling the electromyographic signal to obtain electromyographic data, inputting a data packet to a data receiving module based on a pre-connected target communication link, verifying the data packet, unpacking the data packet passing verification in the data receiving module, and extracting features of multiple dimensions in the target electromyographic data in the data packet; and processing the features of the multiple dimensions to obtain an identification result, so as to confirm that the user is in a molar state in real time based on the identification result.

Description

Technical Field

[0001] This application relates to the technical field of signal processing. Specifically, it relates to a wireless recognition method, device, equipment, and medium for masticatory muscle activity. Background Art

[0002] When the existing technical solution is based on non-invasive detection and analysis of surface electromyogram (EMG) signals, hydrogel electrodes are attached to the target muscle group to collect microvolt-level electrical signals generated by muscle activity. The surface electromyogram signals are transmitted to a pre-amplification circuit through a wired connection for enhancement, and then processed by low-pass, band-pass filtering, and power frequency notch filtering to suppress environmental noise and 50 / 60 Hz power frequency interference. The processed analog signal is digitized by an analog-to-digital converter (ADC) and transmitted to a multi-channel data acquisition device through a wired connection to achieve synchronous acquisition, real-time display, and storage. Finally, a dedicated software performs time-domain (such as root mean square value, integrated electromyogram) and frequency-domain (spectrum distribution) feature analysis on the digital signals to provide quantitative parameters for clinical diagnosis or motor function assessment. The entire system covers the entire process of signal acquisition, conditioning, conversion, transmission, and intelligent analysis.

[0003] However, the existing technology also has the following objective drawbacks: Limited movement and inconvenient use: The limitations of wired connections are significant. The data cable must be fixedly connected between the electrode and the acquisition host, restricting the movement range and natural movement of the subject. Especially during dynamic movement or long-term monitoring, it is prone to entanglement and detachment, reducing the flexibility and comfort of detection.

[0004] Complicated installation and debugging: The multi-channel wiring is cumbersome. Electrodes and connection wires need to be installed for multiple acquisition channels, and the wiring is relatively complex. The debugging, calibration, and installation processes are time-consuming and require high technical requirements for operators, which is not conducive to rapid deployment and large-scale application.

[0005] Signal interference problem: Wired transmission is vulnerable to external electromagnetic interference. Especially when using long cables, signal attenuation and increased noise may cause the collected data to be distorted. Even after filtering, it is difficult to completely eliminate power frequency and other noise interferences, resulting in inaccurate identification of the activities of the user's masticatory muscles.

[0006] Portability and application scenario limitations: Limited by the laboratory environment, since the wired system requires fixed acquisition equipment and a lot of wiring, it is difficult to adapt to real-time monitoring in non-laboratory environments such as outdoors or at home, which is not conducive to long-term dynamic tracking and daily health management.

[0007] Insufficient use comfort: The fixation of the electrode and the cable may cause friction or a sense of restraint on the skin, especially during long-term monitoring, which is likely to cause discomfort and reduce the acceptance of patients or users.

[0008] In summary, although the traditional wired surface electromyography machine has high reliability in data acquisition accuracy and signal quality, it is limited by disadvantages such as wired transmission, complex installation, susceptibility to environmental interference, and inconvenient use. These not only limit its popularization and use in scenarios such as dynamic motion monitoring and long-term home health management, but also cannot accurately identify the activities of the user's masticatory muscles. These disadvantages provide an improvement direction for the development of wireless, modular, and portable technologies. Summary of the Invention

[0009] In view of this, the purpose of this application is to provide a wireless recognition method, device, equipment, and medium for masticatory muscle activities. This wireless recognition method, device, equipment, and medium for masticatory muscle activities effectively solve the problems of inconvenient use in specific occasions and inability to accurately identify the activities of the user's masticatory muscles existing in the wired surface electromyography machine.

[0010] In the first aspect, an embodiment of this application provides a wireless recognition method for masticatory muscle activities, which is applied to an activity recognition system. The activity recognition system includes an electrode unit and a data receiving module. The electrode unit is built with a microprocessor. The method includes: Real-time collect the real-time electromyographic signals of the user's masticatory muscles based on the electrode unit, and preprocess the real-time electromyographic signals through the microprocessor to obtain the electromyographic signals; the electrode unit is externally attached to the user's masticatory muscles. Sample the electromyographic signals to obtain electromyographic data, input the data packets obtained by packing the electromyographic data based on a pre-connected target communication link into the data receiving module, and verify the data packets received by the data receiving module through the target communication link. Unpack the data packets passed the verification in the data receiving module, and extract various dimensions of features in the target electromyographic data in the data packets. Process the various dimensions of features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time that the user is in a bruxism state based on the recognition result.

[0011] Combined with the first aspect, an embodiment of this application provides a first possible implementation manner of the first aspect. Among them, the process of processing the various dimensions of features through a pre-trained recognition model to obtain a recognition result includes: Set corresponding target judgment conditions for the dimensions to which the features belong, and judge whether the features meet the target judgment conditions of the corresponding dimensions to generate judgment results. If the judgment results corresponding to multiple dimensions are all satisfied, determine that the recognition result is the target activity.

[0012] In combination with the first aspect, the embodiments of the present application provide a second possible implementation manner of the first aspect, wherein, determining whether the feature meets the target judgment condition corresponding to the corresponding dimension to generate a judgment result includes: Determine the judgment priorities of multiple dimensions, and sort the multiple dimensions based on the judgment priorities; If the feature meets the target judgment condition corresponding to the first judgment priority, mark the EMG data and then continue to match the target judgment conditions corresponding to the remaining dimensions.

[0013] In combination with the first aspect, the embodiments of the present application provide a third possible implementation manner of the first aspect, wherein, verifying the data packet received by the data receiving module through the target communication link includes: Set multiple verification dimensions and corresponding verification methods, and respectively verify the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain verification results; Fuse the verification results corresponding to the multiple verification dimensions to obtain a fusion result, and determine that the data packet passes the verification based on the fusion result.

[0014] In combination with the first aspect, the embodiments of the present application provide a fourth possible implementation manner of the first aspect, wherein, the verification dimension includes a protocol layer dimension; The step of respectively verifying the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain verification results includes: Adopt a cyclic redundancy check method to detect the data packet to determine whether the data packet appears in a target state; If so, mark the data packet and generate the verification result of the protocol layer dimension.

[0015] In combination with the first aspect, the embodiments of the present application provide a fifth possible implementation manner of the first aspect, wherein, the verification dimension includes an application layer dimension; The step of respectively verifying the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain verification results includes: Adopt multiple application verification methods to perform corresponding verification on the data packet that has passed the verification method set in the protocol layer dimension and generate application verification results; Generate the verification result of the application layer dimension based on the application verification results corresponding to the multiple application verification methods.

[0016] In combination with the first aspect, the embodiments of the present application provide a sixth possible implementation manner of the first aspect, wherein, preprocessing the real-time EMG signal to obtain the EMG signal includes: Extract the attribute data of the real-time EMG signal, and determine the target preprocessing method based on the attribute data; Invoke the target preprocessing method to preprocess the real-time EMG signal to obtain the EMG signal.

[0017] In a second aspect, an embodiment of the present application provides a wireless recognition device for masticatory muscle activities, which is applied to an activity recognition system. The activity recognition system includes an electrode unit and a data receiving module. The electrode unit is built with a microprocessor. The device includes: An acquisition module, configured to collect in real time the real-time EMG signal of the masticatory muscle of the user based on the electrode unit, and preprocess the real-time EMG signal through the microprocessor to obtain the EMG signal; the electrode unit is externally attached to the masticatory muscle of the user; An input module, configured to sample the EMG signal to obtain EMG data, input and pack the data packet obtained from the EMG data based on a pre-connected target communication link into the data receiving module, and verify the data packet received by the data receiving module through the target communication link; An unpacking module, configured to unpack the data packet passed the verification in the data receiving module, and extract various dimensions of features in the target EMG data in the data packet; A processing module, configured to process the various dimensions of features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time that the user is in a bruxism state based on the recognition result.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the wireless recognition method for masticatory muscle activities are executed.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the wireless recognition method for masticatory muscle activities described in any one of the above are executed.

[0020] An embodiment of the present application provides a wireless recognition method for masticatory muscle activities, which is applied to an activity recognition system. The activity recognition system includes an electrode unit and a data receiving module. The electrode unit is built with a microprocessor. The method first collects real-time electromyographic signals of the user's masticatory muscles in real time based on the electrode unit, and preprocesses the real-time electromyographic signals through the microprocessor to obtain the electromyographic signals. The electrode unit is externally attached to the user's masticatory muscles. Secondly, sample the electromyographic signals to obtain electromyographic data, input and package the data packets obtained from the electromyographic data based on a pre-connected target communication link into the data receiving module, and verify the data packets received by the data receiving module through the target communication link. Then unpack the data packets that pass the verification in the data receiving module, and extract various dimensions of features in the target electromyographic data in the data packets. Finally, process the various dimensions of features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time that the user is in a bruxism state based on the recognition result, and ensure the simplicity and integrity of data transmission based on the target communication link and the method of verifying the electromyographic signals. It also avoids the influence of interference based on the preprocessing method, so as to accurately identify that the user is in a bruxism state, thereby providing an effective and accurate way of wireless electromyographic signal acquisition and recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0022] Figure 1 FIG. shows a flowchart of a wireless recognition method for masticatory muscle activities provided by an embodiment of the present application; Figure 2 FIG. shows another flowchart of a wireless recognition method for masticatory muscle activities provided by an embodiment of the present application; Figure 3 FIG. shows a schematic diagram of data transmission provided by an embodiment of the present application; Figure 4 FIG. shows a structural block diagram of a wireless recognition device for masticatory muscle activities provided by an embodiment of the present application; Figure 5 FIG. shows a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. It should be understood that the accompanying drawings in this application are only for the purpose of illustration and description, and are not used to limit the protection scope of this application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of this application. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without a logical context relationship may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of this application.

[0024] In addition, the described embodiments are only some embodiments of this application, rather than all embodiments. The components of the embodiments of this application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of this application claimed, but merely represents the selected embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of this application.

[0025] It should be noted that the term "including" will be used in the embodiments of this application to indicate the existence of the features stated thereafter, but does not exclude the addition of other features.

[0026] Traditional wired surface electromyography machines have high reliability in data acquisition accuracy and signal quality, but they are limited by disadvantages such as wired transmission, complex installation, susceptibility to environmental interference, and inconvenient use. These not only limit their popularity and use in scenarios such as dynamic motion monitoring and long-term home health management, but also cannot accurately identify the activities of the user's masticatory muscles. These disadvantages provide an improvement direction for the development of wireless, modular, and portable technologies.

[0027] Based on this, the embodiments of this application provide a wireless identification method, device, equipment, and medium for masticatory muscle activities during tooth grinding, which will be described below through embodiments.

[0028] Embodiment 1 To facilitate the understanding of this embodiment, first, a wireless identification method for masticatory muscle activities during tooth grinding disclosed in the embodiments of this application will be introduced in detail. As Figure 1 shown in the flowchart of a wireless identification method for masticatory muscle activities during tooth grinding, Figure 2 shows the schematic flowchart of another wireless identification method for masticatory muscle activities during tooth grinding provided by this application, Figure 3The figure shows a schematic diagram of data transmission of the present application. A wireless recognition method for masticatory muscle activity provided by the present application is applied to an activity recognition system. The activity recognition system includes an electrode unit and a data receiving module. The electrode unit is built-in with a microprocessor. The method includes: S101. Collect real-time electromyographic signals of the user's masticatory muscles in real time based on the electrode unit, and preprocess the real-time electromyographic signals through the microprocessor to obtain the electromyographic signals; the electrode unit is externally attached to the user's masticatory muscles; S102. Sample the electromyographic signals to obtain electromyographic data, input packets obtained by packing the electromyographic data into the data receiving module based on a pre-connected target communication link, and verify the packets received by the data receiving module through the target communication link; S103. Unpack the packets that pass the verification in the data receiving module, and extract various dimensions of features in the target electromyographic data in the packets; S104. Process the various dimensions of features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time based on the recognition result that the user is in a bruxism state.

[0029] In step S101, real-time electromyographic signals of the user's masticatory muscles are collected in real time based on the electrode unit. The electrode unit adopts a hydrogel surface electrode with high sensitivity and low noise, and is directly externally attached to the user's masticatory muscles, avoiding the inconvenience to the user during movement or sleep, and also avoiding the problems of difficult installation or operation. The overall design of the electrode unit of the present application is light and small in volume, and adopts an optimized attachment and fixation scheme to reduce interference with the skin and movement, ensuring that the subject feels comfortable when wearing it at night, so as to collect real-time electromyographic signals that are more in line with the true physiological state. The electrode unit includes a plurality of electrodes with high signal-to-noise ratios. The spacing and installation positions between the electrodes are determined by a pre-designed template, ensuring repeatability and stability of the real-time electromyographic signals, and can also be determined according to the needs of the user and the area of the masticatory muscles. The real-time electromyographic signals collected by the electrode unit are at the microvolt level and are easily interfered by skin impedance and environmental noise. High-sensitivity electrodes ensure the accuracy of signal capture. Therefore, the real-time electromyographic signals are preprocessed based on the microprocessor built in the electrode unit, so as to obtain electromyographic signals EMG that are not affected by skin impedance and environmental noise interference.

[0030] In the specific implementation process of step S101, there is an embodiment: the preprocessing the real-time electromyographic signals to obtain the electromyographic signals includes: S1011. Extract the attribute data of the real-time electromyographic signals, and determine the target preprocessing method based on the attribute data; S1012. Invoke the target preprocessing method to preprocess the real-time EMG signal to obtain an EMG signal.

[0031] In steps S1011 - S1012, based on the extraction method preset in the microprocessor, the attribute data of the real-time EMG signal is extracted. The attribute data includes skin impedance, environmental noise interference, and the amplitude at the microvolt level. The environmental noise interference includes noise outside 20 - 500 Hz and 50 / 60 Hz interference. Then, based on the attribute data existing in the real-time EMG signal, the target preprocessing method is determined. That is, corresponding preprocessing methods are set for the above attribute data. The skin impedance and the amplitude at the microvolt level can be processed by the preamplification module in the preamplification and filtering module composed of an amplifier and a supporting circuit. The environmental noise interference is denoised based on the filtering module in the preamplification and filtering module. The filtering module includes a power frequency notch filter (50 / 60 Hz) and a band-pass filter (20 - 500 Hz). That is, the environmental noise interference is filtered and denoised based on the power frequency notch filter and the band-pass filter. The broadband characteristics of the EMG signal need to filter out low-frequency drift and high-frequency noise. Low-noise amplification ensures that the signal still maintains a high signal-to-noise ratio after enhancement. That is, the electrode unit also incorporates a preamplification module and a filtering module to achieve the effect of early conditioning of low amplitude and broadband characteristics. Moreover, the circuits of the preamplification module and the filtering module adopt a miniaturized layout to ensure low power consumption and small size, avoiding a large impact on the volume of the electrode unit.

[0032] In step S102, after the electrode unit preprocesses the real-time EMG signal to obtain an EMG signal, it sends the EMG signal to a high-speed analog-to-digital converter ADC for sampling and real-time conversion into EMG data in the digital state of the EMG signal, that is, the target EMG data is obtained. The sampling rate (1000 - 2000 Hz) and resolution of the high-speed ADC meet the requirements of continuous nighttime monitoring, ensuring the accuracy of the target EMG data. The EMG signal changes rapidly, and the high sampling rate ensures the capture of subtle dynamics, providing a reliable basis for subsequent analysis. Traditional wired systems need to connect the electrodes to the data acquisition device through cables, which are prone to entanglement, restriction of natural movement, and signal interference, especially during dynamic monitoring or long-term nighttime monitoring, where data acquisition is likely to be interrupted.

[0033] The electrode unit has also pre-established a target communication link with the data receiving module. The target communication link has also been sent through pre-tests. That is, the target communication link includes an electrode end and a receiving end. The electrode end is located in the electrode unit, and the receiving end is located in the data receiving module, so as to ensure that the data receiving module receives the data packet including the electromyogram signal EMG output by the electrode unit. The target communication link is a wireless communication module implemented based on a Bluetooth 5.0 wireless module. The Bluetooth 5.0 module has the characteristics of low power consumption and high stability, solving the problem of wired bondage. The high-speed and low-power characteristics of Bluetooth 5.0 support the high-frequency data transmission of EMG. Low-power Wi-Fi or ZigBee can also be used. Then, after the microprocessor in the electrode unit packs the electromyogram signal into a data packet, the data packet where the electromyogram signal is located is input into the receiving end in the data receiving module based on the electrode end of the pre-connected target communication link, so as to realize the input of the electromyogram signal into the data receiving module. The data receiving module can be a dedicated device or a smart phone or a tablet computer. After the receiving end of the data receiving module receives the data packet where the electromyogram signal is located, it verifies the data packet where the data packet received by the data receiving module through the target communication link is located, so as to ensure that it can receive and receive a complete data packet, avoid the loss of the electromyogram signal, and after the verification passes, store and save the electromyogram data for use when needed.

[0034] This application uses a Bluetooth 5.0 wireless transmission module, which not only supports high-speed data transmission, but also has low power consumption and a relatively long transmission distance. Each module is connected through a standardized interface, without the need for a long data cable, so that the user can maintain a natural state and ensure that the collected electromyogram signals are more continuous and more real. This application uses a low-noise amplification circuit and multi-stage filtering technology in the preamplification module and the filtering module to effectively amplify the target signal and filter out environmental interference; at the same time, a high-speed and high-precision ADC is used to digitize the signal, and then the microcontroller is used to pack and preprocess the data, and Bluetooth 5.0 is used to achieve stable transmission, greatly reducing the risk of data packet loss and transmission errors, and providing high-quality data for subsequent intelligent analysis.

[0035] In the specific implementation process of step S102, there is an embodiment: the verification of the data packet received by the data receiving module through the target communication link includes: S1021. Set multiple verification dimensions and corresponding verification methods, and respectively verify the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain a verification result; S1022. Integrate the verification results corresponding to the multiple verification dimensions to obtain an integration result, and determine that the data packet passes the verification based on the integration result.

[0036] In steps S1021 - S1022, the data receiving module sets multiple verification dimensions based on its own structure. The verification dimensions respectively include a protocol layer dimension and an application layer dimension, and corresponding verification methods are set for the protocol layer dimension and the application layer dimension respectively. And based on the structure of the data receiving module itself, the verification priorities of the protocol layer dimension and the application layer dimension are determined. In practice, the verification priority of the protocol layer dimension is greater than that of the application layer dimension. Then, after the data receiving module receives the data packet, the data packet is first verified in the protocol layer dimension, and then in the application layer dimension, and corresponding verification results are generated. The verification results corresponding to multiple verification dimensions are fused to obtain a fusion result. If the data packet passes the verification based on the fusion result, that is, if the verification results of both verification dimensions in the fusion result are passed, then the fusion result is considered as passing the verification, and the data packet is stored. If there is at least one verification dimension in the fusion result whose verification result is not passed, then the fusion result is considered as not passing the verification. This application also sets corresponding remedial measures for different verification dimensions to ensure the timely identification of electromyography data.

[0037] In a specific implementation process of step S1021, there is an embodiment where: the verification dimension includes a protocol layer dimension; The data packet is verified respectively according to the verification methods corresponding to multiple verification dimensions to obtain verification results, including: S102111. Adopt a cyclic redundancy check method to detect the data packet to determine whether the data packet appears in the target state; S102112. If so, mark the data packet and generate the verification result of the protocol layer dimension.

[0038] In steps S102111 - S102112, a cyclic redundancy check method is adopted to detect the data packet to determine whether the data packet appears in the target state. That is, the electrode end regards the head and payload of the data packet as a continuous binary sequence, converts it into a polynomial form, uses the generating polynomial to perform modulo-2 division (without carry / borrow operation) on the data polynomial, and the remainder is the 24-bit CRC code. The CRC code is appended to the end of the data packet to form a complete transmission unit (Header + Payload + CRC). The receiving end in the data receiving module obtains the complete data packet containing the CRC code, and performs the same modulo-2 division operation on the received data (Header + Payload + CRC). If the remainder is 0, the data is complete and the data packet is accepted. If the remainder is non-zero, the data is damaged and the error handling mechanism is triggered. At this time, the data packet is in the error state, which is the target state. If the error state appears, the data packet is marked and the verification result at the protocol layer dimension is generated. The generated verification result is failure. In the specific implementation process of step S1021, there is another embodiment: the verification dimension includes the application layer dimension; The data packet is verified by the verification methods corresponding to multiple verification dimensions to obtain the verification result, including: S102121. Adopt multiple application verification methods to perform corresponding verification on the data packet passing through the verification method set in the protocol layer dimension and generate the application verification result; S102122. Generate the verification result of the application layer dimension based on the application verification results corresponding to multiple application verification methods.

[0039] In steps S102121 - S102122, in the application layer dimension, multiple application verification methods are adopted to perform corresponding verification on the data packet passing through the verification method set in the protocol layer dimension and generate the application verification result. The application verification methods include two verification methods: additional checksum or advanced error detection code, that is, the target communication link established in this application constructs a multi-level fault tolerance system based on cyclic redundancy check method, additional checksum or advanced error detection code to verify the integrity of the electromyography data before and after sending, further capture the errors not detected in the protocol layer dimension, and after detecting the errors in the protocol layer dimension, the application layer dimension attempts to correct them by FEC decoding. If it still fails, ARQ retransmission is triggered.

[0040] If an error is detected, the application layer dimension discards this data packet. Then the receiving end automatically generates or sends a pre-generated retransmission request to the microprocessor in the electrode unit. The microprocessor quickly retransmits the data packets that have not been successfully sent from the buffer. The microcontroller caches the data packets and retransmits them from the buffer when it fails. The retransmission protocol is optimized to reduce latency and ensure the real-time nature of the electromyography data in the data packets. At the same time, the order and integrity of the data packets are also maintained. Existing Bluetooth systems only rely on the protocol layer CRC and ACK / NACK mechanisms, which are suitable for general data but lack support for the real-time nature of the continuous data stream of electromyography data. The retransmission delay may cause data interruption.

[0041] In step S103, after the data receiving module passes the verification of the data packets received by the receiving end, the data receiving module unpacks the data packets that have passed the verification. Thus, the data receiving module receives the target electromyography data and extracts various dimensions of features from the target electromyography data in the data packets. Feature extraction can be based on traditional signal processing algorithms (such as Fourier transform, wavelet transform) or intelligent diagnosis methods based on machine learning. Although the implementation of different feature extraction methods is different, they all aim to extract the features of electromyography data. The various dimensions include the time domain, the frequency domain, and the time-frequency domain. The features in the time domain dimension include the root mean square value (RMS), the integrated electromyogram (IEMG), and the waveform length (WL) of the electromyography data. The features in the frequency domain dimension include the power spectral density (PSD), the median frequency (MF), and the mean power frequency (MPF) of the electromyography data. The time-frequency domain analyzes the data dynamics of the electromyography data from the perspective of wavelet transform coefficients.

[0042] In step S104, the data receiving module transmits the electromyography data to the PC side or the cloud in the form of WIFI or USB. The pre-trained recognition model on the PC side or the cloud processes and analyzes the various dimensions of features to obtain a recognition result. The recognition model is based on the recognition result to confirm in real time that the user is in the bruxism state. If it is determined that the user is in the bruxism state, a graphic report, a curve graph, and a diagnostic conclusion for bruxism are generated, which helps to slow down the occurrence of the user's bruxism phenomenon. The PC side uses its strong computing power to perform complex analysis and combines machine learning to improve the accuracy of electromyography data analysis.

[0043] In the specific implementation process of step S104, there is an embodiment: processing the various dimensions of features through the pre-trained recognition model to obtain a recognition result, including: S1041. Set corresponding target judgment conditions for the dimension to which the feature belongs, and judge whether the feature meets the target judgment conditions of the corresponding dimension to generate a judgment result; S1042. If the judgment results corresponding to multiple dimensions all meet the requirements, determine that the recognition result is the target activity.

[0044] In steps S1041 - S1042, the present application sets corresponding target judgment conditions for three types of multiple dimensions to which the extracted features belong, namely time domain, frequency domain, and time - frequency domain, and determines whether the features meet the corresponding target judgment conditions. For example, the target judgment condition for the frequency domain dimension is whether the amplitude of the electromyogram data is much greater than the set amplitude threshold; for the time domain dimension, whether the root mean square value (RMS) and / or integrated electromyogram (IEMG) are greater than the corresponding preset thresholds; and for the time - frequency domain dimension, the target judgment condition is that the duration conforms to the target time period range, such as 3 - 10 s, and short - term peaks caused by user swallowing are filtered out. After judgment for each corresponding dimension, each dimension generates a corresponding judgment result. If the judgment results corresponding to multiple dimensions all meet the requirements, determine that the recognition result is bruxism. Then the target activity of the user's masticatory muscles is the activity driven by bruxism. At this time, bruxism is distinguished from other oral physiological activities. If it is necessary to detect other oral physiological activities, the dimensions and target judgment conditions set for bruxism can be correspondingly replaced. In the specific implementation process of step S1041, there is an embodiment: The judgment of whether the feature meets the target judgment condition of the corresponding dimension to generate a judgment result includes: S10411. Determine the judgment priorities of multiple dimensions to sort the multiple dimensions based on the judgment priorities. S10412. If the feature meets the target judgment condition corresponding to the first judgment priority, mark the electromyogram data and then continue to match the target judgment conditions corresponding to the remaining dimensions.

[0045] In steps S10411 - S10412, the present application has pre - determined the judgment priorities of multiple dimensions, that is, the judgment priorities of the three dimensions of time domain, frequency domain, and time - frequency domain are not the same. The present application sets the time domain dimension and the frequency domain dimension as the first judgment priority, and the judgment priority of the time - frequency domain dimension is lower than that of the time domain and frequency domain dimensions. After determining the judgment priorities of the above three dimensions, sort the multiple dimensions based on the judgment priorities. Then, if the feature simultaneously meets the target judgment conditions corresponding to the time domain dimension and the frequency domain dimension, at this time, mark the electromyogram data as a potential event, and after the marking is completed, continue to match the target judgment conditions corresponding to the time - frequency domain dimension, so as to confirm that the user is bruxing, thereby driving the masticatory muscle activity.

[0046] This application adopts a modular design, separating functions such as the electrode unit, preamplification / filtering module, ADC analog-to-digital converter, microprocessor, and data reception module into independent modules. The modules are connected using standard interfaces, which not only facilitates maintenance and upgrading but also allows for the replacement of corresponding modules according to different application scenarios, thus greatly enhancing the flexibility and applicability of the system. By using low-power Bluetooth 5.0 and miniaturized low-power circuits, the device can achieve continuous overnight monitoring under single-battery power supply, eliminating the situation of data interruption due to insufficient power. This not only effectively addresses the deficiencies of traditional wired systems in terms of transmission, installation, signal quality, and user comfort but also significantly improves the integrity of continuously monitored data and the accuracy of diagnosis, providing a more reliable and efficient solution for clinical and home health management.

[0047] Embodiment 2 This application also provides a wireless recognition device for masticatory muscle activity during bruxism, as Figure 4 shown in the block diagram of a wireless recognition device for masticatory muscle activity during bruxism. The functions implemented by this wireless recognition device for masticatory muscle activity correspond to the steps of executing an automatic wafer replenishment optimization method on a terminal device as described above. This device can be understood as a component of a server including a processor. The wireless recognition device for masticatory muscle activity described in this application is applied to an activity recognition system, and the activity recognition system includes an electrode unit and a data reception module. The electrode unit has a built-in microprocessor, and the device includes: An acquisition module 401, configured to collect real-time electromyographic signals of the user's masticatory muscles in real time based on the electrode unit, and preprocess the real-time electromyographic signals through the microprocessor to obtain the electromyographic signals; the electrode unit is externally attached to the user's masticatory muscles; An input module 402, configured to sample the electromyographic signals to obtain electromyographic data, input and pack the data packets obtained from the electromyographic data into the data reception module based on a pre-connected target communication link, and verify the data packets received by the data reception module through the target communication link; A unpacking module 403, configured to unpack the data packets that pass the verification in the data reception module and extract various-dimensional features in the target electromyographic data in the data packets; A processing module 404, configured to process the various-dimensional features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time that the user is in a bruxism state based on the recognition result.

[0048] In a feasible implementation manner, the processing module includes: A judgment module, configured to set corresponding target judgment conditions for the dimension to which the feature belongs, and judge whether the feature meets the target judgment conditions of the corresponding dimension to generate a judgment result; A determination module, configured to determine the recognition result as a target activity if the judgment results corresponding to multiple dimensions all meet the requirements.

[0049] In a feasible implementation manner, the processing module further includes: A sorting module, configured to determine the judgment priorities of multiple dimensions, and sort the multiple dimensions based on the judgment priorities; A matching module, configured to, if the feature meets the target judgment condition corresponding to the first judgment priority, mark the EMG data and then continue to match the target judgment conditions corresponding to the remaining dimensions.

[0050] In a feasible implementation manner, the input module includes: A setting module, configured to set multiple verification dimensions and corresponding verification methods, and respectively verify the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain verification results; A fusion module, configured to fuse the verification results corresponding to multiple verification dimensions to obtain a fusion result, and determine that the data packet passes the verification based on the fusion result.

[0051] In a feasible implementation manner, the input module further includes: A detection module, configured to detect the data packet by adopting a cyclic redundancy check method to determine whether the data packet appears in a target state; A marking module, configured to, if so, mark the data packet and generate the verification result of the protocol layer dimension.

[0052] In a feasible implementation manner, the input module also includes: A verification module, configured to perform corresponding verification on the data packet that passes the verification method set by the protocol layer dimension by adopting multiple application verification methods and generate application verification results; A generation module, configured to generate the verification result of the application layer dimension based on the application verification results corresponding to the multiple application verification methods.

[0053] In a feasible implementation manner, the acquisition module includes: An extraction module, configured to extract the attribute data of the real-time EMG signal and determine the target preprocessing method based on the attribute data; An invocation module, configured to invoke the target preprocessing method to preprocess the real-time EMG signal to obtain an EMG signal.

[0054] Embodiment 3 This application also provides an electronic device, such as Figure 5As shown, it includes: a processor 501, a memory 502, and a bus 503. The memory 502 stores machine-readable instructions executable by the processor 501. When the electronic device runs, communication between the processor 501 and the memory 502 is carried out via the bus 503. When the machine-readable instructions are executed by the processor 501, the steps of any one of the wireless identification methods for masticatory muscle activity are performed.

[0055] Embodiment 4 This application also provides a computer-readable storage medium. A computer program is stored on this computer-readable storage medium. When the computer program is run by a processor, the steps of any one of the wireless identification methods for masticatory muscle activity are performed.

[0056] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems and devices can refer to the corresponding processes in the method embodiments, which will not be elaborated in this application. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. Also, for example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0057] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] In addition, in each embodiment of this application, the functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0059] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a platform server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0060] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A wireless recognition method for masticatory muscle activity during chewing, characterized in that, Applied to an activity recognition system, the activity recognition system includes an electrode unit and a data receiving module, and the electrode unit is built with a microprocessor. The method includes: Collecting in real time the real-time electromyogram signal of the user's masticatory muscles based on the electrode unit, and preprocessing the real-time electromyogram signal by the microprocessor to obtain the electromyogram signal; the electrode unit is externally attached to the user's masticatory muscles; Sampling the electromyogram signal to obtain electromyogram data, inputting and packing the data packet obtained from the electromyogram data into the data receiving module based on a pre-connected target communication link, and verifying the data packet received by the data receiving module through the target communication link; Unpacking the data packet that passes the verification in the data receiving module, and extracting various dimensions of features in the target electromyogram data in the data packet; Processing the various dimensions of features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time that the user is in a bruxism state based on the recognition result.

2. The method according to claim 1, wherein The processing the various dimensions of features through a pre-trained recognition model to obtain a recognition result includes: Setting corresponding target judgment conditions for the dimension to which the feature belongs, and judging whether the feature meets the target judgment conditions of the corresponding dimension to generate a judgment result; If the judgment results corresponding to multiple dimensions are all satisfied, it is determined that the recognition result is the target activity.

3. The method according to claim 2, wherein The judging whether the feature meets the target judgment conditions of the corresponding dimension to generate a judgment result includes: Determining the judgment priorities of multiple dimensions, and sorting the multiple dimensions based on the judgment priorities; If the feature meets the target judgment conditions corresponding to the first judgment priority, mark the electromyogram data and continue to match the target judgment conditions corresponding to the remaining dimensions.

4. The method according to claim 1, wherein The verifying the data packet received by the data receiving module through the target communication link includes: Setting multiple verification dimensions and corresponding verification methods, and respectively verifying the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain a verification result; Fusing the verification results corresponding to multiple verification dimensions to obtain a fusion result, and determining that the data packet passes the verification based on the fusion result.

5. The method according to claim 4, wherein The verification dimension includes the protocol layer dimension; The respectively verifying the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain a verification result includes: Adopting a cyclic redundancy check method to detect the data packet to determine whether the data packet appears in a target state; If so, mark the data packet and generate the verification result of the protocol layer dimension.

6. The method according to claim 4, wherein The verification dimension includes the application layer dimension; The respectively verifying the data packet based on the verification methods corresponding to the multiple verification dimensions to obtain a verification result includes: Adopting multiple application verification methods to perform corresponding verification on the data packet passing through the verification method set by the protocol layer dimension and generating an application verification result; Based on the application verification results corresponding to the multiple application verification methods, generating the verification result of the application layer dimension.

7. The method according to claim 1, wherein The preprocessing the real-time electromyogram signal to obtain the electromyogram signal includes: Extracting the attribute data of the real-time electromyogram signal, and determining the target preprocessing method based on the attribute data; Invoke the target preprocessing method to preprocess the real-time electromyogram signal to obtain an electromyogram signal.

8. A wireless recognition device for masticatory muscle activity during molar chewing, characterized in that, Applied to an activity recognition system, the activity recognition system includes an electrode unit and a data receiving module. The electrode unit has a built-in microprocessor. The device includes: An acquisition module for real-time acquisition of the real-time electromyogram signal of the user's masticatory muscles based on the electrode unit, and preprocessing the real-time electromyogram signal by the microprocessor to obtain the electromyogram signal; the electrode unit is externally attached to the user's masticatory muscles; An input module for sampling the electromyogram signal to obtain electromyogram data, inputting and packing the data packet obtained from the electromyogram data based on a pre-connected target communication link to the data receiving module, and verifying the data packet received by the data receiving module through the target communication link; An unpacking module for unpacking the data packet passed the verification in the data receiving module, and extracting various dimensions of features in the target electromyogram data in the data packet; A processing module for processing the various dimensions of features through a pre-trained recognition model to obtain a recognition result, so as to confirm in real time that the user is in a bruxism state based on the recognition result.

9. An electronic device, characterized in that, Includes: A processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of a wireless recognition method for bruxism masticatory muscle activity according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is run by the processor, the steps of a wireless recognition method for bruxism masticatory muscle activity according to any one of claims 1 to 7 are executed.

Images