Temporomandibular joint motion analysis method based on wireless signal and related device

Abstract

The invention discloses a temporal-mandibular joint motion analysis method based on a wireless signal and a related device, which realize non-contact accurate monitoring of temporal-mandibular joint motion behaviors without invasive operation through wireless signal acquisition, time sequence data construction and biomechanical model analysis, and improve the accuracy of the temporal-mandibular joint motion behaviors. According to the method, scattering, reflection and Doppler frequency shift changes caused by temporomandibular joint movement can be captured, displacement, speed and direction characteristics reflecting joint movement are extracted, movement modes (such as mouth opening, mouth closing and lateral sliding) are classified in combination with a machine learning algorithm, and therefore the category of the movement behavior of the temporomandibular joint is accurately recognized. Besides, the sensing technology based on wireless signals is compatible with existing equipment such as Wi-Fi or millimeter wave radar, and the system has the characteristics of equipment miniaturization, low cost and high sensitivity, and can be widely applied to household monitoring and portable medical equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of motion analysis, and specifically to a temporomandibular joint motion analysis method and related device based on wireless signals. Background Art

[0002] The temporomandibular joint (TMJ) is one of the most complex joints in the human body, and its movement involves the fine coordination of the mandible, articular disc and surrounding muscles. Abnormal TMJ function can lead to problems such as limited mouth opening, joint pain, and abnormal occlusion, which have an adverse impact on the daily life of patients. In order to diagnose and treat temporomandibular disorders (TMD), it is of great significance to accurately monitor and analyze joint movement.

[0003] Common monitoring methods mainly include imaging examinations (such as X-rays, magnetic resonance imaging) and surface electromyography (EMG) analysis, but these methods have the following deficiencies: the equipment is expensive, the operation is complex, and it is not suitable for widespread use; the monitoring period is short, and it is difficult to achieve long-term and dynamic monitoring; it is not convenient enough, and patients need to wear equipment or undergo invasive operations; the monitoring accuracy is low and the user experience is poor due to the tension of patients during the examination process. Summary of the Invention

[0004] The main purpose of the present invention is to propose a temporomandibular joint motion analysis method and related device based on wireless signals, aiming to at least solve the technical problems such as low monitoring accuracy and poor user experience caused by patient tension due to invasive operations in the temporomandibular joint monitoring method in the related art.

[0005] In the first aspect of the present invention, a temporomandibular joint motion analysis method based on wireless signals is provided, which is applied to a temporomandibular joint motion analysis device including a signal transmitter and a signal receiver. The signal transmitter is used to send a first wireless signal to the signal receiver in a monitoring area. The temporomandibular joint motion analysis method includes:

[0006] Obtaining a second wireless signal collected by the signal receiver; wherein, the second wireless signal is a signal formed by the first wireless signal based on the motion behavior of the temporomandibular joint in the monitoring area;

[0007] Preprocessing the second wireless signal to obtain the timing data of the motion behavior;

[0008] Constructing a biomechanical model corresponding to the motion behavior of the temporomandibular joint according to the timing data;

[0009] Perform category analysis on the motion behavior according to the biomechanical model, and output the analysis result.

[0010] In a second aspect of the present invention, there is provided a temporomandibular joint motion analysis device based on wireless signals, which is characterized by comprising a signal transmitter, a signal receiver and a processor;

[0011] The signal transmitter is configured to send a first wireless signal to the signal receiver in a monitoring area; wherein, the monitoring area is used to cover the movable range of the temporomandibular joint of a user;

[0012] The signal receiver is configured to collect a second wireless signal passing through the monitoring area; wherein, the second wireless signal is a signal formed by the first wireless signal based on the motion behavior of the temporomandibular joint in the monitoring area;

[0013] The processor is configured to preprocess the second wireless signal to obtain the timing data of the motion behavior, construct a biomechanical model corresponding to the motion behavior of the temporomandibular joint according to the timing data, perform category analysis on the motion behavior according to the biomechanical model, and output the analysis result.

[0014] In a third aspect of the present invention, there is provided an electronic device, which includes a memory, a processor and a bus; the bus is used to realize the connection and communication between the memory and the processor; the processor is configured to execute a computer program stored on the memory; when the processor executes the computer program, the steps in the method for analyzing the motion of the temporomandibular joint based on wireless signals as in the first aspect are realized.

[0015] In a fourth aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method for analyzing the motion of the temporomandibular joint based on wireless signals as in the first aspect are realized.

[0016] The method and related device for temporomandibular joint movement analysis based on wireless signals of the present invention, through wireless signal acquisition, time series data construction and biomechanical model analysis, do not require invasive operations, and only provide a non-intrusive detection method, effectively reducing the tension of patients, thereby realizing non-contact and accurate monitoring of temporomandibular joint movement behavior. This method can also capture the scattering, reflection and Doppler frequency shift changes caused by temporomandibular joint movement, extract the displacement, velocity and direction characteristics reflecting joint movement, and classify movement patterns (such as opening the mouth, closing the mouth, lateral sliding) by combining machine learning algorithms, so as to accurately identify the categories of temporomandibular joint movement behavior. In addition, the wireless signal-based sensing technology is compatible with existing devices such as Wi-Fi or millimeter wave radar, and has the characteristics of device miniaturization, low cost and high sensitivity, and can be widely applied to home monitoring and portable medical devices. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of the steps of the method for temporomandibular joint movement analysis based on wireless signals provided by the embodiments of the present application;

[0019] Figure 2 It is a schematic diagram of the application scenario in the embodiments of the present application;

[0020] Figure 3 It is a schematic diagram of the module connection of the device for temporomandibular joint movement analysis based on wireless signals provided by the embodiments of the present application;

[0021] Figure 4 It is a schematic diagram of the internal structural connection of the electronic device provided by the embodiments of the present application.

[0022] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] It should be noted that related terms such as "first" and "second" can be used to describe various components, but these terms do not limit the components. These terms are only used to distinguish one component from another. For example, without departing from the scope of the present invention, the first component can be called the second component, and similarly, the second component can also be called the first component. The term "and / or" refers to any combination of one or more of the related items and the described items.

[0025] Please refer to Figure 1 , this embodiment provides a method for analyzing temporomandibular joint movement based on wireless signals, which is applied to a temporomandibular joint movement analysis device. The temporomandibular joint movement analysis device at least includes a signal transmitter and a signal receiver. The method includes the following steps:

[0026] Step S101, obtain the second wireless signal collected by the signal receiver.

[0027] When monitoring the temporomandibular joint of a user, it is necessary to pre-arrange the signal transmitter and the signal receiver respectively around the user's head at approximately the same height (please refer to Figure 2 ), so that the user's temporomandibular joint is within the monitoring area formed by the signal transmitter and the signal receiver, that is, the monitoring area will cover the movable range of the user's temporomandibular joint to better monitor the movement behavior of the temporomandibular joint.

[0028] Specifically, the signal transmitter intermittently sends the first wireless signal to the monitoring area, and the first wireless signal reaches the signal receiver after passing through the user's temporomandibular joint. Generally, when the user's temporomandibular joint is performing a movement behavior (for example, protruding forward, opening the mouth, or moving backward, etc.), it will cause changes in the path and intensity of the first wireless signal. Thus, the first wireless signal is converted into the second wireless signal based on the movement behavior of the temporomandibular joint in the monitoring area, that is, the temporomandibular joint movement analysis device can obtain the second wireless signal collected by the signal receiver.

[0029] It should be noted that wireless signals (such as the channel frequency response CSI of Wi-Fi signals or millimeter-wave radar signals) will be affected by human movement during propagation, forming unique signal patterns. That is, the second wireless signal reflects the multi-dimensional characteristics of the movement behavior of the temporomandibular joint, including phase difference, channel amplitude change, etc., as the basic data for subsequent movement behavior analysis.

[0030] Step S102, preprocess the second wireless signal to obtain the timing data of the movement behavior.

[0031] Specifically, detect the channel frequency response in the second wireless signal, preprocess the channel frequency response to obtain the time-series data of the motion behavior. Among them, the channel frequency response in the second wireless signal can be expressed as H(f) = |H(f)|e j φ(f) , where H(f) represents the channel frequency response, |H(f)| is the amplitude attenuation information of the channel, which is used to represent the amplitude attenuation or amplification when passing through the channel, φ(f) is the phase offset information of the channel, which is used to represent the phase change when the signal passes through the channel, and j is the imaginary unit (usually taken as ).

[0032] It can be seen that the channel frequency response generally includes amplitude attenuation information, phase offset information, and Doppler frequency shift information. The amplitude attenuation information is used to represent the attenuation value of the first wireless signal in amplitude after being affected by the motion behavior, the phase offset information is used to represent the offset value of the first wireless signal in phase after being affected by the motion behavior, and the Doppler frequency shift information is used to represent the frequency shift value of the first wireless signal in Doppler after being affected by the motion behavior.

[0033] In addition, when using a high-resolution wireless signal sensor (such as a Wi-Fi device, millimeter-wave radar, or UWB device) as the signal receiver, there will still be noise signals. For example, when using Y = H * X + N to represent the second wireless signal, Y represents the second wireless signal, H represents the channel frequency response in the second wireless signal, X represents the first wireless signal, and N represents the noise in the received signal (generally including Gaussian white noise). Then, the data can be preprocessed (removing environmental noise and irrelevant signal fluctuations), the signal difference can be corrected, and finally the time-series data of the motion behavior (the channel frequency response after removing noise) can be obtained.

[0034] Step S103, construct a biomechanical model corresponding to the motion behavior of the temporomandibular joint according to the time-series data.

[0035] Specifically, after obtaining the time-series data, since it includes the amplitude attenuation information, phase offset information, and Doppler frequency shift information after removing noise, and these information respectively reflect the displacement, velocity, and direction change information of the temporomandibular joint in the motion behavior, a biomechanical model for reflecting the joint motion law can be established accordingly based on the time-series data according to the preset model generation rules.

[0036] Step S104, perform category analysis on the motion behavior according to the biomechanical model, and output the analysis result.

[0037] Specifically, the motion parameters output by the biomechanical model can be used as feature vectors and input into a preset classification module. The neural network or other machine learning models in the classification model, combined with the Softmax function, are used for class analysis, generating the probabilities of each category and comparing the category probabilities, and finally outputting the analysis result.

[0038] Among them, the analysis result can be a motion category (such as opening the mouth, closing the mouth, lateral movement), a pathological state (such as disc displacement, arthritis), or an abnormal level (mild, moderate, severe), and at least includes the probabilities of each motion category (the probability that a certain motion behavior belongs to "opening the mouth" is 80%, and the probability that it belongs to "closing the mouth" is 15%).

[0039] The method for analyzing temporomandibular joint movement based on wireless signals according to the present invention, through wireless signal acquisition, time-series data construction, and biomechanical model analysis, realizes non-contact and precise monitoring of temporomandibular joint movement behaviors without invasive operations, improving the monitoring experience of users; this method can capture the scattering, reflection, and Doppler frequency shift changes caused by temporomandibular joint movement, extract the displacement, velocity, and direction features reflecting joint movement, and combine machine learning algorithms to classify motion patterns (such as opening the mouth, closing the mouth, lateral sliding), thereby accurately identifying the categories of temporomandibular joint movement behaviors.

[0040] The following elaborates on some of the steps involved in steps S101 to S104 in detail:

[0041] In an alternative implementation manner of this embodiment, preprocessing the channel frequency response to obtain time-series data of motion behaviors specifically includes:

[0042] Decompose the channel frequency response according to a preset first calculation formula, jointly filter the channel frequency response through a preset time filter and frequency filter to obtain the filtered target channel frequency response, extract the amplitude attenuation information, phase shift information, and Doppler frequency shift information caused by the temporomandibular joint during motion behaviors based on the target channel frequency response, and generate time-series data corresponding to the motion behaviors according to the amplitude attenuation information, phase shift information, and Doppler frequency shift information.

[0043] Among them, the first calculation formula is H[n,k] represents the channel frequency response, α i [n] represents the complex gain of the signal on path i, used to describe the amplitude attenuation and phase change of the path, τ i [n] represents the propagation delay of the path, f d (i) represents the Doppler frequency shift information, used to reflect the speed and direction changes of temporomandibular joint movement, T Srepresents the time sampling interval, n represents the time index, k represents the frequency index, and N represents the total number of paths. represents the phase offset caused by the propagation delay at frequency f. represents the phase change caused by the Doppler effect at time t.

[0044] Specifically, through the preprocessing of the channel frequency response, especially the combined use of time filters and frequency filters, environmental noise and other interference signals are effectively removed, significantly improving the signal accuracy and reliability of motion behavior analysis. At the same time, the extracted amplitude attenuation information, phase offset information, and Doppler frequency shift information can comprehensively reflect the multi-dimensional characteristics of temporomandibular joint movement, making the time-series data more physically meaningful and facilitating the accurate establishment of subsequent biomechanical models.

[0045] In an alternative implementation of this embodiment, the channel frequency response is jointly filtered by a preset time filter and frequency filter to obtain the filtered target channel frequency response, which specifically includes: jointly filtering the channel frequency response according to a preset second calculation formula to obtain the filtered target channel frequency response.

[0046] Among them, the second calculation formula is H filtered [n,k] represents the target channel frequency response, h t [m] represents the impulse response of the time filter, h f [l] represents the impulse response of the frequency filter, m represents the time filtering index, l represents the frequency filtering index, M t represents the sampling length of the time filter, and Mf represents the sampling length of the frequency filter.

[0047] Specifically, through the flexible parameter design of the joint filter (M t represents the sampling length of the time filter, and Mf represents the sampling length of the frequency filter), this method can adapt to different types of wireless signals (such as Wi-Fi signals, millimeter-wave signals) and different motion behavior patterns, and has high scalability.

[0048] In an alternative implementation of this embodiment, a biomechanical model corresponding to the motion behavior of the temporomandibular joint is constructed based on the time-series data, which specifically includes: respectively extracting the displacement, velocity, and direction change information used to reflect the temporomandibular joint in the motion behavior from the amplitude attenuation information, phase offset information, and Doppler frequency shift information, and constructing a biomechanical model corresponding to the motion behavior of the temporomandibular joint using a preset third calculation formula.

[0049] Specifically, in the biomechanical model, it can be represented by the third calculation formula, and the third calculation formula is M(t) = R(t) + T(t), where R(t) represents the rotational component in the motion behavior, and the rotational component reflecting the rotation of the mandible around the rotation axis includes the angular velocity and angular acceleration of the temporomandibular joint. T(t) represents the translational component in the joint movement, and the translational component includes the displacement changes of the joint in the preset x, y, and z directions.

[0050] Among them, the rotational component is θ(t) represents the rotational angle of the mandible at time t, and R(t) defines the rotational movement of the mandible in the glenoid fossa. The translational component is x(t), y(t), and z(t) are the translational amounts of the articular disc or the mandible along each axis at time t.

[0051] In addition, the biomechanical model can be a six-degree-of-freedom rigid body motion model, which is further expressed as:

[0052] M(t) = R z (θ z (t))·R y (θ y (t))·R x (θ x (t)) + T(t), where R z (θ z (t)), R y (θ y (t)), R x (θ x (t)),

[0053] respectively represent the rotation matrices around the x, y, and z axes.

[0054] Specifically, through the six-degree-of-freedom rigid body motion model, the rotational and displacement characteristics of the mandible are comprehensively considered, realizing a comprehensive, accurate, and efficient description of the temporomandibular joint movement. Thereby, the analysis performance is improved, and the applicable range of the model is expanded, further enhancing the accurate identification of the temporomandibular joint.

[0055] In an alternative implementation manner of this embodiment, the motion behavior is classified and analyzed according to the biomechanical model, and the analysis result is output. Specifically, it includes: extracting the motion trajectory features in the time series data for reflecting the motion behavior, processing the amplitude and phase in the motion trajectory features by using a preset convolutional neural network to obtain a target vector, and importing the target vector into a preset Softmax function to obtain the analysis result; among them, the analysis result includes the probabilities corresponding to the categories of each motion behavior.

[0056] Specifically, the motion trajectory features in the time series data are extracted through the fourth calculation formula and the fifth calculation formula. The fourth calculation formula is Re(H[n,k]) represents the real part of the complex channel state information H[n,k], and Im(H[n,k]) represents the imaginary part of the complex channel state information H[n,k]. Also, the fifth calculation formula is φ[n,k] represents the phase.

[0057] Thus, by using the fourth and fifth calculation formulas, the complex form of the channel state information (CSI) is decomposed into the amplitude |H[n,k]| and the phase φ[n,k], achieving a refined separation of the signal features. Among them, the amplitude reflects the attenuation information of the signal in the propagation path, while the phase reflects the relative position change during signal propagation. This decomposition method improves the resolution and analysis accuracy of signal feature extraction, providing high-quality basic data for subsequent motion behavior analysis.

[0058] In an alternative implementation of this embodiment, a preset convolutional neural network is used to process the trajectory features to obtain target features, specifically including: using the preset convolutional neural network to process the trajectory features to obtain the first features extracted by the convolutional layer and the second features extracted by the pooling layer, and mapping the first features and the second features to a high-dimensional feature space to obtain a target vector.

[0059] Specifically, the calculation formula in the convolutional neural network is Z ij represents the i-th and j-th units of the convolution result, X i+m-1,j+n-1 represents the area in the input CSI matrix covered by the convolution kernel, K mn represents the m-th and n-th weights of the convolution kernel, b represents the bias of the convolution kernel, and h and w respectively represent the height and width of the convolution kernel. Through the above convolution calculation formula, the obtained convolution result (the first features extracted by the convolutional layer) is further calculated through the activation function formula A ij =σ(Z ij ) to obtain the activation features. By performing a non-linear transformation on the convolution result through the activation function, complex patterns of feature changes in the temporomandibular joint movement trajectory can be captured, especially when pathological changes or abnormal motion behaviors are involved, improving the description ability of the model.

[0060] After obtaining the activation features, pooling processing is performed on the activation features. Through the pooling formula P ij =pool({A kl}),k∈[i,i+p-1],l∈[j,j+q-1], P ij represents the second features after pooling (the second features extracted by the pooling layer), pool represents the pooling operation, and p and q represent the sizes of the pooling window.

[0061] After obtaining the first feature and the second feature, the mapping formula y = W·v + b is used to map the first feature and the second feature into a high-dimensional feature space. Here, v represents the expanded feature vector (the first feature and the second feature extracted and flattened by the convolutional layer and the pooling layer), W represents the weight matrix, and b represents the bias vector. Finally, the score vector y is obtained. The score vector y is obtained through the linear transformation by the weight matrix W and the bias vector b. The score vector y (the final high-dimensional feature vector) is the output result of the linear transformation, which contains the key information extracted by convolution and pooling. After high-dimensional mapping, it can represent the trajectory features more comprehensively, with stronger expressive ability and discriminative power, and can provide support for subsequent tasks such as classification, regression, or anomaly detection. It is the core output result of the entire feature processing process.

[0062] After obtaining the target vector y, the target vector y is input into the classification formula in the Softmax function. P(c∣v) represents the probability distribution (the probability of each category c), and Y C is the score of the target vector y on the category c, and C is the total number of categories.

[0063] Specifically, the Softmax function converts the target vector y into the probability distribution P(c∣v) of each category c. Through probability normalization, it clearly represents the possibility that the motion behavior corresponding to the target vector y belongs to each category. For example, the probability that a certain motion behavior belongs to "opening the mouth" is 80%, and the probability that it belongs to "closing the mouth" is 15%, which clearly and intuitively reflects the classification result. That is, the Softmax function not only amplifies the score difference between categories, improves the stability of classification, but also provides an intuitive probability output, which is convenient for accurate judgment of motion patterns (such as opening the mouth, closing the mouth) or pathological states (such as disc displacement, arthritis). At the same time, the output probability value can assist in evaluating the confidence of the model in the classification result, providing a scientific basis for anomaly detection or subsequent analysis.

[0064] Figure 3 Fig. shows the temporomandibular joint motion analysis device based on wireless signals provided by the embodiments of the present invention, including a signal transmitter, a signal receiver, and a processor.

[0065] The signal transmitter is used to send a first wireless signal to the signal receiver in the monitoring area; wherein, the monitoring area is used to cover the movable range of the user's temporomandibular joint; the signal receiver is used to collect a second wireless signal passing through the monitoring area; wherein, the second wireless signal is a signal formed by the first wireless signal based on the motion behavior of the temporomandibular joint in the monitoring area; the processor is used to preprocess the second wireless signal to obtain the time series data of the motion behavior, construct a biomechanical model corresponding to the motion behavior of the temporomandibular joint according to the time series data, and perform category analysis on the motion behavior according to the biomechanical model, and output the analysis result.

[0066] The method and related device for temporomandibular joint movement analysis based on wireless signals of the present invention achieve non-contact and precise monitoring of temporomandibular joint movement behavior through wireless signal acquisition, time-series data construction, and biomechanical model analysis, without the need for invasive operations. This method can capture the changes in scattering, reflection, and Doppler frequency shift caused by temporomandibular joint movement, extract the displacement, velocity, and direction features reflecting joint movement, and classify movement patterns (such as opening the mouth, closing the mouth, and lateral sliding) by combining machine learning algorithms, so as to accurately identify the categories of temporomandibular joint movement behavior. In addition, the wireless signal-based sensing technology is compatible with existing devices such as Wi-Fi or millimeter-wave radar, and has the characteristics of device miniaturization, low cost, and high sensitivity, and can be widely applied to home monitoring and portable medical devices.

[0067] At the same time, the main advantages of this method are as follows: Non-contact: It does not require direct wearing of devices or invasive operations, and is suitable for long-term monitoring and clinical applications. High sensitivity: It can detect displacement changes at the micron level and accurately capture the subtle movements of the TMJ. Convenience: The miniaturization of the device and the low cost make it have broad application prospects in home monitoring and portable medical devices. The TMJ movement recognition technology based on wireless signals not only provides a new means for temporomandibular joint function evaluation, but also promotes the leapfrog development of non-contact biosignal sensing in the field of oral medicine.

[0068] Figure 4 The electronic device provided by the embodiment of the present invention is shown. This electronic device can be used to implement the method for temporomandibular joint movement analysis based on wireless signals in any of the foregoing embodiments. The electronic device includes:

[0069] A memory 401, a processor 402, a bus 403, and a computer program stored on the memory 401 and executable on the processor 402. The memory 401 and the processor 402 are connected through the bus 403. When the processor 402 executes this computer program, it implements the method for temporomandibular joint movement analysis based on wireless signals in the foregoing embodiments. Among them, the number of processors can be one or more.

[0070] The memory 401 can be a high-speed random access memory (RAM, Random Access Memory) or a non-volatile memory, such as a disk memory. The memory 401 is used to store executable program codes, and the processor 402 is coupled to the memory 401.

[0071] Furthermore, the embodiment of the present application also provides a computer-readable storage medium. This computer-readable storage medium can be disposed in the electronic device in each of the foregoing embodiments, and this computer-readable storage medium can be a memory.

[0072] A computer program is stored on the computer-readable storage medium. When the program is executed by a processor, it implements the human body bioelectrical impedance measurement method in the foregoing embodiments. Further, the computer-readable storage medium may also be various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk, or an optical disc that can store program codes.

[0073] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods. 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 coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of devices or modules can be in an electrical, mechanical or other form.

[0074] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing module, or each module exists physically alone, or two or more modules can be integrated in one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0076] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a readable storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. And the foregoing readable storage medium includes: various media such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disc that can store program codes.

[0077] It should be noted that, for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0078] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for analyzing temporomandibular joint motion based on wireless signals, characterized in that: Applicable to a temporomandibular joint motion analysis device comprising a signal transmitter and a signal receiver, wherein the signal transmitter is used to send a first wireless signal to the signal receiver in a monitoring area, and the temporomandibular joint motion analysis method comprises: Acquire a second wireless signal collected by the signal receiver; wherein the second wireless signal is a signal generated by the first wireless signal based on the movement behavior of the temporomandibular joint in the monitoring area; Preprocessing the second wireless signal to obtain time series data of the movement behavior; Constructing a biomechanical model corresponding to the movement behavior of the temporomandibular joint according to the time series data; The movement behavior is subjected to category analysis according to the biomechanical model, and the analysis result is output.

2. The method for analyzing temporomandibular joint motion based on wireless signals according to claim 1, characterized in that: The preprocessing of the second wireless signal to obtain the time series data of the movement behavior specifically includes: detecting a channel frequency response in the second wireless signal; The channel frequency response is preprocessed to obtain time series data of the motion behavior; wherein the channel frequency response includes amplitude attenuation information, phase offset information and Doppler frequency shift information, the amplitude attenuation information is used to indicate the attenuation value of the amplitude of the first wireless signal after being affected by the motion behavior, the phase offset information is used to indicate the offset value of the phase of the first wireless signal after being affected by the motion behavior, and the Doppler frequency shift information is used to indicate the Doppler frequency shift value of the first wireless signal after being affected by the motion behavior.

3. The method for analyzing temporomandibular joint motion based on wireless signals according to claim 2, characterized in that: The preprocessing of the channel frequency response to obtain the time series data of the movement behavior specifically includes: Decomposing the channel frequency response according to a preset first calculation formula; Among them, the first calculation formula is: H[n,k] represents the channel frequency response, α i [n] represents the complex gain of the signal on path i, τ i [n] represents the propagation delay of the path, f d (i) Represents Doppler frequency shift information, T S represents the time sampling interval, n represents the time index, k represents the frequency index, and N represents the total number of paths. represents the phase shift caused by the propagation delay at frequency f, represents the phase change caused by the Doppler effect at time t; Performing joint filtering on the channel frequency response through a preset time filter and a frequency filter to obtain a filtered target channel frequency response; Extracting amplitude attenuation information, phase shift information and Doppler frequency shift information caused by the temporomandibular joint when performing the movement behavior based on the target channel frequency response; The time series data corresponding to the motion behavior is generated according to the amplitude attenuation information, the phase offset information and the Doppler frequency shift information.

4. The method for analyzing temporomandibular joint motion based on wireless signals according to claim 3, characterized in that: The method of jointly filtering the channel frequency response by using a preset time filter and a frequency filter to obtain a filtered target channel frequency response specifically includes: Performing joint filtering on the channel frequency response according to a preset second calculation formula to obtain a filtered target channel frequency response; Among them, the second calculation formula is: H filtered [n,k] represents the target channel frequency response, h t [m] represents the impulse response of the time filter, h f [l] represents the impulse response of the frequency filter, m represents the time filter index, l represents the frequency filter index, M t represents the sampling length of the time filter, and Mf represents the sampling length of the frequency filter.

5. The method for analyzing temporomandibular joint motion based on wireless signals according to claim 3, characterized in that: The step of constructing a biomechanical model corresponding to the movement behavior of the temporomandibular joint according to the time series data specifically includes: Extracting corresponding information reflecting the displacement, velocity and direction change of the temporomandibular joint in the movement behavior from the amplitude attenuation information, the phase offset information and the Doppler frequency shift information respectively; A preset third calculation formula is used to construct a biomechanical model corresponding to the movement behavior of the temporomandibular joint; wherein the third calculation formula is M(t)=R(t)+T(t), R(t) represents the rotational component in the movement behavior, the rotational component includes the angular velocity and angular acceleration of the temporomandibular joint, and T(t) represents the translational component in the joint movement, and the translational component includes the displacement changes of the joint in the preset x, y and z directions.

6. The method for analyzing temporomandibular joint motion based on wireless signals according to claim 3, characterized in that: The performing category analysis on the movement behavior according to the biomechanical model and outputting the analysis result specifically includes: Extracting motion trajectory features from the time series data for reflecting the motion behavior; wherein the motion trajectory features include amplitude and phase; Using a preset convolutional neural network to process the motion trajectory features to obtain a target vector; The target vector is introduced into a preset Softmax function to obtain the analysis result; wherein the analysis result includes the probability corresponding to the category of each movement behavior.

7. The method for analyzing temporomandibular joint motion based on wireless signals according to claim 6, characterized in that: The method of processing the motion trajectory features using a preset convolutional neural network to obtain target features specifically includes: The motion trajectory feature is processed using a preset convolutional neural network to obtain a first feature extracted by a convolution layer and a second feature extracted by a pooling layer; The first feature and the second feature are mapped to a high-dimensional feature space to obtain a target vector.

8. A temporomandibular joint motion analysis device based on wireless signals, characterized in that: It includes a signal transmitter, a signal receiver and a processor; The signal transmitter is used to send a first wireless signal to the signal receiver in a monitoring area; wherein the monitoring area is used to cover the movable range of the user's temporomandibular joint; The signal receiver is used to collect a second wireless signal passing through the monitoring area; wherein the second wireless signal is a signal generated by the first wireless signal based on the movement behavior of the temporomandibular joint in the monitoring area; The processor is used to preprocess the second wireless signal to obtain the time series data of the movement behavior, construct a biomechanical model corresponding to the movement behavior of the temporomandibular joint based on the time series data, perform category analysis on the movement behavior based on the biomechanical model, and output the analysis results.

9. An electronic device, characterized in that: Includes memory, processor and bus; The bus is used to realize the connection and communication between the memory and the processor; The processor is used to execute the computer program stored in the memory; When the processor executes the computer program, the steps in the method for analyzing temporomandibular joint motion based on wireless signals described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for analyzing temporomandibular joint motion based on wireless signals described in any one of claims 1 to 7 are implemented.

Images