Tongue muscle stimulator

Abstract

The present application relates to a tongue muscle stimulator, which includes: an electrode, which is placed in the oral cavity when in use, and is used to electrically stimulate the genioglossus muscle; a sensor, which is used to obtain a pressure signal between the teeth and the tongue; and a controller, which is configured with a computer program to implement the following steps: receiving the pressure signal, and identifying the current tongue movement pattern according to the pressure signal; predicting a drive signal according to the tongue movement pattern, and correspondingly driving the electrode to perform electrical stimulation. The tongue muscle stimulator of the present application can adapt to the electrode position deviation, further improving the wearing experience.

Description

Technical Field

[0001] The present application relates to the technical field of medical devices, and in particular to a tongue muscle stimulator. Background Art

[0002] When the upper airway is narrowed, or the nervous system's regulatory function on the upper airway muscles is reduced during sleep, the airway may partially or completely collapse, the ventilation volume may decrease, and sleep apnea may occur, affecting the quality of sleep.

[0003] Some tongue muscle stimulation devices in the prior art electrically stimulate the tongue or surrounding muscles to train tongue muscle tension and reduce upper airway tissue collapse, but they are not comfortable to wear and have poor stimulation or training effects. Especially after the tongue posture changes, the electrodes in the tongue muscle stimulation device will shift in relative position, which may cause obvious discomfort, making it difficult to ensure the stimulation effect and causing poor patient compliance. Summary of the invention

[0004] The present application provides a tongue muscle stimulator that can adapt to electrode position deviation and further improve the wearing experience.

[0005] The present application provides a tongue muscle stimulator, comprising:

[0006] The electrode is placed in the oral cavity when in use to electrically stimulate the genioglossus muscle;

[0007] A sensor for acquiring a pressure signal between teeth and tongue;

[0008] A controller is configured with a computer program to implement the following steps:

[0009] receiving the pressure signal, and identifying a current tongue movement pattern according to the pressure signal;

[0010] The driving signal is predicted according to the tongue movement pattern, and the electrodes are driven accordingly to implement electrical stimulation.

[0011] Several optional methods are also provided below, but they are not intended to be additional limitations on the above-mentioned overall solution, but are merely further supplements or preferences. Under the premise that there are no technical or logical contradictions, each optional method can be combined with the above-mentioned overall solution separately, and multiple optional methods can also be combined.

[0012] In one embodiment, identifying the current tongue movement pattern according to the pressure signal specifically includes:

[0013] Continuously obtaining the pressure signal to obtain pressure time series data;

[0014] Through the first prior relationship, the tongue movement pattern corresponding to the pressure timing data is identified.

[0015] In one embodiment, the sensors are configured in pairs and correspondingly obtain two-way pressure time series data, and the identification of tongue movement patterns includes:

[0016] Calculate the correlation coefficient r1 of the two-way pressure time series data;

[0017] Calculate the correlation coefficient r2 between each channel of pressure time series data and the pressure time series data to be compared in the first prior relationship;

[0018] The tongue movement pattern is determined based on the correlation coefficient r1 and the correlation coefficient r2.

[0019] In one embodiment, the same tongue movement pattern includes multiple movement stages, and when identifying the tongue movement pattern, the current movement stage is also identified through the first prior relationship.

[0020] In one embodiment, corresponding pressure sampling methods are configured for different exercise stages, and the pressure signal is acquired according to the pressure sampling methods.

[0021] In one embodiment, predicting the driving signal according to the tongue movement pattern specifically includes:

[0022] The pressure signal of the current motion stage is used to calculate the driving signal corresponding to the current motion stage through the second prior relationship.

[0023] In one embodiment, it also includes:

[0024] The pressure signal of the current motion stage is used to obtain the pressure time series data of the subsequent motion stage through the motion state space prediction model, and the corresponding driving signal is predicted.

[0025] In one embodiment, the driving signal is further calibrated, specifically comprising:

[0026] Obtaining corresponding first impedance information according to the current sampling signal;

[0027] comparing the first impedance information with second impedance information corresponding to the current driving signal;

[0028] The motion state space prediction model is updated according to the comparison result, and the updated motion state space prediction model is used to re-predict the drive signal of the subsequent motion stage to complete the calibration.

[0029] In one embodiment, updating the motion state space prediction model includes:

[0030] comparing the first impedance information and the second impedance information and obtaining a deviation value;

[0031] Determining an adjustment trend of a model parameter in the motion state space prediction model according to the deviation value;

[0032] An adjustment range is determined according to the adjustment trend to complete the update.

[0033] In one embodiment, the sampling signal is obtained by using the electrode, and the sampling signal is obtained including:

[0034] Determine the electrode sampling method according to the current tongue movement pattern;

[0035] The sampling signal is obtained according to the electrode sampling method.

[0036] The tongue muscle stimulator of the present application can electrically stimulate the genioglossus muscle through electrodes, and at the same time, combined with the pressure signal obtained by the sensor, it can predict and calibrate specific stimulation parameters in the drive signal, thereby avoiding the hysteresis stimulation problem in the prior art and improving the wearing experience and use effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 This is a schematic diagram of the structure of a tongue muscle stimulator in one embodiment of the present application;

[0039] Figure 2 for Figure 1 Schematic diagram of the middle tongue muscle stimulator from a top view;

[0040] Figure 3 for Figure 2 Schematic diagram of the cross section at AA;

[0041] Figure 4 for Figure 2 Schematic diagram of the cross section at BB;

[0042] Figure 5 It is a schematic diagram of a tongue muscle stimulator from a side view;

[0043] Figure 6 This is a schematic diagram of a tongue muscle stimulator from an upward perspective;

[0044] Figure 7 Schematic diagram of the pressure sensor setup for the tongue muscle stimulator;

[0045] Figure 8 This is a schematic diagram of the electrodes and connection circuits of the tongue muscle stimulator;

[0046] Fig. 9This is a flow chart of a control method for a tongue muscle stimulator in one embodiment of the present application.

[0047] The reference numerals of the components are as follows:

[0048] 100, positioning portion; 110, tooth slot; 111, buccal side wall; 112, lingual side wall;

[0049] 200, working part; 210, cavity;

[0050] 300, electrode; 310, connecting line;

[0051] 400, bridge arm; 410, incisor positioning groove; 420, extension arm; 430, interface assembly;

[0052] 500, sensor;

[0053] 600. Controller. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0055] It should be noted that when a component is referred to as being "fixed to" or "disposed on" another component, it may be directly on the other component or there may also be a central component. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may be a central component at the same time. The terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used in the specification of this application are for illustrative purposes only and do not represent the only implementation method.

[0056] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0057] In the present application, unless otherwise clearly specified and limited, a first feature being “above” or “below” a second feature may mean that the first feature is directly in contact with the second feature, or the first feature and the second feature are indirectly in contact through an intermediate medium. Moreover, a first feature being “above”, “above”, or “above” a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level (or in a state of use, or from a certain perspective of the attached figure) than the second feature. A first feature being “below”, “below”, or “below” a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level (or in a state of use, or from a certain perspective of the attached figure) than the second feature.

[0058] Unless otherwise defined, all technical and scientific terms used in the specification of this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in the specification of this application includes any and all combinations of one or more related listed items.

[0059] In the prior art, the driving signal of the tongue muscle stimulator is used to control the electrode to electrically stimulate the predetermined part, and the driving signal may include several stimulation parameters, such as frequency, pulse width, amplitude, etc. These are adjusted according to the impedance value in the mouth of each user, but the contact area between the electrode and the predetermined part (such as the genioglossus muscle) has a strong correlation with the impedance value. For example, in the initial stage, after the corresponding impedance value is measured according to the degree of fit between the electrode and the genioglossus muscle, the stimulation parameter acceptable to the user is adjusted according to the impedance value. However, when swallowing occurs, or when lying on the side, the movement of the tongue will cause the tongue muscle stimulator to produce relative displacement, resulting in a change in the contact area between the electrode and the predetermined part, especially when the contact area becomes smaller, the stimulation parameter set before is too large, which brings a tingling sensation of electrical stimulation to the user. In addition, simply using impedance to regulate the driving signal also has hysteresis, and the control accuracy is limited.

[0060] An embodiment of the present application provides a tongue muscle stimulator with electrodes and sensors. When the electrodes are placed in the oral cavity, the genioglossus muscle can be electrically stimulated. From the muscle state of the genioglossus muscle, the genioglossus muscle is fan-shaped, and the closer the genioglossus muscle is to the inside, the stronger its muscle strength is. The electrodes of this embodiment are located under the tongue and arranged relatively. The main function is to stimulate the genioglossus muscle and generate muscle tension to prevent the tongue root from falling back. It can further improve breathing, improve sleep quality, or perform muscle training.

[0061] The sensor can specifically adopt a PVDF film pressure sensor to obtain the pressure signal between the teeth and the tongue. The pressure signal does not strictly limit the pressure of the surrounding tissue directly acting on the electrode, but at least has a correlation. For example, the sensor and the electrode are installed on the same deformable component. When the electrode and the surrounding tissue are offset or the pressure changes, it can be sensed by the sensor accordingly.

[0062] The tongue muscle stimulator can also have a built-in or external controller. The controller can use existing technology as far as the hardware itself is concerned, and of course the configuration can be adaptively adjusted. The controller can use chips and related circuits with data interaction, storage and processing capabilities, etc. The controller can communicate with electrodes, sensors and other terminals in a wired or wireless manner.

[0063] In order to support and install electrodes and sensors, the tongue muscle stimulator of this embodiment also includes a positioning part for positioning and cooperating with corresponding tissues in the oral cavity. For example, the positioning part can be positioned in the oral cavity by means of braces or the like. It further includes a working part, which is connected to the positioning part and can be placed under the tongue and close to the genioglossus muscle.

[0064] In an improved embodiment, the working part is a deformable capsule, for example, it can be a hollow air bag, the positioning part has a tooth slot and is arranged in pairs, the two positioning parts are connected by a bridge arm, the bridge arm can be further positioned on the incisors and has an interface component extending to the outside of the oral cavity, an external power supply or an external controller, etc.

[0065] The working parts are also configured in pairs and connected to the corresponding positioning parts. The working parts are respectively located on two opposite sides under the tongue, and each working part is configured with electrodes and sensors.

[0066] The same working part has a relative lingual side and buccal side, wherein the electrode is located on the lingual side of the working part, and the electrodes in the two working parts are arranged facing each other. Since the deformation of the capsule can transmit the pressure changes from a certain direction to other parts of the capsule, the requirements for the installation position of the sensor are relatively loose. For example, the sensor is located on the lingual side, buccal side or towards the lower side of the oral cavity of the working part.

[0067] The electrode is sheet-shaped and fixed to the outer surface of the capsule. The sensor can be fixed to the outer surface of the capsule to directly sense the pressure of the surrounding tissue, or the sensor can be built into the capsule to sense the internal stress generated by the deformation of the capsule, and can even sense the fluid pressure inside the capsule.

[0068] The controller may include a memory and a processor, and the memory stores a computer program for execution by the processor. When the tongue muscle stimulator is working, the computer program is executed accordingly, so that the controller can receive the pressure signal from the sensor and identify the current tongue movement pattern according to the pressure signal; then predict the drive signal according to the tongue movement pattern, and drive the electrode accordingly to implement electrical stimulation.

[0069] There are two sensors, one on each side of the tongue. They can collect and obtain two pressure signals when working. When the tongue tilts to one side or squeezes both sides at the same time, the capsule adaptively deforms, which can change the pressure of the two sensors and the surrounding tissues. Of course, the corresponding pressure signals will also be detected and output by the sensor.

[0070] After the sensor continuously obtains pressure signals in a certain period of time, pressure time series data can be obtained. Then, through the first prior relationship, the characteristics and relative relationship of the two pressure signals are analyzed and compared, and the tongue movement pattern corresponding to the pressure time series data can be identified.

[0071] The first prior relationship includes the correspondence between different tongue movement patterns and pressure changes on both sides of the tongue. Common tongue movement patterns include turning over movement patterns, swallowing movement patterns, breathing movement patterns, etc., and each has different pressure signal change characteristics. For example, in the turning over movement pattern, since the tongue tilts to one side, the difference in the pressure values ​​of the two pressure signals increases. In the swallowing movement pattern, both pressure signals change greatly in a short period of time and the change trends are basically the same, and they recover after the changes. In the breathing movement pattern, the two pressure signals change slowly over a long period of time, and the similarity between adjacent cycles is high. Based on the above principles, a first prior relationship can be established for different tongue movement patterns for identification and comparison.

[0072] Of course, a movement state threshold can be set. When the value or change of the pressure signal does not reach the threshold, it is considered that there is no switching of the tongue movement mode, and the electrode continues to work according to the current tongue movement mode. When the value or change of the pressure signal reaches the threshold, the tongue movement mode can be re-identified.

[0073] When identifying tongue movement patterns, it is possible to calculate:

[0074] The correlation coefficient r1 of the two-way pressure time series data;

[0075] and the correlation coefficient r2 between each channel of pressure time series data and the pressure time series data of the prior motion mode to be compared in the first prior relationship;

[0076] The tongue movement pattern can be further determined in the first priori relationship based on the correlation coefficient r1 and the correlation coefficient r2.

[0077] To address the problem of deviation in the duration of motion features in the same motion pattern of different groups of people, dynamic time warping (DTW) can be used to calculate the distance between the pressure time series data and the prior relationship sequence to avoid the interference of the pressure time series data queue length on the pattern recognition results.

[0078] According to the characteristics of the corresponding tongue movement pattern, the tongue movement pattern can be divided into movement stages. That is, in the same tongue movement pattern, according to the corresponding characteristics (such as the changing trend or amplitude of the pressure time series data), it can be divided into different movement stages. Each movement stage is manifested as a different changing trend of the pressure signal and corresponds to a different electrical stimulation driving signal. Similarly, when identifying the tongue movement pattern, the current movement stage is also identified through the first prior relationship.

[0079] The second prior relationship can be pre-configured according to the characteristics of the driving signal at different stages, and the driving signal corresponding to the current movement stage can be calculated by using the pressure signal of the current movement stage and the second prior relationship. As for the second prior relationship itself, it can be trained based on historical data to construct a corresponding prior model.

[0080] In order to predict the next movement stage or more subsequent movement stages in the same tongue movement pattern, after identifying the previous movement stage, the pressure signal of the current movement stage and the movement state space prediction model can be used to obtain the pressure timing data of the subsequent movement stage for subsequent prediction of the corresponding drive signal.

[0081] The division of tongue movement patterns and specific movement stages also corresponds to different pressure sampling methods, that is, the sensor corresponds to different sampling frequencies or durations to meet the characteristics of the stage. For example, in the identified turning movement pattern, it is necessary to increase the sampling frequency when the turning movement occurs, and then predict the end time of the turning movement, and perform a short-term verification sampling at the end. If it is in the breathing movement, due to the periodicity of the movement, verification sampling is required in each cycle.

[0082] Since the contact condition between the electrode and the predetermined part can be more directly reflected in the change of impedance, the present application, in a further improved embodiment, also uses the electrode contacts to perform impedance measurement, and then uses the impedance information to calibrate the drive signal, that is, in the subsequent cycle control, the impedance information will also participate in the prediction of the drive signal to ensure the discharge stimulation effect and the user experience.

[0083] Different electrode sampling methods can be used for impedance measurement. The electrode sampling method is related to the tongue movement pattern or the movement stage. After the tongue movement pattern and the movement stage are identified or determined, the electrode sampling method is adjusted accordingly to take into account the control accuracy and energy consumption. For example, in the turning over movement mode, the impedance change has the characteristics of rapid time variation. The electrode sampling method of impedance measurement can be configured as a verification fast sampling of the characteristic stage, and is not suitable for smooth sampling processing of long time windows. However, in the respiratory movement mode, periodic sampling can be performed in the characteristic time period based on the periodic characteristics.

[0084] The drive signal itself may also contain or be associated with impedance information. When calibrating the drive signal, specifically:

[0085] Acquire a current sampling signal using an electrode, and obtain corresponding first impedance information according to the current sampling signal;

[0086] Obtaining second impedance information according to the current driving signal, and comparing the first impedance information with the second impedance information;

[0087] The drive signal for the subsequent movement phase is calibrated according to the comparison result, and the electrical stimulation is implemented using the calibrated drive signal.

[0088] The second impedance information is related to the predicted driving signal, but in fact may deviate from the measured first impedance information. Therefore, it is possible to calculate whether the first impedance information satisfies the distribution interval of the second impedance information, and obtain the deviation value between the first impedance information and the second impedance information accordingly. When calibrating the driving signal of the subsequent movement stage, the adjustment trend of the model parameters in the motion state space prediction model can be determined according to the deviation value, and the adjustment amplitude can be further preferably determined to complete the update of the motion state space prediction model, and the updated motion state space prediction model is used to re-predict the pressure time series data corresponding to the next movement stage or subsequent multiple movement stages, and the second prior relationship is used to calculate the updated (i.e., calibrated) driving signal, and the re-predicted driving signal is used to implement electrical stimulation from the next movement stage.

[0089] During the entire use process, when two different time periods are divided into movement stages through the first prior relationship, they may be identified as the same movement stage, but this is only based on the similar changing trends of the pressure signals of the two, but the specific values ​​will be different. Therefore, a dynamic mechanism is adopted in this application to use the current movement stage to predict the pressure time series data of the subsequent movement stage (belonging to the current tongue movement pattern) in real time, and continuously update the movement state space prediction model to ensure the accuracy of the prediction and improve the treatment effect.

[0090] Regarding the specific structure of the tongue muscle stimulator, the following is combined with Figure 1 to Figure 8 To further explain, the tongue muscle stimulator includes:

[0091] The positioning part 100 is used for positioning and cooperating with the corresponding tissue in the oral cavity;

[0092] The working part 200 is connected to the positioning part 100. The working part 200 has a cavity 210, for example, a deformable capsule, i.e., an airbag. At least a portion of the outer surface of the airbag is a bonding surface that deforms adaptively with the shape of the working part 200 to tend to a predetermined position;

[0093] Electrode 300, fixed to the binding surface, for electrical stimulation;

[0094] The sensor 500 is fixed to the working part 200 and is used to collect pressure signals;

[0095] The controller 600 is connected to the electrode 300 and the sensor 500 in an electrical circuit.

[0096] In the bonding surface of the working part 200, the area where the electrode 300 is located is the first area, and the working part 200 has an initial shape without being pressed (see Figure 4 ), the first area has a tendency to bulge outward relative to the surrounding area in the initial shape. Correspondingly, when the working part 200 is pressed, the bulge degree of the first area changes accordingly.

[0097] The top surface of the working part 200 is a flat area for placing the tongue, and the electrode 300 is located on the inner side of the working part 200. The outer edge of the working part 200 gradually expands from the front side (i.e., the part facing the lip side of the oral cavity) to the back side, and the back side further extends over the positioning part 100. The working part 200 as a whole is a drooping shape with one end narrowed and the other end expanded.

[0098] See also Figure 3 , in the left-right direction of the figure, the ratio between the length D1 of the electrode 300 and the length D2 of the working portion 200 ranges from 0.35 to 0.85. Figure 4 In the vertical direction of the figure, the ratio between the height H1 of the electrode 300 and the height H2 of the working part 200 ranges from 0.25 to 0.75. The thickness of the electrode 300 matches the wall thickness of the working part 200.

[0099] The positioning part 100 has a higher strength than the working part 200. When the working part 200 is subjected to an external force, the working part 200 deforms earlier or to a greater extent than the positioning part 100. The positioning part 100 and the working part 200 are polymer materials of different components. Specifically, the polymer material is silica gel, plastic, or a composite material with inorganic materials added.

[0100] See also Figure 2~Figure 5 The positioning portion 100 has a top side and a bottom side opposite to each other, and the bottom side has a tooth slot 110. The corresponding tissue that cooperates with the positioning portion 100 is the tooth tissue. The tooth slot 110 has two opposite slot walls, and the tooth slot 110 corresponds to the molars. The two opposite slot walls of the tooth slot 110 are the buccal side wall 111 and the lingual side wall 112, respectively, and the working portion 200 is connected to the bottom side of the lingual side wall 112. The positioning portion 100 has an inner side and an outer side opposite to each other, and the working portion 200 is located at the bottom side of the positioning portion 100 and further extends to the inner side of the positioning portion 100.

[0101] A bridge arm 400 is connected between the two positioning parts 100. The bridge arm 400 is connected to the outside of the two positioning parts 100 and extends along the trend of tooth arrangement. That is, the bridge arm 400 is C-shaped. The bridge arm 400 and the positioning part 100 form a brace structure to improve the positioning effect of the positioning part 100. Furthermore, the bridge arm 400 is provided with an incisor positioning groove 410.

[0102] The controller 600 is connected to the electrode 300 and the sensor 500 via the connecting line 310 to drive the electrode 300 to perform electrical stimulation and / or detect corresponding signals through the electrode 300 .

[0103] The connection line 310 of the electrode 300 may be embedded in one or more of the bridge arm 400, the positioning portion 100 or the working portion 200, such as Figure 6 as well as Figure 8 As shown in the figure, the controller 600 is externally mounted, and the tongue muscle stimulator is further provided with an interface component 430, through which the controller 600 is connected to the electrode 300. For example, the bridge arm 400 further includes an extension arm 420, and the interface component 430 is disposed on the extension arm 420. The extension arm 420 extends out of the oral cavity from the bridge arm 400 back to the incisor positioning groove 410, and the interface component 430 is disposed on the end of the extension arm 420 located outside the oral cavity.

[0104] See also Figure 7 The tongue muscle stimulator may further include a sensor 500, which is fixed to the working part 200 and is used to detect and feed back a pressure signal to the controller 600. In the figure, the sensor 500 is arranged on the bottom surface of the working part 200.

[0105] See also Fig. 9 Based on the tongue muscle stimulators of the above embodiments, the present application also provides a control method for the tongue muscle stimulator, which can also be understood as providing a method for generating an electrode driving signal based on the tongue muscle stimulator. Specifically, it includes:

[0106] A tongue muscle stimulator is provided. The tongue muscle controller includes a pair of capsules that can be placed on opposite sides of the tongue. The capsules are adaptively deformed under the action of surrounding tissues. Electrodes and sensors are fixed on the capsules. The capsules can specifically be hollow air bags. During use, the air bags are placed in a small gap between the teeth and the tongue. The air bags are compressed and deformed, and the electrode contacts are closely matched with the genioglossus muscle. Each sensor can accurately collect pressure signals related to the surrounding tissues, and the pressure signals can be reflected in the corresponding stimulation parameters in the electrode drive signal.

[0107] The pressure signal from the surrounding tissue is collected by the sensor. When the tongue moves or the pressure of the tissue around the capsule changes, the predetermined part (such as the genioglossus muscle) changes the degree of fit with the electrode. The capsule can first compensate and adapt through its own deformation. Of course, when the tongue moves with a large amplitude or the compensation effect is still insufficient, the sensor can obtain the corresponding pressure signal due to the deformation of the capsule. Therefore, the current tongue movement pattern can be identified based on the pressure signal.

[0108] The driving signal is predicted according to the tongue movement pattern, and the corresponding driving electrode is used to implement electrical stimulation. The stimulation parameters can be modulated to a relatively safe range in advance, and impedance measurements are continuously performed in the later work, and the stimulation parameters are calibrated according to the results of the impedance measurements. For example, during the implementation of electrical stimulation, a sampling signal is also obtained through the electrode to calculate the first impedance information, and the driving signal is calibrated using the first impedance information. Other detailed features of the control method can be combined with the above embodiments.

[0109] It should be understood that the various steps in the flow chart are displayed in sequence according to the indication of the arrows, but these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0110] All or part of the processes in the control method of this embodiment can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium, such as the controller installed in the above embodiments.

[0111] The tongue muscle stimulator of the present application can predict signals for tongue movement, solve the problem of hysteresis stimulation, and further ensure the reliability of the driving signal by calibrating the impedance.

[0112] The technical features of the above-mentioned embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. When the technical features in different embodiments are embodied in the same figure, it can be regarded that the figure also discloses the combination examples of the various embodiments involved.

[0113] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of patent protection of the present application shall be subject to the attached claims.

Claims

1. A tongue muscle stimulator, characterized in that: include: The electrode is placed in the oral cavity when in use to electrically stimulate the genioglossus muscle; A sensor for acquiring a pressure signal between teeth and tongue; A controller is configured with a computer program to implement the following steps: receiving the pressure signal, and identifying a current tongue movement pattern according to the pressure signal, wherein the same tongue movement pattern includes multiple movement stages, configuring corresponding pressure sampling methods for different movement stages, and acquiring the pressure signal according to the pressure sampling method; Predicting the driving signal according to the tongue movement pattern specifically includes using the pressure signal of the current movement stage to calculate the driving signal corresponding to the current movement stage, obtaining the pressure timing data of the subsequent movement stage and predicting the corresponding driving signal, and driving the electrode accordingly to implement electrical stimulation.

2. The tongue muscle stimulator according to claim 1, characterized in that When the current tongue movement pattern is identified according to the pressure signal, it specifically includes: Continuously obtaining the pressure signal to obtain pressure time series data; Through the first prior relationship, the tongue movement pattern corresponding to the pressure timing data is identified.

3. The tongue muscle stimulator according to claim 2, characterized in that The sensors are configured in pairs and correspondingly obtain two-way pressure time series data, and the tongue movement pattern recognition includes: Calculate the correlation coefficient r1 of the two-way pressure time series data; Calculate the correlation coefficient r2 between each channel of pressure time series data and the pressure time series data to be compared in the first prior relationship; The tongue movement pattern is determined based on the correlation coefficient r1 and the correlation coefficient r2.

4. The tongue muscle stimulator according to claim 2, characterized in that: The current motion stage is identified by the first prior relationship; The driving signal corresponding to the current motion stage is obtained by using the pressure signal of the current motion stage and calculating through the second priori relationship.

5. The tongue muscle stimulator according to claim 1, characterized in that: The pressure time series data of the subsequent motion stage is obtained by using the pressure signal of the current motion stage through a motion state space prediction model.

6. The tongue muscle stimulator according to claim 5, characterized in that: The driving signal is calibrated, including: Obtaining corresponding first impedance information according to the current sampling signal; comparing the first impedance information with second impedance information corresponding to the current driving signal; The motion state space prediction model is updated according to the comparison result, and the updated motion state space prediction model is used to re-predict the drive signal of the subsequent motion stage to complete the calibration.

7. The tongue muscle stimulator according to claim 6, characterized in that: Updating the motion state space prediction model includes: comparing the first impedance information and the second impedance information and obtaining a deviation value; Determining an adjustment trend of a model parameter in the motion state space prediction model according to the deviation value; An adjustment range is determined according to the adjustment trend to complete the update.

8. The tongue muscle stimulator according to claim 6, characterized in that: The sampling signal is obtained by using the electrode, and when the sampling signal is obtained, it includes: Determine the electrode sampling method according to the current tongue movement pattern; The sampling signal is obtained according to the electrode sampling method.

9. The tongue muscle stimulator according to claim 1, characterized in that: Also includes: A positioning portion, used for positioning and cooperating with corresponding tissue in the oral cavity; A working portion connected to the positioning portion, wherein the working portion is a deformable airbag, and at least a portion of the outer surface of the airbag is a bonding surface that adaptively deforms with the shape of the working portion to tend toward a predetermined position; The electrode is fixed to the combining surface, the sensor is fixed to the working part, and the controller is connected to the electrode and the sensor circuit.

Images