Systems and methods for classifying and / or characterizing user interfaces

Abstract

Systems and methods for classifying and / or characterizing a user interface are disclosed. The systems and methods include generating acoustic data associated with acoustic reflections of an acoustic signal, the acoustic reflections being indicative, at least in part, of one or more characteristics of a user interface coupled to a respiratory treatment device via a conduit. The systems and methods further include analyzing the generated acoustic data. The systems and methods further include classifying and / or characterizing the user interface based, at least in part, on the analyzed acoustic data.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit and priority of U.S. Provisional Patent Application No. 63 / 108,161, filed October 30, 2020, and U.S. Provisional Patent Application No. 63 / 036,303, filed June 8, 2020, each of which is incorporated herein by reference in its entirety. Technical Field

[0003] This invention generally relates to systems and methods for classifying and / or characterizing user interfaces, and more specifically, to systems and methods for classifying and / or characterizing user interfaces based on acoustic reflections of acoustic signals. Background Technology

[0004] Many individuals suffer from sleep-related and / or breathing disorders, such as periodic limb movement disorder (PLMD), restless legs syndrome (RLS), sleep-disordered breathing (SDB), such as obstructive sleep apnea (OSA), central sleep apnea (CSA), and other types of apnea, such as mixed apnea and hypoventilation, respiratory effort-related arousal (RERA), Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity-related hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disease (NMD), rapid eye movement (REM) behavior disorder (also known as RBD), dream setting behavior (DEB), hypertension, diabetes, stroke, insomnia, and chest wall disease. These conditions are often treated with respiratory therapy systems. Respiratory therapy systems are used to treat sleep-disordered breathing conditions. Each respiratory therapy system typically has a respiratory therapy device that is connected via a catheter to a user interface (e.g., a mask). The user wears the user interface and is supplied with a pressurized airflow from the respiratory therapy device via the catheter.

[0005] User interfaces are typically user-specific categories and types of interfaces, such as direct or indirect connections for user interface categories, and full-face masks, partial-face masks (e.g., masks that cover the mouth but not the nose, or only part of the nose), nasal masks, or nasal pillows for user interface types. Beyond specific categories and types, user interfaces are often specific models manufactured by specific companies. For various reasons, such as ensuring the user is using the correct user interface, knowing the specific category and type of user interface worn by the user, and optionally the specific model, can be beneficial for respiratory therapy systems.

[0006] Various different user interfaces can be used, such as nasal pillows, nasal mask, nasal and oral mask (e.g., full face mask or partial face mask), etc. In some implementations, different forms of air delivery conduit can be used. It is advantageous to know the user interface and conduit connected to the respiratory treatment device for providing improved control over the therapy delivered to the user. For example, it is advantageous to measure or estimate therapy parameters, such as pressure and exhaust flow in the mask. Thus, knowing what user interface is being used can enhance the therapy.

[0007] While the respiratory device can include a menu system that allows the user to input the type of user interface used, e.g., by type, model, manufacturer, etc., the user can input incorrect or incomplete information.

[0008] The present disclosure aims to address these and other issues by classifying and / or characterizing a user interface based on analyzed acoustic data generated from acoustic reflections indicative of one or more features of the user interface. SUMMARY

[0009] According to some implementations of the present disclosure, a method includes generating acoustic data associated with acoustic reflections of an acoustic signal. The acoustic reflections are at least partially indicative of one or more features of a user interface coupled to a respiratory treatment device via a conduit. The method further includes analyzing the generated acoustic data. The analyzing includes windowing the generated acoustic data based at least in part on at least one of the one or more features of the user interface. The method further includes characterizing the user interface based at least in part on the analyzed acoustic data.

[0010] According to aspects of the method, windowing the generated acoustic data includes determining a reference point in the generated acoustic data. According to aspects of the method, the reference point is a minimum point within a predetermined portion of the deconvolution of the generated acoustic data. According to aspects of the method, the reference point is a maximum point within a predetermined portion of the deconvolution of the generated acoustic data. According to aspects of the method, the reference point corresponds to a location of one or more features along a passageway formed at least partially by the conduit and the user interface. According to aspects of the method, the one or more features cause a change in acoustic impedance. According to aspects of the method, the change in acoustic impedance is based at least in part on a narrowing of the passageway at (i) the user interface, (ii) a junction of the conduit and the user interface, or (iii) a combination thereof. According to aspects of the method, the change in acoustic impedance is based at least in part on a widening of the passageway at (i) the user interface, (ii) a junction of the conduit and the user interface, or (iii) a combination thereof. According to aspects of the method, windowing includes a first windowing of the generated acoustic data and a second windowing of the generated acoustic data. According to aspects of the method, the first windowing and the second windowing differ by a selected amount of the generated acoustic data, the selection of the amount of the generated acoustic data being before a reference point in the generated acoustic data, after a reference point in the generated acoustic data, or a combination thereof. The amount of the generated data can be a predetermined number of data points / samples, a predetermined distance, a predetermined frequency, etc. According to aspects of the method, the analysis of the generated acoustic data includes calculating a deconvolution of the generated acoustic data prior to windowing the generated acoustic data. According to aspects of the method, the deconvolution of the generated acoustic data includes calculating a cepstrum of the generated acoustic data. According to aspects of the method, the cepstrum identifies a distance associated with an acoustic reflection that is indicative of a location of one or more features of the user interface along an acoustic path of the acoustic signal and relative to a location of the acoustic sensor. The cepstrum can identify one or more distances associated with each of a corresponding one or more acoustic reflections, thereby being indicative of a location of each of one or more physical features along the acoustic path of the acoustic signal. According to aspects of the method, the analysis of the generated acoustic data includes calculating a derivative of the cepstrum to determine a rate of change of the cepstrum signal. According to aspects of the method, the analysis of the generated acoustic data includes normalizing the generated acoustic data. According to aspects of the method, the normalizing of the generated acoustic data includes subtracting a mean value from the generated acoustic data, dividing by a standard deviation of the generated acoustic data, or a combination thereof. According to aspects of the method, the normalizing of the generated acoustic data addresses a confounding condition. According to aspects of the method, the confounding condition is due to a microphone gain, a breath amplitude, a therapy pressure, or a combination thereof.According to some aspects of the method, the characterizing of the user interface includes inputting the analyzed acoustic data into a machine learning model. In one or more implementations, the machine learning model can be supervised or unsupervised. In one or more implementations, the machine learning model can be a neural network. In one or more implementations, the neural network can be a deep neural network or a shallow neural network. In one or more implementations, the deep neural network can be a convolutional neural network. A machine learning model such as a deep neural network or a convolutional neural network can determine a form factor of the user interface, a model of the user interface, a dimension of one or more elements of the user interface, or a combination thereof. According to some aspects of the method, the deep neural network includes one or more convolutional layers and one or more max-pooling layers. According to some aspects of the method, the convolutional neural network includes N features with a max-pooling of M samples of the N features, and a ratio of N to M is 1 : 1 to 4: 1. According to some aspects of the method, the method further includes emitting the acoustic signal into the conduit connected to the user interface via an audio transducer. According to some aspects of the method, the method further includes emitting the acoustic signal into the conduit via a motor of the respiratory treatment device connected to the conduit. According to some aspects of the method, the acoustic signal is a human audible sound. According to some aspects of the method, the acoustic signal is a human inaudible sound. According to some aspects of the method, the sound is inaudible based on a frequency of the sound, an amplitude of the sound, or a combination thereof. According to some aspects of the method, the acoustic signal is ultrasound. According to some aspects of the method, during the generation of the acoustic data, the user interface is not connected to a user. In such an arrangement, certain confounding factors such as the user’s breathing or undesired noise emitted from the respiratory treatment device can be avoided. According to some aspects of the method, during the generation of the acoustic data, the user interface is connected to a user. According to some aspects of the method, the method further includes providing a flow of pressurized air through the conduit and into the user interface during the generation of the acoustic data. According to some aspects of the method, the method further includes emitting the acoustic signal in the conduit during a period in which there is no flow of pressurized air through the conduit and into the user interface. According to some aspects of the method, the generated acoustic data is generated from a plurality of acoustic reflections from a plurality of acoustic signals. According to some aspects of the method, the generated acoustic data is an average of the plurality of acoustic reflections from the plurality of acoustic signals. Such an averaging can improve a signal-to-noise ratio of the generated acoustic data by suppressing undesired time-varying components or artifacts in the acoustic data.

[0011] According to some implementations, a system is disclosed that includes a control system having one or more processors and a memory having machine-readable instructions stored thereon. The control system is coupled to the memory, and when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system, any of the above aspects are implemented.

[0012] According to some implementations, a system for characterizing a user interface is disclosed that includes a control system having one or more processors configured to implement a method of any of the above aspects.

[0013] According to some implementations, a computer program product including instructions that, when executed by a computer, cause the computer to perform a method of any of the above aspects is disclosed. According to some aspects, the computer program product is a non-transitory computer-readable medium.

[0014] According to some implementations of the present disclosure, a method includes generating acoustic data associated with an acoustic reflection of an acoustic signal. The acoustic reflection is at least partially indicative of one or more features of a user interface coupled to a respiratory treatment device via a conduit. The method further includes analyzing the generated acoustic data to identify one or more feature signatures related to the one or more features of the user interface. Generally, a feature signature can be comprised of one or more acoustic features within the acoustic data. The method further includes classifying the user interface based at least in part on the one or more feature signatures.

[0015] According to some aspects of the method, the user interface category is associated with a direct connection between the conduit and a cushion and / or frame of the user interface. According to some aspects of the method, the one or more features and the one or more feature markers indicate a direct connection between the conduit and the cushion and / or frame. According to some aspects of the method, the user interface category is associated with an indirect connection between the conduit and a cushion and / or frame of the user interface. According to some aspects of the method, the one or more features and the one or more feature markers indicate an indirect connection between the conduit and the cushion and / or frame. According to some aspects of the method, the indirect connection is characterized by another conduit positioned between the conduit and the cushion and / or frame and configured to provide a fluid connection. According to some aspects of the method, the other conduit is a headgear conduit, and the headgear conduit forms part of a headgear arrangement for holding the user interface on the user’s face. The headgear conduit is configured to deliver pressurized air from the conduit to the cushion and / or frame. According to some aspects of the method, the other conduit is a user interface conduit that is (i) more flexible than the conduit, (ii) has a smaller diameter than the conduit, or (i) and (ii). The user interface conduit can also have a shorter length than the conduit. The user interface conduit is configured to deliver pressurized air from the conduit to the cushion and / or frame. According to some aspects of the method, analyzing the generated acoustic data includes computing a frequency spectrum of the generated acoustic data. According to some aspects of the method, analyzing the generated acoustic data includes computing a log of the frequency spectrum. Alternatively, a non-linear operation can be used instead of a log computation. According to some aspects of the method, analyzing the generated acoustic data includes computing a cepstrum of the log spectrum. According to some aspects of the method, analyzing the generated acoustic data includes: selecting a log spectral segment of the generated acoustic data; computing a Fourier transform of the log spectral segment; and associating the one or more features of the user interface with the one or more feature markers within the Fourier transform of the segment. According to some aspects of the method, the one or more features include a maximum amplitude of the cepstrum, a minimum amplitude of the cepstrum, a standard deviation of the cepstrum, a skew of the cepstrum, a kurtosis of the cepstrum, a median of absolute values of the cepstrum, a sum of absolute values of the cepstrum, a sum of positive areas of the cepstrum, a sum of negative areas of the cepstrum, a fundamental frequency, an energy corresponding to the fundamental frequency, an average energy, at least one resonant frequency of a combination of the conduit and the user interface, a variation of the at least one resonant frequency, a number of peaks within a range, a prominent peak, a peak-to-peak distance, or a combination or variation thereof. According to some aspects of the method, the generated acoustic data includes a first reflection within an acoustic reflection of the acoustic signal. According to some aspects of the method, the generated acoustic data includes a second reflection within an acoustic reflection of the acoustic signal. According to some aspects of the method, the generated acoustic data includes a third reflection within an acoustic reflection of the acoustic signal.According to some aspects of the method, the generated acoustic data includes a primary reflection and a secondary reflection within the acoustic reflections of the acoustic signals. According to some aspects of the method, the user interface class associated with a direct connection between the conduit and the cushion and / or frame is classified based on one or more feature signatures having a maximum magnitude of cepstrum greater than a threshold. According to some aspects of the method, the user interface class associated with an indirect connection between the conduit and the cushion and / or frame via a user interface conduit is classified based on one or more feature signatures satisfying a threshold number of peaks. According to some aspects of the method, the user interface class associated with an indirect connection between the conduit and the cushion and / or frame via a user interface conduit is classified based on one or more feature signatures having a maximum amplitude of cepstrum less than a threshold. According to some aspects of the method, the user interface class associated with an indirect connection between the conduit and the cushion and / or frame via a headgear conduit is classified based on one or more feature signatures having an average cepstral value below a threshold. According to some aspects of the method, classifying the user interface based at least in part on the one or more feature signatures includes comparing the one or more feature signatures to one or more known feature signatures of one or more user interfaces of known classes.

[0016] According to some implementations, a system is disclosed that includes a memory storing machine-readable instructions and a control system including one or more processors configured to execute the machine-readable instructions to perform any one or more of the above-described methods and / or implementations of methods.

[0017] The foregoing summary is not intended to represent every implementation of the present application or every aspect thereof. Rather, the foregoing summary merely provides an example of some of the novel aspects and features that are described in more detail below. The above-described features and advantages, as well as other features and advantages of the present application, will become apparent to one of ordinary skill in the art in view of the following detailed description, when considered in conjunction with the appended claims, with reference to the various embodiments described herein and illustrated in the following figures. Other aspects of the present application will become apparent to one of ordinary skill in the art from the detailed description, which follows, when considered in conjunction with the figures and the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0018] The present application, its advantages and features will be better understood from the following description of exemplary embodiments, when considered in connection with the accompanying drawings. These drawings are merely schematic and are not intended to represent the various embodiments to scale. Furthermore, the present application can take many different forms other than the specific embodiments described and illustrated herein.

[0019] Figure 1 is a functional block diagram of a system for classifying and / or characterizing a user interface according to some implementations of the present application.

[0020] Figure 2is a perspective view of at least a portion of a system in accordance with some embodiments of the present application Figure 1 is a perspective view of at least a portion of a system in accordance with some embodiments of the present application

[0021] Figure 3 shows an exemplary timeline of a sleep session in accordance with some implementations of the present application

[0022] Figure 4 is a perspective view of a user interface in accordance with some embodiments of the present application associated with a sleep session of Figure 3 is an exemplary hypnogram associated with a sleep session of

[0023] Figure 5 shows generation of acoustic data in response to acoustic reflections indicative of one or more features of a user interface in accordance with some implementations of the present application

[0024] Figure 6 is a flowchart of a method for characterizing a user interface in accordance with some implementations of the present application

[0025] Figure 7 is a plot of a computed cepstrum of generated acoustic data in accordance with some implementations of the present application

[0026] Figure 8 is a plot of a windowed cepstrum of generated acoustic data in accordance with some implementations of the present application

[0027] Figure 9 is a plot of an aligned windowed cepstrum of generated acoustic data in accordance with some implementations of the present application

[0028] Figure 10 is a plot of a normalized windowed cepstrum of generated acoustic data in accordance with some implementations of the present application

[0029] Figure 11A is a perspective view of a class of user interfaces in accordance with some implementations of the present application

[0030] Figure 11B is a perspective view of a user interface in accordance with some embodiments of the present application Figure 11A is an exploded view of a user interface in accordance with some embodiments of the present application

[0031] Figure 12A is a perspective view of another class of user interfaces in accordance with some implementations of the present application

[0032] Figure 12B is an exploded view of a user interface in accordance with some embodiments of the present application Figure 12A is an exploded view of a user interface in accordance with some embodiments of the present application

[0033] Figure 13A is a perspective view of another class of user interfaces in accordance with some implementations of the present application

[0034] Figure 13B This is according to some implementations of the present invention. Figure 13A A breakdown diagram of the user interface.

[0035] Figure 14A This is a flowchart of a method for classifying user interfaces according to some implementations of the present invention.

[0036] Figure 14B This is a flowchart of a method for analyzing generated acoustic data according to some implementations of the present invention.

[0037] Figure 15 This is a cepstrum curve calculated from the user interface of some implementations of the present invention.

[0038] Figure 16 This is a graph of the additional cepstrum calculation of the user interface according to some implementations of the present invention.

[0039] Figure 17 This is a graph of the additional cepstrum calculation of the user interface according to some implementations of the present invention.

[0040] Figure 18 This is a graph of the additional cepstrum calculation of the user interface according to some implementations of the present invention.

[0041] Figure 19 This is a graph of the additional cepstrum calculation of the user interface according to some implementations of the present invention.

[0042] Figure 20 This is a graph of the additional cepstrum calculation of the user interface according to some implementations of the present invention.

[0043] Figure 21 This is a graph showing the calculated cepstrum curves of the first and second reflections within the cepstrum according to some implementations of the present invention.

[0044] Figure 22 It is a graph of the logarithmic spectrum of acoustic data generated according to some implementations of the present invention.

[0045] Figure 23 This is according to some implementations of the present invention. Figure 22 The graph shows the transformation curve of the logarithmic spectrum.

[0046] Figure 24A A graph of the frequency domain intensity signal based on the generated acoustic data is shown according to some implementations of the present invention.

[0047] Figure 24B The following are some implementations based on the present invention. Figure 24AThe curve of the frequency domain intensity signal and the wave period intensity signal.

[0048] Figure 25A A first cepstral plot calculated from acoustic data generated using a first conduit, and a second cepstral plot calculated from acoustic data generated using a second conduit, are shown according to some implementations of the present invention.

[0049] Figure 25B The following are some implementations based on the present invention. Figure 25A The first curve of the corrected cepstrum of the first cepstrum, and based on Figure 25A The second cepstrum is the corrected second cepstrum curve.

[0050] While the invention allows for various modifications and substitutions, specific implementations are illustrated by way of example in the accompanying drawings and will be described in more detail thereon. However, it should be understood that the invention is not limited to the specific forms disclosed. Rather, the invention is intended to cover all modifications, equivalents, and substitutions falling within the spirit and scope of the invention as defined by the appended claims. Detailed Implementation

[0051] Various embodiments are described with reference to the accompanying drawings, in which the same reference numerals are used throughout the drawings to denote similar or equivalent elements. The drawings are not drawn to scale and are provided merely for illustrative purposes. Several aspects of the invention are described below with reference to exemplary applications used for illustration. It should be understood that numerous specific details, relationships, and methods are set forth to provide a comprehensive understanding of the invention. However, those skilled in the art will readily recognize that the invention can be practiced without one or more of these specific details or using other methods. In other instances, well-known structures or operations have not been shown in detail to avoid obscuring the invention. The various embodiments are not limited to the order of the described actions or events, as some actions may occur in a different order and / or simultaneously with other actions or events. Furthermore, not all of the shown actions or events are required to implement the method according to the invention.

[0052] For example, elements and limitations disclosed in the abstract, summary, and detailed description but not expressly set forth in the claims should not be incorporated into the claims individually or jointly by means of implication, inference, or otherwise. For the purposes of this detailed description, unless otherwise stated, the singular includes the plural, and vice versa. The word “comprising” means “including but not limited to”. Furthermore, for example, approximate words such as “about,” “almost,” “substantially,” “approximately,” “roughly,” etc., may be used herein to mean “within,” “close to,” or “nearly within,” or “within 3-5% of,” or “within acceptable manufacturing tolerances,” or any logical combination thereof.

[0053] Many individuals suffer from sleep-related and / or breathing-related disorders, such as periodic limb movement disorder (PLMD), restless legs syndrome (RLS), sleep-disordered breathing (SDB), such as obstructive sleep apnea (OSA), central sleep apnea (CSA), and other types of apnea, such as mixed apnea and hypoventilation, respiratory effort-related arousal (RERA), Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity-related hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disease (NMD), rapid eye movement (REM) behavior disorder (also known as RBD), dream setting behavior (DEB), hypertension, diabetes, stroke, insomnia, and chest wall disease.

[0054] Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB) characterized by events during sleep that result in closure or obstruction of the upper airway caused by a combination of abnormally small upper airway and loss of normal muscle tone in the areas of the tongue, soft palate and posterior oropharyngeal wall.

[0055] Central sleep apnea (CSA) is another form of sleep apnea-drowsiness (SDB) that occurs when the brain temporarily stops sending signals to the muscles that control breathing. More generally, apnea generally refers to the cessation of breathing caused by air blockage (or cessation of breathing function). Typically, during an obstructive sleep apnea event, an individual will stop breathing for about 15 to 30 seconds. Mixed sleep apnea is another form of SDB, which is a combination of obstructive sleep apnea (OSA) and CSA.

[0056] Other types of apnea include hypoventilation, hyperventilation, and hypercapnia. Hypoventilation is typically characterized by slow or shallow breathing caused by a narrowed airway, rather than airway obstruction. Hyperventilation is typically characterized by increased respiratory depth and / or rate. Hypercapnia is typically characterized by an excess of carbon dioxide in the bloodstream and is usually caused by hypoventilation.

[0057] A respiratory effort-related arousal (RERA) event is typically characterized by an increased respiratory effort lasting 10 seconds or longer, resulting in arousal from sleep, and does not meet the criteria for apnea or hypopnea events. In 1999, the AASM task force defined RERA as "a respiratory sequence characterized by increased respiratory effort leading to awakening from sleep but not meeting the criteria for apnea or hypoventilation. These events must meet the following two criteria: 1. a gradually increasing pattern of negative esophageal pressure, culminating in a sudden change in pressure to an even lower negative level and termination of awakening; 2. the event lasting 10 seconds or longer." In 2000, a study conducted at the NYU School of Medicine and published in Sleep, vol. 23, No. 6, pp. 763-771, entitled "Non-invasive detection of respiratory effort-related awakening (RERA) via a nasal cannula / pressure sensor system," demonstrated that the nasal cannula / pressure sensor system is sufficient and reliable for RERA detection. RERA detectors can be based on actual flow signals derived from respiratory therapy (e.g., PAP) devices. For example, a flow restriction measure can be determined based on the flow signal. An awakening measure can then be derived from the flow restriction measure and the measure of the sudden increase in ventilation. (WO 2008 / 138040, US 9,358,353, US...) Such a method is described in 10,549,053 and US 2020 / 0197640, each of which is incorporated herein by reference in its entirety.

[0058] Cheyne-Stokes respiration (CSR) is another form of spontaneous breathing deficit (SDB). CSR is a dysregulation of the patient's respiratory controller, characterized by rhythmic alternations of waxing and waning ventilation known as the CSR cycle. CSR is characterized by repetitive hypoxia and reoxygenation of arterial blood.

[0059] Obesity hyperventilation syndrome (OHS) is defined as a combination of severe obesity and chronic hypercapnia at wakefulness, without other known causes of hypoventilation. Symptoms include dyspnea, morning headache, and excessive daytime sleepiness.

[0060] Chronic obstructive pulmonary disease (COPD) includes any of the lower airway diseases that share certain common characteristics, such as increased resistance to air movement, prolonged expiratory phase of breathing, and loss of normal lung elasticity.

[0061] Neuromuscular diseases (NMD) encompass a wide range of conditions and ailments that impair muscle function directly through intrinsic muscular pathology or indirectly through neuropathology. The chest wall is a group of thoracic deformities that result in inefficient connection between the respiratory muscles and the thoracic cavity.

[0062] These and other conditions are characterized by specific events that occur when an individual is sleeping (such as snoring, sleep apnea, insufficiency of breathing, restless legs, sleep disturbances, suffocation, increased heart rate, difficulty breathing, asthma attacks, seizures, epilepsy, or any combination thereof).

[0063] The Apnea-Hypopnea Index (AHI) is an index used to indicate the severity of sleep apnea during sleep. An AHI is calculated by dividing the number of apnea and / or hypopnea events experienced by the user during a sleep period by the total number of hours of sleep in that period. An event can be, for example, an apnea lasting at least 10 seconds. An AHI less than 5 is considered normal. An AHI greater than or equal to 5 but less than 15 is considered an indicator of mild sleep apnea. An AHI greater than or equal to 15 but less than 30 is considered an indicator of moderate sleep apnea. An AHI greater than or equal to 30 is considered an indicator of severe sleep apnea. In children, an AHI greater than 1 is considered abnormal. When the AHI is normal, or when the AHI is normal or mild, sleep apnea can be considered “controlled.” The AHI can also be used in conjunction with oxygen desaturation levels to indicate the severity of obstructive sleep apnea.

[0064] Generally, this invention describes a system and method in which acoustic reflection is used to analyze a user interface connected to a respiratory therapy device via a catheter to classify and / or characterize the user interface. Classifying the user interface determines its category, such as direct or indirect. As described in more detail below, an indirect user interface can also be an indirect catheter or indirect frame user interface. Characterizing the user interface determines its specific type, including, for example, the manufacturer and specific model. In one or more implementations, the user interface can be characterized by classification according to the disclosed method. Alternatively, in one or more implementations, the user interface can be characterized according to the disclosed method without direct classification. In this case, the user interface is indirectly classified only by a representation that implicitly identifies the category. Alternatively, in one or more implementations, the user interface can be classified (directly) and characterized by the disclosed method. In one or more implementations, classifying the user interface can, for example, verify the representation of the user interface or create a subset of the user interface from which the user interface is characterized.

[0065] Reference Figure 1 This describes a system 100 according to some implementations of the present invention. System 100 can be used to identify a user interface used by a user and for other purposes. System 100 includes a control system 110, a memory device 114, an electronic interface 119, one or more sensors 130, and optionally one or more user devices 170. In some embodiments, system 100 further includes a respiratory therapy system 120, which includes a respiratory therapy device 122. System 100 can be used to detect and / or identify a user interface 124, as further detailed herein.

[0066] Control system 110 includes one or more processors 112 (hereinafter, processor 112). Control system 110 is typically used to control various components of system 100 and / or analyze data acquired and / or generated by the components of system 100. Processor 112 may be a general-purpose or special-purpose processor or a microprocessor. Although in Figure 1 A processor 112 is shown, but the control system 110 may include any suitable number of processors (e.g., one processor, two processors, five processors, ten processors, etc.), which may be located in a single housing or positioned remotely from each other. The control system 110 (or any other control system) or a portion thereof, such as processor 112 (or any other processor or part of any other control system), may be used to perform one or more steps of any of the methods described herein and / or claimed. The control system 110 may be coupled to and / or located within, for example, the housing of user device 170, and / or the housing of one or more sensors 130. The control system 110 may be centralized (within one such housing) or distributed (within two or more physically different such housings). In embodiments including two or more housings containing the control system 110, such housings may be positioned close to and / or far from each other.

[0067] Memory device 114 stores machine-readable instructions executable by processor 112 of control system 110. Memory device 114 can be any suitable computer-readable storage device or medium, such as random or serial access storage devices, hard disk drives, solid-state drives, flash memory devices, etc. Although Figure 1 A memory device 114 is shown, but system 100 may include any suitable number of memory devices 114 (e.g., one memory device, two memory devices, five memory devices, ten memory devices, etc.). The memory device 114 may be coupled to and / or located within the housing of the respiratory therapy device 122 of the respiratory therapy system 120, within the housing of the user device 170, within the housing of one or more sensors 130, or any combination thereof. Similar to control system 110, the memory device 114 may be centralized (within one such housing) or distributed (within two or more physically different such housings).

[0068] In some implementations, memory device 114 stores a user profile associated with the user. The user profile may include, for example, user-associated demographic information, user-associated biostatistical information, user-associated medical information, self-reported user feedback, user-associated sleep parameters (e.g., sleep-related parameters recorded from one or more earlier sleep periods), or any combination thereof. Demographic information may include, for example, information indicating the user's age, gender, ethnicity, family medical history (e.g., family history of insomnia or sleep apnea), employment status, education status, socioeconomic status, or any combination thereof. Medical information may include, for example, information indicating one or more medical conditions associated with the user, the user's medication use, or both. Medical information data may further include user-associated fall risk assessments (e.g., a fall risk score using the Morse Fall Scale), multiple sleep latency test (MSLT) results or scores, and / or Pittsburgh Sleep Quality Index (PSQI) scores or values. Self-reported user feedback may include self-reported subjective sleep ratings (e.g., poor, average, excellent), self-reported subjective stress levels, self-reported subjective fatigue levels, self-reported subjective health status, information about recent life events experienced by the user, or any combination thereof.

[0069] Electronic interface 119 is configured to receive data (e.g., physiological data and / or acoustic data) from one or more sensors 130, such that the data can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. Electronic interface 119 can communicate with one or more sensors 130 using wired or wireless connections (e.g., using RF communication protocols, WiFi communication protocols, Bluetooth communication protocols, IR communication protocols, via cellular networks, via any other optical communication protocols, etc.). Electronic interface 119 may include an antenna, a receiver (e.g., an RF receiver), a transmitter (e.g., an RF transmitter), a transceiver, or any combination thereof. Electronic interface 119 may also include one or more processors and / or one or more memory devices that are the same as or similar to processor 112 and memory device 114 described herein. In some implementations, electronic interface 119 is coupled to or integrated into user device 170. In other implementations, electronic interface 119 is coupled to or integrated with control system 110 and / or memory device 114 (e.g., within a housing).

[0070] As described above, in some embodiments, system 100 may optionally include a therapeutic respiratory therapy system 120 (also known as a respiratory pressure therapy system). The respiratory therapy system 120 may include a respiratory therapy device 122 (also known as a respiratory pressure device), a user interface 124 (also known as a mask or patient interface), a catheter 126 (also known as a tube or air circuit), a display device 128, a humidifier canister 129, or any combination thereof. In some implementations, a control system 110, a memory device 114, a display device 128, one or more sensors 130, and a humidifier canister 129 are part of the respiratory therapy device 122. Respiratory pressure therapy refers to supplying air to the user's airway inlet at a controlled target pressure that is nominally positive relative to atmosphere throughout the user's respiratory cycle (e.g., opposite to the negative pressure therapy of a canister ventilator or tubing ventilator). The respiratory therapy system 120 is typically used to treat individuals who have one or more sleep-related breathing disorders (e.g., obstructive sleep apnea, central sleep apnea, or mixed sleep apnea), other breathing disorders such as COPD, or other disorders that result in respiratory insufficiency that may be present during sleep or wakefulness.

[0071] The respiratory therapy device 122 is typically used to generate pressurized air to be delivered to a user (e.g., using one or more motors driving one or more compressors). In some implementations, the respiratory therapy device 122 generates a continuous, constant air pressure that is delivered to the user. In other implementations, the respiratory therapy device 122 generates two or more predetermined pressures (e.g., a first predetermined air pressure and a second predetermined air pressure). In still other implementations, the respiratory therapy device 122 is configured to generate a variety of different air pressures within a predetermined range. For example, the respiratory therapy device 122 may deliver at least about 6 cm H2O, at least about 10 cm H2O, at least about 20 cm H2O, between about 6 cm H2O and about 10 cm H2O, between about 7 cm H2O and about 12 cm H2O, etc. The respiratory therapy device 122 may also deliver pressurized air at predetermined flow rates, for example, between about -20 L / min and about 150 L / min, while maintaining positive pressure (relative to ambient pressure). In some implementations, the control system 110, memory device 114, electronic interface 119, or any combination thereof may be coupled to the housing of the respiratory therapy device 122 and / or located within the housing of the respiratory device.

[0072] User interface 124 engages with a portion of the user's face and delivers pressurized air from respiratory therapy device 122 to the user's airway to help prevent airway narrowing and / or collapse during sleep. This can also increase the user's oxygen intake during sleep. Depending on the treatment to be applied, user interface 124 may form a seal with, for example, an area or portion of the user's face, thereby facilitating the delivery of gas at a pressure sufficiently different from ambient pressure (e.g., a positive pressure of approximately 10 cm H2O relative to ambient pressure) to achieve the treatment. For other forms of treatment, such as oxygen delivery, the user interface may not include a seal sufficient to deliver gas at a positive pressure of approximately 10 cm H2O to the airway.

[0073] In some implementations, user interface 124 is or includes a mask that covers the user's nose and mouth (e.g., as shown in the image). Figure 2 (As shown). Alternatively, user interface 124 may be or include a nasal mask that supplies air to the user's nose or a nasal pillow that supplies air directly to the user's nostrils. User interface 124 may include a strap assembly having multiple straps (e.g., including hook and loop fasteners) on a portion of user interface 124 (e.g., face) for positioning and / or stabilizing user interface 124 in a desired position for the user, and a conformal cushioning pad (e.g., silicone, plastic, foam, etc.) to facilitate an airtight seal between user interface 124 and the user. In some implementations, user interface 124 may include connector 127 and one or more vents 125. One or more vents 125 may be used to allow the user's exhaled carbon dioxide and other gases to escape. In other implementations, user interface 124 includes a mouthpiece (e.g., a night-protective mouthpiece molded to conform to the user's teeth, a jaw repositioning device, etc.). In some implementations, connector 127 is different from user interface 124 (and / or conduit 126) but may be connected to user interface (and / or conduit). Connector 127 is configured to connect user interface 124 and fluidly connect it to conduit 126.

[0074] The conduit 126 allows air to flow between two components of the respiratory therapy system 120, such as the respiratory therapy device 122 and the user interface 124. In some implementations, there may be separate branches for inspiratory and expiratory conduits. In other implementations, a single branch air conduit is used for both inspiratory and expiratory functions. Typically, the respiratory therapy system 120 forms an air passage extending between the motor of the respiratory therapy device 122 and the user and / or the user's airway. Therefore, the air passage typically includes at least the motor of the respiratory therapy device 122, the user interface 124, and the conduit 126.

[0075] One or more of the respiratory therapy device 122, user interface 124, conduit 126, display device 128, and humidifier 129 may include one or more sensors (e.g., pressure sensor, flow sensor, or any other sensor 130 described more generally herein). These one or more sensors may be used, for example, to measure the air pressure and / or flow rate of the pressurized air supplied by the respiratory therapy device 122.

[0076] Display device 128 is typically used to display images including still images, video images, or both, and / or information about the respiratory therapy device 122. For example, display device 128 may provide information about the status of the respiratory therapy device 122 (e.g., whether the respiratory therapy device 122 is on / off, the pressure of the air delivered by the respiratory therapy device 122, the temperature of the air delivered by the respiratory therapy device 122, etc.) and / or other information (e.g., sleep scores or treatment scores such as myAir). TM Scores, such as those described in WO 2016 / 061629 and US 2017 / 0311879, each of which is incorporated herein by reference in its entirety, current date / time, user's personal information, user surveys, etc. In some implementations, the display device 128 acts as a human-machine interface (HMI) including a graphical user interface (GUI) configured to display images as input. The display device 128 may be an LED display, an OLED display, an LCD display, etc. The input interface may be, for example, a touchscreen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with the respiratory therapy device 122.

[0077] The humidifier canister 129 is connected to or integrated into the respiratory therapy device 122 and includes a water reservoir for humidifying pressurized air delivered from the respiratory therapy device 122. The respiratory therapy device 122 may include a heater to heat the water in the humidifier canister 129 to humidify the pressurized air supplied to the user. Additionally, in some implementations, the conduit 126 may include a heating element (e.g., coupled to and / or embedded in the conduit 126) that heats the pressurized air delivered to the user. The humidifier canister 129 may be fluidly coupled to a water vapor inlet of an air passage and deliver water vapor into the air passage via the water vapor inlet, or it may be formed in a straight line with the air passage as part of the air passage itself. In other implementations, the respiratory therapy device 122 or the conduit 126 may include a waterless humidifier. The waterless humidifier may include a sensor that interfaces with other sensors located elsewhere in the system 100.

[0078] The respiratory therapy system 120 can be used as, for example, a ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an automated positive airway pressure (APAP) system, a bilevel or variable positive airway pressure (BPAP or VPAP) system, or any combination thereof. A CPAP system delivers a predetermined pressure (e.g., determined by a sleep physician) to the user. An APAP system automatically changes the pressure delivered to the user based at least in part on, for example, breathing data associated with the user. A BPAP or VPAP system is configured to deliver a first predetermined pressure (e.g., inspiratory positive airway pressure or IPAP) and a second predetermined pressure lower than the first predetermined pressure (e.g., expiratory positive airway pressure or EPAP).

[0079] Reference Figure 2 The system 100 is shown according to some implementation methods. Figure 1 As part of the respiratory therapy system 120, the user 210 and bed partner 220 are located in bed 230 and lie on mattress 232. A user interface 124 (e.g., a full-face mask) can be worn by the user 210 during sleep. The user interface 124 is fluidly coupled and / or connected to the respiratory therapy device 122 via conduit 126. The respiratory therapy device 122, in turn, delivers pressurized air to the user 210 via conduit 126 and user interface 124 to increase air pressure in the user 210's throat, thereby helping to prevent airway closure and / or narrowing during sleep. The respiratory therapy device 122 may include a display device 128 that allows the user to interact with the respiratory therapy device 122. The respiratory therapy device 122 may also include a humidifier tank 129 for storing water for humidifying the pressurized air. The respiratory therapy device 122 may be positioned such as Figure 2 The device is located on a bedside table 240 directly adjacent to the bed 230, or more generally, on any surface or structure typically adjacent to the bed 230 and / or the user 210. The user may also wear a blood pressure monitor 180 and an activity tracker 190 while lying on the mattress 232 within the bed 230.

[0080] See again Figure 1The system 100 includes one or more sensors 130, such as a pressure sensor 132, a flow sensor 134, a temperature sensor 136, a motion sensor 138, a microphone 140, a speaker 142, a radio frequency (RF) receiver 146, a radio frequency (RF) transmitter 148, a camera 150, an infrared (IR) sensor 152, a photoplethysmography (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an EEG sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyography (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a humidity sensor 176, a lidar (LiDAR) sensor 178, or any combination thereof. Typically, each of the one or more sensors 130 is configured to output sensor data that is received and stored in a memory device 114 or one or more other memory devices. Sensor 130 may also include an electrooculogram (EOG) sensor, a peripheral oxygen saturation (SpO2) sensor, a skin conductance response (GSR) sensor, a carbon dioxide (CO2) sensor, or any combination thereof.

[0081] Although one or more sensors 130 are shown and described as including each of the following: pressure sensor 132, flow sensor 134, temperature sensor 136, motion sensor 138, microphone 140, speaker 142, RF receiver 146, RF transmitter 148, camera 150, IR sensor 152, PPG sensor 154, ECG sensor 156, EEG sensor 158, capacitance sensor 160, force sensor 162, strain gauge sensor 164, EMG sensor 166, oxygen sensor 168, analyte sensor 174, humidity sensor 176, and LiDAR sensor 178, more generally, one or more sensors 130 may include any combination and any number of each of the sensors described and / or shown herein.

[0082] One or more sensors 130 can be used to generate, for example, physiological data, acoustic data, or both, which are communicated with the user of the respiratory therapy system 120 (such as...). Figure 2The user 210, the respiratory therapy system 120, both the user and the respiratory therapy system 120, or other entities, objects, or activities are associated with the user. The control system 110 may use physiological data generated by one or more sensors 130 to determine sleep-wake signals and one or more sleep-related parameters associated with the user during sleep periods. Sleep-wake signals may indicate one or more sleep stages (sometimes referred to as sleep states), including sleep, wakefulness, relaxation wakefulness, micro-wakefulness, or different sleep stages such as rapid eye movement (REM) stages (which may include typical REM stages and atypical REM stages), a first non-REM stage (commonly referred to as "N1"), a second non-rapid eye movement stage (commonly referred to as "N2"), a third non-rapid eye movement stage (commonly referred to as "N3"), or any combination thereof. Methods for determining sleep stages based on physiological data generated by one or more sensors (e.g., sensor 130) are described in, for example, WO 2014 / 047310, US 10,492,720, US10,660,563, US 2020 / 0337634, WO 2017 / 132726, WO 2019 / 122413, US 2021 / 0150873, WO2019 / 122414, and US 2020 / 0383580, each of which is incorporated herein by reference in its entirety.

[0083] Sleep-wake signals can also be timestamped to indicate the time a user enters bed, the time a user leaves bed, the time a user attempts to fall asleep, etc. Sleep-wake signals from one or more sensors 130 can be measured during a sleep period at a predetermined sampling rate (e.g., one sample per second, one sample every 30 seconds, one sample per minute, etc.). Examples of one or more sleep-related parameters that can be determined for a user, at least in part, based on sleep-wake signals during a sleep period include total time in bed, total sleep time, total wake time, sleep onset wait time, wake-up parameters after sleep, sleep efficiency, segmentation index, amount of time to fall asleep, consistency of respiratory rate, time to fall asleep, wake time, rate of sleep disturbance, number of movements, or any combination thereof.

[0084] Physiological and / or acoustic data generated by one or more sensors 130 can also be used to determine respiratory signals associated with the user during sleep periods. Respiratory signals typically represent the user's breathing during sleep periods. Respiratory signals can indicate, for example, respiratory rate, respiratory rate variability, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory amplitude ratio, inspiratory-expiratory duration ratio, number of events per hour, event pattern, pressure setting of the respiratory therapy device 122, or any combination thereof. Events may include snoring, sleep apnea, central sleep apnea, obstructive sleep apnea, mixed sleep apnea, hypopnea, RERA, flow restriction (e.g., an event where increased intrathoracic pressure indicates increased effort but results in no increase in flow), mask leakage (e.g., from user interface 124), restless legs, sleep disturbance, apnea, increased heart rate, heart rate variability, dyspnea, asthma attack, seizure, epilepsy, fever, cough, sneezing, snoring, wheezing, presence of illness such as the common cold or influenza, increased stress level, etc. The event can be detected by any method known in the art, such as those described in, for example, US5,245,995, US 6,502,572, WO 2018 / 050913, WO 2020 / 104465, each of which is incorporated herein by reference in its entirety.

[0085] Pressure sensor 132 outputs pressure data that can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. In some implementations, pressure sensor 132 is an air pressure sensor (e.g., an atmospheric pressure sensor) that generates sensor data indicating the breathing (e.g., inhalation and / or exhalation) and / or ambient pressure of the user of respiratory therapy system 120. In such implementations, pressure sensor 132 can be coupled to or integrated into respiratory therapy device 122. Pressure sensor 132 can be, for example, a capacitive sensor, an electromagnetic sensor, an inductive sensor, a piezoelectric sensor, a resistive sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof. In one example, pressure sensor 132 can be used to determine the user's blood pressure.

[0086] The flow sensor 134 outputs flow data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the flow sensor 134 is used to determine the airflow rate from the respiratory therapy device 122, the airflow rate through the conduit 126, the airflow rate through the user interface 124, or any combination thereof. In this implementation, the flow sensor 134 can be coupled to or integrated into the respiratory therapy device 122, the user interface 124, or the conduit 126. The flow sensor 134 can be a mass flow sensor, such as a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice flow meter, an ultrasonic flow meter, a hot-wire sensor, an eddy current sensor, a membrane sensor, or any combination thereof.

[0087] Temperature sensor 136 outputs temperature data that can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. In some implementations, temperature sensor 136 generates temperature data indicating the user's core body temperature, the user's skin temperature, the temperature of air flowing from respiratory therapy device 122 and / or through conduit 126, the temperature in user interface 124, ambient temperature, or any combination thereof. Temperature sensor 136 can be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or a semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0088] Motion sensor 138 outputs motion data that can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. Motion sensor 138 can be used to detect user movement during sleep, and / or the movement of any component of respiratory therapy system 120, such as respiratory therapy device 122, user interface 124, or catheter 126. Motion sensor 138 may include one or more inertial sensors, such as accelerometers, gyroscopes, and magnetometers. Motion sensor 138 can be used to detect motion or acceleration associated with an arterial pulse, such as a pulse in or around the user's face and near user interface 124, and is configured to detect characteristics of pulse shape, velocity, amplitude, or volume. In some implementations, motion sensor 138 alternatively or additionally generates one or more signals representing the user's body movement from which signals representing the user's sleep state can be obtained; for example, through the user's breathing movements.

[0089] The output of microphone 140 may be stored in memory device 114 and / or analyzed by processor 112 of control system 110. The acoustic data generated by microphone 140 can be reproduced as one or more sounds (e.g., sounds from the user) during a sleep period to determine (e.g., using control system 110) one or more sleep-related parameters, as described further herein. The acoustic data from microphone 140 can also be used to identify (e.g., using control system 110) events experienced by the user during a sleep period, as described further herein. In other implementations, the acoustic data from microphone 140 represents noise associated with respiratory therapy system 120. In some implementations, system 100 includes multiple microphones (e.g., two or more microphones and / or a microphone array with beamforming) such that sound data generated by each of the multiple microphones can be used to distinguish sound data generated by another of the multiple microphones. Microphone 140 can typically be coupled to or integrated into respiratory therapy system 120 (or system 100) in any configuration. For example, microphone 140 may be disposed within respiratory therapy device 122, user interface 124, conduit 126, or other components. Microphone 140 may also be positioned adjacent to or coupled to the exterior of respiratory therapy device 122, user interface 124, conduit 126, or any other component. Microphone 140 may also be a component of user device 170 (e.g., microphone 140 is a microphone for a smartphone). Microphone 140 may be integrated into user interface 124, conduit 126, respiratory therapy device 122, or any combination thereof. Typically, microphone 140 may be located anywhere within or near the air passage of respiratory therapy system 120, which includes at least the motor of respiratory therapy device 122, user interface 124, and conduit 126. Therefore, the air passage may also be referred to as an acoustic passage.

[0090] Speaker 142 outputs sound waves that are audible to the user. In one or more implementations, the sound waves may be audible to the user of system 100 or inaudible to the user of the system (e.g., ultrasound). Speaker 142 may be used as, for example, an alarm clock or to play alarms or messages to the user (e.g., in response to an event). In some implementations, speaker 142 may be used to transmit acoustic data generated by microphone 140 to the user. Speaker 142 may be coupled to or integrated into respiratory therapy device 122, user interface 124, catheter 126, or user device 170.

[0091] Microphone 140 and speaker 142 can be used as separate devices. In some implementations, microphone 140 and speaker 142 can be combined into acoustic sensor 141 (e.g., a sonar sensor), as described in, for example, WO2018 / 050913 and WO2020 / 104465, which are incorporated herein by reference in their entirety. In this implementation, speaker 142 generates or emits sound waves at predetermined intervals and / or frequencies, and microphone 140 detects reflections of the emitted sound waves from speaker 142. The sound waves generated or emitted by speaker 142 have frequencies inaudible to the human ear (e.g., below 20 Hz or above about 18 kHz) to avoid disturbing the user or the user's bed partner (e.g., in bed). Figure 2 The sleep of the bed partner (220) is monitored. Based at least in part on data from microphone 140 and / or speaker 142, control system 110 can determine the user's position and / or one or more of the sleep-related parameters described herein, such as respiratory signal, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, sleep stage, pressure setting of respiratory therapy device 122, mouth leak status, or any combination thereof. In this document, sonar sensors can be understood to involve active acoustic sensing, such as by generating / transmitting ultrasonic or low-frequency ultrasonic sensing signals through the air (e.g., in the frequency range of, for example, about 17-23 kHz, 18-22 kHz, or 17-18 kHz). Such a system can be considered relative to WO2018 / 050913 and WO 2020 / 104465 described above. In some implementations, speaker 142 is a bone conduction speaker. In some embodiments, one or more sensors 130 include (i) a first microphone that is the same as or similar to microphone 140 and is integrated in acoustic sensor 141; and (ii) a second microphone that is the same as or similar to microphone 140 but is separate from and different from the first microphone integrated in acoustic sensor 141.

[0092] RF transmitter 148 generates and / or transmits radio waves with a predetermined frequency and / or predetermined amplitude (e.g., in the high-frequency band, in the low-frequency band, long-wave signal, short-wave signal, etc.). RF receiver 146 detects the reflection of the radio waves emitted from RF transmitter 148, and this data can be analyzed by control system 110 to determine the user's location and / or one or more of the sleep-related parameters described herein. The RF receiver (RF receiver 146 and RF transmitter 148 or another RF pair) can also be used for wireless communication between control system 110, respiratory therapy device 122, one or more sensors 130, user device 170, or any combination thereof. Although RF receiver 146 and RF transmitter 148 are in... Figure 1While shown as separate and distinct components, in some implementations, the RF receiver 146 and RF transmitter 148 are combined as part of the RF sensor 147 (e.g., a radar sensor). In some such implementations, the RF sensor 147 includes control circuitry. The specific format of the RF communication can be WiFi, Bluetooth, etc.

[0093] In some implementations, the RF sensor 147 is part of a mesh system. An example of a mesh system is a WiFi mesh system, which may include mesh nodes, mesh routers, and mesh gateways, each of which may be mobile / movable or fixed. In such an implementation, the WiFi mesh system includes WiFi routers and / or WiFi controllers and one or more satellites (e.g., access points), each satellite including the same or similar RF sensor as the RF sensor 147. The WiFi routers and satellites communicate continuously with each other using WiFi signals. The WiFi mesh system can be used to generate motion data based at least in part on variations in the WiFi signals between the routers and satellites (e.g., differences in received signal strength), said variations being caused by a moving object or person partially blocking the signal. The motion data may indicate movement, breathing, heart rate, gait, falls, behavior, etc., or any combination thereof.

[0094] Camera 150 outputs image data that can be reproduced as one or more images (e.g., still images, video images, thermal images, or combinations thereof) that can be stored in memory device 114. Image data from camera 150 can be used by control system 110 to determine one or more of the sleep-related parameters described herein. For example, image data from camera 150 can be used to identify the user's location, determine when the user is in bed (e.g., ...). Figure 2 The camera 150 can also be used to track the time the user spends in bed 230, and to determine when the user leaves bed 230. The camera 150 can also be used to track eye movements, pupil dilation (if one or both eyes of the user are open), blink rate, or any changes during REM sleep. The camera 150 can also be used to track the user's position, which can affect the duration and / or severity of apnea events in users with obstructive sleep apnea.

[0095] The output of IR sensor 152 is reproducible as one or more infrared images (e.g., still images, video images, or both) that can be stored in memory device 114. The infrared data from IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep period, including the user's temperature and / or the user's movement. IR sensor 152 can also be used in conjunction with camera 150 when measuring the user's presence, location, and / or movement. For example, IR sensor 152 can detect infrared light with wavelengths between about 700 nm and about 1 mm, while camera 150 can detect visible light with wavelengths between about 380 nm and about 740 nm.

[0096] The output of IR sensor 152 is reproducible as one or more infrared images (e.g., still images, video images, or both) that can be stored in memory device 114. The infrared data from IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep period, including the user's temperature and / or the user's movement. IR sensor 152 can also be used in conjunction with camera 150 when measuring the user's presence, location, and / or movement. For example, IR sensor 152 can detect infrared light with wavelengths between about 700 nm and about 1 mm, while camera 150 can detect visible light with wavelengths between about 380 nm and about 740 nm.

[0097] PPG sensor 154 outputs physiological data associated with the user, which can be used to determine one or more sleep-related parameters, such as heart rate, heart rate pattern, heart rate variability, cardiac cycle, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, estimated blood pressure parameters, or any combination thereof. PPG sensor 154 can be worn by the user, embedded in clothing and / or fabric worn by the user, embedded in and / or connected to user interface 124 and / or its associated helmet (e.g., straps, etc.).

[0098] ECG sensor 156 outputs physiological data associated with the electrical activity of the user's heart. In some implementations, ECG sensor 156 includes one or more electrodes located above or around a portion of the user during sleep. The physiological data from ECG sensor 156 can be used, for example, to determine one or more of the sleep-related parameters described herein.

[0099] EEG sensor 158 outputs physiological data associated with the electrical activity of the user's brain. In some implementations, EEG sensor 158 includes one or more electrodes positioned on or around the user's scalp during sleep. The physiological data from EEG sensor 158 can be used, for example, to determine the user's sleep stage at any given time during a sleep period. In some implementations, EEG sensor 158 may be integrated into user interface 124 and / or an associated helmet (e.g., a strap, etc.).

[0100] The capacitive sensor 160, force sensor 162, and strain gauge sensor 164 output data that can be stored in memory device 114 and used by control system 110 to determine one or more of the sleep-related parameters described herein. EMG sensor 166 outputs physiological data related to the electrical activity generated by one or more muscles. Oxygen sensor 168 outputs oxygen data indicating the oxygen concentration of a gas (e.g., in conduit 126 or at user interface 124). Oxygen sensor 168 can be, for example, an ultrasonic oxygen sensor, an electro-oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, or any combination thereof. In some embodiments, one or more sensors 130 further include a skin conductance response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, a blood oxygen sensor, or any combination thereof.

[0101] Analyte sensor 174 can be used to detect the presence of analytes in a user's exhaled breath. Data output from analyte sensor 174 can be stored in memory device 114 and used by control system 110 to determine the characteristics and concentration of any analytes in the user's breath. In some implementations, analyte sensor 174 is located near the user's mouth to detect analytes in the breath exhaled from the user's mouth. For example, when user interface 124 is a mask covering the user's nose and mouth, analyte sensor 174 can be located inside the mask to monitor the user's mouth breathing. In other implementations, such as when user interface 124 is a nasal mask or nasal pillow mask, analyte sensor 174 can be positioned near the user's nose to detect analytes in the breath exhaled through the user's nose. In other implementations, when user interface 124 is a nasal mask or nasal pillow mask, analyte sensor 174 can be located near the user's mouth. In this implementation, analyte sensor 174 can be used to detect any unintentional air leakage from the user's mouth. In some implementations, the analyte sensor 174 is a volatile organic compound (VOC) sensor that can be used to detect carbon-based chemicals or compounds such as carbon dioxide. In some embodiments, the analyte sensor 174 can also be used to detect whether a user is breathing through their nose or mouth. For example, if the presence of an analyte is detected by data output from the analyte sensor 174 located near the user's mouth or inside a mask (in the implementation where the user interface 124 is a mask), the control system 110 can use that data as an indication that the user is breathing through their mouth.

[0102] The humidity sensor 176 outputs data that can be stored in the storage device 114 and used by the control system 110. The humidity sensor 176 can be used to detect humidity in various areas surrounding the user (e.g., inside the conduit 126 or user interface 124, near the user's face, near the connection between the conduit 126 and the user interface 124, near the connection between the conduit 126 and the breathing device 122, etc.). Therefore, in some implementations, the humidity sensor 176 can be coupled to or integrated into the user interface 124 or the conduit 126 to monitor the humidity of pressurized air from the respiratory therapy device 122. In other implementations, the humidity sensor 176 is placed near any area where humidity levels need to be monitored. The humidity sensor 176 can also be used to monitor the humidity of the surrounding environment around the user, such as the air in the user's bedroom. The humidity sensor 176 can also be used to track the user's biometric response to environmental changes.

[0103] One or more LiDAR sensors 178 can be used for depth sensing. This type of optical sensor (e.g., a laser sensor) can be used to detect objects and construct a three-dimensional (3D) map of the surrounding environment (e.g., a living space). LiDAR typically utilizes pulsed lasers for time-of-flight measurements. LiDAR is also known as 3D laser scanning. In examples using this sensor, a fixed or mobile device (such as a smartphone) with LiDAR sensor 178 can measure and map an area extending 5 meters or more from the sensor. For example, LiDAR data can be fused with point cloud data estimated by an electromagnetic RADAR sensor. LiDAR sensor 178 can also use artificial intelligence (AI) to automatically geofence the RADAR system by detecting and classifying spatial features that may cause problems for the RADAR system, such as glass windows (which may be highly reflective to RADAR). For example, LiDAR can also be used to provide an estimate of a person's height, and how that height changes when the person sits down or falls. LiDAR can be used to form a 3D mesh representation of the environment. In further applications, lidar can reflect radio waves off solid surfaces (e.g., transmissive materials) to allow for the classification of different types of obstacles.

[0104] Although Figure 1 While shown separately, any combination of one or more sensors 130 may be integrated into and / or coupled to any one or more components of system 100, including respiratory therapy device 122, user interface 124, conduit 126, humidifier 129, control system 110, user device 170, or any combination thereof. For example, acoustic sensor 141 and / or RF sensor 147 may be integrated into external device 170 and / or coupled to user device. In such implementations, user device 170 can be considered as an auxiliary device for generating additional or auxiliary data for use by system 100 (e.g., control system 110) according to some aspects of the invention. In some implementations, pressure sensor 132 and / or flow sensor 134 are integrated into and / or coupled to respiratory therapy device 122. In some implementations, at least one of the one or more sensors 130 is not coupled to the breathing device 122, the control system 110, or the user device 170, and is typically positioned near the user during sleep periods (e.g., positioned on or in contact with a part of the user, worn by the user, coupled to or positioned on a bedside table, coupled to the mattress, coupled to the ceiling, etc.). More generally, the one or more sensors 130 may be positioned relative to the user in any suitable location such that the one or more sensors 130 can generate physiological data associated with the user and / or bed partner 220 during one or more sleep periods.

[0105] Data from one or more sensors 130 can be analyzed to determine one or more sleep-related parameters, which may include respiratory signals, respiratory rate, respiratory pattern, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, occurrence of one or more events, number of events per hour, event pattern, average duration of events, range of event durations, ratio between different event numbers, sleep stage, apnea-hypopnea index (AHI), or any combination thereof. One or more events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, intentional user interface leakage, unintentional user interface leakage, mouth leakage, coughing, restless legs, sleep disturbance, apnea, tachycardia, dyspnea, asthma attack, seizure, epilepsy, elevated blood pressure, hyperventilation, or any combination thereof. Many of these sleep-related parameters are physiological parameters, although some sleep-related parameters may be considered non-physiological parameters. Other types of physiological and non-physiological parameters may also be determined based on data from one or more sensors 130 or based on other types of data.

[0106] User device 170 includes display device 172. User device 170 may be, for example, a mobile device such as a smartphone, tablet, laptop, game console, smartwatch, etc. Alternatively, user device 170 may be an external sensing system, a television (e.g., a smart TV), or another smart home device (e.g., a smart speaker such as Google Home, Amazon Echo, Alexa, etc.). In some implementations, user device 170 is a wearable device (e.g., a smartwatch). Display device 172 is typically used to display images including still images, video images, or both. In some implementations, display device 172 acts as a human-machine interface (HMI) including a graphical user interface (GUI) configured to display images and provide input interfaces. Display device 172 may be an LED display, OLED display, LCD display, etc. Input interfaces may be, for example, a touchscreen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with user device 170. In some implementations, system 100 may use and / or include one or more user devices 170.

[0107] Blood pressure device 180 is typically used to help generate physiological data for determining one or more blood pressure measurements associated with a user. Blood pressure device 180 may include at least one of one or more sensors 130 to measure, for example, systolic blood pressure components and / or diastolic blood pressure components.

[0108] In some implementations, the blood pressure device 180 is a blood pressure monitor that includes an inflatable cuff that can be worn by a user and a pressure sensor (e.g., pressure sensor 132 described herein). For example, as Figure 2 As shown in the example, the blood pressure device 180 can be worn on a user's upper arm. In this implementation where the blood pressure device 180 is a blood pressure monitor, the blood pressure device 180 also includes a pump (e.g., a manually operated light bulb) for inflating the cuff. In some implementations, the blood pressure device 180 is coupled to a respiratory therapy device 122 of a respiratory system 120, which in turn delivers pressurized air to inflate the cuff. More generally, the blood pressure device 180 can be communicatively coupled to and / or physically integrated into the control system 110, memory device 114, respiratory therapy system 120, user device 170, and / or activity tracker 190 (e.g., within a housing).

[0109] Activity tracker 190 is typically used to help generate physiological data for determining activity measurements associated with a user. Activity measurements may include, for example, steps, distance traveled, steps climbed, duration of physical activity, type of physical activity, intensity of physical activity, time spent standing, respiratory rate, average respiratory rate, resting respiratory rate, maximum respiratory rate, respiratory rate variability, heart rate, average heart rate, resting heart rate, maximum heart rate, heart rate variability, calories burned, blood oxygen saturation, electrical skin activity (also known as skin conductance or skin response), or any combination thereof. Activity tracker 190 includes one or more sensors 130 described herein, such as motion sensors 138 (e.g., one or more accelerometers and / or gyroscopes), PPG sensors 154, and / or ECG sensors 156.

[0110] In some implementations, the activity tracker 190 is a wearable device that can be worn by the user, such as a smartwatch, wristband, ring, or patch. For example, see reference... Figure 2 The activity tracker 190 is worn on the user's wrist. The activity tracker 190 can also be attached to or integrated into clothing or garments worn by the user. Alternatively, the activity tracker 190 can also be attached to an external device 170 or integrated into the user device (e.g., within the same housing). More generally, the activity tracker 190 can be communicatively attached to or physically integrated into the control system 110, memory device 114, respiratory therapy system 120, user device 170, and / or blood pressure device 180 (e.g., within a housing).

[0111] Although the control system 110 and the memory device 114 are in Figure 1While described and shown as separate and distinct components of system 100, in some implementations, control system 110 and / or memory device 114 are integrated into user device 170 and / or respiratory therapy device 122. Alternatively, in some implementations, control system 110 or a portion thereof (e.g., processor 112) may reside in the cloud (e.g., integrated into a server, integrated into an Internet of Things (IoT) device, connected to the cloud, subjected to edge cloud processing, etc.), or in one or more servers (e.g., remote servers, local servers, etc., or any combination thereof).

[0112] Although system 100 is shown as including all of the above-described components, according to implementations of the invention, more or fewer components may be included in the system for identifying the user interface used by the user. For example, a first alternative system includes a control system 110, a memory device 114, and at least one of one or more sensors 130. As another example, a second alternative system includes a control system 110, a memory device 114, at least one of one or more sensors 130, and a user device 170. As yet another example, a third alternative system includes a control system 110, a memory device 114, a respiratory therapy system 120, at least one of one or more sensors 130, and a user device 170. As yet another example, a fourth alternative system includes a control system 110, a memory device 114, a respiratory therapy system 120, at least one of one or more sensors 130, a user device 170, and a blood pressure device 180 and / or an activity tracker 190. Therefore, various systems for modifying pressure settings can be formed using any part or multiple parts of the components shown and described herein and / or in combination with one or more other components.

[0113] Refer again Figure 2 In some implementations, any one or a combination of the control system 110, the memory device 114, and one or more sensors 130 may be located on and / or in any surface and / or structure typically adjacent to the bed 230 and / or the user 210. For example, in some implementations, at least one of the one or more sensors 130 may be located on and / or in one or more components of the respiratory therapy system 120 at a first location adjacent to the bed 230 and / or the user 210. The one or more sensors 130 may be coupled to the respiratory therapy system 120, the user interface 124, the catheter 126, the display device 128, the humidifier 129, or a combination thereof.

[0114] Alternatively or additionally, at least one of the one or more sensors 130 may be located at a second position on and / or within the bed 230 (e.g., one or more sensors 130 are coupled to and / or integrated into the bed 230). Furthermore, alternatively or additionally, at least one of the one or more sensors 130 may be located at a third position on and / or within the mattress 232, adjacent to the bed 230 and / or the user 210 (e.g., one or more sensors 130 are coupled to and / or integrated into the mattress 232). Alternatively or additionally, at least one of the one or more sensors 130 may be located at a fourth position on and / or within a pillow, generally adjacent to the bed 230 and / or the user 210.

[0115] Alternatively or additionally, at least one of the one or more sensors 130 may be positioned at a fifth location on and / or within the bed seat 240, generally adjacent to the bed 230 and / or the user 210. Alternatively or additionally, at least one of the one or more sensors 130 may be positioned at a sixth location, such that at least one of the one or more sensors 130 is coupled to and / or positioned on the user 210 (e.g., one or more sensors 130 are embedded in or coupled to fabric, clothing, and / or a smart device worn by the user 210). More generally, at least one of the one or more sensors 130 may be positioned relative to the user 210 at any suitable location, such that the one or more sensors 130 can generate sensor data associated with the user 210.

[0116] In some implementations, a primary sensor, such as microphone 140, is configured to generate acoustic data associated with user 210 during sleep periods. For example, one or more microphones (with...) Figure 1 The microphone 140 (which is the same as or similar to the microphone 140) may be integrated into and / or coupled to (i) the circuit board of the respiratory therapy device 122, (ii) the catheter 126, (iii) the connector between the components of the respiratory therapy system 120, (iv) the user interface 124, (v) the headgear (e.g., a strap) associated with the user interface, or (vi) a combination thereof.

[0117] In some implementations, one or more auxiliary sensors may be used in addition to the main sensor to generate additional data. In some such implementations, the one or more auxiliary sensors include: a microphone (e.g., microphone 140 of system 100), a flow sensor (e.g., flow sensor 134 of system 100), a pressure sensor (e.g., pressure sensor 132 of system 100), a temperature sensor (e.g., temperature sensor 136 of system 100), a camera (e.g., camera 150 of system 100), a vane sensor (VAF), a hot filament sensor (MAF), a cold filament sensor, a laminar flow sensor, an ultrasonic sensor, an inertial sensor, or a combination thereof.

[0118] Additional or alternative, one or more microphones (with) Figure 1 The microphone 140 (same as or similar to the microphone) can be integrated into and / or connected to a co-location smart device, such as user device 170, TV, watch (e.g., a mechanical watch worn by the user or another smart device), pendant, mattress 232, bed 230, bedding located on bed 230, pillow, speaker (e.g., Figure 1 The device may be a speaker 142), a radio, a flat panel device, a waterless humidifier, or any combination thereof. The co-location smart device can be any smart device within range for detecting sounds emitted by the user, the respiratory therapy system 120, and / or any part of the system 100. In some implementations, the co-location smart device is a smart device that is in the same room as the user during sleep.

[0119] Alternatively or alternatively, in some implementations, one or more microphones (with) Figure 1 The microphone 140 (same or similar) can be located away from system 100. Figure 1 ) and / or user 210 ( Figure 2 This applies as long as an air passage exists that allows acoustic signals to propagate to one or more microphones. For example, one or more microphones may be in a different room than the room containing system 100. In some implementations, physical obstructions in the user's airway can be characterized and / or determined, at least in part, based on the analysis of acoustic data.

[0120] As used herein, sleep periods can be defined in various ways, at least in part, based on, for example, an initial start time and an end time. In some implementations, a sleep period is the duration of a user's sleep; that is, a sleep period has a start time and an end time, and during a sleep period, the user does not wake up until the end time. In other words, any period during which the user is awake is not included in a sleep period. According to this first definition of a sleep period, if a user wakes up and falls asleep multiple times in the same night, each sleep interval separated by the wake-up intervals is a sleep period.

[0121] Alternatively, in some implementations, the sleep period has a start and end time, and during the sleep period, the user can remain awake as long as the continuous duration of wakefulness is less than a wakefulness duration threshold, without the sleep period ending. The wakefulness duration threshold can be defined as a percentage of the sleep period. The wakefulness duration threshold can be, for example, approximately 20 percent of the sleep period, approximately 15 percent of the sleep period duration, approximately 10 percent of the sleep period duration, 5 percent of the sleep period duration, approximately 2 percent of the sleep period duration, or any other threshold percentage. In some implementations, the wakefulness duration threshold is defined as a fixed amount of time, such as approximately one hour, approximately thirty minutes, approximately fifteen minutes, approximately ten minutes, approximately five minutes, approximately two minutes, or any other amount of time.

[0122] In some implementations, a sleep period is defined as the entire time between the time a user first goes to bed at night and the time the user last leaves bed the following morning. In other words, a sleep period can be defined as the time period that begins at a first time (e.g., 10:00 PM) on a first date (e.g., Monday, January 6, 2020), which can be referred to as the current night, when the user first enters bed intending to go to sleep (e.g., if the user does not intend to watch TV or use their smartphone before going to sleep), and ends at a second time (e.g., 7:00 AM) on a second date (e.g., Tuesday, January 7, 2020), which can be referred to as the following morning, when the user first leaves bed with the intention of not returning to sleep the following morning.

[0123] In some implementations, users can manually define the start and / or end of sleep periods. For example, a user can select (e.g., by clicking or tapping) on ​​an external device 170 ( Figure 1 One or more user-selectable elements are displayed on the user device 172 to manually initiate or terminate a sleep period.

[0124] refer to Figure 3 An exemplary timeline 300 for a sleep period is shown. Timeline 300 includes bedtime (t... 入床 ), sleep onset time (t) GTS ), initial sleep time (t) 睡眠 Awakening A, first micro-awakening MA1 and second micro-awakening MA2, awakening time (t) 觉醒 ) and wake-up time (t 起床 ).

[0125] Bedtime t 入床 Before the user falls asleep (e.g., when the user lies down or sits in bed), the user initially gets into bed (e.g.,Figure 2 The bed occupancy time (t) is associated with the bed 230 in the data. Bed occupancy time (t) can be identified at least in part based on the bed threshold duration. 入床 This distinguishes between when a user goes to bed for sleep and when a user goes to bed for other reasons (e.g., watching television). For example, the bed threshold duration could be at least approximately 10 minutes, at least approximately 20 minutes, at least approximately 30 minutes, at least approximately 45 minutes, at least approximately 1 hour, at least approximately 2 hours, etc. While this document describes bedtime t... 入床 But more generally, bedtime t 入床 This can refer to the time when a user initially enters any location intended for sleeping (e.g., sofa, chair, sleeping bag, etc.).

[0126] Time to fall asleep (GTS) and the time it takes for a user to first try to fall asleep after getting into bed (t) 入床 This is related to [the concept of sleep duration]. For example, after going to bed, a user can engage in one or more activities to relax before attempting to sleep (e.g., reading, watching TV, listening to music, using user device 170, etc.). Initial sleep time (t) 睡眠 ) is the time when the user initially falls asleep. For example, initial sleep time (t) 睡眠 This could be the time when the user initially enters the first non-REM sleep stage.

[0127] Awakening Time t 觉醒 This is the time associated with when a user wakes up without returning to sleep (e.g., the opposite of when a user wakes up at night and returns to sleep). A user may experience one of several unconscious micro-awakenings (e.g., micro-awakenings MA1 and MA2) with short durations (e.g., 5 seconds, 10 seconds, 30 seconds, 1 minute, etc.) after initially falling asleep. This is related to the wakefulness time t. 觉醒 Conversely, the user returns to sleep after each of the micro-awakenings MA1 and MA2. Similarly, the user may have one or more conscious awakenings (e.g., awakening A) after initially falling asleep (e.g., getting up to go to the bathroom, caring for a child or pet, sleepwalking, etc.). However, the user returns to sleep after awakening A. Therefore, the awakening time t 觉醒 It can be defined, for example, at least in part, based on the duration of the wake-up threshold (e.g., the user is awake for at least 15 minutes, at least 20 minutes, at least 30 minutes, at least 1 hour, etc.).

[0128] Similarly, wake-up time t 起床 This is associated with the time a user leaves the bed and gets out of bed to end a sleep period (e.g., the opposite of a user getting up at night to go to the bathroom, care for a child or pet, or sleepwalk). In other words, wake-up time t 起床 This is the time a user last leaves bed and does not return until the next sleep period (e.g., the next night). Therefore, wake-up time t起床 The bed-entry time t for the second subsequent sleep period can be defined, for example, at least in part, based on the duration of the rise threshold (e.g., the user has been out of bed for at least 15 minutes, at least 20 minutes, at least 30 minutes, at least 1 hour, etc.). It can also be defined, at least in part, based on the duration of the rise threshold (e.g., the user has been out of bed for at least 4 hours, at least 6 hours, at least 8 hours, at least 12 hours, etc.). 入床 time.

[0129] As mentioned above, in the initial t 入床 And the last t 起床 During the night, a user can wake up and get out of bed more than once. In some implementations, the final wake-up time t 觉醒 and / or final wake-up time t 起床 It is identified or determined at least in part based on a predetermined threshold duration following an event (e.g., falling asleep or getting out of bed). This threshold duration can be customized for the user. For any time period after getting out of bed at night and then waking up and getting out of bed in the morning (when the user wakes up (t...)...) 觉醒 ) or get up (t 起床 ) and users going to bed (t 入床 ), fall asleep (t GTS ) or fall asleep (t 睡眠 For standard users (between approximately 8 and 14 hours), the threshold period can be used for approximately 12 to approximately 18 hours. For users who spend longer periods in bed, a shorter threshold period can be used (e.g., between approximately 8 and approximately 14 hours). The threshold period can be initially selected and / or adjusted later, at least in part, based on a system that monitors the user's sleep behavior.

[0130] Total time in bed (TIB) is the time to bed entry t 入床 and wake-up time t 起床 The duration between sleep and wake times. Total sleep time (TST) is the duration between initial sleep and wake times, excluding any conscious or unconscious awakenings and / or micro-awakenings in between. Typically, total sleep time (TST) will be shorter than total time in bed (TIB) (e.g., one minute shorter, ten minutes shorter, one hour shorter, etc.). For example, refer to... Figure 3 Timeline 300, Total Sleep Time (TST) spanning initial sleep time t 睡眠 and awakening time t 觉醒 The duration of sleep is between, but does not include, the duration of the first micro-awake MA1, the second micro-awake MA2, and awakening A. As shown in the figure, in this example, the total sleep time (TST) is shorter than the total time in bed (TIB).

[0131] In some implementations, Total Sleep Time (TST) can be defined as Persistent Total Sleep Time (PTST). In this implementation, Persistent Total Sleep Time excludes a predetermined initial portion or period of the first non-REM stage (e.g., a light sleep stage). For example, the predetermined initial portion could be between approximately 30 seconds and approximately 20 minutes, between approximately 1 minute and approximately 10 minutes, between approximately 3 minutes and approximately 5 minutes, etc. Persistent Total Sleep Time is a measure of sustained sleep and smooths the sleep-wake sleep graph. For example, when a user initially falls asleep, the user may be in the first non-REM stage for a very short time (e.g., approximately 30 seconds), then return to the wakeful stage for a very short time (e.g., one minute), and then return to the first non-REM stage. In this example, Persistent Total Sleep Time excludes the first instance of the first non-REM stage (e.g., approximately 30 seconds).

[0132] In some implementations, the sleep period is defined as the time from bedtime (t... 入床 Start at wake-up time (t) 起床 The sleep period ends at the initial sleep time (t), meaning the sleep period is defined as the total time to bed (TIB). In some implementations, the sleep period is defined as the time from the initial sleep time (t). 睡眠 ) begins and at the awakening time (t) 觉醒 End. In some implementations, the sleep period is defined as the total sleep time (TST). In some implementations, the sleep period is defined as the time from the start of sleep (t). GTS ) begins and at the awakening time (t) 觉醒 End. In some implementations, a sleep period is defined as the time from the onset of sleep (t...). GTS Start at wake-up time (t) 起床 The sleep period ends at bedtime. In some implementations, the sleep period is defined as the time from bedtime (t...). 入床 ) begins and at the awakening time (t) 觉醒 The sleep period ends at the initial sleep time (t). In some implementations, the sleep period is defined as the time from the start of sleep (t). 觉醒 Start at wake-up time (t) 起床 )Finish.

[0133] Reference Figure 4 This shows the corresponding timeline 300 according to some implementation methods. Figure 3 An exemplary sleep graph 350 is shown. As illustrated, sleep graph 350 includes a sleep-wake signal 351, a wakefulness stage axis 360, a REM stage axis 370, a light sleep stage axis 380, and a deep sleep stage axis 390. The intersection of the sleep-wake signal 351 and one of axes 360-390 represents a sleep stage at any given time during a sleep period.

[0134] The sleep-wake signal 351 may be generated at least in part based on physiological data associated with the user (e.g., generated by one or more of the sensors 130 described herein). The sleep-wake signal may indicate one or more sleep stages, including wakefulness, relaxed wakefulness, micro-wakefulness, REM sleep, a first non-REM sleep stage, a second non-REM sleep stage, a third non-REM sleep stage, or any combination thereof. In some implementations, one or more of the first non-REM sleep stage, the second non-REM sleep stage, and the third non-REM sleep stage may be grouped together and categorized as light sleep stages or deep sleep stages. For example, light sleep stages may include the first non-REM sleep stage, while deep sleep stages may include the second and third non-REM sleep stages. Although in Figure 4 The sleep graph 350 shown includes a light sleep stage axis 380 and a deep sleep stage axis 390, but in some implementations, the sleep graph 350 may include axes for each of the first non-REM stage, the second non-REM stage, and the third non-REM stage. In other implementations, the sleep-wake signal may also indicate respiratory signals, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory amplitude ratio, inspiratory-expiratory duration ratio, number of events per hour, event pattern, or any combination thereof. Information describing the sleep-wake signal may be stored in the memory device 114.

[0135] Sleep graph 350 can be used to determine one or more sleep-related parameters, such as sleep onset wait time (SOL), wakefulness after sleep onset (WASO), sleep efficiency (SE), sleep segmentation index, sleep blockage, or any combination thereof.

[0136] Sleep onset wait time (SOL) is defined as the time to enter sleep (t). GTS ) and initial sleep time (t 睡眠The sleep start wait time (SOL) represents the time it takes for a user to actually fall asleep after their initial attempt to fall asleep. In some implementations, the SOL is defined as the continuous sleep start wait time (PSOL). The difference between PSOL and the initial sleep start wait time is that PSOL is defined as the duration between the time to fall asleep and a predetermined amount of continuous sleep. In some implementations, the predetermined amount of continuous sleep may include, for example, at least 10 minutes of sleep within a second non-REM stage, a third non-REM stage, and / or a REM stage (with no more than 2 minutes of wakefulness), and / or movement between the first non-REM stage. In other words, continuous sleep of up to, for example, 8 minutes within the second non-REM stage, the third non-REM stage, and / or the REM stage and / or the REM stage. In other implementations, the predetermined amount of continuous sleep may include at least 10 minutes of sleep within the first non-REM stage, the second non-REM stage, the third non-REM stage, and / or the REM stage after the initial sleep time. In this way, the predetermined amount of continuous sleep can exclude any micro-awakening (e.g., a ten-second micro-awakening does not restart the 10-minute session).

[0137] Post-sleep wake-onset (WASO) is associated with the total duration of a user's wakefulness between the initial sleep time and wake time. Therefore, WASO includes brief and micro-awakenings during sleep (e.g., Figure 4 The micro-awakenings (MA1 and MA2) shown can be either conscious or unconscious. In some implementations, a sleep-wake attack (WASO) is defined as a sustained sleep-wake attack (PWASO) that consists only of a total duration of awakenings having a predetermined length (e.g., greater than 10 seconds, greater than 30 seconds, greater than 60 seconds, greater than about 5 minutes, greater than about 10 minutes, etc.).

[0138] Sleep efficiency (SE) is defined as the ratio of total time spent in bed (TIB) to total sleep time (TST). For example, if the total time spent in bed is 8 hours and the total sleep time is 7.5 hours, then the sleep efficiency for that sleep period is 93.75%. Sleep efficiency reflects a user's sleep hygiene. For example, if a user goes to bed before sleep and spends time engaging in other activities (e.g., watching television), sleep efficiency will decrease (e.g., the user is penalized). In some implementations, sleep efficiency (SE) can be calculated at least in part based on the total time spent in bed (TIB) and the total time the user attempts to sleep. In such implementations, the total time the user attempts to sleep is defined as the duration between the time to fall asleep (GTS) and the wake-up time described here. For example, if the total sleep time is 8 hours (e.g., between 11 p.m. and 7 a.m.), the time to fall asleep is 10:45 p.m., and the wake-up time is 7:15 a.m., then in such an implementation, the sleep efficiency parameter is calculated to be approximately 94%.

[0139] The segmentation index is determined at least in part based on the number of awakenings during sleep periods. For example, if a user has two micro-awakes (e.g., Figure 4 As shown in the micro-awakenings MA1 and MA2, the segmentation index can be represented as 2. In some implementations, the segmentation index is scaled between a predetermined range of integers (e.g., between 0 and 10).

[0140] Sleep blocks are associated with the transition between any sleep stage (e.g., first non-REM stage, second non-REM stage, third non-REM stage, and / or REM stage) and the waking stage. Sleep blocks can be calculated at a resolution of, for example, 30 seconds.

[0141] In some implementations, the systems and methods described herein may include generating or analyzing a sleep map including sleep-wake signals to determine or identify bedtime (t) based at least in part on the sleep-wake signals of the sleep map. 入床 ), sleep onset time (t) GTS ), initial sleep time (t) 睡眠 ), one or more first micro-awakenings (e.g., MA1 and MA2), awakening time (t) 觉醒 ), wake-up time (t) 起床 ), or any combination thereof.

[0142] In other implementations, one or more of the sensors 130 can be used to determine or identify the bed entry time (t). 入床 ), sleep onset time (t) GTS ), initial sleep time (t) 睡眠 ), one or more first micro-awakenings (e.g., MA1 and MA2), awakening time (t) 觉醒), wake-up time (t) 起床 (e.g., motion sensor 138, microphone 140, camera 150, or any combination thereof), which in turn defines sleep periods. For example, bedtime t can be determined at least in part based on data generated, for example, by motion sensor 138, microphone 140, camera 150, or any combination thereof. 入床 The time to fall asleep can be determined at least in part based on data from, for example, motion sensor 138 (e.g., data indicating that the user is not moving), camera 150 (e.g., data indicating that the user is not moving and / or that the user has turned off the lights), microphone 140 (e.g., data indicating that the TV is being turned off), user device 170 (e.g., data indicating that the user is no longer using user device 170), pressure sensor 132 and / or flow sensor 134 (e.g., data indicating that the user turns on the breathing therapy device 122, data indicating that the user wears user interface 124, etc.), or any combination thereof.

[0143] Figure 5 The invention illustrates the generation of acoustic data in response to acoustic reflections indicative of one or more features of a user interface. The generation of acoustic data includes an acoustic sensor 141 comprising a microphone 140 (or any type of audio transducer) and a speaker 142. However, as described above, the speaker 142 may alternatively be replaced by another device capable of generating acoustic signals (e.g., a motor of the respiratory therapy device 122). The microphone 140 and speaker 142 are shown at a specific position relative to a conduit 126 connected to the respiratory therapy device 122 (not shown). However, as described above, the positions of the microphone 140 and speaker 142 may differ from those shown.

[0144] Speaker 142 emits an acoustic signal 302 within conduit 126. The acoustic signal 302 is in the form of sound. The sound can be one or more of a standard sound (e.g., raw, unmodified sound from an off-the-shelf sound application), a custom sound, an inaudible frequency, white noise, a broadband pulse, a continuous sine wave, a square wave, a sawtooth wave, and a frequency-modulated sine wave (e.g., a chirp). According to some other implementations, the acoustic signal 302 can be one or more of an audible sound or an ultrasonic sound. According to some other implementations, the acoustic signal 302 is in the form of an inaudible sound, wherein the sound is inaudible based on one or both of its frequency (e.g., the frequency is outside the range of human hearing) or its amplitude (e.g., the amplitude is low enough that the sound is not loud enough to be perceived by humans).

[0145] In one or more implementations, acoustic signal 302 is emitted at specific times, such as when the user first puts on the user interface, after the user removes the user interface, or after a sleep apnea or hypopnea event is detected (e.g., after a sleep apnea or hypopnea event is detected when using a respiratory therapy device). For example, the specific monitoring time is selected to be at 0.1-second intervals over a duration of at least 4 seconds.

[0146] The acoustic signal 302 travels along the length L of the conduit 126 until it contacts a feature 304 of the user interface 124, such as at or near the connection 306 between the user interface 124 and the conduit 126. Feature 304 may include a widening (or narrowing) of the path 308 formed by the conduit 126 and the user interface 124. The widening at feature 304 results in a change in the acoustic impedance of the acoustic signal 302 and the acoustic reflection 310. The acoustic reflection 310 propagates back along the length L of the conduit 126 until it reaches the microphone 140. The microphone 140 detects the acoustic reflection 310 and generates acoustic data in response to it. The generated acoustic data is then analyzed for classification and / or characterization of the user interface, as described below. Figure 6 and 14A Further discussion is needed.

[0147] Acoustic signal 302 may continue beyond feature 304 and enter user interface 124. Although not shown, user interface 124 may include one or more additional features that alter the acoustic impedance of acoustic signal 302, which further generate acoustic reflection 310. Thus, while only feature 304 is shown and described as causing acoustic reflection 310, multiple features of user interface 124 may be present, all of which may contribute to acoustic reflection 310.

[0148] Figure 6 This is a flowchart of a method 400 for characterizing a user interface according to an aspect of the present invention. For convenience, the following description will refer to method 400 performed by a respiratory therapy system (e.g., respiratory therapy system 120). However, one or more other devices may perform method 400, such as one or more user devices 170. For example, such a user device 170 may communicate with respiratory therapy system 120 for analyzing and characterizing data discussed further below.

[0149] In step 402, the respiratory therapy system 120 generates acoustic data associated with the acoustic reflections of the acoustic signal. The acoustic data can be generated based on an acoustic transducer that detects the acoustic reflections. For example, the acoustic transducer could be a microphone that converts the pressure wave of the acoustic reflection into an electrical signal representing the data.

[0150] Acoustic reflection at least partially indicates one or more features of the user interface connected to the respiratory therapy device via a catheter. As an acoustic signal propagates downwards along the catheter, it interacts with one or more features of the catheter, one or more features of the connection between the catheter and the user interface, and one or more features of the user interface. This interaction can cause the acoustic signal to be reflected, thus generating acoustic reflection. (See below for reference.) Figures 15 to 20 In more detail, since acoustic reflections are caused at least in part by one or more features of the user interface, acoustic reflections indicate one or more features of the user interface.

[0151] In one or more implementations, the acoustic signal may be transmitted into a conduit connected to a user interface via an audio transducer, such as a speaker. Alternatively or additionally, the acoustic signal may be transmitted into the conduit via a motor of a respiratory therapy device connected to the conduit. For example, the motor of the respiratory therapy device may emit sound as it forces air through the conduit. The emitted sound may be an acoustic signal, or at least a portion of an acoustic signal.

[0152] In one or more implementations, the acoustic signal can be a sound that is audible to humans (e.g., an average human with average human hearing). A sound is audible to a human when it has a loud amplitude that is loud enough to be detected by a human, and when it has a frequency within the range of frequencies that are within human hearing, typically from about 20 Hz to about 20,000 Hz.

[0153] In one or more implementations, the acoustic signal can be a sound audible to humans (e.g., the average human with average human hearing). Sound is inaudible when it has an amplitude smaller than the lowest perceptible amplitude for humans. Alternatively or additionally, sound is inaudible to humans when it has a frequency outside the range of human hearing, such as the range of about 20 Hz to about 20,000 Hz, as mentioned above. For example, in one or more implementations, the acoustic signal can be ultrasound with a frequency higher than the highest perceptible frequency for human hearing.

[0154] In one or more implementations, method 400 can be performed while the user interface is connected to the user (e.g., worn by the user or otherwise engaged with the user's face). In other words, acoustic signals can be emitted, and acoustic data can be generated based on acoustic reflections using the user interface connected or coupled to the user. Furthermore, the user interface can be connected or coupled to the user while, before, or after the respiratory therapy system is providing treatment to the user. For example, during the generation of acoustic data, a flow of pressurized air can be provided through a conduit and enter the user interface. The provision of treatment can generate acoustic signals, for example, by emitting acoustic signals through the motor of the respiratory therapy device. Alternatively, acoustic signals can be emitted in the conduit while no pressurized air flows through the conduit and enters the user interface.

[0155] Alternatively, the method can be executed when the user interface is not connected or attached to a user. Specifically, acoustic reflections indicating one or more features of the user interface do not require the presence of a user. Therefore, method 400 can be executed before the user wears the user interface or after the user removes the user interface.

[0156] Although step 402 is described as being based on acoustic signals and acoustic reflections, in one or more implementations, the generated acoustic data can be generated from multiple acoustic reflections from multiple acoustic signals. The acoustic signals can be the same acoustic signal repeatedly emitted, or different acoustic signals emitted together to form a single acoustic signal, or they can be emitted separately. When multiple acoustic signals are available for multiple acoustic reflections, the generated acoustic data can be the average of the multiple acoustic reflections from the multiple acoustic signals.

[0157] In step 404, the respiratory therapy system 120 analyzes the generated acoustic data. This analysis includes windowing the generated acoustic data, at least in part based on at least one feature of the respiratory therapy system, such as at least one feature of the user interface, at least one feature of the catheter, etc. At least one feature of the user interface may be, for example, an extension of the connection from the catheter to a cavity formed by the padding of a full-face mask against the user's face. At least one feature of the catheter may be, for example, the length of the catheter. More specifically, the length may be the distance from the acoustic sensor to the location where the catheter connects to the user interface. In one or more implementations, windowing may be at least in part based on at least one of the features of the user interface. Windowing is a selection of a portion of the generated acoustic data used for additional analysis and / or for characterizing the user interface, as described below. Windowing focuses on the generated acoustic data that can distinguish and differentiate the various user interfaces present in the respiratory therapy system. Therefore, windowing may focus on the generated acoustic data that indicates the user interface. Windowing can advantageously allow ignoring signal regions that might otherwise confuse estimates of the user interface, such as varying catheter lengths, differences within the respiratory therapy system, such as different respiratory therapy devices, etc. Therefore, windowing the generated acoustic data selects only regions of the acoustic signal and the corresponding data associated with the user interface. As a result, windowing allows regions of the acoustic signal and corresponding data that would otherwise obscure the user interface estimation, due to factors such as those mentioned above.

[0158] At least one feature has a corresponding point in the generated acoustic data that serves as a reference point. This reference point provides a basis for analyzing the generated acoustic data for different types of user interfaces, catheters, respiratory therapy devices, etc. Therefore, the reference point serves as a reference for further analysis of the generated acoustic data and provides consistency between different acoustic data generated in different environments.

[0159] In one or more implementations, a reference point may correspond to the location of one or more features along a pathway at least partially formed by the catheter and the user interface. For example, a reference point may correspond to a feature of the catheter or a feature of the connection between the catheter and the user interface. In one or more implementations, a reference point may correspond to a feature of the user interface itself. In one or more implementations, the reference point is the same for a given user interface. In one or more implementations, the reference point is the same for all different possible user interfaces. This feature can be universal for different types of user interfaces, such that the feature or at least one variation of the feature exists in all respiratory therapy systems including user interfaces connected to the catheter. For example, the feature may be an extension of the acoustic pathway occurring at the connection between the catheter and the user interface. Although such extension may not be the same for each combination of catheter and different user interfaces, each combination of catheter and user interface may include such an extension. Thus, the expansion at the connection between the catheter and the user interface may be a feature corresponding to a reference point of acoustic data generated by user windowing.

[0160] In general, the reference point can be any feature that causes a change in acoustic impedance and is therefore present in the acoustic data generated from acoustic reflections. In one or more implementations, the change in acoustic impedance can be based at least in part on the narrowing of the path formed by the conduit and user interface, and at (i) the user interface, (ii) the connection between the conduit and user interface, or (iii) a combination thereof. Alternatively, the change in acoustic impedance can be based at least in part on the widening of the path at (i) the user interface, (ii) the connection between the conduit and user interface, or (iii) a combination thereof.

[0161] In one or more implementations discussed further below, the analysis of the generated acoustic data may include performing deconvolution on the generated acoustic data, such as calculating the cepstral spectrum of the generated acoustic data. In this case, the reference point may be the minimum point within a predetermined portion of the deconvolutioned generated acoustic data. Alternatively, the reference point may be the maximum point within a predetermined portion of the deconvolutioned generated acoustic data. As mentioned above, the reference point may be based on the connection between the user interface and the conduit, while the predetermined portion may be based on the length of the conduit. More specifically, the predetermined portion may be based on the distance between the acoustic sensor and the connection between the conduit and the user interface.

[0162] Reference Figure 7 The diagram illustrates calculated cepstrums 500a and 500b obtained from acoustic data generated for two different acoustic reflections. The two cepstrums 500a and 500b are shown merely for descriptive convenience and are not intended to be limiting. For example, a single cepstrum can be calculated for the generated acoustic data used to characterize a user interface. The two cepstrums 500a and 500b are two cepstrums calculated from acoustic data generated differently from the same user interface.

[0163] The curves are shown with frequency on the X-axis and amplitude on the Y-axis. Frequency is analogous to time or distance, but the unit of the X-axis is simply the sample or number of acoustic reflections. The unit of the Y-axis can be any unit used to measure amplitude. The values ​​around the X-axis, 250, are the large minimum values ​​502a and 502b, which can be used as reference points for analyzing the generated acoustic data. These correspond to widening of the path in the conduit, such as the connection point between the conduit and the user interface.

[0164] Return to reference Figure 6 In step 404, in one or more implementations, windowing may include a first window and a second window on the generated acoustic data. In one or more implementations, the first window may identify or locate features of the user interface corresponding to a reference point. Subsequently, the second window may identify or locate other features of the user interface. The first window on the generated acoustic data may differ from the second window on the generated acoustic data by a selected amount of generated acoustic data, the selection of which is before, after, or a combination thereof, the reference point in the generated acoustic data. Relative to the length of the path generated by the conduit and the user interface, the first window may capture only approximately 10 cm before and after the reference point, for example, approximately 10 cm before and after the connection point between the conduit and the user interface. Conversely, the second window may capture approximately 35 cm before and approximately 50 cm after the reference point.

[0165] The amount of data captured by windowing can vary based on the amount of acoustic data generated for the specific analysis associated with the windowing. For example, a first window can be used to identify a reference point. As a result, the size of the resulting window can be smaller because it is entirely focused on identifying the reference point. Once the reference point is determined, a second window can be generated, which can result in a larger second window. The larger second window can capture the generated acoustic data, which is then sent to the characterization step discussed below. The characterization step can benefit from additional data, which is why the second window generated from the second window can be larger than the first window generated from the first window, where the larger window captures more features used to characterize the user interface compared to the first window. Alternatively, the sizes of the windows generated during the first and second windowing can be reversed, with the first window being larger than the second window. A large first window can help determine the correct reference point for the analysis.

[0166] refer to Figure 8 The windowed cepstrums 600a and 600b, corresponding to cepstrums 500a and 500b respectively, are shown after windowing as described above. Windowing in Figure 7 After removing approximately 350 values ​​from the X-axis of the generated acoustic data, and... Figure 7The generated acoustic data is removed before approximately 200 values ​​on the X-axis. Windowing is performed to eliminate the generated acoustic data that is not used to characterize the user interface and may potentially undermine additional analysis and characterization of the acoustic data used to determine the user interface. The resulting retained acoustic data is approximately 80° on either side of reference points 502a and 502b.

[0167] Reference Figure 9 Another result of windowing, shown by windowed cepstrum 600a relative to windowed cepstrum 600b, is based on the alignment of reference points 502a and 502b. As described below, alignment allows for further consistency in the additional analysis of the generated acoustic data and the characterization of the analyzed acoustic data.

[0168] As described above, in one or more implementations, the respiratory therapy system 120 analyzing the generated acoustic data may include deconvolution of the generated acoustic data before windowing it. In one or more implementations, deconvolution of the generated acoustic data may include calculating the cepstrum of the generated acoustic data. The cepstrum identifies distances associated with acoustic reflections, and these distances indicate the location of one or more features of the user interface. More specifically, the cepstrum identifies one or more distances associated with each of the corresponding one or more acoustic reflections, thereby indicating the location of each of one or more physical features along the acoustic path of the acoustic signal. Calculating the cepstrum can be achieved by processing the acoustic reflections in a series of stages: calculating the spectrum of the acoustic reflections via a fast Fourier transform; taking the natural logarithm of the absolute amount of the spectrum; performing an inverse Fourier transform and calculating the real part of the signal to generate the cepstrum. This process may be repeated over multiple time intervals, and an average cepstrum may be estimated. The resulting cepstrum signal transforms the acoustic reflections to a quasi-frequency domain similar to separating reflections in time and / or distance. In one or more implementations, the cepstrum can be calculated using the Fast Fourier Transform of 4096 acoustic reflection samples, optionally with 50% sample overlap. These 4096 samples represent approximately 0.2 seconds of generated acoustic data.

[0169] In one or more implementations, analysis of the generated acoustic data may include calculating the derivative of the cepstral spectrum to determine the rate of change of the cepstral signal. The derivative of the cepstral spectrum can provide additional information for characterizing the user interface, as described below with respect to step 406. The derivative of the cepstral spectrum also allows the network to find alternative features from the same input.

[0170] In one or more implementations, the analysis of the generated acoustic data by the respiratory therapy system 120 may include normalizing the generated acoustic data. Normalizing the generated acoustic data can resolve obfuscation conditions. Obfuscation conditions may be, for example, microphone gain, respiratory amplitude, treatment pressure, varying catheter length, coiled or stretched catheter, different treatment pressures, ambient temperature, or combinations thereof. In one or more implementations, normalization of the generated acoustic data may include subtracting the mean from the generated acoustic data, dividing by the standard deviation of the generated acoustic data, or combinations thereof. The purpose of normalization is to ensure that all inputs to the cepstrum of the analyzed acoustic data have similar amplitudes and are within a range that is natural for characterization, as further described below. In one or more implementations, the purpose of normalization is to ensure that the mean of the cepstrum is always zero.

[0171] Reference Figure 10 The normalized cepstrums 800a and 800b, corresponding to cepstrums 500a and 500b respectively, are shown. Figure 10 relative to Figure 9 As shown by the Y-axis values, the amplitude has been adjusted so that the cepstrum has similar amplitudes and is within the range of natural characteristics, as described below.

[0172] Return to reference Figure 6 In step 406, the respiratory therapy system 120 characterizes the user interface at least in part based on the analyzed acoustic data. Characterizing the user interface involves feeding the analyzed acoustic data into a supervised machine learning model (e.g., a (deep) neural network such as a convolutional neural network) to determine the user interface. In one or more implementations, determining the user interface includes determining the shape factor or type of the user interface (e.g., full face, nose, nasal pillow, etc.), the model of the user interface (e.g., AirFit manufactured by ResMed), and the model of the user interface (e.g., AirFit manufactured by ResMed). TM The dimensions of one or more components of the F20 face shield and user interface, or a combination thereof.

[0173] In one or more implementations, a convolutional neural network (CNN) may include one or more convolutional and max-pooling layers. In one or more implementations, a CNN may include one or more convolutional layers. In one or more implementations, a CNN may include N features. The width of each of the N features may be L samples. The CNN may also allow max-pooling of M samples. Each of the N features is a unique curve or wave within the analyzed acoustic data (e.g., within the cepstral spectrum). In one or more implementations, N may be equal to 64, such that the CNN can represent 64 unique graphs or features within the analyzed acoustic data. Each of the L samples in width represents a data point generated based on acoustic reflections. Therefore, L samples represent L data points generated in response to acoustic reflections. The L samples roughly match the expected size of the features within the acoustic reflections. In one or more implementations, L samples may roughly correspond to a length of about 25 cm. M samples may be, for example, 20 samples, which allows some natural time invariance in the model to account for offsets between different mask reflections. In one or more implementations, the ratio of N to M may be from 1:1 to 4:1. In one or more implementations, the output of a convolutional layer can be fed into one or more fully connected dense layers before classification.

[0174] Although the disclosed embodiments have been shown and described with respect to one or more implementations, equivalent substitutions and modifications will be conceived or known by those skilled in the art upon reading and understanding this specification and the accompanying drawings. Furthermore, while a particular feature of the invention may be disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of other implementations, which may be desirable and advantageous for any given or particular application.

[0175] In one or more implementations, a CNN can be trained based on an augmented training set by adding 20 randomly cyclically shifted samples to the features used to train the CNN. Specifically, the transformation can be applied to features within the dataset used to train the CNN, making it more robust to the temporal portion of acoustic signal shifts, shifts in acoustic data within a window, the addition of noise, and other types of shifts, for use in a more robust system.

[0176] While this application focuses on identifying user interfaces, in one or more implementations, the systems and methods disclosed herein can be used to identify catheters based on the same methods disclosed for identifying user interfaces. For example, different catheters (e.g., different diameters, lengths, materials, etc.) may be used within a respiratory therapy system. The system and methods can be used to identify these different catheters.

[0177] In one or more implementations, conduit 126, rather than the user interface, may be identified. Further details relating to the identification of conduit 126 can be found in U.S. Provisional Application No. 63 / 107,763, filed October 30, 2020, which is incorporated herein by reference in its entirety. In one or more implementations, the conduit may be identified along with the user interface. In cases where both are identified, the order of identification may include identifying both simultaneously, or identifying one first (e.g., the conduit or the user interface) and then the other.

[0178] In one or more implementations, one of the catheters or user interfaces can narrow down the possible choices for identifying the other. For example, a particular catheter may be compatible only with a subset of all user interfaces of a respiratory therapy system. Thus, identifying the catheter can limit subsequent identification of the user interface to only those within that subset. A similar narrowing can be achieved by first identifying the user interface in order to subsequently identify the catheter, thereby simplifying the characterization.

[0179] The characteristics of the aforementioned user interfaces are typically focused at the highest level of the user interface type and can be narrowed down to specific models, aesthetic styles, etc. However, such as Figure 1 and 2 User interfaces 124 in the document have different categories, which can be considered as a distinction between user interfaces that is broader than the type (e.g., full face, nose, nasal pillow, etc.), or at least as broad as the type. According to some implementations, the categories are defined at least in part as directly connected user interfaces (referred to herein as "direct category" user interfaces) or indirectly connected user interfaces (referred to herein as "indirect category" user interfaces). In one or more implementations, the distinction between direct and indirect connection is based on the elements of the user interface connected to the catheter of the respiratory therapy system. That is, the description of direct versus indirect connected user interfaces relates to how pressurized air is delivered from the end of the catheter of the respiratory therapy system to the user through the user interface. As will be described in more detail below, a directly connected user interface typically allows the catheter of the respiratory therapy system to optionally connect directly to the liner and / or frame of the user interface (described below) via a connector. Therefore, pressurized air is delivered directly from the catheter of the respiratory therapy system (optionally via the connector) to the cavity formed by the liner (or liner and frame) of the user interface against the user's face.

[0180] Figure 11A and 11BPerspective views and exploded views of one implementation of a direct-connection user interface (“direct-category” user interface) according to various aspects of the present invention are shown. The direct-category user interface 900 typically includes a pad 930 and a frame 950 defining a volumetric space surrounding the user’s mouth and / or nose. In use, this volumetric space receives pressurized air entering the user’s airway. In some embodiments, the pad 930 and frame 950 of the user interface 900 form a single component of the user interface. The user interface 900 assembly may also be considered to include a headband 910 and an optional connector 970, in the case of the user interface 900, where the headband 910 is typically a strap assembly. When the user wears the user interface 900, the headband 910 is configured to be positioned generally around at least a portion of the user’s head. The headband 910 may be connected to the frame 950 and positioned on the user’s head such that the user’s head is positioned between the headband 910 and the frame 950. The pad 930 is located between the user’s face and the frame 950 to form a seal on the user’s face. Optional connector 970 is configured to connect at one end to frame 950 and / or pad 930 and to a conduit of a respiratory therapy device (not shown). Pressurized air can flow directly from the conduit of the respiratory therapy system through connector 970 into the volume defined by pad 930 (or pad 930 and frame 950) of user interface 900. From user interface 900, pressurized air reaches the user's airway through the user's mouth, nose, or both. Alternatively, if user interface 900 does not include connector 970, the conduit of the respiratory therapy system can be directly connected to pad 930 and / or frame 950.

[0181] For indirectly connected user interfaces (“indirect category” user interfaces), and as will be described in more detail below, the conduit of the respiratory therapy system is indirectly connected to the padding and / or frame of the user interface. In addition to any connector, another element of the user interface is located between the conduit of the respiratory therapy system and the padding and / or frame. This additional element delivers pressurized air from the conduit of the respiratory therapy system to the space volume formed between the padding (or padding and frame) of the user interface and the user's face. Thus, pressurized air is indirectly delivered from the conduit of the respiratory therapy system to the space volume defined by the padding (or padding and frame) of the user interface against the user's face. Furthermore, according to some implementations, the indirect connection category of the user interface can be described as at least two distinct categories: “indirect headgear” and “indirect conduit.” For the indirect headgear category, the conduit of the respiratory therapy system is connected to a headgear conduit, optionally via a connector that is in turn connected to the padding (or padding and frame). The headgear is thus configured to deliver pressurized air from the conduit of the respiratory therapy system to the padding (or padding and frame) of the user interface. Therefore, the head-mounted conduit within the user interface headgear is configured to deliver pressurized air from the conduit of the respiratory therapy system to the pad of the user interface.

[0182] Figure 12A and 12BPerspective and exploded views of one implementation of an indirect catheter user interface 1000 according to various aspects of the present invention are shown. The indirect catheter user interface 1000 includes a pad 1030 and a frame 1050. In some embodiments, the pad 1030 and frame 1050 form integral parts of the user interface 1000. The indirect catheter user interface 1000 may also be considered to include a headband 1010, such as a strap assembly, optionally including a connector 1070, and a user interface catheter 1090 (generally referred to in the art as a “microtube” or “flexible tube”). Typically, the user interface catheter i) is more flexible than the catheter 126 of the respiratory therapy system, (ii) has a smaller diameter than the catheter 126 of the respiratory therapy system, or both (i) and (ii). The user interface catheter may also have a shorter length than the catheter. Similar to user interface 900, headband 1010 is configured to be positioned generally around at least a portion of the user's head when the user wears user interface 1000. The headband 1010 can be connected to the frame 1050 and positioned on the user's head such that the user's head is positioned between the headband 1010 and the frame 1050. A pad 1030 is located between the user's face and the frame 1050 to form a seal on the user's face. An optional connector 1070 is configured to connect at one end to the frame 1050 and / or the pad 1030 and at the other end to a conduit 1090 of the user interface 1000. In other implementations, the conduit 1090 may be directly connected to the frame 1050 and / or the pad 1030. The conduit 1090 is configured at its opposite end relative to the frame 1050 and the pad 1030 to connect to a conduit 126 of a respiratory therapy system (not shown). Figure 12A Pressurized air can be supplied through catheter 126 of the respiratory therapy system. Figure 12A The air flows through the user interface conduit 1090 and optionally through the connector 1070, and enters a space defined by the pad 1030 (or pad 1030 and frame 1050) of the user interface 1000 against the user's face. From this space, pressurized air reaches the user's airway through the user's mouth, nose, or both.

[0183] Considering the above configuration, the user interface 1000 is an indirectly connected user interface because pressurized air is supplied via the user interface conduit 1090 from the conduit 126 (not shown) of the respiratory therapy system. Figure 12A The fluid is delivered to the liner 1030 (or the liner 1030 and the frame 1050), instead of directly from the catheter 126 of the respiratory therapy system. Figure 12A )delivery.

[0184] Figure 13A and 13BPerspective views and exploded views of one implementation of an indirect head-mounted user interface 1100 according to various aspects of the present invention are shown. The indirect head-mounted user interface 1100 includes a pad 1130. The indirect head-mounted user interface 1100 may also be considered to include a head-mounted device 1110 (which may include a strap 1110a and a head-mounted conduit 1110b, and optionally a connector 1170). Similar to user interfaces 900 and 1000, the head-mounted device 1110 is configured to generally be positioned around at least a portion of the user's head when the user wears the user interface 1100. The head-mounted device 1110 includes a strap 1110a that is connectable to and positioned on the user's head via the head-mounted conduit 1110b, such that the user's head is positioned between the strap 1110a and the head-mounted conduit 1110b. The pad 1130 is located between the user's face and the head-mounted conduit 1110b to form a seal on the user's face. Connector 1170 is configured to connect at one end to headband 1110 and at the other end to a catheter of the respiratory therapy system. In other implementations, connector 1170 may be optional, and headband 1110 may alternatively be directly connected to the catheter of the respiratory therapy system. Headband catheter 1110b may be configured to deliver pressurized air from the catheter of the respiratory therapy system to pad 1130, or more specifically, to a volume of space surrounding the user's mouth and / or nose and surrounded by the user pad. Therefore, headband catheter 1110b is hollow to provide a passage for pressurized air. Both sides of headband catheter 1110b may be hollow to provide two passages for pressurized air. Alternatively, only one side of headband catheter 1110b may be hollow to provide a single passage. Figure 13A and 13B In the illustrated embodiment, the head-mounted cannula 1110b includes two channels located on either side of the user's head / face during use. Alternatively, only one channel of the head-mounted cannula 1110b may be hollow to provide a single channel. Pressurized air can flow from the catheter of the respiratory therapy system, through the connector 1170 (if present) and the head-mounted cannula 1110b, and into the space volume between the pad 1130 and the user's face. From the space volume between the pad 1130 and the user's face, the pressurized air reaches the user's airway through the user's mouth, nose, or both.

[0185] Considering the above configuration, the user interface 1100 is an indirect head-mounted user interface because pressurized air is delivered from the duct of the respiratory therapy system to the space between the pad 1130 and the user's face via the head-mounted conduit 1110b, rather than directly from the duct of the respiratory therapy system to the space between the pad 1130 and the user's face.

[0186] In one or more embodiments, the distinction between direct and indirect categories can be defined by the distance pressurized air travels after leaving the conduit of the respiratory therapy device and before reaching the volume of space defined by the padding of the user interface, excluding the connector of the user interface connected to the conduit. This distance is shorter for direct category user interfaces than for indirect category user interfaces, for example, less than 1 cm, less than 2 cm, less than 3 cm, less than 4 cm, or less than 5 cm. This is because the pressurized air travels through additional elements between the conduits of the respiratory therapy system, such as user interface conduit 1090 or headband conduit 1110b, before reaching the volume of space defined by the padding (or padding and frame) of the user interface, thereby forming a seal with the user's face for indirect category user interfaces.

[0187] Figure 14A This is a flowchart of a method 1200 for classifying a user interface according to aspects of the present invention. For convenience, the following description will refer to method 1200 performed by a respiratory therapy system (e.g., respiratory therapy system 120). However, one or more other devices may perform method 1200, such as one or more user devices 170. For example, such user device 170 may communicate with respiratory therapy system 120 for analyzing and classifying data discussed further below.

[0188] In step 1202, the respiratory therapy system 120 generates acoustic data associated with the acoustic reflection of an acoustic signal. Similar to step 402 above, the acoustic data can be generated based on an acoustic transducer that detects the acoustic reflection. For example, the acoustic transducer could be a microphone that converts the pressure wave of the acoustic reflection into an electrical signal representing the data. The acoustic reflection at least partially indicates one or more features of a user interface connected to the respiratory therapy device via a conduit. As the acoustic signal propagates downward along the conduit, it interacts with one or more features of the conduit, one or more features of the connection between the conduit and the user interface, one or more features of the user interface, etc. This interaction can cause the acoustic signal to reflect, thereby generating an acoustic reflection. Because the acoustic reflection is at least partially caused by one or more features of the user interface, the acoustic reflection indicates one or more features of the user interface.

[0189] In one or more implementations, the acoustic signal may be transmitted into a conduit connected to a user interface via an audio transducer, such as a speaker. Alternatively or additionally, the acoustic signal may be transmitted into the conduit via a motor of a respiratory therapy device connected to the conduit. For example, the motor of the respiratory therapy device may emit sound as it forces air through the conduit. The emitted sound may be an acoustic signal, or at least a portion of an acoustic signal.

[0190] In one or more implementations, the acoustic signal can be a sound that is audible to humans (e.g., an average human with average human hearing). A sound is audible to a human when it has a loud amplitude that is loud enough to be detected by a human, and when it has a frequency within the range of frequencies that are within human hearing, typically from about 20 Hz to about 20,000 Hz.

[0191] In one or more implementations, the acoustic signal can be a sound audible to humans (e.g., the average human with average human hearing). Sound is inaudible when it has an amplitude smaller than the lowest perceptible amplitude for humans. Alternatively or additionally, sound is inaudible to humans when it has a frequency outside the range of human hearing, such as the range of about 20 Hz to about 20,000 Hz, as mentioned above. For example, in one or more implementations, the acoustic signal can be ultrasound with a frequency higher than the highest perceptible frequency for human hearing.

[0192] In one or more implementations, method 1200 can be executed when the user connects to or wears the user interface. In other words, acoustic signals can be emitted, and acoustic data can be generated based on acoustic reflections using the user interface connected to or coupled to the user. Furthermore, the user interface can be connected to or coupled to the user while, before, or after the respiratory therapy system is providing treatment to the user. For example, during the generation of acoustic data, a pressurized airflow can be provided through a conduit and enter the user interface. Providing treatment can generate acoustic signals, for example, by emitting acoustic signals through the motor of the respiratory therapy device. Alternatively, acoustic signals can be emitted through the conduit when no pressurized airflow passes through the conduit and enters the user interface.

[0193] Alternatively, the method can be performed when the user interface is not connected or attached to a user. Specifically, acoustic reflections indicating one or more features of the user interface do not require the presence of a user. Therefore, method 1200 can be performed before the user wears the user interface or after the user removes the user interface.

[0194] Although step 1202 is described as being based on acoustic signals and acoustic reflections, in one or more implementations, the generated acoustic data can be generated from multiple acoustic reflections from multiple acoustic signals. The acoustic signals can be the same acoustic signal repeatedly emitted, or different acoustic signals emitted together to form a single acoustic signal, or they can be emitted separately. When multiple acoustic signals are available for multiple acoustic reflections, the generated acoustic data can be the average of the multiple acoustic reflections from the multiple acoustic signals.

[0195] In one or more implementations, the generated acoustic data may include a primary reflection within the acoustic reflections of the acoustic signal. Alternatively, the generated acoustic data may include a secondary reflection within the acoustic reflections of the acoustic signal. Alternatively, the generated acoustic data may include a tertiary reflection within the acoustic reflections of the acoustic signal. The analysis performed in one or more of the following steps may originate from primary, secondary, or tertiary reflections, or a combination thereof; for example, primary and secondary reflections.

[0196] Although described in different parts of this specification Figure 6 Steps 402 and 400 in method 400 Figure 14A Step 1202 of method 1200 is shown as a different step in different flowcharts, but in one or more implementations, step 402 and step 1202 can be the same step.

[0197] In step 1204, the respiratory therapy system 120 analyzes the generated acoustic data to associate one or more features of the user interface with one or more feature markers within the generated acoustic data. The one or more features may include, for example, the maximum amplitude of the transformation, the minimum amplitude of the transformation, the standard deviation of the transformation, the skewness of the transformation, the kurtosis of the transformation, the median of the absolute values ​​of the transformation, the sum of the absolute values ​​of the transformation, the sum of the positive areas of the transformation, the sum of the negative areas of the transformation, the fundamental frequency, the energy corresponding to the fundamental frequency, the average energy, at least one resonant frequency of the combination of the catheter and the user interface, the variation of at least one resonant frequency, the number of peaks within the range, prominent peaks, peak spacing, or combinations thereof. Typically, feature markers may consist of one or more acoustic features within the acoustic data. In one or more implementations, the one or more feature markers may be variations of one or more of the aforementioned aspects over time. Changes in aspects over time can be considered as one or more feature markers specific to a particular category, because changes in aspects over time can be category-specific. These changes can be made during multiple iterations of method 1200, such as continuous iterations over a process of several minutes; or during multiple iterations of method 1200 during a sleep period or night process; or during multiple iterations of method 1200 over several nights, weeks, months, years, etc.

[0198] In one or more implementations, analyzing the generated acoustic data includes generating the spectrum of the generated acoustic data, such as calculating the transform of the generated acoustic data (e.g., Discrete Fourier Transform, DFT or Discrete Cosine Transform, DCT). Subsequently, analyzing the generated acoustic data may also include calculating the logarithm of the spectrum. Further analysis of the generated acoustic data may include calculating the cepstrum of the logarithmic spectrum, such as calculating the inverse transform of the logarithmic spectrum (e.g., iDFT or iDCT). One or more feature tags from the calculated cepstrum can then be analyzed to classify the user interface. Nonlinear operations can be used instead of logarithmic calculations.

[0199] In one or more implementations, the analysis of the generated acoustic data does not need to analyze all of the generated acoustic data. For example, in one or more implementations, analyzing the generated acoustic data may include selecting segments of the aforementioned spectrum. After selecting the segments, the analysis may further include calculating a direct transform (e.g., DFT or DCT) of the spectral segments. Based on the direct transform, one or more features of the user interface may be associated with one or more feature labels within the Fourier transform of the segments to identify the category of the user interface.

[0200] Alternatively, analyzing the generated acoustic data may include selecting a logarithmic spectral segment of the generated acoustic data. Based on the logarithmic spectrum, the analysis may include calculating a transformation of the logarithmic spectrum, such as a Fourier transform of the logarithmic spectrum. Alternatively, the analysis may include calculating the inverse transform of the logarithmic spectrum, or the inverse transform of the logarithmic spectrum transform.

[0201] In one or more specific implementations, Figure 14B A flowchart is shown of a specific method for analyzing acoustic data generated from step 1202, according to some implementations of the present invention. Figure 14B The method can be Figure 14A The sub-method within step 1204 of the method.

[0202] In step 1204-1, a spectrum is generated from the acoustic data. For example, a transform such as the DFT can be generated from the acoustic data. In step 1204-2, the logarithm is obtained from the spectrum generated in step 1204-1. Subsequently, in step 1204-3, a cepstrum can be generated from the logarithmic spectrum of step 1204-2. In step 1204-4, one or more feature markers can then be identified from the cepstrum generated in step 1204-3.

[0203] Instead of proceeding to step 1204-2, refer back to step 1204-1. In step 1204-5, a subset of the spectrum can be extracted, as shown in the following reference. Figure 22 and 23Further discussion follows. In steps 1204-6, a direct transform, such as the DFT, can then be computed from the subset spectrum. In steps 1204-7, one or more feature markers can then be identified from the direct transform of the subset spectrum generated in steps 1204-6.

[0204] Instead of proceeding to step 1204-3, refer back to step 1204-2. In step 1204-8, a subset of the logarithmic spectrum can be extracted, as shown in the reference below. Figure 22 and 23 Further discussion follows. Subsequently, in steps 1204-9, a direct transform, such as the DFT, can be computed from the subset logarithmic spectrum. Alternatively, in steps 1204-10, an inverse transform, such as the iDFT, can be computed from the subset logarithmic spectrum. After steps 1204-9 and 1204-10, one or more feature markers can then be identified from the direct or inverse transform from the subset logarithmic spectrum in step 1204-7.

[0205] Return to reference Figure 14A The segments of the generated acoustic signal discussed above can be selected by trimming the generated acoustic data based on where one or more feature markers indicating the category of the user interface are typically located within the generated acoustic data. For example, Figure 22 The spectrum of exemplary generated acoustic data is shown. The hash segment 2001 of the generated acoustic data graph can be a segment of the generated acoustic data corresponding to acoustic data associated with features of the user interface that can be used to classify the user interface. Therefore, acoustic data generated before and after segment 2001 can be removed, and only (or further) acoustic data generated within segment 2001 can be analyzed to classify the user interface. Figure 23 It shows Figure 22 Further transformations of segment 2001 in the middle, for example Figure 22 The inverse Fourier transform of the logarithmic spectrum of the generated acoustic data is plotted in the image. According to... Figure 23 In the graph, the feature labels of the graph can be used to classify the user interface.

[0206] Specifically, in step 1206, the respiratory therapy system 120 classifies the user interface at least partially based on one or more feature tags. As described above, the category of the user interface can be, for example, direct, indirect frame, or indirect conduit. One or more feature tags can be fed into, for example, a machine learning model (e.g., linear regression, logistic regression, nearest neighbor, decision tree, PCA, Naive Bayes classifier, and k-means clustering, random forest, etc.) and return a category (e.g., direct conduit, indirect conduit, indirect frame). In one or more implementations, classifying the user interface can be at least partially based on one or more feature tags that match one or more known feature tags of one or more user interfaces of known categories. The user interface can be determined based on the known category of the user interface with matching feature tags.

[0207] In one or more implementations, the feature markers used to classify the user interface may relate to a primary reflection within the generated acoustic data. Alternatively, the feature markers used to classify the user interface may relate to reflections other than a primary reflection within the generated acoustic data, such as secondary reflections, tertiary reflections, etc. Alternatively, the feature markers used to classify the user interface may include combinations of reflections, such as primary and secondary reflections; primary and tertiary reflections; primary, secondary, and tertiary reflections; secondary and tertiary reflections, etc.

[0208] Depending on some implementations, direct categories may include one or more feature markers that have a maximum cepstrum amplitude greater than a threshold. Figure 15 and Figure 16 This is a diagram illustrating the calculation of cepstrum for a direct user interface according to some implementations of the present invention. (Refer to...) Figure 15 The diagram illustrates, for example, Figure 11A and 11B The direct category user interface shown is for full-face masks, specifically the AirFit F10. TM The cepstrum of a user interface. The maximum amplitude of the cepstrum satisfies a threshold (e.g., above a certain threshold) that at least partially indicates that the associated user interface is a direct user interface. For example, the threshold could be a value of 0.2 on the y-axis. Because the maximum peak value 1301 is above the 0.2 threshold, the cepstrum indicates that the user interface is of the direct category. Similarly, for Figure 16 The figure illustrates the calculated cepstrum of another direct-category user interface (nose mask, specifically the AirFit N20). The maximum amplitude of the cepstrum satisfies a threshold (e.g., above), for example... Figure 15 The same threshold is 0.2. Specifically, the maximum peak value of 1401 is higher than the same threshold of 0.2. Therefore, the cepstrum indicates that the user interface is a direct category.

[0209] Depending on some implementations, indirect frame categories include one or more feature labels that have an average cepstral value below a threshold. Figure 17 and 18 This is a diagram of an example cepstral plot for an indirect framework class user interface according to some implementations of the present invention. (Refer to...) Figure 17 The diagram illustrates, for example, Figure 12A and 12B The indirect framework category user interface shown (full-face mask, specifically AirFit F30i) TM The cepstrum. The maximum value of the cepstrum satisfies a threshold (e.g., below a certain threshold), indicating that the associated user interface is an indirect frame user interface. For example, the threshold could be a value of 0.2 on the y-axis. Because no peak exceeds the 0.2 threshold, the cepstrum satisfies the threshold and at least partially indicates that the user interface is of the indirect frame category. Furthermore, Figure 17 The cepstral plot in the image shows dispersed cepstral features. This also at least partially indicates that the user interface belongs to the indirect frame category. (Reference) Figure 18 The figure shows the cepstrum of another indirect frame category of user interfaces (nose masks, specifically the AirFit N30i). The maximum amplitude of the cepstrum satisfies a threshold of less than 0.2. Figure 18 The cepstral plot also shows dispersed cepstral feature markers, which at least partially indicate that the user interface is an indirect frame category.

[0210] Depending on some implementations, indirect catheter categories may include one or more feature markers that satisfy a threshold number of peaks. This is, for example, the connection between a catheter in a respiratory therapy system and a catheter in a user interface, as well as the connection between a catheter in a user interface and a connector in a user interface. Figure 19 and 20 This is a diagram of an example cepstral for an indirect framework conduit user interface according to some implementations of the present invention. Reference Figure 19 The diagram illustrates an indirect conduit-type user interface (nasal mask, specifically the AirFit N20). TM The cepstral of ) such as Figure 13A and 13B As shown, the cepstrum includes two prominent peaks, 1701 and 1703. For example, prominent peak 1701 could indicate a connection between catheters in a user interface of a respiratory therapy system. Prominent peak 1703 could indicate, for example, a connection between a catheter of the user interface and a connector of the user interface. Therefore, based on the presence of these two main peaks 1701 and 1703, the cepstrum indicates that the type of user interface is an indirect catheter.

[0211] refer to Figure 20 And similar to Figure 19The prominent peak 1801 can represent, for example, the connection between a catheter in a respiratory therapy system and a catheter in a user interface. The prominent peak 1803 can represent, for example, the connection between a catheter in a user interface and a connector in a user interface. Therefore, based on the presence of these two main peaks 1801 and 1803, the cepstrum indicates that the type of user interface is an indirect catheter.

[0212] Based on the above analysis, feature labels in the generated acoustic data can indicate the category of the user interface. In one or more implementations, a single feature label can be used to classify the user interface, such as a prominent peak satisfying a large threshold. However, in one or more implementations, multiple feature labels can be used to classify the user interface. In one or more implementations, classification can be analogous to representation. For example, classification can be performed based on inputting the analyzed acoustic data into a supervised machine learning model (e.g., a (deep) neural network such as a convolutional neural network) to determine the user interface.

[0213] Reference Figure 21 As mentioned above, the feature tags used to determine the user interface category can be correlated with the primary and secondary reflections in the generated acoustic data. Figure 21 Box 1901 in the figure represents the cepstrum portion corresponding to a single reflection. Figure 21 Box 1903 in the diagram represents the cepstral portion corresponding to a secondary reflection. The amplitude of the cepstral corresponding to a primary reflection can be greater than the amplitude of the cepstral corresponding to a secondary reflection. However, the curve shapes of primary and secondary reflections are similar. In one or more implementations, feature markers in the secondary reflection can be used to confirm feature markers in the primary reflection relative to the category of the user interface. In one or more implementations, the presence / absence of additional reflections (e.g., secondary and / or tertiary reflections) can be used as feature markers for classifying the user interface. In one or more implementations, the ratio of secondary (and / or tertiary) reflections to primary reflections can be used as feature markers for classifying the user interface.

[0214] Such as about Figure 14A As described, classifying user interfaces can be performed as a standalone process. Alternatively, in one or more implementations, classifying user interfaces can be performed as part of a method for characterizing user interfaces to determine their specific manufacturer, type, model, etc. User interfaces can be classified before characterization. Once a category of user interface is determined, that category can be used to define a subset of user interfaces from which the user interfaces are characterized. This can improve the characterization of user interfaces by removing disparate categories that might negatively impact the generation of the characterization.

[0215] Alternatively, the user interface can be characterized first. Afterward, the user interface can be categorized. The user interface category can be used to verify that the identified user interface manufacturer, type, model, etc., match the identified user interface category. If the categories do not match, the user interface can be re-characterized, with or without considering the categories from the characterization process.

[0216] In one or more implementations, a confidence score can be determined during the characterization of the user interface. For example, the confidence score can be determined based on the degree of characterization of the user interface. Based on the confidence score, the characterized user interface can be classified to verify that the category of the user interface matches the user interface's type, model, manufacturer, etc. For example, if the confidence score is below or above a threshold, the user interface can be classified. This category can then be used to verify the characteristics of the user interface. Therefore, although described in different parts of this specification… Figure 6 Method 400 and Figure 14A Method 1200 is shown in different flowcharts, but in one or more implementations, elements of methods 400 and 1200 may overlap, such that the same step within the same method achieves parallel results in the described methods 400 and 1200.

[0217] In some implementations of this disclosure, analyzing acoustic data may include estimating the length of duct 126. The estimated length of duct 126 may be used to define an analysis window for the acoustic data (e.g., a window for characterizing and / or classifying the acoustic data of a user interface after the acoustic data has been windowed).

[0218] Return to reference Figure 5 , 6 Microphones 14A and 14B, 140, can detect reflections 310 caused by feature 304, as well as various other reflections of acoustic signal 302. In some implementations, reflections 310 can be used to determine the length of the conduit. Acoustic data representing acoustic reflections 310 can be used to generate a time-domain intensity signal. The time-domain intensity signal is a measure of the intensity and / or amplitude of reflections 310 over a period of time, as measured by microphone 140. The time-domain intensity signal can be converted to a frequency-domain intensity signal, which can then be used to determine the length of conduit 126. The length of conduit 126 can be used to aid in windowing acoustic data and / or to identify acoustic feature markers of user interface 124.

[0219] In some implementations, the acoustic data represents multiple reflections from multiple acoustic signals, and therefore the time-domain intensity signal can represent not only the reflections of acoustic signal 302. For example, reflections from each of the multiple acoustic signals can be averaged together, and the time-domain intensity signal can be generated from this average.

[0220] Figure 24AA graph of the frequency domain intensity signal 2400, which can be obtained from the time domain intensity signal, is shown. In some implementations, the frequency domain intensity signal 2400 can be obtained from the time domain intensity signal by performing a Fourier transform on the time domain intensity signal. The frequency domain intensity signal 2400 represents the intensity of the acoustic reflection 310 at various frequencies in the frequency band. Therefore, the frequency domain intensity signal 2400 shows the spectrum of the reflection 310 of the acoustic signal 302. Figure 24A In the diagram, the Y-axis represents the absolute value of the intensity of reflection 310, denoted as |x|. The intensity is plotted on a logarithmic scale using arbitrary units. The X-axis represents the frequency of reflection 310, measured in Hertz (Hz). In some implementations, the intensity is plotted on an absolute scale instead of a logarithmic scale.

[0221] Figure 24A The frequency domain intensity signal 2400 represents various frequencies of the reflection 310 from the acoustic signal 302. The acoustic signal 302 and the reflection 310 form standing waves within the conduit 126 and / or the user interface 124. The conduit 126 can support standing waves of various different frequencies. Typically, the lowest frequency of the standing wave supported by the conduit 126 is referred to as the resonant frequency.

[0222] The wavelength of the standing wave at the resonant frequency can be obtained from the resonant frequency and is usually equal to 2L. c L c This is the length of catheter 126. The intensity of a standing wave propagating at a resonant frequency within catheter 126 is generally greater than the intensity of a standing wave propagating at a frequency different from the resonant frequency within catheter 126.

[0223] The frequency domain intensity signal 2400 illustrates the intensity of standing waves with various frequencies propagating within the catheter 126. Peak values ​​in the frequency domain intensity signal 2400 correspond to different standing waves supported within the catheter 126. However, because the catheter 126 connects to both the breathing device 122 and the user interface 124, the frequency domain intensity signal 2400 also represents standing waves partially propagating within the breathing device 122, the user interface 124, or both. Therefore, some peak values ​​in the frequency domain intensity signal 2400 correspond to standing waves partially propagating within the breathing device 122, the user interface 124, or both.

[0224] For example, the frequency domain intensity signal 2400 includes a low-frequency peak 2402 that is larger than the remaining peaks of the frequency domain intensity signal 2400. Peak 2402 may correspond to a standing wave propagating primarily within the breathing device 122. The frequency domain intensity signal 2400 also includes peaks 2404, 2406, and 2408, which represent standing waves propagating at least partially within the user interface 124. Finally, the frequency domain intensity signal 2400 includes a series of peaks 2410 located within a portion 2401 of the frequency domain intensity signal 2400. Figure 24AAs shown, peak 2410 is arranged in a series of peaks with decreasing intensity, typically periodic. This series of peaks 2410 primarily corresponds to the standing wave propagating at the resonant frequency of duct 126, as well as higher harmonics of that resonant frequency, although peak 2410 can also correspond to the standing wave propagating at the resonant frequency of user interface 124 and its higher harmonics. These higher harmonics have a harmonicity equal to 2L. c A standing wave of wavelength / n, where n is a positive integer greater than or equal to two.

[0225] Figure 24B A graph of the wave period intensity signal 2420, which can be obtained from the frequency domain intensity signal 2400, is shown. In some implementations, the wave period intensity signal 2420 is obtained by performing a Fourier transform on a portion 2401 of the frequency domain intensity signal 2400 containing a periodic series of peaks 2410. The wave period intensity signal 2420 is plotted relative to the period of the standing wave, representing the intensity of the reflection 310 within the portion 2401 of the frequency domain intensity signal. The Y-axis of the curve represents the intensity of the reflection 310, denoted as |x|. The intensity is plotted on an absolute scale. The X-axis represents the period of the reflection 310 within the portion 2401 of the frequency domain intensity signal 2400, measured in seconds (e.g., the reciprocal of the frequency).

[0226] As shown in the figure, the wave period intensity signal 2420 contains a peak 2422 that is much larger than other peaks in the wave period intensity signal 2420. Because peak 2422 is larger than the other peaks, peak 2422 corresponds to a standing wave propagating at the resonant frequency of duct 126. The position of peak 2422 along the X-axis represents the period of the standing wave propagating at the resonant frequency. The resonant frequency can be determined by taking the reciprocal of the period of this standing wave. Furthermore, the wavelength λ of this standing wave is typically equal to ν / f, where ν is the speed of sound within duct 126. In some implementations, the speed of sound ν is based at least in part on the temperature and / or humidity of the air within duct 126. Once the wavelength of the standing wave propagating at the resonant frequency is known, it can be determined by taking the reciprocal of its frequency λ = 2L. c The length of catheter 126 is thus determined to be proportional to the wavelength of the standing wave propagating at the resonant frequency and inversely proportional to the resonant frequency.

[0227] In some implementations, a peak different from peak 2422 can be selected as the peak representing the resonant frequency of catheter 126. For example, due to the presence of breathing device 122 and / or user interface 124, the intensity of a standing wave propagating at a frequency different from the resonant frequency may appear greater than the peak value that actually represents the resonant frequency of the standing wave. In these cases, the lowest frequency peak of wave period intensity signal 2420 can be selected as the resonant frequency representing catheter 126.

[0228] Performing Fourier transforms on the initial time-domain and frequency-domain intensity signals 2400, along with any preprocessing steps, typically minimizes noise in the data to allow for easier identification of the catheter's resonant frequency. However, in some implementations, the resonant frequency can be identified from the frequency-domain intensity signal 2400 instead of the wave period intensity signal. For example, after identifying a series of peaks 2410 in the frequency-domain intensity signal 2400, the resonant frequency can be selected directly from these peaks 2410. The peak of the series of peaks 2410 with the lowest frequency can be selected to represent the resonant frequency of the catheter 126.

[0229] In some implementations, the frequency domain intensity signal 2400 itself can be windowed before obtaining the wave period intensity signal 2420. In these implementations, a portion of the frequency domain intensity signal that is expected to include the resonant frequency of the conduit 126 is selected, and the wave period intensity signal 2420 is obtained only from this selected portion. By identifying the portion of the frequency domain intensity signal that is expected to include the resonant frequency and removing additional portions of the frequency domain intensity signal, this reduces the complexity present when analyzing acoustic data. The selection of the portion of the frequency domain intensity signal containing the resonant frequency can be based on a variety of factors. In some implementations, a predetermined estimate of the length of the conduit 126 is used to provide the frequency range in which the expected resonant frequency will fall. For example, if it is known that the conduit 126 is typically between 1.5 meters and 2.0 meters, those length estimates can be used to estimate the portion of the frequency domain intensity signal in which the expected resonant frequency lies. Additionally or optionally, the estimation may be based on the velocity of sound within the conduit 126, the sampling rate of the acoustic data, known conditions inside and outside the conduit 126 (such as temperature or humidity, which can affect the velocity of sound within the conduit 126), and other factors that a person skilled in the art may use to estimate a portion of the frequency domain intensity signal in which resonant frequencies exist.

[0230] In some implementations, alternative transformations and / or analyses can be applied instead of applying a Fourier transform to the frequency domain intensity signal to obtain the wave period intensity signal. For example, an inverse Fourier transform can be applied to the frequency domain intensity signal 2400 to obtain a new time domain intensity signal, and the resonant frequency can be identified from the new time domain intensity signal. In another example, cross-correlation analysis can be applied to the initial time domain intensity signal and the frequency domain intensity signal 2400 to determine the resonant frequency of the duct 126.

[0231] In some implementations, various preprocessing steps can be applied to the frequency domain intensity signal or the wave period intensity signal. In one implementation, preprocessing includes detrending, which removes any fluctuations in the frequency domain intensity signal that are independent of the length of the conduit 126. For example, acoustic data may include artifacts (e.g., peaks, drops, etc.) caused by the physical characteristics of components other than the conduit 126, external noise and / or disturbances, data noise, etc. In additional or alternative implementations, preprocessing includes spectral windowing. Spectral windowing can be used to improve the quality of the frequency domain intensity signal, which is the Fourier transform of the time domain intensity signal. In some cases, the Fast Fourier Transform algorithm applied to the time domain intensity signal can lead to various artifacts and other errors in the frequency domain intensity signal. For example, if the endpoints of the time domain intensity signal are discontinuous, the frequency domain intensity signal can be slightly modified from the actual frequency domain version of the time domain intensity signal. Spectral windowing can be used to correct for discontinuities in the endpoints of the time domain intensity signal, making the frequency domain intensity signal more accurately represent the actual spectrum of the acoustic signal reflection.

[0232] Therefore, when windowing the generated acoustic data in step 404 of method 400, the windowing of the generated acoustic data can be at least partially based on... Figure 24A and 24B The length of the duct 126 is determined. By determining the length of the duct 126, an approximate x-axis position on the cepstral spectrum where the duct 126 ends and the user interface 124 begins can be identified. This position can then be used to define an analysis window for the acoustic data (e.g., to window the acoustic data). As discussed here, the windowed acoustic data can then be used to characterize the user interface 124. In some implementations, these techniques can be used first to estimate the length of the duct 126 to provide an estimate of the position of the user interface 124. Then, one or more reference points can be identified based on the estimated position of the user interface 124, and further analysis of the user interface 124 and / or the duct 126 can be performed. Reference points can be identified, and the user interface 124 and / or the duct 126 can be analyzed, as discussed here. Furthermore, the determined length of the duct 126 can also be used as part of any acoustic feature markers for characterizing and / or classifying the user interface 124. In other implementations, different techniques than those discussed here can be used. Figure 24A and 24B The techniques discussed are used to estimate the length of catheter 126.

[0233] Now refer to Figure 25A and 25BThe determined length of the conduit 126 can also be used to adjust the characterization of the user interface 124 based on acoustic data. When analyzing the user interface 124, identifying its features, and characterizing and / or classifying it as discussed herein, the length of the conduit 126 is assumed. However, the conduit 126 can have a different length than expected, for example due to manufacturing tolerances, different designs, stretching, damage, etc. Furthermore, the apparent effective length of the conduit 126 can vary due to the amount of time it takes for sound to pass through it. This amount of time can vary based on air temperature, humidity, the position / orientation of the conduit 126, etc. If the conduit 126 has a different length than expected (actual or apparent), any acoustic markers identified using the techniques discussed herein can be unintentionally distorted or misrepresented, making the identified acoustic markers irrelevant to the user interface 124 that the user is testing / using. Therefore, an undesirable length of the conduit 126 can reduce the accuracy of any characterization and / or classification of the user interface 124 and may require adjustments to various aspects related to the characterization and / or classification of the user interface 124 based on the length of the conduit 126.

[0234] Figure 25A The upper diagram of cepstral 2500A and the lower diagram of cepstral 2500B are shown. Cepstral 2500A is determined by acoustic data generated from user interface 124 and first-type conduit 126. Cepstral 2500B is determined based on acoustic data generated from the same user interface 124 but from second-type conduit 126. For example, first-type conduit 126 could be... Catheter, while the second type of catheter 126 can be Catheter. The first and second types of catheters 126 have different lengths.

[0235] Cepstrum 2500A and 2500B are shown as frequency on the X-axis and amplitude on the Y-axis. In these implementations, the frequency corresponds to a measurement of the distance along the path through which the acoustic signal propagates. Cepstrum 2500A and 2500B are thus used to show the distance along this path associated with the reflection of the acoustic signal. Reflection is in turn associated with various characteristics of the user interface. Therefore, cepstrum 2500A and 2500B can be used to characterize and / or classify the corresponding user interface 124. While the illustrated implementation shows the use of cepstrum to characterize and / or classify user interface 124, analysis of acoustic data typically includes performing any deconvolution of the acoustic data. The deconvolution of the acoustic data can then be used to characterize and / or classify user interface 124. Cepstrum is a specific type of deconvolution that can be utilized.

[0236] Since the two cepstral spectra 2500A and 2500B were determined from acoustic data generated using the same user interface 124, the two cepstral spectra 2500A and 2500B should generally have the same pattern. However, the different lengths of the conduit 126 cause the cepstral spectra 2500B to be distorted. Figure 25A As shown, cepstrum 2500B is stretched or tailed relative to cepstrum 2500A. For example, due to the stretching or tailing of cepstrum 2500B, cepstrum 2500B includes a peak 2502B positioned forward relative to the corresponding peak 2502A of cepstrum 2500A. The deformation of cepstrum 2500B due to different catheter lengths also affects the position of the peaks along the Y-axis. If cepstrum 2500B is stretched relative to the expected length of the catheter 126 used to obtain cepstrum 2500B, the peaks may be shorter along the Y-axis than they are otherwise. Conversely, if the length of catheter 126 is shorter than expected, cepstrum 2500B may be compressed relative to the normal, and the peaks may be higher along the Y-axis than they are otherwise. Therefore, any features of the user interface 124 obtainable from cepstrum 2500B will differ from those of the user interface 124 obtainable from cepstrum 2500A, even if the same user interface 124 is used to generate two cepstrums. Therefore, as Figure 25A As shown, the length of the conduit 126 can negatively affect the features of the user interface 124.

[0237] Figure 25B The upper plot shows the corrected cepstrum 2504A and the lower plot shows the corrected cepstrum 2504B. Cepstrum 2504A is a corrected version of cepstrum 2500A and includes peak 2506A. Cepstrum 2504B is a corrected version of cepstrum 2500B and includes peak 2506B. Cepstrums 2504A and 2504B have been corrected by scaling cepstrums 2500A and 2500B to a factor equal to (i) the ratio of the measured length of each corresponding catheter 126 to (ii) the assumed length of catheter 126. For example, if a particular catheter is assumed to be 2 meters long, and analysis of the catheter shows that it is actually 1.8 meters long, the new position of each data point along the X-axis in the cepstrum will be equal to the old position along the X-axis multiplied by 1.8 / 2. Figure 25B As shown, the peak 2506A of the corrected cepstrum 2504A is now aligned with the peak 2506B of the corrected cepstrum 2504B, which is expected if the actual length of the conduit 126 is the same.

[0238] In the implementation shown, cepstrums 2500A and 2500B are both scaled to the same length, eliminating the stretching effect caused by the unknown length of the conduit. Scaled to the same assumed length allows for easier comparison if two conduits 126 and their respective user interfaces 124 are being compared. However, any cepstrum generated from acoustic data can generally be scaled to any desired length. For example, in some implementations, it is assumed that two conduits 126 with two different lengths can each be scaled to their respective assumed lengths, even if these lengths are different. Typically, cepstrums can be scaled to their assumed length to eliminate any distortion caused by the actual length of the conduit 126. As discussed herein, this distortion can include stretched cepstrums as well as compressed cepstrums.

[0239] Therefore, the acoustic data used to characterize and / or classify the conduit 126 can be stretched and / or compressed to compensate for differences in the effective length of the conduit 126, such that the length of the conduit 126 does not distort the characterization and / or classification of the user interface 124. This scaling (e.g., stretching and / or compression) of the acoustic data can be performed in the time domain (time signal), frequency domain (spectrum), quasi-frequency domain (cep spectrum), any other domain, or any combination of domains. Scaling can be performed on the spectrum and / or cepstrum, the logarithm of the spectrum and / or cepstrum, a direct transformation of the spectrum and / or cepstrum, a direct transformation of the logarithm of the spectrum and / or cepstrum, an inverse transformation of the spectrum and / or cepstrum, an inverse transformation of the logarithm of the spectrum and / or cepstrum, or any other dataset. Scaling can also be performed on the acoustic data itself before any operation or transformation is performed on it. Scaling can be performed using various signal processing methods, such as interpolation, upsampling, phase coding techniques (which allow control over the frequency shift to be applied to the signal), etc. Therefore, scaling can be used to assist in methods such as 400 and 100 described herein. Figure 6 The discussion focuses on characterizing the user interface 124, and provides assistance as described in this paper regarding method 1200 and... Figure 14A and 14B The discussion focuses on classifying user interfaces 124.

[0240] Additional details regarding the determination of the length of catheter 126 and / or identification of catheter 126 can be found in U.S. Provisional Application No. 63 / 107,763, filed October 30, 2020, which is incorporated herein by reference in its entirety.

[0241] While various embodiments of the invention have been described above, it should be understood that they are given by way of example only and not by way of limitation. Many changes can be made to the disclosed embodiments based on the disclosure without departing from the spirit or scope of the invention. Therefore, the breadth and scope of the invention should not be limited by any of the embodiments described above. Rather, the scope of the invention should be defined by the appended claims and their equivalents.

[0242] One or more elements, aspects, or steps or any part thereof from any one of claims 1-126 may be combined with one or more elements, aspects, or steps or any part thereof from any other claims 1-126 or a combination thereof to form one or more additional implementations and / or claims of the present invention.

[0243] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. Furthermore, the terms “including / includes,” “having / has,” “with,” or variations thereof are used in the detailed description and / or claims, and these terms are intended to be inclusive in a manner similar to the term “comprising.”

[0244] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. Furthermore, terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense, unless expressly defined herein.

Claims

1. A method for classifying and / or characterizing a user interface, comprising: generating acoustic data associated with acoustic reflections of an acoustic signal, the acoustic reflections being indicative at least in part of one or more features of a user interface coupled to a respiratory treatment device via a conduit; analyzing the generated acoustic data, the analyzing comprising computing a deconvolution of the generated acoustic data, the computing a deconvolution of the generated acoustic data comprising computing a cepstrum of the generated acoustic data, and further comprising computing a derivative of the cepstrum to determine a rate of change of the cepstrum signal, the analyzing comprising windowing the generated acoustic data based at least in part on at least one of the one or more features of the user interface; and characterizing the user interface based at least in part on the analyzed acoustic data.

2. The method of claim 1, wherein the windowing the generated acoustic data comprises determining a fiducial point in the generated acoustic data.

3. The method of claim 2, wherein the fiducial point is a minimum point or a maximum point within a predetermined portion of the deconvolution of the generated acoustic data.

4. The method of any one of claims 2-3, wherein the fiducial point corresponds to a location of the one or more features along a passageway at least partially formed by the conduit and the user interface.

5. The method of claim 4, wherein the one or more features cause a change in acoustic impedance, wherein, the change in acoustic impedance is based at least in part on a narrowing or widening of the passageway at (i) the user interface, (ii) a connection of the conduit to the user interface, or (iii) a combination thereof.

6. The method of any one of claims 1-2, wherein the windowing comprises a first windowing of the generated acoustic data and a second windowing of the generated acoustic data, wherein, the first windowing and the second windowing differ by a selected amount of the generated acoustic data, the selection of the amount of the generated acoustic data being before a fiducial point in the generated acoustic data, after the fiducial point in the generated acoustic data, or a combination thereof.

7. The method of claim 1, wherein the cepstrum identifies a distance associated with the acoustic reflections, the distance being indicative of a location of the one or more features of the user interface.

8. The method of any one of claims 1-2, wherein the analyzing of the generated acoustic data comprises normalizing the generated acoustic data, wherein the normalizing of the generated acoustic data comprises subtracting a mean value from the generated acoustic data, dividing by a standard deviation of the generated acoustic data, or a combination thereof.

9. The method of any one of claims 1-2, wherein the characterizing of the user interface comprises inputting the analyzed acoustic data into a convolutional neural network to determine a form factor of the user interface, a model of the user interface, a dimension of one or more elements of the user interface, or a combination thereof.

10. The method of claim 9, wherein the convolutional neural network comprises N features with a max pooling of M samples of the N features, and a ratio of N to M is 1: 1 to 4:

1.

11. The method of any of claims 1-2, further comprising emitting the acoustic signal into the conduit connected to the user interface via an audio transducer or via a motor of the respiratory treatment device connected to the conduit.

12. The method of claim 11, wherein the acoustic signal is an ultrasonic wave.

13. The method of any one of claims 1 to 2, wherein, During generation of the acoustic data, the user interface is not connected to a user.

14. The method of any of claims 1-2, further comprising providing a flow of pressurized air through the conduit and into the user interface during generation of the acoustic data.

15. The method of any of claims 1-2, wherein the generated acoustic data is generated from a plurality of acoustic reflections from a plurality of acoustic signals, and wherein the generated acoustic data is an average of the plurality of acoustic reflections from the plurality of acoustic signals.

16. The method of any of claims 1-2, wherein analyzing the generated acoustic data comprises identifying one or more feature markers associated with the one or more features of the user interface, the method further comprising: classifying the user interface based at least in part on the one or more feature markers.

17. The method of claim 16, wherein the user interface is characterized from a subset of user interfaces determined based at least in part on the class of the user interface.

18. The method of claim 16, further comprising: verifying the characterized user interface based at least in part on the characterized user interface satisfying the class of the user interface.

19. The method of claim 18, further comprising: determining a confidence score that the user interface is correctly characterized, wherein the characterized user interface is verified when the confidence score satisfies a confidence threshold.

20. A system for classifying and / or characterizing a user interface, comprising: a memory storing machine-readable instructions; and a control system comprising one or more processors configured to execute the machine-readable instructions to: generate acoustic data associated with acoustic reflections of an acoustic signal, the acoustic reflections being indicative at least in part of one or more features of a user interface coupled to a respiratory treatment device via a conduit; analyze the generated acoustic data, the analyzing comprising computing a deconvolution of the generated acoustic data, computing a cepstrum of the generated acoustic data, and further comprising computing a derivative of the cepstrum to determine a rate of change of the cepstrum signal, the analyzing comprising windowing the generated acoustic data based at least in part on at least one of the one or more features of the user interface; and characterize the user interface based at least in part on the analyzed acoustic data.

21. The system of claim 20, wherein windowing the generated acoustic data comprises determining a fiducial point in the generated acoustic data.

22. The system of claim 21, wherein the fiducial point is a minimum point or a maximum point within a predetermined portion of the deconvolution of the generated acoustic data.

23. The system of any one of claims 21-22, wherein the fiducial point corresponds to a location of the one or more features along a passageway formed at least partially by the conduit and the user interface.

24. The system of claim 23, wherein the one or more features cause a change in acoustic impedance, wherein the change in acoustic impedance is based at least in part on a narrowing or widening of the passageway at (i) the user interface, (ii) a junction of the conduit and the user interface, or (iii) a combination thereof.

25. The system of any one of claims 20-21, wherein the windowing comprises a first windowing of the generated acoustic data and a second windowing of the generated acoustic data, wherein the first windowing and the second windowing differ by a selected amount of the generated acoustic data, the selection of the amount of the generated acoustic data being before a fiducial point in the generated acoustic data, after a fiducial point in the generated acoustic data, or a combination thereof.

26. The system of claim 20, wherein the cepstrum identifies a distance associated with the acoustic reflection, the distance indicating a location of the one or more features of the user interface.

27. The system of any one of claims 20-21, wherein the analysis of the generated acoustic data comprises normalizing the generated acoustic data, wherein the normalizing of the generated acoustic data comprises subtracting a mean from the generated acoustic data, dividing by a standard deviation of the generated acoustic data, or a combination thereof.

28. The system of any one of claims 20-21, wherein the characterization of the user interface comprises inputting the analyzed acoustic data into a convolutional neural network to determine a form factor of the user interface, a model of the user interface, a dimension of one or more elements of the user interface, or a combination thereof.

29. The system of claim 28, wherein the convolutional neural network comprises N features with a max pooling of M samples of the N features, and a ratio of N to M is 1 : 1 to 4:

1.

30. The system of any one of claims 20-21, wherein the one or more processors are further configured to execute the machine-readable instructions to cause the acoustic signal to be emitted into the conduit connected to the user interface via an audio transducer or via a motor of the respiratory treatment device connected to the conduit.

31. The system of claim 30, wherein the acoustic signal is an ultrasonic wave.

32. The system of any one of claims 20-21, wherein the user interface is not connected to a user during the generation of the acoustic data.

33. The system of any one of claims 20-21, wherein the one or more processors are further configured to execute the machine-readable instructions to generate the acoustic data during a provision of a flow of pressurized air through the conduit and into the user interface.

34. The system of any one of claims 20-21, wherein the generated acoustic data is generated from a plurality of acoustic reflections from a plurality of acoustic signals, wherein the generated acoustic data is an average of the plurality of acoustic reflections from the plurality of acoustic signals.

35. The system of any one of claims 20-21, wherein analyzing the generated acoustic data comprises identifying one or more feature signatures associated with the one or more features of the user interface, and wherein, the control system is configured to execute the machine-readable instructions to: classify the user interface based at least in part on the one or more feature tags.

36. The system of claim 35, wherein the user interface is represented from a subset of user interfaces determined based at least in part on the classification of the user interface.

37. The system of claim 35, wherein the control system is configured to execute the machine-readable instructions to: verify the represented user interface based at least in part on the represented user interface satisfying the classification of the user interface.

38. The system of claim 37, wherein the control system is configured to execute the machine-readable instructions to: determine a confidence score that the user interface is correctly represented, wherein, verify the represented user interface when the confidence score satisfies a confidence threshold.

Images