DETAILED ACTION
Applicant’s arguments, filed 05/21/2026, have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Claims 1-20 are the current claims hereby under examination.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 06/23/2026 has been entered.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Analysis of independent claims 1, 9, and 16:
Step 1 of the subject matter eligibility test (see MPEP 2106.03).
Claim 1 is directed to a computer implemented method, which describes one of the four statutory categories of patentable subject matter, i.e., a method. Claim 9 is directed to a system, which describes one of the four statutory categories of patentable subject matter, i.e., a machine. Claim 17 is directed to a non-transitory computer-program software product, which describes one of the four statutory categories of patentable subject matter, i.e., a machine. Therefore, further consideration is necessary regarding the claims.
Step 2A of the subject matter eligibility test (see MPEP 2106.04).
Prong One: Claims 1, 9, and 16 recite an abstract idea. In particular, the claims generally recite
the following:
converting the at least one breathing audio sample to a breathing spectrogram configured as an image;
processing the image using a trained multi-task convolutional neural network (CNN) to identify image features of the image; and
predicting, using a deep neural network (DNN) layer of the multi-task CNN, a breathing rate and a breathing depth of the user using the image features;
These elements recited in claims 1, 9, and 16 are drawn to an abstract idea since they are directed towards mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III).
“converting the at least one breathing audio sample to a breathing spectrogram configured as an image” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably convert data in one format to another. There is nothing to suggest an undue level of complexity in “converting the at least one breathing audio sample to a breathing spectrogram configured as an image”.
“processing the image using a trained multi-task convolutional neural network (CNN) to identify image features of the image” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably identify image features from the spectrogram. There is nothing to suggest an undue level of complexity in “processing the image using a trained multi-task convolutional neural network (CNN) to identify image features of the image”.
“predicting, using a deep neural network (DNN) layer of the multi-task CNN, a breathing rate and a breathing depth of the user using the image features” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably use the image features from the spectrogram to determine a breathing rate/depth. There is nothing to suggest an undue level of complexity in “predicting, using a deep neural network (DNN) layer of the multi-task CNN, a breathing rate and a breathing depth of the user using the image features”.
Examiner acknowledges that specific, complex algorithms performed by neural networks cannot be performed in the human mind, using pen and paper or a generic computer. However, the abstract ideas identified above are only recited to be performed “using” a trained multi-task CNN or a deep NN layer of the trained multi-task CNN. Without the specifics of how the neural networks perform the processing (e.g., the algorithms they use), the abstract idea remains broad with regard to the use of neural networks. Thus, the claims are still drawn to an abstract idea despite the recitation of neural networks.
Prong Two: Claims 1, 9, and 16 do not recite additional elements that integrate the exception into a practical application. Therefore, the claims are "directed to" the abstract idea. The additional elements merely:
Recite the words "apply it" or an equivalent with the judicial exception, or include instructions to implement the abstract idea on a computer, or merely use the computer as a tool to perform the abstract idea (e.g., “a processing device” (claim 9) and "wherein the DNN layer is separately trained using one or more breathing audio datasets" (claims 1, 9, and 16)) and
Add insignificant extra-solution activity (the pre-solution activity of: using generic data gathering components (e.g., "obtaining at least one breathing audio sample of a user captured using earbuds worn by the user" (claims 1, 9, and 16)); the post-solution activity of: (e.g. “outputting the breathing rate and the breathing depth of the user” (claims 1, 9, and 16))).
As a whole, the additional elements merely serve to gather information to be used by the abstract idea, while generically implementing it on a computer. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing performed remains in the abstract realm, i.e., the result is not used for a treatment. No improvement to the technology is evident. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Step 2B of the subject matter eligibility test (see MPEP 2106.05).
Claims 1, 9, and 16 do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) for the same reasons as described above. E.g., all elements are directed to implementing the abstract ideas on generic processing components, the pre-solution activity of using generic data-gathering components, and generic post-solution activities, which merely facilitate the abstract idea.
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example, “a processing device” as disclosed in the Applicant’s specification “The processor 120 includes one or more processing devices, such as one or more microprocessors, microcontrollers, digital signal processors (DSPs), application specific integrated circuits (ASICs), or field programmable gate arrays (FPGAs). In some embodiments, the processor 120 includes one or more of a central processing unit (CPU), an application processor (AP), a communication processor (CP), or a graphics processor unit (GPU). The processor 120 is able to perform control on at least one of the other components of the electronic device 101 and/or perform an operation or data processing relating to communication or other functions. As described in more detail below, the processor 120 may perform one or more operations for deep audio spectral processing for respiration rate and depth estimation using smart earbuds.” (Paragraph 0038). “Smart earbuds” as disclosed in Applicant’s specification “The proliferation of multi-modal, sensor-equipped, smart earbuds among the general population has made such earbuds suitable for in-ear health monitoring and a minimally-invasive, wearable device for accurate, continuous, and passive respiration rate and depth monitoring. For example, audio sensing from earbuds is an effective mechanism for estimating respiration rate and respiration depth. Earbuds, when worn, reside in close proximity to the respiratory tracts and can capture clear breathing sounds propagated internally through the human body” (Paragraph 0032).
These elements do not qualify as significantly more because these limitations are simply appending well understood, routine, and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int'/, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well understood, routine and conventional activity previously known in the industry (see Electric PowerGroup, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int'/, 110 USPQ2d 1976 (2014); SAP Am. v. lnvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements include a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Analysis of dependent claims 2-8, 10-15, and 17-20:
Claims 6-7 and 14-15 recite mental steps that may be performed in the human mind with the aid of pen and paper or a generic computer, which add to the abstract idea. The mental steps are identified as:
determining an ADL of the user associated with the at least one breathing audio sample; selecting one of the multiple CNNs in the CNN pool as the trained multi-task CNN based on the ADL of the user (claims 6 and 14); and
wherein the ADL of the user is determined using at least one of: motion data captured using the earbuds; and motion data captured using a smart watch worn by the user (claims 7 and 15).
Claims 2-3, 5, 10-11, 13, 17-18, and 20 recite steps that are mathematical concepts, which add to the abstract idea. The mathematical concepts are identified as:
wherein the multi-task CNN is trained using multi-task learning in which the multi-task CNN is trained on multiple objective tasks in parallel, the multiple objective tasks comprising (i) a regression task associated with respiration rate and (ii) a classification task associated with respiration depth (claims 2, 10, and 17);
wherein the multi-task learning uses a hybrid loss function that combines a regression loss for the regression task and a classification loss for the classification task (claims 3, 11, and 18); and
wherein an architecture of each of the multiple CNNs in the CNN pool is determined using a CNN neural architecture grid search during training of the multiple CNNs (claims 5, 13, and 20).
Claims 4, 8, 12, and 19 recite limitations in addition to the abstract idea: they merely
Further describe the abstract idea (“wherein the breathing spectrogram comprises a mel-spectrogram” (claim 8) and “wherein the multi-task CNN comprises one of multiple CNNs in a CNN pool, each of the multiple CNNs in the CNN pool associated with a specific activity of daily living (ADL)” (claims 4, 12, and 19; As the multi-task CNN is merely “used” for the processing/predicting steps of the independent claims (i.e., the abstract idea), this limitation merely further defines the abstract idea of which CNN is “used” for the processing/predicting steps)).
Taken alone or in combination, the additional elements do not integrate the judicial exception into a practical application at least because the abstract idea is not applied, relied on, or used in a meaningful way. The additional elements do not add anything significantly more than the abstract idea. The collective functions of the additional elements merely provide computer/electronic implementation and processing, and no additional elements beyond those of the abstract idea. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements improves the functioning of a computer, output device, improves technology other than the technical field of the claimed invention, etc. The result of the abstract idea does not cause the computing device and/or application to perform differently.
Therefore, claims 1-20 are rejected as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, and Musgrove (US 20200357518), further evidenced by Kogure (US 20200029832).
Regarding claim 1, Kumar discloses a method comprising:
obtaining at least one breathing audio sample of a user captured using earbuds worn by the user (Section II, paragraphs 1-2, “… obtain breath samples of varying intensities … All data was recorded using microphone-enabled, near-range headphones, specifically Apple’s AirPods”);
converting the at least one breathing audio sample to a breathing spectrogram configured as an image (Figs. 2A-B);
processing the image (Fig. 5 “feature extraction” image, wherein the box labeled “feature extraction” contains a breathing spectrogram image; Section II. Data, wherein the data collected is processed into a breathing spectrogram as illustrated in Figs. 2A-B. The inhalation signals from the breathing spectrograms are useful to differentiate between different types of breathing, and these observations support use of the spectrograms in the later section’s data processing described in Section IV) using a trained multi-task convolutional neural network (CNN) to identify image features of the image (Section IVb, paragraph 2, “The model, depicted in Figure 5, was trained with multiple and objective functions as a multi-task learning (MTL) network, where the tasks were RR estimation, heavy breathing detection, and noise detection”);
predicting, using a deep neural network (DNN) layer of the multi-task CNN, a breathing rate and a breathing depth of the user using the image features (Fig. 5, outputs of respiration rate and heavy breathing),
outputting the breathing rate and the breathing depth of the user (Section IVb, paragraph 2, “The model, depicted in Figure 5, was trained with multiple objective functions as a multi-task learning (MTL) network, where the tasks were RR estimation, heavy breathing detection, and noise detection, represented by the three outputs mentioned above”).
Kumar discloses multiple layers of the models tested (Page 4, right column) and Kogure shows that a neural network with an intermediate layer of a plurality of layers is a deep neural network and is trained by deep learning (Paragraph 0129). Kumar fails to disclose training a layer of the neural network separately.
Kumar, Kogure, and Musgrove are in the same field of using neural networks and machine learning models on patient data. Musgrove teaches a technique for preparing data for use in AI-based arrhythmia detection, wherein a neural network trains the intermediate layers separately then the subsequent layers of the neural network which accelerates training (Paragraph 0137). As Kumar is concerned with training neural networks for determining respiration rate from spectrogram image data, Musgrove teaches a faster method of training a neural network by training the different layers. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kumar and Kogure to train a layer of the neural network separately as taught by Musgrove to accelerate training of the neural network.
Regarding claim 2, Kumar as modified further discloses wherein the multi-task CNN is trained using multi-task learning in which the multi-task CNN is trained on multiple objective tasks in parallel, the multiple objective tasks comprising
a regression task associated with respiration rate (Section IV, paragraph 1, “The learning network, an end-to-end model, is not standard in that it simultaneously encompasses both regression and classification tasks.”; Section IVb, paragraph 3, “The individual losses from each task are given below, where concordance correlation coefficient (CCC) loss is used on the RR and RC outputs”) and
a classification task associated with respiration depth (Section IVb, paragraph 3, “… and weighted cross-entropy (CE) loss is used on the breath and noise classification tasks”).
Regarding claim 3, Kumar as modified further discloses wherein the multi-task learning uses a hybrid loss function that combines a regression loss for the regression task and a classification loss for the classification task (Section IVb, paragraph 4, “Additionally, a focal loss term was used for the breath detection task, and a convex mixture of all the losses after dynamic weight averaging, with weighting factor λ, was used as the MTL loss to train the network shown in Figure 5”).
Claims 4-6 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, Musgrove (US 20200357518), and Kogure (US 20200029832) as applied to claim 1 above, and further in view of Laredo et. al. (“Automatic model selection for fully connected neural networks”), hereinafter Laredo.
Regarding claims 4-6, Kumar as modified discloses the multi-task CNN associated with a workout task as above. While Kumar discusses training different convolutional neural network models (Section IVb, paragraphs 1 and 7) based on a workout training dataset, Kumar fails to disclose wherein the multi-task CNN comprises one of multiple CNNs in a CNN pool, each of the multiple CNNs in the CNN pool associated with a specific activity of daily living.
Regarding the limitations of claims 5-6, Kumar as modified further discloses determining that the participants are performing a workout during data collection (Section II, paragraphs 3-4; Section III, paragraph 1) and processes the data using a neural network trained on similar workout training data (Section II, paragraphs 5-6). Kumar as modified fails to disclose, choosing a neural network from a neural network pool and wherein an architecture of the CNNs is determined using a CNN neural architecture grid search.
Kumar, Kogure, Musgrove, and Laredo are in the same field of using neural networks and machine learning models on patient data. Laredo teaches an algorithm for choosing one neural network from a selection of many neural networks in order to find the optimal neural network for a given dataset (Section 1, paragraph 6), wherein an architecture of each of the multiple CNNs in the CNN pool is determined using a CNN neural architecture grid search during training of the multiple CNNs (Section 2, paragraph 1; Section 4, paragraphs 2-6). Kumar compares the performance of various neural networks for determining respiration rate (see Fig. 6), and Laredo teaches choosing one of many neural networks that is an optimal neural network based on the dataset. Kumar would benefit from this teaching as the optimal neural network can be chosen based on the obtained dataset. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kumar, Kogure, and Musgrove to incorporate the CNN pool and architecture grid search of Laredo in order to find the optimal neural network for a given dataset.
Claim 7 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, Musgrove (US 20200357518), Kogure (US 20200029832), and Laredo et. al. (“Automatic model selection for fully connected neural networks”), hereinafter Laredo, as applied to claim 6 above, and further in view of Wisbey (US 20160051185).
Regarding claim 7, while Kumar as modified discloses analyzing the breathing data by intensity caused by working out (Page 2, section II, left column), Kumar as modified fails to disclose determining the activity of a user through motion data.
Kumar, Kogure, Musgrove, Laredo, and Wisbey are in the same field of measuring patient data. Wisbey teaches a system for monitoring user activity through an earphone, wherein the earphone tracks user activity through a motion sensor (Paragraph 0089). One of ordinary skill in the art would have been motivated in applying this known method of identifying a user activity via motion data collected by an earpiece in Wisbey to the earbuds of Kumar as modified, and the results of tracking user activity would have been predictable to one of ordinary skill in the art. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kumar, Kogure, Musgrove, and Laredo to incorporate the motion sensor of Wisbey, and the results of tracking user activity would have been predictable to one of ordinary skill in the art.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, Musgrove (US 20200357518), and Kogure (US 20200029832) as applied to claim 1 above, and further in view of Kariyawasan (WO 2020141999).
Regarding claim 8, while Kumar as modified discusses mel-filterbank energies of the breathing data (Section IV, paragraph 1), Kumar as modified fails to explicitly disclose wherein the spectrogram is a mel-spectrogram.
Kumar, Kogure, Musgrove, and Kariyawasan are in the same field of measuring patient data. Kariyawasan teaches a system for monitoring breathing of a patient from an earpiece (Fig. 1, earpiece breath monitoring device 110), wherein a sound classification model generates a mel-spectrogram from the input breath sound signal (Page 12, lines 1-4 ; Fig. 7) and a neural network is trained on the mel-spectrogram (Page 12, lines 6-15). As Kumar is concerned with monitoring the breathing of a patient and using mel-filterbank energies, Kariyawasan introduces a method of generating a mel-spectrogram from the breath sound signals to train a neural network for determining breathing data. Kariyawasan discusses that mel-spectrograms are used to identifying inhaling and exhaling sounds, and Kumar could benefit from the mel-spectrograms to determine breathing parameters. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the method of Kumar and Musgrove with using a mel-spectrogram of Kariyawasan because it is a substitution of one known spectrogram for a known mel-spectrogram to yield the predictable result of training a neural network and determine breathing data parameters.
Claims 9-11 and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, Musgrove (US 20200357518), Kogure (US 20200029832), and Kariyawasan (WO 2020141999).
Regarding claims 9 and 16, Kumar discloses:
obtain at least one breathing audio sample of a user captured using earbuds worn by the user (Section II, paragraphs 1-2, “… obtain breath samples of varying intensities … All data was recorded using microphone-enabled, near-range headphones, specifically Apple’s AirPods”);
convert the at least one breathing audio sample to a breathing spectrogram configured as an image (Figs. 2A-B);
process the image (Fig. 5 “feature extraction” image, wherein the box labeled “feature extraction” contains a breathing spectrogram image; Section II. Data, wherein the data collected is processed into a breathing spectrogram as illustrated in Figs. 2A-B. The inhalation signals from the breathing spectrograms are useful to differentiate between different types of breathing, and these observations support use of the spectrograms in the later section’s data processing described in Section IV) using a trained multi-task convolutional neural network (CNN) to identify image features of the image (Section IVb, paragraph 2, “The model, depicted in Figure 5, was trained with multiple and objective functions as a multi-task learning (MTL) network, where the tasks were RR estimation, heavy breathing detection, and noise detection”);
predict, using a deep neural network (DNN) layer of the multi-task CNN, a breathing rate and a breathing depth of the user using the image features (Fig. 5, outputs of respiration rate and heavy breathing,
output the breathing rate and the breathing depth of the user (Section IVb, paragraph 2, “The model, depicted in Figure 5, was trained with multiple objective functions as a multi-task learning (MTL) network, where the tasks were RR estimation, heavy breathing detection, and noise detection, represented by the three outputs mentioned above”).
Kumar discloses multiple layers of the models tested (Page 4, right column) and Kogure shows that a neural network with an intermediate layer of a plurality of layers is a deep neural network and is trained by deep learning (Paragraph 0129). While Kumar discusses processing the data (Section IV), Kumar fails to explicitly disclose any processing/memory structure configured to perform the method. Kumar also fails to disclose training a layer of the neural network separately.
Kumar, Kogure, and Kariyawasan are in the same field of measuring patient data. Kariyawasan teaches a processor and storage device with computer executable instructions, which Kariyawasan discusses is useful to carry out the method of monitoring breathing signals (Page 3, lines 20-26). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the device of Kumar and Kogure to incorporate the processor and storage device of Kariyawasan to carry out the method.
Kumar, Kogure, Kariyawasan, and Musgrove are in the same field of using neural networks and machine learning models on patient data. Musgrove teaches a technique for preparing data for use in AI-based arrhythmia detection, wherein a neural network trains the intermediate layers separately then the subsequent layers of the neural network which accelerates training (Paragraph 0137). As Kumar is concerned with training neural networks for determining respiration rate from spectrogram image data, Musgrove teaches a faster method of training a neural network by training the different layers. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kumar, Kogure, and Kariyawasan to train a layer of the neural network separately as taught by Musgrove to accelerate training of the neural network.
Regarding claims 10 and 17, Kumar as modified further discloses wherein the multi-task CNN is trained using multi-task learning in which the multi-task CNN is trained on multiple objective tasks in parallel, the multiple objective tasks comprising
a regression task associated with respiration rate (Section IV, paragraph 1, “The learning network, an end-to-end model, is not standard in that it simultaneously encompasses both regression and classification tasks.”; Section IVb, paragraph 3, “The individual losses from each task are given below, where concordance correlation coefficient (CCC) loss is used on the RR and RC outputs”) and
a classification task associated with respiration depth (Section IVb, paragraph 3, “… and weighted cross-entropy (CE) loss is used on the breath and noise classification tasks.).
Regarding claims 11 and 18, Kumar as modified further discloses wherein the multi-task learning uses a hybrid loss function that combines a regression loss for the regression task and a classification loss for the classification task (Section IVb, paragraph 4, “Additionally, a focal loss term was used for the breath detection task, and a convex mixture of all the losses after dynamic weight averaging, with weighting factor λ, was used as the MTL loss to train the network shown in Figure 5”).
Claims 12-14 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, Musgrove (US 20200357518), Kogure (US 20200029832), and Kariyawasan (WO 2020141999) as applied to claims 9 and 16 above, and further in view of Laredo et. al. (“Automatic model selection for fully connected neural networks”), hereinafter Laredo.
Regarding claims 12-14 and 19-20, Kumar as modified discloses the multi-task CNN associated with a workout task as above. While Kumar discusses training different convolutional neural network models (Section IVb, paragraphs 1 and 7) based on a workout training dataset, Kumar as modified fails to disclose wherein the multi-task CNN comprises one of multiple CNNs in a CNN pool, each of the multiple CNNs in the CNN pool associated with a specific activity of daily living.
Regarding the limitations of claims 13-14 and 19-20, Kumar as modified further discloses determining that the participants are performing a workout during data collection (Section II, paragraphs 3-4; Section III, paragraph 1) and processes the data using a neural network trained on similar workout training data (Section II, paragraphs 5-6). Kumar as modified fails to disclose choosing a neural network from a neural network pool and wherein an architecture of the CNNs is determined using a CNN neural architecture grid search.
Kumar, Kogure, Musgrove, and Laredo are in the same field of using neural networks and machine learning models on patient data. Laredo teaches an algorithm for choosing one neural network from a selection of many neural networks in order to find the optimal neural network for a given dataset (Section 1, paragraph 6), wherein an architecture of each of the multiple CNNs in the CNN pool is determined using a CNN neural architecture grid search during training of the multiple CNNs (Section 2, paragraph 1; Section 4, paragraphs 2-6). Kumar compares the performance of various neural networks for determining respiration rate (see Fig. 6), and Laredo teaches choosing one of many neural networks that is an optimal neural network based on the dataset. Kumar would benefit from this teaching as the optimal neural network can be chosen based on the obtained dataset. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kumar, Kogure, and Musgrove to incorporate the CNN pool and architecture grid search of Laredo in order to find the optimal neural network for a given dataset.
Claim 15 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar et. al. (“Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones”), hereinafter Kumar, Musgrove (US 20200357518), Kogure (US 20200029832), Kariyawasan (WO 2020141999), and Laredo et. al. (“Automatic model selection for fully connected neural networks”), hereinafter Laredo, as applied to claim 14 above, and further in view of Wisbey.
Regarding claim 15, Kumar as modified fails to disclose determining the activity of a user through motion data.
However, Wisbey teaches a system for monitoring user activity through an earphone, wherein the earphone tracks user activity through a motion sensor (Paragraph 0089). One of ordinary skill in the art would have been capable of applying this known method of identifying a user activity via motion data collected by an earpiece in Wisbey to the earbuds of Kumar and the results of tracking user activity would have been predictable to one of ordinary skill in the art. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kumar, Musgrove, and Laredo to incorporate the motion sensor of Wisbey, and the results of tracking user activity would have been predictable to one of ordinary skill in the art.
Response to Arguments
Applicant’s arguments, see pages 8-11, filed 05/21/2026, with respect to the rejection(s) of claims 1-20 under 35 U.S.C. §103 have been fully considered but are not persuasive.
Applicant asserts that Kumar discloses non-image data processing, and does not use image processing to predict a breathing rate and breathing depth. Examiner disagrees.
As described in the rejection above, Kumar discusses in Section II that normal and heavy breathing has observed differences in their respective spectrograms seen in Figs. 2A-B. Kumar states that these temporal spectral representations are used in the model that’s described in Section IV. Additionally, Fig. 5 of Kumar explicitly shows a spectrogram created from the audio data that is input into a neural network. As such, Kumar reads on the claim limitation of processing an image which contains breathing audio data as a breathing spectrogram.
The rejection above has been updated to reflect the amendments.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Ahn et. al. (“Deep Elastic Networks with Model Selection for Multi-Task Learning”) teaches a method of neural network model selection based on the input.
Jacome et. al. (“Convolutional Neural Network for Breathing Phase Detection in Lung Sounds”) teaches using spectrograms as a feature input into a CNN to detect inspiration and expiration phases from lung sound recordings (see Figs. 1-2, sections 2.3.2 and 2.3.3).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NOAH MICHAEL HEALY whose telephone number is (703)756-5534. The examiner can normally be reached Monday - Friday 8:30am - 5:30pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jason Sims can be reached at (571)272-7540. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/NOAH M HEALY/Examiner, Art Unit 3791
/JASON M SIMS/Supervisory Patent Examiner, Art Unit 3791
Prosecution Insights