DETAILED ACTION
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 .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claims 1-20, the use of the terms “embedding”, “embedding space”, etc., and “encoder” render the claims indefinite. More language and details are required to define the encoder and embedding space, as one of ordinary skill in the art of diagnostics would not be familiar with these terms.
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 non-statutory subject matter of abstract ideas under the mental processes and mathematical concepts groupings, without significantly more.
The framework for establishing a prima facie case of lack of subject matter eligibility requires that the Examiner determine: (1) Does the claim fall within the four categories of patent eligible subject matter; (2a) Prong 1: Does the claim recite an abstract idea, law of nature, or natural phenomenon and (2a) Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application; and (2b) Does the claim recite additional elements that amount of significantly more than the judicial exception.
Step (1)
The claimed invention in claims 1-20 are directed to systems and methods, and thus, the claims all fall under one of the four patent eligible categories.
Step (2a) Prong 1 (Judicial Exception)
Regarding claims 1-20, the recited steps are directed towards mental processes of performing concepts in a human mind or by a human using a pen and paper and utilizing mathematical concepts (See MPEP 2106.04(a)(2) subsection[s (I) and] (III)).
Independent claims 1, 10 and 19 recite:
accessing a sensor signal from each of one or more non-contact sensors in an environment of a user;
for each sensor signal, extracting one or more physiological features of the user from that sensor signal; and
for each sensor signal, embedding, by a trained encoder dedicated to the non-contact sensor corresponding to that sensor signal, the one or more physiological features extracted from that sensor signal into a joint sleep-stage embedding space;
determining, based on a final embedding in the joint sleep-stage embedding space that is based at least in part on the embedded physiological features, a similarity between the final embedding and each of a plurality of sleep-stage embeddings, each sleep-stage embedding identifying a predetermined sleep stage of a person; and
predicting, based on each of the similarities between the final embedding and each of the plurality of sleep-stage embeddings, a sleep stage of the user.
Under the broadest reasonable interpretation, these limitations require extracting features from a non-contact sensor, embedding the features into an embedding space, determining similarities of the embedded features to sleep stage embeddings, and predicting the user’s sleep stage. These limitations are processes that, as drafted, cover that which can be wholly performed in a person’s mind via a series of mental observations and judgements and utilizing mathematical concepts. In particular, a person can analyze a signal, extract relevant features of the signal, determine a mathematical relationship/similarity between the features and a reference feature, and then predict the sleep stage of the user based on how similar the features are to a reference. These are data gathering and processing steps (accessing, extracting, determining, predicting) that reflect mental processes and mathematical concepts.
Accordingly, claims 1-20 are directed to a judicial exception including one or more abstract ideas, specifically mental processes and mathematical concepts.
Independent claims 1, 10 and 19 recite the corresponding apparatus associated with the system/method, including a non-contact sensor and processor. Under the broadest reasonable interpretation, these claims also recite a judicial exception including one or more abstract ideas under the mental processes and mathematical concepts buckets.
The additional limitations in dependent claims are:
Claims 2, 11, 20: sensor is in AC or TV
Claims 3, 12: sensor is a millimeter wave radar sensor
Claims 4, 13: multiple sensors, using an AI fusion model
Claims 5, 14: training of the AI fusion model
Claims 6, 15: clustering
Claims 7, 16: training of the encoder
Claims 8, 17: repeating steps to determine sleep quality
Claims 9, 18: additional types of sensors
These limitations comprise additional abstract ideas and/or further limit the abstract ideas of claims 1, 10, and 19.
Step (2a) Prong 2 (Integration into a Practical Application)
This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. MPEP 2106.04(d).
For claims 1-20, the judicial exception is not integrated into a practical application.
Regarding claims 1-20, the additional element of a non-contact sensor amounts to recitation of a generic remote sensor. Merely stating that the abstract idea will be for "predicting a sleep stage" is an instruction to apply the abstract idea in a particular technological environment. As in Alice Corp. v. CLS Bank, 573 U.S. 208, 223 (2014), limiting an abstract idea to a field of use or adding generic hardware does not integrate the exception into a practical application.
Regarding claims 10-20, the additional element of a processor amounts to recitation of a generic processor. This additional element merely defines the field of use of the current claim. This additional element does not practically integrate the judicial exception because this element does not provide improvements to the functioning of a computer or to any the technical field under MPEP 2106.05(a). Furthermore, when the claims, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it is still in the mental processes grouping unless the claim limitation cannot practically be performed in the mind. Likewise, performance of a claim limitation using generic computer components does not preclude the claim limitation from being in the mental processes grouping.
Step (2b) (Inventive Concept)
The claims also do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the judicial exception into a practical application, the additional elements of a non-contact sensor and processor in the field of sleep monitoring are well-understood, routine and conventional activities previously known in the industry as indicated in the following reference:
Zhong et al. (US Pre-Grant Publication 2021/0093203) teaches that using continuous wave radar systems to monitor vital signs is a conventional method (see [0067]).
Franceschetti et al. (US Pre-Grant Publication 2020/0397379) teaches a conventional microprocessor (see [0170]).
Dependent claims 2, 11, and 20 recite a smart TV, which is also recited at a high level of generality and is considered to be well-known, routine and conventional in the art as indicated in the following reference:
Trepanier et al. (US Pre-Grant Publication 2025/0098983) teaches conventional smart TVs (see [0190]).
Accordingly, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Claims 1-20 are thus rejected under 35 USC 101 for reciting patent-ineligible subject matter- abstract ideas and mathematical concepts.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1, 4-10, and 13-19 are rejected under 35 U.S.C. 103 as being unpatentable over Khan et al. (US Pre-Grant Publication 2022/0378346), hereinafter ‘Khan’, in view of Shen et al. (“LGSleepNet: An Automatic Sleep Staging Model Based on Local and Global Representation Learning”, IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-14), hereinafter ‘Shen’.
Regarding claim 1, Khan teaches a method comprising:
accessing a sensor signal (receive wave 102wr, Fig. 1) from each of one or more non-contact sensors (mmWave mapping device 102, Fig. 1) in an environment of a user (physical space 104, Fig. 1);
for each sensor signal, extracting one or more physiological features of the user from that sensor signal (blocks 320-330, Fig. 3, [0079], determining vital signs of the person based on waveforms); and
predicting a sleep stage of the user (Block 340, Fig. 3, [0080], sleep phase classification).
Khan discloses a sleep phase classification module (see block 340, Fig. 3, [0082]) and identifying and recognizing patterns (see [0083]), but does not teach the additional limitations of claim 1.
Shen teaches an automatic sleep staging model (abstract, Fig. 1), further comprising:
for each sensor signal, embedding, by a trained encoder dedicated to the non-contact sensor corresponding to that sensor signal, the one or more physiological features extracted from that sensor signal into a joint sleep-stage embedding space (III Method, B Asymmetric Siamese Neural Network, 2 Global Feature Extraction: "After the tokens are divided, all the tokens are passed to a linear encoding layer for encoding to obtain the corresponding encoding feature set", Fig. 1, global feature extraction);
determining, based on a final embedding in the joint sleep-stage embedding space that is based at least in part on the embedded physiological features, a similarity between the final embedding and each of a plurality of sleep-stage embeddings, each sleep-stage embedding identifying a predetermined sleep stage of a person (III Method, C DAOF Block: "After obtaining the weight matrix, the weight and the embedding feature Es are performed column-wise in the weighted sum operation to obtain the final fusion feature”); and
predicting, based on each of the similarities between the final embedding and each of the plurality of sleep-stage embeddings, a sleep stage of the user ((III Method, C DAOF Block: “After the fusion feature Ff is obtained, it can be input into the subsequent classification layer for ASS", Fig. 1, sleep staging).
It would have been prima facie obvious before the effective filing date of the claimed invention to have modified Khan to incorporate the teachings of Shen to include embedding features, determining a similarity between embeddings and predicting a sleep stage based on embeddings similarities. Doing so would allow for an extraction method to more accurately describe and distinguish different sleep stages, as recognized by Shen (VI Discussion, A Local and Global Representation Learning).
Regarding claim 10, see above rejection of similarly worded claim 1. Khan further teaches:
A system (mmWave mapping system 100, Fig. 5) comprising:
One or more non-contact sensors in an environment of a user (mmWave mapping device 102, Fig. 1); and
one or more non-transitory computer readable storage media storing instructions (memory 506, Fig. 5); and
one or more processors coupled to the one or more non-transitory computer readable storage media and operable to execute the instructions (CPU 504, Fig. 5).
Regarding claim 19, see above rejections of similarly worded claims 1 and 10.
Regarding claims 4 and 13, Khan and Shen teach the system/method of claims 1 and 10. Khan teaches the system/method further comprising:
the one or more non-contact sensors comprise a plurality of non-contact sensors ([0034], one or more mmWave sensors).
Khan teaches an AI combined learning module that learns two features (see [0082]), but does not specifically teach an AI fusion model.
Shen teaches an automatic sleep staging model (abstract, Fig. 1), further comprising:
inputting, to a trained AI fusion model, each of the embeddings (Fig. 1, feature fusion, deep adaptive orthogonal fusion); and
generating, by the trained AI fusion model and based on each of the embeddings, the final embedding (III Method, C DAOF Block: "After obtaining the weight matrix, the weight and the embedding feature Es are performed column-wise in the weighted sum operation to obtain the final fusion feature").
It would have been prima facie obvious before the effective filing date of the claimed invention to have modified Khan to incorporate the teachings of Shen to include an AI fusion model to generate a final embedding. Doing so would improve the compatibility of the fusion between the two types of features, as recognized by Shen (III Method, C DAOF Block).
Regarding claims 5 and 14, Khan and Shen teach the system/method of claims 4 and 13. Khan teaches the training of an AI model (see [0087]), but does not specifically teach the training is for an AI fusion model and is based on a contrastive loss between embeddings.
Shen teaches an automatic sleep staging model (abstract, Fig. 1), further comprising:
wherein the trained Al fusion model is trained based on a contrastive loss between (1) a plurality of training final embeddings output by the Al fusion model and (2) the sleep-stage embeddings (Fig. 1, error metric, weighted polynomial cross entropy loss).
It would have been prima facie obvious before the effective filing date of the claimed invention to have modified Khan to incorporate the teachings of Shen to include an AI fusion model trained based on contrastive loss. Doing so would improve the classification performance of the model, as recognized by Shen (III Method, D WPCE Loss).
Regarding claims 6 and 15, Khan and Shen teach the system/method of claims 1 and 10. Khan teaches the system/method further comprising:
wherein the joint sleep-stage embedding space contains a plurality of clusters, each cluster corresponding to one of the predetermined sleep stages ([0082], clustering).
Regarding claims 7 and 16, Khan and Shen teach the system/method of claims 6 and 15. Khan teaches the system/method further comprising:
wherein each trained encoder is trained by:
collecting, for the non-contact sensor corresponding to that encoder, a plurality of training data and corresponding ground-truth sleep-stage labels ([0084], model is trained based on labels for features).
Khan teaches the training of an AI model and supervised learning (see [0086-0087]), but does not specifically teach updating based on the contrastive loss that aligns the embeddings.
Shen teaches an automatic sleep staging model (abstract, Fig. 1), further comprising:
embedding, by the encoder, the training data in the embedding space; and
updating the encoder based on a contrastive loss that aligns the encoder embeddings with the embedded corresponding ground-truth sleep-stage labels (Fig. 1, back propagation, error metric, weighted polynomial cross entropy loss, IV Experiments, D Hyperparameter Optimization, “During the training process, a novel Lion optimizer is adopted to update and optimize the network weights”).
It would have been prima facie obvious before the effective filing date of the claimed invention to have modified Khan to incorporate the teachings of Shen to include updating based on the contrastive loss that aligns the embeddings. Doing so would enable hyperparameter optimization, training, and evaluation of the deep learning model, as recognized by Shen (IV Experiments, D Hyperparameter Optimization).
Regarding claims 8 and 17, Khan and Shen teach the system/method of claims 1 and 10. Khan teaches the system/method further comprising:
repeating the steps of Claim 1 over a period of time to generate a plurality of predicted sleep stages of the user for the period of time ([0090], sleep quality classification is based on sleep phase classifications at two times); and
determining, based the plurality of predicted sleep stages of the user, a sleep quality of the user for the period of time (block 350, Fig. 3, sleep quality classification).
Regarding claims 9 and 18, Khan and Shen teach the system/method of claims 1 and 10. Khan teaches the system/method further comprising:
wherein the one or more non-contact sensors comprise one or more of a radar, a microphone, a sonar, a thermometer (room temperature 344, Fig. 3), a humidity sensor (room humidity 342, Fig. 3), or a pressure sensor ([0034], mmWave sensor is radar-type sensor, similar to sonar technology, [0080], second sensor can include microphone, thermometer, humidity).
Claims 2-3, 11-12, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Khan et al. (US Pre-Grant Publication 2022/0378346) in view of Shen et al. (“LGSleepNet: An Automatic Sleep Staging Model Based on Local and Global Representation Learning”, IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-14), further in view of Tiron et al. (US Pre-Grant Publication 2023/0190140), hereinafter ‘Tiron’.
Regarding claims 2, 11, and 20, Khan and Shen teach the system/method of claims 1, 10, and 19. Khan teaches that the system may be integrated into existing monitoring technology (see [0007]), but does not specifically teach that one of the sensors is part of an AC or smart TV.
Tiron teaches a method for monitoring sleep disordered breathing using non-contact sensing (abstract), further comprising:
wherein at least one of the one or more non-contact sensors is part of (1) an air conditioner or (2) a smart TV ([0195], sensing technologies executed by processor in smart TV that may be configured with speaker/microphone for SONAR).
It would have been prima facie obvious before the effective filing date of the claimed invention to have modified Khan and Shen to incorporate the teachings of Tiron to include a sensor as part of an AC or smart TV. Doing so would provide an efficient screening apparatus/removes the need for separate tools to analyze data, as recognized by Tiron [0256].
Regarding claims 3 and 12, Khan, Shen, and Tiron teach the system/method of claims 2 and 11. Khan teaches the system/method further comprising:
wherein the at least one non-contact sensor comprises a millimeter-wave radar sensor (mmWave mapping device 102, Fig. 1, [0035] millimeter waves transmitted and received by sensor).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ELIZABETH L OKONAK whose telephone number is (571)272-1594. The examiner can normally be reached Monday-Friday 8-5.
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, Benjamin Klein can be reached at (571) 270-5213. 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.
/E.L.O./Examiner, Art Unit 3792
/SHIRLEY X JIAN/Primary Examiner, Art Unit 3792
Prosecution Insights