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 Objections
Claims 14-19 are rejected to because of the following informalities:
Claims 14-19 recite “further cause the system to” however it is noted that the system is not previously recited as being caused to perform steps, rather claim 13 recites “configuring the one or more processors to”. Examiner recommends amending the claims to recite “further configuring the one or more processors to” or “cause the one or more processors to” for enhanced clarity as to which element of the system is performing the functions rected. Appropriate correction is required.
Claim Interpretation
Claim 4 recites the limitation “to have a mean of zero and a standard deviation of 1”. Examiner notes that the limitation is directed towards intended use, where a limitation directed towards intended use must result in a structural difference between the prior art and the claimed invention in order to distinguish over the prior art. The prior art structure/method must merely be capable of being used “to have a mean of zero and a standard deviation of 1” in order to read on the claimed invention.
Claims 7 and 16 recites the limitation “to obtain a predicted fatigue level, the predicted fatigue level including an odds ratio and a probability of experiencing a change in fatigue level”. Examiner notes that the limitation is directed towards intended use, where a limitation directed towards intended use must result in a structural difference between the prior art and the claimed invention in order to distinguish over the prior art. The prior art structure/method must merely be capable of being used “to obtain a predicted fatigue level including an odds ratio and a probability of experiencing a change in fatigue level” in order to read on the claimed invention.
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 in the form of an abstract idea without significantly more.
In a test for patent subject matter eligibility, the claims pass Step 1 (see 2019 Revised Patent Subject Matter Eligibility), as they are related to a process, machine, manufacture, or composition of matter.
When assessed under Step2A, Prong I, Independent claims 1, 13, and 20 are found to recite a judicial exception (i.e. abstract idea). In this instance, claims 1, 13, and 20 recite the limitations “obtain/ing a pair of valid (PPG) snippets from a PPG signal”, “extract/ing a plurality of PPG features for each valid PPG snippet fo the pair of valid PPG snippets”, “extract/ing a plurality of pairwise features from the plurality of PPG features for each valid PPG snippet”, “predict/ing a fatigue level for the user based on the pairwise features”. The cited limitation(s), under their broadest reasonable interpretation, encompass a mental process (i.e. abstract idea) of obtaining, extracting, and predicting which can be performed in the mind or by a human using a pen and a paper (e.g. observation, evaluation, judgment, opinion). In other words, a person could reasonably obtain a pair of valid PPG snippets from a PPG signal via observation/evaluation of the PPG signal, extract a plurality of PPG features for each valid PPG snippet (where PPG feature can mean a feature that describes a characteristic of a PPG signal which would be readily extractable by a human, examples of such features include but are not limited to heart rate, percentage of N-N interval differences above a threshold, RMS of squared N-N intervals, standard deviation of N-N intervals, etc see [0059] of applicant’s originally filed specification), extract a plurality of pairwise features from the plurality PPG features for each valid PPG snippet via observation/evaluation of the PPG features (where pairwise feature can mean a feature that describes a change in a PPG feature between two time steps which would be readily extractable by a human, examples of such features include but are not limited to mean HR between time step t and time step t-1, changes in N-N intervals or N-N interval differences between time step t and time step t-1, etc. see [0060] of applicant’s originally filed specification), and predict a fatigue level for the user based on the pairwise features via observation/judgment. Examiner notes that with the exception of generic computer-implemented steps (e.g. one or more processors/computing system recited in claim 13 and 20), there is nothing in the claims that preclude the limitation from being performed by a human, mentally or with pen and paper, thus the cited limitation(s) recites a judicial exception (MPEP 2106.04(a)) and the claim must be reviewed under Step 2A, Prong II to determine patent eligibility.
Step 2A, Prong II determines whether any claim recites an additional element that integrates the judicial exception into a practical application. Independent claims recites the following additional element(s):
A PPG sensor (claim 13)
One or more memories storing executable instructions (claim 13)
One or more processors coupled to the PPG sensor and one or more memories, the executable instructions configuring the one or more processors (claim 13)
A non-transitory computer-readable medium having machine-executable instructions stored thereon which, when executed by one or more processors of a computing system cause the computing to… (claim 20)
Obtain/obtaining a pair of valid PPG snippets from a PPG signal (claims 1, 13, and 20)
The additional element(s) in the cited independent claim(s) are not found to integrate the judicial exception into a practical application. In this case, it is noted that the PPG sensor is merely a generic component of a bio-signal measurement system especially in the field of photoplethysmography, the one or more memories/computer-readable medium and processor(s), amount to merely a generic computer for applying the judicial exception, and obtaining a pair of valid PPG snippets is alternatively/additionally considered an additional element which amounts to merely insignificant pre-solution activity of data gathering in the field of photoplethysmography. These elements are seen as adding insignificant extra-solution activity to the judicial exception. They do no more than link the judicial exception to a particular technological environment or field of use. Therefore, under step 2A Prong II the Judicial exception is not integrated into a practical application by additional elements of independent claims 1, 13, and 20 and the claims must be reviewed under Step 2B to determine patent eligibility.
Step 2B determines where a claim amounts to significantly more.
The additional element(s) listed above do not amount to significantly more than the judicial exception. In this instance, as noted above, the additional elements amount to merely generic components of a bio-signal measurement system in the field of photoplethysmography and further amount to mere data gathering. Additionally there is no improvement in the functioning of the computer or technological field, and there is no transformation of subject matter into a different state. Therefore, under Step 2B in a test for patent subject matter eligibility, the judicial exception of the independent claims do not amount to significantly more and the independent claim(s) remain patent ineligible.
Dependent claims 2-12 and 14-19 further limit the abstract idea of independent claims 1 and 13. When analyzed as a whole, these claims are held to be patent ineligible under 35 U.S.C. 101 because the additional recited limitations fail to establish that the claims are not directed towards an abstract idea and do not sufficiently integrate the subject matter into a practical application or recite elements which constitute significantly more than the abstract ideas identified. The dependent claims are directed toward additional elements which encompass abstract ideas
In this instance, dependent claims recite the following limitations:
Extract/ing a pair of raw PPG snippets from the PPG signal (Claims 2 and 14)
Preprocess/ing each raw PPG snippet of the pair of raw PPG snippets to generate a pair of processed PPG snippets (Claims 2 and 14)
Validate/validating each processed PPG snipped of the pair of processed PPG snippets using a trained PPG signal validator to obtain the pair of valid PPG snippets (Claims 2 and 14)
Detect/ing a plurality of peaks in each valid PPG snippet of the of the pair of valid PPG snippets (Claims 3 and 15)
Obtain/ing a plurality of N-N intervals for each valid PPG snippet of the pair of valid PPG snippets based on the respective plurality of peaks (claims 3 and 15)
Extract/ing a plurality of PPG features for each valid PPG snippet of the of the pair of valid PPG snippets based on the respective plurality of N-N intervals (Claims 3 and 15).
building a progressive feature search tree by computing one or more relationships between a respective one or more pairwise features and a respective fatigue level (claims 8 and 17)
classifying the pair of valid PPG snippets (claims 11 and 18)
comparing the fatigue level to a pre-defined criteria (claims 12 and 19)
serving a fatigue alert to the user based on the comparison (claims 12 and 19)
The cited limitation(s), under their broadest reasonable interpretation, encompass mental processes (i.e. abstract idea) which can be performed in the mind or by a human using a pen and a paper (e.g. observation, evaluation, judgment, opinion). In other words, a human could reasonably extract signals, preprocess the signals, validate signals, detect peaks, obtain intervals, extract features, compute relationships between pairwise features and fatigue levels, classify signals, compare a fatigue level to a pre-defined criteria and serve a fatigue alert via observation, evaluation, judgment, and thought. Examiner notes that with the exception of generic computer-implemented steps (e.g. one or more processors), there is nothing in the claims that preclude the limitation from being performed by a human, mentally or with pen and paper, thus the claimed limitation is considered to be directed towards a judicial exception (MPEP 2106.04(a)).
Under Step 2A, Prong II for dependent claims 2-12 and 14-19, present additional elements which only further narrow the judicial exceptions (e.g. claim 2 which recites a trained PPG signal validator amounting to merely a generic computer for applying the judicial exception, preprocessing each raw PPG snippet alternatively/additionally interpreted as an additional element which amounts to merely generic data processing, claim 4 which further narrows the preprocessing to include filtering and normalizing which amount to merely insignificant extra-solution activity, claims 5-6 which further narrow the trained PPG signal validator amounting to merely using a generic computer, claims 7 and 16 which recite merely inputting the pairwise features into a progressive feature search tree amounting to merely inputting data to a generic computer) and provide no additional element which are found to integrate the judicial exception into a practical application.
These dependent claims include no additional claims that are sufficient to amount to significantly more than the judicial exception. Additionally, there is no improvement in the functioning of the computer or technological field, and there is no transformation of subject matter into a different state. As discussed above with respect to integration of the abstract idea into a practical application, the additional claims do not provide any additional elements that would amount to significantly more than the judicial exception. Under Step 2B, these claims are not patent eligible.
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 3, 7, 15-16, and 18 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.
Claims 3 and 15 recite the limitation “extract/ing a plurality of PPG features for each valid PPG snipped of the pair of valid PPG snippets based on the respective plurality of N-N intervals”. It is unclear if the plurality of PPG features are the same PPG features recited previously and in the preamble or if these are different PPG features which are extracted and further used for extracting the plurality of PPG features of claim 1. In other words, it is unclear if the limitation intends to further narrow the PPG features to be extracted using different/distinct PPG features or if the limitation intends to further narrow the PPG features such that they are extracted based on the respective plurality of N-N intervals. It is further unclear if the plurality of N-N intervals are the same as the PPG features or if these are different/distinct from the plurality of PPG features. For examination purposes, it has been interpreted that extracting the plurality of PPG features is based on the plurality of N-N intervals and may be the N-N intervals themselves or may be different, however, clarification is required.
Claims 7 and 16 recite “a predicted fatigue level”. It is unclear if this is the fatigue level predicted in claims 1 and 13 or if this is a different predicted fatigue level. For examination purposes, it has been interpreted to mean either the same or different, however, clarification is required.
Claim 18 recites the limitation “in response to the pair of valid PPG snippets being classified with a low degree of similarity, extract the plurality of pairwise features from the plurality of PPG features for each valid PPG snippet in the pair of valid PPG snippets”. Examiner notes that the limitation is embedded into the “prior to extracting a plurality of pairwise features” limitation, thus rendering the claim unclear as to how extracting the plurality of pairwise features is done prior to extracting the plurality of pairwise features. For examination purposes, it has been interpreted that the limitation is not prior to extracting, however, clarification is required.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3, 13, 15, and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Huang et al. (US 20220039677 A1), hereinafter Huang.
Regarding claims 1, 13, and 20,
Huang teaches a system (at least fig. 11 (1100) and corresponding disclosure in at least comprising:
A PPG sensor (at least fig. 11 (1115) and corresponding disclosure in at least [0096]);
One or more memories storing executable instructions (at least fig. 11 (1112, 1122, and/or 1132) and corresponding disclosure in at least [0095], [0098], and [0100]); and
One or more processors (at least fig. 11 (1111, 1121, and/or 1131) and corresponding disclosure in at least [0095], [0098], and [0100]) coupled to the PPG sensor and one or more memories (see at least fig. 11), the executable instructions configuring the one or more processors to:
obtain a pair of valid photoplethysmogram (PPG) snippets from a PPG signal ([0037] the recording period is divided into consecutive segments of 5 minutes. See also [0043] which discloses The physiological signals used in operation 201 may be received within a sub-period. Such sub-period may be several minutes (e.g., 2 to 10 minutes) or several hours (e.g., 1 to 5 hours). An active phase may include one or more sub-periods. A sleep phase (or a non-active phase) may include one or more sub-periods. A period for recording physiological signals may include several sub-periods, several hours, one or more days, one or more active phases, or one or more sleep phases. Examiner notes that the physiological signal(s) are considered valid in its broadest reasonable interpretation in that Huang uses them for analysis/evaluation),
Extract a plurality of PPG features for each valid PPG snippet of the pair of valid PPG snippets ([0036] which discloses parameters of HRV may be generated or calculated from the physiological signals received or obtained in operation 101 and which discloses upon processing the R-R intervals, the parameters of HRV including parameters in time domain, frequency domain, and time-frequency domain, may be obtained and [0037] For SDANN, the recording period is divided into consecutive segments of 5 minutes; the standard deviations of NN intervals for each consecutive segment of 5 minutes are calculated, and SDANN indicates the average of the standard deviations of NN intervals for the consecutive segments; the unit is μs. NN50 count indicates the number of pairs of adjacent NN intervals differing by more than 50 ms over the entire recording. HRV triangular index indicates the total number of all RR intervals divided by the height of the histogram of all RR intervals)
Extract a plurality of pairwise features from the plurality of PPG features for each PPG snippet ([0037] which discloses parameters in time domain may include SDANN (Standard deviation of the averages of NN intervals in all 5-minute segments of the entire recording) averages of NN intervals in all 5-minute segments of the entire recording, NN50 count (Number of pairs of adjacent NN intervals differing by more than 50 milliseconds in the entire recording and the standard deviations of NN intervals for each consecutive segment of 5 minutes are calculated. Additionally/alternatively, [0039] discloses parameters of HRV in frequency domain may include total power (TP), very low frequency power (VLFP) (i.e., the power distributed in the frequency not exceeding 0.04 Hz), low frequency power (LFP), high frequency power (HFP), normalized LFP (nLFP)may be generated from RR intervals, HFP and ratio of LFP to HFP and [0046] discloses shows curves of the heart rates (therefore extracted changes thereof) and the LF/HF ratios in accordance with some embodiments of the present disclosure. In FIG. 3, the heart rates and the LF/HF ratios may be detected or measured from a subject (or living body). In FIG. 3, the period for recording the physiological signals may be 4 days. Each day in FIG. 3 includes an active phase and a sleep phase. The darker stripes indicate the active phases. The lighter stripes indicate the sleep phases. Therefore High-power frequency and low power frequency are considered pairwise features extracted from the plurality of PPG features for each PPG snippet and/or the heart rate changes over time are considered a plurality of pairwise features. See further [0077] disclosing a disorder ratio of LF/HF in a sleep phase an average value of LF/HF in asleep phase, and a disorder ratio LF/HF in an active phase may be generated and calculated in 703),
Predict a fatigue level for the user based on the pairwise features (at least fig. 1 (105) and corresponding disclosure in at least [1] and at least fig. 4 (409) and corresponding disclosure in at least [0066])
Regarding claims 3 and 15,
Huang further discloses wherein the executable instructions, when executed by the one or more processors to extract a plurality of PPG features for each valid PPG snippet of the pair of valid PPG snippets, further cause the system to: detect a plurality of peaks in each valid PPG snippet of the of the pair of valid PPG snippets ([0037] which discloses use of RR intervals and NN intervals. Examiner notes that such use of RR intervals/NN intervals requires detection of a plurality of peaks in each valid PPG signal); obtain a plurality of N-N intervals for each valid PPG snippet of the of the pair of valid PPG snippets based on the respective plurality of peaks ([0037] which discloses standard Deviation of the Averages of NN intervals in all 5-minute segments of the entire recording); and extract a plurality of PPG features for each valid PPG snippet of the of the pair of valid PPG snippets based on the respective plurality of N-N intervals ([0037] which discloses the standard deviations of NN intervals for each consecutive segment of 5 minutes are calculated, and SDANN indicates the average of the standard deviations of NN intervals for the consecutive segments; the unit is μs. NN50 count indicates the number of pairs of adjacent NN intervals differing by more than 50 ms over the entire recording. HRV triangular index indicates the total number of all RR intervals divided by the height of the histogram of all RR interval)
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.
Claims 2, 4, 6 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Kriara et al. (US 20240194298 A1), hereinafter Kriara.
Regarding claims 2 and 14,
Huang teaches the elements of claims 1 and 13 as previously stated. Huang further teaches wherein the executable instructions, when executed by the one or more processors to obtain a pair of valid PPG snippets from a PPG signal, further cause the system to:
Extract a pair of raw PPG snippets from the PPG signal (see [0037] which discloses the recording period is divided into consecutive segments of 5 minutes);
Huang fails to explicitly teach pre-processing each raw PPG snippet of the pair of raw PPG snippets to generate a pair of processed PPG snippets and validating each processed PPG snippet of the pair of processed PPG snippets using a trained PPG signal validator to obtain the pair of valid PPG snippets.
Kriara, in a similar field of endeavor involving PPG signal evaluation, teaches wherein the executable instructions, when executed by the one or more processors to obtain a pair of valid PPG snippets from a PPG signal, further cause the system to ([0093] which discloses computer proram including computer-executable instructions for performing the method according to the present invention in one or more embodiments enclosed herein when the program is executed on a computer or computer network or a cloud and [0094] disclosing computer-readable storage medium stored thereon having computer-executable instructions):
Extract a pair of raw PPG snippets from a PPG signal ([0025] which discloses the daily PPG signal may be cut into intervals, e.g. 10 second intervals. [0151] which discloses signals 116 comprised by the biological sensor data and the signal comprised by the biological sensor data 110 may be a 10 second interval of a PPG signal. See also figs. 2A-2C depicting raw PPG snippets from a PPG signal);
Preprocess each raw PPG snippet of the pair of raw PPG snippets to generate a pair of processed PPG snippets ([0024] which discloses at least one pre-processing step comprising one or more of filtering or normalizing the biological sensor data. For example, in case of a signal of the PPG device a bandpass filter may be used. Additionally, the signal may be normalized so that values are around 0)
Validate each processed PPG snippet of the pair of processed PPG snippets ([0164] which discloses the class output may use a binary crossentropy loss function to provide a probability between 0 and 1, with a value over 0.5 indicating that the signal 116 is clean and [0151] which discloses classifying quality may comprise discriminating between noisy and clean signals) using a trained PPG signal validator to obtain the pair of valid PPG snippets ([0031] which discloses classifying quality of the signal is performed by using at least one trained trainable model and also [0029] which discloses comprise at least one controlling unit configured for dismissing and/or rejecting biological sensor data categorized as noisy or bad quality)
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified Huang to include pre-processing and validating each processed PPG snippet using a trained PPG signal validator as taught by Kriara in order to provide an approach to detecting reliable or clean signals from a continuous PPG signal in a real world dataset during everyday life activities (Kriara [0100]). Such a modification would allow for ensuring enhanced accuracy of the fatigue determination by Huang such that noisy or bad quality signals may be dismissed or rejected and therefore not used in said determination.
Regarding claim 4,
Huang, as modified, teaches the elements of claim 2 as previously stated. Kriara, as applied to claim 2 above, further teaches wherein preprocessing each raw PPG snippet of the pair of raw PPG snippets to generate a pair of processed PPG snippets comprises:
Filtering each raw PPG snipped of the pair of raw PPG snippets with bandpass filter having a bandpass frequency .6-8 Hz ([0025] which discloses the PPG signals may be pre-processed using a third order Butterworth bandpass filter with 0.5 and 9 Hz frequency cut on per subject daily PPG signals. Examiner notes that the bandpass frequency .6-8 Hz is included in the bandpass filter with .5 and 9 Hz frequency); and
Normalizing each raw PPG snippet of the pair of raw PPG snippets to have a mean of zero and a standard deviation of 1 ([0024] which discloses additionally, the signal may be normalized so that the values are around 0).
Regarding claim 6,
Huang, as modified, teaches the elements of claim 2 as previously stated. Kriara, as applied to claim 2 above, further teaches wherein the trained PPG signal validator is a temporal convolutional network (at least fig. 3A, 3B, or 3C (134) and corresponding disclosure in at least [0158] and [0155] which discloses as input (denoted by reference number 138) filtered PPG signals of 10 seconds each with 20 Hz frequency may be used. Thus, the input 138 may comprise a signal 116 comprising 200 values, such as signals 116 exemplarily described in FIG. 2 and [0165] which discloses dens lays may be used to have an output of the same size as the input 138. Examiner thus notes that the convolutional network 134 is a temporal convolutional network)
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Huang and Kriara, as applied to claim 2 above, and further in view of Xiao et al. (US 20230360664 A1), hereinafter Xiao.
Regarding claim 5,
Huang, as modified, teaches the elements of claim 2 as previously stated. Huang further teaches wherien the term ‘deep learning’ is a broad term and specifically may refer to a class of machine learning algorithms using multiple layers in [0031], however, fails to explicitly teach wherein the trained PPG signal validator is a fast fourier transform (FFT) based multi-layer perceptron network (MLP).
Nonetheless, Xiao, in a similar field of endeavor involving signal analysis teaches wherein a trained PPG signal validator is a fast fourier transform (FFT) based multi-layer perceptron network (MLP) ([0151] which discloses the processing device 110 may determine the SNR based on a sub-band signal and the noise signal value. In some embodiments, the processing device 110 may use a trained SNR estimation model to determine the SNR of each sub-band signal. SNR estimation models may include a multi-layer perceptron (MLP) model, a decision tree (DT) model, a deep neural network (DNN) model, a support vector machine (SVM) model, a K-Nearest Neighbor (KNN) algorithm, and other algorithms or models that can perform a feature extraction and/or classification).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified the trained PPG signal validator of Huang to be a fast fourier transform (FFT) based multi-layer perceptron network (MLP) in order to perform validation of the PPG snippets based on Signal to Noise ratio. Furthermore, such a modification amounts to merely a simple substitution of one known multi-layer network for another yielding predictable results with respect to signal validation thereby rendering the claim obvious (MPEP 2143).
Claims 7-8, 10, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Lu et al. (US 20230397890 A1), hereinafter Lu.
Regarding claims 7 and 16,
Huang teaches the elements of claims 1 and 13 as previously stated. Huang further teaches wherein the executable instructions, when executed by the one or more processors to predict the fatigue level, further cause the system to:
Input the pairwise features into a progressive feature model to obtain predicted fatigue level ([0067] which discloses weighting factors… may be employed to amplify or reduce components of the corresponding HRV parameters. The weighting factors may depend on their correlation with FI and their respective value range contributed to FI, when fitting formula (8) into a multiple linear regression model, the shifting factors … may correspond to the intercept of the model and may be based on the available dataset), the predicted fatigue level including an odds ratio and a probability of experiencing a change in the fatigue level (Examiner notes that the limitations are embedded in a limitation towards intended use as noted in the claim interpretation section above, where to obtain a predicted fatigue level is considered an intended use of the inputting of the pairwise features. Examiner notes that since the multiple linear regression model is used to obtain a predicted fatigue level that it is considered capable of being used to obtain a predicted fatigue level including an odds ratio and a probability of experiencing a change in the fatigue level and therefore reads on the claimed invention).
Huang fails to explicitly teach wherein the executable instructions, when executed by the one or more processors to predict the fatigue level, further cause the system to:
Input the pairwise features into a progressive feature search tree to obtain a predicted fatigue level, the predicted fatigue level including an odds ratio and a probability of experiencing a change in the fatigue level.
Lu, in a similar field of endeavor involving fatigue monitoring, teaches wherein executable instructions, when executed by one or more processors to predict the fatigue level, further cause a system to:
Input the pairwise features into a progressive feature search tree to obtain a predicted fatigue level ([0062] which discloses the fatigue level estimation unit 13 estimates the fatigue level of the subject by applying the feature value calculated in step A3 to the machine learning model in which the relationship between the feature value of the biological data and the fatigue level has been subjected to machine learning (step A4), in [0054] the machine learning model is not limited to the linear model shown in the above Expression 2, and may also be an index model, a logarithmic model, or the like, or a combination of different models, and in [0055] discloses the method of constructing the machine learning model is not particularly limited. Specific methods for machine learning include linear regression, logistic regression, a support vector machine, a decision tree, a regression tree, and a neural network. Thus the machine learned model using a decision/regression tree is considered progressive feature search tree in its broadest reasonable interpretation), the predicted fatigue level including an odds ratio and a probability of experiencing a change in the fatigue level (Examiner notes that the limitations are embedded in a limitation towards intended use as noted in the claim interpretation section above, where to obtain a predicted fatigue level is considered an intended use of the inputting of the pairwise features. Examiner notes that since the machine-learned model (i.e. progressive feature search tree) is used to obtain a predicted fatigue level that it is considered capable of being used to obtain a predicted fatigue level including an odds ratio and a probability of experiencing a change in the fatigue level and therefore reads on the claimed invention).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified Huang to include inputting the pairwise features into a progressive feature search tree as taught by Lu in order to provide an optimized model for obtaining a fatigue level constructed using a relationship between a feature value related to heartbeat fluctuation and the fatigue level (Lu [0052]-[0053]. Furthermore, such a modification amounts to merely a simple substitution of one known fatigue determination algorithm for another yielding predictable results with respect to determining fatigue levels, thereby rendering the claim obvious (MPEP 2143).
Regarding claim 8,
Huang, as modified, teaches the elements of claim 7 as previously stated. Lu further teaches wherein: prior to inputting the pairwise features into a progressive feature search tree: building a progressive feature search tree by computing one or more relationships between a respective one or more pairwise features and a respective fatigue level ([0062] which discloses in which the relationship between the feature value of the biological data and the fatigue level has been subjected to machine learning (step A4))
Regarding claim 10,
Huang, as modified, teaches the elements of claim 8 as previously stated. Lu further teaches wherein the respective one or more pairwise features correspond to a respective tier level and the progressive feature search tree is built by progressively computing the one or more relationships between the respective one or more pairwise features and the respective fatigue level based on the respective tier level ([0062] which discloses in which the relationship between the feature value of the biological data and the fatigue level has been subjected to machine learning (step A4)).
Claims 9 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Huang and Lu, as applied to claims 8 and 16 above, and further in view of Chai et al. (US 20230315811 A1), hereinafter Chai.
Regarding claim 9,
Huang, as modified, teaches the elements of claim 8 as previously stated. Huang fails to explicitly teach wherein the one or more relationships between a respective one or more pairwise features and a respective fatigue level is computed using Fisher's exact test
Huang further teaches determining a correlation between the fatigue index and subjective fatigues index in [0068] and fig. 5 and using the correlation as feedback for updating the operations in [0070]-[0076], however, fails to explicitly teach the one or more relationships between a respective one or more pairwise features and a respective fatigue level being computed using Fisher's exact test.
Nonetheless, Chai, in a similar field of endeavor involving machine learning, teaches wherein a relationship between inputs and outputs are computed using fisher’s exact test ([0030] which discloses the loss adjustment weights may be computed based on an appropriate statistical analysis methodology, such as Fisher’s exact test. Additionally, the loss adjustment weights may be determined based on a comparison of a model output and the label such as ground truth)).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified Huang, as currently modified, to include using fisher’s exact test as taught by Chai in order to provide a statistical analysis for determining loss adjustment weights of the model of Huang, as modified, such that the machine learned model is sufficiently trained (Chai [0030]).
Regarding claim 17,
Huang, as modified, teaches the elements of claim 16 as previously stated. Lu further teaches wherein the executable instructions, when executed by the one or more processors, further cause the system to: prior to inputting the pairwise features into a progressive feature search tree:
build a progressive feature search tree by computing one or more relationships between a respective one or more pairwise features and a respective fatigue level ([0062] which discloses in which the relationship between the feature value of the biological data and the fatigue level has been subjected to machine learning (step A4)).
Huang further teaches determining a correlation between the fatigue index and subjective fatigues index in [0068] and fig. 5 and using the correlation as feedback for updating the operations in [0070]-[0076], however, fails to explicitly teach the one or more relationships between a respective one or more pairwise features and a respective fatigue level being computed using Fisher's exact test.
Nonetheless, Chai, in a similar field of endeavor involving machine learning, teaches wherein a relationship between inputs and outputs are computed using fisher’s exact test ([0030] which discloses the loss adjustment weights may be computed based on an appropriate statistitcal analysis methodology, such as Fisher’s exact test. Additionally, the loss adjust ment weights may be determined based on a comparison of a model output and the label such as ground truth)).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified Huang, as currently modified, to include using fisher’s exact test as taught by Chai in order to provide a statistical analysis for determining loss adjustment weights of the model of Huang, as modified, such that the machine learned model is sufficiently trained (Chai [0030]).
Claims 11 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Fischell et al. (US 20090082682 A1), hereinafter Fischell.
Regarding claims 11 and 18,
Huang teaches the elements of claims 1 and 13 as previously stated. Huang further teaches wherein the executable instructions, when executed by the one or more processors, further cause the system to:
prior to extracting a plurality of pairwise features from the plurality of PPG features for each valid PPG snippet;
classify the pair of valid PPG snippets using a trained differential network, the classification describing a degree of similarity between the pair of valid PPG snippets
Huang fails to explicitly teach wherein the classification describing a degree of similarity between the pair of valid PPG snippets.
Fischell, in a similar field of endeavor involving heart rate evaluation, teaches the classification describing a degree of similarity between the pair of valid PPG snippets prior to extracting a plurality of pairwise features from the plurality of features for each valid biosignal snippet;
classify the pair of valid biosignal snippets using a trained differential network, the classification describing a degree of similarity between the pair of valid biosignal snippets (Claim 3 which discloses the processor (i.e. a trained differential network in its broadest reasonable interpretation) is further configured to process waveform segments and to classify waveform segments, and wherein the determination of a change in heart rate is performed by comparing the heart rate classifications of two segments);
in response to the pair of valid PPG snippets being classified with a low degree of similarity, extract the plurality of pairwise features from the plurality of PPG features for each valid PPG snippet in the pair of valid PPG snippets (Claim 3 which discloses the processor is further configured to process waveform segments and to classify waveform segments, and wherein the determination of a change in heart rate is performed by comparing the heart rate classifications of two segments).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified Huang to include classifying the pair of valid snippets as taught by Fischell in order to identify a change in heart rate between the two segments accordingly.
Claims 12 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Jeong et al. (US 11559211 B2), hereinafter Jeong.
Regarding claims 12 and 19,
Huang teaches the elements of claims 1 and 13 as previously stated. Huang fails to explicitly teach wherein the executable instructions, when executed by the one or more processors, further cause the system to: compare the fatigue level to a pre-defined criteria; and serve a fatigue alert to the user based on the comparison.
Jeong, in a similar field of endeavor involving fatigue monitoring, teaches wherein executable instructions, when executed by one or more processors, further cause a system to compare a fatigue level to a pre-defined criteria (Col. 10 liens 37-48 which discloses the processor 220 may measure the fatigue level based on the heart rate information and Col. 10 lines 49-60 which discloses if the fatigue level is equal to or greater than the specified first range. See also Col. 21, lines 17-20 which discloses the processor 220 may determine whether or not the fatigue level exceeds the specified third range), and serve a fatigue alert to a user based on the comparison (Col. 10 lines 49-60 which discloses the processor may provide a notification to the user if the fatigue level is equal to or greater than the specified first range. See also Col. 21 lines 29-35 which discloses if the fatigue level exceeds the specified third range, the processor 220 may provide a fatigue notification).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have modified Huang, to include comparing the fatigue level and serving a fatigue alert in order to warn a user to stop exercising or to rest (Jeong Col. 10 and 21). Such a modification would reduce an injury risk while maximizing an exercise effect (Jeong Col. 2 lines 1-4 and Col. 10 lines 58-60).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Clifford et al. (Dynamic time warping and machine learning for signal quality assessment of pulsatile signals) and (Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms) teach use of an multi-layer perceptron network for validating biosignals.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BROOKE L KLEIN whose telephone number is (571)270-5204. The examiner can normally be reached Mon-Fri 7:30-4.
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, Anne Kozak can be reached at 571-270-0552. 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.
/BROOKE LYN KLEIN/Primary Examiner, Art Unit 3797
Prosecution Insights