DETAILED ACTION
Applicant’s arguments, filed on 10/23/2025, 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.
Applicants have amended their claims, filed on 10/23/2025, and therefore rejections newly made in the instant office action have been necessitated by amendment.
Claims 1-3 and 5-10 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 .
Claim Objections
Claim 1 is objected to because of the following informalities:
In claim 1, lines 4-5, “a photoplethysmography (PPG) sensor” should read “a PPG sensor”, as the acronym has already been introduced into the claim.
Appropriate correction is required.
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 1-3 and 5-10 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 claim 1, the claim recites the limitation “recurrent neural networks” in lines 7-8. It is unclear if this limitation is meant to refer to the convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks introduced earlier in the claim, or different recurrent neural networks. If it is referring to the recurrent neural networks introduced earlier in the claim, it needs to refer back to it. If it is referring to different recurrent neural networks, it needs to be distinguished from the recurrent neural networks introduced earlier in the claim. For purposes of examination, it is being interpreted as referring to the recurrent neural networks introduced earlier in the claim. Claims 2-3 and 5-6 are also rejected due to their dependency on claim 1.
Further regarding claim 1, the claim recites the limitation “a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network” in lines 8-9. It is unclear if this limitation is meant to refer to the convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks introduced earlier in the claim, or different neural networks. Additionally, if it is referring to the convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks introduced earlier in the claim, it is unclear if this is one type of neural network, or two different types, as earlier in the claim it is introduced as one type of neural network (a convolutional-bidirectional long short-term memory recurrent neural network), yet in lines 8-9, they are introduced as separate neural networks (a convolutional neural network and a bidirectional LSTM recurrent neural network). The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as referring to the convolutional-bidirectional long short-term (LSTM) recurrent neural network from earlier in the claim. Additionally, it is being interpreted as either referring to either one type of neural network (a convolutional-bidirectional long short-term memory recurrent neural network) or two separate types of neural networks (a convolutional neural network and a bidirectional LSTM recurrent neural network). Claims 1-3 and 5-6 are also rejected due to their dependency on claim 1.
Regarding claim 2, the claim recites the limitation “a near-infrared sensor” in lines 2-3. It is unclear if this limitation is meant to be the same sensor as the PPG sensor introduced in claim 1, or a different sensor. If it is meant to refer to the PPG sensor, it should refer back to it. If it is referring to a different sensor, it is unclear how the PPG signal is measured from both the PPG signal from claim 1 and the near-infrared sensor from claim 2. For purposes of examination, it is being interpreted as referring to the PPG sensor from claim 1.
Regarding claim 5, the claim recites the limitation “at least one CNN” in line 3. It is unclear if this limitation is referring to the convolutional neural network from claim 1, or a different convolutional neural network. If it is meant to refer to the convolutional neural network from claim 1, it needs to refer back to it. If it is referring to a different convolutional neural network, it needs to be distinguished from the convolutional neural network from claim 1. For purposes of examination, it is being interpreted as referring to the convolutional neural network from claim 1.
Further regarding claim 5, the claim recites the limitation “at least one bidirectional LSTM recurrent neural network” in line 5. It is unclear if this limitation refers to the bidirectional LSTM recurrent neural network introduced in claim 1, or a different bidirectional LSTM recurrent neural network. If it is meant to refer to the bidirectional LSTM recurrent neural network from claim 1, it needs to refer back to it. If it is referring to a different bidirectional LSTM recurrent neural network, it needs to be distinguished from the bidirectional LSTM recurrent neural network from claim 1. For purposes of examination, it is being interpreted as referring to the bidirectional LSTM recurrent neural network from claim 1.
Regarding claim 7, the claim recites the limitation “recurrent neural networks” in line 8. It is unclear if this limitation is meant to refer to the convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks introduced earlier in the claim, or different recurrent neural networks. If it is referring to the recurrent neural networks introduced earlier in the claim, it needs to refer back to it. If it is referring to different recurrent neural networks, it needs to be distinguished from the recurrent neural networks introduced earlier in the claim. For purposes of examination, it is being interpreted as referring to the recurrent neural networks introduced earlier in the claim. Claims 8-10 are also rejected due to their dependency on claim 7.
Further regarding claim 7, the claim recites the limitation “a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network” in lines 8-9. It is unclear if this limitation is meant to refer to the convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks introduced earlier in the claim, or different neural networks. Additionally, if it is referring to the convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks introduced earlier in the claim, it is unclear if this is one type of neural network, or two different types, as earlier in the claim it is introduced as one type of neural network (a convolutional-bidirectional long short-term memory recurrent neural network), yet in lines 8-9, they are introduced as separate neural networks (a convolutional neural network and a bidirectional LSTM recurrent neural network). The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as referring to the convolutional-bidirectional long short-term (LSTM) recurrent neural network from earlier in the claim. Additionally, it is being interpreted as either referring to either one type of neural network (a convolutional-bidirectional long short-term memory recurrent neural network) or two separate types of neural networks (a convolutional neural network and a bidirectional LSTM recurrent neural network). Claims 8-10 are also rejected due to their dependency on claim 7.
Regarding claim 9, the claim recites the limitation “at least one CNN” in line 4. It is unclear if this limitation is referring to the convolutional neural network from claim 7, or a different convolutional neural network. If it is meant to refer to the convolutional neural network from claim 7, it needs to refer back to it. If it is referring to a different convolutional neural network, it needs to be distinguished from the convolutional neural network from claim 7. For purposes of examination, it is being interpreted as referring to the convolutional neural network from claim 7.
Further regarding claim 9, the claim recites the limitation “at least one bidirectional LSTM recurrent neural network” in lines 7-8. It is unclear if this limitation refers to the bidirectional LSTM recurrent neural network introduced in claim 7, or a different bidirectional LSTM recurrent neural network. If it is meant to refer to the bidirectional LSTM recurrent neural network from claim 7, it needs to refer back to it. If it is referring to a different bidirectional LSTM recurrent neural network, it needs to be distinguished from the bidirectional LSTM recurrent neural network from claim 7. For purposes of examination, it is being interpreted as referring to the bidirectional LSTM recurrent neural network from claim 7.
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 1-3 and 5-10 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. Under the two-step 101 analysis, the claims fail to satisfy the criteria for subject matter eligibility.
Regarding Step 1, claims 1-10 are all within at least one of the four statutory categories.
Claim 1 and its dependent claims disclose a system (machine).
Claim 7 and its dependent claims disclose a method (process).
Regarding Step 2A, Prong One, the independent claims 1 and 7 recite an abstract idea. In particular, the claims generally recite the following:
receive the measured PPG from the pulse wave measurement module and estimate a blood pressure via recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network in a many-to-many configuration.
These elements recited in claims 1 and 7 are drawn to abstract ideas since they involve a mental process that can be practically performed in the human mind including observation, evaluation, judgement, and opinion and using pen and paper.
Receiving the measured PPG from the pulse wave measurement module and estimate a blood pressure via recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network in a many-to-many configuration is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, or with the aid of pen and paper. A person of ordinary skill in the art could reasonably receive the measured PPG values and estimate the blood pressure through the mathematical techniques used in neural networks. These techniques are based on algorithms and calculations and mathematical concepts, which can be performed by hand. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in receiving the measured PPG from the pulse wave measurement module and estimate a blood pressure via the recurrent neural networks.
Regarding Step 2A, Prong Two, claims 1 and 7 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 blood pressure estimation server”), and
Add insignificant extra-solution activity (the pre-solution activity of: using generic data-gathering components (e.g., “a pulse wave measurement module comprising a photoplethysmography (PPG) sensor configured to measure the PPG”).
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.
Regarding Step 2B, claims 1 and 7 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.
Claims 1 and 7 do not recite additional elements that amount to significantly more than the judicial exception itself. In particular, “a pulse wave measurement module configured to measure PPG” does not quantify as significantly more because this limitation merely describes generic, well-known data gathering.
The data gathering step of “a pulse wave measurement module configured to measure PPG” is nothing more than a well-known data gathering step of measuring PPG signals. Such measurements are evidenced by:
US Patent Application Publication No. 20210007617 (Kim) discloses PPG sensors being conventional and used to measure blood pressure (Kim, [0010]);
US Patent Application Publication No. 20190125198 (Kang) discloses PPG-based blood pressure measuring methods as conventional (Kang, [0077]);
US Patent Application Publication No. 20190059753 (Chen) discloses conventional blood pressure measuring methods being based on PPG signals (Chen, [0038]);
US Patent Application Publication No. 20180146865 (Ortlepp) discloses conventional PPG measuring systems being used for blood pressure determination (Ortlepp, [0006]).
Further, the element of a blood pressure estimation server in claims 1 and 7 does not qualify as significantly more because this limitation is 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’l, 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 Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 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. 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 individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Regarding the dependent claims, claims 2-6 depend on claim 1 and claims 8-10 depend on claim 7. The dependent claims merely further define the abstract idea or are additional data output that in well-understood, routine, and previously known to the industry.
For example, the following are dependent claims reciting abstract ideas and can be performed in the human mind:
(Claim 2): “wherein the pulse wave measurement module measures the PPG using a near- infrared sensor” is insignificant pre-solution activity (part of the generic data gathering steps outlined above);
(Claim 3): “wherein the recurrent neural networks are trained with big data which is a collection of the blood pressure measured through A-line and the PPG measured for a same time period” is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 5): “wherein the recurrent neural networks include: at least one CNN to extract multidimensional information from the measured PPG; and at least one bidirectional LSTM recurrent neural network to estimate the blood pressure through the extracted multidimensional information” is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 6): “further comprising: a monitoring terminal configured to receive the estimated blood pressure from the blood pressure estimation server” is insignificant post-solution activity;
(Claim 8): “after the estimation step, further comprising: a monitoring step of receiving, by a monitoring terminal, the estimated blood pressure from the blood pressure estimation server to monitor the blood pressure” is insignificant post-solution activity;
(Claim 9): “wherein the estimation step comprises: an information extraction step of extracting, by the blood pressure estimation server, multidimensional information from the measured PPG via at least one CNN; and a blood pressure estimation step of estimating, by the blood pressure estimation server, the blood pressure from the extracted multidimensional information via at least one bidirectional LSTM recurrent neural network” is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 10): “after the estimation step, further comprising: an analysis step of analyzing, by the blood pressure estimation server, the estimated blood pressure to generate blood pressure analysis information” is insignificant post-solution activity.
The dependent claims do not recite significantly more than the abstract ideas. Therefore, claims 1-3 and 5-10 are rejected as being directed to non-statutory subject matter.
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 and 5-10 are rejected under 35 U.S.C. 103 as being unpatentable over Zhao (US 20200015755) in further view of Ansari (US 20210304855).
Regarding independent claim 1, Zhao teaches a real-time blood pressure monitoring system based on photoplethysmography (PPG) ([0009]: “The herein described systems can accept raw physiological signals (e.g. photoplethysmogram (PPG), electrocardiography (ECG or EKG), etc.) as inputs and after calculation yield arterial blood pressure readings in real time.”) using convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks ([0010]: “The deep leaning module 200 comprises a convolutional neural network (CNN) module”; [0010]: “a one- or multi-layer recurrent neural network (RNN) module”; [0013]: “These informative feature maps can be fed into the RNN module 220 comprising a bidirectional (LSTM) to process the blood pressure dynamics.”), comprising:
a pulse wave measurement module comprising a photoplethysmography (PPG) sensor configured to measure the PPG ([0010]: “The input device comprises a sensor 110 or a plurality of sensors 110 including ECG, EKG, or PPG sensors.”); and
a blood pressure estimation server configured to receive the measured PPG from the pulse wave measurement module ([0011]: “The input device 100 can transmit the physiological signals to the deep learning module 200”) and estimate a blood pressure via the recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network ([0011]: “The RNN module 220 comprising Long-Short Term Memory Networks (LSTMs) can model the temporal dependencies in blood pressure dynamics. The MDN module 230 can to output the arterial blood pressure estimation to an output device 300.”; [0013]: “These informative feature maps can be fed into the RNN module 220 comprising a bidirectional (LSTM) to process the blood pressure dynamics.”; ([0010]: “The deep leaning module 200 comprises a convolutional neural network (CNN) module”).
However, Zhao does not teach estimating a blood pressure via the recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network in a many-to-many configuration.
Ansari discloses a method to receive signals and analyze them using neural networks. Specifically, Ansari discloses using neural networks in a many-to-many configuration ([0071]: “the aggregator 264 may be implemented as a many-to-one recurrent neural network (RNN). In another embodiment, the aggregator 264 may be implemented as a plurality (e.g., a stack) of many-to-many RNNs followed by a many-to-one RNN.”). Zhao and Ansari are analogous arts since they are both related to analyzing signals to determine blood pressure.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the relationship from Ansari into the system from Zhao as it defines the specific relationship between the different neural networks, which can ensure a more detailed analysis and provides a more compact and meaningful representation of the data suitable for downstream analysis (Ansari, [0033]).
Regarding claim 5, the Zhao/Ansari combination teaches the real-time blood pressure monitoring system according to claim 1, wherein the recurrent neural networks include: at least one CNN to extract multidimensional information from the measured PPG (Zhao, [0011]: “The CNN module 210 can extract features from the physiological signals.”; [0016]: “the CNN can be a one dimensional (1D) CNN, a two dimensional (2D) CNN, or a three dimensional (3D) CNN”); and at least one bidirectional LSTM recurrent neural network to estimate the blood pressure through the extracted multidimensional information (Zhao, [0011]: “The RNN module 220 comprising Long-Short Term Memory Networks (LSTMs) can model the temporal dependencies in blood pressure dynamics. The MDN module 230 can to output the arterial blood pressure estimation to an output device 300.”; [0013]: “These informative feature maps can be fed into the RNN module 220 comprising a bidirectional (LSTM) to process the blood pressure dynamics.”).
Regarding claim 6, the Zhao/Ansari combination teaches the real-time blood pressure monitoring system according to claim 1, further comprising: a monitoring terminal configured to receive the estimated blood pressure from the blood pressure estimation server (Zhao, [0011]: “The MDN module 230 can to output the arterial blood pressure estimation to an output device”).
Regarding independent claim 7, Zhao teaches a real-time blood pressure monitoring method using a real-time blood pressure monitoring system based on photoplethysmography (PPG) (Abstract: “Methods and devices for long term, cuffless, and continuous arterial blood pressure estimation using an end-to-end deep learning approach are provided.”; [0009]: “The herein described systems can accept raw physiological signals (e.g. photoplethysmogram (PPG), electrocardiography (ECG or EKG), etc.) as inputs and after calculation yield arterial blood pressure readings in real time.”) using convolutional-bidirectional long short-term memory (LSTM) recurrent neural networks ([0010]: “The deep leaning module 200 comprises a convolutional neural network (CNN) module”; [0010]: “a one- or multi-layer recurrent neural network (RNN) module”; [0013]: “These informative feature maps can be fed into the RNN module 220 comprising a bidirectional (LSTM) to process the blood pressure dynamics.”), the method comprising:
a measurement step of measuring the PPG through a pulse wave measurement module ([0010]: “The input device comprises a sensor 110 or a plurality of sensors 110 including ECG, EKG, or PPG sensors.”); and
an estimation step of estimating, by a blood pressure estimation server ([0011]: “The input device 100 can transmit the physiological signals to the deep learning module 200”), a blood pressure from the PPG via recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network and estimate a blood pressure via the recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network ([0011]: “The RNN module 220 comprising Long-Short Term Memory Networks (LSTMs) can model the temporal dependencies in blood pressure dynamics. The MDN module 230 can to output the arterial blood pressure estimation to an output device 300.”; [0013]: “These informative feature maps can be fed into the RNN module 220 comprising a bidirectional (LSTM) to process the blood pressure dynamics.”; ([0010]: “The deep leaning module 200 comprises a convolutional neural network (CNN) module”).
However, Zhao does not teach estimating a blood pressure via the recurrent neural networks comprising a convolutional neural network (CNN) and a bidirectional LSTM recurrent neural network in a many-to-many configuration.
Ansari discloses a method to receive signals and analyze them using neural networks. Specifically, Ansari discloses using neural networks in a many-to-many configuration ([0071]: “the aggregator 264 may be implemented as a many-to-one recurrent neural network (RNN). In another embodiment, the aggregator 264 may be implemented as a plurality (e.g., a stack) of many-to-many RNNs followed by a many-to-one RNN.”). Zhao and Ansari are analogous arts since they are both related to analyzing signals to determine blood pressure.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the relationship from Ansari into the method from Zhao as it defines the specific relationship between the different neural networks, which can ensure a more detailed analysis and provides a more compact and meaningful representation of the data suitable for downstream analysis (Ansari, [0033]).
Regarding claim 8, the Zhao/Ansari combination teaches the real-time blood pressure monitoring method according to claim 7, after the estimation step, further comprising: a monitoring step of receiving, by a monitoring terminal, the estimated blood pressure by receiving the estimated blood pressure from the blood pressure estimation server to monitor the blood pressure (Zhao, [0011]: “The MDN module 230 can to output the arterial blood pressure estimation to an output device”).
Regarding claim 9, the Zhao/Ansari combination teaches the real-time blood pressure monitoring method according to claim 7, wherein the estimation step comprises: an information extraction step of extracting, by the blood pressure estimation server, multidimensional information from the measured PPG via at least one CNN (Zhao, [0011]: “The CNN module 210 can extract features from the physiological signals.”; [0016]: “the CNN can be a one dimensional (1D) CNN, a two dimensional (2D) CNN, or a three dimensional (3D) CNN”); and a blood pressure estimation step of estimating, by the blood pressure estimation server, the blood pressure from the extracted multidimensional information via at least one bidirectional LSTM recurrent neural network (Zhao, [0011]: “The RNN module 220 comprising Long-Short Term Memory Networks (LSTMs) can model the temporal dependencies in blood pressure dynamics. The MDN module 230 can to output the arterial blood pressure estimation to an output device 300.”; [0013]: “These informative feature maps can be fed into the RNN module 220 comprising a bidirectional (LSTM) to process the blood pressure dynamics.”).
Regarding claim 10, the Zhao/Ansari combination teaches the real-time blood pressure monitoring method according to claim 7, after the estimation step, further comprising: an analysis step of analyzing, by the blood pressure estimation server, the estimated blood pressure to generate blood pressure analysis information (Zhao, [0024]: “the MDN module 230 can model the blood pressure prediction as a classification problem. The outputs can then become a mixture of Gaussian distributions, which is a general case of mean square minimization (MSE). If, however, the output has only one Gaussian distribution, the MDN module 230 function will degrade to a MSE loss.”; [0025]: “The cuffless electronic device can operate through an end-to-end framework and be trained by a backpropagation algorithm. The backpropagation algorithm can calculate the gradient of an error function with respect to the deep learning module's weights.”).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over the Zhao/Ansari combination as applied to claim 1 above, and further in view of Chung (KR 20200095151). Citations to KR 20200095151 will refer to the English Machine Translation that accompanies this Office Action.
Regarding claim 2, the Zhao/Ansari combination teaches the real-time blood pressure monitoring system according to claim 1.
However, the Zhao/Ansari combination is silent on the specific type of sensor used to measure PPG signals.
Chung discloses a blood pressure measuring device. Specifically, Chung teaches wherein the pulse wave measurement module measures the PPG using a near-infrared sensor ([0027]-[0028]: “The optical biosensor (100) is a PPG sensor that is mounted on the first storage section (S1) of the strap (S) and measures the PPG signal at the location of the artery (I) between the bones above the wrist and outputs the signal to the control section (200). Optical biosensors may include light emitter diodes (LEDs) that emit light in a multispectral region encompassing, for example, the visible and near-infrared spectrums with wavelengths from 500 to 1500 nm.”). Zhao and Chung are analogous arts as they are both blood pressure measuring devices.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the sensor from Chung as the Zhao/Ansari combination is silent on the specific type of sensor used, and Chung discloses a suitable sensor in an analogous device.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over the Zhao/Ansari combination as applied to claim 1 above, and further in view of Sekhar (US 20230218179).
Regarding claim 3, the Zhao/Ansari combination teaches the real-time blood pressure monitoring system according to claim 1, wherein the recurrent neural networks are trained ([0009]: “These three modules construct an end-to-end trainable deep learning model”).
However, the Zhao/Ansari combination is silent on the specific techniques used to train the neural networks.
Sekhar discloses a method of estimating blood pressure of a subject. Specifically, Sekhar teaches wherein the recurrent neural networks are trained with big data which is a collection of the blood pressure measured through A-line and the PPG measured for a same time period ([0054]: “The processor 16 then estimates blood pressure coefficients by processing the PPG wavelet coefficients using a machine learning algorithm that has been trained on training data including PPG wavelet coefficients derived from PPGs from light-based Pulse-Plethysmography sensors applied to the skin of test subjects correlated with Invasive Arterial Blood Pressure (ABP) wavelet coefficients derived from simultaneously obtained ABP measurements of systolic and diastolic blood pressure of the test subjects”). Zhao and Sekhar are analogous arts as they are both related to determining blood pressure of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the training method from Sekhar into the system from Zhao since the Zhao/Ansari combination is silent on the specific method used to train the neural networks, and Sekhar discloses a suitable training method in an analogous device.
Response to Arguments
All of applicant’s argument regarding the rejections and objections previously set forth have been fully considered and are persuasive unless directly addressed subsequently.
With regards to the 112(b) rejections of claims 5 and 9, the rejections have been maintained, as the issues raised have not been resolved. Applicant argues that it is clear that no new or different neural networks are intended, however the claims still introduce new neural networks instead of referring back to the previously presented neural networks. The introduction of “at least one CNN” and “at least one bidirectional LSTM recurrent neural network” do not reference the previously presented CNN and bidirectional LSTM recurrent neural network nor are they distinguished from the previously presented neural networks, therefore there is confusion as to whether they are meant to be new, differentiated neural networks included in the neural networks already introduced, or if they are intended to reference the previously introduced types of neural networks.
Applicant's arguments with respect to the 101 rejections of the claims have been fully considered but they are not persuasive. Applicant argues that no human can perform the claimed invention in any practical sense. Examiner disagrees, as the limitations are based on evaluations and mathematical concepts that can be performed in the human mind or with the aid of pen and paper. A person of ordinary skill in the art could perform the calculations necessary to perform the steps required manually given enough time, even though the concepts are complex, therefore they are drawn to an abstract idea. Applicant also argues that the additional elements are not merely generic data gathering or output devices, and that the modules and servers recited as not generic placeholders but specific components, however no structure is provided for these modules and servers, and they are performing known computer functions, therefore they are considered generic placeholders. A PPG sensor is a well known sensor in the industry used to generate a PPG waveform, and the blood pressure estimation server has no provided structure uses known machine learning models, therefore it is not an improvement on the technology, as these machine learning models are known to be performed using servers. The concept of using machine learning models that were previously known do not provide an improvement to technology, and therefore the claims are directed to an abstract idea.
Applicant's arguments with regards to the 102 and 103 rejections have been fully considered but they are not persuasive. With regards to the 103 rejection of claim 2, Applicant argues that choosing the NIR sensor from Chung to use as the PPG sensor is hindsight reasoning. In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, the specific type of PPG sensor in Zhao is not explicitly stated, therefore it would have been obvious to choose a known PPG sensor type to use. Chung discloses a known PPG sensor type (the NIR sensor), therefore it would have been obvious to use that type of sensor, since it is a type of PPG sensor that is commonly used and would be suitable to measure PPG signals.
With regards to the 103 rejection of claim 3, Applicant argues that it would not have been obvious to use the training steps from Sekhar for the machine learning model from Zhao. In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, Zhao is silent on how the machine learning model was trained. It is obvious that a type of training step has been used to train the machine learning model, as that is an essential step in building a machine learning model. Therefore, it would have been obvious to use a known type of training steps to train the machine learning model. Sekhar discloses a specific type of training used for machine learning models, therefore it is obvious that this type of training steps can be used in Zhao, as it has been previously disclosed and is a suitable method for training a machine learning model.
With regards to the 103 rejection of claim 4, which has now been incorporated into the independent claim 1, Applicant argues that it would not have been obvious to combine Ansari with Zhao. However, as stated in the above 103 rejection of claim 1, Ansari states that their machine learning method was created to model physiological input signals to convert them to a more compact and meaningful representation, which can provide an easier, more impactful analysis of the signals, therefore providing the motivation to combine the references (Ansari, [0033]: “the present techniques may be used to model any periodic physiological input signal. The present techniques use coding architectures (e.g., including an encoder and/or a decoder) that are designed to convert one or more physiologic signals into a more compact and meaningful representation suitable for downstream analysis by clinicians and/or algorithms (e.g., a machine learning algorithm)”).
Applicant’s arguments with respect to claims 1 and 5-10 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIN K MCCORMACK whose telephone number is (703)756-1886. The examiner can normally be reached Mon-Fri 7:30-5.
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, Jason Sims can be reached at 5712727540. 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.K.M./Examiner, Art Unit 3791
/MATTHEW KREMER/Primary Examiner, Art Unit 3791