DETAILED ACTION
Applicant’s arguments, filed 05/07/2026, have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application. Applicant has amended their claims, filed 05/07/2026, and therefore rejections newly made in the instant office action have been necessitated by amendment. Applicant has canceled claims 4-5, 14-15, and 20.
Claims 1-3, 6-13, and 16-19 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
Claims 10 and 11 are objected to because of the following informalities:
Claim 10, lines 5-6, “to a pulse condition prediction model” should read “into a pulse condition prediction model”.
Claim 11, line 6, “to an initial neural network model” should read “into an initial neural network model”.
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, 6-13, and 16-19 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 1-2 and 10-11, it is unclear how the pulse condition prediction model “generates” the predicated probability values of the pulse conditions. What algorithm or calculation does the model use to predict a probability of the pulse conditions based on pulse wave intensity, phase difference, or their respective standard deviations? Applicant has amended the claims to recite that the model performs parallel computation via a plurality of hidden layers. However, it is unclear what is required to meet the claim regarding using the hidden layers for a machine learning model. What algorithm or equation does the model use? Does the model weight the to-be-predicted data? For examination purposes, the generating probability values step will be interpreted to mean calculating the probability values based on the measured data using a machine learning model/neural network. For similar reasons, claims 2 and 11 are rejected with respect to training the model. Claims 3, 6-9, 12-13, and 16-19 are also rejected due to their dependence on claims 1 and 10.
Regarding claims 1 and 10, it is unclear how the plurality of predicted probability values are further generated based on an abnormal condition of at least one of the plurality of meridians. The claim recites that the abnormal condition is determined by comparing the first or second standard deviation with a default standard deviation. Is this abnormal condition calculated using the pulse condition prediction model before the model generates the plurality of probability values? Is the abnormal condition calculated, and then the abnormal condition is input into the pulse condition prediction model to determine the plurality of probability values? Applicant should clarify the relationship between how the abnormal condition is calculated and what step the abnormal condition is calculated in. For examination purposes, the claims will be interpreted such that data is measured from a pressure sensor, to-be-predicted data is generated based on the measured waveforms, and a plurality of predicted probability values of a plurality of pulse conditions are generated from a machine learning model based on the to-be-predicted data and comparisons of the data. Claims 2-3, 6-9, 11-13, and 16-19 are also rejected due to their dependence on claims 1 and 10.
Regarding claims 1 and 10, it is unclear what the difference is between a pulse condition and an abnormal condition. Do the plurality of pulse conditions include one or more abnormal conditions or do they all refer to abnormal conditions? If an abnormal condition is determined to be present or not present, the probability of the pulse condition would inherently be 0% or 100%.
Applicant defines an abnormal pulse condition as “in a normal pulse condition, cun, guan and chi have even thickness, if the result of taking the pulse indicates that “chi” section on the left wrist is thin and weak, it means that the subject’s “Qi” in kidney is deficient, and there must be illness at the subject’s pelvic cavity” (Paragraph 0025). How does the “cun, guan, and chi” correspond to the measurements taken from the arterial waveform? Does any deficiency in these elements result in an “abnormal” pulse condition? Applicant states that there must be an illness in the subject’s pelvic cavity, but what is the illness in the pelvic cavity? How does thin and weak “chi” result in some kidney deficiency?
Further, Applicant defines three abnormal pulse conditions as “kidney asthenia, lung asthenia and anemofrigid cold”. However, as described above, it is unclear how these abnormal pulse conditions are used to generate or result in one or more probability values.
Applicant should clarify the relationship between the plurality of pulse conditions and the abnormal condition. For examination purposes, the claims will be interpreted such that data is measured from a pressure sensor, to-be-predicted data is generated based on the measured waveforms, and a plurality of predicted probability values of a plurality of pulse conditions are generated from a machine learning model based on the to-be-predicted data and comparisons of the data. Claims 2-3, 6-9, 11-13, and 16-19 are also rejected due to their dependence on claims 1 and 10.
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, 6-13, and 16-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Analysis of independent claims 1 and 10:
Step 1 of the subject matter eligibility test (see MPEP 2106.03).
Claim 1 is directed to a computer implemented method, which describes one of the four statutory categories of patentable subject matter, i.e., a method. Claim 10 is directed to a system, which describes one of the four statutory categories of patentable subject matter, i.e., a machine. Therefore, further consideration is necessary regarding the claims.
Step 2A of the subject matter eligibility test (see MPEP 2106.04).
Prong One: Claims 1 and 10 recite an abstract idea. In particular, the claims generally recite
the following:
generating, by a processor, to-be-predicted data based on the first arterial waveform;
a plurality of predicted probability values of a plurality of pulse conditions being generated by the pulse condition prediction model performing parallel computation via a plurality of hidden layers having the to-be-predicted data;
wherein generating the to-be-predicted data comprises extracting the plurality of pieces of first pulse wave data from a plurality of harmonics of the first arterial waveform based on a resonance principle; and
wherein the plurality of predicted probability values are further generated based on an abnormal condition of at least one of the plurality of meridians, and the abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation.
These elements recited in claims 1 and 10 are drawn to an abstract idea since they are directed towards mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III).
“generating, by a processor, to-be-predicted data based on the first arterial waveform” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably take an arterial waveform and calculate data therefrom. There is nothing to suggest an undue level of complexity in “generating, by a processor, to-be-predicted data based on the first arterial waveform”.
“a plurality of predicted probability values of a plurality of pulse conditions being generated by the pulse condition prediction model performing parallel computation via a plurality of hidden layers having the to-be-predicted data” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably take calculated arterial waveform data and generate probability values of a condition based therefrom. There is nothing to suggest an undue level of complexity in “a plurality of predicted probability values of a plurality of pulse conditions being generated by the pulse condition prediction model performing parallel computation via a plurality of hidden layers having the to-be-predicted data”. Examiner notes that while a pulse condition prediction model performing parallel computation via a plurality of hidden layers is claimed, the model itself is broadly claimed and performs a process that is common among most machine learning models/neural networks. With a broad claiming of a machine learning model and a way it processes data, this limitation is still directed towards a mental process as a person of ordinary skill in the art would be able to generate the probability values from arterial waveform data.
“wherein generating the to-be-predicted data comprises extracting the plurality of pieces of first pulse wave data from a plurality of harmonics of the first arterial waveform based on a resonance principle” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably generate data from the harmonic frequencies of a dataset. There is nothing to suggest an undue level of complexity in “wherein generating the to-be-predicted data comprises extracting the plurality of pieces of first pulse wave data from a plurality of harmonics of the first arterial waveform based on a resonance principle”.
“wherein the plurality of predicted probability values are further generated based on an abnormal condition of at least one of the plurality of meridians, and the abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably compare standard deviation calculations to determine an abnormal condition and use said abnormal condition in calculating probability values. There is nothing to suggest an undue level of complexity in “wherein the plurality of predicted probability values are further generated based on an abnormal condition of at least one of the plurality of meridians, and the abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation”.
Prong Two: Claims 1 and 10 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., “wherein the to-be-predicted data comprises a plurality of pieces of first pulse wave data of a plurality of meridians; wherein each of the plurality of pieces of first pulse wave data comprises a pulse wave intensity tag, a phase difference tag, a first standard deviation corresponding to the pulse wave intensity tag, and a second standard deviation corresponding to the phase difference tag; wherein the phase difference tag is associated with a phase difference between a phase of the first arterial waveform and a default phase, and wherein the pulse wave intensity tag indicates an intensity of ‘Qi’” (claims 1 and 10) and "wherein the default standard deviation for a first group of the plurality of meridians is different from a default standard deviation for a second group of the plurality of meridians" (claims 1 and 10)) and
Add insignificant extra-solution activity (the pre-solution activity of: using generic data gathering components (e.g., “sensing, by a pressure sensor, a first arterial waveform from an artery of a first subject” (claim 1), "a pressure sensor configured to sense a first arterial waveform from an artery of a first subject" (claim 10), "inputting, by the processor, the to-be-predicted data into a pulse condition prediction model" (claim 1), and “input the to-be-predicted data to a pulse condition prediction model” (claim 10))).
As a whole, the additional elements merely serve to gather information to be used by the abstract idea, while generically implementing it on a computer. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing performed remains in the abstract realm, i.e., the result is not used for a treatment. No improvement to the technology is evident. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Step 2B of the subject matter eligibility test (see MPEP 2106.05).
Claims 1 and 10 do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) for the same reasons as described above. E.g., all elements are directed to implementing the abstract ideas on generic processing components, the pre-solution activity of using generic data-gathering components, and generic post-solution activities, which merely facilitate the abstract idea.
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example, “a processor” as disclosed in the Applicant’s specification “Said processor is, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microcontroller, a programmable logic controller (PLC) or any other processors with signal processing function” (Paragraph 0023) and “a pressure sensor” as disclose in the Applicant’s specification “The pressure sensing module 11 may be implemented in the form of a wristband for sensing artery in the wrist. In an implementation, the pressure sensing module 11 includes one or more sensors configured to sense artery of a first subject to generate a first arterial waveform” (Paragraph 0023). Further, a “pulse condition prediction model” as disclosed in the Applicant’s specification “The pulse condition prediction model described in the present disclosure may be a deep-learning model, and may include trained keras sequential model, trained multilayer perceptron (MLP), trained convolutional neural network model or trained recurrent neural network model” (Paragraph 0033).
These elements do not qualify as significantly more because these limitations are simply appending well understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int'/, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well understood, routine and conventional activity previously known in the industry (see Electric PowerGroup, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int'/, 110 USPQ2d 1976 (2014); SAP Am. v. lnvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements include a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Analysis of dependent claims 2-3, 6-9, 11-13, and 16-19:
Claims 2 and 11 recite mental steps that may be performed in the human mind with the aid of pen and paper or a generic computer, which add to the abstract idea. The mental steps are identified as:
“generating, by the processor, a plurality of pieces of training data based on the plurality of second arterial waveforms” (claim 2);
“where the processor is further configured to generate a plurality of pieces of training data according to the plurality of second arterial waveforms” (claim 11);
Claims 2, 9, 11, and 19 recite steps that are mathematical concepts, which add to the abstract idea. The mathematical concepts are identified as:
“inputting, by the processor, the plurality of pieces of training data into an initial neural network model to train the initial neural network model into, and the pulse condition prediction model” (claim 2);
“the abnormal condition indicates a corresponding one of the first standard deviations or a corresponding one of the second standard deviations being greater than the corresponding default standard deviation” (claim 9);
“to input the plurality of pieces of training data to an initial neural network model, and to generate to train the initial neural network model into the pulse condition prediction model” (claim 11); and
“the abnormal condition indicates a corresponding one of the first standard deviations or a corresponding one of the second standard deviations being greater than [[a]]the corresponding default standard deviation” (claim 19).
Claims 2-3, 6-9, 11-13, and 16-19 recite limitations in addition to the abstract idea: they merely
Further describe the abstract idea (“wherein each of the plurality of pieces of training data comprises a plurality of pieces of second pulse wave data of the plurality of meridians, and each of the plurality of pieces of training data has a plurality of labelled probability values corresponding to the plurality of pulse conditions” (claim 2), “wherein each of the plurality of pieces of second pulse wave data comprises a pulse wave intensity tag and a phase difference tag, wherein the phase difference tag is associated with a phase difference between a phase of the second arterial waveform and a default phase” (claim 7), “wherein each of the plurality of pieces of second pulse wave data further comprises a first standard deviation corresponding to the pulse wave intensity tag and a second standard deviation corresponding to the phase difference tag” (claim 8), “wherein the plurality of labelled probability values is associated with a normal condition or the abnormal condition of a respective one of the plurality of meridians” (claim 9), “wherein each of the plurality of pieces of training data comprises a plurality of pieces of second pulse wave data of the plurality of meridians, and each of the plurality of pieces of training data has a plurality of labelled probability values corresponding to the plurality of pulse conditions” (claim 11), “wherein each of the plurality of pieces of second pulse wave data comprises a pulse wave intensity tag and a phase difference tag, wherein the phase difference tag is associated with a phase difference between a phase of the second arterial waveform and a default phase” (claim 17), “wherein each of the plurality of pieces of second pulse wave data further comprises a first standard deviation corresponding to the pulse wave intensity tag and a second standard deviation corresponding to the phase difference tag” (claim 18), and “wherein the plurality of labelled probability values is associated with a normal condition or the abnormal condition of a respective one of the plurality of meridians” (claim 19)),
Further describe the pre-solution activity (“sensing, by the pressure sensor, a plurality of arteries of a plurality of second subjects, and a plurality of second arterial waveforms being obtained by the plurality of arteries of the plurality of second subjects” (claim 2), “inputting the plurality of pieces of first pulse wave data of the plurality of meridians into an input layer of the pulse condition prediction model, wherein a product of a number of the plurality of meridians and a parameter number corresponding to the plurality of pieces of first pulse wave data, equals to a number of neurons of the input layer” (claim 3), “wherein inputting, by the processor, the plurality of pieces of training data into the initial neural network model comprises: using the plurality of meridians and a plurality of parameters corresponding to the plurality of pieces of second pulse wave data as an input layer of the initial neural network model, wherein a product of a number of the plurality of meridians and a parameter number of the plurality of parameters corresponding to the plurality of pieces of second pulse wave data, equals to a number of neurons of the input layer” (claim 6), “the pressure sensor is further configured to sense a plurality of arteries of a plurality of second subjects to obtain a plurality of second arterial waveforms” (claim 11), “wherein the processor is configured to input the plurality of pieces of first pulse wave data of the plurality of meridians into an input layer of the pulse condition prediction model, wherein a product of a number of the plurality of meridians and a parameter number corresponding to the plurality of pieces of first pulse wave data, equals to a number of neurons of the input layer” (claim 13), “wherein the processor is configured to use the plurality of meridians and a plurality of parameters corresponding to the plurality of pieces of second pulse wave data as an input layer of the initial neural network model, wherein a product of a number of the plurality of meridians and a parameter number of the plurality of parameters corresponding to the plurality of pieces of second pulse wave data, equals to a number of neurons of the input layer” (claim 16)), and
Further describe the post-solution activity (“an input device connected to the processor and configured to receive the plurality of labelled probability values” (claim 12)).
Taken alone or in combination, the additional elements do not integrate the judicial exception into a practical application at least because the abstract idea is not applied, relied on, or used in a meaningful way. The additional elements do not add anything significantly more than the abstract idea. The collective functions of the additional elements merely provide computer/electronic implementation and processing, and no additional elements beyond those of the abstract idea. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements improves the functioning of a computer, output device, improves technology other than the technical field of the claimed invention, etc. The result of the abstract idea does not cause the computing device and/or application to perform differently.
Therefore, claims 1-3, 6-13, and 16-19 are rejected as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 6-13, and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Furness (US 20170258336), Sadriev (US 20190038235), Hatib (US 20100204590), and Lan (TW 202112304 – cited by Applicant).
Regarding claims 1-2 and 7-9, Furness discloses sensing, by a pressure sensor, a first arterial waveform of an artery of a first subject (Paragraph 0012, “The system employs a set of sensors or transducers to capture the pulse waveforms at one or more locations, for example at three locations along a radial artery of the subject or patient”; Fig. 1, sensor/transducer 108 measuring pulse of subjects 106; Figs. 2A-C),
generating, by a processor (Fig. 1, one or more signal processors 144), to-be-predicted data based on the first arterial waveform, wherein the to-be-predicted data comprises a plurality of pieces of first pulse wave data of a plurality of meridians (Paragraph 0105, measuring pulse data at multiple locations on the hand, which Examiner interprets as a plurality of pulse wave data on a plurality of meridians), wherein each of the plurality of pieces of first pulse wave data comprises a pulse wave intensity tag, wherein the pulse wave intensity tag indicates an intensity of “Qi” (Paragraph 0210, pulse width/strength. As Applicant describes “Qi” as the amplitude of the pulse, Furness reads on this limitation by measuring pulse width/strength as Examiner interprets the pulse width/strength measurement to be the amplitude of the pulse waveform); and
inputting, by the processor, the to-be-predicted data into a pulse condition prediction model (Paragraph 0210, inputting the measured data into the database for the system to employ machine learning techniques), and a plurality of predicted pulse conditions being generated by the pulse condition prediction model data (Paragraph 0046, “The system may generate diagnostic models that correlate pulse waveform information, and optionally symptoms, with diagnoses and/or suggested remedial or preventive measures and/or generate metrics of cardiac function”; Paragraph 0186) performing parallel computation via a plurality of hidden layers having the to-be-predicted (Paragraph 0081 and Fig. 1, modeling layer 184b of the machine learning system 162; Paragraph 0089, wherein the system 162 may have more than one predictive models, which Examiner interprets to mean more than one hidden layer)
wherein the conditions are generated based on an abnormal condition of at least one of the plurality of meridians (Paragraph 0047, “The diagnoses can be with respect to various medical or other conditions, ailments and/or maladies”).
Regarding the limitations of claims 2 and 7-9, Furness further discloses sensing a plurality of arteries of a plurality of second subjects, and a plurality of second arterial waveforms being obtained by the plurality of arteries of the plurality of second subjects (Paragraphs 0052, “The front-end system 102 collects diagnostically relevant information about a plurality of subjects 106 (only one shown)”), generating, by the processor, a plurality of pieces of training data based on the plurality of second arterial waveforms (Paragraphs 0080-0081, wherein the initial data set can be used to create a training data subset), wherein each of the plurality of pieces of training data comprises a plurality of pieces of second pulse wave data of the plurality of meridians (Paragraph 0069, wherein multiple waveforms are taken and one or more defining characteristics/parameters are detected), and inputting the training data into an initial neural network model (Paragraph 0007, wherein the training is performed on a neural network) to generate the pulse condition prediction model (Paragraph 0080-0081, wherein the training data subset is received in the input layer to construct a model).
Lastly, Furness discloses wherein each of the plurality of pieces of second pulse wave data comprises a pulse wave intensity tag (Paragraph 0210).
Furness fails to disclose measuring phase difference between a phase of a waveform and a default phase, determining a standard deviation of the pressure wave intensity and phase difference values, and determining probability values of the pulse condition. Furness further fails to disclose wherein generating the to-be-predicted data comprises extracting the plurality of pieces of first pulse wave data from a plurality of harmonics of the first arterial waveform based on a resonance principle, and wherein the plurality of predicted probability values are further generated based on an abnormal condition of at least one of the plurality of meridians, and the abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation, wherein the default standard deviation for a first group of the plurality of meridians is different from a default standard deviation for a second group of the plurality of meridians. Lastly, Furness fails to disclose wherein the training data has labelled probability values corresponding to the pulse conditions and an abnormal condition.
Furness and Sadriev are in the same field of measuring pulse pressure. Sadriev teaches a method for detecting blood pressure changes (Abstract) wherein a system computes the pulse amplitudes (Fig. 3) and phase shift values based on a difference between a historical mode and a more recent mode (Paragraph 0049). Sadriev discusses that phase shift values may indicate changes in the blood pressure (Paragraph 0034). As Furness is concerned with measuring pulse conditions from blood pressure data, Sadriev teaches a method of measuring phase shift as it may indicate changes in blood pressure. Furness would benefit from this added measurement as it would aid in determining blood pressure and blood pressure changes. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Furness to incorporate the phase shift calculation of Sadriev to indicate changes in the blood pressure.
Furness, Sadriev, and Hatib are in the same field of measuring pulse pressure. Hatib teaches an analogous pressure sensor that uses a statistical model for detection of vascular conditions from arterial pressure waveform data, wherein the standard deviation of parameters from the arterial pressure waveform is measured and the difference is compared (Paragraphs 0020 – 0021). Further, Hatib discusses that the difference “is often located along a continuum and a particular subject may have a value between a definite positive indication and a definite negative indication or for some reason in that subject the particular factor may appear to be within a normal range even though the subject is experiencing the vascular condition” (Paragraph 0020; Examiner interprets this to mean that different measurements (i.e., meridians) may have different standard deviations as one subject may experience different values of a standard deviation difference. As such, Hatib reads on the limitation of the default standard deviation being different between a first group of meridians and a second group of meridians). One of ordinary skill in the art would have been motivated in applying this known method of Hatib to the pulse condition method of Furness and Sadriev as a difference in standard deviation typically registers a difference between subjects experiencing a particular vascular condition and those not experiencing the condition (Examiner interprets this to read on the limitation of the “abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation”, as the comparison in standard deviations results in determining if a particular vascular condition is present), and the results of calculating a standard deviation of the measured would have been predictable to one of ordinary skill in the art. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method Furness and Sadriev to incorporate the teachings of calculating a standard deviation of Hatib as a difference in standard deviation is shown between those experiencing a particular vascular condition and those not experiencing the condition.
Furness, Sadriev, Hatib, and Lan are in the same field of measuring pulse pressure. Lan teaches a pulse condition analysis method wherein a prediction model generates probability values of pulse conditions (Page 4, paragraph 2, “Among them, in the case of pulse classification in this embodiment, there may be several possibilities for the interpretation of the pulse. For example, the probability of Ping mai is 85%, and the probability of Xian mai is 85%. The probability of pulse is 10%, the probability of thin pulse is 3%, and the probability of Shen pulse is 1%. Please follow the picture shown in Figure 6. Reply to the content displayed on the smartphone 40, which can be set to display only the highest probability The pulse condition of (for example, only the prediction result is Ping mai), or in addition to the prediction result, the possibility of various pulse conditions can also be displayed together, and the probability can be displayed together for the reference of subject 1 or medical staff”), wherein the data is generated from the signals by converting them to the frequency domain and using resonance theory (Page 4, paragraphs 2-3, using resonance theory; Examiner interprets the resonance theory to read on the limitation of “extracting the plurality of pieces of first pulse wave data from a plurality of harmonics of the first arterial waveform based on a resonance principle”). Additionally, Lan teaches wherein the inputting to the pulse condition prediction model comprises inputting the plurality of pieces of training data into an input layer initial neural network model, and the pulse condition prediction model being generated by the initial neural network model having the plurality of pieces of training data (Page 3, paragraphs 2-3, wherein the prediction model is obtained by pre-training by the steps identified above; Page 7, paragraph 1, wherein the model is a neural network) and each of the plurality of pieces of training data has second pulse wave data having a plurality of labelled probability values corresponding to the plurality of pulse conditions and an abnormal condition (Page 3, paragraphs 2-3, wherein at least one kind of pulse condition data is collected and wherein the pulse condition results of the training samples are known; Page 4, paragraph 3, wherein the probabilities are related to conditions of the pulse). Lan discusses these steps are useful to determine the patient’s health status/state and disease risk. As Furness as modified by Sadriev and Hatib are concerned with measuring pulse pressure data to determine a pulse condition, Lan discloses measuring the probabilities of certain pulse conditions, which is beneficial to determine a patient’s health status, state, and disease risk. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Furness, Sadriev, and Hatib to incorporate the teachings of generating a probability of pulse conditions using a trained neural network of Lan for assessing a patient’s health status and disease risk.
Regarding claim 3, Furness as modified further discloses inputting the plurality of pieces of first pulse wave data of the plurality of meridians into an input layer of the pulse condition prediction model (Paragraphs 0069 and 0078; Fig. 1, input layer 184a). As the number of inputs into the input layer would inherently equal the number of neurons of the input layer, Furness reads on the limitation of “wherein a product of a number of the plurality of meridians and a parameter number corresponding to the plurality of pieces of first pulse wave data, equals to a number of neurons of the input layer”.
Regarding claim 6, Furness as modified further discloses using the plurality of meridians and a plurality of parameters corresponding to the plurality of pieces of second pulse wave data as an input layer of the initial neural network model (Paragraph 0069, wherein the pulse wave information can take the form of one or more values for one or more defining characteristics or parameters of one or more pulse waveforms detects from a subject; Paragraphs 0080-0081, wherein the initial data set can be used to create a training data subset). As the number of inputs into the input layer would inherently equal the number of neurons of the input layer, Furness reads on the limitation of “wherein a product of a number of the plurality of meridians and a parameter number corresponding to the plurality of pieces of first pulse wave data, equals to a number of neurons of the input layer”.
Regarding claims 10-11 and 17-19, Furness discloses a pressure sensor configured to sense a first arterial waveform from an artery of a first subject (Paragraph 0012, “The system employs a set of sensors or transducers to capture the pulse waveforms at one or more locations, for example at three locations along a radial artery of the subject or patient”; Fig. 1, sensor/transducer 108 measuring pulse of subjects 106; Figs. 2A-C),
a processor (Fig. 1, one or more signal processors 144) connected to the pressure sensor and configured to generate to-be-predicted data according to the first arterial waveform and input the to-be-predicted data to a pulse condition prediction model (Paragraph 0210, inputting the measured data into the database for the system to employ machine learning techniques) to generate a plurality of pulse conditions (Paragraph 0046, “The system may generate diagnostic models that correlate pulse waveform information, and optionally symptoms, with diagnoses and/or suggested remedial or preventive measures and/or generate metrics of cardiac function”; Paragraph 0186) by performing parallel computation via a plurality of hidden layers having the to-be-predicted data (Paragraph 0081 and Fig. 1, modeling layer 184b of the machine learning system 162; Paragraph 0089, wherein the system 162 may have more than one predictive models, which Examiner interprets to mean more than one hidden layer),
wherein the to-be-predicted data comprises a plurality of pieces of first pulse wave data of a plurality of meridians (Paragraph 0105, measuring pulse data at multiple locations on the hand, which Examiner interprets as a plurality of pulse wave data on a plurality of meridians), wherein each of the plurality of pieces of first pulse wave data comprises a pulse wave intensity tag, wherein the pulse wave intensity tag indicates an intensity of “Qi” (Paragraph 0210, pulse width/strength. As Applicant describes “Qi” as the amplitude of the pulse, Furness reads on this limitation by measuring pulse width/strength as Examiner interprets the pulse width/strength measurement to be the amplitude of the pulse waveform); and
wherein the conditions are generated based on an abnormal condition of at least one of the plurality of meridians (Paragraph 0047, “The diagnoses can be with respect to various medical or other conditions, ailments and/or maladies”).
Regarding the limitations of claims 11 and 17-19, Furness further discloses wherein the processor is configured to sense a plurality of arteries of a plurality of second subjects to obtain a plurality of second arterial waveforms (Paragraphs 0052, “The front-end system 102 collects diagnostically relevant information about a plurality of subjects 106 (only one shown)”), where the processor is further configured to generate a plurality of pieces of training data according to the plurality of second arterial waveforms (Paragraphs 0080-0081, wherein the initial data set can be used to create a training data subset), to input the plurality of pieces of training data to an initial neural network (Paragraph 0007, wherein the training is performed on a neural network) model to train the initial neural network model into the pulse condition prediction model (Paragraph 0080-0081, wherein the training data subset is received in the input layer to construct a model),
wherein each of the plurality of pieces of training data comprises a plurality of pieces of second pulse wave data of the plurality of meridians (Paragraph 0069, wherein multiple waveforms are taken and one or more defining characteristics/parameters are detected).
Lastly, Furness discloses wherein each of the plurality of pieces of second pulse wave data comprises a pulse wave intensity tag (Paragraph 0210).
Furness fails to disclose measuring phase difference between a phase of a waveform and a default phase, determining a standard deviation of the pressure wave intensity and phase difference values, and determining probability values of the pulse condition. Furness further fails to disclose wherein the plurality of predicted probability values are further generated based on an abnormal condition of at least one of the plurality of meridians, and the abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation, wherein the default standard deviation for a first group of the plurality of meridians is different from a default standard deviation for a second group of the plurality of meridians. Lastly, Furness fails to disclose wherein the training data has labelled probability values corresponding to the pulse conditions and an abnormal condition.
Furness and Sadriev are in the same field of measuring pulse pressure. Sadriev teaches a method for detecting blood pressure changes (Abstract) wherein a system computes the pulse amplitudes (Fig. 3) and phase shift values based on a difference between a historical mode and a more recent mode (Paragraph 0049). Sadriev discusses that phase shift values may indicate changes in the blood pressure (Paragraph 0034). As Furness is concerned with measuring pulse conditions from blood pressure data, Sadriev teaches a method of measuring phase shift as it may indicate changes in blood pressure. Furness would benefit from this added measurement as it would aid in determining blood pressure and blood pressure changes. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Furness to incorporate the phase shift calculation of Sadriev to indicate changes in the blood pressure.
Furness, Sadriev, and Hatib are in the same field of measuring pulse pressure. Hatib teaches an analogous pressure sensor that uses a statistical model for detection of vascular conditions from arterial pressure waveform data, wherein the standard deviation of parameters from the arterial pressure waveform is measured and the difference is compared (Paragraphs 0020 – 0021). Further, Hatib discusses that the difference “is often located along a continuum and a particular subject may have a value between a definite positive indication and a definite negative indication or for some reason in that subject the particular factor may appear to be within a normal range even though the subject is experiencing the vascular condition” (Paragraph 0020; Examiner interprets this to mean that different measurements (i.e., meridians) may have different standard deviations as one subject may experience different values of a standard deviation difference. As such, Hatib reads on the limitation of the default standard deviation being different between a first group of meridians and a second group of meridians). One of ordinary skill in the art would have been motivated in applying this known method of Hatib to the pulse condition method of Furness and Sadriev as a difference in standard deviation typically registers a difference between subjects experiencing a particular vascular condition and those not experiencing the condition (Examiner interprets this to read on the limitation of the “abnormal condition is determined by comparing the first standard deviation or the second standard deviation with a corresponding default standard deviation”, as the comparison in standard deviations results in determining if a particular vascular condition is present), and the results of calculating a standard deviation of the measured would have been predictable to one of ordinary skill in the art. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method Furness and Sadriev to incorporate the teachings of calculating a standard deviation of Hatib as a difference in standard deviation is shown between those experiencing a particular vascular condition and those not experiencing the condition.
Furness, Sadriev, Hatib, and Lan are in the same field of measuring pulse pressure. Lan teaches a pulse condition analysis method wherein a prediction model generates probability values of pulse conditions (Page 4, paragraph 2, “Among them, in the case of pulse classification in this embodiment, there may be several possibilities for the interpretation of the pulse. For example, the probability of Ping mai is 85%, and the probability of Xian mai is 85%. The probability of pulse is 10%, the probability of thin pulse is 3%, and the probability of Shen pulse is 1%. Please follow the picture shown in Figure 6. Reply to the content displayed on the smartphone 40, which can be set to display only the highest probability The pulse condition of (for example, only the prediction result is Ping mai), or in addition to the prediction result, the possibility of various pulse conditions can also be displayed together, and the probability can be displayed together for the reference of subject 1 or medical staff”). Additionally, Lan teaches wherein the inputting to the pulse condition prediction model comprises inputting the plurality of pieces of training data into an input layer initial neural network model, and the pulse condition prediction model being generated by the initial neural network model having the plurality of pieces of training data (Page 3, paragraphs 2-3, wherein the prediction model is obtained by pre-training by the steps identified above; Page 7, paragraph 1, wherein the model is a neural network) and each of the plurality of pieces of training data has second pulse wave data having a plurality of labelled probability values corresponding to the plurality of pulse conditions and an abnormal condition (Page 3, paragraphs 2-3, wherein at least one kind of pulse condition data is collected and wherein the pulse condition results of the training samples are known; Page 4, paragraph 3, wherein the probabilities are related to conditions of the pulse). Lan discusses these steps are useful to determine the patient’s health status/state and disease risk. As Furness as modified by Sadriev and Hatib are concerned with measuring pulse pressure data to determine a pulse condition, Lan discloses measuring the probabilities of certain pulse conditions, which is beneficial to determine a patient’s health status, state, and disease risk. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Furness, Sadriev, and Hatib to incorporate the teachings of generating a probability of pulse conditions using a trained neural network of Lan for assessing a patient’s health status and disease risk.
Regarding claim 12, while Furness as modified fails to explicitly disclose using an input device configured to receive the labelled probability values, Furness as modified discloses an input/output device (Fig. 1, input/output device 152; Paragraph 0066, wherein multiple types of input devices may be connected to the system; Paragraph 0071, “the symptom information can take the form of a description of one or more primary and/or secondary diagnoses by the practitioner 116 for the specific subject 106. The primary and/or second diagnosis may be entered in freeform text, for instance via a freeform text field of a user interface … the primary and/or secondary diagnosis may only be entered when collecting data or information for initially populating or training the system 100”). One of ordinary skill would understand that labeling data would require input from an input device, thus, Furness as modified reads on the claim.
Regarding claim 13, Furness as modified further discloses wherein the processor is configured to input the plurality of pieces of first pulse wave data of the plurality of meridians into an input layer of the pulse condition prediction model (Paragraphs 0069 and 0078; Fig. 1, input layer 184a). As the number of inputs into the input layer would inherently equal the number of neurons of the input layer, Furness reads on the limitation of “wherein a product of a number of the plurality of meridians and a parameter number corresponding to the plurality of pieces of first pulse wave data, equals to a number of neurons of the input layer”.
Regarding claim 16, Furness as modified further discloses wherein the processor is configured to use the plurality of meridians and a plurality of parameters corresponding to the plurality of pieces of second pulse wave data as an input layer of the initial neural network model (Paragraph 0069, wherein the pulse wave information can take the form of one or more values for one or more defining characteristics or parameters of one or more pulse waveforms detects from a subject; Paragraphs 0080-0081, wherein the initial data set can be used to create a training data subset). As the number of inputs into the input layer would inherently equal the number of neurons of the input layer, Furness reads on the limitation of “wherein a product of a number of the plurality of meridians and a parameter number corresponding to the plurality of pieces of first pulse wave data, equals to a number of neurons of the input layer”.
Response to Arguments
Applicant’s arguments, see pages 10-11, filed 05/07/2026, with respect to the 35 U.S.C. §112(b) rejections have been fully considered and are partially persuasive. Applicant has amended the independent claims to recite that the to-be-predicted data includes pulse wave intensity tag (amplitude(s) of the waveform), phase difference, and one standard deviation each from the amplitude and phase difference measurements. Thus, this rejection is withdrawn.
Applicant argues that by amending the claim to recite that the pulse condition prediction model performs parallel computation via a plurality of hidden layers overcomes the rejection to clarify how the predicted probability values are generated. However, Examiner respectfully disagrees.
It still remains unclear how the prediction model generates the predicted probability values. Per Applicant’s specification paragraph 0033, “And, deep learning may be implemented by graphics processing unit (GPU) or tensor processing unit (TPU) performing parallel computation” (the only instance of describing “parallel computation”). This limitation does not clarify how the model makes these calculations; rather, the claim merely states that the model performs calculations. Additionally, per Applicant’s specification paragraphs 0039-0040, the neural network model has a plurality of hidden layers. There is no recitation of how the model makes the calculation, what algorithms are used, and/or what weights may be applied to the data (if any) in the hidden layers. Thus, it is still unclear how the predicted probability values are generated based on the to-be-predicted data.
Applicant has corrected claim 11 to recite “pulse condition prediction model”. Therefore, this rejection is withdrawn.
Upon consideration of the amendments, further 112(b) rejections have been applied.
Applicant’s arguments, see pages 11-12, filed 05/07/2026, with respect to the 35 U.S.C. §103 rejections of claims 1-3, 6-13, and 16-19 have been fully considered but are not persuasive.
Applicant asserts that Hatib fails to disclose or suggest setting different variation tolerances for different meridians of the human body nor differences in high-frequency and low-frequency harmonics. Examiner notes that the limitation of setting variation tolerances for different meridians is not found in the claims, and the limitation of generating the to-be-predicted data from a plurality of harmonics based on a resonance principle is not found in claim 10. While the claims are interpreted in light of the specification, limitations from the specification are not read into the claims (See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Applicant asserts that, since Hatib does not disclose or suggest the above limitations not found in the claims, Hatib does not disclose or suggest that different meridians have different standard deviations. Examiner disagrees.
The claims require that the default standard deviation for a first group of the plurality of meridians be different from a default standard deviation for a second group of the plurality of meridians. As described above, Hatib discusses that the difference in standard deviations of pressure waveform data “is often located along a continuum and a particular subject may have a value between a definite positive indication and a definite negative indication or for some reason in that subject the particular factor may appear to be within a normal range even though the subject is experiencing the vascular condition” (Paragraph 0020). The combination of Furness, Sadriev, and Hatib discloses taking multiple measurements of pressure waveform data, including pulse width/strength and phase difference, and taking the standard deviation of these measurements. Examiner interprets this to mean that the plurality of measurements (i.e., meridians) performed by Furness may have different standard deviations as one subject may experience different values of a standard deviation difference, as suggested by Hatib. As such, Furness as modified by Sadriev and Hatib reads on the limitation of the default standard deviation being different between a first group of meridians and a second group of meridians.
As such, the claims remain rejected. The rejection above has been updated to reflect the amendments.
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 NOAH MICHAEL HEALY whose telephone number is (703)756-5534. The examiner can normally be reached Monday - Friday 8:30am - 5:30pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jason Sims can be reached at (571)272-7540. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/NOAH M HEALY/Examiner, Art Unit 3791
/JASON M SIMS/Supervisory Patent Examiner, Art Unit 3791
Prosecution Insights