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 .
DETAILED ACTION
In the response filed on, 17 November 2025, the following has occurred: claims 1 and 11 have been amended.
Now claims 1-20 are pending.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 17 November 2025 has been entered.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1 and 11 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite system and method for generating a nourishment program for a person. The limitations of:
Claim 1, which is representative of claim 11
[… obtain …] at least a congenital factor relating to a subject, wherein the congenital factor comprises prognostic indicators; implementing parameter training data as a function of the congenital factor […]; determine, using the at least a congenital factor, a nourishment identifier, wherein generating the nourishment identifier includes: generating a congenital parameter as a function of a parameter […] model wherein the parameter […] model is [… built …] using parameter training data configured to correlate at least a congenital factor input to at least a congenital factor output; assigning, using the parameter […] model, the at least a congenital factor, a phenotype; generating, using the phenotype, a congenital relationship, wherein the congenital relationship relates at least an effect of the nourishment identifier on the phenotype and wherein generating the congenital relationship comprises: [… obtaining …] training data comprising a plurality of nutrients correlated to a plurality of effects on congenital disorders; segmenting the training data into one or more cohorts, wherein at least a first cohort comprises healthy subjects and a remainder of the one or more cohorts is classified to least one phenotype; identifying a congenital relationship mismatch for each cohort of the remainder of the one or more cohorts by comparing each of the remainder of the one or more cohorts to the at least a first cohort; and [… creating …] a nutraceutical model to receive phenotypes as inputs and generate congenital relationships as outputs as a function of the training data and the congenital mismatch for each cohort of the remainder of one or more cohorts, wherein the congenital relationship is described by a vector, wherein the vector includes a direction and magnitude that describes if a disorder will improve as a function of a plurality of nutrient amounts and the congenital relationship; and determining the nourishment identifier as a function of the congenital relationship; identify, using the nourishment identifier, at least a nutrition element; calculate a plurality of nutrient amounts of the at least a nutrition element as a function of a plurality of predicted effects of the plurality of nutrient amounts wherein generating the plurality of nutrient amounts comprises: iteratively generating nourishment training data sets comprising previous outputs of the nutraceutical model correlated to previous effects on the subject; generating a relationship between the outputs of the nutraceutical model and the previous effects on the subject; and calculating the plurality of nutrient amounts for the subject as a function of the relationship; and generate a consumption model based on the at least a nutrition element and the plurality of nutrient amounts.
, as drafted, is a process that under its broadest reasonable interpretation, covers a method of organizing human activity (i.e., managing personal behavior including following rules or instructions) via the implementation of generic computer components. That is, via human interaction with the computing device, the claimed invention amounts to managing personal behavior or interaction between people, the Examiner notes as stated in in 2106.04(a)(2), “certain activity between a person and a computer… may fall within the “certain methods of organizing human activity” grouping”. For example, via human interaction with the computing device, the claim encompasses collection of information about a user to make determinations about nourishment for the user to provide the user a consumption model based on determined nutritional needs of the user and use the created model to provide a human user a recommendation for their health. If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “method of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of a computing device, which implements the identified abstract idea. The computing device is recited at a high-level of geniality (i.e., general purpose computers; see Applicant’s Specification Figure 1 and paragraph [0008]) such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claims recite the additional element of “acquire… receiving…”, “using a distributed data storage protocol” and “the parameter machine learning model is iteratively trained… using the parameter machine learning model… training…”. The “acquire… receiving…” steps are recited at a high-level of generality (i.e., as a general means of receiving/transmitting data) and amounts to the mere transmission and/or receipt of data, which is a form of extra-solution activity. The “using a distributed data storage protocol” steps are recited at a high-level of generality (i.e., as a general means of distributing data) and amounts to the mere use of a cloud, which is a form of extra-solution activity. The “the parameter machine learning model is iteratively trained… using the parameter machine learning model… training…” is recited at a high-level of generality (i.e., training a generic off-the-shelf machine learning model to make predictions and using the model in a generic way) and amounts to merely linking of the abstract idea to particular technological environment. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of a computing device to perform the noted steps amounts to no more than mere instructions to apply the exception using generic hardware components. Mere instructions to apply an exception using a generic hardware component cannot provide an inventive concept (“significantly more”).
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “acquire… receiving…”, “using a distributed data storage protocol” and “the parameter machine learning model is iteratively trained… using the parameter machine learning model… training…” were considered extra-solution activity and/or generally linking the abstract idea to a particular technological environment. The “acquire… receiving…” steps have been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in MPEP 2106.0S(d)(II)(i) "Receiving or transmitting data over a network" is well-understood, routine, and conventional. The “using a distributed data storage protocol” has been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in Koumpan (20200138362): see below but at least Figure 4, paragraph [0054]; Peri (2021/0118574): paragraph [0043]; Apte (20160232280): paragraph [0029]; the use of a cloud to distribute data is well-understood, routine, and conventional. The “the parameter machine learning model is iteratively trained… using the parameter machine learning model… training…” has been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in Peri (2021/0118574): see below but at least paragraphs [0074]-[0077], [0106]; Apte (20160232280): paragraph [0076]; training and use of a machine learning model is well-understood, routine, and conventional. Well-understood, routine, and conventional elements/functions cannot provide “significantly more.” As such the claim is not patent eligible.
Claims 2-9 and 11-20 are similarly rejected because either further define the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible.
Claims 2, 5, 12 and 15 further define the training and use of the machine learning process considered above, however this training and use of machine learning was already considered above and is incorporated herein.
Claims 3-4, 7, 13-14 and 17 recite training and use of a classifier/model, however the claim does not recite that this classifier/model is a machine learning model and is therefore not an additional element, as the claims do not recite any additional elements, they cannot provide a practical application and/or significantly more.
Claims 6 and 16 recite creation of training datasets, but does not recite any additional elements and therefore cannot provide a practical application and/or significantly more.
Claims 8 and 18 recite use of a linear programming function, but does not recite any additional elements and therefore cannot provide a practical application and/or significantly more.
Claims 9-10 and 19-20 further define the consumption model and use of a nourishment score, but does not recite any additional elements and therefore cannot provide a practical application and/or significantly more.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. No. 2020/0138362 (hereafter “Koumpan”), in view of U.S. Patent App. No. 2015/0018240 (hereafter “Jackson”), in view of U.S. Patent App. No. 2021/0118574 (hereafter “Peri”).
Regarding (Currently Amended) claim 1, Koumpan teaches a system for generating a nourishment program for addressing congenital disorders (Koumpan: paragraph [0001]-[0002], “generation of a maternal nutrition plan for pregnant woman to prevent the development of chronic diseases in fetuses… a method, system, and computer program product for generation of a personalized maternal nutrition plan for a pregnant mother”. The Examiner notes a chronic disease in a fetus teaches a congenital disorder under the broadest reasonable interpretation), the system comprising:
--a computing device (Koumpan: paragraph [0002], “A computing device”), wherein the computing device is configured to:
--acquire at least a congenital factor relating to a subject, wherein the congenital factor comprises prognostic indicators (Koumpan: paragraph [0002], “A computing device receives real-time maternal physiological data associated with a pregnant mother and fetal physiological data. The computing device receives real-time environmental data associated with the pregnant mother.”, paragraph [0010], “Physiological reading device 110 may be… a genetic information reading device”, paragraph [0017], “fetal physiological sensor(s) 116 may be one or more of… a DNA sequence reading device, a chromosomal reading device”, paragraphs [0027]-[0028], “detect one or more abnormalities utilizing the data obtained from the relationship establishing module 144… an abnormality may be a quantitative or qualitative deviation from a preconfigured physiological metric for a healthy person… Types of abnormalities determined by the abnormality detecting module 147 may include… a DNA sequence indicating a genetic defect, a chromosomal defect… detect abnormalities such as too high a level of a bionutrient, or too low a level of a bionutrient based upon whether the real-time established relationship displays bionutrient data which differs from an accepted range of bionutrient data established by the historically established relationships”. Also see, paragraphs [0032]-[0033]. The Examiner notes genetic information that indicates a defect, reads on the broadest reasonable interpretation of a prognostic indicator in view of Applicant’s specification paragraphs [0010] and [0029]);
implementing [… machine learning …] as a function of the congenital factor using a distributed data storage protocol (Koumpan: Figures 1, 4, paragraph [0024]-[0026], “utilize a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit analysis performed by nutrition plan generating system 140, or any other computer-implemented means to establish a correlation between available maternal physiological data, fetal physiological data, and/or environmental data in real-time”, paragraphs [0053]-[0056], “Cloud computing is a model of service delivery for enabling convenient, on-demand network access to a shared pool of configurable computing resources”, paragraph [0071], “As shown, cloud computing environment 50 includes one or more cloud computing nodes 10”);
--determine, using the at least a congenital factor, a nourishment identifier (Koumpan: paragraphs [0008]-[0010], “During pregnancy, women require a larger intake of nutrients, including protein, carbohydrates, fats, omega-3 fatty acids, omega-6 fatty acids, iron, iodine, vitamin A, folate, etc. Nutrient deficiencies are associated with complications including, for example, birth defects, and poor post-birth physical and/or mental development… The time of year and environment the mother is in during the time of pregnancy also affects the nutritional needs of the mother and fetus… suggested amounts based on the user's personal needs… The suggested amounts of nutrients, food, drinks, dietary supplements, vitamins, etc. in the set or list may be derived from a user's physiological data… Physiological reading device 110 may be… a genetic information reading device”, paragraphs [0027]-[0029], “abnormality detecting module 147 detects a low value of vitamin c… where an abnormality for high blood pressure is detected, the maternal nutrition plan generated by the nutrition plan generation module 148 may contain a set or list of nutrients in suggested amounts for the mother to lower her blood pressure, including lower amounts of sodium and higher amounts of potassium, as well as higher amounts of water”), wherein generating the nourishment identifier includes:
generating a congenital parameter as a function of a parameter machine learning model […] (Koumpan: paragraph [0024]-[0026], “utilize a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit analysis performed by nutrition plan generating system 140, or any other computer-implemented means to establish a correlation between available maternal physiological data, fetal physiological data, and/or environmental data in real-time”, paragraph [0037], “the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses, the historically established relationships obtained from the historical mother and fetus relationship database 130.… detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison… generates a suggested maternal nutrition plan based upon the one or more abnormalities”);
--assigning, using the parameter machine learning model, the at least a congenital factor to a [… abnormality …] (Koumpan: paragraph [0011], “detects one or more abnormalities in the pregnant mother or the fetus”, paragraphs [0024]-[0026], “Relationship establishing module 144 represents hardware and/or software for establishing a real-time relationship between the maternal physiological data, the fetal physiological data, and the environmental data”, paragraph [0027], “Abnormality detecting module 147 represents software and/or hardware for nutrition plan generation system 140 to detect one or more abnormalities utilizing the data obtained from the relationship establishing module 144… Types of abnormalities determined by the abnormality detecting module 147 may include, but are not limited to, fast or slow maternal or fetal heartrate, under or over consumption of water or a particular nutrient, high or low blood pressure, a DNA sequence indicating a genetic defect, a chromosomal defect”);
--generating, using the [… abnormality ….], a congenital relationship, wherein the congenital relationship relates at least an effect of the nourishment identifier on the [… abnormality …] (Koumpan: paragraph [0024], “Relationship establishing module 144 represents hardware and/or software for establishing a real-time relationship between the maternal physiological data, the fetal physiological data, and the environmental data… making determinations regarding the real-time relationship for the generation of a nutrition plan”, paragraphs [0027]-[0029], “detect abnormalities such as too high a level of a bionutrient, or too low a level of a bionutrient based upon whether the real-time established relationship displays bionutrient data which differs from an accepted range of bionutrient data established by the historically established relationships… abnormality detecting module 147 may be able to directly predict which abnormalities have already resulted or likely will result, depending upon the levels bionutrients or other data”. The Examiner notes the relationship relates nourishment identifiers with abnormalities) and wherein generating the congenital relationship comprises: […];
identifying a congenital relationship mismatch for each cohort of the remainder of the one or more cohorts by comparing each of the remainder of the one or more cohorts to the at least a first cohort (Koumpan: paragraph [0027], “An “abnormality,” as discussed herein is a deviation from a regular, recommended, or ideal health state for a similar individual with regard to a nutrient, blood physiology, health conditional state, etc. for a healthy person without preexisting genetic, developmental, or other health disorders”, paragraph [0037], “a real-time relationship is established by the relationship establishing module… the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses, the historically established relationships obtained from the historical mother and fetus relationship database 130… abnormality detecting module 147 of nutrition plan generation system 140 detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison of the real-time established relationship with historically established relationships”. A relationship mismatch is determined for a healthy and abnormal cohort, which reads on what is required under the broadest reasonable interpretation); […],
wherein the congenital relationship […] describes if a disorder will improve as a function of a plurality of nutrient amounts and the congenital relationship (Koumpan: paragraph [0002], “detects one or more abnormalities in the real-time established relationship… detects one or more abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison of the real-time established relationship with historically established relationships”, paragraphs [0024]-[0025], “Relationship establishing module 144 may utilize a matching algorithm, artificial intelligence… The real-time relationship established may indicate “trends” in data”, paragraphs [0027]-[0029], “directly predict which abnormalities have already resulted or likely will result, depending upon the levels bionutrients or other data”. A relationship showing trends for a condition based on nutrition and relationships is taught, and teaches what is shown above, under the broadest reasonable interpretation); and
--determining the nourishment identifier as a function of the congenital relationship (Koumpan: paragraphs [0027]-[0029], “generate a maternal nutrition plan based upon one or more abnormalities… generate a nutrition plan to counter and/or prevent the one or more abnormalities previously detected by the abnormality detecting module 147. If, for example, abnormality detecting module 147 detects a low value of vitamin c, nutrition plan generation module 148 generates a nutrition plan high in vitamin c rich foods such as oranges, lemons, or recommends a vitamin c supplement”, paragraph [0037], “the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses… detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison… generates a suggested maternal nutrition plan based upon the one or more abnormalities”);
--identify, using the nourishment identifier, at least a nutrition element (Koumpan: paragraph [0009], “generate a nutrition plan containing nutrient, food, drinks, dietary supplements, vitamins, etc. containing a low amount of sodium to reduce blood pressure because a user's”, paragraph [0029], “Nutrition plan generation module 148 utilizes the nutritional information regarding foods, drinks, nutrition supplements, vitamins, etc. to automatically generate a nutrition plan to counter and/or prevent the one or more abnormalities previously detected by the abnormality detecting module 147”); and
calculate a plurality of nutrient amounts of the at least a nutrition element as a function of a plurality of predicted effects of the plurality of nutrient amounts wherein generating the plurality of nutrient amounts comprises: […] calculating the plurality of nutrient amounts for the subject as a function of the relationship (Koumpan: paragraph [0009], “"Nutrition plan" as discussed herein refers to computer- provided set or list of nutrients, food, drinks, dietary supplements, vitamins, etc. for a user to intake (or limit intake of) in suggested amounts… a set of nutrients in suggested amounts”, paragraph [0029], “the nutrition plan generated by nutrition plan generation module 148 may contain a set or list of nutrients in suggested amounts”, paragraph [0037], “a real-time relationship is established by the relationship establishing module… the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses, the historically established relationships obtained from the historical mother and fetus relationship database 130… abnormality detecting module 147 of nutrition plan generation system 140 detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison of the real-time established relationship with historically established relationships”); and
--generate a consumption model based on the at least a nutrition element and the plurality of nutrient amounts (Koumpan: paragraph [0015], “Reading interface 112 may also present further information to the user, including foods, drinks, vitamins, and/or other dietary supplements to consume to address one or more abnormalities, as well as a schedule of when to consume them in order for the user to comply with the personalized maternal nutrition plan presented to the individual”);
Koumpan may not explicitly teach (underlined below for clarity):
--assigning, using the parameter machine learning model the at least a congenital factor to a phenotype; generating, using the phenotype, a congenital relationship, wherein the congenital relationship relates at least an effect of the nourishment identifier on the phenotype;
receiving […] data comprising a plurality of nutrients correlated to a plurality of effects on congenital disorders;
Jackson teaches assigning, using the parameter machine learning model the at least a congenital factor to a phenotype; generating, using the phenotype, a congenital relationship, wherein the congenital relationship relates at least an effect of the nourishment identifier on the phenotype (Jackson: paragraph [0002], “a computer-implemented system for analyzing responses of an optically-visible rare-disease cell-phenotype of a cell to a drug or nutraceutical from the drug/nutraceutical library… detects the response of the optically-visible rare-disease cell-phenotype to a drug or nutraceutical from the drug/nutraceutical library… the computer-implemented system correlates the response of the optically-visible rare-disease phenotype to a drug or nutraceutical in the drug/nutraceutical library with the effect of the drug or nutraceutical on at least one symptom of the rare disease in vivo… an assay for a biomarker that correlates with the rare-disease phenotype”, paragraph [0023], “Certain rare diseases are associated with optically-visible cell phenotypes. As opposed to traditional biochemical assays, phenotypic screens based on optically-visible phenotypes enable medical professionals to visualize (a) the phenotypic response of a known drug/nutraceutical and (b) the whole cell effects (e.g., toxicity and dose response) of the known drug/nutraceutical”, paragraph [0040], “a cell with optically-visible rare-disease cell phenotype obtained (or, differentiated) from”);
receiving […] data comprising a plurality of nutrients correlated to a plurality of effects on congenital disorders (Jackson: paragraph [0002], “system correlates the response of the optically-visible rare-disease phenotype to a drug or nutraceutical”, paragraph [0028], “naturally-occurring cells obtained from a subject with a rare disease cell phenotype, cells derived from stem cells obtained from a subject with a rare disease cell phenotype, or cells derived from iPS cells produced from cells from a subject with a rare disease cell phenotype”);
One of ordinary skill in the art before the effective filing date would have found it obvious to include using determinations about phenotype and phenotype relationships as taught by Jackson within the determination and relationships using nutrition and abnormalities as taught by Koumpan with the motivation of “reduces the time, number of assays, and costs needed to identify known drugs/nutraceuticals that may be repurposed to treat rare diseases” (Jackson: paragraph [0023]).
Koumpan and Jackson may not explicitly teach (underlined below for clarity):
implementing parameter training data as a function of the congenital factor using a distributed data storage protocol;
generating a congenital parameter as a function of a parameter machine learning model wherein the parameter machine learning model is iteratively trained using parameter training data configured to correlate at least a congenital factor input to at least a congenital factor output;
receiving training data comprising a plurality of nutrients correlated to a plurality of effects on congenital disorders;
segmenting the training data into one or more cohorts, wherein at least a first cohort comprises healthy subjects and a remainder of the one or more cohorts is classified to least one phenotype;
training a nutraceutical model to receive phenotypes as inputs and generate congenital relationships as outputs as a function of the training data and the congenital mismatch for each cohort of the remainder of one or more cohorts,
wherein the congenital relationship is described by a vector, wherein the vector includes a direction and magnitude that describes if a disorder will improve as a function of a plurality of nutrient amounts and the congenital relationship;
iteratively generating nourishment training data sets comprising previous outputs of the nutraceutical model correlated to previous effects on the subject; generating a relationship between the outputs of the nutraceutical model and the previous effects on the subject;
Peri teaches implementing parameter training data as a function of the congenital factor using a distributed data storage protocol (Peri: paragraph [0041], “Using diverse technologies for collection, processing, storage and distribution of data such as… Cloud Servers”, paragraph [0074]-[0075], “techniques can be trained on millions of medical records having medical, clinical and biological characteristics of the mothers to attain the ability to generalize maternal and infant risks. Pre-processed data can be forwarded to the AI Suite for learning how to generalize and predict”);
generating a congenital parameter as a function of a parameter machine learning model wherein the parameter machine learning model is iteratively trained using parameter training data configured to correlate at least a congenital factor input to at least a congenital factor output (Peri: paragraph [0036], “a set of machine learning models/techniques trained to learn to extract information/data from the structured and unstructured data, assemble knowledge from the extracted data and map the assembled data to the characteristics of associated maternal, fetal and infant risks to perform a risk prediction, wherein the machine learning models are selected from, but not limited to, logistic regression, Support Vector Machine (SVM) regression and neural networks which include but not limited to, convolutional neural network (CNN), recurrent neural network (RNN) and long short-term memory model (LSTM)”, paragraph [0040], “The MIHIC system uses self-learning models including, but not limited to, reinforcement learning to continually improve the prediction of score and stratification of risk level as Low, Medium and High”, paragraphs [0074]-[0077], “Artificial Intelligence for Prediction… trained on millions of medical records having medical, clinical and biological characteristics of the mothers to attain the ability to generalize maternal and infant risks”, paragraphs [0105]-[0104], “For each iteration, weights w and biases B are updated using the function”. The Examiner notes the machine learning model is iteratively trained);
receiving training data comprising a plurality of nutrients correlated to a plurality of effects on congenital disorders (Peri: paragraph [0074]-[0075], “techniques can be trained on millions of medical records having medical, clinical and biological characteristics of the mothers to attain the ability to generalize maternal and infant risks. Pre-processed data can be forwarded to the AI Suite for learning how to generalize and predict”);
segmenting the training data into one or more cohorts, wherein at least a first cohort comprises healthy subjects and a remainder of the one or more cohorts is classified to least one phenotype (Peri: paragraph [0027], “stratifying pregnant mothers into High, Medium and Low risk categories through its MIHIC scores”, paragraphs [0036]-[0039], “a risk of interest across different population groups… risk factors for cohorts”, paragraph [0088], “number of patients with that risk in the training data set”. The training data is stratified into various cohorts);
training a nutraceutical model to receive phenotypes as inputs and generate congenital relationships as outputs as a function of the training data and the congenital mismatch for each cohort of the remainder of one or more cohorts (Peri: paragraph [0003], “detect the possible patterns that can lead to high risk of disease manifestation and progress in patients but also help them to recommend treatments”, paragraphs [0036]-[0039], “The suite of AI algorithms comprise a set of machine learning models/techniques trained to learn… risk factors associated with a risk of interest across different population groups… risk factors for cohorts”, paragraph [0117], “multiple machine learning model will be trained on subset of data and best ensemble of those models will be employed for the prediction”),
wherein the congenital relationship is described by a vector, wherein the vector includes a direction and magnitude that describes if a disorder will improve as a function of a plurality of nutrient amounts and the congenital relationship (Peri: paragraph [0029], “MIHIC system improves healthcare outcomes in mother, fetus and child by decreasing maternal and infant mortality rates, while improving other indicators of maternal and infant health by enabling early interventions”, paragraph [0036], “machine learning models are selected from, but not limited to, logistic regression, Support Vector Machine (SVM) regression”, paragraph [0040], “determine a risk score… continually improve the prediction of score and stratification of risk level as Low, Medium and High. MIHIC score is a quantification of identified possible risks to the mother, fetus and infant”, paragraphs [0070]-[0072], “Association between risk factors and clinical characteristics can be illustrated using scatter plots, correlation matrices depicting the degree of association and their impact… shows type of correlation and strength of relationship for the two preeclampsia risk factors. For example, in the women having high risk for preeclampsia the relationship between Urine protein and PCR is linear, with strong positive correlation”, paragraphs [0075]-[0077], “To improve the performance of the prediction model, vector representation can be adopted… information extracted from clinical notes and ultrasound scans are also combined with the other characteristics of the data and are represented as vectors… information about the properties of the object are represented in vectors”);
iteratively generating nourishment training data sets comprising previous outputs of the nutraceutical model correlated to previous effects on the subject; generating a relationship between the outputs of the nutraceutical model and the previous effects on the subject (Peri: paragraph [0036], “a set of machine learning models/techniques trained to learn to extract information/data from the structured and unstructured data, assemble knowledge from the extracted data and map the assembled data to the characteristics of associated maternal, fetal and infant risks to perform a risk prediction, wherein the machine learning models are selected from, but not limited to, logistic regression, Support Vector Machine (SVM) regression and neural networks which include but not limited to, convolutional neural network (CNN), recurrent neural network (RNN) and long short-term memory model (LSTM)”, paragraph [0040], “The MIHIC system uses self-learning models including, but not limited to, reinforcement learning to continually improve the prediction of score and stratification of risk level as Low, Medium and High”, paragraphs [0074]-[0077], “Artificial Intelligence for Prediction… trained on millions of medical records having medical, clinical and biological characteristics of the mothers to attain the ability to generalize maternal and infant risks”, paragraphs [0105]-[0104], “For each iteration, weights w and biases B are updated using the function”. The Examiner notes the machine learning model is iteratively trained);
One of ordinary skill in the art before the effective filing date would have found it obvious to include iteratively training a machine learning model with vectors representing learned relationships as taught by Peri within the machine learning models using learned relationships as taught by Koumpan and Jackson with the motivation of “improves healthcare outcomes in mother, fetus and child by decreasing maternal and infant mortality rates, while improving other indicators of maternal and infant health” (Peri: paragraph [0029]).
Regarding (Original) claim 2, Koumpan, Jackson and Peri teaches the limitations of claim 1, and further teaches wherein determining the nourishment identifier further comprises: training a parameter machine-learning model with training data that includes a plurality of data entries correlating congenital factors to congenital parameters; and generating the congenital parameter as a function of the parameter machine-learning model and the at least a congenital factor; and determining the nourishment identifier as a function of the congenital parameter (Koumpan: paragraph [0024]-[0026], “utilize a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit analysis performed by nutrition plan generating system 140, or any other computer-implemented means to establish a correlation between available maternal physiological data, fetal physiological data, and/or environmental data in real-time”, paragraph [0037], “the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses, the historically established relationships obtained from the historical mother and fetus relationship database 130.… detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison… generates a suggested maternal nutrition plan based upon the one or more abnormalities”; Peri: paragraphs [0036], [0040] and [0074]-[0077]).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (Previously Presented) claim 3, Koumpan, Jackson and Peri teaches the limitations of claim 1, and further teaches wherein identifying the phenotype further comprises: training a congenital classifier using training data which includes a plurality of data entries of congenital factors from a subset of categorized subjects; classifying the at least a congenital factor to the phenotype using the congenital classifier; and identifying the phenotype as a function of the classifying (Koumpan: paragraph [0026]-[0028], “similarity determining module 145 may rely on any of a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit analysis performed by nutrition plan generating system 140, or any other computer-implemented means to locate similarities in pre-pregnancy data available and the maternal physiological data… Types of abnormalities determined by the abnormality detecting module 147 may include, but are not limited to, fast or slow maternal or fetal heartrate, under or over consumption of water or a particular nutrient, high or low blood pressure, a DNA sequence indicating a genetic defect, a chromosomal defect, a high AFP level, exposure to high levels of pollutants, high or low body temperature, high skin conductance from large amounts of sweat, etc.”, paragraph [0037], “the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses, the historically established relationships obtained from the historical mother and fetus relationship database 130.… detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison… generates a suggested maternal nutrition plan based upon the one or more abnormalities”; Jackson paragraphs [0023] and [0040]; Peri: paragraphs [0036], [0040] and [0081]).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (Previously Presented) claim 4, Koumpan, Jackson and Peri teaches the limitations of claim 3, and further teaches wherein classifying further comprises classifying the at least a congenital parameter to a nutrition-linked congenital disorder category (Koumpan: paragraph [0026]-[0028], “locate similarities in pre-pregnancy data available and the maternal physiological data… Types of abnormalities determined by the abnormality detecting module 147 may include, but are not limited to, fast or slow maternal or fetal heartrate, under or over consumption of water or a particular nutrient, high or low blood pressure, a DNA sequence indicating a genetic defect, a chromosomal defect, a high AFP level, exposure to high levels of pollutants, high or low body temperature, high skin conductance from large amounts of sweat, etc.”; Peri: paragraph [0036], “a set of machine learning models/techniques trained to learn to extract information/data from the structured and unstructured data, assemble knowledge from the extracted data and map the assembled data to the characteristics of associated maternal, fetal and infant risks to perform a risk prediction”, paragraph [0040], “stratification of risk level as Low, Medium and High”, paragraph [0049], “characteristics are categorized under demographic, medical, clinical and genetic”. The Examiner notes determination of a DNA sequence classified as a genetic defect teaches what is require of the claim under the broadest reasonable interpretation).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (Original) claim 5, Koumpan, Jackson and Peri teaches the limitations of claim 1, and further teaches generating a nutraceutical model using a machine-learning process and training data which includes a plurality of data entries correlating effects of nourishment identifiers to phenotypes; and determining the congenital relationship as a function of the nutraceutical model and the phenotype (Koumpan: paragraph [0024]-[0026], “utilize a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit analysis performed by nutrition plan generating system 140, or any other computer-implemented means to establish a correlation between available maternal physiological data, fetal physiological data, and/or environmental data in real-time”, paragraph [0037], “the similarity determining module 145 compares the real-time established relationship with historically established relationships between pregnant mother and fetuses, the historically established relationships obtained from the historical mother and fetus relationship database 130.… detects any abnormalities in the real-time established relationship between the pregnant mother and the fetus based upon the comparison… generates a suggested maternal nutrition plan based upon the one or more abnormalities”; Jackson: paragraph [0005], “the computer-implemented system comprises an algorithm that determines degrees of response of the optically-visible rare-disease cell phenotype to a drug or nutraceutical in the drug/nutraceutical library”; Peri: paragraphs [0036], [0040], [0074]-[0077], [0158-[161] and [0345]).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (Previously Presented) claim 6, Koumpan, Jackson and Peri teaches the limitations of claim 5, and further teaches generate a nourishment training dataset from a plurality of congenital relationship outputs of the nutraceutical model (Koumpan: paragraph [0011], “obtain historically established relationships between pregnant mothers and fetuses, which are further utilized”, paragraph [0032], “Historically established relationships stored by the historical mother and fetus relationship database 130 are maintained”; Peri: paragraph [0004], “learn and adopt the real-time feed-back and incorporate it for future predictions”, paragraph [0082], “self-learning capabilities to learn continuously from the data provided”, paragraph [0098], “a dataset having characteristics of the pregnant women along with outcomes of delivery, the MIHIC platform processes the data for augmentation and forwards it to the AI suite consisting of various models to gain knowledge by assessing the maternal, fetal and infant conditions.”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (Original) claim 7, Koumpan, Jackson and Peri teaches the limitations of claim 1, and further teaches generating a nutrition model using training data including a plurality of data entries of nourishment identifiers correlating to nutrition elements; and determining the at least a nutrition element as a function of the nutrition model and the nourishment identifier (Koumpan: paragraph [0024]-[0026], “utilize a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit analysis performed by nutrition plan generating system 140, or any other computer-implemented means to establish a correlation between available maternal physiological data, fetal physiological data, and/or environmental data in real-time”, paragraph [0029], “Nutrition plan generation module 148 utilizes the nutritional information regarding foods, drinks, nutrition supplements, vitamins, etc. to automatically generate a nutrition plan to counter and/or prevent the one or more abnormalities previously detected by the abnormality detecting module 147”, paragraph [0037], “generates a suggested maternal nutrition plan based upon the one or more abnormalities”; Jackson: paragraph [0005], “the computer-implemented system comprises an algorithm that determines degrees of response of the optically-visible rare-disease cell phenotype to a drug or nutraceutical in the drug/nutraceutical library”; Peri: paragraphs [0036], [0040], [0074]-[0077], [0158-[161] and [0345]).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (Original) claim 8, Koumpan, Jackson and Peri teaches the limitations of claim 7, and further teaches generating a linear programming function with the plurality of nutrition elements wherein the linear programming function outputs at least an ordering of the plurality of nutrition elements according to the consumption model (Koumpan: paragraph [0015], “Reading interface 112 may also present further information to the user, including foods, drinks, vitamins, and/or other dietary supplements to consume to address one or more abnormalities, as well as a schedule of when to consume them in order for the user to comply with the personalized maternal nutrition plan presented to the individual”, paragraph [0024]-[0026], “utilize a matching algorithm, artificial intelligence, cognitive computing, a ranking algorithm, a best-fit