DETAILED ACTION
Claims 1-20 have been examined and are pending.
Claims 1-20 are rejected (Non-Final Rejection).
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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on April 25, 2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS has been considered by the examiner.
Claim Objection
Claim 3 is objected to because of the following informalities: Claim 3 recites “The method of claim 1, The method of claim 1, …”, which includes repetitive language. Appropriate correction is required.
Claim Rejections - 35 U.S.C. § 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.
To determine if a claim is directed to patent ineligible subject matter, the Court has guided the Office to apply the Alice/Mayo test, which requires:
1. Determining if the claim falls within a statutory category;
2A. Determining if the claim is directed to a patent ineligible judicial exception consisting of a law of nature, a natural phenomenon, or abstract idea; and
2B. If the claim is directed to a judicial exception, determining if the claim recites limitations or elements that amount to significantly more than the judicial exception.
(See MPEP 2106).
Claims 1-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more. The claim(s) recite a mental process and a mathematical calculation. See MPEP 2106.04(a)(2)(I) and MPEP 2106.04(a)(2)(III).
The following is an analysis based on the 2019 Revised Patent Subject Matter Eligibility Guidance (2019 PEG).
Claims 1-20 Step 1, Statutory Category:
Yes: Claims 1-20 are directed to the statutory category of a process. See MPEP § 2106.03.
Claim 1 Steps 2A and 2B:
Step 2A is a two-prong inquiry. See MPEP 2106.04(II)(A). Under the first prong, examiners evaluate whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim. Abstract ideas include mathematical concepts, certain methods of organizing human activity, and mental processes. MPEP 2106.04(a)(2). The second prong is an inquiry into whether the claim integrates a judicial exception into a practical application. MPEP 2106.04(d).
Claim 1 Step 2A Prong One: Does the Claim Recite a Judicial Exception?
For the sake of identifying the abstract ideas, a copy of the claim is provided below. The limitations of the claims that describe abstract ideas are bolded.
1. A method comprising:
determining, by a computing device, operational data associated with a plurality of operational parameters associated with an asset, wherein the plurality of operational parameters comprise one or more groups of operational parameters, and wherein each group of operational parameters of the one or more groups of operational parameters is labeled according to a feature score;
determining, based on the operational data, a plurality of feature scores for a predictive model;
training, based on a first portion of the operational data, the predictive model according to the plurality of feature scores;
testing, based on a second portion of the operational data, the predictive model; and
outputting, based on the testing, the predictive model.
The limitations “determining, by a computing device, operational data associated with a plurality of operational parameters associated with an asset, wherein the plurality of operational parameters comprise one or more groups of operational parameters, and wherein each group of operational parameters of the one or more groups of operational parameters is labeled according to a feature score”, “determining, based on the operational data, a plurality of feature scores for a predictive model” and “testing, based on a second portion of the operational data, the predictive model” are abstract ideas because they are directed to mental processes, observations, evaluations, judgments, and/or opinions. The limitations, as drafted and under broadest reasonable interpretation, “can be performed in the human mind or by a human using a pen and paper”. See MPEP 2106.04(a)(2)(III). For example, a human could determine operational data associated with an asset (e.g., transformer) and feature scores and test a predictive model (e.g., compare output with test/reference data). The limitations of “training, based on a first portion of the operational data, the predictive model according to the plurality of feature scores” can be performed using mathematical calculations/equations and therefore encompass mathematical concepts. See MPEP 2106.04(a)(2)(I).
Claim 1 Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception/Abstract idea into practical application?
Under Step 2A Prong Two, this judicial exception is not integrated into a practical application because the additional claim limitations outside of the abstract idea only present mere instructions to apply an exception, generally link the use of the judicial exception to the technological environment, or insignificant extra-solution activity. In particular, the claim recites the additional limitations of:
• “outputting, based on the testing, the predictive model” (insignificant extra-solution activity – mere data outputting – See MPEP 2106.04(d) referencing MPEP 2106.05(g); this limitation can be viewed as nothing more than mere data outputting in conjunction with the abstract idea (see MPEP 2106.05(g)).
Claim 1 Step 2B: Do the additional elements, considered individually and in combination, amount to significantly more than the judicial exception?
The Examiner must consider whether each claim limitation individually or as an ordered combination amount to significantly more than the abstract idea. This analysis includes determining whether an inventive concept is furnished by an element or a combination of elements that are beyond the judicial exception. For limitations that were categorized as “apply it” or generally linking the use of the abstract idea to a particular technological environment or field of use, the analysis is the same.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As explained above, there is one type of additional element(s). The additional element is “outputting … the predictive model”, which is at best viewed as nothing more than insignificant extra-solution activity (mere data outputting). Recitation of outputting a prediction model is mere data outputting that is recited at a high level of generality, and, is also Well-Understood, Routine and Conventional (WURC). This limitation therefore remains insignificant extra-solution activity even upon reconsideration. Thus, this limitation does not amount to significantly more.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and/or data outputting/gathering, which do not provide an inventive concept. The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception. See MPEP 2106.05(f).
Considering the claim limitations as an ordered combination, claim 1 does not include significantly more than the abstract idea. The claim 1 is not patent subject matter eligible. Dependent claims 2-10 are further addressed below after addressing each independent claim.
Claim 11 Steps 2A and 2B:
Claim 11 Step 2A Prong One: Does the Claim Recite a Judicial Exception?
For the sake of identifying the abstract ideas, a copy of the claim is provided below. The limitations of the claims that describe abstract ideas are bolded.
11. A method comprising:
receiving, at a computing device, operational parameter data comprising a plurality of operational parameters of an asset, wherein the plurality of operational parameters are determined during an analysis of one or more operations performed by the asset;
providing, to a predictive model, the operational parameter data; and
determining, based on the predictive model, a prediction score associated with a maintenance cycle performed on the asset.
The limitations “determining, based on the predictive model, a prediction score associated with a maintenance cycle performed on the asset” can be performed using mathematical calculations/equations and therefore encompass mathematical concepts. See MPEP 2106.04(a)(2)(I). See, e.g., Paras. [0035] & [0040] of specification indicating machine learning-based classifier uses statistical algorithm to predict a score.
Claim 11 Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception/Abstract idea into practical application?
Under Step 2A Prong Two, this judicial exception is not integrated into a practical application because the additional claim limitations outside of the abstract idea only present mere instructions to apply an exception, generally link the use of the judicial exception to the technological environment, or insignificant extra-solution activity. In particular, the claim recites the additional limitations of:
• “receiving, at a computing device, operational parameter data comprising a plurality of operational parameters of an asset, wherein the plurality of operational parameters are determined during an analysis of one or more operations performed by the asset” (insignificant extra-solution activity – mere data gathering/inputting – See MPEP 2106.04(d) referencing MPEP 2106.05(g); this limitation can be viewed as nothing more than mere data gathering/inputting in conjunction with the abstract idea (see MPEP 2106.05(g)).
• “providing, to a predictive model, the operational parameter data” (insignificant extra-solution activity – mere data gathering – See MPEP 2106.04(d) referencing MPEP 2106.05(g); this limitation can be viewed as nothing more than mere data gathering in conjunction with the abstract idea (see MPEP 2106.05(g)).
Claim 11 Step 2B: Do the additional elements, considered individually and in combination, amount to significantly more than the judicial exception?
The Examiner must consider whether each claim limitation individually or as an ordered combination amount to significantly more than the abstract idea. This analysis includes determining whether an inventive concept is furnished by an element or a combination of elements that are beyond the judicial exception. For limitations that were categorized as “apply it” or generally linking the use of the abstract idea to a particular technological environment or field of use, the analysis is the same.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As explained above, there is one type of additional element(s). The additional elements are “receiving operational parameter data” and “providing the operational parameter data”, which is at best viewed as nothing more than insignificant extra-solution activity (mere data gathering/inputting). Recitation of receiving and providing operational parameter data is mere data gathering/inputting that is recited at a high level of generality, and, is also Well-Understood, Routine and Conventional (WURC). This limitation therefore remains insignificant extra-solution activity even upon reconsideration. Thus, this limitation does not amount to significantly more.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and/or data outputting/gathering, which do not provide an inventive concept. The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception. See MPEP 2106.05(f).
Considering the claim limitations as an ordered combination, claim 11 does not include significantly more than the abstract idea. The claim 1 is not patent subject matter eligible. Dependent claims 11-20 are further addressed below.
Dependent Claims 2-10 and 11-20
Regarding claims 2-10 and 14, claim 2 depends from claim 1 and further recites: “wherein the operational data comprises one or more data sets, wherein each data set of the one or more data sets comprises data indicative of a time series of data associated with the plurality of operational parameters associated with the asset”, claim 3 depends from claim 1 and further recites: “wherein the plurality of operational parameters comprises one or more of power parameters, voltage parameters, current parameters, capacity parameters, heat parameters, cooling tubes parameters, oil tank parameters, sunlight duration parameters, height of the transformer, date of manufacture, manufacturer data, date of installation, vehicle traffic density, or air temperature parameters”, claim 4 depends from claim 1 and further recites: “wherein the asset comprises a transformer”, claim 5 depends from claim 1 and further recites: “wherein determining the operational data associated with the plurality of operational parameters comprises: determining a time series of data associated with the plurality of operational parameters associated with the asset, wherein the time series comprises one or more time periods; performing an analysis for each time period of the data of the one or more time periods of the data; and generating, based on the analysis of each time period of the data, the operational data, wherein the operational data comprises a data set associated with each time period”, claim 6 depends from claim 1 and further recites: “wherein determining the operational data associated with the plurality of operational parameters comprises: determining baseline feature scores for each group of operational parameters of the plurality of operational parameters; labeling the baseline feature scores for each group of operational parameters of the plurality of operational parameters as the feature score associated with each group of operational parameters; and generating, based on the labeled baseline feature scores, the operational data”, claim 7 depends from claim 1 and further recites: “wherein determining, based on the operational data, the plurality of feature scores for the predictive model comprises: determining, from the operational data, feature scores associated with two or more operational data sets of a plurality of operational data sets as a first set of candidate feature scores; determining, from the operational data, feature scores associated with the first set of candidate feature scores that satisfy a first threshold score as a second set of candidate feature scores; and determining, from the operational data, feature scores associated with the second set of candidate feature scores that satisfy a second threshold score as a third set of candidate feature scores, wherein the plurality of feature scores comprises the third set of candidate feature scores”, claim 8 depends from claim 1 and further recites: “wherein the predictive model is configured to output a prediction score indicative of a measure of success of a maintenance cycle performed on the asset”, claim 9 depends from claim 8 and further recites: “further comprising determining, based on the prediction score satisfying a threshold, a prediction indicative of the maintenance cycle being successful”, claim 10 depends from claim 8 and further recites “further comprising determining, based on the prediction score satisfying a threshold, a prediction indicative of the maintenance cycle being unsuccessful” and claim 14 depends from claim 11 and further recites “further comprising training the predictive model.” These features have been considered in combination with the features required by the claim(s) from which these claims depend. The bolded portion of the additional feature are considered to further clarify the details of the mathematical concepts and/or the human’s mental activity (e.g., with pen and paper). See MPEP 2106.04(a)(2)(I) and (III). Therefore, these features are considered to be drawn to the abstract idea without adding significantly more, and hence claims 2-10 are considered to be ineligible under 35 U.S.C. § 101.
Claim 12 has substantially similar limitations as recited in claim 3, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 13 has substantially similar limitations as recited in claim 4, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 15 has substantially similar limitations as recited in claim 1, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 16 has substantially similar limitations as recited in claim 5, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 17 has substantially similar limitations as recited in claim 6, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 18 has substantially similar limitations as recited in claim 7, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 19 has substantially similar limitations as recited in claim 9, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
Claim 20 has substantially similar limitations as recited in claim 10, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 101 for similar reasons in view of the § 101 analysis of claim 11.
For the foregoing reasons, claims 1-20 are rejected under 35 U.S.C. § 101 as being directed to patent ineligible subject matter.
Claim Rejections - 35 U.S.C. § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 7, 11-16 and 18 are rejected under 35 U.S.C. § 102(a)(1) as being anticipated by SMILEY et al. (U.S. Patent Publication No. 2014/0365271 A1), which was cited in Applicant’s IDS dated 25 April 2024.
Regarding claim 1, SMILEY discloses a method comprising: determining, by a computing device, operational data associated with a plurality of operational parameters associated with an asset (generating a health profile of an industrial asset … data may be retrieved … the data may include operational data, environmental data, performance data, maintenance data, and/or other types of data which may be useful to determine how the industrial asset performs, an environment in which the industrial asset performs, and/or events that occur with respect to the industrial asset (e.g., outage events, fire events, maintenance events, etc.), Para. [0121] of SMILEY; See also industrial asset is used herein to describe a piece of equipment, element thereof, and/or a group of equipment logically and/or physically assembled together to form a production unit … examples of such industrial assets may include a transformer, Para. [0027] of SMILEY), wherein the plurality of operational parameters comprise one or more groups of operational parameters (identifying subsets of industrial assets (e.g., where a subset corresponds to a group of industrial assets that share a common set of characteristics), Para. [0031] of SMILEY; See also subsets may be based upon manufacturer, voltage class, operating climate, Para. [0030] of SMILEY; See also a class of industrial assets is divided into one or more subsets, including a first subset, based upon one or more criteria (e.g., where class may be defined as a group of industrial assets configured to perform a similar function). Such criteria may include voltage class, operating environment, manufacturer, output production, loading capacity, etc., Para. [0035] of SMILEY; See also a subset may relate to a group of industrial assets that operate in similar environments, are members of a same voltage class, share a common manufacturer, are similar in age, Para. [0049] of SMILEY; See also the model parameters may limit the volume of data retrieved to include merely one or more specific type(s) of data … example types of data include, among other things, data indicative of dissolved gas concentrations, data indicative of internal temperatures, data indicative of loadings, data indicative of metal fatigue measurements, data indicative of ambient air temperatures, data indicative of humidity measurements, and/or data indicative of production output … as another example, the assessment period may limit the volume of data retrieved to include data collected/generated during merely a specified period of time, Para. [0059] of SMILEY; See also an assessment date and time may be specified when the model is executed (e.g., ‘today’, or midnight of the last day of the preceding month), and the assessment period may be defined by the model as a period starting two months prior to the assessment date and ending on the assessment date (e.g., thus the dates included within the assessment period are a function of when the model is executed), Para. [0053] of SMILEY; [Examiner’s Note: the operational data (parameters) of SMILEY is grouped by time (the assessment period) and into subsets based on criteria (e.g., similar function, voltage class, operating environment, manufacturer, similar in age, etc.]), and wherein each group of operational parameters of the one or more groups of operational parameters is labeled according to a feature score (a confidence profile describes a confidence in the probability of an event (e.g., condition, cause, impact, etc.) occurring or not occurring … the confidence profile may be based upon the type of data from which the probability was determined, a quality of the data (e.g., an accuracy of a sensor or other tool utilized to generate the data), a quantity of data available from which to compute the probability, and/or how strongly that data correlates with the outcome (e.g., how strongly the data used serves as an indicator of a condition, cause, etc.) … the confidence profile may be a numerical score (e.g., 90% confidence in the condition), may be a range (e.g., 85-92% confidence in the condition), may follow a distribution function, and/or may describe a cone of uncertainty (e.g., where there is a first confidence associated with the likelihood of a condition occurring within the next 3 months and a second confidence associated with the likelihood of a condition occurring with the next 6 months), for example, Para. [0025] of SMILEY; See also “the first model may be selected based upon the criterion/criteria used to divide industrial assets into subsets … it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer,” Para. [0038] of SMILEY; See also the output of the testing is a numerical score or other grading feature that describes the strength of the data (e.g., in terms of quality and/or quantity), Para. [0116] of SMILEY); determining, based on the operational data, a plurality of feature scores for a predictive model (model logic may be configured to forecast the dissolved hydrogen concentration in the oil over the next year (e.g., by extrapolating the last 6 months of data indicative of dissolved hydrogen concentrations) … the model logic may be further configured to assign a confidence to the forecast … by way of example, over the past six months, over 1000 measurements may have been taken with merely a small deviation in such measurements … based upon the number of measurements taken within the last 6 months, the small deviation in such measurements, and the 85% confidence in the measurements, a high confidence score may be assigned to the forecast, Para. [0072] of SMILEY; [the 85% confidence in the measurements is interpreted a plurality of feature scores]; See also the model logic may also describe a process by which a confidence is assigned to the data, a process by which the data is evaluated to generate a forecast (e.g., probability), and/or a process by which a confidence may be computed (e.g., where a higher confidence may be assigned to a first forecast relative to the confidence assigned to a second forecast based upon the quantity and/or quality of data used to generate the first forecast versus the second forecast), Para. [0062] of SMILEY; See also Paras. [0027], [0038], [0116] and [0121] of SMILEY); training, based on a first portion of the operational data, the predictive model according to the plurality of feature scores (the model selected to analyze industrial assets of a subset, and/or features of the model (e.g., model parameters and/or model logic) may be refined over a period of time to achieve specified objectives (e.g., a specified confidence in a forecast, a specified forecasting period, etc.), Para. [0031] of SMILEY; See also a learning feature is configured to update an aspect of the model based upon discrepancies between the predicted health and the actual health of the industrial asset during the prediction period (e.g., was a predicted condition present, was a cause of the condition correctly predicted, was the impact of the condition correctly predicted, etc.), Para. [0032] of SMILEY; See also identifying subsets of industrial assets (e.g., where a subset corresponds to a group of industrial assets that share a common set of characteristics), selecting a model that (e.g., best) predicts the health of the subset, iteratively updating the model based upon differences and/or similarities between forecasts generated by the model and the actual health of industrial assets included within the subset during a period applicable to the forecast, and/or determining for respective industrial assets or a group of assets which model(s) or combination of models (e.g., such as meta-models that consider output from multiple models) provides an effective (e.g., most effective) prediction for the business purposes of the industrial entity, Para. [0031] of SMILEY; See also Paras. [0027], [0038], [0116] and [0121 of SMILEY]); testing, based on a second portion of the operational data, the predictive model (process may continue until desired stopping criteria are satisfied (e.g., respective models in a data store have been tested, the confidence profile of the health profile satisfies specified thresholds, etc.), Para. [0040] of SMILEY; See also a learning feature is configured to update an aspect of the model based upon discrepancies between the predicted health and the actual health of the industrial asset during the prediction period (e.g., was a predicted condition present, was a cause of the condition correctly predicted, was the impact of the condition correctly predicted, etc.), Para. [0032] of SMILEY; [determining whether the model correctly predicts a condition is interpreted as testing the predictive/forecasting model]; See also identifying subsets of industrial assets (e.g., where a subset corresponds to a group of industrial assets that share a common set of characteristics), selecting a model that (e.g., best) predicts the health of the subset, iteratively updating the model based upon differences and/or similarities between forecasts generated by the model and the actual health of industrial assets included within the subset during a period applicable to the forecast, and/or determining for respective industrial assets or a group of assets which model(s) or combination of models (e.g., such as meta-models that consider output from multiple models) provides an effective (e.g., most effective) prediction for the business purposes of the industrial entity, Para. [0031] of SMILEY; [identifying a model that best predicts the health of the subset is interpreted as involving testing the predictive model]; See also Paras. [0064] & [0086] of SMILEY); and outputting, based on the testing, the predictive model (model logic and/or model parameters may be refined based upon the discrepancies to update the model and/or improve an accuracy of the model … moreover, a different model may be selected for generating a health profile of an industrial asset based upon the discrepancies, and/or different criteria may be used to sort industrial assets into subsets based upon the discrepancies, for example, Para. [0032] of SMILEY; See also it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer … if transformers are divided at 106 based upon manufacturer, the first model may be selected to generate health profiles for the first subset of transformers, which are manufactured by the first manufacturer, and the second model may be selected to generate health profiles for a second subset of transformers, which are manufactured by the second manufacturer, Para. [0038] of SMILEY; See also Paras. [0027], [0030]-[0031], [0116] and [0121] of SMILEY).
Regarding claim 2, SMILEY discloses the method of claim 1. SMILEY further discloses wherein the operational data comprises one or more data sets, wherein each data set of the one or more data sets comprises data indicative of a time series of data associated with the plurality of operational parameters associated with the asset (upon a triggering event (e.g., user initiation, time period lapsed, environmental event, operating event, etc.), at least a portion of the data record of the first industrial asset may be provided to the first model, which analyzes the portion of the data record to generate a first health profile of the first industrial asset, Para. [0039] of SMILEY; See also assessment period refers herein to a period of time during which data that forms the basis of the prediction is collected/generated … by way of example, data collected over the last year may be input into the model (e.g., where the last year is the assessment period), Para. [0052] of SMILEY; See also y-axis 304 represents parts-per-million (ppm) and the x-axis 306 represents time … the assessment period 308 describes a time window of data samplings used to generate the health profile and the prediction period 310 describes a forecast window of interest, Para. [0065] of SMILEY; See also Paras. [0027], [0030], [0031], [0116] and [0121] of SMILEY).
Regarding claim 3, SMILEY discloses the method of claim 1. SMILEY further discloses wherein the plurality of operational parameters comprises one or more of power parameters, voltage parameters, current parameters, capacity parameters, heat parameters, cooling tubes parameters, oil tank parameters, sunlight duration parameters, height of the transformer, date of manufacture, manufacturer data, date of installation, vehicle traffic density, or air temperature parameters (the model parameters may limit the volume of data retrieved to include merely one or more specific type(s) of data … example types of data include, among other things, data indicative of dissolved gas concentrations, data indicative of internal temperatures, data indicative of loadings, data indicative of metal fatigue measurements, data indicative of ambient air temperatures, data indicative of humidity measurements, and/or data indicative of production output … as another example, the assessment period may limit the volume of data retrieved to include data collected/generated during merely a specified period of time, Para. [0059] of SMILEY; See also subsets may be based upon manufacturer, voltage class, operating climate, Para. [0030] of SMILEY; See also a class of industrial assets is divided into one or more subsets, including a first subset, based upon one or more criteria (e.g., where class may be defined as a group of industrial assets configured to perform a similar function). Such criteria may include voltage class, operating environment, manufacturer, output production, loading capacity, etc., Para. [0035] of SMILEY; See also a subset may relate to a group of industrial assets that operate in similar environments, are members of a same voltage class, share a common manufacturer, are similar in age, Para. [0049] of SMILEY).
Regarding claim 4, SMILEY discloses the method of claim 1. SMILEY further discloses wherein the asset comprises a transformer (industrial assets may include a transformer, Para. [0027] of SMILEY).
Regarding claim 5, SMILEY discloses the method of claim 1. SMILEY further discloses wherein determining the operational data associated with the plurality of operational parameters comprises: determining a time series of data associated with the plurality of operational parameters associated with the asset, wherein the time series comprises one or more time periods (assessment period refers herein to a period of time during which data that forms the basis of the prediction is collected/generated … by way of example, data collected over the last year may be input into the model (e.g., where the last year is the assessment period), Para. [0052] of SMILEY; See also Paras. [0027], [0030], [0031], [0065], [0116] and [0121] of SMILEY); performing an analysis for each time period of the data of the one or more time periods of the data (the assessment period may be different for different types of data to be analyzed by the model, Para. [0055] of SMILEY; See also Paras. [0027], [0030]-[0031], [0039], [0052] and [0065] of SMILEY); and generating, based on the analysis of each time period of the data, the operational data, wherein the operational data comprises a data set associated with each time period (by way of example, it may be desirable for the model to analyze data indicative of an ambient air temperature that has been collected over at least a one year span, while it may be desirable for the model to analyze data indicative of dissolved gas concentrations within the industrial asset collected over merely a 6 month span … accordingly, an assessment period for data indicative of ambient air temperature may be 1 year and an assessment period for data indicative of dissolved gas concentrations may be 6 months, Para. [0055] of SMILEY; See also Paras. [0030], [0031], [0039], [0052], [0065], [0116] and [0121] of SMILEY).
Regarding claim 7, SMILEY discloses the method of claim 1. SMILEY further discloses wherein determining, based on the operational data, the plurality of feature scores for the predictive model comprises: determining, from the operational data, feature scores associated with two or more operational data sets of a plurality of operational data sets as a first set of candidate feature scores (a confidence profile describes a confidence in the probability of an event (e.g., condition, cause, impact, etc.) occurring or not occurring … the confidence profile may be based upon the type of data from which the probability was determined, a quality of the data (e.g., an accuracy of a sensor or other tool utilized to generate the data), a quantity of data available from which to compute the probability, and/or how strongly that data correlates with the outcome (e.g., how strongly the data used serves as an indicator of a condition, cause, etc.) … the confidence profile may be a numerical score (e.g., 90% confidence in the condition), may be a range (e.g., 85-92% confidence in the condition), may follow a distribution function, and/or may describe a cone of uncertainty (e.g., where there is a first confidence associated with the likelihood of a condition occurring within the next 3 months and a second confidence associated with the likelihood of a condition occurring with the next 6 months), for example, Para. [0025] of SMILEY; See also the first model may be selected based upon the criterion/criteria used to divide industrial assets into subsets … it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer, Para. [0038] of SMILEY; See also the output of the testing is a numerical score or other grading feature that describes the strength of the data (e.g., in terms of quality and/or quantity), Para. [0116] of SMILEY; See also Paras. [0027], [0030], [0031] and [0121] of SMILEY); determining, from the operational data, feature scores associated with the first set of candidate feature scores that satisfy a first threshold score as a second set of candidate feature scores (a confidence profile describes a confidence in the probability of an event (e.g., condition, cause, impact, etc.) occurring or not occurring … the confidence profile may be based upon the type of data from which the probability was determined, a quality of the data (e.g., an accuracy of a sensor or other tool utilized to generate the data), a quantity of data available from which to compute the probability, and/or how strongly that data correlates with the outcome (e.g., how strongly the data used serves as an indicator of a condition, cause, etc.) … the confidence profile may be a numerical score (e.g., 90% confidence in the condition), may be a range (e.g., 85-92% confidence in the condition), may follow a distribution function, and/or may describe a cone of uncertainty (e.g., where there is a first confidence associated with the likelihood of a condition occurring within the next 3 months and a second confidence associated with the likelihood of a condition occurring with the next 6 months), for example, Para. [0025] of SMILEY; See also the first model may be selected based upon the criterion/criteria used to divide industrial assets into subsets … it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer, Para. [0038] of SMILEY; See also the output of the testing is a numerical score or other grading feature that describes the strength of the data (e.g., in terms of quality and/or quantity) … if the strength of the data is below a threshold, a decision may be made at 1112 to update the set of factors at 1114. For example, if a numerical score of 0-50 (e.g., where 0 is worst and 100 is best) is associated with the data, the quality and/or quantity of the data set may be too weak for updating the model, and a decision may be made at 1112 to update the set of factors (e.g., broaden the factors to increase the number of industrial assets within a subset) … if the strength of the data is above the threshold, a decision may be made at 1112 that the subset is a good subset, may end the method 1100 at 1116, and may proceed with selecting a model, updating a model, etc. as described in FIG. 1, Para. [0116] of SMILEY; See also Paras. [0027], [0030], [0031] and [0121] of SMILEY); and determining, from the operational data, feature scores associated with the second set of candidate feature scores that satisfy a second threshold score as a third set of candidate feature scores, wherein the plurality of feature scores comprises the third set of candidate feature scores (at 118 in the example method 100, the differences and/or similarities between the actual events and the predicted events may be used to update model logic and/or model parameters of the first model and/or second model, to update criterion/criteria used to divide the class of industrial assets into subsets (e.g., where based upon the re-division, the first industrial asset is part of a third subset), and/or to select a third model for generating health profiles for at least one of the first subset, the second subset, and/or the third subset, Para. [0042] of SMILEY; See also Paras. [0027], [0030], [0031], [0116] and [0121] of SMILEY).
Regarding claim 11, SMILEY discloses a method comprising: receiving, at a computing device, operational parameter data comprising a plurality of operational parameters of an asset (generating a health profile of an industrial asset … data may be retrieved … the data may include operational data, environmental data, performance data, maintenance data, and/or other types of data which may be useful to determine how the industrial asset performs, an environment in which the industrial asset performs, and/or events that occur with respect to the industrial asset (e.g., outage events, fire events, maintenance events, etc.), Para. [0121] of SMILEY; See also industrial asset is used herein to describe a piece of equipment, element thereof, and/or a group of equipment logically and/or physically assembled together to form a production unit … examples of such industrial assets may include a transformer, Para. [0027] of SMILEY; See also Paras. [0030], [0031], [0039], [0052], [0065] and [0116] of SMILEY), wherein the plurality of operational parameters are determined during an analysis of one or more operations performed by the asset (a class of industrial assets is divided into one or more subsets, including a first subset, based upon one or more criteria (e.g., where class may be defined as a group of industrial assets configured to perform a similar function). Such criteria may include voltage class, operating environment, manufacturer, output production, loading capacity, etc., Para. [0035] of SMILEY; See also the model parameters may limit the volume of data retrieved to include merely one or more specific type(s) of data … example types of data include, among other things, data indicative of dissolved gas concentrations, data indicative of internal temperatures, data indicative of loadings, data indicative of metal fatigue measurements, data indicative of ambient air temperatures, data indicative of humidity measurements, and/or data indicative of production output … as another example, the assessment period may limit the volume of data retrieved to include data collected/generated during merely a specified period of time, Para. [0059] of SMILEY); providing, to a predictive model, the operational parameter data (model logic may be configured to forecast the dissolved hydrogen concentration in the oil over the next year (e.g., by extrapolating the last 6 months of data indicative of dissolved hydrogen concentrations) … the model logic may be further configured to assign a confidence to the forecast … by way of example, over the past six months, over 1000 measurements may have been taken with merely a small deviation in such measurements … based upon the number of measurements taken within the last 6 months, the small deviation in such measurements, and the 85% confidence in the measurements, a high confidence score may be assigned to the forecast, Para. [0072] of SMILEY; [the 85% confidence in the measurements is interpreted a plurality of feature scores]; See also the model logic may also describe a process by which a confidence is assigned to the data, a process by which the data is evaluated to generate a forecast (e.g., probability), and/or a process by which a confidence may be computed (e.g., where a higher confidence may be assigned to a first forecast relative to the confidence assigned to a second forecast based upon the quantity and/or quality of data used to generate the first forecast versus the second forecast), Para. [0062] of SMILEY; See also Paras. [0027], [0030], [0031], [0038], [0116] and [0121] of SMILEY); and determining, based on the predictive model, a prediction score associated with a maintenance cycle performed on the asset (as another example, data may be collected from sensors associated with the industrial asset and analyzed to identify performance changes that may indicate maintenance is needed and/or to identify early indicators of an imminent failure, Para. [0004] of SMILEY; [the system may determine that the asset will pass or fail a maintenance check using the feature scores]; See also Paras. [0027], [0029]-[0031], [0116] and [0121] of SMILEY).
Claim 12 has substantially similar limitations as recited in claim 3, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 102 for similar reasons using SMILEY as applied to claim 11.
Claim 13 has substantially similar limitations as recited in claim 4, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 102 for similar reasons using SMILEY as applied to claim 11.
Regarding claim 14, SMILEY discloses the method of claim 1. SMILEY further discloses training the predictive model (the model selected to analyze industrial assets of a subset, and/or features of the model (e.g., model parameters and/or model logic) may be refined over a period of time to achieve specified objectives (e.g., a specified confidence in a forecast, a specified forecasting period, etc.), Para. [0031] of SMILEY; See also a learning feature is configured to update an aspect of the model based upon discrepancies between the predicted health and the actual health of the industrial asset during the prediction period (e.g., was a predicted condition present, was a cause of the condition correctly predicted, was the impact of the condition correctly predicted, etc.), Para. [0032] of SMILEY; See also identifying subsets of industrial assets (e.g., where a subset corresponds to a group of industrial assets that share a common set of characteristics), selecting a model that (e.g., best) predicts the health of the subset, iteratively updating the model based upon differences and/or similarities between forecasts generated by the model and the actual health of industrial assets included within the subset during a period applicable to the forecast, and/or determining for respective industrial assets or a group of assets which model(s) or combination of models (e.g., such as meta-models that consider output from multiple models) provides an effective (e.g., most effective) prediction for the business purposes of the industrial entity, Para. [0031] of SMILEY; See also Paras. [0027], [0038], [0116] and [0121 of SMILEY]).
Claims 15 has substantially similar limitations as recited in claim 1, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 102 for similar reasons using SMILEY as applied to claim 11.
Claims 16 has substantially similar limitations as recited in claim 5, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 102 for similar reasons using SMILEY as applied to claim 11.
Claims 18 has substantially similar limitations as recited in claim 7, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 102 for similar reasons using SMILEY as applied to claim 11.
Claims 6 and 17 are rejected under 35 U.S.C. § 103 as being unpatentable over SMILEY et al. (U.S. Patent Publication No. 2014/0365271 A1), which was cited in Applicant’s IDS dated 25 April 2024 in view of LIAO (U.S. Patent Application Publication No. 2013/0060524 A1), which was cited in Applicant’s IDS dated 25 April 2024.
Regarding claim 6, SMILEY discloses the method of claim 1. SMILEY further discloses wherein determining the operational data associated with the plurality of operational parameters comprises: determining (a confidence profile describes a confidence in the probability of an event (e.g., condition, cause, impact, etc.) occurring or not occurring … the confidence profile may be based upon the type of data from which the probability was determined, a quality of the data (e.g., an accuracy of a sensor or other tool utilized to generate the data), a quantity of data available from which to compute the probability, and/or how strongly that data correlates with the outcome (e.g., how strongly the data used serves as an indicator of a condition, cause, etc.) … the confidence profile may be a numerical score (e.g., 90% confidence in the condition), may be a range (e.g., 85-92% confidence in the condition), may follow a distribution function, and/or may describe a cone of uncertainty (e.g., where there is a first confidence associated with the likelihood of a condition occurring within the next 3 months and a second confidence associated with the likelihood of a condition occurring with the next 6 months), for example, Para. [0025] of SMILEY; See also the first model may be selected based upon the criterion/criteria used to divide industrial assets into subsets … it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer, Para. [0038] of SMILEY; See also the output of the testing is a numerical score or other grading feature that describes the strength of the data (e.g., in terms of quality and/or quantity) … if the strength of the data is below a threshold, a decision may be made at 1112 to update the set of factors at 1114. For example, if a numerical score of 0-50 (e.g., where 0 is worst and 100 is best) is associated with the data, the quality and/or quantity of the data set may be too weak for updating the model, and a decision may be made at 1112 to update the set of factors (e.g., broaden the factors to increase the number of industrial assets within a subset) … if the strength of the data is above the threshold, a decision may be made at 1112 that the subset is a good subset, may end the method 1100 at 1116, and may proceed with selecting a model, updating a model, etc. as described in FIG. 1, Para. [0116] of SMILEY; See also Paras. [0027], [0030], [0031] and [0121] of SMILEY); labeling (a confidence profile describes a confidence in the probability of an event (e.g., condition, cause, impact, etc.) occurring or not occurring … the confidence profile may be based upon the type of data from which the probability was determined, a quality of the data (e.g., an accuracy of a sensor or other tool utilized to generate the data), a quantity of data available from which to compute the probability, and/or how strongly that data correlates with the outcome (e.g., how strongly the data used serves as an indicator of a condition, cause, etc.) … the confidence profile may be a numerical score (e.g., 90% confidence in the condition), may be a range (e.g., 85-92% confidence in the condition), may follow a distribution function, and/or may describe a cone of uncertainty (e.g., where there is a first confidence associated with the likelihood of a condition occurring within the next 3 months and a second confidence associated with the likelihood of a condition occurring with the next 6 months), for example, Para. [0025] of SMILEY; See also the first model may be selected based upon the criterion/criteria used to divide industrial assets into subsets … it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer, Para. [0038] of SMILEY; See also the output of the testing is a numerical score or other grading feature that describes the strength of the data (e.g., in terms of quality and/or quantity) … if the strength of the data is below a threshold, a decision may be made at 1112 to update the set of factors at 1114. For example, if a numerical score of 0-50 (e.g., where 0 is worst and 100 is best) is associated with the data, the quality and/or quantity of the data set may be too weak for updating the model, and a decision may be made at 1112 to update the set of factors (e.g., broaden the factors to increase the number of industrial assets within a subset) … if the strength of the data is above the threshold, a decision may be made at 1112 that the subset is a good subset, may end the method 1100 at 1116, and may proceed with selecting a model, updating a model, etc. as described in FIG. 1, Para. [0116] of SMILEY; See also Paras. [0027], [0030], [0031] and [0121] of SMILEY); and generating, based on the labeled (a confidence profile describes a confidence in the probability of an event (e.g., condition, cause, impact, etc.) occurring or not occurring … the confidence profile may be based upon the type of data from which the probability was determined, a quality of the data (e.g., an accuracy of a sensor or other tool utilized to generate the data), a quantity of data available from which to compute the probability, and/or how strongly that data correlates with the outcome (e.g., how strongly the data used serves as an indicator of a condition, cause, etc.) … the confidence profile may be a numerical score (e.g., 90% confidence in the condition), may be a range (e.g., 85-92% confidence in the condition), may follow a distribution function, and/or may describe a cone of uncertainty (e.g., where there is a first confidence associated with the likelihood of a condition occurring within the next 3 months and a second confidence associated with the likelihood of a condition occurring with the next 6 months), for example, Para. [0025] of SMILEY; See also the first model may be selected based upon the criterion/criteria used to divide industrial assets into subsets … it may be believed that the first model is more accurate at forecasting transformers manufactured by a first manufacturer and that a second model is more accurate at forecasting transformers manufactured by a second manufacturer, Para. [0038] of SMILEY; See also the output of the testing is a numerical score or other grading feature that describes the strength of the data (e.g., in terms of quality and/or quantity) … if the strength of the data is below a threshold, a decision may be made at 1112 to update the set of factors at 1114. For example, if a numerical score of 0-50 (e.g., where 0 is worst and 100 is best) is associated with the data, the quality and/or quantity of the data set may be too weak for updating the model, and a decision may be made at 1112 to update the set of factors (e.g., broaden the factors to increase the number of industrial assets within a subset) … if the strength of the data is above the threshold, a decision may be made at 1112 that the subset is a good subset, may end the method 1100 at 1116, and may proceed with selecting a model, updating a model, etc. as described in FIG. 1, Para. [0116] of SMILEY; See also Paras. [0027], [0030], [0031] and [0121] of SMILEY).
SMILEY does not appear to explicitly disclose determining a baseline; labeling the baseline; and based on the labeled baseline, performing an action. LIAO, however, is in the same field of analyzing/diagnosing operational data of machines/assets (Para. [0003] of LIAO) and teaches determining a baseline (generation of the model may include, for example, analyzing the key parameters over time to determine a baseline … the baseline may be used to establish ranges of normal operation and to identify outlying values that may be beyond expectations for normal operation, Para. [0040] of LIAO); labeling the baseline (the baseline may be used to establish ranges of normal operation and to identify outlying values that may be beyond expectations for normal operation, Para. [0040] of LIAO); and based on the labeled baseline, performing an action (outlying values may then be defined, for example, as values extending beyond one, two, or three standard deviations from the mean, or some other predetermined threshold, Para. [0040] of LIAO; See also when one or more key parameters fall beyond the normal operating range, an alert may be generated to inform maintenance personnel of the potential problem, Para. [0005] of LIAO).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to modify the feature scoring of assets/machines in SMILEY to include the baseline labeling of LIAO for the purpose of providing the system with data that it may use to compare the operational parameters to (Para. [0040] of LIAO) and identifying potential problems before serious and costly failures occur (Para. [0006] of LIAO).
Claims 17 has substantially similar limitations as recited in claim 6, except it depends (indirectly) from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 103 for similar reasons using SMILEY as applied to claim 11.
Claims 8-10 and 19-20 are rejected under 35 U.S.C. § 103 as being unpatentable over SMILEY et al. (U.S. Patent Publication No. 2014/0365271 A1), which was cited in Applicant’s IDS dated 25 April 2024 in view of HOFFMAN et al. (U.S. Patent No. 10,977,593 B1), which was cited in Applicant’s IDS dated 25 April 2024.
Regarding claim 8, SMILEY discloses the method of claim 1. SMILEY does not appear to explicitly disclose wherein the predictive model is configured to output a prediction score indicative of a measure of success of a maintenance cycle performed on the asset.
However, HOFFMAN is in the same field of models predicting the outcomes of equipment/assets (Col. 1, Lines 30-33, of HOFFMAN) and does disclose wherein the predictive model is configured to output a prediction score indicative of a measure of success of a maintenance cycle performed on the asset (the predictive model 170 accepts input data 140, which may include information from the maintenance plan 142, as well as additional data, such as weather data 144, and provides an output indicating a predicted risk of the scheduled maintenance action … the predictive model 170 generates one or more outcome scores 172 indicating likelihoods of potential outcomes of the maintenance action. These outcomes may include, among others, success, failure, an expected time or time range to complete the maintenance, and various safety hazards, Col. 9, Line 65 – Col. 10, Line 8, of HOFFMAN).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to modify the feature scoring of assets/machines in SMILEY to include the maintenance prediction(s) of HOFFMAN (to arrive at the claimed features) for the purpose of increasing the likelihood that the particular maintenance action will achieve its purpose and avoid harm to a person or damage to property (Col. 1, Lines 28-39, of HOFFMAN).
Regarding claim 9, SMILEY as modified by HOFFMAN teaches the method of claim 8. HOFFMAN further discloses determining, based on the prediction score satisfying a threshold, a prediction indicative of the maintenance cycle being successful (the specific thresholds can be set individually for each different outcome assessed by the predictive models … in addition, to generate the outcome likelihoods with recommended changes reflected, the predictive models can be used again to generate outcome scores, this time with the planned data plus the identified new plan elements recommended by the server 110, Col. 16, Lines 59-65, HOFFMAN; See also Col. 9, Line 65 – Col. 10, Line 8, of HOFFMAN).
Regarding claim 10, SMILEY as modified by HOFFMAN teaches the method of claim 8. HOFFMAN further discloses comprising determining, based on the prediction score satisfying a threshold, a prediction indicative of the maintenance cycle being unsuccessful (the specific thresholds can be set individually for each different outcome assessed by the predictive models … in addition, to generate the outcome likelihoods with recommended changes reflected, the predictive models can be used again to generate outcome scores, this time with the planned data plus the identified new plan elements recommended by the server 110, Col. 16, Lines 59-65, HOFFMAN; See also Col. 9, Line 65 – Col. 10, Line 8, of HOFFMAN).
Claims 19 has substantially similar limitations as recited in claim 9, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 103 for similar reasons using SMILEY as applied to claim 11.
Claim 20 has substantially similar limitations as recited in claim 10, except it depends from parent base claim 11; therefore, it is rejected under 35 U.S.C. § 103 for similar reasons using SMILEY as applied to claim 11.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: POTYRAILO et al. (U.S. Patent Application Publication No. 2022/0326212) teaches “controller can examine the measurements provided by the sensor probe assemblies and may use the measurements to predict, self-correct (e.g., using a digital twin of the equipment), and forecast oil change intervals for the equipment” (Para. [0101]) and “different hypothetical or planned future operating conditions may result in the controller determining that the lubricant needs to be changed sooner (e.g., than a scheduled maintenance), later (than the scheduled maintenance), that the equipment cannot safely operate under the designated conditions, or the like” (Para. [0108]).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN P HOCKER whose telephone number is (571)272-0501. The examiner can normally be reached Monday-Friday 9:00 AM - 5:00 PM EST.
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, Rehana Perveen can be reached on (571)272-3676. 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.
/JOHN P HOCKER/Examiner, Art Unit 2189
JOHN P. HOCKER
Examiner
Art Unit 2189
/REHANA PERVEEN/Supervisory Patent Examiner, Art Unit 2189
Prosecution Insights