DETAILED ACTION
This action is responsive to the claims filed on 05/29/2025. Claims 21-37 are pending for examination.
This action is Final.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 04/10/2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
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 35-37 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Statutory Categories
Claims 35-37 are directed to a method.
Independent Claims – Claim 35
Step 2A Prong 1: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes. Independent claim 35 recites limitations that are abstract ideas in the form of mental processes:
Claim 35 recites:
produce a production prediction in response to data, (training stated at a high level of generality such that it is considered a mental process of evaluation that can reasonably be performed by human mind with the aid of pen and paper)
This claim further recites the following additional elements for the purposes of Step 2A Prong Two analysis:
A method comprising: obtaining first training data comprising training production fluid data and training productions, (limitation is merely inputting/receiving information and is considered insignificant extra-solution activity, see MPEP 2106.05(g))
and wherein the data are obtained for a production fluid. (limitation is merely inputting/receiving information and is considered insignificant extra-solution activity, see MPEP 2106.05(g))
and training a production prediction model using the first training data, wherein the production prediction model is trained to (a recitation of only the idea of a solution or outcome without reciting details of how a solution is accomplished is being considered merely as instructions to apply an exception under MPEP 2106.05(f))
wherein the training production fluid data are associated with a training chemical composition of training production fluids and a training flow rate of the training production fluids; (limitation is merely inputting/receiving information and is considered insignificant extra-solution activity, see MPEP 2106.05(g), furthermore this recites a type of data inputted and does not cause the data inputting step to practically integrate the exception under MPEP 2106.05(g);)
The additional limitations fail step 2A Prong 2 of the 101 analysis because they do not transform the claim into a practical application. These limitations are too abstract or lack technical improvement that would make the concept practically useful. Without clear utility or integration into a specific field, the claim does not relate to any particular application. It does not meet the requirements of Step 2A Prong 2, as it fails to make the concept meaningfully applicable in practice.
This claim recites the following additional elements for the purposes of Step 2B analysis:
A method comprising: obtaining first training data comprising training production fluid data and training productions, (limitation is merely inputting/receiving information and is considered insignificant extra-solution activity, see MPEP 2106.05(g))
and wherein the data are obtained for a production fluid. (limitation is merely inputting/receiving information and is considered insignificant extra-solution activity, see MPEP 2106.05(g))
and training a production prediction model using the first training data, wherein the production prediction model is trained to (a recitation of only the idea of a solution or outcome without reciting details of how a solution is accomplished is being considered merely as instructions to apply an exception under MPEP 2106.05(f))
wherein the training production fluid data are associated with a training chemical composition of training production fluids and a training flow rate of the training production fluids; (limitation is merely inputting/receiving information and is considered well-understood, routine, and conventional activity under MPEP 2106.05(d))
The claim also fails Step 2B of the analysis because the additional limitations do not amount to significantly more than the abstract idea itself. The additional limitations do not enhance the claim in a way that would move it beyond its abstract ideas as they minimally elaborate on the core concept without adding any inventive or technical substance. The claim is unpatentable.
Dependents of Claims 35
The remaining dependent claims corresponding to independent claims 21 and 28 do not recite additional elements, whether considered individually or in combination, that are sufficient to integrate the judicial exception into a practical application or amount to significantly more than the judicial exception. The analysis of which is shown below:
The claims below recite additional limitations which fail step 2A Prong 2 of the 101 analysis because they do not transform the claim into a practical application. These limitations are too abstract or lack technical improvement that would make the concept practically useful. Without clear utility or integration into a specific field, the claim does not relate to any particular application. It does not meet the requirements of Step 2A Prong 2, as it fails to make the concept meaningfully applicable in practice.
The claims also fails Step 2B of the analysis because the additional limitations do not amount to significantly more than the abstract idea itself. The additional limitations do not enhance the claim in a way that would move it beyond its abstract ideas as they minimally elaborate on the core concept without adding any inventive or technical substance. The claims are unpatentable.
Claim 36 recites the further limitation of:
The method of claim 35, further comprising: obtaining second training data comprising the training production fluid data and training reliability data; and (limitation is merely inputting/receiving information and is considered insignificant extra-solution activity, see MPEP 2106.05(g))
training a classification model using the second training data, wherein the classification model is trained to produce a reliability in response to the data. (a recitation of only the idea of a solution or outcome without reciting details of how a solution is accomplished is being considered merely as instructions to apply an exception under MPEP 2106.05(f))
and producing a reliability from the trained classification model in response to the data. (a recitation of only the idea of a solution or outcome without reciting details of how a solution is accomplished is being considered merely as instructions to apply an exception under MPEP 2106.05(f))
Claim 37 recites the further limitation of:
The method of claim 36, wherein the second training data further comprises training recommendation data, (this recites a type of data inputted and does not cause the data inputting step to practically integrate the exception under MPEP 2106.05(g);)
and wherein the classification model is further trained to produce a recommendation in response to the data. (a recitation of only the idea of a solution or outcome without reciting details of how a solution is accomplished is being considered merely as instructions to apply an exception under MPEP 2106.05(f))
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim 35 is rejected under 35 U.S.C. 102(a)(1) as being unpatentable by Pradyumna Thiruvenkatanathan (US 2021/0148199 A1; published May 20, 2021), hereafter referred to as Pradyumna.
Claim 35: Pradyumna teaches the following limitations:
A method comprising: obtaining first training data comprising training production fluid data and training productions, wherein the training production fluid data are associated with a training chemical composition of training production fluids (Pradyumna, paragraph 61, “Referring again to FIG. 1, the processor 168 within the acquisition device 160 may be configured to perform various data processing processes to detect the fluid inflow events of one or more fluids along the length of the wellbore 114 (more specifically along the length of optical fiber 162).”, fluid inflow events are detected and obtained as input data.
Paragraph 18, “As utilized herein, a ‘fluid inflow event’ includes fluid inflow (e.g., any fluid inflow regardless of composition thereof), gas phase inflow, aqueous phase inflow, and/or hydrocarbon phase inflow. The fluid can comprise other components such as solid particulate matter in some embodiments, as discussed in more detail herein.”, a fluid inflow event determines the chemical compositions (aqueous vs gas vs hydrocarbon) of production fluids)
and a training flow rate of the training production fluids; (Pradyumna, paragraph 86, “The fluid inflow event detection model at 214 may be configured to detect fluid inflows and/or fluid inflow rates in different fluid phases through different types of production assemblies, pipes, annuli, and the like. In some embodiments, the fluid inflow event detection model at 214 may be trained to detect the fluid inflow events. Specifically, acoustic data from a known fluid flow (e.g., one in which the type, phase, and amount of fluid therein is known or otherwise determined) can be used in the fluid inflow event detection model development process to determine one or more multivariate models indicative of an inflowing fluid in one or more fluid phases and/or in a flowing fluid within the wellbore within one or more fluid phases”, a multivariate model is explicitly trained on flow rate information.)
and training a production prediction model using the first training data, wherein the production prediction model is trained to produce a production prediction in response to data, and wherein the data are obtained for a production fluid. (Pradyumna, paragraph 98, “In some embodiments, the fluid inflow prediction model may predict a fluid inflow and/or fluid inflow rates based on a production rate of the one or more fluids from the production zone of the wellbore and/or the operating parameter(s) as described above. In some embodiments, the fluid inflow prediction model may predict a fluid inflow and/or fluid inflow rate(s) based on one or more reservoir properties of the production zone either in lieu of or in addition to the other parameters described above.”)
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
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.
Claims 21, 25-28, 32-34 are rejected under 35 U.S.C. 103 as being unpatentable over Pradyumna in view of Tang et al. (Tang, L., Li, J., Lu, W., Lian, P., Wang, H., Jiang, H., ... & Jia, H. (2021). Well control optimization of waterflooding oilfield based on deep neural network. Geofluids, 2021(1), 8873782.), hereafter referred to as Tang.
Claim 21: Pradyumna teaches the following limitations:
A method comprising: disposing a sensor within a pipe, wherein the pipe is fluidly connected to a reservoir via a production well; (Pradyumna, paragraph 37, “A fluid monitoring system can also be present in the wellbore. The fluid monitoring system can serve to monitor the inflow and/or flow of fluids along the wellbore. In some embodiments, a DAS system 110 can be disposed in the wellbore. As described herein, a DAS system 110 may be utilized to detect or monitor fluid inflow and/or flow along the wellbore 114. In some embodiments, the DAS system 110 can be used to characterize the phase of an inflowing fluid and/or specific volumetric measurements of the fluids to obtain production rates of the hydrocarbon and one or more additional fluids.”, teaches placing a Distributed Acoustic Sensor (DAS) within the production wellbore tubing to monitor fluid inflow and flow, satisfying the disposition of a sensor within a pipe fluidly connected to the reservoir via a production well.)
obtaining, using the sensor, data for a production fluid flowing through the pipe, wherein the data are associated with a chemical composition of the production fluid and a flow rate of the production fluid; (Pradyumna, paragraph 37, “In some embodiments, the DAS system 110 can be used to characterize the phase of an inflowing fluid and/or specific volumetric measurements of the fluids to obtain production rates of the hydrocarbon and one or more additional fluids.”, discloses using the DAS system to characterize fluid phases (chemical compositions of hydrocarbon phases) and volumetric measurements (flow rates).)
transferring the data from the sensor to a base station; (Pradyumna, paragraph 61, “Referring again to FIG. 1, the processor 168 within the acquisition device 160 may be configured to perform various data processing processes to detect the fluid inflow events of one or more fluids along the length of the wellbore 114 (more specifically along the length of optical fiber 162). For instance, the memory 170 may be configured to store an application or program (e.g., comprising machine-readable instructions, such as, for instance, non-transitory machine-readable instructions) to perform the data analysis. While shown as being contained within the acquisition device 160, the memory 170 can comprise one or more memories, any of which can be external to the acquisition device 160.”, teaches collecting sensor data via the acquisition device 160 and making it available to downstream processing such as to memory storage external to the acquisition device (e.g. a base station).)
inputting the data into a trained production prediction model; (Pradyumna, paragraph 85, “Thus, the fluid inflow event detection model at block 214 may comprise a multivariate model in which the two or more frequency domain features are variables that may be provided by acoustic data (e.g., such as acoustic data obtained from DAS system 110 as previously described above). Thus, the fluid inflow event detection model may utilize one or more (e.g., at least two) of the frequency domain features as inputs therein.”, sensor data from DAS is input to a trained prediction model.)
producing a production prediction from the trained production prediction model in response to the data; (Pradyumna, paragraph 96, “In addition, in some embodiments, the correlating at block 218 may comprise constructing a fluid inflow prediction model that correlates the fluid inflow(s) (including the fluid inflow rate(s) per fluid type and/or phase as described above) with the operating parameter or parameters. Thus, the fluid inflow prediction model may receive input (at least partially) from the output of the fluid inflow detection model described above (e.g., such as the fluid inflow events and/or rates).”)
Tang, in the same field of fluid reservoir prediction, teaches the following limitations which Pradyumna fails to teach:
updating a water injection scheme based on the production prediction; (Tang, page 2, col. 1, paragraph 2, “Subsequent comparison schemes are randomly generated under the constraints of reservoir engineering, production performance prediction models are used to quickly predict production performance, and then the objective function value of each scheme is calculated to compare and optimize the optimal scheme.”, Tang’s framework uses the production prediction to evaluate and optimize injection/production schemes (including water injection), i.e., updating water injection control based on the prediction.
Tang, page 2, col. 1, paragraph 1, “Based on reservoir numerical simulation methods: this method first establishes a numerical simulation model based on the reservoir and fluid data provided by the oilfield, then uses the orthogonal experimental design method to set up multiple sets of different injection and production plans, and finally compares and selects the best based on parameters such as net present value [5–9]”, further support for showing that a selection of scheme pertaining to water injection is updated)
Pradyumna further teaches:
adjusting a component that water flows through [based on the water injection scheme], wherein the component is fluidly connected to the reservoir via an injection well; and (Pradyumna, paragraph 104, “In some embodiments, a processor (e.g., processor 168 in FIG. 1) or other controller may be coupled to a choke valve or other pressure adjustment mechanism of the wellbore. Thus, during operations, the processor may automatically make adjustments to the position of the choke so as to maintain the well within the operating envelope. For instance, if a well operator desires to increase a drawdown pressure of the well, the processor may automatically adjust the position of the choke valve to achieve the desired drawdown pressure while maintaining the operating parameter (e.g., drawdown pressure, rate of change of pressure, etc.) within the operating envelope so as to avoid or at least limit fluid inflow from the production zones of the wellbore.”).
Pradyumna does not expressly disclose that the choke valve is adjusted based on the water injection scheme. However, Tang teaches(Tang, page 4, section 3, paragraph 1, “The principle of the well control optimization methods is as follows: read production dynamic data and oil saturation field data from the numerical simulation model, form training and test data sets through data processing, and use these data to establish a production dynamic prediction model based on a multi-input deep neural network. Then, randomly generate injection-production schemes with different injection-production parameters, apply the production dynamic prediction model to predict the production dynamics of each scheme, calculate the objective function value, and select the scheme corresponding to the largest objective function as the optimal scheme.”), Here, Tang shows the updating of injection control parameters, which is interpreted to allow for the adjusting of the choke feature of Pradyumna, in order to create desired output based on the water injection scheme optimization. .
Tang further teaches:
injecting, using an injection system, the water through the adjusted component and into the reservoir via the injection well. (Tang, page 6, section 3.4, paragraph 2, “The parameters to be designed for each plan are as follows: (1) control frequency; (2) water injection volume of each injection well during each regulation; (3) fluid production volume of each production well during each regulation.”, water injection parameters pertain to control frequency, injection volume, and fluid production value, all of which may be applied to the choke valve of Pradyumna.
Tang, page 6, section 3.4, “In this step, the control frequency is used as a part of the injection-production parameter design, combined with reservoir engineering constraints, to generate different injection-production plans and then use the production dynamic prediction model formed in the previous step to predict the production dynamics and obtain the future production dynamic results of each plan.”, =.
Tang does not expressly disclose a choke valve for performing the adjustments of choke parameters based on the optimal water injection scheme. However Pradyumna does teach a choke valve being used to control water injection (downward pressure), (Pradyumna, paragraph 25, “As described herein, the drawdown pressure may be influenced or managed by the actuation of choke valves or other pressure adjustment devices (e.g., pumps, valves, etc.), and can be selected individually across zones when the proper completion assemblies are present.”), therefore it is interpreted by the examiner that the adjustment of Pradyumna’s choke valve can be determined by the optimal water injection parameters gained from Tang.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Pradyumna with that of Tang and extend the use of water injection schemes to further optimize production goals of a wellbore system. A motivation for which is to identify the most optimal control scheme for desired production parameter design. (Tang, page 10, section 4.6.5, “Because this method can quickly generate thousands of injection-production plans and can quickly optimize these plans, it is entirely possible to use this advantage to control the frequency as part of the injection production parameter design.”)
Claim 25: Pradyumna and Tang teaches the limitations of claim 21, Pradyumna further teaches:
The method of claim 21, wherein transferring the data comprises wirelessly transferring the data. (Pradyumna, paragraph 132, “Alternatively, the processor 782 may process the executable instructions and/or data structures by remotely accessing the computer program product, for example by downloading the executable instructions and/or data structures from a remote server through the network connectivity devices 792.”
Paragraph 128, “The network connectivity devices 792 may take the form of modems, modem banks, Ethernet cards, universal serial bus (USB) interface cards, serial interfaces, token ring cards, fiber distributed data interface (FDDI) cards, wireless local area network (WLAN) cards”)
Claim 26: Pradyumna and Tang teaches the limitations of claim 21, Tang further teaches:
The method of claim 21, wherein the water injection scheme comprises water injection control parameters comprising at least one of a water injection rate, a time duration of water injection, or a component size. (Tang, page 6, col. 2, paragraph 2, “The parameters to be designed for each plan are as follows: (1) control frequency; (2) water injection volume of each injection well during each regulation; (3) fluid production volume of each production well during each regulation.”, Tang teaches designing and adjusting water injection volumes (rate and duration implicitly via regulation frequency) as part of the injection scheme.)
The rationale and motivation to combine the teachings of Pradyumna and Tang are similar to that applied for claim 21 above.
Claim 27: Pradyumna and Tang teaches the limitations of claim 21, Pradyumna further teaches:
The method of claim 21, wherein the component comprises a choke. (Pradyumna, paragraph 104, “In some embodiments, a processor (e.g., processor 168 in FIG. 1) or other controller may be coupled to a choke valve or other pressure adjustment mechanism of the wellbore. Thus, during operations, the processor may automatically make adjustments to the position of the choke so as to maintain the well within the operating envelope. For instance, if a well operator desires to increase a drawdown pressure of the well, the processor may automatically adjust the position of the choke valve to achieve the desired drawdown pressure while maintaining the operating parameter (e.g., drawdown pressure, rate of change of pressure, etc.) within the operating envelope so as to avoid or at least limit fluid inflow from the production zones of the wellbore.”)
Claim 28 has limitations substantially similar to that of claim 21, as such a similar analysis applies.
Claims 32-34 has limitations substantially similar to claims 25-27, as such a similar analysis applies.
Claims 22 and 29 are rejected under 35 U.S.C. 103 as being unpatentable over Pradyumna in view of Tang and Bai et al. (Bai, H., Cao, M., Huang, P., & Shan, J. (2021). Self-supervised semi-supervised learning for data labeling and quality evaluation. arXiv preprint arXiv:2111.10932.), hereafter referred to as Bai.
Claim 22: Pradyumna and Tang teaches the limitations of claim 21, Pradyumna further teaches:
The method of claim 21, further comprising: inputting the data into a trained classification model; (Pradyumna, paragraph 85, “Thus, the fluid inflow event detection model at block 214 may comprise a multivariate model in which the two or more frequency domain features are variables that may be provided by acoustic data (e.g., such as acoustic data obtained from DAS system 110 as previously described above). Thus, the fluid inflow event detection model may utilize one or more (e.g., at least two) of the frequency domain features as inputs therein.”, sensor data from DAS is input to a trained prediction model.)
Bai, in the same field of machine learning reliability, teaches the following limitations:
and producing a reliability from the trained classification model in response to the data. (Bai, page 3, paragraph 1, “Based on the consistency assumption [29] that nearby nodes are likely to have the same label, we can perform label propagation (LP) on the nearest neighbor graph to propagate information from samples with known labels to samples without label or with noisy labels as follows
PNG
media_image1.png
21
417
media_image1.png
Greyscale
”, the computation of smoothed pseudo labels of input data inherently include a calculation of “reliability” during the smoothing process. The output Y˜ (t+1) reflects deviations between original and smoothed input, thus increasingly smoothed inputs are originally identified as less reliable (noisy).
Page 4, section 3.2, paragraph 2, “We first examine the evidence for the consistency assumption [29] by simulating random noise in labels and then performing LP. If our nearest neighbor graph faithfully captures the similarity among data, LP will aggregate and smooth out the inconsistency from noisy neighbor labels so that the neighbors with the correct label can stand out.”, by simulating random noise in labels and then performing label propagation to smooth out the inconsistency from noisy neighbor labels so that the neighbors with the correct label can ‘stand out’, the method measures each samples label inconsistency and uses the magnitude of that correction (how much smoothing was needed) as its reliability score.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Pradyumna with that of Bai and use a two-part model for data reliability checking. A motivation for which is to identify the best data for classification and training. (Bai, page 2, section 2.2, paragraph 2, “After training is complete, we use `(fθ(xi), fθ(xj )) as a similarity metric between xi and xj .”, the model evaluates consistency by computing the similarity metric (the normalized dot product) between the learned representation of different images. If the representations of similar images are close, the data is deemed reliable.)
Claim 29 has limitations substantially similar to that of claim 22, as such a similar analysis applies.
Claim 36 is rejected under 35 U.S.C. 103 as being unpatentable over Pradyumna as applied to claim 35, in further view of Bai.
Claim 36: Pradyumna teaches the limitations of claim 35, Pradyumna, further teaches:
The method of claim 35, further comprising: obtaining second training data comprising the training production fluid data and training reliability data; (Pradyumna, paragraph 30, “In addition, the wellbore 114 can be a new wellbore, an existing wellbore, a straight wellbore, an extended reach wellbore, a sidetracked wellbore, a multi-lateral wellbore, and other types of wellbores for drilling and completing one or more production zones.”, new wellbore information may be obtained and is interpreted as the second training data.)
Bai, in the same field of machine learning reliability, further teaches:
and training a classification model using the second training data, wherein the classification model is trained to produce a reliability in response to the data. (Bai, page 3, paragraph 1, “Based on the consistency assumption [29] that nearby nodes are likely to have the same label, we can perform label propagation (LP) on the nearest neighbor graph to propagate information from samples with known labels to samples without label or with noisy labels as follows
PNG
media_image1.png
21
417
media_image1.png
Greyscale
”, the computation of smoothed pseudo labels of input data inherently include a calculation of “reliability” during the smoothing process. The output Y˜ (t+1) reflects deviations between original and smoothed input, thus increasingly smoothed inputs are originally identified as less reliable (noisy).
Page 4, section 3.2, paragraph 2, “We first examine the evidence for the consistency assumption [29] by simulating random noise in labels and then performing LP. If our nearest neighbor graph faithfully captures the similarity among data, LP will aggregate and smooth out the inconsistency from noisy neighbor labels so that the neighbors with the correct label can stand out.”, by simulating random noise in labels and then performing label propagation to smooth out the inconsistency from noisy neighbor labels so that the neighbors with the correct label can ‘stand out’, the method measures each samples label inconsistency and uses the magnitude of that correction (how much smoothing was needed) as its reliability score.)
The rationale and motivation to combine the teachings of Pradyumna and Bai are similar to that applied for claim 22 above.
Claims 23-24 and 30-31 are rejected under 35 U.S.C. 103 as being unpatentable over Pradyumna in view of Tang and Bai as applied to claims 22 and 29, and further in view of Mishra et al. (US11017321B1; published May 25, 2021), hereafter referred to as Mishra.
Claim 23: Pradyumna, Tang, and Bai teaches the limitations of claim 22, Mishra, in the same field of machine learning for production systems further teaches:
The method of claim 22, further comprising producing a recommendation from the trained classification model in response to the data, wherein the recommendation comprises a recommendation of replacing a defective sensor. (Mishra, abstract, “Machine learning (ML) models may be trained to categorize events that are detected based on operating characteristics data associated with the equipment asset, to determine a status of the equipment asset, and to recommend one or more maintenance actions (or other actions). Output that indicates the maintenance actions may be displayed to a user or used to automatically initiate performance of one or more of the maintenance actions.”, the classification of events (e.g., detecting a defective sensor via its degraded/low-reliability data signature) leads to determining an equipment status, and that the system recommends maintenance actions in response to that status. It’s interpreted that maintenance actions comprises recommendations to replace components, such as the sensors of Pradyunma.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Pradyumna with that of Mishra and use preventative maintenance/repair checking. A motivation for which is to identify faulty components in a system and determine ways to replace/resolve them. (Mishra, col. 13, line 54, “Determination of the maintenance actions may be based on analysis of historical repair data associated with the equipment asset 150 ( e.g. , work orders associated with the equipment asset 150 ) , and historical operating characteristics data indicating results of the historical repairs ( e.g. maintenance actions ) , historical status data associated with the equipment asset 150 , user input ,other information , or a combination thereof .”, historical repair data is used by the model to predict the best method to repair/resolve components or equipment.)
Claim 24: Pradyumna and Tang teaches the limitations of claim 23 Pradyumna further teaches:
The method of claim 23, further comprising replacing the defective sensor. Mishra, col. 20, line 3, “As non - limiting examples , the maintenance actions 116 may include inspection of the equipment asset 150 , maintenance or repair to the equipment asset 150 , replacement of the equipment asset 150… The output 138 may enable display of one or more of the maintenance actions 116 , enable automated performance of one or more of the maintenance actions 116”, once the recommendation to replace the defective sensor is produced, the system can initiate the corresponding maintenance action, including possibly automating parts ordering or guiding a technician to perform the replacement.)
The rationale and motivation to combine the teachings of Pradyumna and Mishra are similar to that applied for claim 23 above.
Claims 30-30has limitations substantially similar to claims 23-23, as such a similar analysis applies.
Claim 31: Pradyumna and Tang teaches the limitations of claim 30 Pradyumna further teaches:
The system of claim 30, further comprising a replacement equipment configured to replace the defective sensor. (Mishra, col. 20, line 3, “As non - limiting examples , the maintenance actions 116 may include inspection of the equipment asset 150 , maintenance or repair to the equipment asset 150 , replacement of the equipment asset 150… The output 138 may enable display of one or more of the maintenance actions 116 , enable automated performance of one or more of the maintenance actions 116”, once the recommendation to replace the defective sensor is produced, the system can initiate the corresponding maintenance action, including possibly automating parts ordering or guiding a technician to perform the replacement.)
Claim 37 is rejected under 35 U.S.C. 103 as being unpatentable over Pradyumna in view of Bai, as applied to claim 36, and further in view of Mishra.
Claim 37: Pradyumna, and Bai teaches the limitations of claim 36, Mishra, in the same field of machine learning for production systems further teaches:
The method of claim 36, wherein the second training data further comprises training recommendation data, (Mishra, col. 13, line 54, “Determination of the maintenance actions may be based on analysis of historical repair data associated with the equipment asset 150 ( e.g. , work orders associated with the equipment asset 150 ) , and historical operating characteristics data indicating results of the historical repairs ( e.g. maintenance actions ) , historical status data associated with the equipment asset 150 , user input ,other information , or a combination thereof .”, historical repair data is used by the model to predict the best method to repair/resolve components or equipment.)
and wherein the classification model is further trained to produce a recommendation in response to the data. (Mishra, abstract, “Machine learning (ML) models may be trained to categorize events that are detected based on operating characteristics data associated with the equipment asset, to determine a status of the equipment asset, and to recommend one or more maintenance actions (or other actions). Output that indicates the maintenance actions may be displayed to a user or used to automatically initiate performance of one or more of the maintenance actions.”, the classification of events (e.g., detecting a defective sensor via its degraded/low-reliability data signature) leads to determining an equipment status, and that the system recommends maintenance actions in response to that status. It’s interpreted that maintenance actions comprises recommendations to replace components, such as the sensors of Pradyunma.)
The rationale and motivation to combine the teachings of Pradyumna and Mishra are similar to that applied for claim 23 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure-Masoner, L. O., & Wackowski, R. K. (1994, April). Rangely Weber Sand Unit CO2 project update: Decisions and issues facing a maturing EOR project. In SPE Improved Oil Recovery Conference? (pp. SPE-27756); Katterbauer, K., Marsala, A., & Qasim, A. A. (2021, December). A deep learning wag injection method for Co2 recovery optimization. In SPE Middle East Oil and Gas Show and Conference (p. D041S050R004).
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HYUNGJUN B YI whose telephone number is (703)756-4799. The examiner can normally be reached M-F 9-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Jung can be reached on (571) 270-3779. 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.
/H.B.Y./Examiner, Art Unit 2146
/SHAHID K KHAN/Primary Examiner, Art Unit 2146
Prosecution Insights