CTNF 18/776,641 CTNF 83629 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. This office action is in response to application 18776641 filed on July 18, 2024. Claims 1-20 are pending. Information Disclosure Statement As required by M.P.E.P. 609(C), the applicant’s submissions of the Information Disclosure Statements dated July 18, 2024 and April 30, 2025 are acknowledged by the examiner and the cited references have been considered in the examination of the claims now pending. As required by M.P.E.P 609, a copy of the PTOL-1449 initialed and dated by the examiner is attached to the office action. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-21-aia AIA Claim s 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Salman et al. (US20220262104A1) in further view of Zhu et al. (US20050043921A1) . Regarding claim 1, Salman teaches a method for … equipment fault analysis, the method comprising: training, using first training data, one or more machine learning models to categorize previously unseen images of … equipment into one or categories of a plurality of categories (a method can utilize a framework that can improve machine learning to, for example, generate a trained machine ... An example of a machine learning model is a neural network ... a trained machine may be utilized for one or more tasks to assess data. For example, consider image data that include features where a task can be to classify one or more features in the image data ... machine learning as to one or more ML tools that can provide for object detection ... As an example, object detection can include detection of a solid object ... a pipeline can be a solid object (e.g., a pipe) ... FIG. 25 shows an example of a machine learning block 2540 suitable for use in active learning where the machine learning block 2540 includes receiving training data)([0038], [0039], [0046], and [0249]; training data is used to train a model to classify objects (e.g., equipment such as a pipe) in captured images) ; and training, using second training data, the one or more machine learning models to generate captions for the previously unseen images of … equipment (include detection capabilities, for example, to detect one or more conditions that may warrant action as to status of one or more pieces of subsea equipment (e.g., a damaged pump, a leaking valve, a shifted piece of equipment, a covered piece of equipment, an uncovered piece of equipment, etc.) ... object detection may detect a status such as broken or not broken … Such statuses, as captured in one or more images, may place substantial demands on labeling where labeled images are to be utilized ... features, objects, etc., may be in a state that can be assigned a status, which may be a detectable status through use of an inspection tool or inspection tools)([0075], [0078], and [0087]; the trained model further assigns captions (i.e., status descriptions such as “damaged pump”, “not broken”, etc.) to classified objects) . Although Salman discloses of analysis to equipment (Machine learning techniques, particularly supervised deep neural networks can provide for some amount of automation of video analysis and equipment imagery)([0204]) . Salman does not teach fault analysis of an electrical submersible pump. However, analyzing fault of an electrical submersible pump using trained models is taught by Zhu (Referring now to FIG. 1, system 10 for modeling behavior of electric submersible pump application ... Training data set 20 is of data related to one or more behaviors of electric submersible pump application ... These data may relate to at least one predetermined characteristic of the electric submersible pump application and may further be arranged as a plurality of data sets ... Neural network model is able to utilize training set 20 and measured data 23 to manipulate a model of submersible electrical pump application ... output of neural network model 40 may be used to aid with ... fault diagnosis of electric submersible pump application)([0007], [0008], [0010], and [0015]) . The examiner notes Salman and Zhu teach analyzing equipment. As such, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify Salman to include the analyzing of Zhu such that fault of an electrical submersible pump is analyzed. One would be motivated to make such a combination to provide the advantage of detecting fault in additional types of equipment. Regarding claim 2, Salman-Zhu teach the method of claim 1, the method further comprising: training, using third training data, the one or more machine learning models to determine a cause of a failure (Salman - Where a system operates with adequate object detection capabilities, a cause of failure may be more readily determined)([0081]) . Regarding claim 3, Salman-Zhu teach the method of claim 2, further comprising: providing a plurality of images of electrical submersible pump equipment as input to a machine learning model of the one or more machine learning models, wherein the first training data, the second training data, and the third training data do not include the plurality of images of the electrical submersible pump equipment (Salman - include receiving labeled images; acquiring unlabeled images; performing active learning by training an inspection learner using at least a portion of the labeled images to generate a trained inspection learner)([0003]; models are trained using previously captured images) ; and generating, using the machine learning model, a failure cause based, at least in part, on the plurality of images of the electrical submersible pump equipment (Salman - Where a ML tool trained at least in part via active learning can be utilized to more accurately analyze image data (e.g., as to equipment, fluid, sand, etc.), earlier detection may be possible as well as cause of failure)([0081]) . Regarding claim 4, Salman-Zhu teach the method of claim 3, further comprising generating, using the one or more machine learning models, a reliability report based, at least in part, on the plurality of images of electrical submersible pump equipment (Salman - As to logging, rather than manually tracing anomalies occurrences on paper, an edge-based implementation can perform logging automatically, for example, by automatically generating a report)([0195]) . Regarding claim 5, Salman-Zhu teach the method of claim 1, the method further comprising: providing an image of electrical submersible pump equipment as input to a machine learning model of the one or more machine learning models, wherein the first training data does not include the image of the electrical submersible pump equipment (Salman - include receiving labeled images; acquiring unlabeled images; performing active learning by training an inspection learner using at least a portion of the labeled images to generate a trained inspection learner … Labeled data can be considered “ground truth” data in that one or more features have been detected with certainty and labeled with an appropriate moniker ... e.g., a damaged pump, a leaking valve, a shifted piece of equipment, a covered piece of equipment, an uncovered piece of equipment, etc.)([0003], [0048], and [0075]; images of equipment (e.g., pump) are provide as training data to detect equipment) ; and generating, using the machine learning model, an indication of a category of the plurality of categories (Salman - As to deep object detection, an approach may aim to classify and localize objects of predefined classes on an image)([0206]) . Regarding claim 6, Salman-Zhu teach the method of claim 1, the method further comprising: providing an image of electrical submersible pump equipment as input to a machine learning model of the one or more machine learning models, wherein the second training data does not include the image of the electrical submersible pump equipment (Salman - include receiving labeled images; acquiring unlabeled images; performing active learning by training an inspection learner using at least a portion of the labeled images to generate a trained inspection learner … Labeled data can be considered “ground truth” data in that one or more features have been detected with certainty and labeled with an appropriate moniker ... e.g., a damaged pump, a leaking valve, a shifted piece of equipment, a covered piece of equipment, an uncovered piece of equipment, etc.)([0003], [0048], and [0075]; images of equipment (e.g., pump) are provide as training data to detect equipment) ; and generating, using the machine learning model, a caption corresponding to the image of the electrical submersible pump equipment (Salman - include detection capabilities, for example, to detect one or more conditions that may warrant action as to status of one or more pieces of subsea equipment … a pipe (or other solid object) is “broken” … Such statuses, as captured in one or more images, may place substantial demands on labeling where labeled images are to be utilized ... features, objects, etc., may be in a state that can be assigned a status, which may be a detectable status through use of an inspection tool or inspection tools)([0075], [0078], and [0087]; a caption (i.e., status description such as “broken”) is assigned to a classified object) . Regarding claim 7, Salman-Zhu teach the method of claim 1, wherein the first training data comprises at least a first plurality of images of electrical submersible pump equipment and the second training data comprises at least a second plurality of images of electrical submersible pump equipment with associated captions (Salman - FIG. 4 shows an example of a method 410 that includes a reception block 414 for receiving labeled images; an acquisition block 418 for acquiring unlabeled images; a performance block 422 for performing active learning by training an inspection learner using at least a portion of the labeled images to generate a trained inspection learner that outputs information responsive to receipt of one of the unlabeled images by the trained inspection learner)([0103]; training data includes images and associated labels (i.e., classification of objects and statuses) to train a model) . Regarding system claims 8-14, the claims generally correspond to method claims 1-7, respectively, and recite similar features in system form; therefore, the claims are rejected under similar rationale. Regarding non-transitory computer-readable medium claims 15-20, the claims generally correspond to method claims 1-6, respectively, and recite similar features in non-transitory computer-readable medium form; therefore, the claims are rejected under similar rationale. Conclusion The prior art made of record on form PTO-892 and not relied upon is considered pertinent to applicant's disclosure. Applicant is required under 37 C.F.R. § 1.111(c) to consider the reference fully when responding to this action. The document cited therein and enumerated below teaches a method and apparatus for equipment fault analysis using machine learning. US20190169962A1 US20200285997A1 US20220036541A1 US20230212937A1 US20240003242A1 US20240018863A1 US20240177541A1 US20250077338A1 US20250122794A1 US20250225784A1 CN112785091A CN112832999A The document cited therein and enumerated below teaches a method and apparatus for using machine learning to analyze images. US20180268256A1 US20210337098A1 US20220108210A1 US20230334814A1 US11263482B2 Any inquiry concerning this communication or earlier communications from the examiner should be directed to Yongjia Pan whose telephone number is (571)270-1177. 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, Scott Baderman can be reached at 571-272-3644. 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. /YONGJIA PAN/Primary Examiner, Art Unit 2118 Application/Control Number: 18/776,641 Page 2 Art Unit: 2118 Application/Control Number: 18/776,641 Page 4 Art Unit: 2118 Application/Control Number: 18/776,641 Page 5 Art Unit: 2118 Application/Control Number: 18/776,641 Page 6 Art Unit: 2118 Application/Control Number: 18/776,641 Page 7 Art Unit: 2118 Application/Control Number: 18/776,641 Page 8 Art Unit: 2118 Application/Control Number: 18/776,641 Page 9 Art Unit: 2118
Prosecution Insights