DETAILED ACTION
This office action is in response to communications filed 5/5/2025
Claims 1-4, 6-12, 14-22 are pending
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 .
Response to Arguments
Applicant argues: “Thus, Applicant submits that the amended claims overcome the 35 U.S.C. 101 rejection, because the claimed invention is directed to a technological process applied to a specific field (vehicle structural health monitoring), uses real-world, physically connected structural health monitoring sensors, including a strain gauge and/or a displacement transducer, to acquire input, outputs a practical classification for vehicle inspection, and improves existing processes by automating a real-world task with physical context, thereby demonstration integration into a practical application”.(Applicant’s argument at page 15)
Examiner response: The examiner respectfully disagrees. The use of strain gauge and/or displacement transducer to collect input data limitation as recited in the amended claim 1 simply adds insignificant extra solution activity to the judicial exception and therefore does not amount to an inventive concept as per MPEP 2106.05 (g): “As explained by the Supreme Court, the addition of insignificant extra-solution activity does not amount to an inventive concept, particularly when the activity is well-understood or conventional”. Using a strain gauge and/or a displacement transducer to measure strain is well known in the art as discloses by Giaier et al. US Patent 9,452,657 B1, col 4, lines 1-10 “Strain sensors or strain gauges are well-known devices for measuring strain in a material. Many sensors and detection circuits are commercially available which are optimized for determining strain in both torsion or tension modes”. Since the additional element even when considered in combination, does not provide an inventive concept, claim 1 therefore is ineligible.
Applicant’s remaining arguments with respect to other claims are substantially encompassed in the argument above, therefore examiner responds with the same rationale as stated above. For at least the foregoing reasons, the examiner maintains 101 rejection.
Applicant's arguments with respect to rejection of claims under 35 USC 102 and 103 have been considered but are moot in view of the new ground of rejection.
Claim Objections
Claims 1,10 and 19 are objected to because of the following informalities: Claims 1,10 and 19 recite the term "and/or", which is selective language, the examiner suggests using either the "and" term or the "or" term, otherwise the claims should be worded in a clearer fashion to claim both terms. For the purpose of this examination the examiner is selecting the "or" term from this selective language. Appropriate correction is required.
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.
1. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea (mental process) without significantly more.
Regarding claim 1, in Step 1 of the 101 analysis set forth in the MPEP 2106, the claim recites a machine that by assistance of peripheral components identifies and diagnoses solutions to faults in a vehicle system. A machine is one of the four statutory categories of invention.
In Step 2a Prong 1 of the 101 analysis set forth in the MPEP 2106, the examiner has determined that the following limitations recite a process that under broadest reasonable interpretation, covers a mental process but for recitation of generic computer components:
“Extract features of the run-time event input data;” (a person can mentally extract information from readings given by an instrument by evaluating the data, and making a judgement on the values and meaning of the data (MPEP 2106)).
“Determine a predicted inspection classification based upon the extracted features,” (a person can mentally come to the conclusion of the classification of a given set of data as a process of simply evaluating the data, and making a judgement of a prediction to classify the data by (MPEP 2106)).
If claim limitations, under their broadest reasonable interpretation, covers
performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas.
According, the claim “recites” an abstract idea.
In Step 2a Prong 2 of the 101 analysis set forth in MPEP 2106, the examiner has
determined that the following additional elements do not integrate this judicial exception
into a practical application:
“A maintenance computing system comprising:” (uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)))
“a processor and non-volatile memory storing executable instructions that, in response to execution by the processor, cause the processor to:” (uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)))).
“execute an inspection classifier including at least a first artificial intelligence model, the inspection classifier being configured to: … The predicted inspection classification being one of a plurality of candidate inspection classifications;” (uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)))
“receive run-time input data from a plurality of data sources associated with a vehicle,” (insignificant mere data gathering (MPEP 2106.05(g)))
“the data sources including one or more structural health monitoring sensors instrumented on the vehicle;” (generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h)))
“and output the predicted inspection classification, wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer” (insignificant mere data output (MPEP 2106.05(g)))
Since the claim does not contain any other additional elements that are indicative
of integration into a practical application, the claim is “directed” to an abstract idea.
In step 2b Prong 2 of the 101 analysis set forth in the 2019 PEG, the examiner
has determined that the claim does not include additional elements that are sufficient to
amount to significantly more than the judicial exception.
As discussed above, additional element (vii) recites generally linking the use of the judicial exception to a particular technological environment or field of use, which is not indicative of significantly more. Additional element (iii, iv, v) recite application of a computer tool (artificial intelligence model), which is not indicative of significantly more. Additional element (vi, viii) recite insignificant extra-solution activity in the form of mere data gathering and mere data output respectively, which additionally is well understood, routine, and conventional activity of receiving data over a network (MPEP 2106.05(d)(II), which is not indicative of significantly more. Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide more than the abstract idea. Therefore, the claim is not patent eligible.
Regarding claim 2, it is dependent on claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further claim 2 recites “wherein the inspection classifier has been trained on inspection classifier training data including inspection training input data and associated ground truth labels,” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “the inspection training input data including structural health data from one or more structural health monitoring sensors instrumented on the vehicle,” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “and the inspection ground truth labels being user inputted inspection classification associated with the inspection training input data” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “the user inputted inspection classifications being selected from the plurality of candidate inspection classifications” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 3, it is dependent on claim 2, and thereby incorporates the limitations of, and corresponding analysis applied to claim 2. Further claim 3 recites “wherein the inspection classifier training data further includes at least one of camera images, audio data, or dimensional measurements;” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more. Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 4, it is dependent on claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further claim 4 recites “wherein the processor is configured to:” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “receive user input of an adopted inspection classification for the run-time event input data;” (In step 2a, In step 2a, Prong 2, this recites insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network which is well understood, routine, and conventional, which is not indicative of significantly more.) “and perform feedback training of the first artificial intelligence model using the run-time event input data and the adopted inspection classification as a feedback training data pair” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites using a computer to perform an abstract idea, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 6, it is dependent on claim 4, and thereby incorporates the limitations of, and corresponding analysis applied to claim 4. Further “wherein the processor is further configured to execute a repair classifier including at least a second artificial intelligence model, being configured to:” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “receive run-time inspection input data including inspection-associated input data and the adopted inspection classification;” (In step 2a, In step 2a, Prong 2, this recites insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) “extract inspection features of the run-time inspection input data;” (In step 2a, Prong 1, a person can mentally come a conclusion of reading one or more instrument(s) that are outputting information during operation as a process of simply making an evaluation and observation of the information being presented to them, and making a judgement on the context of the information provided (MPEP 2106). If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for recitation of generic computer components then it falls within the mental process grouping of abstract ideas. According, the claim recites an abstract idea.) “determine a predicted classification based upon the extracted inspection features,” (In step 2a, Prong 1, a person can mentally come to the conclusion of making a prediction of the classification of an event as of process of simply making an evaluation of the different measurements and elements that comprise the event, and making a judgement on the best terminology to classify the event by. If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for recitation of generic computer components then it falls within the mental process grouping of abstract ideas. According, the claim recites an abstract idea.) “the predicted repair classification being one of a plurality of candidate repair classifications;” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “output the predicted repair classification;” (In step 2a, Prong 2, this recites insignificant data output (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites transmitting data over a network, which is not indicative of significantly more.) “receive user input of an adopted repair classification for the run-time inspection input data;” (In step 2a, In step 2a, Prong 2, this recites insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) “and perform feedback training of the second artificial intelligence model using the inspection-associated input data and the adopted repair classification as a feedback training data pair” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 7, it is dependent on claim 6, and thereby incorporates the limitations of, and corresponding analysis applied to claim 6. Further claim 7 recites “wherein the repair classifier has been trained on repair classifier training data including repair training input data and associated ground truth labels,” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “the repair training input data including imaging studies and electrical measurements, and the ground truth labels being user inputted repair classifications associated with the repair training input data,”” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “the user inputted repair classifications being selected from the plurality of candidate repair classifications” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 8, it is dependent on claim 6, and thereby incorporates the limitations of, and corresponding analysis applied to claim 6. Further claim 8 recites “wherein the processor further executes a monitoring classifier including a third artificial intelligence model, the monitoring classifier being configured to:” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “receive run-time repair input data including repair-associated input data and an adopted repair classification;” (In step 2a, Prong 2, this recites insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) “extract features of the run-time repair input data;” (In step 2a, Prong 1, a person can mentally come a conclusion of reading one or more instrument(s) that are outputting information during operation as a process of simply making an evaluation and observation of the information being presented to them, and making a judgement on the context of the information provided (MPEP 2106). If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for recitation of generic computer components then it falls within the mental process grouping of abstract ideas. According, the claim recites an abstract idea.) “determine a predicted monitoring classification based upon the extracted repair features,” (In step 2a, Prong 1, a person can mentally come to the conclusion of making a prediction of the classification of an event as of process of simply making an evaluation of the different measurements and elements that comprise the event, and making a judgement on the best terminology to classify the event by. If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for recitation of generic computer components then it falls within the mental process grouping of abstract ideas. According, the claim recites an abstract idea) “the predicted monitoring classification being one of a plurality of candidate monitoring classifications;” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “output the predicted monitoring classification;” (In step 2a, Prong 2, this recites insignificant data output (MPEP 2106.05(g)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer to transmit data over a network, which is not indicative of significantly more.) “receive user input of an adopted monitoring classification for the run-time repair input data;” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) “and perform feedback training of the third artificial intelligence model using the run-time repair input data and the adopted monitoring classification as a feedback training data pair” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 9, it is dependent on claim 8, and thereby incorporates the limitations of, and corresponding analysis applied to claim 8. Further claim 9 recites “wherein the repair-associated input data include at least one of repair materials or type of repair” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 10, in Step 1 of the 101 analysis set forth in the MPEP 2106, the claim recites a machine that by assistance of peripheral components identifies and diagnoses solutions to faults in a vehicle system. A machine is one of the four statutory categories of invention.
In Step 2a Prong 1 of the 101 analysis set forth in the MPEP 2106, the examiner has determined that the following limitations recite a process that under broadest reasonable interpretation, covers a mental process but for recitation of generic computer components:
“Extract features of the run-time event input data;” (a person can mentally extract information from readings given by an instrument by evaluating the data, and making a judgement on the values and meaning of the data (MPEP 2106)).
“Determine a predicted inspection classification based upon the extracted features,” (a person can mentally come to the conclusion of the classification of a given set of data as a process of simply evaluating the data, and making a judgement of a prediction to classify the data by (MPEP 2106)).
If claim limitations, under their broadest reasonable interpretation, covers
performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas.
According, the claim “recites” an abstract idea.
In Step 2a Prong 2 of the 101 analysis set forth in MPEP 2106, the examiner has
determined that the following additional elements do not integrate this judicial exception
into a practical application:
“A maintenance computing method, comprising: executing an inspection classifier including at least a first artificial intelligence model,” (uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)))
“executing the inspection classifier including: receiving run-time event input data from a plurality of data sources associated with a vehicle,” (insignificant mere data gathering (MPEP 2106.05(g)))
“the data sources including one or more structural health monitoring sensors instrumented on the vehicle;” (generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h)))
“The predicted inspection classification being one of a plurality of candidate inspection classifications;” (generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h)))
“outputting the predicted inspection classification; wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer”” (insignificant mere data output (MPEP 2106.05(g)))
“receiving user input of an adopted inspection classification for the run-time event input data;” (insignificant mere data gathering (MPEP 2106.05(g)))
“and performing feedback training of the first artificial intelligence model using the run-time event input data and the adopted inspection classification as a feedback data pair.” (uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)))
Since the claim does not contain any other additional elements that are indicative of integration into a practical application, the claim is “directed” to an abstract idea.
In step 2b Prong 2 of the 101 analysis set forth in the 2019 PEG, the examiner has determined that the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
As discussed above, additional element (v, vi) recites generally linking the use of the judicial exception to a particular technological environment or field of use, which is not indicative of significantly more. Additional element (iii, ix) recites application of a computer tool (artificial intelligence model), which is not indicative of significantly more. Additional element (iv, vii, viii) recites insignificant extra-solution activity in the forms of data gathering and data output, which is not indicative of significantly more. Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide more than the abstract idea. Therefore, the claim is not patent eligible.
Regarding claim 11, it is dependent on claim 10, and thereby incorporates the limitations of, and corresponding analysis applied to claim 10. Further claim 11 recites “prior to executing the inspection classifier, training the inspection classifier on inspection classifier training data including training input data and associated ground truth labels,” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “the training input data including structural health data from the structural health monitoring sensors instrumented on the vehicle,” (generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h)), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the judicial exception to the training of an artificial intelligence model, which is not indicative of significantly more.) “and the ground truth labels being user inputted inspection classifications associated with the training input data,” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more) “the user inputted inspection classifications being selected from the plurality of candidate inspection classifications.” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g)), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 12, it comprises similar limitations as claim 3 and therefore is rejected upon similar rationale.. Regarding claim 14, it comprises similar limitations as claim 6 and therefore is rejected upon similar rationale. Since the claims do not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception the claims are not patent eligible.
Regarding claim 15, it is dependent on claim 14, and thereby incorporates the limitations of, and corresponding analysis applied to claim 14. Further claim 15 recites “prior to executing the repair classifier, training the repair classifier on repair classifier training data including repair classifier training input data and associated ground truth labels,” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “the repair classifier training input data including imaging studies and electrical measurements,” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “and the ground truth labels being user inputted repair classifications associated with the repair classifier training input data,” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g)), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more) “the user inputted repair classifications being selected from the plurality of candidate repair classifications.” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g)), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 16, it comprises similar limitations as claim 8 and therefore is rejected upon similar rationale. Regarding claim 17, it comprises similar limitations as claim 9 and therefore is rejected upon similar rationale. Since the claims do not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception the claims are not patent eligible.
Regarding claim 18, it is dependent on claim 16, and thereby incorporates the limitations of, and corresponding analysis applied to claim 16. Further claim 18 recites “prior to executing the monitoring classifier, training the monitoring classifier on monitoring training data including monitoring training input data and associated ground truth labels,” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “the monitoring training input data including imaging studies and electrical measurements,” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g)), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more) “and the ground truth labels being user inputted repair classifications associated with inspection training input data,” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) “the user inputted repair classifications being selected from the plurality of candidate repair classifications.” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g)), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 19, in Step 1 of the 101 analysis set forth in the MPEP 2106, the claim recites a machine that by assistance of peripheral components identifies and diagnoses solutions to faults in a vehicle system. A machine is one of the four statutory categories of invention.
In Step 2a Prong 1 of the 101 analysis set forth in the MPEP 2106, the examiner has determined that the following limitations recite a process that under broadest reasonable interpretation, covers a mental process but for recitation of generic computer components:
“receiving user input of an adopted inspection classification for the run-time event input data;” (a person can mentally come to a conclusion of a means to give input of a decision of classification based on data provided to them as a process of simply evaluating the data provided to them, and making a judgement on how the data should be classified. (MPEP 2106))
If claim limitations, under their broadest reasonable interpretation, covers
performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas.
According, the claim “recites” an abstract idea.
In Step 2a Prong 2 of the 101 analysis set forth in MPEP 2106, the examiner has determined that the following additional elements do not integrate this judicial exception into a practical application:
“A maintenance computing system, comprising: a processor and a non-volatile memory storing executable instructions that, in response to execution by the processor, cause the processor to:” (using a computer to perform an abstract idea (MPEP 2106.05(f)))
“execute an inspection classifier configured to determine a predicted inspection classification based on run-time event input data from structural health monitoring sensors instrumented on a vehicle;” (generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h)))
“output the predicted inspection classification;” (mere insignificant data output (MPEP 2106.05(g)))
“performing feedback training of the inspection classifier using the run-time event input data and the adopted inspection classification as a feedback training data pair;” (using a computer to perform an abstract idea (MPEP 2106.05(f)))
“execute a repair classifier to determine a predicted repair classification based upon run-time inspection input data including inspection-associated input data and the adopted inspection classification;” (generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h)))
“output the predicted repair classification” (mere insignificant data output (MPEP 2106.05(g)))
“receive user input of an adopted repair classification for the run-time inspection input data” ; “wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer” (mere insignificant data gathering (MPEP 2106.05(g)))
“perform feedback training of the repair classifier using the run time inspection input data and the adopted repair classification as a feedback training data pair” (using a computer to perform an abstract idea (MPEP 2106.05(f)))
Since the claim does not contain any other additional elements that are indicative of integration into a practical application, the claim is “directed” to an abstract idea.
In step 2b Prong 2 of the 101 analysis set forth in the 2019 PEG, the examiner has determined that the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
As discussed above, additional element (iii, vi) recites generally linking the use of the judicial exception to a particular technological environment or field of use, which is not indicative of significantly more. Additional element (ii, v, xi) recite application of a computer tool (artificial intelligence model), which is not indicative of significantly more. Additional element (iv, vii, viii) recites insignificant extra-solution activity in the form of receiving input over a network and outputting gather information to the user, which is not indicative of significantly more. Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide more than the abstract idea. Therefore, the claim is not patent eligible.
Regarding claim 20, it is dependent on claim 19, and thereby incorporates the limitations of, and corresponding analysis applied to claim 19. Further claim 20 recites execute a monitoring classifier to determine a predicted monitoring classification based upon run-time repair input data including repair-associated input data and the adopted repair classification; (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) “output the predicted monitoring classification” (In step 2a, Prong 2, this recites mere insignificant data output (MPEP 2106.05(g)), which is not indicative to integration into a practical application. In step 2b, the limitation recites outputting classification data to a user, which is not indicative of significantly more.) “receive user input of an adopted monitoring classification for the run-time repair input data;” (In step 2a, Prong 2, this recites mere insignificant data gathering (MPEP 2106.05(g), which is not indicative to integration into a practical application. In step 2b, the limitation recites receiving data over a network, which is not indicative of significantly more.) “and perform feedback training of the monitoring classifier using the run-time repair input data and the adopted monitoring classification as a feedback training data pair.” (In step 2a, Prong 2, this recites using a computer to perform an abstract idea (MPEP 2106.05(f)), which is not indicative of integration into a practical application. In step 2b, the limitation recites use of a computer as a tool to perform an abstract idea, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 21, it is dependent on claim 3, and thereby incorporates the limitations of, and corresponding analysis applied to claim 3. Further claim 21 recites “wherein the run-time event input data further includes at least one of camera images, audio data, or dimensional measurements” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Regarding claim 22, it is dependent on claim 12, and thereby incorporates the limitations of, and corresponding analysis applied to claim 12. Further claim 22 recites “wherein the run-time event input data further includes at least one of camera images, audio data, or dimensional measurements” (In step 2a, Prong 2, this recites generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05(h))), which is not indicative of integration into a practical application. In step 2b, the limitation recites generally linking the invention to a particular technological environment or field of use, which is not indicative of significantly more.) Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
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.
3. Claims 1 and 4 are rejected under 35 U.S.C. 103 as being unpatentable over Anthony Pub No.: US 2018/0315260 A1, hereinafter “Anthony” and further in view of Black et al.,( US Patent Application Publication 2018/0170532 A1, hereinafter “Black”)
Regarding claim 1, Anthony teaches,
execute an inspection classifier including at least a first artificial intelligence model, ([0026] FIG. 1 illustrates how sensors (1) feed signal processing elements (2) which in turn drive decisions by a machine learning (ML) model (ie. classification by at least a first AI model) [0036] The ML model makes determinations about the diagnosis of the vehicle (healthy or specific error)… This will either reinforce the ML model if the diagnosis was correct, or tell the ML model it was incorrect and re-classify it appropriately. (ie. The ML model is performing the job of classifying inspected features)) the inspection classifier being configured to: receive run-time event input data from a plurality of data sources associated with a vehicle, the data sources including one or more structural health monitoring sensors instrumented on the vehicle; ([0026] One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones, accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) etc., located on or near a vehicle. (ie. a plurality of sources are being used to determine vehicle health during the active run-time of the vehicle)) the data sources including structural health monitoring sensors instrumented on the vehicle; ([0026] The sensors can be specialized sensors integrated with the vehicle at the time of manufacture, specialized sensors installed as aftermarket components by a dealer or the consumer, or may be provided by the operators personal mobile device such as a smartphone or tablet which is located in the vehicle. (ie. data source is located on the vehicle)) extract features of the run-time event input data; ([0075] FIG. 7 illustrates the output of a machine learning model that identifies a failure in real-time (ie. data features gathered during run-time), that is, something has happened (the engine is pinging, or the brakes are squealing), and there is some relative importance, or not, of the issue (29).) determine a predicted inspection classification based upon the extracted features, ([0036] In one approach, a companion OBD-II reader is plugged into the car (or otherwise accessed) to read diagnostic codes in real time while a nearby device (phone or special hardware) is also collecting sensor data. The ML model makes determinations about the diagnosis of the vehicle (ie. input data is being used to classify) (healthy or specific error).) the predicted inspection classification being one of a plurality of candidate inspection classifications; ([0028] The filter/signal processing techniques are tailored to the specific attribute condition, symptom, or whatever it is that the system is trying to detect. A combination of filtering and signal processing methods will typically be unique for the symptom to be identified, selected during a system design phase. (ie. a plurality of outputs specialized to the type of vehicle system is in)) and output the predicted inspection classification. ([0043] The diagnostic information may also be sent to a partner network (ie. output inspection classified data) of dealerships or repair facilities at (15). These partners may provide real-time price quoting for a needed repair, so that the user can have a list of options to compare.) [wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer]
Anthony fails to expressly teach wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer.
However, Black teaches wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer.(Black par [0044] teaches the Structural Health Monitoring is conducted via strain gauges or strain sensors mounted on aircraft structure)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Anthony and Black to achieve the claimed invention . One would have been motivated to make such combination to mitigate incorrect forces to extend the life of structures and/or critical components.(Black par [0016])
Regarding claim 4, Anthony and Black further teaches
receive user input of an adopted inspection classification for the run-time event input data; (Anthony par [0082] teaches An optional incentive program may be developed to reward the end user and mechanic, or other manual process, to gather and share the diagnosis information which can be used to improve the ML model (ie. Shared data for classification is received by the system)) and perform feedback training of the first artificial intelligence model using the runtime event input data and the adopted inspection classification as a feedback training data pair. (Anthony par [0081] The cloud system may attempt to diagnose the anomaly by processing the data further and then analyze it against the global population of data from other deployments and test data (45) (ie. data is tested against other data the ML model has in a training type environment). Once a diagnosis is found the result may be sent back to the end user, and the local system is updated with an improved ML model (48) (ie. once the training is completed it is fed back into the model for use by the end user with implemented improvements). Anthony par [0082], the end user may be asked to engage a mechanic or other manual process to diagnose the system (49). An optional incentive program may be developed to reward the end user and mechanic, or other manual process, to gather and share the diagnosis information which can be used to improve the ML model (ie. the training process includes user inputted adopted classifications) (52).)
4. Claims 2-3 and 6-12,14-18 and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Anthony, Black and further in view of Mishra et al. Patent No.: US 11,017,321 B1, hereinafter “Mishra”.
Regarding claim 2 Anthony and Black teach,
the inspection training input data including structural health data from one or more structural health monitoring sensors instrumented on the vehicle, (Anthony par [0026] One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones, accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) etc., located on or near a vehicle. (ie. a plurality of sources are being used to determine vehicle health)
Regarding Claim 2, while Anthony and Black teach the use of an artificial intelligence (AI) model for the use in providing insight on the structural health of a vehicle based on gathered sensor data, Anthony and Black do not explicitly teach,
wherein the inspection classifier has been trained on inspection classifier training data including inspection training input data and associated inspection ground truth labels, … , and the inspection ground truth labels being user inputted inspection classifications associated with the inspection training input data, the user inputted inspection classifications being selected from the plurality of candidate inspection classifications.
However, in analogous art that similarly teaches the use of AI to diagnose and make predictions of maintenance actions using sensors, Mishra teaches:
wherein the inspection classifier has been trained on inspection classifier training data including inspection training input data and associated inspection ground truth labels, ((Page 9, Column 3) The first set of ML models may be trained using training data that is generated based on historical operating characteristics data, historical event data, ratings associated with historical events (e.g., from the knowledge base) (ie. training values initially derived by past event truths [ground truth] from the user created knowledge base), and the like.)
Mishra further teaches,
and the inspection ground truth labels being user inputted inspection classifications associated with the inspection training input data, ((Page 9, Column 3) Alternatively, the detected events and the operating characteristics data may be compared to a list of priority events from the knowledge base (e.g., priority events that are identified based on input from engineers or other experts, (ie. The inputted data is being used by users of the system to generate a database of training information based on the prementioned knowledge base, where the knowledge base is made up of in part user inputted ground truth labels) analysis performed by the system, or a combination thereof).) the user inputted inspection classifications being selected from the plurality of candidate inspection classifications. ((Page 9, Column 3) Alternatively, the detected events and the operating characteristics data may be compared to a list of priority events from the knowledge base (ie. The candidate inspection can be one of many events from a list of pre-classified events)
It would be obvious to one of ordinary skill in the art before the effective filing date of the invention to have combined Mishra’s teaching of a multi agent artificial intelligence model for use in maintenance based predictive classification and action recommendation including training data received from run-time events paired with historical data including user inputted documentation and action adoption, with Anthony and Black’s teaching of a vehicle diagnostic artificial intelligence modeled to provide the users with predictive fault detection through the utilization of multiple sources of sensor data. It would have been further obvious to this person of ordinary skill in the art to be motivated to make this combination, with reasonable chance of success, to allow each modular artificial intelligence classification agent to be granted tailored and relevant types of training data based on the required classification type, and further to decrease the time required in each iterative feedback training phase to maintain higher accuracy in the output and agent availability for new classification jobs.
Regarding claim 3 Anthony, Black and Mishra teach,
wherein the inspection classifier training data further includes at least one of camera images, audio data, or dimensional measurements; Anthony par [0009] teaches The data received from the OBD-II or other sensors may be used to train the model or as other inputs to the model. Anthony par [0036] teaches One preferred method of training is supervised learning. In one approach, a companion OBD-II reader is plugged into the car (or otherwise accessed) to read diagnostic codes in real time while a nearby device (phone or special hardware) is also collecting sensor data. The ML model makes determinations about the diagnosis of the vehicle (healthy or specific error). That determination will be compared to the OBD-II readout (or smartphone or other device sensors) to provide feedback to the machine learning process. This will either reinforce the ML model if the diagnosis was correct, or tell the ML model it was incorrect and re-classify it (ie. The training data includes data gathered from the sensors that include both audio and vibrational (dimensional) data taken from the vehicle) appropriately..)
Regarding claim 6, Anthony and Black teach,
extract inspection features of the run-time inspection input data; (Anthony par ([0075] FIG. 7 illustrates the output of a machine learning model that identifies a failure in real-time (ie. data features gathered during run-time), that is, something has happened (the engine is pinging, or the brakes are squealing) (ie. The events happening being found by the inspection classifier), and there is some relative importance, or not, of the issue (29)) determine a predicted repair classification based upon the extracted inspection features, ([0051] Thus sensors (9) might be able to detect a problem that is just starting to occur, and the app might respond by making a report or suggesting actions of an early problem detection/one that may not need immediate attention, but one that should be monitored. Thus, the system can report different levels of problems. At one level, it may report that the motor is in immediate danger of failing; but in other instances it can also determine a future maintenance need, such as an oil change is needed based on the sensed data. (ie. system predicts a type of repair based on input information).) receive user input of an adopted repair classification for the run-time inspection input data; (Anthony par [0043] teaches The diagnostic information may also be sent to a partner network of dealerships or repair facilities at (15). These partners may provide real-time price quoting for a needed repair (ie. The partners sending the chosen response provide input of adopted classification), so that the user can have a list of options to compare.)
Regarding claim 6, while Anthony and Black teach the use of at least a first AI model to predict maintenance actions for a vehicle based on sensor data, Anthony and Black do not explicitly teach,
wherein the processor is further configured to execute a repair classifier including at least a second artificial intelligence model, the repair classifier being configured to: receive run-time inspection input data including inspection-associated input data and the adopted inspection classification; … , the predicted repair classification being one of a plurality of candidate repair classifications; output the predicted repair classification; … ; and perform feedback training of the second artificial intelligence model using the inspection-associated input data and the adopted repair classification as a feedback training data pair.
However, in analogues art that leverages multiple AI agents in an effort to provide insight on maintenance actions and predicted causes of failure, Mishra teaches:
wherein the processor is further configured to execute a repair classifier including at least a second artificial intelligence model, the repair classifier being configured to: ((Page 9, Column 3) the monitoring device may provide the operating characteristics data and the detected events as input data to a first set of one or more machine learning (ML) models (ie. System contains more than one model based on needs) receive run-time inspection input data including inspection-associated input data and the adopted inspection classification; ((Page 9, Column 3) the monitoring device may provide the operating characteristics data and the detected events as input data (ie. The first model is feeding associated inspection data to the second model) to a first set of one or more machine learning (ML) models) the predicted repair classification being one of a plurality of candidate repair classifications; ((Page 9, Column 3) (ML) models that are configured to group the events into clusters based on categories, such as priorities, of the events. One such cluster may correspond to priority/worthy events (e.g., events that are associated with maintenance actions that have a significant impact on performance of the equipment asset, such as a significant likelihood to prevent occurrence of a fault). (ie. the events [classifications] is a valid choice from a set of events to choose from) output the predicted repair classification; ((Page 9, Column 4) the monitoring device may generate an output that indicates at least the one or more actions. As a particular example, the monitoring device may provide an output to a display device to cause the display device to display the one or more maintenance actions, (ie. the output is the repair classification chosen by the ML model) as well as other information.) and perform feedback training of the second artificial intelligence model using the inspection-associated input data and the adopted repair classification as a feedback training data pair. ((Page 9, Column 3) The second set of ML models may be trained using training data that is generated based on historical operating characteristics data, historical event data, statuses (e.g., insights) associated with the historical events and operating characteristics, (ie. the information of historical events [adopted actions] and the operating characteristics [input data] work as a pair in training the model) and the like.)
It would be obvious to one of ordinary skill in the art before the effective filing date of the invention to have combined Mishra’s teaching of a multi agent artificial intelligence model for use in maintenance based predictive classification and action recommendation including training data received from run-time events paired with historical data including user inputted documentation and action adoption, with Anthony and Black’s teaching of a vehicle diagnostic artificial intelligence modeled to provide the users with predictive fault detection through the utilization of multiple sources of sensor data. It would have been further obvious to this person of ordinary skill in the art to be motivated to make this combination, with reasonable chance of success, to allow each modular artificial intelligence classification agent to be granted tailored and relevant types of training data based on the required classification type, and further to decrease the time required in each iterative feedback training phase to maintain higher accuracy in the output and agent availability for new classification jobs.
Regarding claim 7, Anthony , Black and Mishra further teach,
the repair training input data including imaging studies and electrical measurements, (Anthony par [0026] teaches One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones, accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) [0087] the sensors may detect a disturbance or irregularity in some electromagnetic (EM) field. (ie. electrical measurements))
Mishra further teaches,
wherein the repair classifier has been trained on repair classifier training data including repair training input data and associated ground truth labels, ((Page 9, Column 3) The second set of ML models may be trained using training data that is generated based on historical operating characteristics data, historical event data, statuses (e.g., insights) associated with the historical events and operating characteristics, (ie. the training data includes both current and prior operating characteristics, and "historical" events [ground truth] labels) and the like.) and the ground truth labels being user inputted repair classifications associated with the repair training input data, ((Page 9, Column 3) The second set of ML models may be trained using training data that is generated based on historical operating characteristics data, historical event data, statuses (e.g., insights) associated with the historical events and operating characteristics, and the like. (ie. "historical event data" that represents user inputted ground truth labels of events)) the user inputted repair classifications being selected from the plurality of candidate repair classifications. ((Page 9, Column 3) As used herein, a status of the equipment asset may include or correspond to an operating state of the equipment asset, an issue or condition experienced by the equipment asset, a root cause associated with the condition, an impact of the condition, or a combination thereof. (ie. the conditions in combination or independently provide a plurality of classifications for repair actions))
Regarding claim 8, while Anthony, Black and Mishra teach,
the monitoring classifier being configured to: receive run-time repair input data including repair-associated input data and an adopted repair classification; (Anthony par [0051] There may be something else in (12), and that's the potential for recognizing symptoms of future problems. Thus sensors (9) might be able to detect a problem that is just starting to occur (ie. the same data being used for the repair classifier can be used to provide notice of systems in the vehicle to be monitored), and the app (ie. system running the ML model) might respond by making a report or suggesting actions of an early problem detection/one that may not need immediate attention, but one that should be monitored. Thus, the system (ie. ML model running the classifier) can report different levels of problems.) extract repair features of the run-time repair input data; (Anthony par [0087] FIG. 9 shows examples of diagnostic information that might be collected from engine (53), transmission (55), brakes (54), electrical (57) or chassis (56) sensors that include mechanical components that are moving, that are generating vibrations, or that are generating unexpected sounds, etc. In other instances, the sensors may detect a disturbance or irregularity in some electromagnetic (EM) field (ie. during run-time the electrical measurements being taken, and the invention as claimed uses this form of run-time input data to train the repair classifier). This might be caused by a warped brake rotor, failed alternator, failed ignition system, or some other failed electromagnetic component such as a failed Automatic Braking System (ABS).)
Mishra further teaches,
wherein the processor further executes a monitoring classifier including at least a third artificial intelligence model, ((Page 9, Column 3) After determining the status (e.g., insight), the monitoring device may provide the operating characteristics data, the priority events, and the status as third input data to a third set of one or more ML models (ie. at least a third ML model) that are configured to determine maintenance actions to be performed at the equipment asset.) determine a predicted monitoring classification based upon the extracted repair features, ((Page 9, Column 4) After determination of one or more maintenance actions (ie. The system determines the best prediction for an action), the monitoring device may generate an output that indicates at least the one or more actions.) the predicted monitoring classification being one of a plurality of candidate monitoring classifications; ((Page 9, Column 4) After determination of one or more maintenance actions (ie. A plurality of actions are available through the classifier), the monitoring device may generate an output that indicates at least the one or more actions.) output the predicted monitoring classification; ((Page 9, Colum 4) As a particular example, the monitoring device may provide an output to a display device (ie. Monitor classification is output) to cause the display device to display the one or more maintenance actions, as well as other information.) receive user input of an adopted monitoring classification for the runtime repair input data; ((Page 9, Colum 4) The third set of ML models may be trained using training data that is generated based on historical operating characteristics data, historical work orders (e.g., data indicative of previously performed maintenance actions), historical event data, historical insight-action relationship data, and the like. (ie. historical work orders contains user accepted classifications of events that are documented in the system)) and perform feedback training of the third artificial intelligence model using the run-time repair input data and the adopted monitoring classification as a feedback training data pair. ((Page 9, Column 4) A detailed knowledge base storing information related to operation of the equipment asset may also be generated and maintained for use in training the ML models or performing any of the described operations.(ie. Actions including training of the ML model based on feedback associated with previous and current actions)).
Regarding claim 9 Anthony, Black and Mishra further teach,
wherein the repair-associated input data include at least one of repair materials or type of repair. ((Mishra Page 15, Column 13) teaches For example, the third training data may include labelled historical status data associated with the equipment asset 150, labelled historical status data associated other equipment assets that are similar to the equipment asset 150, or a combination thereof. The labels of this labelled historical status data may indicate observed or identified maintenance actions performed to prevent or alleviate faults corresponding to the respective labelled historical status data.)
Regarding claim 10 Anthony teaches,
executing an inspection classifier using a processor and associated memory, the inspection classifier including at least a first artificial intelligence model, executing the inspection classifier including: (Anthony par [0026] FIG. 1 illustrates how sensors (1) feed signal processing elements (2) which in turn drive decisions by a machine learning (ML) model (ie. Inspection by at least a first AI model)) receiving run-time event input data from a plurality of data sources associated with a vehicle, (Anthony par [0026] One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones, accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) etc., located on or near a vehicle. (ie. a plurality of sources are being used to determine vehicle health)) the data sources including structural health monitoring sensors instrumented on the vehicle; (Anthony par [0026] The sensors can be specialized sensors integrated with the vehicle at the time of manufacture, specialized sensors installed as aftermarket components by a dealer or the consumer, or may be provided by the operators personal mobile device such as a smartphone or tablet which is located in the vehicle. (ie. data source is located on the vehicle)) extracting features of the run-time event input data; (Anthony par [0075] FIG. 7 illustrates the output of a machine learning model that identifies a failure in real-time (ie. data features gathered during run-time), that is, something has happened (the engine is pinging, or the brakes are squealing), and there is some relative importance, or not, of the issue (29)) determining a predicted inspection classification based upon the extracted features, (Anthony par [0036] In one approach, a companion OBD-II reader is plugged into the car (or otherwise accessed) to read diagnostic codes in real time while a nearby device (phone or special hardware) is also collecting sensor data. The ML model makes determinations about the diagnosis of the vehicle (ie. input data is being used to classify) (healthy or specific error)) the predicted inspection classification being one of a plurality of candidate inspection classifications; (Anthony par [0028] The filter/signal processing techniques are tailored to the specific attribute condition, symptom, or whatever it is that the system is trying to detect. A combination of filtering and signal processing methods will typically be unique for the symptom to be identified, selected during a system design phase. (ie. a plurality of outputs specialized to the type of vehicle system is in)) outputting the predicted inspection classification; (Anthony par [0043] The diagnostic information may also be sent to a partner network (ie. output inspection classified data) of dealerships or repair facilities at (15). These partners may provide real-time price quoting for a needed repair, so that the user can have a list of options to compare.)
Regarding claim 10, Anthony teaches a system that leverages AI for assisting in the diagnosis of faults and maintenance actions to be taken following the examination of data provided by sensors, Anthony does not explicitly teach,
receiving user input of an adopted inspection classification for the runtime event input data; and performing feedback training of the first artificial intelligence model using the run-time event input data and the adopted inspection classification as a feedback training data pair.
However, in analogous art that leverages similar AI systems for the use in fault detection and maintenance predicting, Mishra teaches:
receiving user input of an adopted inspection classification for the runtime event input data; (((Page 9, Column 3) The first set of ML models may be trained using training data that is generated based on historical operating characteristics data (ie. information gathered from the sensors in run-time), historical event data (ie. the historical event data has adopted actions in it that are classified in the system), ratings associated with historical events (e.g., from the knowledge base), and the like. Alternatively, the detected events and the operating characteristics data may be compared to a list of priority events from the knowledge base (ie. run-time and adopted classification used as a pair to train the model) (e.g., priority events that are identified based on input from engineers or other experts, analysis performed by the system, or a combination thereof)) and performing feedback training of the first artificial intelligence model using the run-time event input data and the adopted inspection classification as a feedback training data pair. ((Page 9, Column 3) The first set of ML models may be trained using training data that is generated based on historical operating characteristics data (ie. information gathered from the sensors in run-time), historical event data (ie. the historical event data has adopted actions in it that are classified in the system), ratings associated with historical events (e.g., from the knowledge base), and the like. Alternatively, the detected events and the operating characteristics data may be compared to a list of priority events from the knowledge base (ie. run-time and adopted classification used as a pair to train the model) (e.g., priority events that are identified based on input from engineers or other experts, analysis performed by the system, or a combination thereof)
It would be obvious to one of ordinary skill in the art before the effective filing date of the invention to have combined Mishra’s teaching of a multi agent artificial intelligence model for use in maintenance based predictive classification and action recommendation including training data received from run-time events paired with historical data including user inputted documentation and action adoption, with Anthony’s teaching of a vehicle diagnostic artificial intelligence modeled to provide the users with predictive fault detection through the utilization of multiple sources of sensor data, it would have been further obvious to this person of ordinary skill in the art to be motivated to make this combination, with reasonable chance of success, to allow each modular artificial intelligence classification agent to be granted tailored and relevant types of training data based on the required classification type, and further to decrease the time required in each iterative feedback training phase to maintain higher accuracy in the output and agent availability for new classification jobs.
Anthony and Mishra do not teach wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer.
However, Black teaches wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer.(Black par [0044] teaches the Structural Health Monitoring is conducted via strain gauges or strain sensors mounted on aircraft structure)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Anthony, Mishra and Black to achieve the claimed invention . One would have been motivated to make such combination to mitigate incorrect forces to extend the life of structures and/or critical components.(Black par [0016])
Regarding claim 11 they comprise limitations similar to those of claim 2, and are therefore rejected for similar rationale. Regarding claim 12 comprises limitations similar to claim 3, and therefore is rejected for similar rationale. Similarly claim 14 comprises limitations similar to claim 6, and therefore is rejected for similar rationale. Regarding claim 15 they comprise limitations similar to claim 7, and therefore is rejected for similar rationale. Similarly claim 16 comprises limitations similar to claim 8, and therefore is rejected for similar rationale. Regarding claim 17 they comprise limitations similar to claim 9, and therefore is rejected for similar rationale.
Regarding claim 18, Anthony, Mishra and Black teach,
the monitoring training input data including imaging studies and electrical measurements, (Anthony[0026] One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones, accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) [0087] the sensors may detect a disturbance or irregularity in some electromagnetic (EM) field. (ie. electrical measurements and imaging studies))
Mishra teaches:
prior to executing the monitoring classifier, training the monitoring classifier on monitoring training data including monitoring training input data and associated ground truth labels, ((Page 9, Column 4) The third set of ML models (ie. the monitoring classifier) may be trained using training data that is generated based on historical operating characteristics data, historical work orders (e.g., data indicative of previously performed maintenance actions), historical event data, historical insight-action relationship data, (ie. as discussed prior where a maintenance action can include monitoring and associated historical data provides ground truth data based on user input) and the like.) and the ground truth labels being user inputted repair classifications associated with inspection training input data, ((Page 9, Column 3) The second set of ML models may be trained using training data that is generated based on historical operating characteristics data, historical event data, statuses (e.g., insights) associated with the historical events and operating characteristics, and the like. (ie. "historical event data" that represents user inputted ground truth labels of events)) the user inputted repair classifications being selected from the plurality of candidate repair classifications. ((Page 9, Column 3) As used herein, a status of the equipment asset may include or correspond to an operating state of the equipment asset, an issue or condition experienced by the equipment asset, a root cause associated with the condition, an impact of the condition, or a combination thereof. (ie. the conditions in combination or independently provide a plurality of classifications for repair actions))
Regarding claim 21, Anthony, Mishra and Black teach wherein the run-time event input data further includes at least one of camera images, audio data, or dimensional measurements.(Anthony par ([0026] One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones (ie. at least one of camera images, audio data, or dimensional measurements), accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) etc., located on or near a vehicle.)
Regarding claim 22, Anthony, Mishra and Black teach wherein the run-time event input data further includes at least one of camera images, audio data, or dimensional measurements. (Anthony par ([0026] One or more sensors (1), also called “listening devices” herein, may include audio, vibration, electromagnetic, or other sensors such as microphones (ie. at least one of camera images, audio data, or dimensional measurements), accelerometers, gyroscopes, magnetometers, vibration detectors, piezoelectronics, Micro Electrical Mechanical Systems (MEMS) devices, Inertial Measurement Units (IMU) etc., located on or near a vehicle.)
5. Claims 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Mishra and further in view of Black.
Regarding claim 19 Mishra teaches,
A maintenance computing system comprising: a processor and a non-volatile memory storing executable instructions that, in response to execution by the processor, cause the processor to ((Page 8, Column 2) The present application discloses systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning techniques to analyze and categorize events associated with an equipment asset, such as industrial machinery, to recommend a status of the equipment asset based on the events, and to determine and recommend maintenance actions (Page 10, Colum 5) In a particular aspect, a method for event categorization and maintenance action recommendation using machine learning includes receiving, by one or more processors, operating characteristics data associated with industrial machinery and event data indicating events detected based on the operating characteristics data. (ie. The maintenance computing system contains the claimed basic computing components in its structure to accomplish its maintenance computing tasks) The method also includes identifying, by the one or more processors, one or more priority events associated with the industrial machinery) execute an inspection classifier configured to determine a predicted inspection classification based on run-time event input data from structural health monitoring sensors instrumented on a vehicle; ((Page 9, Column 3) In one aspect a monitoring device (e.g., a control panel, a server, a user device, or the like) may receive operating characteristics data from sensors configured to monitor an equipment asset. In other implementations, the equipment asset 150 may include or correspond to equipment or devices used in other industries or businesses, such as telecommunication equipment (e.g., routers, gateways, base stations, servers, network nodes, and the like), information services equipment (e.g., servers, databases, storage devices, and the like), power equipment (e.g., generators, transformers, power lines, regulators, and the like), vehicles (e.g., cars, trucks, military vehicles, watercraft, aircraft, spacecraft, drones, farming vehicles, trains, and the like) (ie. Vehicles are included in the context of the equipment asset described), or another type of equipment that is monitored for performance in real-time. (ie. sensors provide information to the model being executed) The monitoring device may detect events based on the operating characteristics data, and the monitoring device may provide the operating characteristics data and the detected events as input data to a first set of one or more machine learning (ML) models that are configured to group the events into clusters based on categories (ie. run-time input data from sensors used to make classifications)) output the predicted inspection classification; ((Page 17, Column 19) 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, revisiting an operating envelope associated with equipment asset 150, inspecting, repairing, or replacing peripheral systems of the equipment asset 150, or the like. The recommendation engine 132 may output indications of the maintenance actions (ie. model outputs inspection action [inspection classification]) 116.) receiving user input of an adopted inspection classification for the run-time event input data; ((Page 23, Column 31) The method 300 also includes receiving user input (ie. receiving user input), at 328. For example, a user may provide feedback regarding the performance of the ML models, such as whether a determined status/insight is affirmed or rejected (ie. input includes if the adopted status/insight [classification] is adopted), additional information related to performance of the maintenance actions, observations of performance of the equipment asset, etc.) performing feedback training of the inspection classifier using the run-time event input data and the adopted inspection classification as a feedback training data pair; ((Page 23, Column 31) The method 300 also includes receiving user input, at 328. For example, a user may provide feedback regarding the performance of the ML models, such as whether a determined status/insight is affirmed or rejected, additional information related to performance of the maintenance actions, observations of performance of the equipment asset, etc. In some implementations, output of the performance monitoring, at 326, the user input received at 328, or a combination thereof, may be provided as feedback data for use in maintaining the knowledge base (ie. The ML models as described prior utilizing runtime input data for inspection and user input present for use in model training), at 304. For example, the knowledge base may be updated based on the feedback data, and the ML models may be further trained based on the feedback data (ie. above data is used in feedback training).) execute a repair classifier to determine a predicted repair classification based upon run-time inspection input data including inspection-associated input data and the adopted inspection classification; ((Page 18, Column 21) In some implementations, these maintenance actions may be displayed to the user for acceptance by the user, and the maintenance actions may be initiated or performed by the monitoring device 102 based on user input indicating that the maintenance actions are accepted. (Detailed Description 37) As described above, the system 100 provides an automated system for monitoring operating characteristics (ie. classification) and other real-time data provided by the equipment asset 150 and the sensors 152 to identify the priority events 112, determine the status 114 associated with the priority events 112, and determine the maintenance actions 116 to be performed at the equipment asset (ie. to execute a repair classified action) 150 to prevent (or reduce a severity of) a fault at the equipment asset 150) output the predicted repair classification; ((Page 1, 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) (ie. the maintenance actions being the models predicted repair classification based on the category of need). Output that indicates the maintenance actions may be displayed to a user (ie. information is output) or used to automatically initiate performance of one or more of the maintenance actions.) receive user input of an adopted repair classification for the run-time inspection input data; ((Page 23, Column 31) The method 300 also includes receiving user input (ie. receiving user input), at 328. For example, a user may provide feedback regarding the performance of the ML models, such as whether a determined status/insight is affirmed or rejected, additional information related to performance of the maintenance actions (ie. affirmation or rejection of adopted classification of a model), observations of performance of the equipment asset, etc.) and perform feedback training of the repair classifier using the run-time inspection input data and the adopted repair classification as a feedback training data pair. ((Page 23, Column 31) The method 300 also includes receiving user input, at 328. For example, a user may provide feedback regarding the performance of the ML models, such as whether a determined status/insight is affirmed or rejected, additional information related to performance of the maintenance actions, observations of performance of the equipment asset, etc. In some implementations, output of the performance monitoring, at 326, the user input received at 328, or a combination thereof, may be provided as feedback data for use in maintaining the knowledge base (ie. The ML models as described prior utilizing runtime input data for repair actions and user input [related to adoption of action] present for use in model training), at 304. For example, the knowledge base may be updated based on the feedback data, and the ML models may be further trained based on the feedback data (ie. above data is used in feedback training).)
Mishra fails to expressly teach wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer.
However, Black teaches wherein the one or more structural health monitoring sensors include a strain gauge and/or a displacement transducer.(Black par [0044] teaches the Structural Health Monitoring is conducted via strain gauges or strain sensors mounted on aircraft structure)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Mishra and Black to achieve the claimed invention . One would have been motivated to make such combination to mitigate incorrect forces to extend the life of structures and/or critical components.(Black par [0016])
Regarding claim 20 Mishra and Black further teach,
execute a monitoring classifier to determine a predicted monitoring classification based upon run-time repair input data including repair-associated input data and the adopted repair classification; ((Mishra Page 9, Column 3) In one aspect a monitoring device (e.g., a control panel, a server, a user device, or the like) may receive operating characteristics data from sensors configured to monitor an equipment asset. (ie. sensors provide information to the model being executed) The monitoring device may detect events based on the operating characteristics data, and the monitoring device may provide the operating characteristics data and the detected events as input data to a first set of one or more machine learning (ML) models that are configured to group the events into clusters based on categories (ie. run-time input data from sensors used to make classifications).) output the predicted monitoring classification; ((Mishra Page 23, Column 31) In some implementations, output of the performance monitoring, at 326 (ie. the model outputs information predicted for monitoring the system), the user input received at 328, or a combination thereof, may be provided as feedback data for use in maintaining the knowledge base, at 304. For example, the knowledge base may be updated based on the feedback data, and the ML models may be further trained based on the feedback data. (Detailed Description 63) As described above, the method 300 maintains a knowledge base, trains ML models, and deploys ML models for generating recommendations associated with monitoring the equipment asset (ie. one of the deployed models in the system performs the job of monitoring continuously).) receive user input of an adopted monitoring classification for the run-time repair input data; ((Mishra Page 23, Column 31) The method 300 also includes receiving user input (ie. receiving user input), at 328. For example, a user may provide feedback regarding the performance of the ML models, such as whether a determined status/insight is affirmed or rejected, additional information related to performance of the maintenance actions (ie. affirmation or rejection of adopted classification of a model), observations of performance of the equipment asset, etc.) and perform feedback training of the monitoring classifier using the run-time repair input data and the adopted monitoring classification as a feedback training data pair. ((Mishra Page 23, Column 31) The method 300 also includes receiving user input, at 328. For example, a user may provide feedback regarding the performance of the ML models, such as whether a determined status/insight is affirmed or rejected, additional information related to performance of the maintenance actions, observations of performance of the equipment asset, etc. In some implementations, output of the performance monitoring, at 326, the user input received at 328, or a combination thereof, may be provided as feedback data for use in maintaining the knowledge base (ie. The ML model utilizes a knowledge base that is grounded in historical data provided by user inputted feedback, this information is then used for training), at 304. For example, the knowledge base may be updated based on the feedback data, and the ML models may be further trained based on the feedback data (ie. above data is used in feedback training).)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Mahipal et al., US Patent Application Publication 2022/0067667 A1 , par [0007] discloses methods for predictive maintenance of a component of a vehicle. Hinduja et al., US Patent Application Publication 2022/0068053 A1, discloses a predictive maintenance method for determining a health status of a vehicle system (Hinduja’s abstract). Hinduja par [0075] discloses the classifier may determine whether the vehicular system is healthy or not such as requires any repairs or replacements.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HIEN DUONG whose telephone number is (571)270-7335. The examiner can normally be reached Monday-Friday 8:00AM-5:00PM.
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, Viker Lamardo can be reached at 571-270-5871. 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.
/HIEN L DUONG/Primary Examiner, Art Unit 2147
Prosecution Insights