DETAILED ACTION
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 .
Priority
Application 18/083,583 filed on 12/19/2022 claims priority to TAIWAN 111139137 filed on 10/14/2022.
Response to Amendment
This office action is in response to amendments filed on 12/19/2025 wherein claims 1-2, 6-12, 14, and 16-20 are pending and have been considered below. Claims 3-5, 13, and 15 have been canceled.
Information Disclosure Statement
The information disclosure statement filed 09/25/2023 fails to comply with 37 CFR 1.98(a)(3)(i) because it does not include a concise explanation of the relevance, as it is presently understood by the individual designated in 37 CFR 1.56(c) most knowledgeable about the content of the information, of each reference listed that is not in the English language. It has been placed in the application file, but the information referred to therein has not been considered. Non-Patent Literature Documents “Office Action of Taiwan Counterpart Application” has not been considered as it is in a foreign language. Examiner respectfully requests a copy of “Office Action of Taiwan Counterpart Application” in the English language.
Claim Objections
Claims 11-12, 14, 16-20 are objected to because of the following informalities:
Regarding independent claims 11 and 20: Applicant uses the phrase “initial a display” (claim 11) and “initialing a display” (claim 20). Examiner believes this is a typographical error and these phrases should read “initiate a display” and “initiating a display.” However, Applicant could intend something different. Appropriate correction is required.
Regarding claims 12, 14, and 16-19: Claims 12, 14, and 16-19 are also objected to as they depend from the independent claims.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-2, 6-12, 14, and 16-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite an abstract idea as discussed below. This abstract idea is not integrated into a practical application for the reasons discussed below. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception for the reasons discussed below.
Step 1 of the 2019 Guidance requires the examiner to determine if the claims are to one of the statutory categories of invention. Applied to the present application, the claims belong to one of the statutory classes of a process or product as a computer implemented method or a computer system/product.
Step 2A of the 2019 Guidance is divided into two Prongs. Prong 1 requires the examiner to determine if the claims recite an abstract idea, and further requires that the abstract idea belong to one of three enumerated groupings: mathematical concepts, mental processes, and certain methods of organizing human activity.
Claim 1 is copied below, with the limitations belonging to an abstract idea being underlined.
A method for suggesting equipment maintenance comprising:
obtaining equipment operation information of equipment measured by at least one sensor;
determining energy efficiency of the equipment according to the equipment operation information;
generating status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition;
determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input; and
initiating a display indicating suggestion information of the at least one maintenance item
wherein generating the status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting the maintenance condition comprises:
obtaining a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval;
calculating a statistic of the first equipment characteristic quantities;
obtaining a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval:
calculating a statistic of the second equipment characteristic quantities;
generating a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities: and generating a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities,
wherein determining at least one maintenance item corresponding to the equipment comprises:
selecting at least one target characteristic category from the at least one characteristic category according to the difference inspection value;
inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items; and
determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model.
Claim 11 is copied below, with the limitations belonging to an abstract idea being underlined.
An electronic device comprising:
a display;
a storage circuit storing a plurality of instructions;
a processor coupled to the display and the storage circuit, and accessing the instructions to:
obtain equipment operation information of equipment measured by at least one sensor;
determine energy efficiency of the equipment according to the equipment operation information;
obtain a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval:
calculate a statistic of the first equipment characteristic quantities;
obtain a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval:
calculate a statistic of the second equipment characteristic quantities;
generate status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition;
generate a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities;
generate a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities;
select at least one target characteristic category from the at least one characteristic category according to the difference inspection value:
input the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items;
determine at least one maintenance item according to the first predicted probabilities output by the first machine learning model:
and initial a display indicating suggestion information of the at least one maintenance item in response to determining the at least one maintenance item.
Claim 20 is copied below, with the limitations belonging to an abstract idea being underlined.
A computer readable recording medium storing a program, in response to a computer loading the program,
obtaining equipment operation information of equipment measured by at least one sensor; determining energy efficiency of the equipment according to the equipment operation information;
generating the status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition; determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input; and
providing initialing a display indicating suggestion information of the at least one maintenance item through a display in response to determining the at least one maintenance item,
wherein generating the status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting the maintenance condition comprises:
obtaining a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval;
calculating a statistic of the first equipment characteristic quantities;
obtaining a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval;
calculating a statistic of the second equipment characteristic quantities;
generating a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities; and
generating a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities,
wherein determining at least one maintenance item corresponding to the equipment comprises:
selecting at least one target characteristic category from the at least one characteristic category according to the difference inspection value;
inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items; and
determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model.
The limitations underlined can be considered to describe a series of mental and/or mathematical concepts where “determine/determining” and “generate/generating” may include a series of calculations leading to one or more numerical results or answers, obtained by a sequence of mathematical operations on numbers or may include an observation, evaluation, judgement, and/or opinion which are concepts performed in the human mind. The lack of a specific equation in the claim merely points out that the claim would monopolize all possible appropriate equations/two-group significance tests for accomplishing this purpose in all possible systems. These steps recited by the claim therefore amount to a series of mental and/or mathematical steps, making these limitations amount to an abstract idea.
In summary, the highlighted steps in the claim above therefore recite an abstract idea at Prong 1 of the 101 analysis.
The additional elements in the claim have been left in normal font.
The additional concepts of “obtain/obtaining” “input/inputting,” “output/outputting” and “provide/providing” equates to extra solution data activity (See MPEP 2106.05(g)).
The additional limitations in relation to the computer, computer product, or computer system does not offer a meaningful limitation beyond generally linking the use of the method to a computer (see Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 217, 110 USPQ2d 1976, 1981 (2014)). The claim does not recite a particular machine applying or being used by the abstract idea.
The claims do not integrate the abstract idea into a practical application. Various considerations are used to determine whether the additional elements are sufficient to integrate the abstract idea into a practical application. The claim does not recite a particular machine applying or being used by the abstract idea. The claim does not effect a real-world transformation or reduction of any particular article to a different state or thing. (Manipulating data from one form to another or obtaining a mathematical answer using input data does not qualify as a transformation in the sense of Prong 2.)
The claims do not contain additional elements which describe the functioning of a computer, or which describe a particular technology or technical field, being improved by the use of the abstract idea. (This is understood in the sense of the claimed invention from Diamond v Diehr, in which the claim as a whole recited a complete rubber-curing process including a rubber-molding press, a timer, a temperature sensor adjacent the mold cavity, and the steps of closing and opening the press, in which the recited use of a mathematical calculation served to improve that particular technology by providing a better estimate of the time when curing was complete. Here, the claim does not recite carrying out any comparable particular technological process.) In all of these respects, the claim fails to recite additional elements which might possibly integrate the claim into a particular practical application. Instead, based on the above considerations, the claim would tend to monopolize the abstract idea itself, rather than integrate the abstract idea into a practical application.
Step 2b of the 2019 Guidance requires the examiner to determine whether the additional elements cause the claim to amount to significantly more than the abstract idea itself. The considerations for this particular claim are essentially the same as the considerations for Prong 2 of Step 2a, and the same analysis leads to the conclusion that the claim does not amount to significantly more than the abstract idea.
Therefore, claims 1, 11, and 20 are rejected under 35 U.S.C. 101 as directed to an abstract idea without significantly more.
Dependent claims 2-10 and 12-19 are similarly ineligible. The dependent claims merely add limitations which further detail the abstract idea with limitations such as “obtains/obtaining” “determines/determining,” “compares/comparing” “generates/generating” “calculates/calculating” “selects/selecting” and “inputs/inputting” do not help to integrate the claim into a practical application or make it significant more than the abstract idea (which is recited in slightly more detail, but not in enough detail to be considered to narrow the claim to a particular practical application itself). Considering all the limitations individually and in combination, the claimed additional elements do not show any inventive concept to applying algorithms such as improving the performance of a computer or any technology, and do not meaningfully limit the performance of the application.
Additionally, claim 20 is rejected under 35 USC § 101 because the claimed invention is directed to non-statutory subject matter. The claims are drawn to a "A computer readable recording medium storing a program". The broadest reasonable interpretation of a claim drawn to a computer readable medium covers forms of non-transitory tangible media and transitory propagating signals per se in view of the ordinary and customary meaning of computer readable media, particularly when the specification is silent (see MPEP 2111.01). Because the broadest reasonable interpretation covers a signal per se, a rejection under 35 USC 101 is appropriate as covering non-statutory subject matter. See 351 OG 212, Feb 23, 2010.
The Examiner respectfully suggests that Applicant amends the claims as follows: "non-transitory computer readable medium containing computer instructions stored therein for causing a computer processor to perform".
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 1-2, 6-7, 11-12, 14, 16-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yaacov et al., hereinafter Yaacov, U.S. Pub. No. 2020/0250109 A1 in view of Rollins et al., hereinafter Rollins, U.S. Pub. No. 2022/0261021 A1 in view of Burke et. al., U.S. Pub. No. 2022/0156275 A1.
Regarding Independent claim 1 Yaacov teaches:
“A method for suggesting equipment maintenance” (Yaacov, ¶ 0019).
“comprising: obtaining equipment operation information of equipment measured by at least one sensor; determining energy efficiency of the equipment according to the equipment operation information” (Yaacov, fig. 6, fig. 11, ¶ 0089-¶ 0099: Yaacov teaches “monitoring and measuring peripheral machines through external sensors thereby understanding the efficiency of the peripheral machines” (¶ 0090,) “predicting maintenance of peripheral machines by connecting to a peripheral machine and connecting to a general system of a manufacturing facility to learn a real-time production line needs” (¶ 0091) and “examining and calculating the efficiency of every connected machine and a total efficiency of the production line” (¶ 0094).)
“determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model” (Yaacov, ¶ 0010, ¶ 0019: Yaacov teaches using machine learning trained by sensor data to monitor machines (¶ 0010) where the “trained model serves as a basis for a control system” (¶ 0011) where the control system performs “anomaly detection, and predictive maintenance (e.g. when actual performance diverges from the model’s predictions)” (¶ 0019).
Yaacov does not teach:
“generating status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition;
determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input”
Rollins teaches:
“generating status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition; determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input” (Rollins, fig. 3, ¶ 0258: Rollins teaches processing the “actual real-time performance and environment data and then correlates such data to the stored historical data and the data representing the operational characteristics of subsystems and components (where “correlates” discloses generating status difference data of the equipment where the “data” discloses equipment operation information) in order to” among other things, determine system efficiency and perform proactive and predictive maintenance events (¶ 0258) disclosing the “energy efficiency” meets a “maintenance condition.” Moreover, “the present invention predicts design fan speed from the tower performance curve and the fan map and then compares the design fan speed to operating performances” disclosing “status difference data” and “the operating of the fan 12 at higher speeds may trigger an inspection” (¶ 0258) disclosing “a maintenance item,” an “inspection,” is determined due to “status difference data.”)
Yaacov teaches a “proactive engine unit for operation optimizing and predicting the maintenance of peripheral machines” (¶ 0071) using “all available data and information relevant to the situation of the peripheral machines” (¶ 0260). Moreover, the “proactive engine unit” contains a “modeler” which includes but is not limited to a “rule-based, thermo-dynamic, and artificial intelligence” type of model (¶ 0263). Therefore the combination of Yaacov and Rollins discloses the limitation “determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input”
Rollins teaches:
“initiating a display indicating suggestion information of the at least one maintenance item through a display in response to determining the at last on maintenance item” (Rollins, fig. 2, ¶ 0202: Rollins teaches “Industrial computer 300 will trend the data and make a decision as to whether to display a notice on display 306 that notifies the operators that an inspection (maintenance item) of the cooling tower is necessary” (¶ 0202).)
Both Yaacov and Rollins teach maintaining machinery therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility by predicting and alerting the system that maintenance is required as taught by Yaacov by including the method of using the energy efficiency and a status difference to determine maintenance items as taught by Rollins as analyzing an asset’s energy consumption enables maintenance workers to identify potential problems and provide timely repairs avoiding costly unplanned downtime in order to provide a system that “provides recommendations, insights and proactive actions to improve efficiency based on the analysis” (Rollins, ¶ 0267.)
wherein generating the status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting the maintenance condition (see above) comprises:
Yaacov does not teach:
“obtaining a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval;
calculating a statistic of the first equipment characteristic quantities;
obtaining a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval:
calculating a statistic of the second equipment characteristic quantities; generating a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities
generating a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities”
Rollins teaches:
“obtaining a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval; obtaining a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval: generating a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities” (Rollins, fig. 2, ¶ 0258-¶ 0259: Rollins teaches “Industrial computer 300 process the actual real-time (current time interval) performance and environmental data and then correlates such data (second equipment characteristic quantities) to the stored historical data (first equipment characteristic quantities which are of a reference time interval) and the data representing the operational characteristics of subsystems and components” (¶ 0258) in order to “determine deviation from previous trends and design curves (disclosing the first equipment characteristic quantities) and related operating tolerance band” (disclosing second equipment characteristic quantities (¶ 0259)) (¶ 0258) where “deviation” discloses a “difference inspection value.”)
Both Yaacov and Rollins teach maintaining machinery therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov by including the method of comparing equipment characteristic quantities of a current time frame and a reference time frame as disclosed by Rollins to help identify causes of inefficiencies in order to provide a system that “provides recommendations, insights and proactive actions to improve efficiency based on the analysis” (Rollins, ¶ 0267.)
Burke teaches:
“calculating a statistic of the first equipment characteristic quantities; calculating a statistic of the second equipment characteristic quantities; and generating a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities” (Burke, fig. 1, ¶ 0013, ¶ 0060-0062: Burke teaches “the method 100 comprises time-stamping a performance statistic computed using an interval window and placing the time-stamped performance statistic into storage” thereby allowing “a real-time performance statistic computed using an instantaneous window (calculated statistic of the second equipment characteristic quantities) to be easily and directly compared to the same performance static computed using an interval window at any period or point in time previously (calculated statistic of the first equipment characteristic quantities) (¶ 0060) and the comparison “may enable easier extraction of practical insights from the real-time and historical data analytics” (¶ 0013) therefore Burke discloses “generating a difference rate” by comparing the computed statistics.
Both Yaacov and Burke us data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including the data analysis method of comparing computed statistics of real-time and a previous time frame as disclosed by Burke to help identify causes of inefficiencies in order to provide a system where using “only events relevant or necessary for computing a statistic to be taken into account” where “Irrelevant or unnecessary events can be ignored, improving efficiency” (Burke, ¶ 0027).
Yaacov teaches:
“wherein determining at least one maintenance item corresponding to the equipment” (Yaacov, ¶ 0071, ¶ 0260-¶ 0263: Yaacov teaches “proactive engine unit for operation optimizing and predicting the maintenance of peripheral machines” (¶ 0071) using “all available data and information relevant to the situation of the peripheral machines” (¶ 0260). Moreover, the “proactive engine unit” contains a “modeler” which includes but is not limited to a “rule-based, thermo-dynamic, and artificial intelligence” type of model (¶ 0263). disclosing “determining at least one maintenance item corresponding to the equipment”
Yaacov does not teach:
selecting at least one target characteristic category from the at least one characteristic category according to the difference inspection value;
inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items;
Burke teaches:
“selecting at least one target characteristic category from the at least one characteristic category according to the difference inspection value; inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to a first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of” predictions (Burke, fig. 4, ¶ 0127: Fig. 4 depicts “computing one or more performance statistics” (350) disclosing “at least one characteristic category” where the “real-time data analytics and historical data analytics computed at step 350 are directly comparable” (¶ 0127) disclosing “second” and “first equipment characteristic quantities” which are “comparable” disclosing a comparison, and “providing the one or more statistics computed over a predetermined duration of time to the machine learning model as training data: and providing the one or more statistics computed at an instantaneous point in time to the machine learning model as real data to generate the one or more predicted statistics” (claim 12) disclosing the input of “at least one characteristic category” into a machine learning model which outputs “predicted statistics.”)
Both Yaacov and Burke us data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including the data analysis method of comparing computed statistics of real-time and a previous time frame as disclosed by Burke to help identify causes of inefficiencies in order to provide a system where using “only events relevant or necessary for computing a statistic to be taken into account” where “Irrelevant or unnecessary events can be ignored, improving efficiency” (Burke, ¶ 0027).
Yaacov teaches the machine learning is used to determine “maintenance items” (see above.)
Regarding claim 2 Yaacov as modified teaches:
“determining the energy efficiency of the equipment according to the equipment operation information” (see claim 1 above.)
“obtaining at least one production data of the equipment; and determining the energy efficiency according to a ratio of the at least one production data to electricity consumption of the equipment” (Yaacov, ¶ 0265: Yaacov teaches measurement data includes “Energy output of each individual monitored machine” disclosing “production data of the equipment.” Moreover, “Monitored machine efficiency (Output/Energy that was used to generated (sic) this output)” (¶ 0265).)
“wherein the method further comprises: obtaining an energy efficiency measurement indicator by comparing the energy efficiency with predetermined energy efficiency” (Yaacov, ¶ 0199: Yaacov teaches “the benchmark may be that the deviation between the energy efficiency predicted by system (predetermined energy efficiency) as compared to actual value (energy efficiency) in the last 24 hours . . .” (¶ 0199) where “the deviation” discloses the energy efficiencies are being compared.)
“comparing the energy efficiency measurement indicator with a measurement threshold; and determining whether the energy efficiency meets the maintenance condition” (Yaacov, ¶ 0286-¶ 0287: Yaacov teaches “In the cases of big changes (energy efficiency measurement indicator) in efficiency (e.g. as compared to a pre-defined level,), total efficiency examiner 1102 triggers operation plan modeler 1106 to re-evaluate the operation plan (e.g. turn off a machine that has low efficiency and activate a machine with higher efficiency instead)(maintenance condition)” (¶ 0286).)
Regarding claim 6 Yaacov as modified teaches:
“obtaining a textual abnormality description of the equipment; and inputting the textual abnormality description to a second machine learning model, the second machine learning model outputting a plurality of second predicted probabilities corresponding to the predetermined maintenance items” (Yaacov, ¶ 0010-¶ 0011, ¶ 0019, ¶ 0151-¶ 0152,
¶ 0155: Yaacov teaches “sensors measure metric values and provide these values to the control system during both training and regular operation” (¶ 0152) where different types of metrics include “Demand output metric – a metric that is used as a system goal or to calculate a system goal. For example, a volume sensor on a pipe leading to the manufacturing machines may be used as demand output metric to calculate the system goal of maximizing volume” (¶ 0155) disclosing a “textual” data which is sensor data and is used by the machine learning model to train and monitor machines (¶ 0010) where the “trained model serves as a basis for a control system” (¶ 0011) where the control system performs “anomaly detection, and predictive maintenance (e.g. when actual performance diverges from the model’s predictions)” (¶ 0019).
“wherein determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model (see claim 5 above) comprises”:
“determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model and the second predicted probabilities output by the second machine learning model” (Yaacov teaches “examining and calculating the efficiency of every connected machine” (¶ 0094) and “Demand output metric – a metric that is used as a system goal or to calculate a system goal. For example, a volume sensor on a pipe leading to the manufacturing machines may be used as demand output metric to calculate the system goal of maximizing volume” (¶ 0155) where both data with respect to “every connected machine” and data with respect to “a system goal” are used to determine “at least one maintenance item” where the different types of data are used to determine different types of probability outputs by the machine learning model to train and monitor machines (¶ 0010) where the “trained model serves as a basis for a control system” (¶ 0011) and where the control system performs “anomaly detection, and predictive maintenance (e.g. when actual performance diverges from the model’s predictions (predicted probabilities))” (¶ 0019).)
Regarding claim 7 Yaacov as modified teaches:
“inputting the first predicted probabilities and the second predicted probabilities to a third machine learning model, the third machine learning model outputting a plurality of third predicted probabilities corresponding to the predetermined maintenance items; and selecting the at least one maintenance item from the predetermined maintenance items according to the third predicted probabilities of the predetermined maintenance items.” (Yaacov, ¶ 0256-¶ 0265: Yaacov teaches the control system includes two main interconnected units, a monitoring unit and a proactive engine unit” (¶ 0256) where the “proactive engine unit performs operation optimization (and optionally predictive maintenance) of the peripheral machines” (¶ 0260). The “proactive engine contains two main components, a plan processor and a modeler” (¶ 0262) where “the types of models include but are not limited to” rule-based thermo-dynamic and artificial intelligence (AI)” (¶ 0263). The “monitoring unit uses the smart devices to measure through external sensors all the required input for the system to calculating the efficiency of the machines, to optimize the operation plane of the machines and to predict the maintenance of demand-side equipment” (¶ 0265) disclosing “third predicted probabilities,” where the types of data include “Monitored machines workload, hours, and various operational and maintenance data” (¶ 0265) where “maintenance data” discloses “first” and “second predicted probabilities.”)
Regarding Independent claim 11 Yaacov teaches:
An electronic device comprising: a display; a storage circuit storing a plurality of instructions; a processor coupled to the display and the storage circuit (Yaacov, ¶ 0107).
accessing the instructions to: obtain equipment operation information of equipment measured by at least one sensor; determine energy efficiency of the equipment according to the equipment operation information; (Yaacov, fig. 6, fig. 11, ¶ 0089-¶ 0099: Yaacov teaches “monitoring and measuring peripheral machines through external sensors thereby understanding the efficiency of the peripheral machines” (¶ 0090,) “predicting maintenance of peripheral machines by connecting to a peripheral machine and connecting to a general system of a manufacturing facility to learn a real-time production line needs” (¶ 0091) and “examining and calculating the efficiency of every connected machine and a total efficiency of the production line” (¶ 0094).)
“determine the at least one maintenance item according to the first predicted probabilities output by the first machine learning model” (Yaacov, ¶ 0010, ¶ 0019: Yaacov teaches using machine learning trained by sensor data to monitor machines (¶ 0010) where the “trained model serves as a basis for a control system” (¶ 0011) where the control system performs “anomaly detection, and predictive maintenance (e.g. when actual performance diverges from the model’s predictions)” (¶ 0019).
Yaacov does not teach:
“obtain a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval:
calculate a statistic of the first equipment characteristic quantities;
obtain a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval:
calculate a statistic of the second equipment characteristic quantities;
generate status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition;
generate a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities;
generate a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities;
select at least one target characteristic category from the at least one characteristic category according to the difference inspection value:
input the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items;
initial a display indicating suggestion information of the at least one maintenance item in response to determining the at least one maintenance item.”
Rollins teaches:
“obtain a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval: obtain a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval” (Rollins, fig. 2, ¶ 0258-¶ 0259: Rollins teaches “Industrial computer 300 process the actual real-time (current time interval) performance and environmental data and then correlates such data (second equipment characteristic quantities) to the stored historical data (first equipment characteristic quantities which are of a reference time interval) and the data representing the operational characteristics of subsystems and components” (¶ 0258) in order to “determine deviation from previous trends and design curves (disclosing the first equipment characteristic quantities) and related operating tolerance band” (disclosing second equipment characteristic quantities (¶ 0258).)
“generate status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition” (Rollins, fig. 3, ¶ 0258: Rollins teaches processing the “actual real-time performance and environment data and then correlates such data to the stored historical data and the data representing the operational characteristics of subsystems and components (where “correlates” discloses generating status difference data of the equipment where the “data” discloses equipment operation information) in order to” among other things, determine system efficiency and perform proactive and predictive maintenance events (¶ 0258) disclosing the “energy efficiency” meets a “maintenance condition.” Moreover, “the present invention predicts design fan speed from the tower performance curve and the fan map and then compares the design fan speed to operating performances” disclosing “status difference data” and “the operating of the fan 12 at higher speeds may trigger an inspection” (¶ 0258) disclosing “a maintenance item,” an “inspection,” is determined due to “status difference data.”)
“generate a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities” (Rollins, ¶ 0258-¶ 0259: Rollins teaches “determine deviation from previous trends and design curves (disclosing the first equipment characteristic quantities) and related operating tolerance band” (disclosing second equipment characteristic quantities (¶ 0258) where “deviation” discloses a “difference inspection value.”)
initial a display indicating suggestion information of the at least one maintenance item in response to determining the at least one maintenance item.” (Rollins, fig. 2, ¶ 0202: Rollins teaches “Industrial computer 300 will trend the data and make a decision as to whether to display a notice on display 306 that notifies the operators that an inspection (maintenance item) of the cooling tower is necessary” (¶ 0202).)
Both Yaacov and Rollins teach maintaining machinery therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility by predicting and alerting the system that maintenance is required as taught by Yaacov by including the method of using the energy efficiency and a status difference to determine maintenance items as taught by Rollins as analyzing an asset’s energy consumption enables maintenance workers to identify potential problems and provide timely repairs avoiding costly unplanned downtime in order to provide a system that “provides recommendations, insights and proactive actions to improve efficiency based on the analysis” (Rollins, ¶ 0267.)
Burke teaches:
“calculate a statistic of the first equipment characteristic quantities;
calculate a statistic of the second equipment characteristic quantities;
generate a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities” (Burke, fig. 1, ¶ 0013, ¶ 0060-0062: Burke teaches “the method 100 comprises time-stamping a performance statistic computed using an interval window and placing the time-stamped performance statistic into storage” thereby allowing “a real-time performance statistic computed using an instantaneous window (calculated statistic of the second equipment characteristic quantities) to be easily and directly compared to the same performance static computed using an interval window at any period or point in time previously (calculated statistic of the first equipment characteristic quantities) (¶ 0060) and the comparison “may enable easier extraction of practical insights from the real-time and historical data analytics” (¶ 0013) therefore Burke discloses “generating a difference rate” by comparing the computed statistics.
“select at least one target characteristic category from the at least one characteristic category according to the difference inspection value:
input the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality” predictions (Burke, fig. 4, ¶ 0127: Fig. 4 depicts “computing one or more performance statistics” (350) disclosing “at least one characteristic category” where the “real-time data analytics and historical data analytics computed at step 350 are directly comparable” (¶ 0127) disclosing “second” and “first equipment characteristic quantities” which are “comparable” disclosing a comparison, and “providing the one or more statistics computed over a predetermined duration of time to the machine learning model as training data: and providing the one or more statistics computed at an instantaneous point in time to the machine learning model as real data to generate the one or more predicted statistics” (claim 12) disclosing the input of “at least one characteristic category” into a machine learning model which outputs “predicted statistics.”)
Both Yaacov and Burke us data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including the data analysis method of comparing computed statistics of real-time and a previous time frame as disclosed by Burke to help identify causes of inefficiencies in order to provide a system where using “only events relevant or necessary for computing a statistic to be taken into account” where “Irrelevant or unnecessary events can be ignored, improving efficiency” (Burke, ¶ 0027).
Yaacov teaches the machine learning is used to determine “maintenance items” (see above.)
Regarding claim 12:
Claim 12 recites analogous limitations to claim 2 above and is therefore rejected on the same premise.
Regarding claim 14:
“generates the status difference data of the equipment according to the equipment operation information in response to an operation period in the equipment operation information meeting a regular maintenance period” (Rollins, fig. 3, ¶ 0258: Rollins teaches a “variable process control system” that “analyzes historical process demand and environmental stress as well as current process demand and current environmental stress to minimize the energy used to vary the fan speed” (¶ 0025) and processes the “actual real-time performance and environment data and then correlates such data to the stored historical data and the data representing the operational characteristics of subsystems and components (where “correlates” discloses generating status difference data of the equipment where the “data” discloses equipment operation information) in order to” among other things, determine system efficiency and perform proactive and predictive maintenance events (¶ 0258) disclosing the “energy efficiency” meets a “maintenance condition.” Moreover, “the present invention predicts design fan speed from the tower performance curve and the fan map and then compares the design fan speed to operating performances” disclosing “status difference data.” Additionally, “Fan operation is represented by a sine wave over a 24 hour period” (¶ 0159) disclosing an “operational period.”)
Yaacov teaches “the control system is run periodically (e.g. every five minutes). The time period may be selected according to the nature of the manufacturing facility” disclosing a “regular maintenance period” therefore the combination of Yaacov and Rollins teaches “generates the status difference data of the equipment according to the equipment operation information in response to an operation period in the equipment operation information meeting a regular maintenance period.”
Both Yaacov and Rollins teach maintaining machinery therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility by predicting and alerting the system that maintenance is required as taught by Yaacov by including the method of using a status difference of an operational period to determine maintenance items as taught by Rollins as analyzing an asset’s energy consumption enables maintenance workers to identify potential problems and provide timely repairs avoiding costly unplanned downtime in order to provide a system that “provides recommendations, insights and proactive actions to improve efficiency based on the analysis” (Rollins, ¶ 0267.)
Regarding claim 16:
Claim 16 recites analogous limitations to claim 6 above and is therefore rejected on the same premise.
Regarding claim 17:
Claim 17 recites analogous limitations to claim 7 above and is therefore rejected on the same premise.
Regarding Independent claim 20 Yaacov teaches:
“A computer readable recording medium storing a program, in response to a computer loading the program” (Yaacov, ¶ 0164-¶ 0166.)
“comprising: obtaining equipment operation information of equipment measured by at least one sensor; determining energy efficiency of the equipment according to the equipment operation information” (Yaacov, fig. 6, fig. 11, ¶ 0089-¶ 0099: Yaacov teaches “monitoring and measuring peripheral machines through external sensors thereby understanding the efficiency of the peripheral machines” (¶ 0090,) “predicting maintenance of peripheral machines by connecting to a peripheral machine and connecting to a general system of a manufacturing facility to learn a real-time production line needs” (¶ 0091) and “examining and calculating the efficiency of every connected machine and a total efficiency of the production line” (¶ 0094).)
“determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model” (Yaacov, ¶ 0010, ¶ 0019: Yaacov teaches using machine learning trained by sensor data to monitor machines (¶ 0010) where the “trained model serves as a basis for a control system” (¶ 0011) where the control system performs “anomaly detection, and predictive maintenance (e.g. when actual performance diverges from the model’s predictions)” (¶ 0019).
Yaacov does not teach:
“generating status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition;
determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input”
Rollins teaches:
“generating status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting a maintenance condition; determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input” (Rollins, fig. 3, ¶ 0258: Rollins teaches processing the “actual real-time performance and environment data and then correlates such data to the stored historical data and the data representing the operational characteristics of subsystems and components (where “correlates” discloses generating status difference data of the equipment where the “data” discloses equipment operation information) in order to” among other things, determine system efficiency and perform proactive and predictive maintenance events (¶ 0258) disclosing the “energy efficiency” meets a “maintenance condition.” Moreover, “the present invention predicts design fan speed from the tower performance curve and the fan map and then compares the design fan speed to operating performances” disclosing “status difference data” and “the operating of the fan 12 at higher speeds may trigger an inspection” (¶ 0258) disclosing “a maintenance item,” an “inspection,” is determined due to “status difference data.”)
Yaacov teaches a “proactive engine unit for operation optimizing and predicting the maintenance of peripheral machines” (¶ 0071) using “all available data and information relevant to the situation of the peripheral machines” (¶ 0260). Moreover, the “proactive engine unit” contains a “modeler” which includes but is not limited to a “rule-based, thermo-dynamic, and artificial intelligence” type of model (¶ 0263). Therefore the combination of Yaacov and Rollins discloses the limitation “determining at least one maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input”
Rollins teaches:
“initiating a display indicating suggestion information of the at least one maintenance item through a display in response to determining the at last on maintenance item” (Rollins, fig. 2, ¶ 0202: Rollins teaches “Industrial computer 300 will trend the data and make a decision as to whether to display a notice on display 306 that notifies the operators that an inspection (maintenance item) of the cooling tower is necessary” (¶ 0202).)
Both Yaacov and Rollins teach maintaining machinery therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility by predicting and alerting the system that maintenance is required as taught by Yaacov by including the method of using the energy efficiency and a status difference to determine maintenance items as taught by Rollins as analyzing an asset’s energy consumption enables maintenance workers to identify potential problems and provide timely repairs avoiding costly unplanned downtime in order to provide a system that “provides recommendations, insights and proactive actions to improve efficiency based on the analysis” (Rollins, ¶ 0267.)
wherein generating the status difference data of the equipment according to the equipment operation information in response to the energy efficiency meeting the maintenance condition (see above) comprises:
Yaacov does not teach:
“obtaining a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval;
calculating a statistic of the first equipment characteristic quantities;
obtaining a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval:
calculating a statistic of the second equipment characteristic quantities; generating a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities
generating a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities”
Rollins teaches:
“obtaining a plurality of first equipment characteristic quantities of the equipment corresponding to at least one characteristic category within a reference time interval; obtaining a plurality of second equipment characteristic quantities of the equipment corresponding to the at least one characteristic category within a current time interval: generating a difference inspection value in the status difference data by comparing the first equipment characteristic quantities with the second equipment characteristic quantities” (Rollins, fig. 2, ¶ 0258-¶ 0259: Rollins teaches “Industrial computer 300 process the actual real-time (current time interval) performance and environmental data and then correlates such data (second equipment characteristic quantities) to the stored historical data (first equipment characteristic quantities which are of a reference time interval) and the data representing the operational characteristics of subsystems and components” (¶ 0258) in order to “determine deviation from previous trends and design curves (disclosing the first equipment characteristic quantities) and related operating tolerance band” (disclosing second equipment characteristic quantities (¶ 0259)) (¶ 0258) where “deviation” discloses a “difference inspection value.”)
Both Yaacov and Rollins teach maintaining machinery therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov by including the method of comparing equipment characteristic quantities of a current time frame and a reference time frame as disclosed by Rollins to help identify causes of inefficiencies in order to provide a system that “provides recommendations, insights and proactive actions to improve efficiency based on the analysis” (Rollins, ¶ 0267.)
Burke teaches:
“calculating a statistic of the first equipment characteristic quantities; calculating a statistic of the second equipment characteristic quantities; and generating a difference rate in the status difference data according to a difference between the statistic of the first equipment characteristic quantities and the statistic of the second equipment characteristic quantities” (Burke, fig. 1, ¶ 0013, ¶ 0060-0062: Burke teaches “the method 100 comprises time-stamping a performance statistic computed using an interval window and placing the time-stamped performance statistic into storage” thereby allowing “a real-time performance statistic computed using an instantaneous window (calculated statistic of the second equipment characteristic quantities) to be easily and directly compared to the same performance static computed using an interval window at any period or point in time previously (calculated statistic of the first equipment characteristic quantities) (¶ 0060) and the comparison “may enable easier extraction of practical insights from the real-time and historical data analytics” (¶ 0013) therefore Burke discloses “generating a difference rate” by comparing the computed statistics.
Both Yaacov and Burke us data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including the data analysis method of comparing computed statistics of real-time and a previous time frame as disclosed by Burke to help identify causes of inefficiencies in order to provide a system where using “only events relevant or necessary for computing a statistic to be taken into account” where “Irrelevant or unnecessary events can be ignored, improving efficiency” (Burke, ¶ 0027).
Yaacov teaches:
“wherein determining at least one maintenance item corresponding to the equipment” (Yaacov, ¶ 0071, ¶ 0260-¶ 0263: Yaacov teaches “proactive engine unit for operation optimizing and predicting the maintenance of peripheral machines” (¶ 0071) using “all available data and information relevant to the situation of the peripheral machines” (¶ 0260). Moreover, the “proactive engine unit” contains a “modeler” which includes but is not limited to a “rule-based, thermo-dynamic, and artificial intelligence” type of model (¶ 0263). disclosing “determining at least one maintenance item corresponding to the equipment”
Yaacov does not teach:
selecting at least one target characteristic category from the at least one characteristic category according to the difference inspection value;
inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items;
Burke teaches:
“selecting at least one target characteristic category from the at least one characteristic category according to the difference inspection value; inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to a first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of” predictions (Burke, fig. 4, ¶ 0127: Fig. 4 depicts “computing one or more performance statistics” (350) disclosing “at least one characteristic category” where the “real-time data analytics and historical data analytics computed at step 350 are directly comparable” (¶ 0127) disclosing “second” and “first equipment characteristic quantities” which are “comparable” disclosing a comparison, and “providing the one or more statistics computed over a predetermined duration of time to the machine learning model as training data: and providing the one or more statistics computed at an instantaneous point in time to the machine learning model as real data to generate the one or more predicted statistics” (claim 12) disclosing the input of “at least one characteristic category” into a machine learning model which outputs “predicted statistics.”)
Both Yaacov and Burke us data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including the data analysis method of comparing computed statistics of real-time and a previous time frame as disclosed by Burke to help identify causes of inefficiencies in order to provide a system where using “only events relevant or necessary for computing a statistic to be taken into account” where “Irrelevant or unnecessary events can be ignored, improving efficiency” (Burke, ¶ 0027).
Yaacov teaches the machine learning is used to determine “maintenance items” (see above.)
Claims 8-10 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Yaacov as modified by Rollins and Burke as applied to claim 1 and 11 respectively above, and further in view of Vaidya et al., U.S. Pub. No. 2020/0018200 A1.
Regarding claim 8 Yaacov as modified teaches:
“the suggestion information of the at least one maintenance item” (see claim 1 above) comprises
“a consumables quantity and a consumables specification of the at least one maintenance item, the at least one maintenance item comprises a first maintenance item and a second maintenance item and the method further comprises: obtaining a plurality of combinations of consumables quantities corresponding to the first maintenance item and the second maintenance item according to a maximum consumables limit of the first maintenance item and a maximum consumables limit of the second maintenance item” (Yaacov ¶ 0287: Yaacov teaches “if oil temperature increases to 15 degree higher than optimal temperature (consumables specification) it is know from previous experience that oil replacement may be needed and/or that worn-down parts may malfunction soon and/or very high ambient temperature” (¶ 0287) where “oil replacement” and “worn-down parts” malfunctioning disclose “at least one maintenance item comprises a first maintenance item and a second maintenance item” and “oil replacement” and/or “worn-down parts” discloses “a plurality of combinations of consumables quantities corresponding to the first maintenance item and the second maintenance item” and “if oil temperature increases to 15 degree higher than optimal temperature” discloses “a maximum consumables limit.”)
Yaacov does not teach:
“inputting each of the combinations of consumables quantities to an energy efficiency difference prediction model, and obtaining an energy efficiency difference prediction value of each of the combinations of consumables quantities; determining an optimal combination of consumables quantities according to the energy efficiency difference prediction value of each of the combinations of consumables quantities, wherein the optimal combination of consumables quantities indicates a suggested consumables quantity for the first maintenance item and a suggested consumables quantity for the second maintenance item; and
selecting the consumables specification of the first maintenance item with reference to a consumables specification recommendation matrix of the first maintenance item, and selecting the consumables specification of the second maintenance item with reference to a consumables specification recommendation matrix of the second maintenance item.”
Vaidya teaches:
“inputting each of the combinations of consumables quantities to an energy efficiency difference prediction model, and obtaining an energy efficiency difference prediction value of each of the combinations of consumables quantities; determining an optimal combination of consumables quantities according to the energy efficiency difference prediction value of each of the combinations of consumables quantities, wherein the optimal combination of consumables quantities indicates a suggested consumables quantity for the first maintenance item and a suggested consumables quantity for the second maintenance item; and selecting the consumables specification of the first maintenance item with reference to a consumables specification recommendation matrix of the first maintenance item, and selecting the consumables specification of the second maintenance item with reference to a consumables specification recommendation matrix of the second maintenance item.” (Vaidya, fig. 4, fig. 5, fig. 6, ¶ 0017, ¶ 0056: Vaidya teaches, with respect to the lubricant, if the viscosity is outside of a threshold, the system determines lubricant service is needed such as changing or topping off the lubricant (¶ 0049) where changing or topping off the lubricant discloses a “quantity.” With respect to the filter, if the pressure differential, which is specific to the type of installed filter, is greater than a limit the system determines filter service is needed (¶ 0054). Moreover, the “systems and methods monitor and determine various fluid quality parameters and filter element pressure drop, which can be used to determine real-time estimates of the remaining useful life for both the filter element and the fluid” (abstract) disclosing “energy efficiency.” Additionally, “after one of the triggers is received (at 436 or 514) the controller 112 determines whether the remaining life of the non-triggered consumable (i.e., the other of the lubricant or the filter element 111) is greater than a threshold remaining life” (¶ 0056). Fig. 6 depicts a matrix used to determine whether the filter, the lubricant, or both are in need of service.
Both Yaacov as modified and Vaidya use data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including determining when consumables such as old contaminated and decomposed lubricant and filters clogged with dirt and debris from the lubricant should be replaced to avoid damage to a machine as taught by Vaidya in order to provide a system where replacement of consumables at the optimal time reduces down time of the machine and the equipment powered by the machine.
Regarding claim 9 Yaacov as modified does not teach:
“maintenance benefit assessment information, and the method further comprises: generating the maintenance benefit assessment information of the equipment according to the energy efficiency difference prediction value corresponding to the optimal combination of consumables quantities.”
Vaidya teaches:
“maintenance benefit assessment information, and the method further comprises: generating the maintenance benefit assessment information of the equipment according to the energy efficiency difference prediction value corresponding to the optimal combination of consumables quantities” (Vaidya, fig. 6, ¶ 0057: Vaidya teaches If the remaining useful life of the non-triggered consumable is greater than the threshold remaining useful life, then the controller 112 initiates a warning or alert indicating that the triggering consumable (i.e., whichever of the lubricant or the filter element 111 is associated with the trigger that initiated the method 600) requires changing at 604 If the remaining useful life of the non-triggered consumable is less than the threshold remaining useful life, than the controller 112 initiates a warning or alert indicating that both the consumables (i.e., both the lubricant and the filter element 111) requires changing at 606, In either situation, the alert or warning is presented or exhibited to the operator via the operator device 120 (e.g., as a dashboard light, as a push notification, as an audible alert, as an e-mail, etc.)” (¶ 0057) thereby teaching determining which combination of consumables, one or both, needs service dependent on the remaining useful life (energy efficiency) where the optimal combination is “exhibited to the operator” disclosing the “maintenance benefit assessment information” is “generated.”)
Both Yaacov as modified and Vaidya use data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including generating maintenance benefit assessment information as taught by Vaidya in order to provide a system where replacement of consumables at the optimal time reduces down time of the machine and the equipment powered by the machine.
Regarding claim 10 Yaacov as modified does not teach:
“generating the status difference data of the equipment according to the equipment operation information in response to an operation period in the equipment operation information meeting a regular maintenance period.”
Vaidya teaches:
“generating the status difference data of the equipment according to the equipment operation information in response to an operation period in the equipment operation information meeting a regular maintenance period” (Vaidya, ¶ 0017, ¶ 0019, ¶ 0057 : Vaidya teaches If the remaining useful life of the non-triggered consumable is greater than the threshold remaining useful life, then the controller 112 initiates a warning or alert indicating that the triggering consumable (i.e., whichever of the lubricant or the filter element 111 is associated with the trigger that initiated the method 600) requires changing at 604 If the remaining useful life of the non-triggered consumable is less than the threshold remaining useful life, than the controller 112 initiates a warning or alert indicating that both the consumables (i.e., both the lubricant and the filter element 111) requires changing at 606, In either situation, the alert or warning is presented or exhibited to the operator via the operator device 120 (e.g., as a dashboard light, as a push notification, as an audible alert, as an e-mail, etc.)” (¶ 0057) thereby teaching “status difference data” concerning the “equipment” through the combination of consumables when one or both needs service dependent on the remaining useful life where “the ‘remaining useful life’ of a consumable can refer to a fraction or percentage of the amount of the useful life of the consumable that is determined based on how much of the useful life remains after the consumable has been used for a certain period of time” (¶ 0017) where “a certain period of time” discloses a “regular maintenance period.”)
Both Yaacov as modified and Vaidya use data analysis to improve the efficiency of a system therefore it would have been obvious to a person of ordinary skill in the art to have modified the system for controlling machines in a manufacturing facility as taught by Yaacov as modified by including a regular maintenance period as taught by Vaidya as regular maintenance period reduce unexpected breakdowns and lower long-term overall costs and thereby providing a system with improved operational efficiency and reliability.
Regarding claim 18:
Claim 18 recites analogous limitations to claim 8 above and is therefore rejected on the same premise.
Regarding claim 19:
Claim 19 recites analogous limitations to claim 9 above and is therefore rejected on the same premise.
Response to Arguments
Applicant’s arguments (remarks) filed on 12/19/2025 have been fully considered.
Regarding Discussion of Claim Rejections under 35 U.S.C. 101 page 14-16 of Applicant’s remarks, Examiner acknowledges Applicant’s arguments. Applicant argues “Firstly, regarding Step 2A, prong I, claim 1 is amended to comprise the steps such as obtaining sensor data, generating status data, applying machine learning models, and initiating a displaying indicating suggestion information. Additionally, the maintenance item corresponding to the equipment is determined according to output of a first machine learning model using the status difference data as input. The Applicant respectfully submits that such limitations involve the process of determining maintenance item corresponding to the equipment according to output of a first machine learning model using the status difference data as input, and initiating a display indicating suggestion information of the maintenance item cannot be practically performed in the human mind and do not cover mathematical steps. Hence, these claimed technical steps are not practically performed by human and is more than mathematical concepts. Thus, claim 1 is eligible because it does not recite a judicial exception. (Step 2A, Prong I: No)” (remarks, page 15).
Examiner respectfully disagrees. Limitations such as “generating status data, applying machine learning models” and “determining maintenance item” are algorithms or programs which are mathematical routines, additionally “determining maintenance item” could be a mental step as a person can mentally determine a maintenance item to be performed. Moreover, “obtaining sensor data” and :initiating a display indicating suggestion information” equates to extra solution data activity (See MPEP 2106.05(g)). Regarding “applying machine learning models” equates to applying a computer program and is therefore extra solution data activity.
Applicant argues “Secondly, regarding Step 2A, prong II and Step 2B, the claimed method automatically identifies the maintenance item applicable to the equipment based on the characteristic status of the equipment (paragraph [0083] of the published application). The status data is generated according to the equipment operation information, which is obtained/ measured by sensor or measuring instrument. Additionally, by determining the optimal consumables quantity and the optimal consumables specification of the maintenance item, the operation energy efficiency of the equipment can be improved. Thus, the present application achieves a concrete technical effect through the use of machine learning models, rather than merely involving abstract judgments or numerical calculations. As such, the claimed invention contributes to technical improvements and is integrated into a practical application, which should be patent eligible under Step 2A, prong II and Step 2B” (remarks, page 15-16).
Examiner respectfully disagrees. The claim language of independent claims 1, 11, and 20 amounts to no more than an algorithm run on a generic computer to determine a result. The amended limitations do not provide sufficient detail to amount to significantly more than the judicial exception. Claim language states “determining the at least one maintenance item according to the first predicted probabilities output by the first machine learning model” does not claim a maintenance item is actively being applied to a system but that the algorithm has “determined” a maintenance item and is merely describing an intended maintenance item and therefore is not a specific practical application. Examiner respectfully suggests the maintenance item and its purpose be actively claimed.
Regarding Discussion of Claim Rejections under 35 U.S.C. 103 page 16-19 of Applicant’s remarks, Applicant argues “However, Burke does not teach or suggest inputting the difference rate to the model. Even Burke teaches that the real-time data analytics and historical data analytics computed at step 350 are directly comparable (paragraph [0127] of Burke), Burke does not explicitly teach or suggest using the difference rate (as claimed) as an input of the model.
Thus, Burke does not disclose the feature "inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category or the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items" in the currently amended claim 1 (remarks page 17-18).
Examiner respectfully disagrees. Claim language states "inputting the difference rate, the statistic of the first equipment characteristic quantities, and the statistic of the second equipment characteristic quantities associated with the at least one target characteristic category OR the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items" (emphasis added). Yaacov as modified by Burke teaches “inputting the at least one characteristic category to the first machine learning model, the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items." Burke teaches “providing the one or more statistics computed over a predetermined duration of time to the machine learning model as training data: and providing the one or more statistics computed at an instantaneous point in time to the machine learning model as real data to generate the one or more predicted statistics” (claim 12) disclosing the input of “at least one characteristic category” into a machine learning model and Yaacov teaches machine learning is used to determine “maintenance items” as Yaacov teaches “proactive engine unit performs operation optimization (and optionally predictive maintenance) of the peripheral machines” (¶ 0260) where the “proactive engine” includes a “modeler” with artificial intelligence as a model (¶ 0262-¶ 0263) . Sensor data and is used by the machine learning model to train and monitor machines (¶ 0010) where the “trained model serves as a basis for a control system” (¶ 0011) where the control system performs “anomaly detection, and predictive maintenance (e.g. when actual performance diverges from the model’s predictions)” (¶ 0019) disclosing “the first machine learning model outputting a plurality of first predicted probabilities corresponding to a plurality of predetermined maintenance items” as “predicted maintenance of the peripheral machines” and “when actual performance diverges from the model’s predictions” disclose “a plurality of predetermined maintenance items” as “the model’s predictions” are predetermined and associated with specific maintenance items.
Regarding Dependent claims 2, 6-10, 12, 14, and 16-19 the above answers are sufficient to respond to the applicant’s arguments.
Conclusion
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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Quintana, U.S. Patent No. 10,690,566 B1, teaches a method for determining a health index of a machine in order to make predictive and corrective maintenance.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Denise R Karavias whose telephone number is (469)295-9152. The examiner can normally be reached 7:00 - 3:00 M-F.
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, Arleen M. Vazquez can be reached at 571-272-2619. 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.
/DENISE R KARAVIAS/Examiner, Art Unit 2857
/MICHAEL J DALBO/Primary Examiner, Art Unit 2857