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 .
Response to Amendment
Claims 1, 11, and 20 are amended and claims 2 and 12 are cancelled. Claims 1, 3-11, and 13-20 are pending.
Response to Arguments
Applicant's arguments filed 1/29/2026 have been fully considered.
Regarding the rejections of claims 2 and 12 under 112(b), and as noted by Applicant on page 14 of the response, claims 2 and 12 are cancelled thus rendering the rejections moot.
Regarding the rejection of claim 20 under 101 as being directed to non-statutory subject matter, the amendment to claim 20 overcomes the rejection, which is withdrawn.
Regarding the rejections of claims 1, 3-11, and 13-20 under 101 as being directed to a judicial exception without significantly more, Examiner respectfully disagrees with Applicant’s arguments on pages 15-16 for the following reasons.
On pages 15-16 of the response and regarding Step 2A Prong 1, Applicant notes that “… the claim now includes obtaining equipment operation information of a plurality of air compressors by measuring instruments, training a plurality of candidate prediction models using the plurality of training feature variables and an actual total displacement volume of the air compressors in another previous unit time period, selecting a production prediction model from the candidate prediction models, outputting a predicted total displacement volume according to the candidate feature variables associated with the air compressors and the production prediction model, and determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume associated with the air compressors.” Applicant contends “[s]uch process involves the processes of training a plurality of candidate prediction models and then selecting a production prediction model from the candidate prediction models according to a model measurement indicator, then using the selected production prediction model to output the predicted total displacement volume, which is used to determine the suggested equipment parameter. These processes cannot be carried out by the human being mentally or manually, but require machine-based computation applied to digital image data.”
Examiner submits that the steps of selecting a production prediction model from the candidate prediction models, and determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume associated with the air compressors can in a broadest reasonable interpretation be implemented via mental processes (e.g., evaluation and judgment) and therefore fall within the mental processes judicial exception. Examiner acknowledges that portions of the training process such as obtaining equipment operation information of a plurality of air compressors by measuring instruments, training a plurality of candidate prediction models using the plurality of training feature variables and an actual total displacement volume of the air compressors in another previous unit time period, and outputting a predicted total displacement volume according to the candidate feature variables associated with the air compressors and the production prediction model, fall outside the abstract idea exception. However, as noted in the current grounds of rejection these elements, considered individually and/or in combination with all elements of the claim appear to be merely means of implementing the functions falling within the judicial exception via known computer means such that the claim as a whole does not appear to represent a significant improvement to a particular technology (e.g., improvement in computer functionality in implementing gas compressor monitoring/control).
The use of “measurement instruments” for obtaining the equipment operation information is recited at a high level of generality (no particularized characterization of the types of data collected and/or means of collection in relation to the target parameter “total displacement volume”) and therefore represents high level data collection. The step of training a plurality of candidate prediction models using the plurality of training feature variables and an actual total displacement volume represents providing of the program instructions (model provided by training) using a training/learning process that itself corresponds to mental processes (e.g., learning via pattern matching) other program processing that itself has no particularized functional relation to the underlying steps (predicting a total displacement volume) that fall within the judicial exception. Therefore, the overall process appears to represent using machine learning for preparing and deploying a model to implement functions that fall within the judicial exception, with any potential utility in the field of air compressor monitoring and control substantially confined to the abstract idea itself.
With further regard to Step 2A Prong 1, Applicant contends on page 16 of the response that the claimed limitations do not involve mathematical relationships. Examiner submits, as set forth in the current grounds of rejection, that “determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume and an estimated maximum loading volume associated with the air compressors” in claim 11 is determined as falling within the mathematical relationships sub-category of mathematical concepts (MPEP 2106.04(a)(2)), as well as the mental processes exception, because, as depicted and described with reference to Applicant’s FIG. 5 (e.g., Applicant’s specification [0060] and Table 6) the step of determining a suggested equipment parameter may be implemented by a linear regression that is fundamentally characterized by mathematical relations/calculations and therefore constitutes mathematical relationships.
Regarding Step 2A Prong 2, Applicant contends that claim 1 provides an improved prediction method that obtains predicted total displacement volume of air compressors according to equipment operation and the trained machine learning model and in which the suggested equipment parameter of at least one air compressor may be determined according to the prediction, such that an equipment manager may know and plan how to adjust air compressor parameters to save electricity rather than relying on long-term accumulated personal experiences.
Examiner acknowledges that computer and machine learning implementation of the prediction of total displacement volume and corresponding control adjustments may be efficient as a result of its automated implementation. However, such efficiency appears to be confined to computer and machine learning automation per se, rather than an innovative computer/machine learning configuration that effectuates an improvement in such prospective efficiency. Therefore, the computer/machine learning elements considered as a whole in combination with the elements constituting the judicial exception do not appear to result in the claim as a whole amounting to significantly more than the judicial exception.
Regarding the rejections of independent claims 1, 11, and 20 under 103, Examiner respectfully disagrees with Applicant’s arguments on pages 17-20 for the following reasons.
On page 17 of the response, Applicant contends that the combination of the cited references fails to render obvious the feature "training a plurality of candidate prediction models corresponding to a plurality of machine learning algorithms using the plurality of training feature variables and an actual total displacement volume of the air compressors in another previous unit time period” and "selecting a production prediction model from the candidate prediction models according to a model measurement indicator" in the currently amended claim 1.
Regarding "training a plurality of candidate prediction models … using the plurality of training feature variables and an actual total displacement volume … in another previous unit time period,” Applicant asserts on page 19 that CN112560193 merely teaches selecting the sample data/training samples at different locations and times during operation of the actual air supply system and does not teach or suggest “an actual total displacement volume of the air compressors.”
Examiner submits that on page 8, third paragraph beginning with “based on the above” CN112560193 explains that actual operation data is used for training the neural network model and that on page 8, 13th paragraph beginning with “using artificial neural network to establish” CN112560193 explains that the learning data includes collected input variables and output variables. In the Abstract CN112560193 discloses that the model “output” (corresponding to output variable) is the exhaust (displacement) volume. The Examiner submits that that in overall context, with the training data comprising actual operation data including input features and output features (features estimated by the model based in the input features) for the model, and in which the model is configured to output the displacement volume, the training data would correspond and include actual output displacement volume, which in the absence of indication of “partial” output displacement would constitute a broadest reasonable interpretation of total output displacement volume, as previously measured as an output variable.
Regarding "selecting a production prediction model from the candidate prediction models according to a model measurement indicator," Applicant asserts on page 19 that CN112560193 merely teaches a repeated recursive processing in which multiple versions of the neural network model are tested based on a testing criterion to derive the final model, such that CN112560193 trains the neural network model to derive an optimal model, rather than selecting a model from a plurality of models according to a model measurement indicator as claimed.
Examiner submits that the testing to derive a final model entails a process whereby given instances of the model are tested until a “final” model is determined and therefore effectively constitutes selecting a model from among candidate models.
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, 3-11, and 13-20 are rejected under 35 U.S.C. 101 because the claimed invention in each of these claims is directed to the abstract idea judicial exception without significantly more.
Independent claim 11, substantially representative also of independent claims 1 and 20, recites:
“[a]n electronic device, comprises:
a display;
a storage circuit, storing a plurality of instructions; and
a processor, coupled to the display and the storage circuit and accessing the instructions to execute:
obtaining equipment operation information of a plurality of air compressors (by measuring instruments in claim 1);
generating a plurality of candidate feature variables corresponding to a plurality of previous unit time periods according to the equipment operation information of each of the air compressors;
extracting a plurality of training feature variables from the plurality of candidate feature variables;
training a plurality of candidate prediction models corresponding to a plurality of machine learning algorithms using the plurality of training feature variables and an actual total displacement volume of the air compressors in another previous unit time period;
selecting a production prediction model from the candidate prediction models according to a model measurement indicator;
generating a plurality of feature variables associated with the plurality of air compressors according to the equipment operation information of each of the air compressors;
inputting the plurality of feature variables associated with the air compressors to the production prediction model;
outputting a predicted total displacement volume according to the feature variables associated with the air compressors and the production prediction model;
determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume and an estimated maximum loading volume associated with the air compressors; and
instructing to display suggestion information associated with the suggested equipment parameter for controlling operation of the air compressors via the display.”
The claim limitations considered to fall within in the abstract idea are highlighted in bold font above and the remaining features are “additional elements.”
Step 1 of the subject matter eligibility analysis entails determining whether the claimed subject matter falls within one of the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: process, machine, manufacture, or composition of matter. Claim 11 recites a device (machine), claim 1 recites a method, and claim 20 recites an article of manufacture and therefore each falls within a statutory category.
Step 2A, Prong One of the analysis entails determining whether the claim recites a judicial exception such as an abstract idea. Under a broadest reasonable interpretation, the highlighted portions of claim 11 fall within the abstract idea judicial exception. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, the highlighted subject matter falls within the mental processes category (including an observation, evaluation, judgment, opinion) and the mathematical concepts category (mathematical relationships, mathematical formulas or equations, mathematical calculations). MPEP § 2106.04(a)(2).
The recited functions:
“generating a plurality of candidate feature variables corresponding to a plurality of previous unit time periods according to the equipment operation information of each of the air compressors”
“extracting a plurality of training feature variables from the plurality of candidate feature variables”
“selecting a production prediction model from the candidate prediction models according to a model measurement indicator”
“generating a plurality of feature variables associated with the plurality of air compressors according to the equipment operation information of each of the air compressors” and
“determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume and an estimated maximum loading volume associated with the air compressors,”
may be performed as mental processes.
Generating a plurality of candidate feature variables corresponding to a plurality of previous unit time periods according to the equipment operation information of each of the air compressors may be performed via mental processes (e.g., evaluation of equipment operation data and judgment in determining/deriving corresponding features related to operation that may pertain to a conceived of output condition of the equipment). Extracting a plurality of training feature variables from the plurality of candidate feature variables may be performed via mental processes (e.g., evaluation of the candidate features and judgment in determining which candidates may be most relevant to an equipment output condition). Selecting a production prediction model from the candidate prediction models according to a model measurement indicator may be performed via mental processes (e.g., evaluation of model performances and judgment in selecting an optimally performing model). Generating a plurality of feature variables associated with a plurality of air compressors according to equipment operation information of each of the air compressors may be performed via mental processes (e.g., evaluation of equipment operation information and judgment in determining/ascertaining corresponding feature variables). Determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume and an estimated maximum loading volume associated with the air compressors may also be performed via mental processes (e.g., evaluation of predicted total displacement volume and estimated maximum loading volume to determine, via judgment, a suggested equipment parameter).
The recited function “determining a suggested equipment parameter of at least one of the air compressors according to the predicted total displacement volume and an estimated maximum loading volume associated with the air compressors” in claim 11 is further determined by the Examiner as falling within the mathematical relationships sub-category of mathematical concepts (MPEP 2106.04(a)(2)) because, as depicted and described with reference to Applicant’s FIG. 5 (e.g., Applicant’s specification [0060] and Table 6) the step of determining a suggested equipment parameter may be implemented by a linear regression that is fundamentally characterized by mathematical relations/calculations and therefore constitutes mathematical relationships.
Step 2A, Prong Two of the analysis entails determining whether the claim includes additional elements that integrate the recited judicial exception into a practical application. “A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the judicial exception” (MPEP § 2106.04(d)).
MPEP § 2106.04(d) sets forth considerations to be applied in Step 2A, Prong Two for determining whether or not a claim integrates a judicial exception into a practical application. Based on the individual and collective limitations of claim 11 and applying a broadest reasonable interpretation, the most applicable of such considerations appear to include: improvements to the functioning of a computer, or to any other technology or technical field (MPEP 2106.05(a)); applying the judicial exception with, or by use of, a particular machine (MPEP 2106.05(b)); and effecting a transformation or reduction of a particular article to a different state or thing (MPEP 2106.05(c)).
Regarding improvements to the functioning of a computer or other technology, none of the “additional elements” including “electronic device” comprising “a display; a storage circuit, storing a plurality of instructions; and a processor, coupled to the display and the storage circuit and accessing the instructions,” and the functions “obtaining equipment operation information of a plurality of air compressors” (by measuring instruments for claim 1), “training a plurality of candidate prediction models corresponding to a plurality of machine learning algorithms using the plurality of training feature variables and an actual total displacement volume of the air compressors in another previous unit time period,” “inputting the plurality of feature variables associated with the air compressors to the production prediction model,” “outputting a predicted total displacement volume according to the feature variables associated with the air compressors and the production prediction model,” and “instructing to display suggestion information associated with the suggested equipment parameter for controlling operation of the air compressors via the display” in any combination appear to integrate the abstract idea in a manner that technologically improves any aspect of a device or system that may be used to implement the highlighted step or a device for implementing the highlighted step such as a signal processing device or a computer.
Instead, “electronic device” comprising “a display; a storage circuit, storing a plurality of instructions; and a processor, coupled to the display and the storage circuit and accessing the instructions” represent routine, conventional computing means for implementing the functions falling within the judicial exception and therefore constitute insignificant extra solution activity that fails to integrate the judicial exception into a practical application. Obtaining equipment operation information of a plurality of air compressors (by measuring instruments for claim 1) represents high level data collection having no particularized functional relation to the steps falling within the judicial exception and therefore constitutes insignificant extra solution activity that neither integrates the judicial exception into a practical application nor results in the claim as a whole amounting to significantly more than the judicial exception. Training a plurality of candidate prediction models corresponding to a plurality of machine learning algorithms using the plurality of training feature variables and an actual total displacement volume of the air compressors in another previous unit time period represents routine preparation and application of computer program instructions using other computer instructions for implementing the steps falling within the judicial exception and therefore constitutes insignificant extra solution activity. The functions inputting the plurality of feature variables associated with the air compressors to the production prediction model, outputting a predicted total displacement volume according to the feature variables associated with the air compressors and the production prediction model, and instructing to display suggestion information associated with the suggested equipment parameter for controlling operation of the air compressors via the display represent conventional, routine data output processing having no particularized relation to functions falling within the judicial exception and therefore constitute insignificant post solution type extra solution activity that fails to integrate the judicial exception into a practical application. Using a “production prediction model” as the means by which to obtain/output a predicted total displacement volume represents computer instructions for implementing functions falling within the judicial exception and therefore also constitutes extra solution activity that neither integrates the judicial exception into a practical application nor results in the claim as a whole amounting to significantly more than the judicial exception.
Regarding application of the judicial exception with, or by use of, a particular machine, the additional elements are configured and implemented in a non-particularized manner with respect to implementing monitoring and controlling compressed air systems via computer means.
Regarding a transformation or reduction of a particular article to a different state or thing, claim 11 does not include any such transformation or reduction. Instead, claim 11 as a whole entails processing input information (feature variables associated with operation information and using well-known feature-based model training techniques) by applying standard processing techniques (modeling) to the information to determine equipment parameter information with the additional elements failing to provide a meaningful integration of the abstract idea (determining predicted total displacement volume and determining an equipment parameter based on the predicted total displacement volume and a maximum loading volume) in an application that transforms an article to a different state. Instead, the additional elements represent extra-solution activity that does not integrate the judicial exception into a practical application. In view of the various considerations encompassed by the Step 2A, Prong Two analysis, claim 11 does not include additional elements that integrate the recited abstract idea into a practical application.
Therefore, claim 11 is directed to a judicial exception and requires further analysis under Step 2B.
Regarding Step 2B, and as explained in the Step 2A Prong Two analysis, the additional elements in claim 11 constitute insignificant extra solution activity and therefore fail to result in the claim as a whole amounting to significantly more than the judicial exception. Furthermore, the additional elements appear to be generic and well understood as evidenced by the disclosures of Van Roy (US 2023/0313950 A1), CN112560193, and Kim (US 2023/0034599 A1), which teach substantially similar computing platform and modeling for determining compressor system parameters (control settings).
As explained in the grounds for rejecting claim 11 under 103, Van Roy teaches “electronic device” comprising “a storage circuit, storing a plurality of instructions; and a processor, coupled to the display and the storage circuit and accessing the instructions,” obtaining a predicted total displacement volume according to the feature variables associated with the air compressors and “a production prediction model” that is trained using feature-based model training. Similarly, Kim teaches a computer implemented method in which the computer includes storage, a processor, and a display (FIG. 1 depicting computer system including CPU 12, memory 13, and monitor 2) and in which modeling is used for determining control settings [0037]-[0039]). CN112560193 also teaches computer implemented modeling of compressor group operation including training prediction models (Abstract).
Therefore, the additional elements in claim 11 are insufficient in combination with the elements constituting the judicial exception to amount to significantly more than the judicial exception.
Independent claim 11 is therefore not patent eligible under 101.
Independent claims 1 and 20 recite substantially the same elements as claim 11 that fall within the judicial exception and include no further additional elements that either integrate the judicial exception into a practical application or result in the claim as a whole amounting to significantly more than the judicial exception.
Claims 1 and 20 are therefore also not patent eligible under 101.
Claims 3-10 depending from claim 1, and claims 13-19 depending from claim 11, provide additional features/steps which are part of an expanded algorithm that includes the abstract idea of claim 11 (Step 2A, Prong One). None of dependent claims 3-10 and 13-19 recite additional elements that integrate the abstract idea into practical application (Step 2A, Prong Two), and all fail the “significantly more” test under the step 2B for substantially similar reasons as discussed with regards to claim 11.
For example, claim 3, substantially representative also of claim 13, recites “calculating a maximum unit loading volume of each of the air compressors according to a plurality of historical displacement volumes of each of the air compressors in a plurality of previous unit time periods and idling information of each of the air compressors; and obtaining the estimated maximum loading volume by summing up the maximum unit loading volume of each of the air compressors” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper). Furthermore, the step of “obtaining the estimated maximum loading volume by summing up the maximum unit loading volume of each of the air compressors” is found to fall within the mathematical concepts exception (mathematical relations) because this step is fundamentally characterized by mathematical relations/calculations (adding).
Claim 4, substantially representative also of claim 14, recites “calculating an expected maximum displacement volume of a first air compressor in a first previous unit time period according to an idling rate of the first air compressor and one of the historical displacement volumes of the first air compressor in the first previous unit time period in response to determining that the first air compressor among the air compressors is in an idling state in the first previous unit time period in the previous unit time periods; and determining the maximum unit loading volume of the first air compressor in the previous unit time periods by comparing the expected maximum displacement volume with the historical displacement volumes in the previous unit time periods or a plurality of expected maximum displacement volumes in the previous unit time periods of the first air compressor,” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper).
Claim 5 recites “calculating the idling rate of the first air compressor according to an idling hour of the first air compressor within a statistical time period,” which fall within the mental concepts judicial exception because this step may be performed via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper). The step is further found to fall within the mathematical concepts judicial exception because calculation of an idling rate based on an idling period (hour) within a statistical time period is fundamentally characterized by mathematical relations/calculations.
Claim 6, substantially representative also of claim 15, recites “comparing the predicted total displacement volume with the estimated maximum loading volume; and determining the suggested equipment parameter of each of the air compressors according to the predicted total displacement volume in response to the predicted total displacement volume being greater than the estimated maximum loading volume,” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper).
Claim 7, substantially representative also of claim 16, recites “obtaining an output loading ratio of each of the air compressors according to a plurality of historical displacement volumes or a plurality of expected maximum displacement volumes of each of the air compressors in a plurality of previous unit time periods; generating a predicted loading displacement volume of each of the air compressors according to the predicted total displacement volume and the output loading ratio of each of the air compressors; and determining the suggested displacement pressure of each of the air compressors according to the predicted loading displacement volume of each of the air compressors,” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper). Furthermore, the step “obtaining an output loading ratio of each of the air compressors according to a plurality of historical displacement volumes or a plurality of expected maximum displacement volumes of each of the air compressors in a plurality of previous unit time periods,” is further found to fall within the mathematical concepts judicial exception because determining a loading ratio based on displacement volumes in multiple time periods is fundamentally characterized by mathematical relations/calculations.
Claim 8, substantially representative also of claim 17, recites “calculating a difference between the predicted total displacement volume and the estimated maximum loading volume; calculating a target displacement pressure of each of the air compressors according to the difference; calculating an electricity saving volume corresponding to each of the air compressors according to the target displacement pressure of each of the air compressors and a reference displacement pressure of each of the air compressors; selecting a first air compressor from the air compressors according to the electricity saving volume corresponding to each of the air compressors and a displacement pressure limit; and determining the suggested displacement pressure of the first air compressor as the target displacement pressure of the first air compressor, and determining the suggested displacement pressure of a second air pressure that is not selected among the air compressors as the reference displacement pressure,” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper). Furthermore, the step “calculating a difference between the predicted total displacement volume and the estimated maximum loading volume,” is further found to fall within the mathematical concepts judicial exception because calculating a difference between a predicted volume and an estimated loading volume is fundamentally characterized by mathematical relations/calculations.
Claim 9, substantially representative also of claim 18, recites “comparing the predicted total displacement volume with the estimated maximum loading volume; selecting a plurality of activated air compressors from the air compressors according to a usage rank in response to the predicted total displacement volume being less than the estimated maximum loading volume; and determining the suggested equipment parameter of each of the activated air compressors,” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper).
Claim 10, substantially representative also of claim 19, recites “generating an estimated electricity saving volume according to the suggested equipment parameter of at least one of the air compressors and a reference equipment parameter of the at least one of the air compressors; and generating electricity saving benefit information in the suggestion information according to the estimated electricity saving volume,” which fall within the mental concepts judicial exception because these steps may be performed, individually and in combination, via mental processes (e.g., evaluation and judgement potentially aided by pen-and-paper).
Dependent claims 3-10 and 13-19 therefore also constitute ineligible subject matter under 101.
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.
Claims 1, 11, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Van Roy (US 2023/0313950 A1) in view of CN 112560193, and further in view of Kim (US 2023/0034599 A1).
As to claims 1, 11, and 20, Van Roy teaches “[a]n equipment parameter recommendation method (Abstract method for generating compressed air system instructions),” “[a]n electronic device (FIGS. 1 and 2 master controller; claim 16 computer-implemented method; [0045] method is computer-implemented), comprises:” “a storage circuit, storing a plurality of instructions ([0045] method is computer-implemented including execution of instructions (inherently requires storage (e.g., memory) for execution of instructions); and a processor, coupled to” “the storage circuit and accessing the instructions ([0045] method is computer-implemented including execution of instructions (inherently requires processor for execution of instructions)” and “[a] computer readable recording medium, storing a program, and a computer loading the program to execute ([0045] method is computer-implemented including execution of instructions (inherently requires storage (e.g., memory) for execution of instructions)”
for implementing a method comprising:
“obtaining equipment operation information ([0020] process variables (e.g., flow) indicative of operation) of a plurality of air compressors (FIG. 1 compressed air system comprises multiple compressors 101-103) by measuring instruments ([0021] state of compressed air system determined based on sensor measurements of process variables);
generating a plurality of candidate feature variables corresponding to a plurality of previous unit time periods according to the equipment operation information of each of the air compressors ([0077]-[0078] data generated/obtained from current and past observations used for training the predictor function (i.e., current and past collected from sensor measurements per [0021] generated as “features”));
extracting a plurality of training feature variables from the plurality of candidate feature variables ([0077]-[0078] model trained using data selected/extracted data from current and past observations (i.e., a portion of past and more recent (current) data selected for training));
training a” [model] “corresponding to a” [machine learning algorithm] “using the plurality of training feature variables ([0077]-[0079] model trained (therefore is a machine learning algorithm) using selected data from current and past observations (i.e., a portion of past and more recent (current) data selected for training))”
“generating a plurality of feature variables associated with the plurality of air compressors ([0012] estimate current state of compressed air system; FIG. 1 compressed air system comprises multiple compressors 101-103; [0021] current state derived from process variables; [0023] current state may comprise variables) according to the equipment operation information of each of the air compressors ([0021] current state derived from measured sensor data measuring process variables; [0023] current state indicative of compressed air system status);
inputting the plurality of feature variables associated with the air compressors to the production prediction model ([0074] prediction block 203 that per [0076]-[0078] is a trained model considers (and therefore has received as input) past process variable data and current process variable data that per [0069] are estimated from measurements);
outputting a predicted total displacement volume ([0013] and [0024] predict/output future process variable profile; [0072] prediction entails predicting the profile variable, which may be flow demand, over a particular time horizon (constitutes a total volume over a period)) according to the feature variables associated with the air compressors ([0069]-[0070] estimation block estimates and provides the current status to prediction block (FIG. 2 input from estimator 202 to prediction block 203); [0071]-[0072] prediction block uses current process variables for prediction) and the production prediction model (FIG. 2 prediction block 203 representing some form of algorithm (model) for processing current state/variables inputs 224 to generate prediction 225; [0075]-[0076]);
determining a suggested equipment parameter of at least one of the air compressors (FIG. 2 model predictive control (MPC) block 205 providing control output 210 to compressed air system 113, [0060] master controller controls the compressed air system (controlling the multi-compressor system inherently entails providing control over equipment); [0015]-[0016] and [0026]-[0027] MPC provides an action profile comprising control “actions”; [0064] actions are instructions (parameters) for compressed air system) according to the predicted total displacement volume (FIG. 1 MPC block 205 configured to determine control output 210 based on input from prediction block 203; [0015]-[0016] and [0026]-[0027] action profiled determined based on future process variable profile) and an estimated maximum loading volume associated with the air compressors (FIG. 1 MPC block 205 configured to determine control output 210 based on input from estimator 202 as well as input from prediction block 203; [0026] a known or estimated volume of the compressed air system (e.g., vessel volume or volume of whole compressed air system) may be used to sample the prediction profile data, and in this manner the predicted total displacement volume and maximum loading volume are used to determine the prediction data provided to MPC block 205 for determining the action profile).”
Van Roy does not appear to expressly teach that “an actual total displacement volume of the air compressors in another previous unit time period” is used in addition to the feature variables (e.g., as another feature variable or as a target output) for training “a plurality of candidate models” that are machine learning models, and further do not teach “selecting the production prediction model from the candidate prediction models according to a model measurement indicator.”
CN112560193 discloses a method for controlling air compressor operation (Abstract) that includes using actual displacement volume in a previous time period for training a machine learning model (page 8, third paragraph beginning with “based on the above” explaining that actual operation data is used for training the neural network model; page 8, 13th paragraph beginning with “using artificial neural network to establish” explaining that the learning data includes collected input variables and output variables; Abstract model “output” (corresponding to output variable) is the exhaust (displacement) volume. The Examiner notes that in overall context, with the training data comprising actual operation data including input features and output features (features estimated by the model based in the input features) for the model, and in which the model is configured to output the displacement volume, the training data would correspond and include actual output displacement volume, which in the absence of indication of “partial” output displacement would constitute a total output displacement volume, as previously measured as an output variable).
The training method taught by CN112560193 further includes training a plurality of candidate models that are machine learning models and selecting a prediction model from the candidate prediction models according to a model measurement indicator (page 4, the ninth through eleventh paragraphs beginning with “in a group sample, removing the verification sample” and page 8, 13th paragraph beginning with “using artificial neural network to establish through page 9, 11th paragraph describing a repeated, recursive processing in which multiple versions of the neural network model are tested (verified) based on a testing criterion (prediction error) to derive the final model).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied the teachings of CN112560193 of using actual displacement volume in a previous time period for training a machine learning model and furthermore in which the training includes training a plurality of candidate models that are machine learning models and selecting a prediction model from the candidate prediction models according to a model measurement indicator to the method taught by Van Roy, such that in combination the method includes using “an actual total displacement volume of the air compressors in another previous unit time period” in addition to the feature variables (e.g., as a target output) for training “a plurality of candidate models” that are machine learning models, and “selecting the production prediction model from the candidate prediction models according to a model measurement indicator.”
The motivation for including an actual displacement volume in the training data (e.g., as the target output) would have been to apply actual displacement data to ensure accurate displacement prediction as suggested by CN112560193. The motivation for training multiple models and selecting a final production model from the multiple/candidate models would have been to implement a selective process whereby testing/verification may be used to ensure optimal model performance as suggested by CN112560193.
Regarding, the “electronic device” in claim 11 including “a display” that in coupled to a processor, and the steps in each of claims 1, 11, and 20 of “instructing to display suggestion information associated with the suggested equipment parameter for controlling operation of the air compressors via a display,” Van Roy in FIG. 4 discloses a graphical form (displayed) of future estimation information generated by the MPC including an action set 407 (FIG. 4 depicting action set 407 as implemented over an interval) for the compressors; [0088] action for controlling the compressors). However, it is not clear from Van Roy’s disclosure whether this graphical information is actually displayed (instructed to display).
Kim discloses a method for determining/assigning compressor settings values (Abstract) that includes displaying (having been instructed to) suggestion information associated with suggested equipment control parameters via a display coupled with a processor (FIG. 2 output unit 120 that per [0074] includes display screen and per FIG. 1 is functionally integrated with and therefore coupled to CPU 12; FIG. 7 depicting a displayed table including controller pressure settings values (suggested values); [0075]-[0076]; [0079]-[0083] describing user application of displayed controller setting values).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Kim’s teaching of displaying suggested information associated with suggested equipment control parameters via a display to the method taught by Van Roy as modified by CN112560193 such that in combination the method includes instructing to display suggestion information associated with the suggested equipment parameter for controlling operation of the air compressors via a display.
The motivation would have been to enable human operators/managers to apply or at least monitor the suggested equipment parameter information to enhance efficient user implementation or oversight of controlling a compressor system as suggested by Kim.
Claims 10 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Van Roy in view of CN112560193 and Kim as applied to claims 1 and 11 above, and further in view of Wen (US 2023/0340962 A1).
As to claim 10, the combination of Van Roy, CN112560193, and Kim teaches “[t]he equipment parameter recommendation method according to claim 1, further comprising:
generating an” “electricity saving volume according to the suggested equipment parameter of at least one of the air compressors (Van Roy: [0059] control via the MPC (per [0015]-[0016], [0026]-[0027], [0060], and [0064], provides an action profile comprising control actions/instructions for compressed air system) generates an amount of energy (in context is inherently electrical energy) savings (consumption optimization)) and a reference equipment parameter of the at least one of the air compressors (Van Roy’s generated electricity savings is inherently a function of equipment operation parameters).”
Kim’s disclosed method also includes using equipment parameter control for generating energy savings ([0014], [0017], [0083]).
Van Roy, CN112560193, and Kim, do not individually or in combination expressly teach generating an energy savings estimate that (per antecedent relation in claim 1) is integrated into the displayed results such that the combination of Van Roy, CN112560193, and Kim do not teach generating an “estimated” electricity saving volume and “generating electricity saving benefit information in the suggestion information according to the estimated electricity saving volume.”
Wen discloses a system/method for optimizing air compressor operations in part to obtain electrical energy savings (Abstract; [0018]-[0020]) that includes generating an estimated electrical saving volume/amount ([0018]-[0020], FIG. 7 depicting displayed user interface including block 730 depicting period-based energy savings) according to a suggested equipment parameter of at least one air compressor ([0020] operations parameters are associated with efficiency evaluation) and a reference equipment parameter of the at least one of the air compressors ([0020] operations parameters and time are associated as reference values for efficiency evaluation) and generating electricity saving benefit information in association with suggestion information according to the estimated electricity saving volume (FIG. 7 depicting displayed user interface including section 730 depicting period-based energy savings displayed in the interface in association with section 710 displaying optimum suggestion (operation) vs actual operation status and section 720 displaying current operation status; [0031]).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Wen’s teaching of generating an electrical savings estimate and generating electricity saving benefit information within suggestion information according to the estimated saving volume to the method taught by Van Roy as modified by CN112560193 and Kim, such that in combination the method includes generating an estimated electricity saving volume according to the suggested equipment parameter of at least one of the air compressors, and generating electricity saving benefit information in the suggestion information according to the estimated electricity saving volume.
The motivation would have been to enhance the flexibility of use of energy savings data via generating the estimate and to display such information in association with displayed suggested equipment parameter to enable a user to potentially apply the combined information to select equipment operating parameters that may increase energy efficiency.
As to claim 19, the combination of Van Roy, CN112560193, and Kim teaches “[t]he electronic device according to claim 11, wherein the processor further executes:
generating an” “electricity saving volume according to the suggested equipment parameter of at least one of the air compressors (Van Roy: [0059] control via the MPC (per [0015]-[0016], [0026]-[0027], [0060], and [0064], provides an action profile comprising control actions/instructions for compressed air system) generates an amount of energy (in context is inherently electrical energy) savings (consumption optimization)) and a reference equipment parameter of the at least one of the air compressors (Van Roy’s generated electricity savings is inherently a function of equipment operation parameters).”
Kim’s disclosed system also includes using equipment parameter control for generating energy savings ([0014], [0017], [0083]).
Van Roy, CN112560193, and Kim, do not individually or in combination expressly teach generating an energy savings estimate that (per antecedent relation in claim 11) is integrated into the displayed results such that the combination of Van Roy and Kim do not teach generating an “estimated” electricity saving volume and “generating electricity saving benefit information in the suggestion information according to the estimated electricity saving volume.”
Wen discloses a system/method for optimizing air compressor operations in part to obtain electrical energy savings (Abstract; [0018]-[0020]) that includes generating an estimated electrical saving volume/amount ([0018]-[0020], FIG. 7 depicting displayed user interface including block 730 depicting period-based energy savings) according to a suggested equipment parameter of at least one air compressor ([0020] operations parameters are associated with efficiency evaluation) and a reference equipment parameter of the at least one of the air compressors ([0020] operations parameters and time are associated as reference values for efficiency evaluation) and generating electricity saving benefit information in association with suggestion information according to the estimated electricity saving volume (FIG. 7 depicting displayed user interface including section 730 depicting period-based energy savings displayed in the interface in association with section 710 displaying optimum suggestion (operation) vs actual operation status and section 720 displaying current operation status; [0031]).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Wen’s teaching of generating an electrical savings estimate and generating electricity saving benefit information within suggestion information according to the estimated saving volume to the device taught by Van Roy as modified by CN112560193 and Kim, such that in combination the device is configured for generating an estimated electricity saving volume according to the suggested equipment parameter of at least one of the air compressors, and generating electricity saving benefit information in the suggestion information according to the estimated electricity saving volume.
The motivation would have been to enhance the flexibility of use of energy savings data via generating the estimate and to display such information in association with displayed suggested equipment parameter to enable a user to potentially apply the combined information to select equipment operating parameters that may increase energy efficiency.
Subject Matter Found Patentably Distinct Over the Prior Arts
Claims 3-9 and 13-18 are found to be patentably distinct over the prior arts for the following reasons:
The most pertinent prior arts are represented by Van Roy (US 2023/0313950 A1), CN112560193, and Kim (US 2023/0034599 A1).
Regarding claim 3, the prior arts, individually or in combination, do not fairly disclose or suggest:
“calculating a maximum unit loading volume of each of the air compressors according to a plurality of historical displacement volumes of each of the air compressors in a plurality of previous unit time periods and idling information of each of the air compressors; and
obtaining the estimated maximum loading volume by summing up the maximum unit loading volume of each of the air compressors,” taken in combination with the other limitations of claim 3, including limitation incorporated by dependence on claim 1.
Claims 4-5 depend from claim 3 and are likewise patentably distinct over the prior arts for the same reasons.
Claim 13 includes substantially the same elements that distinguish claim 3 from the prior arts and is likewise patentably distinct over the prior arts for the same reasons.
Claim 14 depends from claim 13 and is likewise patentably distinct over the prior arts for the same reasons.
Regarding claim 6, the most pertinent prior arts are represented by Van Roy, CN112560193, and Kim, which individually or in combination, do not fairly disclose or suggest:
“comparing the predicted total displacement volume with the estimated maximum loading volume; and
determining the suggested equipment parameter of each of the air compressors according to the predicted total displacement volume in response to the predicted total displacement volume being greater than the estimated maximum loading volume,” taken in combination with the other limitations of claim 6, including limitation incorporated by dependence on claim 1.
Claims 7-8 depend from claim 6 and are likewise patentably distinct over the prior arts for the same reasons.
Claim 15 includes substantially the same elements that distinguish claim 6 from the prior arts and is likewise patentably distinct over the prior arts for the same reasons.
Claims 16-17 depends from claim 15 and are likewise patentably distinct over the prior arts for the same reasons.
Regarding claim 9, the most pertinent prior arts are represented by Van Roy, CN112560193, and Kim teaches the elements of claim 1 from which claim 9 depends. Regarding the elements specific to claim 9, Van Roy further teaches “determining the suggested equipment parameter of each of the activated air compressors (FIG. 2 model predictive control (MPC) block 205 providing control output 210 to compressed air system 113, [0060] master controller controls the compressed air system (controlling the multi-compressor system inherently entails providing control over equipment); [0015]-[0016] and [0026]-[0027] MPC provides an action profile comprising control “actions”; [0064] actions are instructions (parameters) for compressed air system).”
The prior arts, individually or in combination, do not fairly disclose or suggest:
“comparing the predicted total displacement volume with the estimated maximum loading volume;
selecting a plurality of activated air compressors from the air compressors according to a usage rank in response to the predicted total displacement volume being less than the estimated maximum loading volume,” taken in combination with the other limitations of claim 9, including limitation incorporated by dependence on claim 1.
Claim 18 includes substantially the same elements that distinguish claim 9 from the prior arts and is likewise patentably distinct over the prior arts for the same reasons.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW W BACA whose telephone number is (571)272-2507. The examiner can normally be reached Monday - Friday 8:00 am - 5:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Schechter can be reached at (571) 272-2302. 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.
/MATTHEW W. BACA/Examiner, Art Unit 2857
/ANDREW SCHECHTER/Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights