DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is responsive to pending claims 1-20 filed 5/22/2023.
Claim Objections
The following claim(s) are objected to for formality issues:
Claim 19 claims a “non-transient” computer readable medium, while the Specifications 0055, 0059 define only a “non-transitory” computer readable medium. Hence, confusion may arise as to whether something distinct from “non-transitory” is possibly intended. Amending to “non-transitory” would preserve consistency and overcome this rejection.
Appropriate correction(s) are required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The 35 U.S.C. 101 subject matter eligibility analysis first asks whether the claim is directed to one of the four statutory categories (Step 1). It next asks whether the claim is directed to an abstract idea (Step 2A), via Prong 1, whether an abstract idea (e.g., mathematical concept, mental process, certain methods of organizing human activity) is recited, and Prong 2, whether it is integrated into a practical application. It finally asks whether the claim as a whole includes additional elements that amount to significantly more than the judicial exception (Step 2B). See MPEP 2106.
STEP 1: The claims falls within one of the four statutory categories:
All claims are directed to hardware systems, methods, and non-transitory computer media and hence fall within one of the four statutory categories.
STEP 2A PRONG 1: The claims recite a judicial exception:
Claim 1 is directed to a technique for evaluating data logs, such as ACARS data, to derive an estimate of fuel flow. Such a evaluation model is trained or compared to a ground truth fuel flow data as derive from gross weight values. As such, it is directed to a mental process, that of estimating fuel flow based on various readings based on various heuristics and adjusting such estimates and heuristics based on feedback from a different source. In particular (additional elements are underlined below):
For claim 1: a system comprising:
a memory configured to store instructions; and
one or more processors configured to:
receive a plurality of Aircraft Communication Addressing and Reporting System (“ACARS”) data packages that include a gross weight value for an aircraft (receiving data for evaluation is a mental process);
generate a first fuel flow estimate based at least on a comparison of a plurality of gross weight values for the aircraft (Evaluating differences may be performed mentally);
generate training data based on the plurality of ACARS data packages (considering the parameters of data in order to form heuristics, such as against a ground truth, may be performed mentally);
provide the training data as input to a machine learning model to generate a second fuel flow estimate (Generating, via heuristics, fuel flow estimates based on data is a mental process);
compare the first and second fuel flow estimates to generate a fuel flow error value (comparing generated estimates with derived ground truth data in order to determine error is a mental process); and
modify the machine learning model to reduce the fuel flow error value (updating model heuristics, etc. is a mental process).
For claim 3: The system of claim 2, wherein the one or more processors are configured to modify the machine learning model by modifying a network weight associated with one or more nodes of the neural network (Modifying neural network weights via optimization algorithms, such as backpropagation, is a mathematic concept).
For claim 4: The system of claim 2, wherein one or more processors are configured to modify the machine learning model by back propagation (Modifying neural network weights via optimization algorithms, such as backpropagation, is a mathematic concept).
For claim 5: The system of claim 1, wherein the one or more processors are further configured to, after modifying the machine learning model to reduce the fuel flow error value, provide the training data as input to the machine learning model to generate a third fuel flow estimate (Generating additional inferences such as via an updated heuristic model is a mental process).
For claim 6: The system of claim 5, wherein the one or more processors are further configured to generate one or more aircraft traffic management parameters based at least on the third fuel flow estimate (Generating additional parameters, such as for air traffic management, is a mental process).
For claim 7: The system of claim 5, wherein the one or more processors are further configured to generate one or more fuel planning parameters based at least on the third fuel flow estimate (Generating additional parameters, such as for air traffic management, is a mental process).
For claim 8: The system of claim 5, wherein the one or more processors are further configured to generate one or more aircraft maintenance parameters based at least on the third fuel flow estimate (Generating additional parameters, such as for air traffic management, is a mental process).
For claim 9: The system of claim 1, wherein the machine learning model is tail-specific (Generating tail-specific data-based heuristics is a mental process).
For claim 10: The system of claim 1, wherein the ACARS data package comprises flight time data, altitude data, temperature data, location data, or a combination thereof (Evaluating these parameters may be performed in the mind).
For claim 11: The system of claim 1, wherein one or more processors are configured to generate training data by removing an ACARS data package from the training data if the ACARS data package does not include a data set required for the training data (Considering subgroups of data is a mental process).
For claim 12: The system of claim 1, wherein one or more processors are further configured to receive a superset of ACARS data packages and determining whether each of the superset of ACARS data packages includes the gross weight value (Evaluating and selecting data for relevancy is a mental process).
For claim 13: The system of claim 1, wherein the ACARS data packages do not include fuel flow data (Evaluating ACARS package data is a mental process).
Claims 14-20 recite similar limitations and are hence similarly analyzed.
STEP 2A PRONG 2: The claims do not integrate the exception into a practical application:
The additional elements in claim 1-20 comprise the use of computer memory-and processor configurations and the use of machine learning models in place of mental heuristics.
However, these comprise mere instructions to implement the abstract idea on a computer or via machine learning models and hence do not comprise an integration into a practical application.
For claim 2. The additional elements comprise: wherein the machine learning model is a neural network.
However, these comprise mere instructions to implement the abstract idea on a neural network and hence do not comprise an integration into a practical application.
STEP 2B: The claim as a whole do not include additional elements that amount to significantly more than the abstract idea:
The additional elements in claim 1-20 comprise the use of computer memory-and processor configurations and the use of machine learning models in place of mental heuristics.
However, the use of general purpose processing configuration and machine learning models is well-understood, routine and conventional (WURC) and hence does not constitute significantly more.
For claim 2. The additional elements comprise: wherein the machine learning model is a neural network.
However, the use of neural networks is well-understood, routine and conventional (WURC) and hence does not constitute significantly more.
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.
Claim(s) 1, 5, 9-10, 14-16, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (CN 208188885 U) in view of Chatterji ("Fuel burn estimation using real track data", published 2011).
For claim 1, Zhang discloses: a system comprising:
a memory configured to store instructions; and
one or more processors configured to (p.4: STM32F40S is an integrated chip containing a processor and a memory, see informational reference “STM32F405/415 documentation” p.1: Cortex processor, flash memory, etc.):
receive a plurality of Aircraft Communication Addressing and Reporting System (“ACARS”) data packages that include a gross weight value for an aircraft (p.5 “Principle”: real-time ACARS data packages are received, including real time weight readings, hence, gross weight, for entry into fuel prediction model);
generate a first fuel flow estimate (ibid: a first fuel flow estimate is generated based on processing the ACARS packets);
generate training data based on the plurality of ACARS data packages (ibid: as fuel flow estimate from ACARS is used to correct fuel prediction model, this data package constitutes training data);
provide the training data as input to a machine learning model to generate a second fuel flow estimate (ibid: live fuel flow readings are provided as corrective input to a machine prediction model in order to adjust and refine the model, hence, machine learning model, the machine learning model generating additional fuel flow estimates);
compare the first and second fuel flow estimates to generate a fuel flow error value (ibid: Error values are generated based on comparison); and
modify the machine learning model to reduce the fuel flow error value (ibid: fuel model is corrected dynamically).
Zhang does not disclose: wherein the generate is based at least on a comparison of a plurality of gross weight values for the aircraft.
Chatterji discloses: wherein the generate is based at least on a comparison of a plurality of gross weight values for the aircraft (§II disclose an overall procedure for estimating fuel flow rate, the fuel flow rate based on gross weight, the calculated fuel flow rate then being fed back and subtracted from the gross weight in an iterative process; see also p.11 last ¶ describing iterative or momentary fuel flow calculation based on iterative gross weight from initial weight readings).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang by incorporating the fuel flow estimation technique of Chatterji. Both concern the art of fuel flow estimation, and the incorporation would have, according to Chatterji, establish a model for momentary fuel flow, especially when weight estimations are not available (abstract), develop better fuel estimation with fewer simplifications (p.2 ¶2), or when weight data is unavailable (p.2 ¶2), i.e., spans of time when momentary data is unavailable; to provide fuel estimates using live communicated sources (p.15: “Fuel Estimation Using ASDI Data”).
For claim 5, Zhang modified by Chatterji discloses the system of claim 1, as described above. Zhang further discloses: wherein the one or more processors are further configured to, after modifying the machine learning model to reduce the fuel flow error value, provide the training data as input to the machine learning model to generate a third fuel flow estimate (Zhang p.5 “Principle”: as the modification occurs iteratively, based on intermittent labeling data, further iterations are performed after modifications, hence, additional portions of the training data are input to the model to generate additional fuel flow estimates and corrections).
For claim 9, Zhang discloses the system of claim 1, as described above. Zhang further discloses: wherein the machine learning model is tail-specific (Zhang p.5: as live ACAR readings are used to generate the machine learning model, the model is tail specific).
For claim 10, Zhang discloses the system of claim 1, as described above. Zhang further discloses: wherein the ACARS data package comprises flight time data, altitude data, temperature data, location data, or a combination thereof (Zhang p.5: altitude).
Claims 14-16, 19-20 recite analogous methods and computer readable media as the above systems and are hence likewise rejected.
Claim(s) 2-4, 11-13, 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (CN 208188885 U) in view of Chatterji ("Fuel burn estimation using real track data", published 2011) in view of Di ("A hybrid deep neural network based on multi-time window convolutional bidirectional LSTM for civil aircraft APU hazard identification", published 2022).
For claim 2, Zhang modified by Chatterji discloses the system of claim 1, as described above. Zhang does not disclose: wherein the machine learning model is a neural network.
Di discloses: wherein the machine learning model is a neural network (p.346 fig.1 gives overview of using a neural network to process ACARS data).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the neural network technique of Di. Both concern the art of processing ACARS data, and the incorporation would have, according to Di, use an effective data-driven technique to extract and form predictions from data (p.345 col.2, §3.1 ¶1).
For claim 3, Zhang modified by Chatterji modified by Di discloses the system of claim 2, as described above. Zhang modified by Chatterji modified by Di further discloses: wherein the one or more processors are configured to modify the machine learning model by modifying a network weight associated with one or more nodes of the neural network (Di §5.1 gives overview of HDNN training via a loss function and the Adam optimizer with default optimizers, hence, adjusting weights via backpropagation with a loss function).
For claim 4, Zhang modified by Chatterji modified by Di discloses the system of claim 2, as described above. Zhang modified by Chatterji modified by Di further disclose: wherein one or more processors are configured to modify the machine learning model by back propagation (§5.1 gives overview of HDNN training via a loss function and the Adam optimizer with default optimizers, hence, adjusting weights via backpropagation with a loss function).
For claim 11, Zhang discloses the system of claim 1, as described above. Zhang does not disclose: wherein one or more processors are configured to generate training data by removing an ACARS data package from the training data if the ACARS data package does not include a data set required for the training data.
Di discloses: generate training data by removing an ACARS data package from the training data if the ACARS data package does not include a data set required for the training data (p.350 §4.1 “Data Description” discloses data preprocessing and filtering of ACARS data for a particular machine learning task, including selecting the A13 report from a large volume a ACARS data and removing irrelevant data such as ACW1, ACW2, NA, etc. Hence, training data is generated by removing data not including relevant data for training the data).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the data preprocessing of Di. Both concern the art of processing ACARS data, and the incorporation would have, according to Di, effectively obtain data related to aircraft safety and monitoring by obtaining more focused data, such as to reduce computer analysis time (p.345 col.2 ¶2, §4.1 ¶1-3).
For claim 12, Zhang discloses the system of claim 1, as described above. Zhang does not disclose: wherein one or more processors are further configured to receive a superset of ACARS data packages and determining whether each of the superset of ACARS data packages includes the gross weight value.
Di discloses: receive a superset of ACARS data packages and determining whether each of the superset of ACARS data packages includes target value (§4.1 ¶1-3: Di contemplates data preprocessing from a superset to determine whether a target A13 report is present and whether target values (see Table 2) are present relevant to a particular inference task, hence combination with Zhang yielding application to values relevant to the fuel flow task including gross weight value).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the data preprocessing of Di. Both concern the art of processing ACARS data, and the incorporation would have, according to Di, effectively obtain data related to aircraft safety and monitoring by obtaining more focused data, such as to reduce computer analysis time (p.345 col.2 ¶2, §4.1 ¶1-3).
For claim 13, Zhang discloses the system of claim 1, as described above. Zhang does not disclose: wherein the ACARS data packages do not include fuel flow data.
Di discloses: wherein the ACARS data packages do not include fuel flow data (§4.1 ¶1-3 discloses ACARS as sampling arbitrary QAR data, hence, depending on application, ACARS data may not include fuel flow data based on manually and flexibly set parameter acquisition criteria, see fig.8).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the data preprocessing of Di. Both concern the art of processing ACARS data, and the incorporation would have, according to Di, effectively obtain data related to aircraft safety and monitoring by obtaining more focused data, such as to reduce computer analysis time (p.345 col.2 ¶2, §4.1 ¶1-3).
Claims 17-18 recite analogous methods and computer readable media as the above systems and are hence likewise rejected.
Claim(s) 6-8 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (CN 208188885 U) in view of Chatterji ("Fuel burn estimation using real track data", published 2011) in view of Baumann ("Using machine learning for data-based assessing of the aircraft fuel economy", published 2019).
For claim 6, Zhang modified by Chatterji discloses the system of claim 5, as described above. Zhang modified by Chatterji does not disclose: wherein the one or more processors are further configured to generate one or more aircraft traffic management parameters based at least on the third fuel flow estimate.
Baumann discloses: wherein the one or more processors are further configured to generate one or more aircraft traffic management parameters based at least on the third fuel flow estimate (fig.1 shows dynamic fuel performance assessment being fed into recommendations for operation and maintenance, see also p.4 col.1-col.2 ¶1: using such assessments for flight planning, hence, generating flight or fuel planning parameters based on the fuel parameters; see also p.3 ¶3: using performance models for trajectory planning in air traffic management; §3 ¶2: addressing anomalies in operational flight procedures).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the flight planning parameter generation of Baumann. Both concern the art of generating dynamic fuel flow estimates, and the incorporation would have, according to Baumann, generate a data-based and aircraft specific model for more accurate diagnoses and forecasting (p.4 col.1).
For claim 7, Zhang modified by Chatterji discloses the system of claim 5, as described above. Zhang modified by Chatterji does not discloses: wherein the one or more processors are further configured to generate one or more fuel planning parameters based at least on the third fuel flow estimate.
Baumann discloses: wherein the one or more processors are further configured to generate one or more fuel planning parameters based at least on the third fuel flow estimate (fig.1 shows dynamic fuel performance assessment being fed into recommendations for operation and maintenance, see also p.4 col.1: using such assessments for flight planning, hence, generating flight or fuel planning parameters based on the fuel parameters).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the flight planning parameter generation of Baumann. Both concern the art of generating dynamic fuel flow estimates, and the incorporation would have, according to Baumann, generate a data-based and aircraft specific model for more accurate diagnoses and forecasting (p.4 col.1).
For claim 8, Zhang modified by Chatterji discloses the system of claim 5, as described above. Zhang modified by Chatterji further discloses: wherein the one or more processors are further configured to generate one or more aircraft maintenance parameters based at least on the third fuel flow estimate.
Baumann discloses: wherein the one or more processors are further configured to generate one or more aircraft traffic management parameters based at least on the third fuel flow estimate (fig.1 shows dynamic fuel performance estimate being fed into recommendations for operation and maintenance, see also p.4 col.1 ¶1: using data driven models to evaluate retrofits or modifications, p.2 col.1 ¶1: optimize performance-based modifications based on dynamic fuel consumption model).
It would have been obvious before the effective filing date to a person of ordinary skill in the art to modify the system of Zhang modified by Chatterji by incorporating the flight planning parameter generation of Baumann. Both concern the art of generating dynamic fuel flow estimates, and the incorporation would have, according to Baumann, generate a data-based and aircraft specific model for more accurate diagnoses and forecasting (p.4 col.1).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Root (US 20200273348 A1) discloses a tail-specific aircraft parameter calculation module.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LIANG LI whose telephone number is (303)297-4263. The examiner can normally be reached Mon-Fri 9-12p, 3-11p MT (11-2p, 5-1a ET).
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. The examiner is available for interviews Mon-Fri 6-11a, 2-7p MT (8-1p, 4-9p ET).
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor Jennifer Welch can be reached on (571)272-7212. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center or Private PAIR to authorized users only. Should you have questions about access to Patent Center or the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/LIANG LI/
Primary examiner AU 2143