DETAILED ACTION
Status of Claims
This Office action is in response to the election filed on 02/23/2026. Claims 1-17 are currently pending and are presented for examination, and claims 18-20 are withdrawn from consideration.
Election/Restrictions
Applicant’s election without traverse of Invention I (i.e., claims 1-17) in the reply filed 02/23/2026 is acknowledged.
Information Disclosure Statement
The information disclosure statement submitted on 05/21/2025 is in compliance with 37 C.F.R. 1.97 and is being considered by the examiner.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description: reference character 610 in FIG. 6.
Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
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 11-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claims do not fall within at least one of the four categories of patent eligible subject matter.
Regarding claim 11:
Claim 11 is directed toward “A machine trained to make fuel burn predictions for aircraft flight, comprising: an input engine… a prediction engine… a summation engine… and an output engine.” Under the broadest reasonable interpretation of the claim, consistent with the instant specification, this trained machine comprising the different engines appears to solely comprise software elements; it appears that none of the elements of claim 11 are required to be physical components. This interpretation is supported by ¶ 97 of the specification, which states that “The terms ‘module,’ ‘program,’ and ‘engine’ may be used to describe an aspect of computing system 900 implemented to perform a particular function. In some cases, a module, program, or engine may be instantiated via logic machine 910 executing instructions held by storage machine 920. It will be understood that different modules, programs, and/or engines may be instantiated from the same application, service, code block, object, library, routine, API, function, etc. Likewise, the same module, program, and/or engine may be instantiated by different applications, services, code blocks, objects, routines, APIs, functions, etc. The terms ‘module,’ ‘program,' and ‘engine’ may encompass individual or groups of executable files, data files, libraries, drivers, scripts, database records, etc.” Additionally, the examiner could not find anything in the specification that would require the machine or its engines to include any structural components.
MPEP 2106.03(I) states that “Non-limiting examples of claims that are not directed to any of the statutory categories include: Products that do not have a physical or tangible form, such as… a computer program per se (often referred to as ‘software per se’) when claimed as a product without any structural recitations.” Accordingly, the trained machine comprising an input engine, a prediction engine, a summation engine, and an output engine is considered software per se, which is not a “process, machine, manufacture, or composition of matter” as defined in 35 U.S.C. § 101.
The examiner respectfully suggests amending claim 11 to positively recite a structural component such as a computer processor, as would be supported by ¶ 92 of the specification.
Regarding claims 12-17:
Claims 12-17 are rejected because of their dependency upon rejected claim 11, and also because they do not positively recite any physical components to overcome the rejection.
While claim 14 specifies that the machine further comprises an “adjustment engine,” the broadest reasonable interpretation of this adjustment engine comprises software elements consistent with ¶ 97 of the specification.
While claim 15 specifies that the machine further comprises a trained encoder arranged logically upstream of a trained decoder, the broadest reasonable interpretation of the trained encoder and the trained decoder comprises software elements consistent with ¶¶ 51 and 60 of the specification.
While claim 17 specifies that the machine further comprises a fully connected layer, the broadest reasonable interpretation of the fully connected layer comprises software elements consistent with ¶¶ 49 and 60 of the specification.
Claims 1 and 4-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claims 1 and 11:
Step 1: Claim 1 is directed to a method for selecting a cruise phase route for an aircraft (i.e., a process). Claim 1 is directed to at least one of the four statutory categories.
Claim 11 is directed to the corresponding machine. As explained above, claim 11 is not directed to any of the statutory categories. However, claim 11 could potentially be amended to fall within one of the four statutory categories; for example, claim 11 could be amended to positively recite a computer processor. The remainder of the patent eligibility analysis will be performed based on the assumption that claim 11 would be amended to fall within one of the four statutory categories.
Step 2A, prong 1: Claims 1 and 11 recite the abstract concept of selecting a cruise phase route for an aircraft. This abstract idea is described at least in claims 1 and 11 by the mental process steps of, for each candidate route, predicting a sequence of fuel burn quantities based on at least the sequences of multivariate flight data and the upcoming atmospheric conditions; summing the fuel burn quantities over the candidate cruise phase route to obtain an estimated fuel burn; and indicating a preferred candidate cruise phase route having a lowest estimated fuel burn. These steps each fall into the mental processes grouping of abstract ideas as they include a human using pen and paper to assist in mentally performing mathematical calculations to predict the sequence of fuel burn quantities, sum the fuel burn quantities to obtain an estimate fuel burn, and then write down some marking that indicates which candidate cruise phase route has the lowest estimated fuel burn. The limitations as drafted are processes that, under their broadest reasonable interpretation, cover their performance in the human mind if not for the recitation of generic computing components.
Other than reciting a trained machine comprising an input engine, prediction engine, summation engine, and output engine, nothing in the recited mental process steps precludes the abstract idea from practically being performed in the human mind. If not for the “machine” and “engine” language, the claims encompass a human being mentally executing the steps with the help of pen and paper.
Step 2A, prong 2: The claims recite elements additional to the abstract concepts. However, these additional elements fail to integrate the abstract idea into a practical application.
Claim 1 recites the steps of receiving sequences of multivariate flight data from at least one prior flight; receiving a set of candidate phase routes; and receiving upcoming atmospheric conditions including at least upcoming tail winds for each of the set of candidate cruise phase routes. These steps amount to insignificant extra-solution activity, as they simply gather data necessary to perform the abstract idea (i.e., all uses of the abstract idea require such data gathering). The recitation of such insignificant extra-solution activity does not integrate the abstract idea into a practical application (see MPEP 2106.05(g)).
Claim 11 recites a trained machine comprising an input engine, prediction engine, summation engine, and output engine. These are generic computing components (in light of instant specification ¶¶ 90-97) that are simply employed as tools for performing the steps of the abstract idea. The use of such generic computing components for executing the abstract idea does not integrate the abstract idea into a practical application (see MPEP 2106.05(f)). Claim 11 further recites the steps of receiving sequences of multivariate flight data from at least one prior flight; receiving a set of candidate phase routes; and receiving upcoming atmospheric conditions including at least upcoming tail winds for each of the set of candidate cruise phase routes. These steps amount to insignificant extra-solution activity that does not integrate the abstract idea into a practical application as explained regarding claim 1 above.
Step 2B: The additional elements are re-evaluated in Step 2B to determine if they are more than what is well-understood, routine, conventional activity in the field. The instant specification provides no indication that the trained machine and its engines are anything other than conventional computing components that are used to perform the steps of the abstract idea. The mere use of such generic and conventional computing components for executing the abstract idea does not amount to significantly more than the abstract idea itself (see MPEP 2106.05(f)).
MPEP 2106.05(d)(II), and the cases cited therein, including Intellectual Ventures I, LLC v. Symantec Corp., 838 F.3d 1307, 1321 (Fed. Cir. 2016), TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610 (Fed. Cir. 2016), and OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363 (Fed. Cir. 2015), indicate that mere collection or receipt of data over a network is a well‐understood, routine, and conventional function when it is claimed in a merely generic manner (as it is here). Accordingly, the recited steps of receiving sequences of multivariate flight data from at least one prior flight; receiving a set of candidate phase routes; and receiving upcoming atmospheric conditions including at least upcoming tail winds for each of the set of candidate cruise phase routes are merely insignificant extra-solution activity that does not amount to significantly more than the abstract idea itself (see MPEP 2106.05(g)).
For the above reasons, the additional elements do not amount to significantly more than the abstract idea itself, whether considered individually or in combination. Therefore, when considering the combination of elements and the claimed invention as a whole, claims 1 and 11 are not patent-eligible.
Regarding claims 4-10 and 12-17:
Dependent claims 4-9 and 13 recite limitations that merely serve to further define the received data and the mental process steps of the independent claims. None of the limitations of claims 4-9 and 13 preclude the abstract idea from being performed in the human mind with the help of pen and paper. Accordingly, the limitations of claims 4-9 and 13 are considered as additional mental process steps.
Claim 10 recites that predicting the sequence of fuel burn quantities is further based on a hidden state of a trained machine, wherein for each of a pre-selected series of prior flights, a corresponding sequence of multivariate flight data recorded during the prior flight is processed in a trainable machine to develop the hidden state, which minimizes an overall residual for replicating the fuel burn quantities in each corresponding sequence. This amounts to general linking of the abstract idea to the technological field of machine learning. The recited features including processing multivariate data to develop a hidden state and minimize an overall residual for replicating the quantities in each sequence are central to the functioning of machine learning models, and their inclusion does not go beyond specifying at a high level that machine learning is used for predicting the sequence of fuel burn quantities. Claims 15-17 further specify that the machine further comprises a trained encoder arranged logically upstream of a trained decoder, wherein the encoder is trained to emit a vector that features an input sequence of multivariate flight data, wherein the decoder is trained to replicate the fuel burn quantities of the input sequence based on the vector, thereby generating an output sequence; that the encoder and the decoder are configured according to a long short-term memory (LSTM) architecture; and that the machine additionally comprises a fully connected layer configured to interpret the fuel burn quantities at each time step of the output sequence. The use of such a trained encoder and decoder and a fully connected layer is also central to the functioning of machine learning and does not go beyond specifying at a high level that machine learning is used for predicting the sequence of fuel burn quantities. Also, specifying the use of an LSTM architecture simply points to one commonly used type of machine learning and requires that it is used for the fuel burn prediction at a high level. Simply specifying that such machine learning is used to execute the abstract idea does not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea itself (see MPEP 2106.05(h)).
Claim 12 recites that the input engine is further configured to receive flight parameters for an aircraft, wherein each sequence of fuel burn quantities is further based on the received flight parameters for the aircraft. This amounts to additional insignificant extra-solution activity, because it is conventional data gathering that is required for the execution of the abstract idea. The recitation of such insignificant extra-solution activity does not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea itself (see MPEP 2106.05(g)).
Claim 14 specifies that the machine further comprises an adjustment engine configured to adjust a length of one or more cruise phases included in the multivariate flight data to a common cruise phase length. The step of adjusting a length of the cruise phase(s) to a common cruise phase length is another mental process step, as it could be accomplished in the human mind with the help of pen and paper. For example, a human could draw graphs showing the cruise phase(s) and adjust the length(s) until they were one common length. Additionally, the recited adjustment engine is a generic computing component (as supported by ¶¶ 90-97 of the instant specification) that merely serves as a tool for executing the abstract idea. Further, the specification provides no indication that the recited adjustment engine is anything other than a conventional computing component used to execute the abstract idea. The use of such generic and conventional computing components for performing the abstract idea does not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea itself (see MPEP 2106.05(f)).
As explained above, dependent claims 4-10 and 12-17 merely recite additional mental process steps, limitations further defining the mental process, and additional elements that amount to additional generic computing components, insignificant extra-solution activity, and general linking limitations. These additional elements fail to integrate the abstract idea into a practical application or amount to significantly more than the abstract idea itself. Therefore, when considering the combination of elements and the claimed invention as a whole, claims 4-10 and 12-17 are not patent-eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-6 and 11-12 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Cabos (US 2013/0046422 A1).
Regarding claim 1:
Cabos discloses the following limitations:
“A method for selecting a cruise phase route for an aircraft, comprising: receiving sequences of multivariate flight data from at least one prior flight.” (Cabos ¶ 17: “The ground based system receives the mission specific output data from the aircraft-based system. The mission specific output data is stored in memory of a computerised flight following system. The received data is analysed and compared with previously stored data. It is determined if the received data is different from previously stored data. If a change is required the data on board the aircraft is automatically updated. Master document lists held on both the aircraft-based and ground-based systems are resynchronized.”)
“receiving a set of candidate cruise phase routes.” (Cabos ¶ 6: “If it is determined that predefined route are available which are in accordance with over-flight permissions the predefined routes are used as a set of candidate routes for deriving a flight route.”)
“receiving upcoming atmospheric conditions including at least upcoming tail winds for each of the set of candidate cruise phase routes.” (Cabos ¶ 86: “the flight planning engine 51 examines weather data that is contained in the mission data subset and determines the strength and the direction of actual and forecast wind records and the forecast precipitation and weather conditions and warnings such as those contained in SIGMET or warnings about the presence of volcanic ash. The flight planning engine 51 calculates a preferred route of flight taking into consideration headwinds and tailwinds and areas in which significant weather is known or forecast to exist.”)
“for each candidate cruise phase route, predicting a sequence of fuel burn quantities based on at least the sequences of multivariate flight data and the upcoming atmospheric conditions.” (Cabos ¶ 90: “In an eleventh step 101, the candidate or proposed routes for the flight are processed through a vertical optimisation algorithm to determine the most suitable route in terms of, amongst other things operating performance, fuel burn and cost, taking into consideration the winds and temperatures over the route of the flight using the GRIB data from the mission data subset, and other operational factors likely to affect the flight.”)
“and summing the fuel burn quantities over the candidate cruise phase route to obtain an estimated fuel burn.” (Cabos ¶ 90: “In this eleventh step 101, fuel calculations are made with respect to the amount of fuel that may be required for the flight along the proposed routes between the departure point and the destination and to any alternate aerodromes required for operational or other considerations, calculations in relation to the amount of fuel required for the flight between specific points along a route, and calculations with respect to any reserves and/or contingency fuel and/or additional fuel.” Calculating fuel required between specific points along a route and calculating the fuel required between the departure and destination points is equivalent to summing together the sequence of fuel burn quantities to arrive at the total estimated fuel requirement as claimed.)
“and indicating a preferred candidate cruise phase route having a lowest estimated fuel burn.” (Cabos ¶ 94: “In the twelfth step 102, the most fully optimised is selected and presented to the flight crew for acceptance or for other input should they wish to do so.” Also, Cabos ¶ 13: “the optimization is configurable by adjusting the relative weight of contributing factors such as fuel consumption, cost and flight time.”)
Regarding claim 2:
Cabos discloses “The method of claim 1,” and Cabos also discloses the method “further comprising fueling the aircraft based at least on the lowest estimated fuel burn.” (Cabos ¶ 98: “the aircraft-based system may use … the communications gateway 32 to transmit a fuel order to a re-fuelling agent or other person responsible for organising the loading of the fuel onto the aircraft 11.”)
Regarding claim 3:
Cabos discloses “The method of claim 1,” and Cabos also discloses “wherein the aircraft is at least partially autonomous, the method further comprising: controlling the aircraft to follow. the preferred candidate cruise phase route.” (Cabos ¶ 14: “Further processing of the selected flight route comprises, for example, loading the flight route into a flight management computer system of the aircraft for a generation of autopilot commands during a flight using an ARINC Bus system.”)
Regarding claim 4:
Cabos discloses “The method of claim 1,” and Cabos additionally discloses “wherein each sequence of fuel burn quantities is further based on received flight parameters for the aircraft.” (Cabos ¶ 90: “The flight planning engine 51 also calculates the required fuel for a given flight route, taking into account the aircraft's 11 specifications, the aircraft's 11 weight and the weather data. The weight of the aircraft includes the weight of the aircraft and the passenger and cargo weight, which is provided as a part of the mission data subset that is received as part of the airline data.”)
Regarding claim 5:
Cabos discloses “The method of claim 1,” and Cabos additionally discloses “wherein the atmospheric conditions further include air temperature.” (Cabos ¶ 92: “The flight optimisation module 61 evaluates the output from the flight planning process in terms of the expected gross weight of the aircraft 11 which is taken from the airline data, the weather conditions 42, including winds and temperatures, restrictions imposed by NOTAM and rules and regulations as well as the cruise parameters for long range cruise (LRC), the Mach Number or, alternatively, the indicated airspeed (IAS), the fuel policies and technical data provided by the airline, such as the performance characteristics of the aircraft 11.”)
Regarding claim 6:
Cabos discloses “The method of claim 1,” and Cabos additionally discloses “wherein the atmospheric conditions further include altitude.” (Cabos ¶ 92: “The vertical optimization is carried out for each of the flight phases to determine the most appropriate heights to operate at after consideration of the take-off weight of the aircraft 11, the climb and cruise performance, headwinds or tailwinds and other operational factors, such as restrictions imposed by air traffic control or a flow management unit.”)
Regarding claim 11:
Cabos discloses “A machine trained to make fuel burn predictions for aircraft flight, comprising: an input engine … a prediction engine … a summation engine … and an output engine.” (Cabos ¶ 33: “According to the application, an operational flight plan as well as an ATC (air traffic control) flight plan is generated automatically and the ATC flight plan is send to the responsible ATC agencies.” Also, Cabos ¶¶ 56 and 81: “flight planning unit 51 comprises a user interface 58, a data output interface 59, a flight planning engine 60 that includes a flight route optimizer 61,” where “The flight planning engine commences its flight planning activities when required to do so by input from the flight crew via the user interface 58 or may be automatically activated by parameter settings in the flight planning application.” Cabos discloses the claim limitations in light of ¶ 97 of the instant specification, which states that “The terms ‘module,’ ‘program,’ and ‘engine’ may be used to describe an aspect of computing system 900 implemented to perform a particular function. In some cases, a module, program, or engine may be instantiated via logic machine 910 executing instructions held by storage machine 920. … The terms ‘module,’ ‘program,’ and ‘engine’ may encompass individual or groups of executable files, data files, libraries, drivers, scripts, database records, etc.”)
The remaining limitations of claim 11 are disclosed by Cabos using the same rationale applied to claim 11 above, mutatis mutandis.
Regarding claim 12:
Claim 12 is rejected with the same rationale applied to claim 4 above, mutatis mutandis.
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 7 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Cabos as applied to claims 1 and 11 above, and further in view of Inokuchi (US 2021/0016872 A1).
Regarding claim 7:
Cabos discloses “The method of claim 1,” but does not specifically disclose “wherein the multivariate flight data is discretized based on ranges of tail wind speeds.” However, Inokuchi does teach this limitation. (Inokuchi ¶ 25: “The control calculation unit may determine a wind speed width in a range bin from an increase in a power spectral width of scattering in the range bin as the amount of wind speed change in the radiation axis direction, and may represent a value of an intensity of a turbulence by the wind speed width.” Additionally, Inokuchi ¶ 82: “In order to calculate the mode, it is necessary to generate a histogram by dividing the observed value in a finite wind speed range, so that the resolution of the flight speed measurement value will depend on the division width of the wind speed.” Note that while Inokuchi does not explicitly mention that the wind speeds are tail wind speeds, Cabos ¶ 86 discloses the specific consideration of tailwinds.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Cabos by using discretized ranges of wind speeds as taught by Inokuchi with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Inokuchi ¶ 82 teaches that this modification allows for the data to be presented in different formats including histogram graphs. A person having ordinary skill in the art would have recognized that this would be helpful for determining approximate values of the most commonly observed wind speeds.
Regarding claim 13:
Claim 13 is rejected using the same rationale applied to claim 7 above, mutatis mutandis.
Claims 8 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Cabos as applied to claims 1 and 11 above, and further in view of Ghaemi et al. (US 2018/0003506 A1), hereinafter referred to as Ghaemi.
Regarding claim 8:
Cabos discloses “The method of claim 1,” but does not specifically disclose “wherein a length of one or more cruise phases included in the multivariate flight data is adjusted to a common cruise phase length.” However, Ghaemi does teach this limitation. (Ghaemi ¶ 23: “for a given cruise altitude and speed, determine the optimal flight path that starts at a prescribed initial altitude, speed, and weight and burns less fuel when compared to any other trajectory that starts at the same initial condition and terminates at the same cruise altitude and speed—and traverses the same horizontal distance.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Cabos by using candidate cruise phases with common lengths as taught by Ghaemi with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this upon recognizing that candidate cruise phases with common lengths could be more easily compared with one another when determining which candidate cruise phase is most optimal for final selection.
Regarding claim 14:
Cabos discloses “The machine of claim 11,” but does not specifically disclose the machine “further comprising an adjustment engine configured to adjust a length of one or more cruise phases included in the multivariate flight data to a common cruise phase length.” However, Ghaemi does teach this limitation. (Ghaemi ¶ 23: “for a given cruise altitude and speed, determine the optimal flight path that starts at a prescribed initial altitude, speed, and weight and burns less fuel when compared to any other trajectory that starts at the same initial condition and terminates at the same cruise altitude and speed—and traverses the same horizontal distance.” Additionally, Ghaemi ¶ 57: “Apparatus 500 may comprise a computing apparatus and may execute program instructions to perform any of the functions described herein. Apparatus 500 may comprise an implementation of server, a dedicated processor-enabled device, and other systems, including aircraft deployed systems and systems deployed in a ground-based control center or facility.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Cabos by using candidate cruise phases with common lengths as taught by Ghaemi with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this upon recognizing that candidate cruise phases with common lengths could be more easily compared with one another when determining which candidate cruise phase is most optimal for final selection. Additionally, it would have been obvious to use a computing apparatus to facilitate this to avoid any need for a human operator to perform intensive calculations and potentially introduce human error to the analysis.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Cabos as applied to claim 1 above, and further in view of Thorsteinsson et al. (WO 2008/096376 A1), hereinafter referred to as Thorsteinsson.
Regarding claim 9:
Cabos discloses “The method of claim 1,” but does not specifically disclose “wherein two or more candidate cruise phase routes include one or more overlapping segments.” However, Thorsteinsson does teach this limitation. (Thorsteinsson p. 12 ll. 19-27 and FIG. 6 reproduced below: “consider Figure 6, which illustrates a starting position A and a destination position B, with nine possible way points in between. Assume for the purposes of the present explanation that the region between positions A and B represent the geographical region which must be traversed, and the only possible way points are way points 11 to 33 as shown on Figure 6. For each way point 11 to 33, GRIB forecast data 402 is available in memory 40, and the vehicle energy model 404 has already been stored. The route planner controller 48 must therefore use the vehicle energy usage calculator 44 to plot the most fuel efficient route from A to B across the region, via the possible way points.” Also, Thorsteinsson 5 ll. 17-20: “Moreover, whilst in embodiments of the invention described herein we focus on vehicles such as ships, or other sea going vessels, the invention is not limited to such, and can be used to plot routes for any vehicles, such as land transport vehicles, or aircraft, for which environmental conditions play a part in their fuel usage.”)
PNG
media_image1.png
687
394
media_image1.png
Greyscale
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Cabos by considering candidate routes with overlapping segments as taught by Thorsteinsson, because this modification amounts to a combination of prior art elements according to known methods to yield predictable results (see MPEP 2143(I)(A)). Using candidate routes with overlapping segments would have predictably functioned similarly whether done within the route selection method of Thorsteinsson or whether integrated into the flight route derivation method of Cabos.
Claims 10 and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Cabos as applied to claims 1 and 11 above, and further in view of Zhu et al. (the non-patent article “Flight time prediction for fuel loading decisions with a deep learning approach”), hereinafter referred to as Zhu.
Regarding claim 10:
Cabos discloses “The method of claim 1,” but does not specifically disclose “wherein predicting the sequence of fuel burn quantities is further based on a hidden state of a trained machine, wherein for each of a pre-selected series of prior flights, a corresponding sequence of multivariate flight data recorded during the prior flight is processed in a trainable machine to develop the hidden state, which minimizes an overall residual for replicating the fuel burn quantities in each corresponding sequence.” However, Zhu does teach these limitations. (Zhu Abstract discloses a trained model for analyzing fuel burn to optimize fuel loading, and Zhu p. 7 discloses training the model to develop a “hidden state as ht∈ RM.” Also, Zhu p. 9 § 3.3: “During the training phase, we use the Adam optimization algorithm … to train our model by minimizing the mean squared error (MSE) between the predicted ŷi and the ground truth yi ∈ R.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the system of Cabos by incorporating a hidden state of a trained machine that is developed using multivariate data and that minimizes a residual for replicating the fuel burn quantities as taught by Zhu with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this since Zhu Abstract teaches that this configuration results in a trained model that can provide more accurate flight time predictions and help to optimize fuel loading and reduce fuel consumption.
Regarding claim 15:
Cabos discloses “The machine of claim 11,” but does not specifically disclose the machine “further comprising a trained encoder arranged logically upstream of a trained decoder, wherein the encoder is trained to emit a vector that featurizes an input sequence of multivariate flight data, and wherein the decoder is trained to replicate the fuel burn quantities of the input sequence based on the vector, thereby generating an output sequence.” However, Zhu does teach these limitations. (Zhu p. 4 first paragraph discloses that it is known in the art to use “a deep generative model that consists of LSTM layers as the encoder and decoder to predict aircraft trajectories.” Also, Zhu p. 9 §§ 3.3-4.1 teach to train the model by minimizing the error between the predictions and the ground truth values, where the training data includes fuel loadings and actual fuel consumption of each flight.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the system of Cabos by incorporating a model with a trained encoder and decoder for taking an input sequence and then replicating fuel burn quantities to generate an output sequence as is taught by Zhu with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this since Zhu Abstract teaches that this configuration results in a trained model that can provide more accurate flight time predictions and help to optimize fuel loading and reduce fuel consumption.
Regarding claim 16:
The combination of Cabos and Zhu teaches “The machine of claim 15,” and Zhu further teaches “wherein the encoder and the decoder are configured according to a long short-term memory (LSTM) architecture.” (Zhu p. 7 § ii: “We choose to use LSTM layer in the model because it has been shown that LSTM is effective in learning long and short temporal dependences.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Cabos by using a LSTM architecture as taught by Zhu with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Zhu p. 7 § ii teaches that “LSTM is effective in learning long and short temporal dependences.”
Regarding claim 17:
The combination of Cabos and Zhu teaches “The machine of claim 16,” and Zhu further teaches the machine “further comprising a fully connected layer configured to interpret the fuel burn quantities at each time step of the output sequence.” (Zhu p. 4 last paragraph discloses that “After concatenating the useful features extracted from original complex structured and high-dimensional inputs, a fully connected neural network is adopted for regression and outputs the predicted flight time.” Also, Zhu p. 9 § b discloses the use of a “fully connected layer (FCL)” for analyzing the output information at each interval.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Cabos by using a fully connected layer for interpreting the output information as taught by Zhu with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Zhu Abstract teaches that this configuration results in a trained model that can provide more accurate flight time predictions and help to optimize fuel loading and reduce fuel consumption.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Moser (US 2017/0032682 A1) ¶¶ 26 and 79-80 disclose a flight operations system that considers input data including wind speed, and where “Once the destination is determined, the system may calculate or otherwise measure (854) the flight distance and calculate (856) the time for the planned flight. In addition, the fuel required for the planned route may be calculated (858). … The flight may be rerun (874) at various altitudes to select to the best altitude for example, based on minimum fuel burn or minimum flight time.”
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Madison R Inserra whose telephone number is (571)272-7205. The examiner can normally be reached Monday - Friday: 9:30 AM - 6:30 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Aniss Chad can be reached at 571-270-3832. 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.
/Madison R. Inserra/Primary Examiner, Art Unit 3662