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 .
Amendments
This action is in response to amendments filed December 23rd, 2025, in which Claims 1-13 are amended. Claims 14 and 15 are added. The amendments have been entered, and Claims 1-15 are currently pending.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-15 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the limitation a non-explicit parameter having no ground truth. This limitation is indefinite, because the ordinary meaning of having no ground truth contradicts the use of the term in the claims and specification, for example Claim 8 (wherein the non-explicit parameter is the congestion level at the arrival point, where one of ordinary skill of the art would understand a congestion level to have a ground truth) and [0094] (“non explicit parameter Q may be … represented by an occupancy level of the runways of the arrival airport with respect to the maximum capacity of the arrival airport, for each time slot” which clearly does have a ground truth value). Attempts to interpret the scope of the limitation in light of the specification are also indefinite, as per [0035], using the language “such as for example a parameter having no explicit formula” where “such as for example” does not clearly define a scope.
For the purpose of examination, any parameter “having no explicit formula” (for example, excluding terms like distance = velocity * time) or any “parameter computed using a data-based method” ([0035]) will be considered to be within the claim scope.
Claim 1 recites the limitations said first neural network and said second neural network. There is insufficient antecedent basis for these limitations in the claims, because the claim only previously recites a first neural network-based predictor and a second neural network-based predictor (i.e. neural network is used only as an adjective, and not a noun).
Claim 14 recites the limitation the congestion parameter. There is insufficient antecedent basis for this limitation in the claims, because the parent claims have only recited that the non-explicit parameter is a congestion level but no mention of a specific congestion parameter.
Dependent claims 2-15 are rejected for inheriting and failing to cure the indefiniteness of the independent claim.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations are: first neural network-based predictor configured to compute an estimate and second neural network-based prediction configured to compute an estimate.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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, 3, 4, and 6 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Labao et al., “Cascaded deep network systems with linked ensemble components for underwater fish detection in the wild.”
Regarding Claim 1, Labao teaches a control system (Labao, pg. 103, 1st column, 1st paragraph, “keeping track of fish stocks and population is crucial to effectively control fish harvesting”) comprising a device for predicting a value of a control variable intended to be used by said control system (Labao, pg. 105, Fig. 1 & pg. 109, Fig. 5, prediction of the “Final Object-ness probability” or number of final fish objects is the value of a control variable) the control variable depending on multiple parameters, the parameters comprising a non-explicit parameter having no ground-truth, a link between the non-explicit parameter and the parameters upon with the control variable depends being known (Labao, pg. 109, Fig. 5, “sub-feature maps after ROI crop” and “RPN roi proposals” are non-explicit parameters having no ground-truth and are known to be linked to whether the input image contains a fish or not) wherein the prediction device comprises a first neural network-based predictor configured to compute an estimate of said non-explicit parameter (Labao, pg. 109, Fig. 5, “101-layer residual network trunk” & “Dual RPN”) and a second neural network-based predictor configured to compute an estimate of the value of the control variable from the estimate of the non-explicit parameter (Labao, pg. 109, Fig. 5, “Cascade 1-7”), the two predictors receiving an input dataset (Labao, pg. 109, Fig. 5, “Input image” & pg. 109, 1st column, last paragraph, “Our training data consists of ten underwater video sequences”) each neural network being associated with a set of weights, the prediction device being configured to jointly train the two predictors, in a training phase, by applying a plurality of iterations of a single learning function to the two predictors to determine the weights of said first neural network and said second neural network, the learning function comprising a forward propagation block configured to compute, in response to the input datasets applied to the two predictors, a gradient of a minimization function for minimizing a cost function of the first predictor; and a backpropagation block, configured to update at least some weights of the neural networks of the two predictors by backpropagating the gradients computed by the forward propagation block (Labao, pg. 103, Abstract, “all components are jointly trained by backpropagation” & pg. 107, 2nd column, 2nd paragraph, “backpropagation of the gradient corrections to be passed across cascades during training” & pg. 109, 1st column, 1st paragraph, “network training is performed end-to-end for 400 epochs … In a forward pass, 4K proposals per RPN are processed” & pg. 119, 1st paragraph, “optimal network weights”) wherein the prediction device being configured to estimate the value of the control variable at a future time, in a generalization phase, after said iterations of the learning function, by applying input data to the neural networks of the two predictors using the said weights determined in the training phase (Labao, pg. 110, Section 5, “Performance – The performance of each system is measured in terms of how well each predicts the bounding box coordinates of fish objects per frame” the invention is used to make inferences after training) and wherein the control system being configured to use said estimated value of the control variable to perform a control (Labao, pg. 103, 1st column, 1st paragraph, “keeping track of fish stocks and population is crucial to effectively control fish harvesting”).
Regarding Claim 3, Labao teaches the control system as claimed in Claim 1 (and thus the rejection of Claim 1 is incorporated). Labao further teaches wherein the first predictor comprises a neural network receiving input data (Labao, pg. 109, Fig. 5, “101-layer residual network trunk” & “Dual RPN” & “Input image”).
Regarding Claim 4, Labao teaches the control system as claimed in Claim 1 (and thus the rejection of Claim 1 is incorporated). Labao further teaches wherein the first predictor comprises a set of neural networks, each receiving specific input data (Labao, pg. 109, Fig. 5, “101-layer residual network trunk” & “Input image”& “Dual RPN” & “feature map”).
Regarding Claim 6, Labao teaches the control system as claimed in Claim 1 (and thus the rejection of Claim 1 is incorporated). Labao further teaches wherein the first predictor is configured to broadcast the output value of the non-explicit parameter to external systems using communication means (Labao, pg. 106, Fig. 2, the output from the bounding box of the first predictor /RPN is displayed and must have been communicated to the external display system).
Claims 1, 5, 7, 9, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Pang et al., “A Recurrent Neural Network Approach for Aircraft Trajectory Prediction with Weather Features from Sherlock.”
Regarding Claim 1, Pang teaches a control system (Pang, Abstract, “The next generation air traffic management system …”) comprising a device for predicting a value of a control variable intended to be used by said control system (Pang, title, “Aircraft Trajectory Prediction” & Abstract, “3D prediction … 4D prediction” & pg. 9, 1st paragraph, “the first part is a 3D prediction … the second part is a 4D prediction” of latitude, longitude, and optionally altitude, and each time stamp i of the trajectory), the control variable depending on multiple parameters, the parameters comprising a non-explicit parameters having no ground-truth, a link between the non-explicit parameter and the parameters on which the control variable depends being known (Peng, pg. 8, “Architecture” Eqs. (2a-2m), where the output
h
t
is the control variable and
h
x
is a non-explicit parameter having no ground-truth as it is a hidden state of the neural network) wherein the prediction device comprises a first neural network-based predictor configured to compute an estimate of said non-explicit parameter (Peng, Peng, pg. 8, “Architecture” Eqs. (2a-2e), where non-explicit parameter
h
x
is estimated) and a second neural network-based predictor configured to estimate the value of the control variable from the estimate of the non-explicit parameter (Peng, pg. 8, “Architecture” Eqs. (2f-2m), where the output
h
t
is the control variable) the two predictors receiving an input dataset (Peng, pg. 3, last two paragraphs, “All data used in this paper are obtained from the Sherlock Data Warehouse …[including] flight summary information … flight track points … flight plan” & pg. 5, 2nd paragraph, “Weather data” & pg. 8, “The input to each LSTM fold would be the current position … and the convective weather cube”), each neural network being associated with a set of weights, the prediction device being configured to jointly train the two predictors, in a training phase, by applying a plurality of iterations of a single learning function to the two predictors to determine the weights of first neural network and said second neural network (Peng, pg. 8, last paragraph, “parameters such as weight and bias tensor are initialized” & pg. 9, 1st paragraph, “after training for 900 epochs … the optimizer used in our model is Adam”) the learning function comprising a forward propagation block configured, so as to compute, in response to input datasets applied to the two predictors, a gradient of a minimization function for minimizing a cost function of the first predictor (Peng, pg. 8, final paragraph, “The loss function is defined as the mean squared error” & Abstract, “Training with a dataset of 2528 for 500 epochs with the Adam optimizer” where Adam denotes gradients); and a backpropagation block, configured to update at least some weights of the neural networks by backpropagating the gradients computed by the forward propagation block (Peng, pg. 3, 3rd paragraph, “for the model to update in the backpropagation process”), wherein the prediction device being configured to estimate the value of the control variable at a future time, in a generalization phase, after said iterations of the learning function, by applying input data to the neural networks of the two predictors using said weights determined in the training phase (Peng, pg. 9, 1st paragraph, “Results … 25% of the data is split as the testing set” & Fig. 5, using the trained model on data to generate results) wherein the control system being configured to use said estimated value of the control variable to perform a control (Peng, Abstract, “calibrate the last on-file flight plan prior to takeoff” using the weather data).
Regarding Claim 5, Peng teaches the control system as claimed in Claim 1 (and thus the rejection of Claim 1 is incorporated). Peng further teaches wherein the second predictor is configured to apply the predicted value at input of the first prediction (Peng, pg. 8, Eq. (2e), output predicted value
h
t
is applied at input of the first predictor to compute
h
x
, see 1st paragraph, “The input to each LSTM fold would be the current prediction”).
Regarding Claim 7, Peng teaches the control system as claimed in Claim 1 (and thus the rejection of Claim 1 is incorporated). Peng further teaches wherein the control variable is the time of arrival of a given aircraft taking a trajectory between a departure point and an arrival point (Pang, title, “Aircraft Trajectory Prediction” & Abstract, “3D prediction … 4D prediction” & pg. 9, 1st paragraph, “the first part is a 3D prediction … the second part is a 4D prediction” of latitude, longitude, and optionally altitude, and each time stamp i of the trajectory, see also pg. 9, Fig. 5) the non-explicit parameter relating to the arrival point of the aircraft (the hidden state non-explicit parameter
h
x
is used to predict each point in the trajectory and is thus relating to the arrival point of the aircraft).
Regarding Claim 9, Peng teaches the control system as claimed in Claim 7 (and thus the rejection of Claim 7 is incorporated). Peng further teaches wherein the non-explicit parameter is a global delay parameter (the hidden state non-explicit parameter
h
x
is used to predict each point in the global trajectory at every time, giving delay. and is thus a global delay parameter).
Regarding Claim 15, Peng teaches the control system as claimed in Claim 1 (and thus the rejection of Claim 1 is incorporated). Peng further teaches wherein the control variable is the Estimated Time of Overflight (Peng, title, “Aircraft Trajectory Prediction” & Abstract, “4D prediction” & pg. 9, 1st paragraph, “the second part is a 4D prediction” of latitude, longitude, and altitude, at each time stamp i of the trajectory, thus giving Time of Overflight for each trajectory point).
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Roundtree, US PG Pub 2002/0002548, in view of Ng, “Sparse Autoencoder.”
Regarding Claim 1, Roundtree teaches a control system (Roundtree, [0047], “Use of actual departure and arrival times permits, for example, a traveler to make more reliable travel plans than if those plans were based solely upon the scheduled time”) comprising a device for predicting a value of a control variable intended to be used by said control system (Roundtree, title, “Arline Fight Departure and Arrival Prediction”) depending on multiple parameters (Roundtree, Abstract, “a neural network processes the structured historical and real-time data based upon the received flight information”) … wherein the prediction device comprises a first neural network-based predictor (Roundtree, Abstract, “a neural network processes the structured historical and real-time data based upon the received flight information”) … wherein the prediction device being configured to estimate the value of the control variable at a future time, in a generalization phase … by applying input data to the neural network …. (Roundtree, Abstract, “a neural network processes the structured historical and real-time data based upon the received flight information and provides predicted actual departure and arrival times”) wherein the control system being configured to use said estimated value of the control variable to perform a control (Roundtree, [0070-0071], “The system server can thus provide multiple predicted departure and arrival times … This information can be displayed in text, for example, on the display of the user device” where presenting the output on a user device is performing a control using said estimated value of the control variable).
While Roundtree uses a neural network to predict the estimated arrival time/control variable, Roundtree is silent on the training and data processing of the neural network. However, Ng teach the details of neural network training and use, including the control variable/output prediction depending on multiple parameters, the parameters comprising a non-explicit parameter having no ground-truth, a link between the non-explicit parameter and the parameters on which the control variable depends being known (Ng, pg. 3 or pg. 5, any of the hidden layer activations, say pg. 5, first paragraph,
a
(
2
)
, in the figures are non-explicit parameters having no ground truth that effect the control variable) wherein the prediction device comprise a first neural network-based predictor configured to compute an estimate of said non-explicit parameter (Ng, pg. 3, the first layer of the neural network is a first neural network-based predictor which computes said non-explicit parameter
a
(
2
)
) and a second neural network-based predictor configured to compute an estimate of the value of the control variable from the estimate of the non-explicit parameter (Ng, pg. 3, the final layer of the neural network is a second neural network-based predictor which computes the final output/estimate of the value of the control variable based on hidden layer values
a
(
2
)
/the estimate of the non-explicit parameter) each neural network being associated with a set of weights (Ng, pg. 5, first paragraph, with weights
W
(
1
)
and
W
(
2
)
for the first and second networks respectively) , the prediction device being configured to jointly train the two predictors, in a training phase, (Ng, pg. 6, 1st paragraph, “to train this network”) by applying a plurality of iterations of a single learning function to the to predictors to determine the weights of said first neural network and said second neural network (Ng, pg. 6, Section 2.2, “Backpropagation algorithm” consists of iterations, see pg. 7, 3rd paragraph, “One iteration of gradient descent updates the parameters W, b as follows”) the learning function comprising: a forward propagation block, configured to compute, in response to the input datasets applied to the two predictors, a gradient of a minimization function for minimizing a cost function of the first predictor (Ng, pg. 6, Eq. (8) is the cost function; pg. 8, 1st paragraph, Steps 1-4 “Perform a feedforward pass” & “Compute the desired partial derivatives”) and a backpropagation block, configured to update at least some weights of the neural networks of the two predictors by backpropagating the gradients computed by the forward propagation block (Ng, pg. 8, 1st paragraph, Step 3 repeated is the backwards propagation, also see last paragraph, Steps 1-3 for backpropagation to update the weights). Then, the use of the neural network for predictions in the use phase will also be after said iterations of the learning function by applying input data to the neural networks of the two predictions using said weights, i.e. Roundtree is silent on the training, but using the network after training it as per Ng teaches the limitations. It would have been obvious to one of ordinary skill in the art before the effective filing date to train a multi-layer neural network in the manner of Ng, in order to use as the neural network of Roundtree. The motivation to do so is that Roundtree needs a neural network, but is silent on how to obtain it, and Ng teaches, via university lecture notes, how to train a neural network for a specific purpose (Ng, pg. 1, “Supervised learning is one of the most powerful tools of AI”).
Regarding Claim 7, the Roundtree/Ng combination of Claim 1 teaches the control system of Claim 1 (and thus the rejection of Claim 1 is incorporated). The combination has already been shown to teach wherein the control variable is the time of arrival of a given aircraft taking a trajectory between a departure point and an arrival point (Roundtree, Abstract, “a neural network processes the structured historical and real-time data based upon the received flight information and provides predicted actual departure and arrival times”) the non-explicit parameter relating to the arrival point of the aircraft (the hidden layer activations/non-explicit parameter is used to compute the time of arrival at the arrival point of the aircraft, and is thus related to the arrival point).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Roundtree, in view of Ng, and further in view of Luo, US Patent 10,853,696.
Regarding Claim 2, the Roundtree/Ng combination of Claim 1 teaches the control system of Claim 1 (and thus the rejection of Claim 1 is incorporated). Roundtree/Ng does not teach, but Luo teaches, wherein the backpropagation block is configured to update the weights of the second predictor, while the weights of the first predictor are fixed (Luo, column 3, line 65 – column 4, line 2, “the online system generates the classification model by freezing weights in layers in a neural network prior to an output layer of the neural network and modifies weights between the output layer and an adjacent layer prior”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply Lou’s freezing training strategy to the neural network training of Roundtree/Ng. The motivation to do so that “the machine learning embedding model is more readily generalizable … improving the accuracy and applicability of the resulting classification model” (Luo, column 4, lines 26-29, i.e. freezing early layers during training is a known strategy for improving neural network performance).
Claim 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Roundtree, in view of Ng, and further in view of Ai et al, “A deep learning approach to predict the spatial and temporal distribution of flight delay in a network.”
Regarding Claim 10, the Roundtree/Ng combination of Claim 7 teaches the control system as claimed in Claim 7 (and thus the rejection of Claim 7 is incorporated). The combination has not been shown to teach, but Ai teaches the input data of the first predictor comprise features relating to said given aircraft, information relating to aircraft arriving at the arrival point, and the maximum number of aircraft associated with the arrival point (Ai, pg. 6032, “Air route congestion … The congestion of air routes connecting the airport … the number of aircraft of airport (i,j) passing though air route … Airport throughput …. Flow control” where these are relating to said given aircraft, relating to aircraft arriving at the arrival point, and related to the maximum number of aircraft at the airport). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the specific data of Ai as input for the predictions of Ng/Roundtree. The motivation to do so is that Roundtree says that many input data sources can be used (Roundtree, Abstract, “The system also retrieves real-time data that may affect the scheduled flight”) and the information of Ai does effect potential arrival times.
Regarding Claim 11, the Roundtree/Ng/Ai combination of Claim 10 teaches the control system as claimed in Claim 10 (and thus the rejection of Claim 10 is incorporated). The combination, via Ai, further teaches wherein the input data relating to aircraft arriving at the arrival point comprise the number and type of aircraft expected to land at the arrival point per time range (Ai, pg. 6032, “Air route congestion … The congestion of air routes connecting the airport … the number of aircraft of airport (i,j) passing though air route … Airport throughput”).
Claim 12 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Roundtree, in view of Ng, and further in view of Ayhan et al., “Predicting Estimated Time of Arrival for Commercial Flights.”
Regarding Claim 12, the Roundtree/Ng combination of Claim 7 teaches the control system as claimed in Claim 7 (and thus the rejection of Claim 7 is incorporated). The combination has not been shown to teach, but Ayhan teaches wherein the input data of the second predictor comprise features relating to said given aircraft, information relating to aircraft arriving at the arrival point, and capacity information associated with the arrival point (Ayhan, pg. 36, Table 2, “Flight – Airline, Flight no” & “Airport arrival count” & “Airport congestion rate”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the specific data of Ayhan as input for the predictions of Ng/Roundtree. The motivation to do so is that Roundtree says that many input data sources can be used (Roundtree, Abstract, “The system also retrieves real-time data that may affect the scheduled flight”) and the information of Ayhan does effect potential arrival times.
Regarding Claim 13, the Roundtree/Ng combination of Claim 7 teaches the control system as claimed in Claim 7 (and thus the rejection of Claim 7 is incorporated). The combination has not been shown to teach, but Ayhan teaches wherein the input data of the second predictor comprise a time slot representing the expected landing range for said given aircraft (Ayhan, pg. 36, Table 2, “Temporal – time bin”), and a history of values of the non-explicit parameter over a past time period (Ayhan, pg. 36, Table 2, “Airport congestion rate – Current vs. historical”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the specific data of Ayhan as input for the predictions of Ng/Roundtree. The motivation to do so is that Roundtree says that many input data sources can be used (Roundtree, Abstract, “The system also retrieves real-time data that may affect the scheduled flight”) and the information of Ayhan does effect potential arrival times.
Response to Arguments
Applicant’s arguments filed December 23rd, 2025, have been fully considered, but are not fully persuasive.
Applicant’s amendments have overcome the Specification Objection, 35 U.S.C. 101, and 35 U.S.C. 112(b) rejections of the previous office action, but have required additional new 35 U.S.C. 112(b) rejections to be made in this office action.
Applicant’s arguments with respect to the prior art rejections of the claims have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Specifically, each of the new references Labao, Pang, and Roundtree in combination with Ng teach a control system where two neural network-based predictors are jointly trained.
Conclusion
Claim 8 has been searched, but no combination of prior art which anticipates nor renders the claim obvious has been uncovered. Claim 14 is dependent upon Claim 8 and thus also cannot be rejected with respect to prior art statutes.
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 BRIAN M SMITH whose telephone number is (469)295-9104. The examiner can normally be reached Monday - Friday, 8:00am - 4pm Pacific.
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, Kakali Chaki can be reached at (571) 272-3719. 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.
/BRIAN M SMITH/Primary Examiner, Art Unit 2122
Prosecution Insights