DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claim 1-15 are pending and examined herein per Applicant’s 10/24/2025 filing with the USPTO.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/24/2023 was in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea (i.e. mental processes) without practical application or significantly more when the elements are considered individually and as an ordered combination.
Step 1: Is the claimed invention to a process, machine, manufacture or composition of matter?
Yes, the claims fall within at least one of the four categories of patent eligible subject. Claims 1-5 are to a method (process), claims 6-10 are to a system (machine) and claims 11-15 are to a medium (manufacture).
Step 2A, prong 1: Does the claim recite an abstract idea, law or nature, or natural phenomenon?
Yes, the claims are found to recite an abstract idea. Specifically, the abstract idea of mental processes. Where mental processes is defined as a mental processes relates to concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III).
Claim 1 (as a representative claim) recites the following, where the limitations found to contain elements of the abstract idea are in bold italics:
1. A processor implemented method, comprising:
receiving, via one or more hardware processors, information on a) scheduled arrival time, b) actual arrival time, c) scheduled departure time, and d) actual departure time, of a plurality of vehicles for one or more scheduled trips for a plurality of stations, as training data;
identifying, via the one or more hardware processors, a set of spatiotemporal features of each of the plurality of vehicles for the plurality of stations, by processing the training data, wherein the set of spatiotemporal features comprise an arrival delay and a departure delay for the plurality of stations; and
training, via the one or more hardware processors, a chained neural network using the set of spatiotemporal features to generate a trained neural network model, wherein training the chained neural network comprising:
predicting the arrival delay and the departure delay for each of the plurality of vehicles at a first future station among a plurality of future stations in each of the one or more scheduled trips, by processing the set of spatiotemporal features using a first neural network model among a plurality of neural network models forming the chained neural network; and
predicting the arrival delay and the departure delay for each of the plurality of vehicles at one or more of a plurality of future stations subsequent to the first future station in each of the one or more scheduled trips, by each of a plurality of neural network models subsequent to the first neural network model in the chained neural network, wherein each of the plurality of neural network models subsequent to the first neural network model predicts the arrival delay and the departure delay by processing information on at least one of a) the arrival delay and departure delay at a pre-defined number of previous stations, and b) the predicted arrival delay and the predicted departure delay from a pre-defined number of previous neural network models.
It is noted that the claimed invention applies a neural network model it is not directed to the model. The claims instead are directed toward predicting of delay in arrival and departures for vehicles. A human using the power of his mind’s ability to reason could identify spatiotemporal features. Similarly given the known information (received and identified information) a person could make the claimed predictions (arrival and departure delays) using the power of the human mind’s ability to evaluate data and draw a conclusion.
Step 2A, prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No, the claimed invention does not recite additional elements that integrate the abstract idea into a practical application. Where a practical application is described as integrating the abstract idea by applying it, relying on it, or using the abstract idea in a manner that imposes a meaningful limit on it such that the claim is more than a drafting effort designed to monopolize it, see October 2019: Subject Matter Eligibility at p. 11.
The identified judicial exception is not integrated into a practical application. In particular, the claims recites the additional limitations see non-bold-italicized elements above. The receiving elements are determined to be steps of data-gathering, insignificant extra solution activity.
Where 2106.05(g) MPEP states, “term "extra-solution activity" can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim. Extra-solution activity includes both pre-solution and post-solution activity. An example of pre-solution activity is a step of gathering data for use in a claimed process, e.g., a step of obtaining information about credit card transactions, which is recited as part of a claimed process of analyzing and manipulating the gathered information by a series of steps in order to detect whether the transactions were fraudulent. An example of post-solution activity is an element that is not integrated into the claim as a whole, e.g., a printer that is used to output a report of fraudulent transactions, which is recited in a claim to a computer programmed to analyze and manipulate information about credit card transactions in order to detect whether the transactions were fraudulent.”
The Office finds that merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea; adding insignificant extra solution activity to the judicial exception; or only generally linking the use of the abstract idea to a particular technological environment or field is not sufficient to integrate the judicial exception into a practical application.
Step 2B: Does the claim recite additional elements that amount to significantly more than the abstract idea?
No, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and as part of the ordered combination. It is further noted that computing elements used to implement the claimed invention are general and generic – see instant specification “one or more hardware processors 102 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, node machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions.” (Spec. [41]).
Where 2106.05(d)(I)(2) of the MPEP states, “A factual determination is required to support a conclusion that an additional element (or combination of additional elements) is well-understood, routine, conventional activity. Berkheimer v. HP, Inc., 881 F.3d 1360, 1368, 125 USPQ2d 1649, 1654 (Fed. Cir. 2018). However, this does not mean that a prior art search is necessary to resolve this inquiry. Instead, examiners should rely on what the courts have recognized, or those in the art would recognize, as elements that are well-understood, routine, conventional activity in the relevant field when making the required determination. For example, in many instances, the specification of the application may indicate that additional elements are well-known or conventional. See, e.g., Intellectual Ventures v. Symantec, 838 F.3d at 1317; 120 USPQ2d at 1359 ("The written description is particularly useful in determining what is well-known or conventional"); Internet Patents Corp. v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1418 (Fed. Cir. 2015) (relying on specification’s description of additional elements as "well-known", "common" and "conventional"); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 614, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (Specification described additional elements as "either performing basic computer functions such as sending and receiving data, or performing functions ‘known’ in the art.").”
These limitations do NOT offer an improvement to another technology or technical field; improvements to the functioning of the computer itself; apply the judicial exception with, or by use of, a particular machine; effect a transformation or reduction of a particular article to a different state or thing; add a specific limitation other than what is well-understood, routine and conventional in the field, or add unconventional steps that confine the claim to a particular useful application; or other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment. Therefore, these additional limitations when considered individually or in combination do not provide an inventive concept that can transform the abstract idea into patent eligible subject matter.
The other independent claims recite similar limitations and are rejected for the same reasoning given above.
The dependent claims do not further limit the claimed invention in such a way as to direct the claimed invention to statutory subject matter.
Claims 2, 7, and 12 further defines the set of spatiotemporal features which adds to the identified abstract idea without practical application or significantly more.
Claims 3, 5, 8, 10, 13 and 15 further define what the model is trained to predict which adds to the identified abstract idea without practical application or significantly more. As explained above given the known information the human mind can make prediction for a plurality of stations and use characteristics to make the claimed determination.
Claims 4, 9, and 14 further define the input data for the model which adds to the identified abstract idea without practical application or significantly more.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Davidich (US 2019/0084600 A1) in view of Agrawal et al (US 2023/0244866 A1).
Claims 1, 6, and 11
Davidich teaches a processor implemented method (Davidich abstract “method determines a duration of an embarking process and/or a disembarking process of at least one autonomously movable object”), comprising:
receiving, via one or more hardware processors, information on a) scheduled arrival time, b) actual arrival time, c) scheduled departure time, and d) actual departure time, of a plurality of vehicles for one or more scheduled trips for a plurality of stations, as training data (Davidich [26] “time data mainly concern timely features and may be an input variable selected out of the group consisting of: a scheduled arrival time of the mobile unit at a station, a scheduled departure time of the mobile unit at a station, an actual arrival time of the mobile unit at a station, an actual departure time of the mobile unit at a station”);
identifying, via the one or more hardware processors, a set of spatiotemporal features of each of the plurality of vehicles for the plurality of stations, by processing the training data, wherein the set of spatiotemporal features comprise an arrival delay and a departure delay for the plurality of stations (Davidich [24] “configuration data mainly concern (a) characteristic(s), like (a) spatial or dimensional characteristic(s), of (an) element(s) or component(s) being involved in the embarking and/or disembarking process and may be an input variable selected out of the group consisting of: a location, dimension or kind of an obstacle—inside and outside of the mobile unit, a characteristic of the movable unit, like a number of wagons, a characteristic of a station of the movable unit, like in which direction the train is entering the station and thus at which side of the train the doors will open” and [40] “ the determination of the delay and/or the total delay is based on real time data as an input for the spatial discreet dynamical model.”); and
predicting the arrival delay and the departure delay for each of the plurality of vehicles at a first future station among a plurality of future stations in each of the one or more scheduled trips, by processing the set of spatiotemporal features using a first neural network model among a plurality of neural network models forming the chained neural network (Davidich [59] “ online for estimation of current delay of a train (prediction of train delay) based on a current situation”, also see [151] where the claimed invention applies to the plurality); and
predicting the arrival delay and the departure delay for each of the plurality of vehicles at one or more of a plurality of future stations subsequent to the first future station in each of the one or more scheduled trips, by each of a plurality of neural network models subsequent to the first neural network model in the chained neural network, wherein each of the plurality of neural network models subsequent to the first neural network model predicts the arrival delay and the departure delay by processing information on at least one of a) the arrival delay and departure delay at a pre-defined number of previous stations, and b) the predicted arrival delay and the predicted departure delay from a pre-defined number of previous neural network models (Davidich [139] “estimation of disembarking the train 34 is the same as described above. In this case not only the scheduled time tsa, tsd of the train 34 (when the train 34 should arrive at the station 24, 24′, 24″, 26 and leave) can be taken into account, but also the real arrival time taa, tad (instead of the scheduled time) and it can be taken into account that the train 34 is not allowed to depart earlier than the scheduled time tsd. Taking these changes into account one can easily simulate current delays Y at each station 24, 24′, 24″, 26 and predict the total delay Yt of a train ”, also see [151] where the claimed invention applies to the plurality).
Davidich further teaches a method for training a model used in the determination method (Davidich [2]) but does not expressly teach the limitation of: training, via the one or more hardware processors, a chained neural network using the set of spatiotemporal features to generate a trained neural network model, wherein training the chained neural network comprising.
Agrawal training, via the one or more hardware processors, a chained neural network using the set of spatiotemporal features to generate a trained neural network model, wherein training the chained neural network comprising (Agrawal [58] “recurrent neural network can comprise a neural network where connections between nodes form a directed or undirected graph along a temporal sequence. In further embodiments, a chained neural network can predictions of previously trained networks into a training process of new networks, forming a chain-like ensemble. In many embodiments, a HMCN can comprise a hybrid neural network comprising one or more layers from each to the above referenced types.”)
Both Davidich and Agrawal both use models to make decisions, see their respective Abstracts. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Davidich the training, via the one or more hardware processors, a chained neural network using the set of spatiotemporal features to generate a trained neural network model, wherein training the chained neural network comprising as taught by Agrawal since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
With respect to independent system claim 6 (Davidich [79] “the control center 42 contains as part of the computer 46 a determination system 48 for performing the method ”) and medium claim 11 (Davidich [57] “a computer readable medium having a computer program”), which recite substantially similar limitations as those rejected above; therefore these claims are also rejected for the same reasoning given above.
Independent system claim 6 recites the additionally taught features of one or more hardware processors; a communication interface; and a memory storing a plurality of instructions, wherein the plurality of instructions cause the one or more hardware processors to (Davidich [54] “determining system may contain a computer and may be located at and/or controlled from a control center of the network” where the computer implies the claimed hardware elements and [57] “the invention and/or the described embodiments thereof may be realised—at least partially or completely—by means of a computer readable medium having a computer program, which computer program, when executed on a computer, realizes the method according to the invention ”):
Independent claim 11 medium claim 11 recites the additionally taught features of one or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause (Davidich [57] “a computer readable medium having a computer program, which computer program, when executed on a computer”):
Claims 2, 7, and 12
Davidich in view of Agrawal teach all the limitations of the processor implemented method of claim 1, wherein set of spatiotemporal features of each of the plurality of vehicles for the plurality of stations is identified based on a travel history information of each of the plurality of vehicles obtained from at least one data source (Davidich [41] and [127-137] where disclosed distance and time are the equivalent of the claimed spatiotemporal).
With respect to system claim 7 and medium claim 12, which recite substantially similar limitations as those rejected above; therefore these claims are also rejected for the same reasoning given above.
Claims 3, 8, and 13
Davidich in view of Agrawal teach all the limitations of the processor implemented method of claim 1, wherein each of a plurality . . . models is configured to predict the arrival delay and the departure delay for one or more of the plurality of stations (Davidich [122]).
Davidich does not expressly teach that the model used in his disclosure is the claimed “a plurality of neural network models”; however Agrawal teaches, in an analogous art, the claimed element of “plurality of neural network models” (Agrawal [58]).
Both Davidich and Agrawal both use models to make decisions, see their respective Abstracts. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Davidich the plurality of neural network models as taught by Agrawal since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
With respect to system claim 8 and medium claim 13, which recite substantially similar limitations as those rejected above; therefore these claims are also rejected for the same reasoning given above.
Claims 4, 9, and 14
Davidich in view of Agrawal teach all the limitations of the processor implemented method of claim 1, Davidich does not expressly teach the following limitations, but Agrawal does teach in an analogous art the claimed limitation of wherein a chain length of the chained neural network depends on one or more characteristics of a network obtained through analysis of the training data (Agrawal [58]).
Both Davidich and Agrawal both use models to make decisions, see their respective Abstracts. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Davidich the chain length of the chained neural network depends on one or more characteristics of a network obtained through analysis of the training data as taught by Agrawal since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
With respect to system claim 9 and medium claim 14, which recite substantially similar limitations as those rejected above; therefore these claims are also rejected for the same reasoning given above.
Claims 5, 10, and 15
Davidich in view of Agrawal teach all the limitations of the processor implemented method of claim 4, Davidich does not expressly teach the following limitations, but Agrawal does teach in an analogous art the claimed limitation of wherein a final neural network model in a sequence of the plurality of neural network models forming the chained neural network is used to predict the arrival delay and the departure delay at all remaining future stations greater than the chain length for each of the plurality of vehicles in each of the one or more scheduled trips (Agrawal [58]).
Both Davidich and Agrawal both use models to make decisions, see their respective Abstracts. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Davidich the final neural network model in a sequence of the plurality of neural network models forming the chained neural network is used to predict the arrival delay and the departure delay at all remaining future stations greater than the chain length for each of the plurality of vehicles in each of the one or more scheduled trips as taught by Agrawal since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
With respect to system claim 10 and medium claim 15, which recite substantially similar limitations as those rejected above; therefore these claims are also rejected for the same reasoning given above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Regikumar et al (2023) "TrainChaiNN - A Train Delay Prediction Model Using Chained Adversarial Neural Networks," teaches TrainChaiNN, a novel chained adversarial neural network model. TrainChaiNN uses fewer features and is capable of predicting delays and the subsequent cascaded delays with high accuracy. We have benchmarked the model against three published models using nation-wide railway datasets from Belgium and the UK. The model predicts arrival and departure delays with low Mean Absolute Error (MAE) of 23 and 39 seconds for Belgium and UK datasets respectively. Applying predictions of TrainChainNN to multi-hop journey-planning more than halves delay-induced failures when compared to other models. It also outperforms other models for dealing with out-of-distribution data and for predicting rarely occurring major delays.
Pineda-Jaramillo et al (2023) "Short-Term Arrival Delay Time Prediction in Freight Rail Operations Using Data-Driven Models" teaches goal of this study is to investigate a set of data-driven models for the short-term prediction of arrival delay time using data from the National Railway Company of Luxembourg of freight rail operations between Bettembourg (Luxembourg) and other nine terminal stations across the EU, and then investigate the effects of the features associated with the arrival delay time. For our dataset, the lightGBM model outperformed other models in predicting the arrival delay time in freight rail operations, with departure delay time, trip distance, and train composition appearing to be the most influential features in predicting the arrival delay time in the short-term.
Wang et al (2019) “Train delay analysis and prediction based on big data fusion” teaches Length of a train delay propagation chain: The total number of trains in the consecutive train delay sequence at each station.
Regikumar et al (US 2024/0112096 A1) teaches a system and method for delay prediction for scheduled public transport. A multi-architectural deep learning approach has been used to predict the delays of a queried vehicle in the scheduled public transport. For this, historical operational data is transformed into temporal, and spatiotemporal data.
Jorgensen et al (US 2022/0215760 A1) teaches predicting a flight arrival time of a given aircraft flight, between an origin airport and a destination airport, of a given aircraft based on a set of features. The method comprises determining a predicted time delay of a flight departure time of the given aircraft flight from the origin airport.
Adachi et al (US 2015/0317558 A1) teaches the maximum chain lengths of chains used for each neural network are listed. For example, for a neural network having a neural network parameter of 4/4/4/4/4, the neural network includes five layers and each layer includes four nodes, and the total number of nodes.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to FOLASHADE ANDERSON whose telephone number is (571)270-3331. The examiner can normally be reached Monday to Thursday 12:00 P.M. to 6:00 P.M. CST.
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, Rutao Wu can be reached at (571) 272-6045. 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.
/FOLASHADE ANDERSON/Primary Examiner, Art Unit 3623