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 . In the event the determination of the status of the application as subject to 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.
Status of Claims
Claims 1-20 are currently pending and are being hereby examined herein.
Response to Amendment / Remarks
Any reference to the prior office action refers to the non-final rejection dated 27 October 2025. The objections from the prior office action are withdrawn. The rejections under 35 U.S.C 101 from the prior office action are withdrawn. Applicant’s arguments, with respect to the prior art rejections from the prior office action, have been considered but are moot because the new ground of rejection (necessitated by amendments to the claims) does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 22 January 2026 has been considered by the Examiner.
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.
Claims 1-9, 11-17, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent No. 3,946,973 (Budway and McGlumphy, hereinafter, Budway) in view of U.S. Pub. No. 2024/0185643 (hereinafter, Joo).
Regarding Claim 1, Budway discloses A method…for operations of a classification yard (see at least column 1), comprising: generating a set of production predictions associated with one or more car events at a first point of a route within the classification yard using a production set of control parameters associated with the first point of the route, wherein the production set of control parameters includes one or more parameters associated with the rollability of one or more railcar cuts through the first point of the route (see at least columns 8-9, equation (1), and Fig. 2: “A3 and B3 - linear regression coefficients (associated with the path between D and E) that relate R3 to R1, stored constants for each path between intermediate and group retarders, and for each path between group and tangent retarders”; “R1 - measured average cut rolling resistance between locations A and B”; “G'3 - the average effective grade between locations D' and E. A stored constant for each different path between adjacent retarders based on the statistics of actual car behavior”; equation (1) solved for Vx which is cut speed at location D; based on a “target” (i.e., production prediction) travel time between locations B’ and E’); obtaining actual measurements associated with the one or more car events at the first point of the route (see at least column 3 lines 30-65, column 6 lines 45-65, and column 7 lines 20-35: “actual system performance”; “Each master, inermediate, and group retarder is supplied with control apparatus which includes a speed measuring device and a direct speed control apparatus”; “The various parameters for this cut of cars, or single car, are then measured and, together with other information previously measured or recorded, are stored in the computer as indicated by the data flow lines”; “Initial target run times are determined by simulating the behavior and control of average cuts, using assumed values of length and R, and then a final target run time is determined from statistics from actual system performance”); and
controlling operations of the classification yard for a subsequent railcar cut traveling through the first point of the route using the replaced production set of control parameters for the first point of the route to control a speed of the subsequent railcar cut traveling through the first point of the route (see at least column 3 lines 40-50 and column 4 lines 1-10; “Initial target run times are determined by simulating the behavior and control of average cuts, using assumed values of length and R, and then a final target run time is determined from statistics from actual system performance”; “The basic retarder control process is then based on determining requested exit speeds so as to make each cut of cars match its target run time from the crest to the entrance of each successive retarder through which it passes while enroute to the selected bowl storage track”).
To summarize, Budway discloses an equation for determining an exit speed at a certain point in a railroad classification yard based on a target time to travel to a subsequent location in the railroad classification yard. The equation is dependent on “constants” that are calculated parameters of the system. Budway does not explicitly disclose updating the “constants” based on the results of how long it actually takes to travel to the subsequent location in the railroad classification yard (estimating a candidate set of control parameters associated with the first point of the route based on the actual measurements associated with the one or more car events at the first point of the route; generating a set of backoffice predictions associated with the one or more car events at the first point of the route using the candidate set of control parameters associated with the first point of the route; comparing the set of production predictions associated with the one or more car events at the first point of the route and the set of backoffice predictions associated with the one or more car events at the first point of the route to determine which of the production set of control parameters or the candidate set of control parameters for the first point of the route yields more accurate predictions for the one or more car events at the first point of the route, wherein the set of backoffice predictions is generated for the one or more car events after the one or more car events have occurred using the candidate set of control parameters, and wherein comparing the set of production predictions and the set of backoffice predictions includes evaluating a predictive accuracy of the set of production predictions based on the actual measurements associated with the one or more car events, prior to replacing the production set of control parameters; determining to replace the production set of control parameters for the first point of the route with the candidate set of control parameters in response to a determination that the candidate set of control parameters yields more accurate predictions for the one or more car events at the first point of the route than the production set of control parameters). However, the invention of Budway could have been predictably improved by using machine learning to determine if other values for the so-called constants would have resulted in a more accurate determination of the true travel time based on real results (as opposed to just accepting the target travel time), and if those values for the so-called constants were more accurate, changing the control to the new, improved, more accurate, constants. Adding that modification would read on the rest of the limitations of Claim 1.
Joo, in the same field of improving models of vehicle parameters, and therefore analogous art, teaches updating variables through machine learning: …automatically tuning control parameters… estimating a candidate set of control parameters associated with the first point of the route based on the actual measurements associated with the one or more car events at the first point of the route; generating a set of backoffice predictions associated with the one or more car events at the first point of the route using the candidate set of control parameters associated with the first point of the route (see at least [0008]: “updating a linear regression model by learning the linear regression model, optimized by learning it with initial data, by use of new driving data, improving prediction accuracy of the DTE”);
comparing the set of production predictions associated with the one or more car events at the first point of the route and the set of backoffice predictions associated with the one or more car events at the first point of the route to determine which of the production set of control parameters or the candidate set of control parameters for the first point of the route yields more accurate predictions for the one or more car events at the first point of the route, wherein the set of backoffice predictions is generated for the one or more car events after the one or more car events have occurred using the candidate set of control parameters, and wherein comparing the set of production predictions and the set of backoffice predictions includes evaluating a predictive accuracy of the set of production predictions based on the actual measurements associated with the one or more car events, prior to replacing the production set of control parameters (see at least [0018], [0083], [0102]-[0104], and FIG. 4A: “the processor may be configured, if the re-learning is required, to collect driving data for a predetermined driving period, and to learn the DTE prediction model using the collected driving data”; “The processor 140 may be configured to determine whether re-learning of the DTE prediction model is required based on a difference between a prediction value of the DTE prediction model and an actual driving distance”; “determine performance of the DTE prediction model based on the loss function such as Mean Squared Error (MSE), Mean Absolute Error (MAE), or R2_score”);
determining to replace the production set of control parameters for the first point of the route with the candidate set of control parameters in response to a determination that the candidate set of control parameters yields more accurate predictions for the one or more car events at the first point of the route than the production set of control parameters (see at least [0079] and [0102]-[0104]: “The processor 140 may define the linear regression model reflecting the initial Bayesian probability distribution as a prior probability model, may be configured to generate a posterior probability model based on additionally collected driving data of the vehicle and the prior probability model, may update the posterior probability model with the linear regression model reflecting the initial Bayesian probability distribution, and may be configured to predict the DTE using a linear regression model reflecting the updated Bayesian probability distribution”; “The DTE prediction apparatus 100 utilizes a loss function to find an optimal coefficient value, and the loss function is, e.g., MSE”); and
… using the replaced production set of control parameters for the first point of the route (see at least FIG. 2).
As evidenced by Joo, one of ordinary skill in the art understands how to use machine learning to improve the accuracy of equations by replacing variables with updated variables. Specifically, one of ordinary skill in the art would have been motivated to modify Budway based on Joo because known work (i.e., the updating with machine learning of Joo) in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art. Specifically, Budway discusses market forces: smooth and continuous flow of cars in the railyard results the market-preferred optimal efficiency (see at least column 1), so one of ordinary skill in the art would have been motivated to look for ways to make the sure the equations (specifically, the constants in the equations) of Budway were the most accurate possible for optimization of the railway. One of ordinary skill would have looked to Joo and applied the machine learning solution to the equation of Budway. Therefore, the invention as claimed would have been obvious, before the effective filing date of the invention, with a reasonable expectation of success, to one having ordinary skill in the art, because one of ordinary skill in the art would have realized that confirming the true arrival timing would have been advantageous for optimization and would have wanted to update the “constants” in the equation of Budway with machine learning to improve the arrival timing calculations.
Regarding Claim 2, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Budway discloses wherein the first point of the route includes one or more of a route segment and a device of the classification yard (see at least column 2, column 5, column 7, Fig. 1, and Fig. 2: location D is a wheel detector at the end of retarder 2).
Regarding Claim 3, the Budway and Joo combination teaches the limitations of Claim 2. Furthermore, Budway discloses wherein the device of the classification yard includes one or more of: a switch; a retarder; and a wheel detector (see at least column 2, columns 5-7, Fig. 1, and Fig. 2: “This route passes in succession through four retarders, a master, an intermediate, a group, and a tangent point retarder, each shown by a conventional block. It is to be noted that the size of the block representing a particular retarder is not representative of the size or length of that retarder with relation to the others along the route. No diverging track routes are shown in this simplified sketch but track switches for diverting cars over such other routes to other bowl tracks exist between each pair of adjacent retarders. In other words, one or two switches, would be located between the master and intermediate retarders to divert cars through other intermediate retarders directed towards other selected storage tracks. Similar track switches would exist between the intermediate and group, and group and tangent point retarders. It may also be noted that, although the first three retarders are common to more than one route, each tangent retarder is used to control the car speed in a particular single bowl track such as the track BT shown immediately to the right of the tangent retarder illustrated”; “Wheel detectors for detecting the passage of each wheel-axle set of a cut of cars are shown by conventional symbols located at selected points along the route from the hump to bowl track BT”; location D is a wheel detector at the end of retarder 2).
Regarding Claim 4, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Budway discloses wherein the one or more car events include one or more of: a railroad cut traveling through the first point of the route at a first speed; the railroad cut arriving at the first point of the route at a first time; the railroad cut entering at an entry point of the first point of the route at an entry speed; and the railroad cut exiting at an exit point from the first point of the route at an exit speed (see at least column 7 lines 50-65: “The variables and constants of equation (1) are defined on the basis that it is being applied for control of retarder 2”).
Regarding Claim 5, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Budway discloses wherein the production set of control parameters for the first point of the route includes one or more of: rolling resistance coefficients; temperature coefficients; regression coefficients; switch coefficients; retarder coefficients; detector coefficients; and angle coefficients (see at least columns 8-9: “A3 and B3 - linear regression coefficients (associated with the path between D and E) that relate R3 to R1, stored constants for each path between intermediate and group retarders, and for each path between group and tangent retarders”; “R1 - measured average cut rolling resistance between locations A and B”; “G'3 - the average effective grade between locations D' and E. A stored constant for each different path between adjacent retarders based on the statistics of actual car behavior”).
Regarding Claim 6, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Joo (with the same motivation to combine as Claim 1) teaches wherein estimating the candidate set of control parameters associated with the first point of the route based on the actual measurements associated with the one or more car events at the first point of the route includes applying a regression algorithm to the actual measurements associated with the one or more car events at the first point of the route to obtain the candidate set of control parameters associated with the first point of the route (see at least [0114]: “The basic linear regression model may have different performance before and after driving, and the Bayesian linear regression model, which is the posterior probability model applied in an exemplary embodiment of the present disclosure, may collect and learn data before and after driving, and may relearn it if performance before and after driving changes.”).
Regarding Claim 7, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Budway discloses wherein one or more of the set of production predictions and the set of backoffice predictions include predictions of one or more of: energy of a railroad cut at the first point of the route; speed of the railroad cut at the first point of the route; and arrival time of the railroad cut at the first point of the route (see at least column 8 lines 5-10: “TE - The "target" travel time between locations B' and E' for the center of a cut”).
Regarding Claim 8, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Joo (with the same motivation to combine as Claim 1) teaches wherein comparing the set of production predictions associated with the one or more car events at the first point of the route and the set of backoffice predictions associated with the one or more car events at the first point of the route includes applying a statistical comparison between the set of production predictions associated with the one or more car events at the first point of the route and the set of backoffice predictions associated with the one or more car events at the first point of the route (see at least FIG. 4A).
Regarding Claim 9, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Joo teaches (with the same motivation to combine as Claim 1) wherein comparing the set of production predictions associated with the one or more car events at the first point of the route and the set of backoffice predictions associated with the one or more car events at the first point of the route includes: calculating a production absolute value average difference between the set of production predictions associated with the one or more car events at the first point of the route and the actual measurements associated with the one or more car events at the first point of the route (see at least [0116], [0149], FIG. 4A, and FIG. 4B: “FIG. 4A illustrates a probability distribution 301 of the basic linear regression equation, a probability distribution 302 of actual driving data, and a probability distribution 303 based on the Bayesian linear regression equation”; “Furthermore, the DTE prediction apparatus 100 may verify performance of the Bayesian linear model using an MSE as a loss function (S208)”);
calculating a backoffice absolute value average difference between the set of backoffice predictions associated with the one or more car events at the first point of the route and the actual measurements associated with the one or more car events at the first point of the route (see at least [0102], [0111], [0149], FIG. 4A, and FIG. 4B: “the DTE prediction apparatus 100 may collect new driving data to verify the relearned Bayesian linear model (S207). Furthermore, the DTE prediction apparatus 100 may verify performance of the Bayesian linear model using an MSE as a loss function (S208).”; “The DTE prediction apparatus 100 utilizes a loss function to find an optimal coefficient value, and the loss function is, e.g., MSE.”; “The DTE prediction apparatus 100 may collect data of an actual driving distance and DTE prediction value (predicted driving distance) for each driving cycle (driving cycle, DC, driving once), and may compare the actual driving distance with the DTE prediction value for each driving cycle”);
comparing the production absolute value average difference and the backoffice absolute value average difference to determine which one of the production absolute value average difference and the backoffice absolute value average difference is smaller; determining that the candidate set of control parameters yields more accurate predictions for car events at the first point of the route than the production set of control parameters in response to a determination that the production absolute value average difference is not smaller than the backoffice absolute value average difference for the first point of the route; and determining that the production set of control parameters yields more accurate predictions for the one or more car events at the first point of the route than the candidate set of control parameters in response to a determination that the production absolute value average difference is smaller than the backoffice absolute value average difference for the first point of the route (see at least [0062], [0079], [0102]-[0104], FIG. 4A, and FIG. 4B: “The DTE prediction apparatus 100 utilizes a loss function to find an optimal coefficient value, and the loss function is, e.g., MSE.”; “The DTE prediction apparatus 100 may input initial data as parameters of the initial linear regression model and learn it so that performance of the linear regression model may be optimized. The linear regression model may be updated if accuracy of a DTE prediction value by the linear regression model is lower than a predetermined reference value, by monitoring whether performance of the linear regression model deteriorates due to future vehicle driving, battery aging, vehicle friction change, etc.”; “The processor 140 may define the linear regression model reflecting the initial Bayesian probability distribution as a prior probability model, may be configured to generate a posterior probability model based on additionally collected driving data of the vehicle and the prior probability model, may update the posterior probability model with the linear regression model reflecting the initial Bayesian probability distribution, and may be configured to predict the DTE using a linear regression model reflecting the updated Bayesian probability distribution.”; “The DTE prediction apparatus 100 may obtain a global optimal parameter by applying a gradient descent method using a loss function.”; “determine performance of the DTE prediction model based on the loss function such as Mean Squared Error (MSE), Mean Absolute Error (MAE), or R2_score”).
Regarding Claim 11, Budway discloses A system… for operations of a classification yard, comprising: at least one processor; and a memory operably coupled to the at least one processor and storing processor-readable code that, when executed by the at least one processor, is configured to perform operations (see at least Fig. 1). All other limitations are substantially similar to Claim 1, and therefore rejected for the same reasons.
Regarding Claim 12, Claim 12 is substantially similar to Claim 2, and therefore rejected for the same reasons.
Regarding Claim 13, Claim 13 is substantially similar to Claim 4, and therefore rejected for the same reasons.
Regarding Claim 14, Claim 14 is substantially similar to Claim 5, and therefore rejected for the same reasons.
Regarding Claim 15, Claim 15 is substantially similar to Claim 6, and therefore rejected for the same reasons.
Regarding Claim 16, Claim 15 is substantially similar to Claim 7, and therefore rejected for the same reasons.
Regarding Claim 17, Claim 17 is substantially similar to Claim 9, and therefore rejected for the same reasons.
Regarding Claim 19, Budway discloses A computer-based tool … for operations of a classification yard, the computer-based tool including non-transitory computer readable media having stored thereon computer code which, when executed by a processor, causes a computing device to perform operations (see at least Fig. 1). All other limitations are substantially similar to Claim 1, and therefore rejected for the same reasons.
Regarding Claim 20, Claim 20 is substantially similar to Claim 9, and therefore rejected for the same reasons.
Claims 10 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Budway in view of Joo in further view of JP2010098849A (Yamamoto et al., hereinafter, Yamamoto).
Regarding Claim 10, the Budway and Joo combination teaches the limitations of Claim 1. Furthermore, Budway discloses. Furthermore, Budway discloses wherein the one or more car events at the first point of the route are classified into a bucket classification (see at least column 5 lines 40-65: “classify each passing car into one of a number of predetermined weight classes”). Furthermore, Joo teaches clustering classifications (see at least [0021]) and impacts on the model including seasonal impacts (see at least [0111]). The Budway and Joo combination does not explicitly teach the bucket classification including one or more of: a wet classification to classify the one or more car events occurring during wet weather conditions; a dry classification to classify the one or more car events occurring during dry weather conditions; a cold classification to classify the one or more car events occurring during cold weather conditions; a warm classification to classify the one or more car events occurring during warm weather conditions; a hot classification to classify the one or more car events occurring during hot weather conditions; and a resilience bearing type classification to classify the one or more car events associated with a railroad cut including one or more train cars having a resilience type bearing.
Yamamoto, in the same field of train controls, and therefore analogous art, teaches the bucket classification including one or more of: a wet classification to classify the one or more car events occurring during wet weather conditions; a dry classification to classify the one or more car events occurring during dry weather conditions; a cold classification to classify the one or more car events occurring during cold weather conditions; a warm classification to classify the one or more car events occurring during warm weather conditions; a hot classification to classify the one or more car events occurring during hot weather conditions; and a resilience bearing type classification to classify the one or more car events associated with a railroad cut including one or more train cars having a resilience type bearing (see at least [0024]-[0025]: separate models based on rainy / sunny / fine weather).
It would have been obvious, before the effective filing date of the invention, with a reasonable expectation of success, to one having ordinary skill in the art, to combine the teachings of Budway and Joo with one or more of the clusters taught by Yamamoto with the motivation of improving the accuracy of models under various weather conditions which are known to impact the rollability of trains (see at least Yamamoto [0004]-[0005]).
Regarding Claim 18, Claim 18 is substantially similar to Claim 10, and therefore rejected for the same reasons.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDRA ROBYN MORFORD whose telephone number is (571)272-6109. The examiner can normally be reached Monday - Friday 8:00 AM - 4:00 PM ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Thomas Worden can be reached at (571) 272-4876. 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.
/JASON HOLLOWAY/Primary Examiner, Art Unit 3658
/A.R.M./Examiner, Art Unit 3658
Prosecution Insights