DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This final office action is in response to the amendment filed 2 February 2026.
Claims 1-4, 6-12, and 14-22 are pending. Claims 21-22 are newly added. Claims 1, 9, and 17 are independent claims.
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.
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, 3, 6-7, 9, 11, 14-15, and 17-22 are rejected under 35 U.S.C. 103 as being unpatentable over Fowe et al. (US 2017/0004707, published 5 January 2017, hereafter Fowe) and further in view of Nunkesser et al. (US 11441918, 371 date 27 February 2019, hereafter Nunkesser) and further in view of Ghosh et al. (US 2020/0111005, filed 19 December 2018, hereafter Ghosh) and further in view of Jorgueski et al. (WO 2019/121537, published 27 June 2019, hereafter Jorgueski) and further in view of Fowe (US 2019/0279502, published 12 September 2019, hereafter Fowe 502) and further in view of Sajjadi Mohammadabadi et al. (US 2020/0293796, published 17 September 2020, hereafter Sajjadi Mohammadabadi)
As per independent claim 1, Fowe discloses a computer implemented method for predicting a traffic pattern for a road segment (paragraph 0005), the computer-implemented method comprising:
aggregating, based on a distribution of speeds associated with location probe points representative of travel of vehicles along the road segment during an interval of time (paragraph 0043), first traffic data for an upstream road segment of the road segment (paragraph 0054)
aggregating, based on the distribution of speeds associated with the location probe points for the vehicles (paragraph 0043), second traffic data for a first downstream road segment of the road segment (paragraph 0037)
aggregating, based on the distribution of speeds associated with the location probe points for the vehicles (paragraph 0043), third traffic data for a second downstream road segment of the road segment (paragraph 0054)
determining at least one traffic event classification for a divergence in the road segment between (i) a first portion of the road segment comprising the upstream road segment and (ii) a second portion of the road segment comprising the first downstream road segment and the second downstream road segment (paragraph 0041)
a first set of traffic data, a second set of traffic data, and a third set of traffic data (paragraph 0054: Here, traffic data associated with a first traffic data (S1) is an upstream road segment; data associated with a second traffic data (S2) is a downstream road segment; data associated with a third traffic data (S3) is a downstream road segment where the second traffic data (S2) and third traffic data (S3) represent diverging road segments)
Fowe fails to specifically disclose:
generating a first training dataset associated with the first speed classification based on the first aggregated data
generating a second training dataset associated with the second speed classification based on the second aggregated data
training a machine learning model by inputting (i) the first training dataset associated with the first speed classification and (ii) the speed training dataset associated with the second speed classification to the machine learning model, wherein the training enables the machine learning model to predict a traffic event classification
However, Nunkesser, which is analogous to the claimed invention because it is directed toward predicting traffic data based upon a machine learning model, discloses:
generating a first training dataset associated with the first speed classification based on the first aggregated data (Figure 6, item 230; Figure 9, item 342; column 17, line 66- column 18, line 22: Here, a first training dataset, first tracking data, is used to train the model)
generating a second training dataset associated with the second speed classification based on the second aggregated data (Figure 6, items 232 and 234; Figure 9, item 344; column 18, lines 23-31: Here, a second training dataset, second tracking data, is used to train the model)
training a machine learning model by inputting (i) the first training dataset associated with the first speed classification and (ii) the speed training dataset associated with the second speed classification to the machine learning model, wherein the training enables the machine learning model to predict a traffic event classification (Figure 9, item 346; column 18, lines 32-62: Here, the machine learning model is trained using both datasets to predict speed for the particular vehicle type based upon the two training datasets)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed for various vehicle types across a road segment (Nunkesser: column 18, lines 40-62).
Further, Fowe fails to specifically disclose training a machine learning model based on first-order logic associated with a set of logic rules for different sets of data.
However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on first-order logic associated with a set of logic rules for different sets of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with Fowe-Nunkesser, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
Fowe fails to specifically disclose:
determining first aggregated data comprising a first portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies first clustering criterion for a first type of speed cluster associated with a first speed classification
determining second aggregated data comprising a second portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies second clustering criterion for a second type of speed cluster associated with a second speed classification
wherein the first portion of the road segment comprises the upstream road segment and wherein the second portion of the road segment comprises the first downstream road segment and the second downstream road segment
However, Jorgueski, which is analogous to the claimed invention because it is directed toward clustering data based upon directional information, discloses:
determining first aggregated data comprising a first portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies first clustering criterion for a first type of speed cluster associated with a first speed classification (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
determining second aggregated data comprising a second portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies second clustering criterion for a second type of speed cluster associated with a second speed classification (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
wherein the first portion of the road segment comprises the upstream road segment and wherein the second portion of the road segment comprises the first downstream road segment and the second downstream road segment (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Jorgueski with Fowe-Nunkesser-Ghosh, with a reasonable expectation of success, as it would have allowed for segmenting data to avoid unnecessary processing (Jorgueski: paragraph 0009). Specifically, by grouping and separating data into different channels, only those channels of interest would be required to be processed at a client device for providing traffic data, thereby reducing unnecessary processing activity (Jorgueski: paragraph 0011).
Additionally, Fowe fails to specifically disclose determining distance interval data comprising a first distance interval associated with the upstream road segment, a second distance interval associate with the first downstream road segment, and a third distance interval associate with the second downstream road segment. However, Fowe 502, which is analogous to the claimed invention because it is directed toward determining upstream and downstream road conditions to identify merging traffic, discloses determining distance interval data comprising a first distance interval associated with the upstream road segment, a second distance interval associate with the first downstream road segment, and a third distance interval associate with the second downstream road segment (paragraphs 0035-0039). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 502 with Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have improved the ability to identify and predict upstream/downstream road conditions to improve predicting traffic patterns. This would have allowed for improved travel time predictions for end users.
Finally, Fowe fails to specifically disclose a third training dataset associated with the distance interval, training a machine learning model by inputting the third training dataset associated with the distance interval, and predict a traffic event classification based on the third training dataset associated with the distance interval data.
However, Sajjadi Mohammadabadi, with is analogous to the claimed invention because it is directed toward using a deep neural network to train and use distance data (paragraph 0023: Here, an intersection is classified by training the machine learning model to predict distances to intersections), discloses a third training dataset associated with the distance interval (paragraph 0051: Here, a training dataset is derived from the sensor data to train the model to compute distances to intersections), training a machine learning model by inputting the third training dataset associated with the distance interval, and predict a traffic event classification based on the third training dataset associated with the distance interval data (Figure 6, item B608; paragraph 0084: Here, the neural network computes data representative of the distance to at least one or more intersections/distances). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Sajjadi Mohammadabadi with Fowe-Nunkesser-Ghosh-Jorjueski-Fowe 502, with a reasonable expectation of success, as it would have allowed for generating training data and training a model based upon the distance to an intersection in order to identify and train a model to identify intersections (Sajjadi Mohammadabadi: paragraph 0051).
As per dependent claim 3, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Fowe discloses providing a first average speed associated with the first traffic data, a second average speed associated with the second traffic data, and a third average speed associated with traffic data (paragraphs 0059).
Fowe fails to specifically disclose training, based on the first traffic data, the second traffic data, and the third traffic data, a machine learning model that predicts the traffic pattern for the road segment.
However, Nunkesser, which is analogous to the claimed invention because it is directed toward predicting traffic data based upon a machine learning model, discloses training, based on traffic data, a machine learning model that predicts traffic pattern for a road segment (Figures 6 and 9; column 1, lines 32-53). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
As per dependent claim 6, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Nunkesser discloses training a machine learning model to perform traffic predictions (Figures 6 and 9). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe, Nunkesser, and Ghosh, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
Fowe fails to specifically disclose identifying an intersection between the upstream road segment and the downstream road segment. However, Fowe 502 discloses identifying an intersection between an upstream road segment and the downstream road segment (paragraphs 0035-0037). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 297 with Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have provided further characterization of traffic patterns for analysis by a machine learning model. This would have improved identification and prediction based upon these different types of traffic patterns.
As per dependent claim 7, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Nunkesser discloses wherein the machine learning model predicts an average speed of vehicles on the road segment (Figure 6). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
With respect to claims 9, 11, and 14-15, the applicant discloses the limitations substantially similar to those in claims 1, 3, and 6-7, respectively. Claims 9, 11, and 14-15 are similarly rejected.
As per independent claim 17, Fowe discloses a computer-implemented method for predicting a traffic pattern for a road segment, the computer-implemented method comprising:
aggregating data based on first traffic data for a road segment, second traffic data for the first road segment, and third traffic data for the second road segment, wherein the first traffic data, the second traffic data, and the third traffic data are determined based on a distribution of speeds associated with location prove points representative of travel of vehicles along the road segment during an interval of time (paragraphs 0037, 0043, and 0054)
a first set of traffic data, a second set of traffic data, and a third set of traffic data (paragraph 0054: Here, traffic data associated with a first traffic data (S1) is an upstream road segment; data associated with a second traffic data (S2) is a downstream road segment; data associated with a third traffic data (S3) is a downstream road segment where the second traffic data (S2) and third traffic data (S3) represent diverging road segments)
Fowe fails to specifically disclose:
determining distance interval data comprising a first distance interval associated with the upstream road segment, a second distance interval associate with the first downstream road segment, and a third distance interval associate with the second downstream road segment
generating a first training dataset associated with the first speed classification based on the first aggregated data
generating a second training dataset associated with the second speed classification based on the second aggregated data
training a machine learning model by inputting (i) the first training dataset associated with the first speed classification and (ii) the speed training dataset associated with the second speed classification to the machine learning model, wherein the training enables the machine learning model to predict a traffic event classification
However, Nunkesser, which is analogous to the claimed invention because it is directed toward predicting traffic data based upon a machine learning model, discloses:
generating a first training dataset associated with the first speed classification based on the first aggregated data (Figure 6, item 230; Figure 9, item 342; column 17, line 66- column 18, line 22: Here, a first training dataset, first tracking data, is used to train the model)
generating a second training dataset associated with the second speed classification based on the second aggregated data (Figure 6, items 232 and 234; Figure 9, item 344; column 18, lines 23-31: Here, a second training dataset, second tracking data, is used to train the model)
training a machine learning model by inputting (i) the first training dataset associated with the first speed classification and (ii) the speed training dataset associated with the second speed classification to the machine learning model, wherein the training enables the machine learning model to predict a traffic event classification (Figure 9, item 346; column 18, lines 32-62: Here, the machine learning model is trained using both datasets to predict speed for the particular vehicle type based upon the two training datasets)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed for various vehicle types across a road segment (Nunkesser: column 18, lines 40-62).
Further, Fowe fails to specifically disclose training a machine learning model based on first-order logic associated with a set of logic rules for different sets of data.
However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on first-order logic associated with a set of logic rules for different sets of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with Fowe-Nunkesser, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
Additionally, Fowe 502 discloses identifying an intersection between an upstream road segment and the downstream road segment (paragraphs 0035-0037) and discloses determining distance interval data comprising a first distance interval associated with the upstream road segment, a second distance interval associate with the first downstream road segment, and a third distance interval associate with the second downstream road segment (paragraphs 0035-0039).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 502 with Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have improved the ability to identify and predict upstream/downstream road conditions to improve predicting traffic patterns. This would have allowed for improved travel time predictions for end users.
Fowe fails to specifically disclose:
determining first aggregated data comprising a first portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies first clustering criterion for a first type of speed cluster associated with a first speed classification
determining second aggregated data comprising a second portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies second clustering criterion for a second type of speed cluster associated with a second speed classification
wherein the first portion of the road segment comprises the upstream road segment and wherein the second portion of the road segment comprises the first downstream road segment and the second downstream road segment
However, Jorgueski, which is analogous to the claimed invention because it is directed toward clustering data based upon directional information, discloses:
determining first aggregated data comprising a first portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies first clustering criterion for a first type of speed cluster associated with a first speed classification (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
determining second aggregated data comprising a second portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies second clustering criterion for a second type of speed cluster associated with a second speed classification (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
wherein the first portion of the road segment comprises the upstream road segment and wherein the second portion of the road segment comprises the first downstream road segment and the second downstream road segment (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Jorgueski with Fowe-Nunkesser-Ghosh, with a reasonable expectation of success, as it would have allowed for segmenting data to avoid unnecessary processing (Jorgueski: paragraph 0009). Specifically, by grouping and separating data into different channels, only those channels of interest would be required to be processed at a client device for providing traffic data, thereby reducing unnecessary processing activity (Jorgueski: paragraph 0011).
Finally, Fowe fails to specifically disclose a third training dataset associated with the distance interval, training a machine learning model by inputting the third training dataset associated with the distance interval, and predict a traffic event classification based on the third training dataset associated with the distance interval data.
However, Sajjadi Mohammadabadi, with is analogous to the claimed invention because it is directed toward using a deep neural network to train and use distance data (paragraph 0023: Here, an intersection is classified by training the machine learning model to predict distances to intersections), discloses a third training dataset associated with the distance interval (paragraph 0051: Here, a training dataset is derived from the sensor data to train the model to compute distances to intersections), training a machine learning model by inputting the third training dataset associated with the distance interval, and predict a traffic event classification based on the third training dataset associated with the distance interval data (Figure 6, item B608; paragraph 0084: Here, the neural network computes data representative of the distance to at least one or more intersections/distances). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Sajjadi Mohammadabadi with Fowe-Nunkesser-Ghosh-Jorjueski-Fowe 502, with a reasonable expectation of success, as it would have allowed for generating training data and training a model based upon the distance to an intersection in order to identify and train a model to identify intersections (Sajjadi Mohammadabadi: paragraph 0051).
As per dependent claim 18, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 17, and the same rejection is incorporated herein. Nunkesser discloses facilitating a routing of a vehicle based on the machine learning model (Figures 3-4). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
As per dependent claim 19, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 17, and the same rejection is incorporated herein. Nunkesser discloses causing rendering of a navigation route via a map display based on the machine learning model (Figures 3-4). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
As per dependent claim 20, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 17, and the same rejection is incorporated herein. Nunkesser discloses wherein the predicting includes predicting an average speed of vehicles on the road segment based on the machine learning model (Figure 6). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
As per dependent claim 21, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Fowe discloses wherein the traffic event classification corresponds to a highway congestion even or a ramp congestion event associate with the road segment (paragraph 0035: Here, a split lane congestion event is determined. This congestion may be identified with respect to ramps and/or highways (Figure 6)).
As per dependent claim 22, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Fowe discloses wherein the traffic event classification corresponds to a particular traffic event classification that is selected from a plurality of traffic event classifications comprising at least a first traffic event classification, and a second traffic event classification, and a third traffic event classification (paragraph 0054: Here, traffic data associated with a first traffic data (S1), a second traffic data (S2), and a third traffic data (S3), is used to identify a traffic event classification (paragraph 0035)).
Claims 2, 4, 8, 10, 12, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi and further in view of Fowe (US 2018/0033297, published 1 February 2018, hereafter Fowe 297).
As per dependent claim 2, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Nunkesser discloses providing traffic profile information as input for the machine learning model (Figures 6 and 9). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
However, Fowe fails to specifically disclose determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data. However, Fowe 297, which is analogous to the claimed invention because it is directed toward utilizing data for traffic conditions, discloses determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data (paragraph 0032). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 297 with Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have provided further characterization of traffic patterns for analysis by a machine learning model. This would have improved identification and prediction based upon these different types of traffic patterns.
As per dependent claim 4, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Nunkesser, which is analogous to the claimed invention because it is directed toward predicting traffic data based upon a machine learning model, discloses training, based on traffic data, a machine learning model that predicts traffic pattern for a road segment (Figures 6 and 9; column 1, lines 32-53). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
Fowe fails to specifically disclose providing a first number of vehicles associated with the first traffic data, a second number of vehicles associated with the second traffic data, and a third number of vehicles associated with the third traffic data. However, Fowe 297 discloses providing a first number of vehicles associated with the first traffic data, a second number of vehicles associated with the second traffic data, and a third number of vehicles associated with the third traffic data (paragraph 0035-0037). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 297 with Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have provided further characterization of traffic patterns for analysis by a machine learning model. This would have improved identification and prediction based upon these different types of traffic patterns.
As per dependent claim 8, Fowe, Nunkesser, Ghosh, Jorgueski, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Nunkesser discloses training a machine learning model to perform traffic predictions (Figures 6 and 9). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
Fowe fails to specifically disclose a number of vehicles on the road segment. However, Fowe 297 discloses determining a number of vehicles on the road segment (paragraphs 0035-0037). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 297 with Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have provided further characterization of traffic patterns for analysis by a machine learning model. This would have improved identification and prediction based upon these different types of traffic patterns.
With respect to claims 10, 12, and 16, the applicant discloses the limitations substantially similar to those in claims 2, 4, and 8, respectively. Claims 10, 12, and 16 are similarly rejected.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-4, 6-12, and 14-20 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-3, 5-7, and 12 of copending Application No. 17/132,758 (US 2022/0198923) in view of Fowe and further in view of Ghosh and further in view of Jorgueski and further in view of Nunkesser and further in view of Fowe 502, and further in view of Sajjadi Mohammadabadi. Although the claims at issue are not identical, they are not patentably distinct from each other because the copending application recites limitations which are substantially similar to those within the present application.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Current application:
Co-pending application:
1. A computer-implemented method for predicting a traffic pattern for a road segment, the computer-implemented method comprising:
aggregating, based on a distribution of speeds associated with location probe points representative of travel of vehicles along the road segment during an interval of time, first traffic data for an upstream road segment of the road segment;
aggregating, based on the distribution of speeds associated with the location probe points for vehicles, second traffic data for a first downstream road segment of the road segment;
the second traffic data, and the third traffic data
1. A computer-implemented method for determining a split lane traffic pattern for a road segment, the computer-implemented method comprising:
aggregating, based on a distribution of speeds associated with location probe points representative of travel of vehicles along the road segment during an interval of time, the first traffic data for an upstream road segment of the road segment;
aggregating, based on the distribution of speeds associated with the location probe points for the vehicle, the second traffic data for a first downstream road segment of the road segment;
aggregating, based on the distribution of speeds associated with the location probe points for the vehicles, third traffic data for a second downstream road segment for the road segment; and
2. The computer-implemented method, further comprising: determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic, data and the third traffic data
1. (continued)
determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data.
3. The computer-implemented method, wherein… providing a first average speed associated with the first traffic data, a second average speed associated with the second traffic data, and a third average speed associated with the third traffic data as input
determine the at least one traffic event classification for the divergence in the road segment between (i) the first portion of the road segment and (ii) the second portion of the road segment.
2. The method wherein the determining the traffic classification profile comprises determining the traffic classification profile based on a first average speed associated with the first traffic data, a second average speed associated with the second traffic data, and a third average speed associated with the third traffic data.
1. (continued)
determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data.
4. The computer-implemented method wherein providing a first number of vehicles associated with the first traffic data, a second number of vehicles associated with the second traffic data, and a third number of vehicles associated with the third traffic data as input for the machine learning model to determine the at least one traffic event classification for the divergence in the road segment between (i) the first portion of the road segment and (ii) the second portion of the road segment.
5. The computer-implemented method wherein the determining the traffic classification profile comprises determining the traffic classification profile based on a first number of vehicles associated with the first traffic data, a second number of vehicles associated with the second traffic data, and a third number of vehicles associated with the traffic data.
1. (continued)
determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data.
5. (cancelled)
6. The computer-implemented method wherein the determining the traffic classification profile comprises determining the traffic classification profile based on a first distance interval associated with the upstream road segment, a second distance interval associated with the first downstream road segment, and a third distance interval associated with the second downstream road segment.
1. (continued)
determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data.
6. The computer-implemented method wherein the divergence in the road segment corresponds to an intersection in a road segment between (i) the first portion of the road segment and (ii) the second portion of the road segment.
7. The computer-implemented method wherein the determining the traffic classification profile comprises classifying the road segment as a ramp (Here, the examiner interprets a ramp as an intersection)…
1. (continued)
determining a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data, and the third traffic data.
8. The computer-implemented method wherein the machine learning model predicts a number of vehicles on the road segment.
5. The computer-implemented method wherein the determining the traffic classification profile comprises determining the traffic classification profile based on a first number of vehicles associated with the first traffic data, a second number of vehicles associated with the second traffic data, and a third number of vehicles associated with the traffic data.
17. A computer-implemented method for predicting a traffic pattern for a road segment, the computer-implemented method comprising:
identifying an intersection between (i) a portion of a road segment comprising an upstream road segment of the road segment and (ii) a second portion of the road segment comprising a first downstream road segment of the road segment and a second downstream road segment of the road segment
at least one traffic event classification associated with the intersection between (i) the first portion of the road segment comprising the upstream road segment and (ii) the second portion of the road segment comprising the first downstream road segment and the second downstream road segment,
and wherein the first traffic data, the second traffic data, and the third traffic data are determined based on a distribution of speeds associated with location probe points representative of travel of vehicles along the road segment during an interval of time.
An apparatus configured to determine a split lane traffic pattern for a road segment…
aggregate, based on a distribution of speeds associated with location probe points representative of travel of vehicles along the road segment during an interval of time
aggregate, based on the distribution of speeds associated with the location probe points for the vehicles, second traffic data for a first downstream road segment of the road segment
aggregate, based on the distribution of speeds associated with the location probe points for the vehicles, third traffic data for a second downstream road segment of the road segment
determine a traffic classification profile for the road segment based on statistical analysis of the first traffic data, the second traffic data and the third traffic data.
6. … wherein the determining the traffic classification profile comprises determining the traffic classification profile based on a first distance interval associated with the upstream road segment, a second distance interval associated with the first downstream road segment, and a third distance interval associated with the second downstream road segment
20. The computer-implemented method wherein the predicting the at least one traffic event classification associated with the intersection comprises predicting an average speed of vehicles on the road segment.
3. The method further comprising partitioning the distribution of speeds associated with the upstream road segment and the first downstream road segment into respective speed clusters to facilitate determining the first average speed associated with the first traffic data and the second average speed associated with the second traffic data.
With respect to claim 1, the patent fails to specifically disclose:
wherein the divergence in the road segment is between (i) a first portion of the road segment comprising the upstream road segment and (ii) a second portion of the road segment comprising the first downstream road segment and the second downstream road segment.
training a machine learning model that determines at least one classification for a divergence in the road segment based on a first-order logic associated with a set of logic rules for the first traffic data
However, Fowe discloses determining at least one traffic event classification for a divergence in the road segment between (i) a first portion of the road segment comprising the upstream road segment and (ii) a second portion of the road segment comprising the first downstream road segment and the second downstream road segment (paragraph 0041). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with the copending application, with a reasonable expectation of success, as it would have allowed for classifying segments as upstream/downstream. This would have facilitated training the ML model using upstream/downstream segments in order to improve traffic identification.
Additionally, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on first-order logic associated with a set of logic rules for different sets of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
Additionally, Fowe fails to specifically disclose:
determining first aggregated data comprising a first portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies first clustering criterion for a first type of speed cluster associated with a first speed classification
determining second aggregated data comprising a second portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies second clustering criterion for a second type of speed cluster associated with a second speed classification
wherein the first portion of the road segment comprises the upstream road segment and wherein the second portion of the road segment comprises the first downstream road segment and the second downstream road segment
However, Jorgueski, which is analogous to the claimed invention because it is directed toward clustering data based upon directional information, discloses:
determining first aggregated data comprising a first portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies first clustering criterion for a first type of speed cluster associated with a first speed classification (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
determining second aggregated data comprising a second portion of (a) the first traffic data, (b) the second traffic data, and (c) the third traffic data that satisfies second clustering criterion for a second type of speed cluster associated with a second speed classification (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
wherein the first portion of the road segment comprises the upstream road segment and wherein the second portion of the road segment comprises the first downstream road segment and the second downstream road segment (paragraphs 0012-0015: Here, a vehicle provides Cooperative Awareness Messages (CAM) including location, velocity, and heading to a server (paragraphs 0004-0005). Data from the CAM messages are aggregated and grouped (clustered) by road and travel direction based upon the provided travel information (paragraph 0012). This aggregated data includes traffic data from a plurality of different road segments and travel directions (paragraph 0024). Each of these roads segments constitutes one of the first, second, and third traffic data. Additionally, the directional information is analogous to the claimed upstream and downstream traffic data)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Jorgueski with Fowe-Ghosh, with a reasonable expectation of success, as it would have allowed for segmenting data to avoid unnecessary processing (Jorgueski: paragraph 0009). Specifically, by grouping and separating data into different channels, only those channels of interest would be required to be processed at a client device for providing traffic data, thereby reducing unnecessary processing activity (Jorgueski: paragraph 0011).
Additionally, the copending application fails to specifically disclose:
generating a first training dataset associated with the first speed classification based on the first aggregated data
generating a second training dataset associated with the second speed classification based on the second aggregated data
training a machine learning model by inputting (i) the first training dataset associated with the first speed classification and (ii) the speed training dataset associated with the second speed classification to the machine learning model, wherein the training enables the machine learning model to predict a traffic event classification
However, Nunkesser, which is analogous to the claimed invention because it is directed toward predicting traffic data based upon a machine learning model, discloses:
generating a first training dataset associated with the first speed classification based on the first aggregated data (Figure 6, item 230; Figure 9, item 342; column 17, line 66- column 18, line 22: Here, a first training dataset, first tracking data, is used to train the model)
generating a second training dataset associated with the second speed classification based on the second aggregated data (Figure 6, items 232 and 234; Figure 9, item 344; column 18, lines 23-31: Here, a second training dataset, second tracking data, is used to train the model)
training a machine learning model by inputting (i) the first training dataset associated with the first speed classification and (ii) the speed training dataset associated with the second speed classification to the machine learning model, wherein the training enables the machine learning model to predict a traffic event classification (Figure 9, item 346; column 18, lines 32-62: Here, the machine learning model is trained using both datasets to predict speed for the particular vehicle type based upon the two training datasets)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Nunkesser with the copending application, with a reasonable expectation of success, as it would allowed for modeling and predicting speed for various vehicle types across a road segment (Nunkesser: column 18, lines 40-62).
Further, the copending application fails to specifically disclose determining distance interval data comprising a first distance interval associated with the upstream road segment, a second distance interval associate with the first downstream road segment, and a third distance interval associate with the second downstream road segment. However, Fowe 502, which is analogous to the claimed invention because it is directed toward determining upstream and downstream road conditions to identify merging traffic, discloses determining distance interval data comprising a first distance interval associated with the upstream road segment, a second distance interval associate with the first downstream road segment, and a third distance interval associate with the second downstream road segment (paragraphs 0035-0039). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe 502 with the copending application-Fowe-Nunkesser-Ghosh-Jorgueski, with a reasonable expectation of success, as it would have improved the ability to identify and predict upstream/downstream road conditions to improve predicting traffic patterns. This would have allowed for improved travel time predictions for end users.
Finally, the copending application fails to specifically disclose a third training dataset associated with the distance interval, training a machine learning model by inputting the third training dataset associated with the distance interval, and predict a traffic event classification based on the third training dataset associated with the distance interval data.
However, Sajjadi Mohammadabadi, with is analogous to the claimed invention because it is directed toward using a deep neural network to train and use distance data (paragraph 0023: Here, an intersection is classified by training the machine learning model to predict distances to intersections), discloses a third training dataset associated with the distance interval (paragraph 0051: Here, a training dataset is derived from the sensor data to train the model to compute distances to intersections), training a machine learning model by inputting the third training dataset associated with the distance interval, and predict a traffic event classification based on the third training dataset associated with the distance interval data (Figure 6, item B608; paragraph 0084: Here, the neural network computes data representative of the distance to at least one or more intersections/distances). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Sajjadi Mohammadabadi with Fowe-Nunkesser-Ghosh-Jorjueski-Fowe 502, with a reasonable expectation of success, as it would have allowed for generating training data and training a model based upon the distance to an intersection in order to identify and train a model to identify intersections (Sajjadi Mohammadabadi: paragraph 0051).
With respect to claim 2, the copending application fails to specifically disclose providing the traffic classification profile as input for the machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model (paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claim 3, the copending application fails to specifically disclose training the machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claim 4, the copending application fails to specifically disclose training the machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claim 5, the copending application fails to specifically disclose training the machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claim 6, the copending application fails to specifically disclose training the machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
As per dependent claim 7, the copending application fails to specifically disclose wherein the machine learning model predicts an average speed of vehicles on the road segment. However, Nunkesser discloses wherein the machine learning model predicts an average speed of vehicles on the road segment (Figure 6). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Nunkesser with the copending application-Fowe-Ghosh-Jorgueski, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
With respect to claim 8, the copending application fails to specifically disclose training the machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claims 9-12 and 14-16, the applicant discloses the limitations substantially similar to those in claims 1-4 and 6-8, respectively. Claims 9-12 and 14-16 are similarly rejected.
With respect to claim 17, the patent fails to specifically disclose:
predicting, based on a machine learning model that is trained to utilize first-order logic associated with a set of logic rules
wherein the machine learning model is trained based on first traffic data for the upstream road segment, second traffic data for the first downstream road segment, and third traffic data for the second downstream road segment
However, Fowe discloses determining at least one traffic event classification for a divergence in the road segment between (i) a first portion of the road segment comprising the upstream road segment and (ii) a second portion of the road segment comprising the first downstream road segment and the second downstream road segment (paragraph 0041). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with the copending application, with a reasonable expectation of success, as it would have allowed for classifying segments as upstream/downstream. This would have facilitated training the ML model using upstream/downstream segments in order to improve traffic identification.
Additionally, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on first-order logic associated with a set of logic rules for different sets of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claim 18, the copending application fails to specifically disclose facilitating a routing of a vehicle based on a machine learning model. However, Ghosh, which is analogous to the claimed invention because it is directed toward training a machine learning model, discloses training a machine learning model based on a set of data (paragraphs 0044-0049: Here, a machine learning application is used to train data for autonomous vehicle systems (paragraph 0044). This includes processing first-order logic parameters, specified as first-order logic rules for the system (paragraph 0048) to learn to improve safety of the model(paragraph 0044)). It would have been obvious to have combined Ghosh with the patent-Fowe, with a reasonable expectation of success, because it would have allowed for training the machine learning model using first-order logic rules. This would have for expressing information about data for training the machine learning model.
With respect to claim 19, the copending application fails to specifically disclose rendering a navigation route via a map display based on the machine learning model. However, Nunkesser discloses causing rendering of a navigation route via a map display based on the machine learning model (Figures 3-4). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Nunkesser with the copending application-Fowe-Ghosh-Jorgueski, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
With respect to claim 20, the copending application fails to specifically disclose predicting an average speed of vehicles on the road segment based on the machine learning model. However, Nunkesser discloses wherein the predicting includes predicting an average speed of vehicles on the road segment based on the machine learning model (Figure 6). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined the copending application with Nunkesser, with a reasonable expectation of success, as it would allowed for modeling and predicting speed and times associated with navigating a road segment. This would have allowed for improved travel time predictions for end users.
As per dependent claim 21, the copending application, Fowe, Ghosh, Jorgueski, Nunkesser, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Fowe further discloses wherein the traffic event classification corresponds to a highway congestion even or a ramp congestion event associate with the road segment (paragraph 0035: Here, a split lane congestion event is determined. This congestion may be identified with respect to ramps and/or highways (Figure 6)). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with the copending application, with a reasonable expectation of success, as it would have allowed for classifying segments as upstream/downstream. This would have facilitated training the ML model using upstream/downstream segments in order to improve traffic identification.
As per dependent claim 22, the copending application, Fowe, Ghosh, Jorgueski, Nunkesser, Fowe 502, and Sajjadi Mohammadabadi disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Fowe discloses wherein the traffic event classification corresponds to a particular traffic event classification that is selected from a plurality of traffic event classifications comprising at least a first traffic event classification, and a second traffic event classification, and a third traffic event classification (paragraph 0054: Here, traffic data associated with a first traffic data (S1), a second traffic data (S2), and a third traffic data (S3), is used to identify a traffic event classification (paragraph 0035)). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Fowe with the copending application, with a reasonable expectation of success, as it would have allowed for classifying segments as upstream/downstream. This would have facilitated training the ML model using upstream/downstream segments in order to improve traffic identification.
Response to Arguments
Applicant’s arguments with respect to the rejection of claims under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of the Fowe, Ghosh, Jorgueski, Nunkesser, Fowe 502, and Sajjadi Mohammadabadi.
Applicant’s arguments with respect to the provisional rejection of claims under double patenting have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of the copending application, Fowe, Ghosh, Jorgueski, Nunkesser, Fowe 502, and Sajjadi Mohammadabadi.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Fowe (US 2019/0213874): Discloses probe data for monitoring multi-modal traffic scenarios and identifying distances to determine traffic distribution (paragraph 0004; Abstract)
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 KYLE R STORK whose telephone number is (571)272-4130. The examiner can normally be reached 8am - 2pm; 4pm - 6pm.
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, Omar Fernandez Rivas can be reached at 571/272-2589. 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.
/KYLE R STORK/Primary Examiner, Art Unit 2128