DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This action is in response to the amendments filed on 07/09/2026. Wherein, claims 1, 8, and 15 have been amended. Claims 1-20 are rejected.
Response to Arguments
Applicant’s arguments, see REMARKS, filed 07/09/2026, with respect to the rejections under 35 USC § 112b have been fully considered and are persuasive. Therefore, the previous rejections under 35 USC § 112b have been withdrawn.
Applicant’s arguments with respect to the rejection(s) of claim(s) 1, 3, 4, 7, 8, 10, 11, 14, 15, 17, and 18 under 35 USC § 102 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 Therefore, the rejection has been withdrawn.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 Lange et al.
Applicant’s arguments with respect to the rejection(s) of claim(s) 2, 5, 6, 9, 12, 13, 16, 19, and 20, 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 Therefore, the rejection has been withdrawn.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 Lange et al.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 3, 4, 7, 8, 10, 11, 14, 15, 17, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Pittman et al. (US 2022/0375340 A1, “Pittman”) in view of Lange et al. (Traffic Prediction with Advanced Graph Neural Networks, “Lange”).
Regarding claims 1, 8, and 15, Pittman discloses machine-learning based control of traffic operation and teaches:
An apparatus (FIG. 6 is a schematic representation of an example traffic network 400 according to the present disclosure. The traffic network 400 may include vehicles 402a-402/ communicatively coupled to one or more roadside units (RSUs) 410a and 410b. The traffic network 400 may also include localized servers 420a and 420b communicatively coupled to the RSUs 410a and 410b. The localized server 420a may be configured to receive and process data from the RSUs 410a and 410b, and the localized server 420b may be configured to receive and process data for other RSUs, which are not illustrated for brevity – See at least ¶ [0041]) comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to: (In some aspects, the described embodiments may include software on the RSUs 410. The software on the RSUs 410 may be stored in memory and executable by a processor, which may be included on the RS Us 410 – See at least ¶ [0043])
receive training data indicating events and attributes associated with the events, (In some embodiments, the machine learning model 220 may be trained to output the traffic simulations 230 based on one or more datasets including different types of traffic condition information 210. For example, the machine learning model 220 may be trained based on GPS information associated with one or more vehicles traveling on a highway traffic system. As another example, the machine learning model 220 may be configured to obtain vehicular driving behavior data, such as hard braking occurrences, vehicular acceleration, unusual or sudden steering, etc., and the machine learning model 220 may be trained to identify and/or predict the occurrence of one or more traffic events (e.g., accidents, traffic jams, etc.) based on the vehicular driving behavior data. As another example, the machine learning model 220 may be trained based on traffic information such as video streams of the highway traffic system, traffic signal timing data, ramp meter controller data, wrong way driver detection data, dedicated short-range communication (DSRC) data between connected vehicles, cellular-to-vehicle (C-V2X) data, etc. As another example, the machine learning model 220 may be trained based on information related to a given highway traffic system, such as social media data, construction information, and/or public safety data – See at least ¶ [0037]) wherein the events indicate traffic spillover from routes to regions local to the routes; (At block 640, a probability of traffic congestion may be determined. The probability of traffic congestion may be an estimation indicating how likely a traffic jam or other traffic congestion event is to occur based on present traffic conditions. In some embodiments, the machine learning model may provide a reasoning for the determined probability of traffic congestion to provide interpretability of the results provided by the machine learning model – See at least ¶ [0063]; Examiner notes that the congestion determination includes multiple intersections from the traffic incident, i.e., regions local to the routes – See at least ¶ [0054]) []
using the training data, train a machine learning model to predict impact, within a first region local to a first route, of traffic congestion of a first route on a first region local to the first route based on first attributes associated with the first route, (At block 640, a probability of traffic congestion may be determined. The probability of traffic congestion may be an estimation indicating how likely a traffic jam or other traffic congestion event is to occur based on present traffic conditions. In some embodiments, the machine learning model may provide a reasoning for the determined probability of traffic congestion to provide interpretability of the results provided by the machine learning model – See at least ¶ [0063]; In some embodiments, traffic congestion of the highway traffic system 100b may be reduced by controlling at which ramp vehicles may enter and/or exit the highway road 130. For example, traffic congestion may be reduced by guiding vehicles 150b to enter the highway road 130 at on-ramp 120 and vehicle 150c to enter the highway road 130 at on-ramp 122. In some embodiments, determining at which ramps vehicles may enter and/or exit the highway road 130 to reduce traffic congestion may include analysis of the effects entering and/or exiting the highway road 130 at multiple on- and/or off-ramps along the highway traffic system 100b. For example, a given highway traffic system may include any suitable number of ramps. Guiding vehicles to enter and/or exit the given highway traffic system at the first and fourth ramps may have a different effect on traffic congestion on the given highway traffic system compared to guiding vehicles to enter and/or exit the given highway traffic system at the first and fifth ramps – See at least ¶ [0026]; Examiner notes that the system considers the impact to local regions and the route – See at least ¶ [0054]) wherein the first region includes at least a portion of an alternative route that diverges from the first route; (As shown in fig. 2, the model is applied to a highway system, intersections entering and exiting the highway system, and attached roads, e.g., service road 115. Therefore, the region includes at least a portion of alternative route, e.g., intersections and service roads, that diverges from the first route.)
receive as input the first attributes associated with the first route; (FIG. 4 shows an embodiment of an example system 200 that may be used to simulate and predict traffic conditions. In some embodiments, a machine learning model 220 may be configured to obtain traffic condition information 210 and generate one or more traffic simulations 230 including information relating to traffic control. A traffic control system 240 may obtain one of the traffic simulations 230 and/or the information relating to traffic control associated with the one traffic simulation 230 – See at least ¶ [0034])
cause the machine learning model to predict the impact within the first region based on the first attributes; and (In some embodiments, the machine learning model 220 may generate a number of traffic simulations 230 modeling one or more characteristics of the highway traffic system, such as travel time between ramps, maximum traffic volume capacity, potential origin-destination information for vehicles, etc. The traffic simulations 230 may identify existing road conditions and/or predict future road conditions based on the provided traffic condition information 210. Additionally or alternatively, the machine learning model 220 may determine accident-occurrence predictions and/or effects of hypothetical accidents on traffic flow, and the traffic simulations 230 may include simulated traffic controls that may mitigate the effects of the simulated accidents predicted by the machine learning model 220 on traffic congestion. Additionally or alternatively, the traffic condition information 210 may include one or more constraints for operation of the highway traffic system, such as a minimum traffic volume density, a maximum vehicular speed, a minimum vehicular speed, etc., that may be included in the traffic simulations 230. In these and other embodiments, the machine learning model 220 may be configured to consider each data point included in the traffic condition information 210 individually, all of the data points included in the traffic condition information 210 collectively, and/or some combination thereof for training and/or deployment of the machine learning model 220 – See at least ¶ [0036]; Examiner notes that this occurs for an entire region – See at least ¶ [0054])
provide the impact as output. (At block 640, a probability of traffic congestion may be determined. The probability of traffic congestion may be an estimation indicating how likely a traffic jam or other traffic congestion event is to occur based on present traffic conditions. In some embodiments, the machine learning model may provide a reasoning for the determined probability of traffic congestion to provide interpretability of the results provided by the machine learning model – See at least ¶ [0063])
Pittman does not explicitly teach wherein the events indicate traffic spillover from routes to regions local to the routes, each region including at least a portion of an alternative route that diverges from a respective one of the routes. However, Lange discloses traffic prediction with advanced graph neural networks and teaches:
wherein the events indicate traffic spillover from routes to regions local to the routes, each region including at least a portion of an alternative route that diverges from a respective one of the routes (We divided road networks into “Supersegments” consisting of multiple adjacent segments of road that share significant traffic volume. …Our model treats the local road network as a graph, where each route segment corresponds to a node and edges exist between segments that are consecutive on the same road or connected through an intersection…Graph Neural Networks extend the learning bias imposed by Convolutional Neural Networks and Recurrent Neural Networks by generalising the concept of “proximity”, allowing us to have arbitrarily complex connections to handle not only traffic ahead or behind us, but also along adjacent and intersecting roads. In a Graph Neural Network, adjacent nodes pass messages to each other. By keeping this structure, we impose a locality bias where nodes will find it easier to rely on adjacent nodes (this only requires one message passing step) – See at least pg. 3-7)
In summary, Pittman teaches identifying the impact of spillover from routes to a surrounding region, e.g., intersections, highways, and service roads. Pittman does not explicitly teach each region including at least a portion of an alternative route that diverges from a respective one of the routes. However, Lange discloses traffic prediction with advanced graph neural networks and teaches splitting the connected road network up into many sub regions and identifying the impact of congestion in each of those regions.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the instant application to have modified the machine-learning based control of traffic operation of Pittman to provide for the traffic prediction with advanced graph neural networks, as taught in Lange, to help improve the accuracy of ETAs at a global scale (At Lange pg. 3)
Regarding claims 3, 10, and 17, Pittman further teaches:
wherein the attributes indicate: (i) one or more types of incidents that caused the traffic spillover from the routes; (ii) locations of the incidents on the routes; (iii) a functional class of a road segment in which each of the incidents occurred; (iv) temporal information associated with the events; (v) traffic congestion of the routes and the regions; (vi) weather condition of the routes; (vii) weather conditions of the regions; or (viii) a combination thereof. (FIG. 3 illustrates a third view of the example
embodiment of the highway traffic system 100c according to the present disclosure. Analysis of the highway traffic system 100c may include identification and/or evaluation of road conditions, such as one or more weather conditions 162, one or more road defects 164, maintenance work 166, and/or road-surface markings 168 of the highway traffic system 100c – See at least ¶ [0028]; In some embodiments, the road defects 164 may include any flaws and/or abnormalities in the highway road 130 that may affect driving on the highway traffic system 100c. For example, the road defects 164 may include uneven road pavement, potholes, broken rail guards, defective light poles, etc. The road defects 164 may increase traffic congestion by, for example, reducing potential vehicle throughput on the highway road 130 and/or increasing the likelihood of accidents occurring (which in tum may cause traffic congestions). As mentioned above in relation to the weather conditions 162, the effects of the road defects 164 on traffic congestion may be compounded by the presence of other road conditions – See at least ¶ [0030])
Regarding claims 4, 11, and 18, Pittman further teaches:
wherein the impact is defined by: (i) a change in traffic congestion within the first region; and (ii) a duration of which the traffic congestion of the first region will be greater than average traffic congestion of the first region. (At block 620, traffic data corresponding to the roadway traffic system may be obtained. In some embodiments, the traffic data may be indicative of real-time traffic conditions on the roadway traffic system. For example, the traffic data may include average speed of vehicles traveling on the traffic system, the number of vehicles on the traffic system, average travel time of vehicles traveling on the traffic system, likely origin-destination information, occurrence of accidents, visibility of signage, visibility of striping, weather conditions, presence of road maintenance, etc. The traffic data may be obtained from one or more sensors positioned near the traffic system – See at least ¶ [0061]; At block 640, a probability of traffic congestion may be determined. The probability of traffic congestion may be an estimation indicating how likely a traffic jam or other traffic congestion event is to occur based on present traffic conditions. In some embodiments, the machine learning model may provide a reasoning for the determined probability of traffic congestion to provide interpretability of the results provided by the machine learning model – See at least ¶ [0063])
Regarding claims 7 and 14, Pittman further teaches:
wherein the computer program code instructions are configured to, when executed, cause the apparatus to, based on the impact, generate a second route that diverges from the first route and terminates at the same destination as the first route. (In some embodiments, traffic congestion of the highway traffic system 100b may be reduced by controlling at which ramp vehicles may enter and/or exit the highway road 130. For example, traffic congestion may be reduced by guiding vehicles 150b to enter the highway road 130 at on-ramp 120 and vehicle 150c to enter the highway road 130 at on-ramp 122. In some embodiments, determining at which ramps vehicles may enter and/or exit the highway road 130 to reduce traffic congestion may include analysis of the effects entering and/or exiting the highway road 130 at multiple on- and/or off-ramps along the highway traffic system 100b. For example, a given highway traffic system may include any suitable number of ramps. Guiding vehicles to enter and/or exit the given highway traffic system at the first and fourth ramps may have a different effect on traffic congestion on the given highway traffic system compared to guiding vehicles to enter and/or exit the given highway traffic system at the first and fifth ramps – See at least ¶ [0026])
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 2, 9, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Pittman in view of Lange, as applied to claims 1, 8, and 15, and in further view of Scofield et al. (US 2014/0278031 A1, “Scofield”).
Regarding claims 2, 9, and 16, the combination of Pittman and Lange does not explicitly each wherein a functional class of the first route is greater than a functional class of each road segment within the first region. However, Scofield discloses event-based traffic routing and teaches:
wherein a functional class of the first route is greater than a functional class of each road segment within the first region. (In some embodiments, the avoidance zone may merely comprise those road segments where the degree of traffic congestion is expected to be above the specified threshold. In other embodiments, the avoidance zone may further comprise road segments where the degree of traffic congestion is expected to be less than the specified threshold and/or road segments where insufficient traffic data is available from which to forecast traffic congestion. By way of example, traffic sensors may not measure vehicle counts on alleyways or side-streets that connect two or more higher capacity road segments. Accordingly, there may be little to no historical traffic data from which to forecast traffic congestion along such alleyways or side-streets. However, due to the spatial proximity of one or more alleyways or side-streets to a road segment where the degree of traffic congestion is forecasted to be above a specified threshold, the zone creation component 410 may develop the avoidance zone in a manner that includes such side-streets or alleyways, for example (e.g., because it is likely such alleyways or side-streets will also be congested if a nearby road segment is likely to be congested) – See at least ¶ [0050])
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the instant application to have modified the machine-learning based control of traffic operation of Pittman and Lange to provide for the event-based traffic routing, as taught in Scofield, to identify road segments that are likely to be congested (e.g., road segments where drivers are likely to experience slower speeds than typically experienced on the road segment) due to an event at a venue. (At Scofield ¶ [0004])
Claim(s) 5, 12, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Pittman in view of Lange, as applied to claims 1, 8, and 15, and in further view of Shao et al. (US 2023/0419823 A1, “Shao”).
Regarding claims 5, 12, and 19, the combination of Pittman and Lange does not explicitly teach wherein the attributes include air quality index (AQI) values of the regions, and wherein the impact indicates an AQI value of the first region. However, Shao discloses methods and systems for managing exhaust emission in a smart city based on industrial internet of things and teaches:
wherein the attributes include air quality index (AQI) values of the regions, and wherein the impact indicates an AQI value of the first region. (In some embodiments, the pollution index information may be determined, by the management platform 230, through processing the total amount of exhaust emission and weather information in the preset area through the first model. The vehicle limit information may be determined based on the pollution index information by the management platform – See at least ¶ [0058]; the total amount of vehicle exhaust emission in the preset area may be estimated by the value of vehicle flow reflected by the vehicle information in the preset area, and then the air pollution index of the preset road segment may be determined according to the total amount of exhaust emission, and then whether the vehicles in the preset area are restricted and the mode of restriction may be accurately determined according to the air pollution index, so as to avoid vehicles entering into the preset area and aggravating the air pollution in the preset area – See at least ¶ [0059])
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the instant application to have modified the machine-learning based control of traffic operation of Pittman and Lange to provide for the methods and systems for managing exhaust emissions, as taught in Shao, to improve traffic congestion and reduce the impact of vehicle exhaust on the urban environment. (At Shao ¶ [0003])
Claim(s) 6, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Pittman in view of Lange, as applied to claims 1, 8, and 15, and in further view of Cella (US 2020/0103244 A1, “Cella”).
Regarding claims 6, 13, and 20, the combination of Pittman and Lange does not explicitly teach wherein the attributes include noise levels of the regions, and wherein the impact indicates a noise level of the first region. However, Cella discloses intelligent transportation systems and teaches:
wherein the attributes include noise levels of the regions, and wherein the impact indicates a noise level of the first region. (An aspect provided herein includes a system for transportation, comprising: a cognitive system for routing at least one vehicle within a set of vehicles based on a set of routing parameters determined by facilitating coordination among a designated set of vehicles, wherein the coordination is accomplished by taking at least one input from at least one game-based interface for a user of a vehicle in the designated set of vehicles – See at least ¶ [0030]; In embodiments, the set of routing parameters includes at least one of traffic congestion , desired arrival times, preferred routes, fuel efficiency, pollution reduction, accident avoidance, avoiding bad weather, avoiding bad road conditions, reduced fuel consumption, reduced carbon footprint, reduced noise in a region, avoiding high-crime regions, collective satisfaction, maximum speed limit, avoidance of toll roads, avoidance of city roads, avoidance of undivided highways, avoidance of left turns, avoidance of driver-operated vehicles – See at least ¶ [0032])
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the instant application to have modified the machine-learning based control of traffic operation of Pittman and Lange to provide for the intelligent transportation systems, as taught in Cella, to provide systems that enable improved mobility and transportation for passengers and for objects, such as freight, goods, animals and the like. (At Cella ¶ [0003])
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 CHASE L COOLEY whose telephone number is (303)297-4355. The examiner can normally be reached Monday-Thursday 7-5MT.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Aniss Chad can be reached at 571-270-3832. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/C.L.C./Examiner, Art Unit 3662
/ANISS CHAD/Supervisory Patent Examiner, Art Unit 3662
Prosecution Insights