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 .
Response to Applicant’s Arguments/Remarks
Amendments and Remarks filed on 04/17/2026 have been fully considered and are addressed as follow:
Regarding the Claim Rejections Under 35 U.S.C. § 103: Applicants “Amendment and Remarks” have been fully considered, but they are not persuasive.
On page 9, applicant submits Daniels teaches “the vehicle event recorder both collects sensor data and runs the model.” The examiner agrees, but Claims 1-5, 9-16, and 18-20 are rejected using the combination of multiple references. Petersen does teach splitting up processes to be either on the vehicle-side or server-side [Petersen ¶ 0067-0068]. Additionally, it is known in the art to spit-up process to be executed either server-side or vehicle side based on computational need or complexity.
On page 9, applicant submits “Daniels does not describe a step of confirming that collision has actually occurred based on dashcam footage.” As outlined in the non-final office action, Rishi was used to teach this limitation not Daniel.
On page 9, applicant submits that the motivation to combine Daniels and Petersen “does not identify any specific technical reason why a person of ordinary skill in the art would have arranged these elements.” In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, Daniels does teach a preprocessing step which includes filtering of the telematics data before inputting it into a model to create the collision score [Daniels ¶ 0028]. Peterson teaches applying specifically a heuristic filter on data to determine a potential collision [Petersen ¶ 0087]. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention with a reasonable expectation of success to combine prefiltering process used before inputting into a model as taught by Daniels with using the more fine-grained heuristic filter as taught by Petersen in order to improve accuracy and reliability of collision detection.
On page 10, applicant submits Rishi “describes the video analytics system operating on its own, not in conjunction with, and used to confirm the output of, a separately operating feature-vector predictive model as the claims require.” Rishi does teach using both IMU sensor data and video data to calculate the probability of an anomaly (accident) [Rishi, Col 13 lines 7-10 “In an embodiment, the probability of occurrence of the anomaly may be calculated from the probability values obtained from the IMU sensor data analytics system 102 and the video analytics system 104.”]. Therefore, Rishi does teach the limitation of “confirming that collision has occurred based on the dashcam footage and an output of the predictive model.”
On page 10, applicant submits “Transplanting Yao’s feature vector methodology into the Daniel’s system … is not a straightforward combination.” The examiner submits that Daniels does teach preprocessing the data before inputting it into a model which includes normalization and alignment which are known process for creating a feature vector. Yao is used to explicitly teach using a feature vector as input to a model. Therefore, it would have not required substantial redesign to combine Yao’s feature vector with Daniels model.
On page 11, applicant submits “this is a paradigmatic case of hindsight reconstruction. In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
On page 11, applicant submits “A person of ordinary skill in the art would understand that the heuristic filter step in independent claims 1 and 4 and in dependent claims 5 and 16 is directed to the same inventive concept that the Examiner has acknowledged is not taught by the prior art.” While it might be directed to the same inventive concept, the examiner submits the scope of the claims 1, 4, 5, and 16 are much broader and simply claim a heuristic filter and how a heuristic filter works, and therefore, are still taught by the prior art as outlined below. Claims 6-8 and 17 specifically define the sub-processes used in the heuristic filter which is the allowable subject matter, not just the use of a heuristic filter.
For these reasons, the examiner respectfully disagrees with applicant’ arguments, and the examiner asserts that the cited art does teach or suggest each and every element of claims 1-5, 9-16, and 18-20 as outlined below. It is the Office’s stance that all of the claimed subject matter has been properly rejected.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-5, 9-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Daniels (US PGPub 2021/0387584) in view of Petersen (US PGPub 2022/0242427) in view of Rishi (US Patent 10814815) and in further view of Yao (US Patent 10816351).
Regarding claim 4, Daniels discloses A method comprising:
receiving telematics data from a computing device installed in a vehicle [Daniels ¶ 0026 "In the example shown, in 500, sensor data is received from a plurality of sensors." and Figure 5];
predicting that the feature vector represents a collision by inputting the feature vector into a predictive model trained to classify feature vectors of telematics data to binary classifications of collisions [Daniels ¶ 0026 "In 504, the preprocessed sensor data is processed using a model to create a collision score. In 506, the collision score is provided. In 508, a collision indication indicating whether or not a collision occurred is determined."];
retrieving dashcam footage associated with the vehicle [Daniels ¶ 0018 "For example, actions of the set of actions comprise archiving and/or fetching data (e.g., providing instructions to a vehicle event recorder and/or digital video recorder to archive collision data and provide data to a vehicle data center where it can also be archived)"];
transmitting a notification of the collision to a remote computing device [Daniels ¶ 0026 "In 516, an indication to take an action is determined based at least in part on the collision score. For example, taking an action comprises fetching data, providing data to a human reviewer, providing an indication to a client, storing data, creating a report, initiating a 911 call, initiating driver contact for a client operator, providing a request for a tow truck, providing a request for a backup truck for cargo transfer, providing a request for an ambulance"].
Daniels does teach preprocessing sensor data through filtering [Daniels ¶ 0026]. Daniels does not explicitly teach applying a heuristic filter on the telematics data to classify the telematics data as representing a potential collision of the vehicle.
However, in a related field of invention, Petersen does teach
applying a heuristic filter on the telematics data to classify the telematics data as representing a potential collision of the vehicle [Petersen ¶ 0087 "In some examples, the analysis of the data describing the vehicle during the time period to determine whether the potential collision is a non-collision may be carried out by checking the data against sets of criteria/criterion that are each related to non-collision events. If, in connection with a potential collision, data describing the vehicle during the time period matches at least one criterion associated with a non-collision event, the system may determine that the potential collision was not a collision and instead was the non-collision event." and Figure 2B block 258].
Therefore, it would have been obvious to one having ordinary skill in the art before the
effective filing date of the claimed invention with a reasonable expectation of success to combine the filtering processing of sensor data as taught by Daniels with using heuristic filtering as taught by Petersen in order to improve accuracy and reliability of collision detection [Petersen ¶ 0095].
Daniels and Peterson do not teach confirming that a collision has occurred based on the dashcam footage and an output of the predictive model.
However, in a related field of invention, Rishi does teach
confirming that a collision has occurred based on the dashcam footage and an output of the predictive model [Rishi Col 3 lines 57-67 and Col 4 lines 1-6 "In an embodiment, the IMU sensor data analytics system 102 may detect an anomaly corresponding to an automobile 10. The anomaly may be an accident. The anomaly may be detected based on a threshold trigger. In an embodiment, the video analytics system 104 may capture video feeds corresponding to the automobile 10. The video analytics system 104 may be configured to detect the anomaly corresponding to the automobile 10. The video analytics system 104 may be trained to determine the anomaly present in a video feed."]
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention with a reasonable expectation of success to combine the sensor fusion process for determining a collision as taught by Daniels with using dashcam footage as taught by Rishi in order to improve accuracy and reliability of collision detection.
Daniels, Peterson, and Rishi do not teach generating a feature vector representing the telematics data.
However, in a related field of invention, Yao does teach
generating a feature vector representing the telematics data [Yao, Col 6 lines 9-11 "The feature generation module 220 generates feature vectors for use in training models and predicting trip durations"];
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention with a reasonable expectation of success to combine the sensor fusion process for determining a collision using a model as taught by Daniels with creating a feature vector as taught by Yao in order to improve accuracy and reliability of collision detection. Additionally, it is well known in the art that a feature vector is the standard format for input used in a machine learning model.
Regarding claim 5, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Peterson further teaches wherein the heuristic filter comprises a plurality of sub-processes that independently predict that a collision has occurred based on the telematics data and a determination step that employs a multi-signal coincidence process [Petersen ¶ 0164-165 "The process may further include the facility filtering the detected potential collisions to generate updated potential collisions at block 604 by removing the potential collisions that are false positives (or non-collision events)." and Figure 3].
Therefore, it would have been obvious to one having ordinary skill in the art before the
effective filing date of the claimed invention with a reasonable expectation of success to combine the filtering processing of sensor data as taught by Daniels with using heuristic filtering as taught by Petersen in order to improve accuracy and reliability of collision detection [Petersen ¶ 0095].
Regarding claim 9, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Daniels further teaches wherein applying a heuristic filter on the telematics data comprises executing the heuristic filter on the computing device installed within the vehicle [Daniels ¶ 0023 " Preprocessing application 208 comprises an application for filtering, normalization, alignment, bias removal, subsampling, sample shortening, sample padding, spectrogramming, and/or mel spectrogramming." and Figures 1 and 2 The vehicle 106 holds the vehicle event recorder 102 and the vehicle event recorder has a processor 204 that executes the preprocessing application 208 which does the data filtering.].
Regarding claim 10, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Yao further teaches wherein the predictive model comprises a gradient boosting tree [Yao, Col 8 lines 19-29 "Some examples of machine learning algorithms that may be used to train the models include gradient boosting trees, nearest neighbor, naïve Bayes, etc. Data feature vectors, generated by the feature generation module 220 to train the real-time model 225 and the historical model 230, include input values such as the features previously detailed in the description of the feature generation module 220, and associated output values, such as the actual trip duration of a completed trip. Such feature vectors are used as inputs to the machine learning algorithms."].
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention with a reasonable expectation of success to combine the sensor fusion process for determining a collision using a machine learning model as taught by Daniels with using a gradient boosting tree as taught by Yao in order to improve accuracy and reliability of collision detection. Additionally, it is well known in the art that a gradient boosting tree is a type of machine learning model.
Regarding claim 11, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Daniels further teaches wherein retrieving dashcam footage associated with the vehicle comprise extracting timestamps from the telematics data to define an event window and retrieving the dashcam footage using the timestamps [Daniels ¶ 0027 " In 608, the sensor data is aligned. For example, alignment comprises timestamp alignment or peak alignment. Timestamp alignment comprises adjusting sensor data measurements for sensors sampled at different times in order to synchronize the sensor data sampling."].
Regarding claim 12, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Daniels further teaches wherein confirming that a collision has occurred based on the dashcam footage and an output of the predictive model comprises displaying the dashcam footage via a reviewing computer interface and receiving a user input confirming or rejecting the output of the predictive model [Daniels ¶ 0026 "For example, taking an action comprises fetching data, providing data to a human reviewer"].
Regarding claim 13, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Daneil does teach using telematics data and auto data to determine a collision [Daniels, Figure 8 shows using two neural network output (telematics data and auto data) to determine a collision score and ¶ 0031]. However, Rishi explicitly further teaches wherein confirming that a collision has occurred based on the dashcam footage and an output of the predictive model comprises inputting the dashcam footage into a machine learning model configured to output a classification indicating whether a collision has occurred [Rishi Col 3 lines 57-67 and Col 4 lines 1-6 "In an embodiment, the IMU sensor data analytics system 102 may detect an anomaly corresponding to an automobile 10. The anomaly may be an accident. The anomaly may be detected based on a threshold trigger. In an embodiment, the video analytics system 104 may capture video feeds corresponding to the automobile 10. The video analytics system 104 may be configured to detect the anomaly corresponding to the automobile 10. The video analytics system 104 may be trained to determine the anomaly present in a video feed."].
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention with a reasonable expectation of success to combine the sensor fusion process for determining a collision as taught by Daniels with using dashcam footage as taught by Rishi in order to improve accuracy and reliability of collision detection.
Regarding claim 14, Daniels as modified by Petersen, Yao, and Rishi teaches the method of claim 4. Daniels further teaches wherein transmitting a notification of the collision to a remote computing device comprises transmitting the notification to one or more of a first responder computing device and a fleet manager computing device [Daniels ¶ 0026 "In 516, an indication to take an action is determined based at least in part on the collision score. For example, taking an action comprises fetching data, providing data to a human reviewer, providing an indication to a client, storing data, creating a report, initiating a 911 call, initiating driver contact for a client operator, providing a request for a tow truck, providing a request for a backup truck for cargo transfer, providing a request for an ambulance."].
Regarding claims 1-3, all limitations have been examined with respect to the method in claims 4, 5, and 14. The method taught/disclosed in claims 4, 5, and 14 can clearly perform on the system of claims 1-3. Therefore, claims 1-3 are rejected under the same rationale.
Regarding claims 15-16 and 18-20, all limitations have been examined with respect to the method in claims 4-5 and 12-14. The medium taught/disclosed in claims 15-16 and 18-20 can clearly perform the method of claims 4-5 and 12-14. Therefore, claims 15-16 and 18-20 are rejected under the same rationale.
Allowable Subject Matter
Claims 6-8 and 17 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
THIS ACTION IS MADE FINAL. 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 JOSEPHINE RICH whose telephone number is (571)272-6384. The examiner can normally be reached M-F 8-5pm.
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, Scott Browne can be reached at (571) 270-0151. 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.
/J.E.R./Examiner, Art Unit 3666 /SCOTT A BROWNE/Supervisory Patent Examiner, Art Unit 3666
Prosecution Insights