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 .
Claim Interpretation - 35 USC § 101
The present claims overcome the previous 35 U.S.C. 101 rejection because the independent claims explicitly recite that a machine learning model is positively generated, using training data, and this machine learning model is then used to perform an action.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
The term “anomaly” in claim 1 is a relative term which renders the claim indefinite. The term “anomaly” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. Specifically, claim 3 attempts to define this modification, but does so in another relative term “abnormal vehicle activity.” This is completely unbounded. If, however, claim 3 was amended to remove this term, then anomaly would be appropriately defined and not subject to this rejection.
All claims are rejected because of this.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-4, 6-11, 13-18, and 20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chen “Car Damage Detection and Patch-to-Patch Self-supervised Image Alignment”, 2021, hereinafter “Chen”.
Regarding claim 1, Chen discloses a computer-implemented method for managing dynamic digital vehicle identity (Abstract discloses Most computer vision applications aim to identify pixels in a scene and use them for diverse purposes. One intriguing application is car damage detection for insurance carriers which tends to detect all car damages by comparing both pre-trip and post-trip images, even requiring two components: (i) car damage detection; (ii) image alignment. Firstly, we implemented a Mask R-CNN model to detect car damages on custom images. Whereas for the image alignment section, we especially propose a novel self-supervised Patch-to-Patch SimCLR inspired alignment approach to find perspective transformations between custom pre/post car rental images except for traditional computer vision method) comprising:
generating, by a computing device, a vehicle profile associated with a vehicle based on a first received image of the vehicle (Page 1, Col. 1, P2-3 disclose that in general, car damages can be classified into three primary categories as metal damage, glass damage and miscellaneous damage based on which component they impact. Also, the most general strategy to detect car damages is training an object detection network (e.g., Faster-RCNN [4], Retinanet, YOLO) on a large number of labeled images. Image alignment refers to the process of minimizing the differences between the aligned image and the reference image, typically by finding a transformation that maps the pixels of the aligned image to the corresponding pixels in the reference image. This is a first received image and a second received image);
wherein generating the vehicle profile comprises generating, by the computing device, a mircro-pattern associated with the vehicle based on at least one analysis of the first received image (Col. 1, last paragraph, Col. 2, P1-P2, and Fig. 1 disclose a portion of a vehicle based on an image. This is a micro-pattern based on analysis);
generating, utilizing a machine learning model trained on one or more datasets derived from the vehicle profile, a unique immutable fingerprint of the vehicle designed to monitor the vehicle based on the micro-pattern (As above, the micro-pattern is unique to the vehicle because it is a picture of that vehicle. Page 2, Section III. Discuses the use of machine learning in this process);
detecting, by the computing device, one or more modifications of the vehicle based on an analysis of a second received image of the vehicle (As discussed in the first limitation, the reference deals with identifying damage based on pixel differences);
transmitting, by the computing device, an alert based on the one or more modifications indicating an anomaly associated with the micro-pattern based on a plurality of contextual information ascertained by the machine learning model (See Fig. 5).
Regarding claim 2, Chen teaches wherein the micro-pattern comprises a plurality of internal and external parameters of the vehicle (As above, the micro-pattern is unique to the vehicle because it is a picture of that vehicle); and wherein the micropattern is compared a plurality of sensor data associated with the vehicle (this is addressed above and in Fig. 4. The parameters can be any individual markings on the vehicle).
Regarding claim 3, Chen discloses wherein the one or more modifications comprise at least one crack, blip, scratch, color change, license plate change, or abnormal vehicle activity associated with the vehicle (Col. 2, P1 discloses car damages includes at least scratches).
Regarding claim 4, Chen discloses tracking, by the computing device, the vehicle via computer visioning system (Col. 1, P1 discloses the paper relates to computer vision); and filtering, utilizing temporal action localization, a plurality of images associated with the vehicle based on the comparison indicating a lack of anomaly (Page 2, Col. 1, Fig. 4 and last paragraph disclose comparison of pictures and specifically by comparing 32*32 patches on individual pictures. Also, the abstract specifically states that the custom images are pre and post car rental images, so this means there is a comparison before and after the damage and this is temporal).
Regarding claim 6, Chen discloses wherein the one or more modifications indicating the anomaly is based on the one or more modifications exceeding a threshold associated with the micro-pattern (Page 2, Col. 2 discloses at least a threshold based on pixels, and loss optimization).
Regarding claims 7, the 32*32 patches are two dimensional codes.
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.
Claim(s) 5, 12, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen “Car Damage Detection and Patch-to-Patch Self-supervised Image Alignment”, 2021, hereinafter “Chen,” in view of Singh, “Accelerate Car Damage Annotation With Labellerr's Auto Labeling Using SAM”, https://www.labellerr.com/blog/accelerate-car-damage-annotation-with-labellerr-auto-labeling/, 2024, hereinafter “Singh.”
Regarding claims 5, Chen discloses wherein a first vehicle fingerprint derived from the first received image is compared to a second vehicle fingerprint derived from the second received image (See claim 4). However, while Chen discloses both image generation and logical decision making as discussed above, it uses a Mask R-CNN learning system, not specifically generative artificial intelligence utilized for incremental extrapolation.
However, Singh, which is directed to exactly the same problem as Chen, namely assessing vehicle damage after accidents for insurance claim processing, does teach on Page 5 that using GANs and other generative create realistic and diversified automotive damage images to add with real-world data (this is equivalent to incremental extrapolation). Page 6 provides the motivation to do so as being able to annotate data with increased speed and accuracy, thereby doubling their release velocity for developing AI-powered image analysis software. Therefore, it would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to use GANs for image generation to supplement the image creation and analysis process of Chen.
Claims 12 and 19 are duplicate claims.
Response to Arguments
The 35 U.S.C. 101 rejections have been withdrawn due to claim amendments. Regarding 35 U.S.C. 102 arguments, Applicant does not indicate which portions or limitations Chen does not teach, rather asserts, in generalities, that Chen does not disclose the independent claim. Please refer to the claim rejection above for how Chen teaches each limitation.
Prior Art Cited but Not Relied on
Mohamad, CAR DAMAGE SEVERITY ASSESSMENT USING SUPERVISED DEEP LEARNING 2024, teaches the assessment of car damage severity is a critical task in the automotive industry, particularly in insurance claims processing, repairs, and traffic safety analysis. Traditionally, car damage assessment has heavily relied on manual inspections by experts. However, this approach suffers from several limitations, including subjectivity, time consumption, and potential errors, which can lead to inaccurate assessments, delayed insurance claims, and compromised repair processes. This study aims to addresses challenges in accurately assessing car damage severity using deep learning techniques, aiming to overcome limitations associated with manual inspection, such as subjectivity, time consumption, and potential errors. A robust data preprocessing pipeline is implemented using TensorFlow's ImageDataGenerator to prepare and augment the car damage severity assessment dataset, enhancing the model's ability to generalize across diverse data. Once preprocessed, the study continues with 4 supervised deep learning model which are Roboflow, ResNet, EfficientNetV2L and VGG19, with the best performing is EfficientNetV2L with an accuracy of 81%. when trained on 400x400 pixel images for 10 epochs.
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 ARYAN E WEISENFELD whose telephone number is (571)272-6602. The examiner can normally be reached M-F 9-5.
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, Angela Ortiz can be reached at 5712726805. 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.
ARYAN E. WEISENFELD
Primary Examiner
Art Unit 3689
/ARYAN E WEISENFELD/ Primary Examiner, Art Unit 3663
Prosecution Insights