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
Claims 1-20, as originally filed 07/24/2025, are pending and have been examined on the merits (claims 1, 11, and 17 being independent). The applicant’s claim for a benefit of a provisional application 62/815,711, filed 03/08/2019 has been received and a parent application, 16/693,031 has been issued.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/24/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 9 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
As the recited limitation in claim 9, “….the particular damaged vehicle component is obscured from view in the image.”, the subject matter is not properly described in the application as filed, and provide an explanation of your position. The recited claim is not clear as to how the particular damaged vehicle component is obscured from view in the image because the claimed limitations are not described in the application with sufficient detail such that one skilled in the art can reasonably conclude that the inventor had possession of the claimed invention at the time of filing.
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 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.
Claims 1-2, 5-8, 10-12, 15-17, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Hanson et al. (hereinafter Hanson), US Publication Number 2017/0352104 A1 in view of Li et al. (hereinafter Li), US Publication Number 2018/0260793 A1.
Regarding claim 1:
Hanson discloses the following:
A method of estimating damage to a vehicle, the method comprising: (see Hanson, at least [abstract] discloses “Systems and methods for automatically determining damage information and publishing said damage information are provided. A notice of loss associated with a damaged item may be received. An apparatus may analyze the damaged item to determine damage information for any damage elements present on the damaged item.”, and see also [0004-0006])
receiving, by a processor, an image illustrating damage to a vehicle, the vehicle being characterized by a vehicle type; (see Hanson, at least [0090] discloses “The enhanced claims processing system may receive a first notice of loss from a claimant regarding damage to an item (block 1004) such as a vehicle. A damage information collector may be launched at a damage information collection device (block 1006) operated by the claimant.”; [0091] discloses “The enhanced claims processing system may also receive an indication of the damaged portion of the item (block 1010), e.g., a damaged area or a damaged component.”, and see also [0086] discloses “With respect to damaged vehicles, image metadata may include, e.g., the make, model, and year of the vehicle; the area or component of the vehicle that is damaged in the image; and the type of damage depicted in the image.”)
Hanson does not explicitly disclose the following, however Li further teaches:
selecting, by the processor and based on the vehicle type, a machine learning algorithm configured to identify similarities between digital images illustrating damaged vehicles of the vehicle type; (see Li, at least [0172] discloses “Some embodiments use machine learning to perform the task of prediction of vehicle damage from an auto claim. Thousands of historical auto claims are stored in one or more databases, such as database 110 in FIG. 1, for training and testing of the disclosed system. The database also stored auto claim images and other pieces of information that come with a claim, such as vehicle make, model, color, age, and current market value, for example.”, [0233] discloses “the server computing device trains a plurality of CNNs to detect damage to a respective plurality of external vehicle parts 2604. At step 2606, the server computing device receives a set of images corresponding to a new claim. At step 2608, the server computing device executes the first CNN to detect the pose of the vehicle in each of the images in the set of image. At step 2610, the server computing device executes the plurality of CNNs to determine which external vehicle parts are damaged. At step 2612, the server computing device executes a Markov Random Field (MRF) algorithm to infer damage to internal parts of the vehicle from the damaged external vehicle parts. At step 2614, the server computing device estimates a repair cost based on the external and internal damaged parts.”, and [0236] discloses “a deep learning system (e.g., Convolutional Neural Network) is trained on a large number of images of damaged vehicles and corresponding information about damage, e.g., its extent and location on the vehicle, in order to learn to assess damage presented with input images. The data used to train the model may be available from an insurance company's auto claims archives. A pattern learning technique can then be used predict damage to both the exterior and interior of the vehicle from input images of a damaged vehicle.”, and also Examiner notes: as cited above, Li teaches executing the plurality of CNNs to determine which external vehicle parts are damaged and executing a Markov Random Field (MRF) algorithm to infer damage to internal parts of the vehicle from the damaged external vehicle parts in order to determine similarities between images illustrating damaged vehicles of the both the exterior and interior of the vehicle from input images of a damaged vehicle. That is, Li teaches the selection of machine learning algorithm that is based on vehicle type such as make, model, and age and further based on the pose of the matched vehicle as recited limitations.)
identifying, by the processor, and using the machine learning algorithm and the image, a plurality of stored images of damaged vehicles of the vehicle type, wherein the plurality of stored images show vehicle damage corresponding to the damage illustrated in the image; (see Li, at least [0236] discloses “a deep learning system (e.g., Convolutional Neural Network) is trained on a large number of images of damaged vehicles and corresponding information about damage, e.g., its extent and location on the vehicle, in order to learn to assess damage presented with input images. The data used to train the model may be available from an insurance company's auto claims archives. A pattern learning technique can then be used predict damage to both the exterior and interior of the vehicle from input images of a damaged vehicle, as well as the associated repair costs”, and see also [0239])
identifying, by the processor and based on stored information associated with the plurality of stored images, a likelihood that the vehicle has a particular damaged vehicle component; (see Li, at least [0063] discloses “computer vision techniques are used to first clean the received images of unwanted artifacts, such as background clutter and specular reflections, and then, to find the best matching image of a reference vehicle of the same make/model/year. The system compares the received images with the corresponding reference images along several attributes, e.g., edge distribution, texture, and shape. Using a variety of computer vision techniques, the system recognizes where and how the received images depart from the reference images, and identifies the corresponding part(s) and/or regions on the exterior of the vehicle that are damaged. The reference images can, in some embodiments, be derived from a commercial 3D model of a vehicle of the same make and model, or from images of the same vehicle taken prior to the occurrence of damage in the current claim”, and [0236] discloses “a deep learning system (e.g., Convolutional Neural Network) is trained on a large number of images of damaged vehicles and corresponding information about damage, e.g., its extent and location on the vehicle, in order to learn to assess damage presented with input images. The data used to train the model may be available from an insurance company's auto claims archives. A pattern learning technique can then be used predict damage to both the exterior and interior of the vehicle from input images of a damaged vehicle.”)
determining, by the processor, that the likelihood is greater than a threshold value; and (see Li, at least [0140] discloses “Embodiments of the disclosure first find edges in the two images using a standard edge finding algorithm, and then compute the distributions of the length and orientations of edges in each window. The distance between the distributions within a window is then computed (using entropy or Kullback-Leibler divergence, for example). If a window exceeds a threshold that is empirically determined, the window may contain damage.”, and see also [0271])
determining, by the processor and based on the likelihood being greater than the threshold value, an estimated cost associated with repair or replacement of the particular damaged vehicle component. (see Li, at least [0094] discloses “the server calculates an estimated repair cost for the vehicle based on the detected external damage and inferred internal damage. The server accesses one or more databases of parts and labor cost for each external and internal part that is estimated to need repair or replacement.”, and see also [0271])
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include a similar or the same previously analyzed vehicle that has similar or the same types of damage (e.g., as a result of a similar accident to a similar vehicle or part, etc.) as using machine learning technologies, as taught by Li in order to provide more accurate damage analysis/cost estimate for the damaged vehicle. (see Li, [0233-0236])
Regarding claim 2:
Hanson discloses the following:
The method of claim 1, wherein the image is received, via a network, from an electronic device. (see Hanson, at least [0082] discloses “The enhanced claims processing server 902, in this example, is in signal communication with a damage information collection device 904 via a network 906 such as the Internet. As described, a claimant may utilize the damage information collection device 904 to provide damage information that indicates the damage to a damaged item.”)
Regarding claim 5:
Hanson does not explicitly disclose the following, however Li further teaches:
The method of claim 1, wherein the estimated cost is determined based at least in part on the stored information associated with the plurality of stored images. (see Li, at least [0094] discloses “the server calculates an estimated repair cost for the vehicle based on the detected external damage and inferred internal damage. The server accesses one or more databases of parts and labor cost for each external and internal part that is estimated to need repair or replacement.”, and see also [0176])
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include a similar or the same previously analyzed vehicle that has similar or the same types of damage (e.g., as a result of a similar accident to a similar vehicle or part, etc.) as using machine learning technologies, as taught by Li in order to provide more accurate damage analysis/cost estimate for the damaged vehicle. (see Li, [0233-0236])
Regarding claim 6:
Hanson does not explicitly disclose the following, however Li further teaches:
The method of claim 1, wherein the estimated cost is determined based at least in part on at least one of manufacturer information, a labor cost, or repair data of a same vehicle component as the particular damaged vehicle component. (see Li, at least [0176] discloses “the machine learning system prepares a repair cost appraisal for the vehicle by looking up the damaged parts and labor cost in a database. The damaged parts list can be compared to a list of previously damaged parts prior to the occurrence of the current damage, and a final list of newly damaged parts is determined through subtraction of previously damaged parts.”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include a similar or the same previously analyzed vehicle that has similar or the same types of damage (e.g., as a result of a similar accident to a similar vehicle or part, etc.) as using machine learning technologies, as taught by Li in order to provide more accurate damage analysis/cost estimate for the damaged vehicle. (see Li, [0233-0236])
Regarding claim 7:
Hanson discloses the following:
The method of claim 1, wherein the vehicle type is indicative of at least one of make, model, or year. (see Hanson, at least [0060] discloses “the damage information 504 may describe or otherwise indicate the damage to an item such as a vehicle. The damage information 504 may identify the item type such as the make, model, and year where the item is a vehicle for example.”)
Regarding claim 8:
Hanson does not explicitly disclose the following, however Li further teaches:
The method of claim 1, wherein selecting the machine learning algorithm comprises selecting, by the processor, from a plurality of machine learning algorithms trained using respective sets of digital images illustrating damaged vehicles of a same vehicle type. (see Li, at least [0233] discloses “the server computing device trains a plurality of CNNs to detect damage to a respective plurality of external vehicle parts 2604. At step 2606, the server computing device receives a set of images corresponding to a new claim. At step 2608, the server computing device executes the first CNN to detect the pose of the vehicle in each of the images in the set of image. At step 2610, the server computing device executes the plurality of CNNs to determine which external vehicle parts are damaged. At step 2612, the server computing device executes a Markov Random Field (MRF) algorithm to infer damage to internal parts of the vehicle from the damaged external vehicle parts. At step 2614, the server computing device estimates a repair cost based on the external and internal damaged parts.”, [0236] discloses “a deep learning system (e.g., Convolutional Neural Network) is trained on a large number of images of damaged vehicles and corresponding information about damage, e.g., its extent and location on the vehicle, in order to learn to assess damage presented with input images. The data used to train the model may be available from an insurance company's auto claims archives. A pattern learning technique can then be used predict damage to both the exterior and interior of the vehicle from input images of a damaged vehicle.”, and also Examiner notes: as cited above, Li teaches executing the plurality of CNNs to determine which external vehicle parts are damaged and executing a Markov Random Field (MRF) algorithm to infer damage to internal parts of the vehicle from the damaged external vehicle parts in order to determine similarities between images illustrating damaged vehicles of the both the exterior and interior of the vehicle from input images of a damaged vehicle. That is, Li teaches the selection of machine learning algorithm that is based on vehicle type such as make, model, and age and further based on the pose of the matched vehicle.”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include a similar or the same previously analyzed vehicle that has similar or the same types of damage (e.g., as a result of a similar accident to a similar vehicle or part, etc.) as using machine learning technologies, as taught by Li in order to provide more accurate damage analysis/cost estimate for the damaged vehicle. (see Li, [0233-0236])
Regarding claim 10:
Hanson does not explicitly disclose the following, however Li further teaches:
The method of claim 1, further comprising:
receiving, by the processor, an actual cost associated with the repair or the replacement of the particular damaged vehicle component; and (see Li, at least [0176] discloses “the machine learning system prepares a repair cost appraisal for the vehicle by looking up the damaged parts and labor cost in a database. The damaged parts list can be compared to a list of previously damaged parts prior to the occurrence of the current damage, and a final list of newly damaged parts is determined through subtraction of previously damaged parts.”)
retraining, by the processor, the machine learning algorithm with training data including the actual cost and the image. (see Li, at least [0177] discloses “Additionally, some embodiments can classify a claim into categories as a total, medium, or small loss claim by taking the damaged parts list, repair cost estimation, and current age and monetary value of the vehicle as input to a classifier whose output is the loss type which takes the three values-total, medium and small. Any machine learning technique can be used for the classifier, e.g., logistic regression, decision tree, artificial neural network, support vector machines (SVM), and bagging.”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include a similar or the same previously analyzed vehicle that has similar or the same types of damage (e.g., as a result of a similar accident to a similar vehicle or part, etc.) as using machine learning technologies, as taught by Li in order to provide more accurate damage analysis/cost estimate for the damaged vehicle. (see Li, [0233-0236])
Regarding claim 12:
Hanson discloses the following:
The system of claim 11, the acts further comprising causing presentation, on a user interface, of the estimated cost. (see Hanson, at least [0104] discloses “the line-item cost estimate may be transmitted to the customer, who may present the estimate to a repair center of their choosing or from a list of authorized repair centers.”)
Regarding claim 11: it is similar scope to claim 1, and thus it is rejected under similar rationale.
Regarding claim 15: it is similar scope to claim 8, and thus it is rejected under similar rationale.
Regarding claim 16: it is similar scope to claim 10, and thus it is rejected under similar rationale.
Regarding claim 17: it is similar scope to claims 1 and 12, and thus it is rejected under similar rationale.
Regarding claim 19: it is similar scope to claim 8, and thus it is rejected under similar rationale.
Regarding claim 20: it is similar scope to claim 10, and thus it is rejected under similar rationale.
Claims 3-4, 13-14, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Hanson in view of Li in further view of Wang et al. (hereinafter Wang), US Publication Number 2018/0182039 A1.
Regarding claim 3:
Hanson and Li do not explicitly disclose the following, however Wang further teaches:
The method of claim 2, further comprising:
determining, by the processor, that the image does not satisfy a criterion; (see Wang, at least [0122] discloses “determine whether the shooting angles of the damage assessing images are identical to each other”)
displaying, by the processor, on a display the electronic device, a request for at least one additional image; and (see Wang, at least [0122] discloses “generate reminder information of continuously collecting damage assessing images from different shooting angles and send the reminder information to the terminal.”)
responsive to the request, receiving, by the processor and from the electronic device, an additional image. (see Wang, at least [0122] discloses “if Y images of the received damage assessing images have the same shooting angles, the reminder information can be read as, for example, "Y images have the same shooting angles, please continuously collecting Y-1 images from different shooting angles respectively".”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include collecting damage assessing images from different shooting angles and sending the reminder information to the terminal for collecting images from different shooting angles, as taught by Wang in order to provide more accurate damage analysis for the damaged vehicle. (see Wang, [0122])
Regarding claim 4:
Hanson and Li do not explicitly disclose the following, however Wang further teaches:
The method of claim 3, wherein the request prescribes an angle at which the at least one additional image be captured. (see Wang, at least [0122] discloses “if Y images of the received damage assessing images have the same shooting angles, the reminder information can be read as, for example, "Y images have the same shooting angles, please continuously collecting Y-1 images from different shooting angles respectively".”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include collecting damage assessing images from different shooting angles and sending the reminder information to the terminal for collecting images from different shooting angles, as taught by Wang in order to provide more accurate damage analysis for the damaged vehicle. (see Wang, [0122])
Regarding claims 13 and 18: it is similar scope to claim 3, and thus it is rejected under similar rationale.
Regarding claim 14: it is similar scope to claim 4, and thus it is rejected under similar rationale.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Hanson in view of Li in further view of Lota et al. (hereinafter Lota), US Publication Number 2020/0258208 A1.
Regarding claim 9:
Hanson and Li do not explicitly disclose the following, however Lota further teaches:
The method of claim 1, wherein the particular damaged vehicle component is obscured from view in the image. (see Lota, at least [0069] discloses “Environmental conditions, such as sun light, street lights, and precipitation may impact and even obscure the appearance of colors and textures of surfaces of vehicle 305. For example, a reflective surface in bright light may decrease the signal - to - noise ratio at the image sensor thereby obscuring a surface aberration. Images of surfaces of different colors exposed to different environmental conditions, reflective surfaces, and dull surfaces may be contained within repository 335 and used for training or used as a basis for the comparison . These extracted images may be used to train the machine learning to correct for these factors to identify the actual parameters (e.g. , HSL parameters) of the surface.”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify determining damage information for any damage elements present on the damaged vehicle of Hanson to include environmental conditions, such as sun light, street lights, and precipitation may impact and even obscure the appearance of colors and textures of surfaces of vehicle, as taught by Lota in order to view better for a damage on the vehicle. (see Lota, [0002])
Conclusion
The prior art made of record but not relied upon herein but pertinent to Applicant’s disclosure is listed in the enclosed PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YONG S PARK whose telephone number is (571)272-8349. The examiner can normally be reached M-F 9:00-5:00 PM, EST.
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, Bennett M. Sigmond can be reached on (303)297-4411. 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.
/YONGSIK PARK/Examiner, Art Unit 3694
July 30, 2026
/BENNETT M SIGMOND/Supervisory Patent Examiner, Art Unit 3694
Prosecution Insights