DETAILED ACTION
Status of the Claims
The following is a Final Office Action in response to amendments and remarks filed 04 June 2026.
Claims 1, 9 and 15 have been amended.
Claims 1-20 are pending and have been examined.
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 Arguments
Applicant's arguments filed 04 June 2026 have been fully considered but they are not persuasive.
Applicants argue that the 35 U.S.C. 101 rejection under the Alice Corp. vs. CLS Bank Int’l be withdrawn; however the Examiner respectfully disagrees. As an initial note, the arguments are not compliant under 37 CFR 1.111(b) as they amount to a mere allegation of patent eligibility. The Examiner refers Applicant to the updated rejection below, addressing the instant amendments.
Applicant’s remarks with respect to the prior art have bene fully considered and addressed in the updated rejections below.
In response to arguments in reference to any depending claims that have not been individually addressed, all rejections made towards these dependent claims are maintained due to a lack of reply by the Applicants in regards to distinctly and specifically pointing out the supposed errors in the Examiner's prior office action (37 CFR 1.111). The Examiner asserts that the Applicants only argue that the dependent claims should be allowable because the independent claims are unobvious and patentable over the prior art.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims are directed to a process (an act, or series of acts or steps), a machine (a concrete thing, consisting of parts, or of certain devices and combination of devices), and a manufacture (an article produced from raw or prepared materials by giving these materials new forms, qualities, properties, or combinations, whether by hand labor or by machinery). Thus, each of the claims falls within one of the four statutory categories (Step 1). The claims recite a method (process) and system with apparatuses, however, the claim(s) recite(s) predicting repair or total loss of a vehicle based upon a weighted decision which is an abstract idea of organizing human activities as well as a mental process.
The limitations of “receiving... a plurality of data comprising one or more images or video of a motor vehicle involved in a motor vehicle accident, vehicle data describing categorization of the motor vehicle, telematics data recorded within a threshold of time of the motor vehicle accident, and triage data responding to a state of the motor vehicle determined by an observer of the motor vehicle; preprocessing the plurality of data by performing input data transformation to convert the plurality of data from different file types into a unified digital format; extracting features from the plurality of data using one or more of...initiating a data imputation process to supplement the plurality of data; processing, by a set of trained machine learning models including a feature extraction layer, the plurality of data and the extracted features for a plurality of respective data categories including image data, video data, vehicle data, telematics data and triage data; for each of the plurality of data categories: determining, by the set of trained machine learning models, a categorization of the motor vehicle as repairable or a total loss and a confidence score associated with the categorization; comparing the confidence score for the respective data category to a corresponding category-specific threshold value; in response to the confidence score exceeding the corresponding category-specific threshold value, assigning the categorization for the respective data category as an output of the set of trained machine learning models; determining a weighted decision based on the categorization and associated confidence scores across the plurality of data categories; selecting a question of a set of questions based on the weighted decision and providing the question to [the user]; upon receiving a response to the question via the GUI, providing the response to the set of trained machine learning models, updating the plurality of data with the response and reprocessing the updated plurality of data using the set of trained machine learning models; recalculating, by the set of trained machine learning models, the confidence score for each data category based on the updated plurality of data; updating the weighted decision based on the recalculated confidence scores; and when the weighted decision exceeds a confidence threshold, updating the GUI to present information associated with the weighted decision indicating the motor vehicle as repairable or a total loss,” as drafted, is a process that, under its broadest reasonable interpretation, covers organizing human activities--fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) and/or a mental process—concepts performed in the human mind (including an observation, evaluation, judgment, opinion) but for the recitation of generic computer components (Step 2A Prong 1). That is, other than reciting “by an action prediction system,” (or “a processor that is configured to” in claim 15) nothing in the claim element precludes the step from the methods of organizing human interactions grouping or from practically being performed in the mind. For example, but for the “by an action prediction system,” (or “a processor that is configured to” in claim 15) language, “receiving,” “initiating, “determining,” ‘determining,” “selecting,” “providing,” and “updating” in the context of this claim encompasses the user manually collecting accident data (such as photos, questions/statements, evidence) to generate a repair estimate and ultimately the decision of a total loss or not which is a business relation/fundamental economic practice/commercial or legal interaction/ traditionally performed by an insurance adjuster or automotive mechanic by hand or mental process/judgement of observing a vehicle and deciding whether or not to repair or if it is a total loss. However, if possible, the Examiner should consider the limitations together as a single abstract idea rather than as a plurality of separate abstract ideas to be analyzed individually. “For example, in a claim that includes a series of steps that recite mental steps as well as a mathematical calculation, an examiner should identify the claim as reciting both a mental process and a mathematical concept for Step 2A, Prong One to make the analysis clear on the record.” MPEP 2106.04, subsection II.B. Under such circumstances, however, the Supreme Court has treated such claims in the same manner as claims reciting a single judicial exception. Id. (discussing Bilski v. Kappos, 561 U.S. 593 (2010)). Here, the limitations are considered together as a single abstract idea for further analysis. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitations as a mathematical concept, while some of the limitations may be performed in the mind after certain limitations are performed, but for the recitation of generic computer components, then it falls within the grouping of abstract ideas. (Step 2A, Prong One: YES). Accordingly, the claim(s) recite(s) an abstract idea.
This judicial exception is not integrated into a practical application (Step 2A Prong Two). Method claim 1 is devoid of any structure whatsoever (an action prediction system and graphical user interface (GUI) do not expressly or inherently recite structure). The “graphical user interface (GUI)” is also simply provided to a user for insignificant extrasolution data gathering. Next, the claims only recites one additional element – using an action prediction system or processor to perform the steps. The action prediction system or processor in the steps is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of electronic data storage, query, retrieval and arithmetic) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Specifically the claims amount to nothing more than an instruction to apply the abstract idea using a generic computer or invoking computers as tools by adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d)(I) discussing MPEP 2106.05(f). The recitation of “...applying the plurality of data as input to a set of trained machine learning models” in the limitations also merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element “trained machine learning models” limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (machine learning) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h). Furthermore, this use of “trained machine learning models” is also only mere instructions to apply an already trained technique. Accordingly, the combination of these additional elements does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea, even when considered as a whole (Step 2A Prong Two: NO).
The claim does not include a combination of additional elements that are sufficient to amount to significantly more than the judicial exception (Step 2B). As discussed above with respect to integration of the abstract idea into a practical application (Step 2A Prong 2), the combination of additional elements of using an action prediction system or processor to perform the steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Reevaluating here in step 2B, the “graphical user interface (GUI)” in the step(s) which are insignificant extrasolution activities are also determined to be well-understood, routine and conventional activity in the field. The Symantec, TLI, and OIP Techs court decisions in MPEP 2106.05(d)(II) indicate that the mere receipt or transmission of data over a network is well-understood, routine, and conventional function when it is claimed in a merely generic manner (as is here). Therefore, when considering the additional elements alone, and in combination, there is no inventive concept in the claim. As such, the claim(s) is/are not patent eligible, even when considered as a whole (Step 2B: NO).
Claims 2-7, 10, 12-14, and 16-20 recite(s) the additional limitation(s) further limiting the weighted decision, categories, and data, which is still directed towards the abstract idea previously identified and is not an inventive concept that meaningfully limits the abstract idea. Again, as discussed with respect to claims 1 and 15, the claims are simply limitations which are no more than mere instructions to apply the exception using a computer or with computing components. Accordingly, the additional element(s) does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Even when considered as a whole, the claims do not integrate the judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Claims 8-9 and 11 recite(s) the additional limitation(s) further limiting the machine learning and including artificial intelligence which merely indicates a field of use or technological environment in which the judicial exception is performed and is not an inventive concept that meaningfully limits the abstract idea. Again, as discussed with respect to claims 1 and 15, the claims are simply limitations which are no more than mere instructions to apply the exception using a computer or with computing components. Accordingly, the additional element(s) does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Even when considered as a whole, the claims do not integrate the judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Claims 1-20 are therefore not eligible subject matter, even when considered as a whole.
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.
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.
Claim(s) 1-8 and 10-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kelsh et al. (US PG Pub. 2018/0082378) and further in view of Taliwal et al. (US PG Pub. 2017/0293894).
As per claims 1 and 15, Kelsh discloses a method for automatically predicting repair or total loss actions in relation to a motor vehicle accident, and An accident prediction system for automatically predicting repair or total loss actions in relation to a motor vehicle accident comprising: a memory; and a processor that is configured to execute machine readable instructions stored in the memory for causing the processor to: the method comprising (loss assessment server, loss assessment computer, Kelsh ¶36):
receiving, by an action prediction system, a plurality of data comprising one or more images or video of a motor vehicle involved in a motor vehicle accident, vehicle data describing categorization of the motor vehicle, telematics data recorded within a threshold of time of the motor vehicle accident, and triage data responding to a state of the motor vehicle determined by an observer of the motor vehicle (In one example depicted in FIG. 8, after a user has proceeded past the tutorial screen, the camera of mobile device 120 may be activated and the user interface associated with the camera of mobile device 120 may generate a semi-translucent overlay 802C on the viewport 802A of the mobile device. The semi-translucent overlay 802C may be semi-opaque and, as such, may allow for viewing of the image data captured by the camera of the mobile device 120 through the semi-translucent overlay 802C. As shown in screen 802, the semi-translucent overlay 802C may be generated in a center portion of viewport 802A. Additionally, image data corresponding to the vehicle of the user (e.g., 802B) may also be displayed in the viewport 802A in instances in which the vehicle is in the perceptible range of the camera of the mobile device. As shown in screen 804, as the user of mobile device 120 approaches the damaged vehicle, the image data corresponding to the damaged vehicle of the user (e.g., 804B) may take up more area in the viewport 804A of mobile device 120. Conversely, the size of the semi-transparent overlay 804B may remain fixed compared to the size of the semi-transparent overlay 802C depicted in screen 802. Furthermore, as shown in screen 804, the image data corresponding to the vehicle of the user (e.g., 804B) may be viewable through the semi-translucent overlay 804C in instances in which the semi-translucent overlay 804C and the image data corresponding to the vehicle are overlapped. As shown in screen 806, the user may be able to orient the mobile device 120 relative to the user's damaged vehicle in such a way as to cause the image data corresponding to the vehicle of the user (e.g., 806B) to be aligned with the semi-translucent overlay 806C, Kelsh ¶78; Loss assessment computer 162 of loss assessment server 160 may be able to determine, based on the vehicle operational data received from telematics device 113, on-board computer 115 via vehicle communication systems 114, and/or mobile device 120, that vehicle 110 has been involved in an accident, ¶37; post-accident assistance measures, ¶38);
preprocessing the plurality of data by performing input data transformation to convert the plurality of data from different file types into a unified digital format (The pre-FNOL system 140 may be configured to initially process the pictures submitted by the user in order to determine if they are of a quality, size, and shape suitable to perform the pre-FNOL loss assessment methods described herein. In some instances, the pre-FNOL server 140 may be further configured to analyze the photos provided by the user to determine whether or not they correspond to the areas identified by the user selected accordion-type, selectable fields and the user selected sub-options, Kelsh ¶75);
extracting features from the plurality of data using one or more of optical character recognition (OCR), computer vision, natural language processing (NLP), generative artificial intelligence (Al) or deep learning techniques (In one example, responsive to receiving a user selection of an accordion-type, selectable field of the plurality of accordion-type, selectable fields corresponding to a particular macro area of the vehicle (e.g., front, rear, driver side, passenger side), pre-FNOL system 140 may activate a camera on mobile device 120 and accompanying user interface. As shown in FIG. 8, when activated, the user interface associated with the camera of mobile device 120 may generate a semi-translucent overlay 802C on the viewport 802A of the mobile device. In some instances, the semi-translucent overlay 802C may correspond to the macro area of the vehicle corresponding to the user selected accordion-type field. For example, in the event that the user selected the accordion-type, selectable field corresponding to the front of the vehicle, the user interface associated with the camera of mobile device 120 may generate a semi-translucent overlay 802C corresponding to the front of the vehicle. In some instances, the semi-translucent overlay 802C may correspond to the vehicle selected by the user in step 212 (e.g., Vehicle A or Vehicle B). However, in other instances, the semi-translucent overlay of the vehicle may correspond to a generic vehicle of a class similar to that of the vehicle selected by the user in step 212 (e.g., truck, sedan, coupe, hatchback, etc.). In one example, the semi-translucent overlay may correspond to the outline of the vehicle (either the user-selected vehicle or the generic vehicle of the class similar to that of the user-selected vehicle) and in another example, the semi-translucent overlay may correspond to the outline of vehicle with lines denoting the additional structure included therein. Alternatively, the semi-translucent overlay may be a geometric shape such as an oval, circle, rectangle, square, and the like. The semi-translucent overlay may serve as an aide for the user in capturing an image suitable for the pre-FNOL system 140 to conduct the pre-FNOL loss assessment calculations. In some instances, before the pre-FNOL system 140 activates the camera on mobile device 120 and the accompanying user interface including the semi-translucent overlay, a tutorial screen may be presented to the user demonstrating the proper use of the semi-translucent overlay. The tutorial screen may provide the user with a plurality of user interface screen shots depicting correct and incorrect usages of the semi-translucent overlay. In regards to correct usages, the tutorial screen may show a green check mark corresponding to instances in which the semi-translucent overlay is properly aligned with a vehicle. In regards to incorrect usages, the tutorial screen may show a red ‘X’ corresponding to instances in which the semi-translucent overlay is not properly aligned with the vehicle. Through the presentation of the tutorial screen, the user may be able to better understand how to use the semi translucent overlay in capturing pictures of the damaged areas of the vehicle suitable for the pre-FNOL system 140 to conduct the pre-FNOL loss assessment calculations, Kelsh ¶76-¶77)(Examiner notes the ability to initially process photos with a translucent overlay to identify features as the ability to use computer vision to extract the features)
initiating a data imputation process to supplement the plurality of data (Additionally, the post-accident assistance measures may include providing a post-accident checklist to a driver of vehicle 110 through a pre-FNOL loss assessment application operating on mobile device 120 and/or a webpage associated with the pre-FNOL system 140 being utilized and/or accessed by mobile device 120. The post-accident check list may include a list of tasks to be performed by a driver of vehicle 110 in order to be eligible to receive insurance compensation for the accident and/or be able to be eligible for pre-FNOL loss assessment. Such tasks may include acquiring insurance information from other drivers of other vehicles involved in the accident, taking photos of areas of vehicle 110 damaged in the accident, taking photos of areas of other vehicles damaged in the accident, and the like. In some instances, performance of post-accident assistance measures may be optional, Kelsh ¶45);
processing, by a set of trained machine learning models including a feature extraction layer, the plurality of data and the extracted features for a plurality of respective data categories including image data, video data, vehicle data, telematics data and triage data (The loss assessment matrix may be a standardized m-by-n matrix storing the data associated with the accident in numerical form. The data may be entered by the loss assessment server 160 in the order in which the category corresponding to the data is received from mobile device 120 (e.g., vehicle operational data first, responses to the preliminary questions second, user vehicle selection information third, and the detailed damage descriptions fourth). The order in which the data categories are received may further correspond to the row or column of the loss assessment matrix into which the data is entered and stored. In other words, the first category of data received (e.g., vehicle operational data) may occupy the first row or first column of the loss assessment matrix. From there, loss assessment server 160 may enter each individual data item within the first category along the first row or the first column in sequential matrix elements comprised within the first row or the first column. For example, in regards to the received vehicle operational data (e.g., the first category), the first element within the first row or first column may be vehicle velocity at the time of the accident, the second element within the first row or first column may be vehicle acceleration at the time of the accident, the third element within the first row or first column may be the degree of brake activation during the time of the accident, and so on until each of the received data elements within the first category are entered into the first row or first column. After entering each of the received data elements associated with the first category, the loss assessment matrix may enter each of the received data elements within the second, third, and fourth categories in a manner similar to that described above with respect to the first category. In some instances, the loss assessment matrix may further include a fifth category occupying a fifth row and/or column. The fifth category may be reserved for the type of damage to the vehicle, costs of repairing damages to the vehicle, type of repairs needed to fix the damages to the vehicle, repair completion time, and accompanying insurance policy changes associated with filing a claim to cover the calculated costs of repairing damages to the vehicle. As will be described in further detail below, the loss assessment matrix may also include a sixth category occupying a sixth row and/or column. The sixth category may correspond to instances in which the user is provided with general damage screen 606, Kelsh ¶97-¶98);
for each of the plurality of data categories:
determining, by the set of trained machine learning models, a categorization of the motor vehicle as repairable or a total loss and a confidence score associated with the categorization (specific categories have values, ¶100; Additionally, the historical data source server 150 may further associate a level of confidence to the overall quality of the match of the loss assessment matrix to each of the matched historical loss assessment matrices based upon the total number of correlated data elements. For example, a correlation of one data element will be given a minimum confidence level, whereas a correlation of each and every data element will be given a maximum confidence level, Kelsh ¶106; confidence rating, ¶114; weights, machine learning algorithms, ¶110);
determining a weighted decision based on the categorization and associated confidence scores across the plurality of data categories (weights for elements in the assessment matrices, Kelsh ¶107-¶110);
comparing the confidence score for the respective data category to a corresponding category-specific threshold value; in response to the confidence score exceeding the corresponding category-specific threshold value, assigning the categorization for the respective data category as an output of the set of trained machine learning model (For example, a correlation of one data element will be given a minimum confidence level, whereas a correlation of each and every data element will be given a maximum confidence level, Kelsh ¶106; confidence rating, ¶114; weights, machine learning algorithms, ¶110);
selecting a question of a set of questions based on the weighted decision and providing the question to a graphical user interface (GUI) (Upon completion of the post-accident assistance measures and/or receiving an indication that an accident has occurred, a user of mobile device 120 may provide answers to one or more questions regarding the accident and one or more pictures associated with damage to vehicle 110. The user may then transmit the answers to the one or more questions and one or more photos to pre-FNOL system 140 for loss assessment processing. Pre-FNOL system 140 may analyze the one or more answers provided by the user and the one or more photos to determine a cost to repair the damages to vehicle 110 and accompanying insurance policy changes associated with filing a claim to cover the repair costs. In some instances, pre-FNOL system 140 may incorporate vehicle operation data received from any one, or combination of, vehicle operation sensors 111, telematics device 113, on-board computer 115 via vehicle communication system 114, and mobile computing device 120 and historical data provided by historical data source server 150 in determining the cost to repair the damages to vehicle 110 and accompanying insurance policy change, Kelsh ¶6);
upon receiving a response to the question via the GUI, providing the response to the set of trained machine learning models, wherein output from the set of trained machine learning models iteratively adjusts the confidence score for each category and the weighted decision (Through analysis of the responses to the questions and the pictures of the damages, the pre-FNOL system may determine repair costs for the damages to the insured property and accompanying insurance policy changes associated with filing a claim to cover the repair costs, Kelsh ¶4; Pre-FNOL system 140 may analyze the one or more answers provided by the user and the one or more photos to determine a cost to repair the damages to vehicle 110 and accompanying insurance policy changes associated with filing a claim to cover the repair costs. In some instances, pre-FNOL system 140 may incorporate vehicle operation data received from any one, or combination of, vehicle operation sensors 111, telematics device 113, on-board computer 115 via vehicle communication system 114, and mobile computing device 120 and historical data provided by historical data source server 150 in determining the cost to repair the damages to vehicle 110 and accompanying insurance policy changes, ¶46); and
updating the plurality of data with the response and reprocessing the updated plurality of data using the set of trained machine learning models (In such instances in which a first and a second weight are associated with each data element of the loss assessment matrices, the historical data source server 150 may determine a first confidence rating for the overall quality of the match of the loss assessment matrix to each of the historical loss assessment matrices based upon the total number of correlated data elements in regards to the cost of repairing the vehicle and a second confidence rating in regards to the accompanying changes to the insurance policy. For example, the loss assessment matrix may be matched against a historical loss assessment matrix based on a correlation of one data element. The data element may be associated with a first weight and second weight, wherein the first weight is greater than the second weight. Accordingly, the first confidence rating in regards to the cost of repairing the vehicle may be greater than the second confidence rating in regards to the accompanying changes to the insurance policy. The weight(s) associated with each data element of the plurality of data elements comprised within the loss assessment matrices and the confidence level(s) and/or rating(s) associated with the quality of the overall match of the loss assessment matrix to one or more historical loss assessment matrices may be configured to dynamically change over time. The changes may be determined by machine learning algorithms (e.g., Hidden Markov Model, Recurrent Neural Net, etc.) configured to place additional emphasis on the most recent historical loss assessment profile data included in historical data source database 154. In another example, the historical data source server 150 may perform a preliminary search of the loss assessment matrix against the historical loss assessment matrices stored in the historical data source database 154. Specifically, the historical data source server 150 may conduct a search of the historical loss assessment matrices stored in the historical data source database 154 based on the vehicle make, model, and damage location indicated by the associated data elements within the loss assessment matrix. In the event that a plurality of hits and/or matches are determined, historical data source server 150 may perform a second search of the loss assessment matrix against the preliminarily matched historical loss assessment matrices based on the remainder of the data elements of the loss assessment matrix. The second search may be performed to determine the overall quality of the match of the loss assessment matrix to each of the matched historical loss assessment matrices in the manner described in any of the above-mentioned examples, Kelsh ¶109-¶111);
recalculating, by the set of trained machine learning models, the confidence score for each data category based on the updated plurality of data (changes and updates to the models, Kelsh ¶109-¶111);
updating the weighted decision based on the recalculated confidence scores (changes and updates to the models, Kelsh ¶109-¶111);
While Kelsh discloses the ability to present the user with repair estimates, file claims and even find a repair shop (Kelsh ¶126, ¶134, ¶181) but does not expressly disclose when the weighted decision exceeds a confidence threshold, updating the GUI to present information associated with the weighted decision indicating the motor vehicle as repairable or a total loss.
However, Taliwal teaches when the weighted decision exceeds a confidence threshold, updating the GUI to present information associated with the weighted decision indicating the motor vehicle as repairable or a total loss (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139).
Both the Kelsh and Taliwal references are analogous in that both are directed towards/concerned with vehicle damage assessment. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to use Taliwal’s ability to determine the type of loss in Kelsh’s system to improve the system and method with reasonable expectation that this would result in a vehicle assessment system that is able to provide accurate damage assessments.
The motivation being that from end-to-end, the process of vehicle inspection, estimate generation, claim approval, and vehicle repair can be long and complex, involving several parties including at least a customer, an auto repair shop, and a claim adjustor. Accordingly, there is a need in the art for an improved system that overcomes some of the drawbacks and limitations of conventional approaches (Taliwal ¶2-¶3).
As per claims 2 and 16, Kelsh and Taliwal disclose as shown above with respect to claims 1 and 15. Taliwal further teaches wherein the weighted decision aggregates the categorization and the confidence score for the individual categories (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139).
As per claims 3 and 17, Kelsh and Taliwal disclose as shown above with respect to claims 1 and 15. Kelsh further discloses wherein the weighted decision identifies a greatest value of the confidence score for the individual categories (The comparison performed by loss assessment server 160 may commence with a comparison of the historical accident photo gallery associated with the historical loss assessment matrix matched with the highest level of confidence by historical data source server 150. In instances in which first and second confidence levels were determined, loss assessment server may base commencement off of the first confidence level (e.g., confidence level associated with calculating the cost of repairing the vehicle). Loss assessment server 160 may perform the comparison by first comparing the macro damage pictures of the front, rear, driver side, and/or passenger side of the user's vehicle to the one or more historical macro damage pictures associated with the corresponding vehicle areas and then comparing the micro damage pictures of the of the specific damage areas of the vehicle within the front, rear, driver side, and/or passenger side to the corresponding vehicle areas with the one or more historical micro damage pictures, Kelsh ¶116; highest level of confidence, ¶117).
As per claims 4 and 18, Kelsh and Taliwal disclose as shown above with respect to claims 1 and 15. Taliwal further teaches wherein the weighted decision identifies a repairable versus total loss vehicle damage classification (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139) (Examiner notes medium loss and small loss as repairable classifications).
As per claims 5 and 19, Kelsh and Taliwal disclose as shown above with respect to claims 1 and 15. Taliwal further teaches wherein when the weighted decision exceeds the confidence threshold, updating the GUI to present a repairable vehicle damage classification (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139).
As per claims 6 and 20, Kelsh and Taliwal disclose as shown above with respect to claims 1 and 15. Taliwal further teaches wherein when the weighted decision exceeds the confidence threshold, updating the GUI to present a total loss vehicle damage classification (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139).
As per claim 7, Kelsh and Taliwal disclose as shown above with respect to claim 1. Kelsh further discloses wherein the categorization comprises damage triage questionnaire details, context driven image artifacts and/or video stream which infers damage recognition to various parts/panel of the vehicle, or vehicular metadata (In one example depicted in FIG. 8, after a user has proceeded past the tutorial screen, the camera of mobile device 120 may be activated and the user interface associated with the camera of mobile device 120 may generate a semi-translucent overlay 802C on the viewport 802A of the mobile device. The semi-translucent overlay 802C may be semi-opaque and, as such, may allow for viewing of the image data captured by the camera of the mobile device 120 through the semi-translucent overlay 802C. As shown in screen 802, the semi-translucent overlay 802C may be generated in a center portion of viewport 802A. Additionally, image data corresponding to the vehicle of the user (e.g., 802B) may also be displayed in the viewport 802A in instances in which the vehicle is in the perceptible range of the camera of the mobile device. As shown in screen 804, as the user of mobile device 120 approaches the damaged vehicle, the image data corresponding to the damaged vehicle of the user (e.g., 804B) may take up more area in the viewport 804A of mobile device 120. Conversely, the size of the semi-transparent overlay 804B may remain fixed compared to the size of the semi-transparent overlay 802C depicted in screen 802. Furthermore, as shown in screen 804, the image data corresponding to the vehicle of the user (e.g., 804B) may be viewable through the semi-translucent overlay 804C in instances in which the semi-translucent overlay 804C and the image data corresponding to the vehicle are overlapped. As shown in screen 806, the user may be able to orient the mobile device 120 relative to the user's damaged vehicle in such a way as to cause the image data corresponding to the vehicle of the user (e.g., 806B) to be aligned with the semi-translucent overlay 806C, Kelsh ¶78; Loss assessment computer 162 of loss assessment server 160 may be able to determine, based on the vehicle operational data received from telematics device 113, on-board computer 115 via vehicle communication systems 114, and/or mobile device 120, that vehicle 110 has been involved in an accident, ¶37; The comparison performed by loss assessment server 160 may commence with a comparison of the historical accident photo gallery associated with the historical loss assessment matrix matched with the highest level of confidence by historical data source server 150. In instances in which first and second confidence levels were determined, loss assessment server may base commencement off of the first confidence level (e.g., confidence level associated with calculating the cost of repairing the vehicle). Loss assessment server 160 may perform the comparison by first comparing the macro damage pictures of the front, rear, driver side, and/or passenger side of the user's vehicle to the one or more historical macro damage pictures associated with the corresponding vehicle areas and then comparing the micro damage pictures of the of the specific damage areas of the vehicle within the front, rear, driver side, and/or passenger side to the corresponding vehicle areas with the one or more historical micro damage pictures, ¶116).
As per claim 8, Kelsh and Taliwal disclose as shown above with respect to claim 1. Kelsh further discloses wherein the set of trained machine learning models for individual categories comprise at least two of machine learned, statistical, and image-based CV models that are trained on different datasets (The weight(s) associated with each data element of the plurality of data elements comprised within the loss assessment matrices and the confidence level(s) and/or rating(s) associated with the quality of the overall match of the loss assessment matrix to one or more historical loss assessment matrices may be configured to dynamically change over time. The changes may be determined by machine learning algorithms (e.g., Hidden Markov Model, Recurrent Neural Net, etc.) configured to place additional emphasis on the most recent historical loss assessment profile data included in historical data source database 154, Kelsh ¶110).
Taliwal teaches a second, or additional trained machine learning models, including CNNs (Taliwal ¶35-¶36).
As per claim 10, Kelsh and Taliwal disclose as shown above with respect to claim 1. Taliwal further teaches wherein the individual categories comprise Repairable, Borderline repairable, and total loss (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139).
The combination of Kelsh and Taliwal does not expressly disclose Borderline total loss. However, the Examiner asserts that it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the total loss, medium loss and small loss to include large loss, or “borderline total loss” since the Taliwal reference is already capable of making a loss determination based upon the factors and vehicular metadata. Furthermore, one of ordinary skill, before the effective filing date of the claimed invention, would have found it obvious to repeat the processes in claims 1 for individual categories because duplication is obvious, MPEP 2144.04.VI.B. The duplication of parts (or steps) has no patentable significance unless a new and unexpected result is produced. Examiner finds no evidence that performing the processes in claims 1 for large loss or borderline total loss would produce new and unexpected results as compared to performing the processes in claim 1 for a small, medium, or total loss.
As per claim 11, Kelsh and Taliwal disclose as shown above with respect to claim 1. Kelsh further discloses receiving a rank order and weight of the individual categories that adjusts the weighted decision for the individual categories (The weight(s) associated with each data element of the plurality of data elements comprised within the loss assessment matrices and the confidence level(s) and/or rating(s) associated with the quality of the overall match of the loss assessment matrix to one or more historical loss assessment matrices may be configured to dynamically change over time. The changes may be determined by machine learning algorithms (e.g., Hidden Markov Model, Recurrent Neural Net, etc.) configured to place additional emphasis on the most recent historical loss assessment profile data included in historical data source database 154, Kelsh ¶110).
As per claim 12, Kelsh and Taliwal disclose as shown above with respect to claim 1. Kelsh further discloses receiving a profile that adjusts the weighted decision for the individual categories (The weight(s) associated with each data element of the plurality of data elements comprised within the loss assessment matrices and the confidence level(s) and/or rating(s) associated with the quality of the overall match of the loss assessment matrix to one or more historical loss assessment matrices may be configured to dynamically change over time. The changes may be determined by machine learning algorithms (e.g., Hidden Markov Model, Recurrent Neural Net, etc.) configured to place additional emphasis on the most recent historical loss assessment profile data included in historical data source database 154, Kelsh ¶110).
As per claim 13, Kelsh and Taliwal disclose as shown above with respect to claim 1. Taliwal further teaches comparing the weighted decision with a confidence margin threshold; and based on the comparison, determine a second category associated with the weighted decision (determination of a “total loss,” Taliwal ¶38-¶40; output of the determination total loss, medium loss, small loss, ¶139) (Examiner notes the loss levels as including the confidence margin threshold in order to discern between the loss levels).
As per claim 14, Kelsh and Taliwal disclose as shown above with respect to claim 1. Kelsh further discloses removing question-answer data from the input that is applied to the set of trained machine learning models for individual categories; and supplementing determinations from the one or more image or video as the input that is applied to the set of trained machine learning models for individual categories (Pre-FNOL system 140 may analyze the one or more answers provided by the user and the one or more photos to determine a cost to repair the damages to vehicle 110 and accompanying insurance policy changes associated with filing a claim to cover the repair costs. In some instances, pre-FNOL system 140 may incorporate vehicle operation data received from any one, or combination of, vehicle operation sensors 111, telematics device 113, on-board computer 115 via vehicle communication system 114, and mobile computing device 120 and historical data provided by historical data source server 150 in determining the cost to repair the damages to vehicle 110 and accompanying insurance policy changes, Kelsh ¶45) (Examiner notes that the Kelsh system “may” analyze the answers which includes the ability to remove or not analyze the answers to the questions).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kelsh et al. (US PG Pub. 2018/0082378) and Taliwal et al. (US PG Pub. 2017/0293894) further in view of Mahler-Haug et al. (US PG Pub. 2025/0069148).
As per claim 9, Kelsh and Taliwal disclose as shown above with respect to claim 1. The combination of Kelsh and Taliwal do not expressly disclose wherein the question is generated using a generative AI process.
However, Mahler-Haug teaches wherein the question is generated using a generative AI process (generating user interface prompts, questions, Mahler-Haug ¶17; with generative artificial intelligence, ¶23 and ¶40).
The Kelsh, Taliwal, and Mahler-Haug references are analogous in that both are directed towards/concerned with vehicle damage assessment. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to use Mahler-Haug’s ability to generate response prompts with generative AI in Taliwal’s and Kelsh’s system to improve the system and method with reasonable expectation that this would result in a vehicle assessment system that is able to provide accurate damage assessments.
The motivation being that there is a need to improve assessment. Insurance claims are provided to insurance providers to receive insurance benefits, such as payouts, when an insured vehicle is stolen or damaged. Insurance providers may use statements surrounding an insurance claim to analyze insurance claims in order to determine damage severity and the associated cost of damages and/or financial liability in a given time period. However, gathering large amounts of insurance or claim data from a user can be time consuming and challenging (Mahler-Haug ¶2).
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.
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure can be located on the PTO-892.
Any inquiry concerning this communication or earlier communications from the Examiner should be directed to ANDREW B WHITAKER whose telephone number is (571)270-7563. The examiner can normally be reached on M-F, 8am-5pm, EST.
If attempts to reach the examiner by telephone are unsuccessful, the Examiner’s supervisor, Lynda Jasmin can be reached on (571) 272-6782. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-
automated- interview-request-air-form
/ANDREW B WHITAKER/Primary Examiner, Art Unit 3629
Prosecution Insights