Patent Issued for Systems and methods for using image analysis to automatically determine vehicle information (USPTO 11830265): State Farm Mutual Automobile Insurance Company

2023 DEC 20 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States) has been issued patent number 11830265, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Antonetti, Joseph (Champaign, IL, US), Foreman, Gary (Champaign, IL, US), Imran, Abid (Champaign, IL, US), Loew, Justin (Champaign, IL, US), Moon, Calvin (Urbana, IL, US).

This patent was filed on June 3, 2022 and was published online on November 28, 2023.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Entities who maintain and process accounts for individuals sometimes require accountholders to submit certain information associated with their accounts. For example, insurance companies sometimes require their policyholders to submit odometer readings for vehicles covered by insurance policies, where the insurance companies may use the odometer readings for various insurance processing and for maintaining account information. Generally, the entities must manually review and identify the relevant information and update the accounts to reflect the information.

“However, these submissions and reportings may be inaccurate and/or may include information reported in a fraudulent manner. This results in inaccurate account information which can negatively impact costs for individuals. Additionally, and especially in instances of fraudulently-reported information, increased costs may be passed down to individuals.

“Accordingly, there is an opportunity to analyze individual-submitted information for accuracy, such that respective accounts may be accurately updated.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “In an embodiment, a computer-implemented method of analyzing image data associated with a vehicle of an individual is provided. The method may include accessing a digital image depicting an alphanumeric string, generating, by a computer processor, a set of filtered digital images using the digital image, analyzing, by the computer processor, the set of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in a set of OCR results respectively associated with the set of filtered digital images, analyzing the set of OCR results to identify a set of common elements representative of the alphanumeric string depicted in the digital image, and determining a machine-encoded alphanumeric string based on the set of common elements.

“In another embodiment, a system for analyzing image data associated with a vehicle of an individual is provided. The system may include a memory storing a set of computer-executable instructions, and a processor interfacing with the memory. The processor may be configured to execute the computer-executable instructions to cause the processor to: access a digital image depicting an alphanumeric string, generate a set of filtered digital images using the digital image, analyze the set of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in a set of OCR results respectively associated with the set of filtered digital images, analyze the set of OCR results to identify a set of common elements representative of the alphanumeric string depicted in the digital image, and determine a machine-encoded alphanumeric string based on the set of common elements.”

The claims supplied by the inventors are:

“1. A computer-implemented method of analyzing image data, the method comprising: accessing, by a computer processor, a plurality of optical character recognition (OCR) results respectively generated from a plurality of digital images depicting an alphanumeric string, wherein each of the plurality of OCR results includes a confidence level for each character in the respective OCR result; analyzing the plurality of OCR results to identify a set of common elements extracted from at least a portion of the plurality of OCR results; and determining each character of a machine-encoded alphanumeric string based on the set of common elements and the confidence level for each character in the respective OCR result of the plurality of OCR results, wherein the machine-encoded alphanumeric string is representative of the alphanumeric string depicted in the plurality of digital images.

“2. The computer-implemented method of claim 1, wherein the plurality of digital images is a plurality of filtered digital images, and wherein the computer-implemented method further comprises: generating, by the computer processor, the plurality of filtered digital images using a digital image; and analyzing, by the computer processor, the plurality of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in the plurality of OCR results respectively associated with the plurality of filtered digital images.

“3. The computer-implemented method of claim 2, wherein generating the plurality of filtered digital images using the digital image comprises: generating a first filtered digital image by applying a first digital filter to the digital image; and generating a second filtered digital image by applying a second digital filter to the digital image.

“4. The computer-implemented method of claim 1, further comprising: applying a set of rules to the plurality of OCR results to remove at least a portion of the plurality of OCR results.

“5. The computer-implemented method of claim 4, wherein applying the set of rules to the plurality of OCR results comprises: determining, for an OCR result of the plurality of OCR results, that the OCR result indicates a string comprising a number of digits that exceeds a threshold number of digits; and removing the OCR result.

“6. The computer-implemented method of claim 4, wherein applying the set of rules to the plurality of OCR results comprises: accessing a previously-reported metric associated with an account of an individual; comparing the previously-reported metric to an OCR result of the plurality of OCR results to determine that content of the OCR result is not possible; and removing the OCR result.

“7. The computer-implemented method of claim 1, wherein analyzing the plurality of OCR results to identify the set of common elements comprises: analyzing the plurality of OCR results using at least one string metric to identify the set of common elements.

“8. A system for analyzing image data, comprising: a memory storing a set of computer-executable instructions; and a processor interfacing with the memory, and configured to execute the computer-executable instructions to cause the processor to: access a plurality of optical character recognition (OCR) results respectively generated from a plurality of digital images depicting an alphanumeric string, wherein each of the plurality of OCR results includes a confidence level for each character in the respective OCR result, analyze the plurality of OCR results to identify a set of common elements extracted from at least a portion of the plurality of OCR results, and determine each character of a machine-encoded alphanumeric string based on the set of common elements and the confidence level for each character in the respective OCR result of the plurality of OCR results, wherein the machine-encoded alphanumeric string is representative of the alphanumeric string depicted in the plurality of digital images.

“9. The system of claim 8, wherein the plurality of digital images is a plurality of filtered digital images, and wherein the processor is configured to execute the computer-executable instructions to further cause the processor to: generate the plurality of filtered digital images using a digital image, and analyze the of plurality of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in the plurality of OCR results respectively associated with the plurality of filtered digital images.

“10. The system of claim 9, wherein to generate the plurality of filtered digital images using the digital image, the processor is configured to: generate a first filtered digital image by applying a first digital filter to the digital image, and generate a second filtered digital image by applying a second digital filter to the digital image.

“11. The system of claim 8, wherein the processor is configured to execute the computer-executable instructions to further cause the processor to: apply a set of rules to the plurality of OCR results to remove at least a portion of the plurality of OCR results.

“12. The system of claim 11, wherein to apply the set of rules to the plurality of OCR results, the processor is configured to: determine, for an OCR result of the plurality of OCR results, that the OCR result indicates a string comprising a number of digits that exceeds a threshold number of digits, and remove the OCR result.

“13. The system of claim 11, wherein to apply the set of rules to the plurality of OCR results, the processor is configured to: access a previously-reported metric associated with an account of an individual, compare the previously-reported metric to an OCR result of the set of OCR results to determine that content of the OCR result is not possible, and remove the OCR result.

“14. The system of claim 8, wherein to analyze the plurality of OCR results to identify the set of common elements, the processor is configured to: analyze the plurality of OCR results using at least one string metric to identify the set of common elements.

“15. A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors, the instructions comprising: instructions for accessing a plurality of optical character recognition (OCR) results respectively generated from a plurality of digital images depicting an alphanumeric string, wherein each of the plurality of OCR results includes a confidence level for each character in the respective OCR result; instructions for analyzing the plurality of OCR results to identify a set of common elements extracted from at least a portion of the plurality of OCR results; and instructions for determining each character of a machine-encoded alphanumeric string based on the set of common elements and the confidence level for each character in the respective OCR result of the plurality of OCR results, wherein the machine-encoded alphanumeric string is representative of the alphanumeric string depicted in the plurality of digital images.

“16. The non-transitory computer-readable storage medium of claim 15, wherein the plurality of digital images is a plurality of filtered digital images, and wherein the instructions further comprise: instructions for generating the plurality of filtered digital images using a digital image; and instructions for analyzing the plurality of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in the plurality of OCR results respectively associated with the plurality of filtered digital images.

“17. The non-transitory computer-readable storage medium of claim 16, wherein the instructions for generating the plurality of filtered digital images using the digital image comprise: instructions for generating a first filtered digital image by applying a first digital filter to the digital image; and instructions for generating a second filtered digital image by applying a second digital filter to the digital image.

“18. The non-transitory computer-readable storage medium of claim 15, wherein the instructions further comprise: instructions for applying a set of rules to the plurality of OCR results to remove at least a portion of the set of OCR results.

“19. The non-transitory computer-readable storage medium of claim 18, wherein the instructions for applying the set of rules to the plurality of OCR results comprise: instructions for determining, for an OCR result of the plurality of OCR results, that the OCR result indicates a string comprising a number of digits that exceeds a threshold number of digits; and instructions for removing the OCR result.

“20. The non-transitory computer-readable storage medium of claim 18, wherein the instructions for applying the set of rules to the plurality of OCR results comprise: instructions for accessing a previously-reported metric associated with an account of an individual; instructions for comparing the previously-reported metric to an OCR result of the plurality of OCR results to determine that content of the OCR result is not possible; and instructions for removing the OCR result.”

For the URL and additional information on this patent, see: Antonetti, Joseph. Systems and methods for using image analysis to automatically determine vehicle information. U.S. Patent Number 11830265, filed June 3, 2022, and published online on November 28, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11830265)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)