# US 10,319,007 B1 · Database image matching using machine learning with output estimation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,319,007 B1 - Document ID: US10319007B1 - Status: Granted - Kind: B1 - Application number: 15/915,998 - Filed: 2018-03-08 - Granted: 2019-06-11 - Earliest claimed: 2018-03-08 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Qiaochu Tang; Sunil Subrahmanyam Vasisht; Stephen Michael Wylie; Geoffrey Dagley; Micah Price; Jason Richard Hoover - Web page: https://patentgrep.com/patent/US10319007B1 ## CPC - G06Q 30/06: Buying, selling or leasing transactions - G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information} - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06N 3/084: Backpropagation, e.g. using gradient descent - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for processing an image including a vehicle using machine learning can include determining a location of the client device. The method can further include receiving a first image of a vehicle from an image sensor of the client device and matching, using machine learning, the first image to one or more images of vehicles in a vehicle database to identify the vehicle. The vehicle database can list vehicles located at the determined location of the client device and images of the vehicles. The method can include retrieving vehicle information from the vehicle database, based on the identified vehicle, and obtaining comparison information based at least in part on the vehicle information. The method can include estimating a quote for the vehicle based on the comparison information and transmitting the estimated quote for display on the client device. ## Claims ### Claim 1 A system for processing an image including a vehicle using machine learning, comprising: a processor in communication with a client device; and a storage medium storing instructions that, when executed, cause the processor to perform operations comprising: determining a location of the client device; mapping the location of the client device to a vehicle dealership; receiving a first image of a vehicle from an image sensor of the client device; matching, using machine learning, the first image to one or more images of vehicles in a vehicle database of the vehicle dealership to identify the vehicle, the vehicle database listing vehicles located at the vehicle dealership, the vehicle database including images of the listed vehicles, wherein matching includes: inputting the image to an input layer of a first convolutional neural network; extracting features indicating characteristics of the vehicle from an output layer of the first convolutional neural network; inputting the extracted features to an input layer of a second convolutional neural network; determining attributes of the vehicle from an output layer of the second convolutional neural network; and determining the identified vehicle as a vehicle in the matched one or more images in the database having associated attributes matching the determined attributes; retrieving vehicle information from the vehicle database, based on the identified vehicle; obtaining comparison information from a comparison resource of a service provider based at least in part on the vehicle information; estimating a quote for the identified vehicle based on the comparison information; and transmitting the estimated quote for display on the client device. ### Claim 2 (depends on 1) The system of claim 1, wherein the operations further comprise: determining that the first image is below an acceptability threshold; and transmitting information for display on the client device, the information including an error message or a guiding line for obtaining a second image of the vehicle. ### Claim 3 (depends on 1) The system of claim 1, wherein obtaining the comparison information further comprises retrieving pricing information based at least in part on the vehicle information. ### Claim 4 (depends on 3) The system of claim 3, wherein the pricing information is retrieved based at least in part on personal information of a user of the client device. ### Claim 5 (depends on 3) The system of claim 3, wherein estimating the quote for the vehicle comprises calculating statistics of the pricing information. ### Claim 6 (depends on 5) The system of claim 5, wherein estimating the quote for the vehicle comprises receiving selections or modifications of financing terms and recalculating statistics of the pricing information based on the received selections or modifications of the financing terms. ### Claim 7 (depends on 1) The system of claim 1, wherein the processor and the comparison resource are associated with distinct service providers. ### Claim 8 A computer-implemented method for processing an image including a vehicle using machine learning, the method comprising: determining a location of a client device; mapping the location of the client device to a vehicle dealership; receiving a first image of a vehicle from an image sensor of the client device; matching, by a system using machine learning, the first image to one or more images of vehicles in a vehicle database of the vehicle dealership to identify the vehicle, the vehicle database listing vehicles located at the vehicle dealership, the vehicle database including images of the listed vehicles, wherein matching includes: inputting the image to an input layer of a first convolutional neural network; extracting features indicating characteristics of the vehicle from an output layer of the first convolutional neural network; inputting the extracted features to an input layer of a second convolutional neural network; determining attributes of the vehicle from an output layer of the second convolutional neural network; and determining the identified vehicle as a vehicle in the matched one or more images in the database having associated attributes matching the determined attributes; retrieving vehicle information from the vehicle database, based on the identified vehicle; obtaining comparison information from a comparison resource of a service provider based at least in part on the vehicle information; estimating a quote for the identified vehicle based on the comparison information; and transmitting the estimated quote for display on the client device. ### Claim 9 (depends on 8) The method of claim 8, further comprising: determining that the first image is below an acceptability threshold; and transmitting information for display on the client device, the information including an error message or a guiding line for obtaining a second image of the vehicle. ### Claim 10 (depends on 8) The method of claim 8, wherein obtaining the comparison information further comprises retrieving pricing information. ### Claim 11 (depends on 10) The method of claim 10, wherein the pricing information is retrieved based at least in part on personal information of a user of the client device. ### Claim 12 (depends on 10) The method of claim 10, wherein estimating the quote for the vehicle comprises calculating statistics of the pricing information. ### Claim 13 (depends on 12) The method of claim 12, wherein estimating the quote for the vehicle comprises receiving selections or modifications of financing terms and recalculating statistics of the pricing information based on the received selections or modifications of the financing terms. ### Claim 14 (depends on 8) The method of claim 8, wherein the comparison resource stores pricing information, vehicle-related information, and personal information, and wherein the quote for the vehicle is estimated based on pricing information, vehicle-related information, and personal information retrieved from the comparison resource. ### Claim 15 (depends on 8) The method of claim 8, wherein the system and the comparison resource are associated with distinct service providers. ### Claim 16 A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to operate a computer system for processing an image including a vehicle using machine learning, comprising: determining a location of a client device; mapping the location of the client device to a vehicle dealership; receiving a first image of a vehicle from an image sensor of the client device; matching, using machine learning, the first image to one or more images of vehicles in a vehicle database of the vehicle dealership to identify the vehicle, the vehicle database listing vehicles located at the vehicle dealership, the vehicle database including images of the listed vehicles, wherein matching includes: inputting the image to an input layer of a first convolutional neural network; extracting features indicating characteristics of the vehicle from an output layer of the first convolutional neural network; inputting the extracted features to an input layer of a second convolutional neural network; determining attributes of the vehicle from an output layer of the second convolutional neural network; and determining the identified vehicle as a vehicle in the matched one or more images in the database having associated attributes matching the determined attributes retrieving vehicle information from the vehicle database, based on the identified vehicle; obtaining comparison information from a comparison resource of a service provider based at least in part on the vehicle information; estimating a quote for the identified vehicle based on the comparison information; and transmitting the estimated quote for display on the client device. ### Claim 17 (depends on 16) The non-transitory computer-readable medium of claim 16, wherein the computer system and the comparison resource are associated with distinct service providers.