IP Library Granted Patent US 11,823,139
Granted Patent B2
US 11,823,139 · App. 16/261,235 · Granted Nov 21, 2023

Image-based transaction processing

Inventor: Itamar David Laserson (Givat Shmuel, IL)
Assignee: NCR Corporation
G06Q20/047G06F3/0482G06Q20/045G06Q20/327G06T7/13G06V30/416G06K7/1413G06K7/1417G06V30/10H04N23/64
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,823,139
App. No.
16/261,235
Granted
Nov 21, 2023
Kind
B2
Abstract

An image of a transaction receipt is obtained and optical character recognition (OCR) is processed on the image to identify a transaction identifier, a transaction total, and a handwritten amount associated with a transaction. When a confidence value associated with the OCR is above a threshold value, the handwritten amount is processed automatically through a transaction interface for the transaction to update the transaction total for the transaction.

Claims (28)

1. A method, comprising:

providing a processor of a cloud-based server executable instructions from a non-transitory computer-readable storage medium causing the processor to perform processing comprising:

obtaining an image associated with a transaction receipt for a transaction;

identifying from the image a transaction identifier, and a transaction total and an electronic payment system (EPS) associated with the transaction receipt, wherein identifying further includes identifying the transaction identifier from a barcode or Quick Response (OR) represented within the image;

determining whether the transaction total is to be adjusted based on a handwritten amount recognized in the image by processing a specialized Optical Character Recognition (OCR) that makes an assumption as to a location of a decimal point to identify a tip amount from the handwritten amount in order to revise the transaction total by the tip amount using the transaction total and an expected percentage for the tip amount and numerical digits identified in the handwritten amount wherein when the handwritten amount includes no separator character at all in the numerical digits, wherein determining further includes performing specialized OCR on the image based on the handwritten amount being restricted to a currency amount for a currency;

completing the transaction with the handwritten amount added to the transaction total through interaction with a transaction interface associated with the EPS based on the transaction identifier;

interacting with an application interface of a mobile application that provided the image of the transaction receipt and based on the interacting providing a running total for processed tips for a given day for a given attendant, providing specific transactions and corresponding specific tips, providing particular transactions for which there were given tip amounts that were above what is considered customary and for which there were no tips given at all, and further based on the interacting recording comments provided by the given attendant through the mobile application on attendant identified transactions;

operating the cloud-based server executable instructions in a mobile device mode of operation, wherein during the mobile device mode of operation individual transaction receipts are processed in real time

operating the cloud-bases server executable instructions in a scanner-based batch mode of operation, wherein during the scanner-based batch mode of operation the individual transaction receipts are stored and processed in batches;

maintaining certain receipts that exceed a threshold amount for confirmation and providing a listing of the certain receipts through the transaction interface; and

processing the method without requiring manual interaction with the EPS system by the given attendant.

2. The method of claim 1 further comprising, iterating back to the obtaining for a plurality of images associated with a plurality of transactions.

3. The method of claim 1 , wherein determining further includes flagging the transaction identifier and the image when the handwritten amount exceeds a predefined percentage of the transaction total.

4. The method of claim 1 , wherein determining further includes flagging the transaction identifier and the image when a presence of the handwritten amount is detected within the image but is unable to be recognized as a specific numerical value.

5. The method of claim 1 , wherein completing further includes batching the handwritten amount, the transaction identifier, and the image for batch processing with the transaction interface during the scanner-batch mode of operation.

6. The method of claim 5 , wherein batching further includes maintaining exception images associated with other transactions that were unable to be included with the batch processing.

7. The method of claim 1 , wherein completing further includes process an Application Programming Interface (API) for automated interaction with the transaction interface to complete the transaction.

8. A system, comprising:

a server device having at least one processor configured to execute instructions from a non-transitory computer-readable storage medium, the instructions representing a transaction completion manager;

a mobile device having at least one processor configured to execute instructions from a non-transitory computer-readable storage medium, the instructions representing a mobile application;

the mobile application is provided to the at least one processor of the mobile device causing the at least one processor of the mobile device to perform processing to:

initiate a camera when the mobile application is launched for execution on the mobile device, automatically send an image captured by the camera as a transaction receipt having a handwritten tip to the transaction completion manager, and process an application interface to the service device; and

the transaction completion manager is provided to the at least one processor of the server device causing the at least one processor of the server device to perform processing to:

identify a user associated with the mobile device on receipt of the image from the mobile application, identify a transaction identifier from a barcode or Quick Response (OR) represented within the image, perform optical character recognition on the image to identify a transaction identifier, a transaction total, an electronic payment system (EPS), and the handwritten tip, determine the handwritten tip by processing a specialized Optical Character Recognition (OCR) on the image based on the handwritten tip being restricted to a currency amount for a currency and that makes an assumption as to a location of a decimal point to identify a tip amount from the handwritten tip in order to revise the transaction total by the tip amount using the transaction total and an expected percentage for the tip amount and numerical digits identified in the handwritten tip, wherein when the handwritten tip includes no separator character at all in the handwritten tip, interact with a transaction interface of the EPS to update the transaction total to include the handwritten tip using the transaction identifier;

interact with the application interface of the mobile application and based on interactions with the application interface provide a running total for processed tips for a given day for the user, provide specific transactions and corresponding specific tips, provide particular transactions for which there were given tip amounts that were above what is considered customary and for which there were no tips given at all, further based on the interactions with the application interface record comments provided by the user through the mobile application on user identified transactions, and to operate in a mobile device mode of operation and to operate in a scanner-based batch mode of operation, wherein during the mobile device mode of operation individual transaction receipts are processed in real time and during the scanner-based batch mode of operation the individual transaction receipts are stored and processed in batches;

maintain certain receipts that exceed a threshold amount for confirmation and providing a listing of the certain receipts through the transaction interface; and

process the transaction completion manager without requiring manual interaction with the EPS by the user.

9. The system of claim 8 , wherein the transaction completion manager is further configured to perform processing to: maintain exception images from received transaction receipt images for which the transaction completion manager was unable to identify at least one of: a transaction identifier, a transaction total, and the handwritten tip.

Assignments (5)
CHANGE OF NAME Recorded Nov 9, 2023
From: NCR CORPORATION
To: NCR VOYIX CORPORATION
Reel/Frame 065532/0893 →
SECURITY INTEREST Recorded Oct 25, 2023
From: NCR VOYIX CORPORATION
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 065346/0168 →
CORRECTIVE ASSIGNMENT TO CORRECT THE PROPERTY NUMBERS SECTION TO REMOVE PATENT APPLICATION: 15000000 PREVIOUSLY RECORDED AT REEL: 050874 FRAME: 0063. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST. Recorded Apr 12, 2021
From: NCR CORPORATION
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 057047/0161 →
SECURITY INTEREST Recorded Oct 29, 2019
From: NCR CORPORATION
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 050874/0063 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 29, 2019
From: LASERSON, ITAMAR DAVID
To: NCR CORPORATION
Reel/Frame 048170/0779 →
Continuity (1)
Related Publication 20200242582A1 · Jul 30, 2020