Granted Patent B1

US 9,922,375 · App. 14/493,059 · Granted Mar 20, 2018

Inventor: Alan Neveu (Wilmington, NC)

Assignee: Certify, Inc.

G06Q40/12G06K9/18

Abstract

Claims (44)

1. A method of parsing receipt information using a computer system, the method comprising:

receiving, by the computer system, an image of a receipt;

requesting execution of an optical character recognition (OCR) component to convert the image to text;

accessing a plurality of regular expressions associated with a plurality of vendor elements;

identifying a string of characters in the text that match a character pattern specified by at least one regular expression of the plurality of regular expressions, wherein the at least one regular expression includes metacharacters;

capturing a value of a vendor element from the text, wherein the value of the vendor element comprises the string of characters that match the character pattern;

accessing reference data specifying additional elements associated with the value of the vendor element and information to identify values of the additional elements;

capturing the values of the additional elements in the text based on the reference data, wherein the act of capturing the values includes:

searching the text for regular expressions associated with the additional elements; and

locating the values of the additional elements using receipt format information associated with the additional elements that specifies locations for the values relative to the regular expressions; and

storing the value of the vendor element and the values of the additional elements in a data store.

2. The method of claim 1 , further comprising identifying a category for a transaction described by the receipt.

3. The method of claim 2 , wherein identifying the category includes identifying the category using at least one of the value of the vendor element and the values of the additional elements.

4. The method of claim 1 , wherein receiving the image includes receiving an image from an external system.

5. A non-transitory computer readable medium storing sequences of computer executable instructions to implement a method for parsing receipt information, the sequences of instructions including instructions to:

receive an image of a receipt;

request execution of an optical character recognition (OCR) component to convert the image to text;

access a plurality of regular expressions associated with a plurality of vendor elements;

identify a string of characters in the text that match a character pattern specified by at least one regular expression of the plurality of regular expressions, wherein the at least one regular expression includes metacharacters;

capture a value of a vendor element from the text, wherein the value of the vendor element comprises the string of characters that match the character pattern;

access reference data specifying additional elements associated with the value of the vendor element and information to identify values of the additional elements;

capture the values of the additional elements in the text based on the reference data, wherein capturing the values of the additional elements includes:

searching the text for regular expressions associated with the additional elements; and

locating the values of the additional elements using receipt format information associated with the additional elements that specifies locations for the values relative to the regular expressions; and

store the value of the vendor element and the values of the additional elements in a data store.

6. The computer readable medium of claim 5 , wherein the sequences of instructions further include instructions to identify a category for a transaction described by the receipt.

7. The computer readable medium of claim 6 , wherein the instructions to identify the category include instructions to identify the category using at least one of the value of the vendor element and the values of the additional elements.

8. A system comprising:

a memory;

at least one processor in data communication with the memory;

an optical character recognition (OCR) component executable by the at least one processor; and

a receipt parsing component executable by the at least one processor and configured to:

receive an image of a receipt;

request execution of the OCR component to convert the image to text;

access a plurality of regular expressions associated with a plurality of vendor elements;

identify a string of characters in the text that match a character pattern specified by at least one regular expression of the plurality of regular expressions, wherein the at least one regular expression includes metacharacters;

capture a value of a vendor element from the text, wherein the value of the vendor element comprises the string of characters that match the character pattern;

access reference data specifying additional elements associated with the value of the vendor element and information to identify values of the additional elements;

capture the values of the additional elements in the text based on the reference data, wherein capturing the values of the additional elements includes:

searching the text for regular expressions associated with the additional elements; and

locating the values of the additional elements using receipt format information associated with the additional elements that specifies locations for the values relative to the regular expressions;

store the value of the vendor element and the values of the additional elements in a data store;

wherein the receipt parsing component is further configured to: identify a telephone number on the receipt and trigger a reverse telephone number lookup service to capture information on the vendor.

9. The method of claim 8 , further comprising identifying a telephone number on the receipt and triggering a reverse telephone number lookup service to capture information on the vendor.

Assignments (9)