Method, medium, and system for intelligent receipt scanning and analysis

Patent metadata

Field	Value
Publication number	US-9865012-B2
Application number	US-201514634299-A
Country	US
Kind code	B2
Filing date	Feb 27, 2015
Priority date	Aug 22, 2014
Publication date	Jan 9, 2018
Grant date	Jan 9, 2018

Abstract

Intelligent receipt scanning and analysis may include scanning a receipt that includes information related to a product. The information related to the product may be transformed to text, and extracted from the text by utilizing a machine learning process. The extracted information may be compared to known information for a plurality of known products to identify the product as a known product of the plurality of known products or an unknown product. The extracted information related to the product and known product information, from the known information, for the known product of the plurality of known products may be analyzed in response to a determination that the extracted information is similar to the known product information for the known product of the plurality of known products.

First claim

What is claimed is:

1. An intelligent receipt scanning and analysis system which increases comprehension accuracy of a scanned receipt, comprising:
at least one processor;
an electronic receipt scanner, executed by the at least one processor, to scan a receipt, wherein the receipt includes information related to a product;
a scan transformer, executed by the at least one processor, to transform the information related to the product from the scanned receipt to text;
an information extractor, executed by the at least one processor, to utilize a machine learning process to extract the information related to the product from the text;
a product matcher, executed by the at least one processor, to compare the extracted information related to the product to known information for a plurality of known products to identify the product as a known product of the plurality of known products or an unknown product by:
comparing a description of the product with product labels of the plurality of known products; and
in response to a determination that
the description of the product is within a specified distance to a product label of the product labels of the plurality of known products, and
a price of the product is within a specified high price threshold and a specified low price threshold compared to a price of one of the plurality of known products.

identifying the product as one of the plurality of known products; and

a product analyzer, executed by the at least one processor, to analyze the extracted information related to the product and known product information, from the known information, for the known product of the plurality of known products in response to a determination that the extracted information related to the product is similar to the known product information for the known product of the plurality of known products.

2. The intelligent receipt scanning and analysis system according to claim 1 , further comprising:
a report generator, executed by the at least one processor, to generate a report based on the analysis of the extracted information related to the product and the known product information for the known product of the plurality of known products, wherein the report includes identification of purchasers of the product.

3. The intelligent receipt scanning and analysis system according to claim 1 , further comprising:
a report generator, executed by the at least one processor, to generate a report based on the analysis of the extracted information related to the product and the known product information for the known product of the plurality of known products, wherein the report includes identification of potential purchasers of the product.

4. The intelligent receipt scanning and analysis system according to claim 1 , further comprising:
a report generator, executed by the at least one processor, to generate a report based on the analysis of the extracted information related to the product and the known product information for the known product of the plurality of known products, wherein the report includes identification of a lowest price of the product.

5. The intelligent receipt scanning and analysis system according to claim 1 , wherein the receipt scanner includes a mobile phone.

6. The intelligent receipt scanning and analysis system according to claim 1 , wherein the extracted information related to the product includes at least one of
a purchase location of the product,
the description of the product, or
the price of the product.

7. The intelligent receipt scanning and analysis system according to claim 1 , wherein the receipt scanner is to scan the receipt by generating a plurality of snapshots of the receipt at a specified constant rate.

8. The intelligent receipt scanning and analysis system according to claim 1 , wherein the information extractor is to utilize the machine learning process to estimate a pattern for the receipt.

9. The intelligent receipt scanning and analysis system according to claim 8 , wherein the pattern is based on a location of at least one of
a price in a products zone of the receipt,
a seller name in a seller zone of the receipt,
a date in a date zone of the receipt, or
a numerical amount in an amount total zone of the receipt.

10. The intelligent receipt scanning and analysis system according to claim 1 , wherein the information extractor is to utilize the machine learning process to estimate a pattern for a product line related to the product.

11. The intelligent receipt scanning and analysis system according to claim 10 , wherein the pattern is based on a location of at least one of
a price in a price zone of the receipt, or
a numerical amount in an amount total zone of the receipt that matches a total of all prices in the price zone of the receipt.

12. The intelligent receipt scanning and analysis system according to claim 1 , wherein the product matcher is to compare the extracted information related to the product to known information for a plurality of known products by:
comparing the description of the product with the product labels of the plurality of known products;
in response to a determination that the description of the product matches the product label of the product labels of the plurality of known products, identifying the product as the known product of the plurality of known products; and
in response to a determination that the description of the product matches a plurality of the product labels of the plurality of known products, analyzing at least one of seller information related to a seller of the product or price information related to the price of the product.

13. The intelligent receipt scanning and analysis system according to claim 12 , wherein analyzing price information related to the price of the product further comprises:
comparing the price of the product to prices of known products related to the plurality of the product labels of the plurality of known products; and
identifying the product as the one of the known products related to the plurality of the product labels of the plurality of known products for which the price of the product is closest to a price of the one of the known products.

14. The intelligent receipt scanning and analysis system according to claim 12 , wherein analyzing price information related to the price of the product further comprises:
comparing the price of the product to prices of known products related to the plurality of the product labels of the plurality of known products; and
identifying the product as the one of the known products related to the plurality of the product labels of the plurality of known products for which the price of the product is within the specified high price threshold and the specified low price threshold compared to the price of the one of the known products.

15. The intelligent receipt scanning and analysis system according to claim 1 , wherein the product matcher is to compare the extracted information related to the product to known information for a plurality of known products to identify the product as a known product of the plurality of known products or an unknown product by:
generating a probability of the identification of the product as the one of the known products; and
in response to a determination that the probability of the identification of the product as the one of the known products is greater than a specified probability threshold, identifying the product as the one of the known products.

16. The intelligent receipt scanning and analysis system according to claim 1 , wherein the product analy

Assignees

• Accenture Global Services Ltd

Inventors

• Vidal Richard
• Souche Christian

Classifications

• G06Q30/00

  Commerce · CPC title

• G06F17/30253

  Physics · mapped topic

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06N99/005

  Physics · mapped topic

• G06F17/3061

  Physics · mapped topic