Attribute fill using text extraction

US10102195B2 · kind B2 · utility

Assignee

• AMAZON TECHNOLOGIES, INC. · US

Inventors

• Jianhui Wu · Chengdu, CN
• Taibai Xu · Seattle, US
• Wenke Zhang · Burlingame, US
• Rongzhou Shen · Bothell, US
• Krishnamurthy Viswanathan · Village of La Jolla, US
• Gabriel Parent · Keyano, CA
• Jiwei Cao · Jingwei, CN
• Debprakash Patnaik · Bengaluru, IN

Key dates

• Filing date: Jun 25, 2014
• Grant date: Oct 16, 2018
• Expiry date: Nov 11, 2034

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q30/06
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Systems and methods involve filling missing attribute values from unstructured text. A computing device may provide a plurality of items, such as an item catalog for an electronic marketplace. When an item is found to have a missing attribute value, a plurality of existing values for that attribute is compiled by mining other items. Text associated with the item is parsed to determine possible values for the attribute. From those possible values, the most likely value is identified and the missing attribute value is populated with that value.