Retail recommendation domain model

US7698170B1 · kind B1 · utility

Assignee

• Versata Development Group, Inc. · US

Inventors

• Timothy P. Darr · Bristow, US
• Thomas H. Dillon · Austin, US
• Sherrill J. Packebush · Austin, US
• Michael K. Grant · Austin, US
• James Singh · Austin, US
• Jacob Leffler · Austin, US
• Jeremy S. Wacksman · Evanston, US
• Neil C. Thier · Austin, US

Key dates

• Filing date: Aug 5, 2004
• Grant date: Apr 13, 2010
• Expiry date: Feb 11, 2029

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q30/02
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

A data processing system normalizes data sets (such as low-resolution transaction data) into high-resolution data sets by mapping generic information into attribute-based specific information that is stored in a database. By establishing a shared domain model for representing items in the recommendation context, catalog and quote history with common terms and concepts, a recommendation engine operating in the shared domain may process the attribute-based representations to make specific and relevant recommendations to the customer. In addition, when certain attribute values are normalized over time, recommendations derived from past order history can be intelligently applied to current orders. The normalized representation of elements in the shared domain may also be used to generate compelling selling point text for each recommendation that is specific to the marketing objectives of the seller and identifies the objectives of the buyer.