Method and system for targeted marketing by leveraging video-based demographic insights

• US 7,617,981 B2
• Filed: 06/07/2007
• Issued: 11/17/2009
• Est. Priority Date: 04/28/2005
• Status: Active Grant

• Current Assignee: Toshiba Global Commerce Solutions Holdings Corporation (Toshiba Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Dietrich, Brenda Lynn, Hampapur, Arun, Senior, Andrew W., Apte, Chidanand
• Primary Examiner(s): Hess; Daniel A
• Application Number:
  US11/759,367
• Publication Number:
  US 20070228141A1
• Time in Patent Office: 894 Days
• Field of Search: 235/454, 235/462.01, 902/22, 705/14, 705/16, 705/18, 705/21
• US Class Current: 235/454
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/208 Input by product or record sensing, e.g. weighing or scanner processing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Demographic and transaction data are presented in a report usable for marketing-related purposes and other applications using a camera apparatus to capture customer image data at a point-of-sale location and sends the image data to a customer image database where the image data is stored. Demographic data (such as gender, age group, height) are extracted from the customer image data and sent to the customer image database. Point-of-sale transaction data is collected and sent to a transaction database where the transaction data is stored. A computer processes customer image data, transaction data, and attributes relating to the customer image data and transaction data, to correlate extracted demographic data to transaction data. The correlated data is preferably sent to a target marketing database and used to generate a market research report.

Claims

1. A method for generating statistical analysis of customer demographics and point-of-sale transactions, comprising:

receiving a transaction data from a point of sale terminal, having transaction data reflecting a customer transaction, and generating a corresponding plurality of transaction attributes including a transaction date/time data, a purchased item identifier attribute, and a purchase price attribute;

optically scanning the transaction location over a time period including the transaction date/time represented by said transaction date/time data, and generating a corresponding time sequence of customer image data associated with said transaction, said customer image data including a scanning date/time data;

extracting a plurality of customer attributes from said time sequence of customer image data associated with said transaction, said attributes including a customer age attribute, a customer gender attribute, and a customer demographic attribute;

classifying said customer according to said extracted customer attributes associated with said transaction, based on a given customer classification scheme, wherein said customer classification scheme includes a customer demographic classification, and generating a corresponding customer classification data having a customer demographic classification data, wherein said classifying is based in part on said transaction date/time data;

classifying said transaction according to said attributes associated with said transaction, based on a given transaction classification scheme, wherein said classification scheme includes a transacted item classifier, and generating a corresponding transaction classification data having a transacted item classification data;

repeating said receiving a transaction data from a point of sale terminal, optically scanning the transaction location, extracting a plurality of customer attributes, classifying said customer, and classifying said transaction over a given time period to generate a plurality of customer classifier data and transaction classifier data;

storing said plurality of customer classifier data and transaction classifier data to form a transaction database reflecting a plurality of transaction and, for each transaction, the corresponding customer classification data and transaction classification data;

correlating said customer classification data and said transaction classification data, said correlating including calculating a correlation between the customer demographics classification data and the items transacted classification data, and generating a corresponding correlation data; and

generating a market report data, based on said correlation data.