Browse Prior Art Database

System and method for assessing consumer interaction via pattern detection and prediction in social networks

IP.com Disclosure Number: IPCOM000247311D
Publication Date: 2016-Aug-22
Document File: 4 page(s) / 119K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is an Assessing Consumer Interaction system and method that works with Internet of Things (IoT) technologies to learn a user’s food preferences and daily interactions and behaviors, and then apply that information to determine a marketing strategy and/or recommend purchasing options to consumers.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 37% of the total text.

Page 01 of 4

System and method for assessing consumer interaction via pattern detection and prediction in social networks

The novel contribution is an Assessing Consumer Interaction system and method that

works with Internet of Things (IoT) technologies to learn a user's food preferences and daily interactions and behaviors, and then apply that information to determine a marketing strategy and/or recommend purchasing options to consumers.

The core novelty is the consideration of the user's context(e.g., location, social environment, time of the day, activity, health state, etc.) and subsequent recommendation of suitable substitutions. The system learns from the user's behavior, social network, and other connections to develop new and effective substitutions, which it then recommends directly to the user, the retailer, or both.

For example, the system learns how a person with celiac disease interacts/behaves in a grocery store. Based on that knowledge, the system can execute a marketing strategy to meet the customer´s needs. Even in large supermarkets, the system can let the user know the location of a specific item or comparable substitutes to meet the user's needs. Because of its machine learning properties, the system stores information about the user's purchasing patterns, and then applies those patterns to new locations (e.g., user purchase an item at a chain store in one country, and the system can indicate the location of the same item at the store in another country).

In addition, a person can manually enter temporary dietary preferences (e.g., dietary restrictions due to medical treatment). If the system has information from users with the same or similar requirements, it can apply that information to offer selections to the user that has recently entered preferences/conditions. The system may learn from cohorts to enable people with similar preferences and dietary needs to benefit from one another, especially when people travel to locations where the options are unfamiliar.

The system may also learn from the combinations of products and suggest alternative actions, such as a recipe. For example, if the user typically purchases the same products, then the system can suggest possible/alternative recipes.

In an IoT synchronization, the user enters a profile from a device (e.g., mobile application, store loyalty card system, etc.) into the system. The system learns the user's preferences and accordingly displays information on a tablet for the user.

Data inputs for the system include:


• Food preferences (e.g., vegan, vegetarian, diabetic, celiac disease, health/fitness, kosher, etc.)

• Time spent in a specific product, row, group of products, etc.

• User company (e.g., is consumer buying alone or with company?) • Date/Time • Local events (e.g., holidays, festivals, etc.)

• Current location

1


Page 02 of 4

• Mood (e.g., tired, excited, calm, etc.)

• User expectation (e.g., user may qualify products as bad, good, excellent...