Real-Time Targeted Advertising in Brick-and-Mortar Stores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional advertising techniques are limited in reaching individual customers effectively, as they rely on mass media and cannot target specific preferences, tastes, or buying habits, leading to lower conversion rates and less effective use of advertising dollars.
Innovation Solution
A system that uses sensors such as face recognition, proximity sensors, and transaction recognition within brick-and-mortar stores to collect customer data and dynamically display targeted advertisements based on individual profiles, allowing for real-time updates and personalized messaging.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If mass media advertising is used to reach large numbers of viewers, then the coverage area is improved, but the targeting precision deteriorates
Solution Approach 1:
The patent segments the advertising message delivery by customer type, location, and timing. Different advertising content is presented to different customer segments (e.g., new customers vs. returning customers, different demographics) based on sensor data classification, allowing broad coverage while maintaining precise targeting for each segment.
Solution Approach 2:
The system implements local quality by customizing advertising content based on the specific characteristics of each customer or customer group. Advertising messages are tailored to match customer demographics, shopping behavior, and location within the store, ensuring that each customer receives locally optimized content rather than generic mass media advertising.
2Device complexity
If static advertisements are displayed in brick-and-mortar stores, then the device complexity is reduced, but the adaptability deteriorates
Solution Approach 1:
The patent transforms static advertising displays into dynamic systems that automatically adjust content based on real-time sensor data. Advertising messages change dynamically according to customer presence, demographics, and behavior patterns, enabling the system to adapt to different situations without requiring complex manual reconfiguration.
Solution Approach 2:
The advertising system performs self-service by automatically selecting and displaying appropriate advertisements based on sensor-collected customer information. The system autonomously processes customer data, determines relevant advertising content, and updates displays without human intervention, maintaining simplicity while achieving high adaptability.
3Loss of information
If sensors and sensing systems are deployed to collect customer information, then the information quality is improved, but the device complexity deteriorates
Solution Approach 1:
The patent employs multi-functional sensor systems that can collect various types of customer information (demographics, behavior patterns, location) using integrated sensing capabilities. The sensor network is designed to serve multiple advertising objectives simultaneously, reducing overall system complexity while maintaining high information quality across different data types.
4Ease of operation
If advertisements are updated weekly or monthly, then the ease of operation is improved, but the productivity deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where sensor data about customer responses to advertisements is continuously collected and used to automatically adjust and optimize ad content. This closed-loop system enables real-time updates based on measured effectiveness, increasing productivity without requiring manual operational intervention, thus maintaining ease of operation while achieving dynamic optimization.
Data Source
AI summary
Architecture for presenting advertisements in realtime in retail establishments. A sensor component includes sensors for collecting information about a customer or group of customers as they move through the store. The sensors can include capability for image processing, audio processing, light sensing, velocity sensing, direction sensing, proximity sensing, face recognition, pose recognition, transaction recognition, and biometric sensing, for example. A customer component analyzes the information and generates a profile about the customer. Advertisements are selected for presentation that target the customers as they walk in proximity of a presentation system of the store. An advertisement component facilitates dynamic presentation of a targeted advertisement to the individual as a function of the profile. The customer component can infer information during analysis using machine learning and reasoning.


