Wireless Set-Top Box Ad Watching Detection via Wi-Fi Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advertisers lack the ability to determine if users are watching advertisements and discern their sentiments, leading to inefficiencies in ad placement and customization.
Innovation Solution
A system comprising a set-top box (STB) and router that use machine learning models to detect user presence and sentiment through Wi-Fi sensing, voice detection, remote control activity, and television state, generating reports for advertisers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If advertisers purchase advertisement slots without user presence verification, then advertisement delivery is simple and fast, but advertisers cannot know if users are watching the advertisements
Solution Approach 1:
The patent introduces an intermediary detection system comprising a processor and sensor array that mediates between the advertisement delivery system and users. This intermediary captures images and videos during advertisement playback and analyzes them to determine user presence and engagement, thereby providing the missing information without requiring direct complex interaction between advertisers and users.
Solution Approach 2:
The patent replaces manual verification methods with automated image and video analysis systems. The processor automatically analyzes captured visual data to detect user presence, advertisement viewing status, and even user reactions, substituting mechanical human verification with automated computational analysis.
2Loss of information
If no user sentiment detection is implemented, then advertisement system operation is simple, but advertisers cannot discern user sentiments or customize advertisements effectively
Solution Approach 1:
The system introduces an intermediary sentiment analysis component that processes visual and audio data captured during advertisement playback. This intermediary analyzes user facial expressions, body language, and verbal reactions to determine sentiment, providing advertisers with actionable insights without requiring direct complex sentiment detection infrastructure.
Solution Approach 2:
The patent replaces subjective human sentiment assessment with automated image and video analysis algorithms. The processor analyzes visual cues such as facial expressions and body language, as well as audio cues, to objectively determine user sentiment toward advertisements, replacing manual evaluation with computational analysis.
3Loss of information
If advertisement slots are filled without viewing verification, then advertisement delivery efficiency is high, but advertisers cannot optimize ad placement based on actual viewing data
Solution Approach 1:
The patent implements a feedback mechanism where the detection system continuously monitors advertisement playback and user presence, then feeds this information back to the advertisement delivery system. This feedback loop enables real-time optimization of ad placement decisions based on actual viewing data, allowing advertisers to adjust their strategies dynamically.
Solution Approach 2:
The system replaces manual ad placement optimization with automated analysis of viewing data. The processor analyzes captured images and videos to determine whether advertisements are being viewed, then uses this data to optimize future ad slot allocation, replacing subjective decision-making with data-driven automation.
Data Source
AI summary
A wireless set top box (STB) determines whether a user is watching an advertisement on a display device. When playback of the advertisement starts, the STB requests a router to determine the presence of the user, and the router determines the presence by performing sensing (such as Wi-Fi sensing) in conjunction with using a machine learning model. The router sends a response to the STB that indicates whether the user is present. The STB uses the response in combination with various events detected by the STB to determine whether the user is watching the advertisement. The STB also analyzes feedback from the user to determine whether the user has a positive or negative sentiment towards the advertisement.