Machine Learning System for Resident Television Content Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content targeting techniques struggle to determine which resident in a shared residential space is consuming television content, as they lack user information, restricting the relevance of demographics and content recommendations.
Innovation Solution
A machine learning system that detects logins on television devices, identifies resident profiles, and uses a machine learning model to predict which resident is watching by analyzing viewing history and demographic information, even when multiple residents share a login.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If content targeting is performed in shared residential spaces, then content relevance to specific users can be improved, but the ability to identify which resident is consuming content deteriorates due to lack of user information
Solution Approach 1:
The patent introduces television device identifiers and viewing behavior data as intermediary elements that bridge the gap between content delivery and user identification. These intermediaries carry information about viewing patterns, device usage, and household composition without requiring direct user identification, enabling content relevance improvement while preserving privacy.
Solution Approach 2:
The patent replaces traditional mechanical user identification methods (such as login credentials, remote control pairing, or explicit user input) with machine learning-based prediction systems. The ML model substitutes direct measurement of user identity with indirect inference from viewing behavior patterns, device usage data, and household resident information.
2Device complexity
If traditional content targeting methods are used without user identification, then system complexity is reduced, but content personalization and monetization effectiveness deteriorate
Solution Approach 1:
The patent performs preliminary actions by collecting and processing household resident information, television device identifiers, and viewing behavior data before content delivery. The machine learning model is pre-trained with household composition data and viewing patterns, enabling it to make accurate predictions without adding complexity to the real-time content delivery system.
Solution Approach 2:
The system enables self-service by allowing the machine learning model to automatically predict which resident is consuming content without requiring manual user identification or complex authentication systems. The model autonomously analyzes viewing behavior patterns and device usage data to identify the consuming resident, eliminating the need for additional user input or complex identification infrastructure.
Data Source
AI summary
As described herein, a machine learning system, method, and computer program are provided to predict which resident of a residential space is watching television for content targeting purposes. In use, a login to a television service on a television device in a residential space is detected. Additionally, information defining a plurality of residents of the residential space is identified. Further, a profile determined for the login is identified, where the profile is associated with a particular resident of the plurality of residents or a particular resident group of the plurality of residents. Still yet, the profile and the information defining the plurality of residents of the residential space is input to a machine learning model to predict one or more residents of the plurality of residents that is consuming the television service on the television device.