TV Content Presentation Using Viewing History for User Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing content recommendation systems for television viewing, particularly in shared household settings, struggle to accurately identify individual user preferences due to the difficulty in performing personal authentication and generating user profiles, leading to ineffective content suggestions.
Innovation Solution
A content presentation method that collects and analyzes viewing history to determine active time segments, extracts meta data from viewed content, and generates user profiles for each segment, allowing for the selection of contents compatible with individual preferences and life patterns, enabling the creation of playlists that suit users' interests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If personal authentication devices (fingerprint, facial recognition) are attached to identify individuals, then user identification accuracy is improved, but manufacturing cost increases
Solution Approach 1:
The system uses the television device itself to perform identification by analyzing viewing patterns and behavior characteristics during normal operation, eliminating the need for external authentication hardware. The television automatically generates user profiles based on collected viewing data.
Solution Approach 2:
Physical authentication devices (fingerprint sensors, facial recognition cameras) are replaced with a software-based analysis system that processes viewing history and behavior data to identify users, substituting mechanical/hardware authentication with computational analysis.
2Adaptability or versatility
If buttons for personal identification are provided on remote controller, then user identification capability is improved, but ease of operation deteriorates due to burden on user
Solution Approach 1:
The television system automatically performs user identification without requiring manual input from users. The system passively collects viewing data and analyzes behavior patterns to identify who is watching, eliminating the need for users to press buttons or perform authentication actions.
Solution Approach 2:
The system performs preliminary data collection during normal viewing operations, gathering viewing history and behavior characteristics before authentication is needed. This preliminary accumulation of data enables automatic identification when the television is turned on or when content selection is required.
3Measurement precision
If viewing history analysis is performed to generate user profiles, then recommendation accuracy is improved, but device complexity increases
Solution Approach 1:
The system divides user identification into separate functional modules: viewing history collection, behavior analysis, profile generation, and content recommendation. Each module performs a specific function, making the overall complex system manageable through functional segmentation.
Solution Approach 2:
The television device performs multiple functions using the same data collection infrastructure: it collects viewing history for both content recommendation and user identification purposes, eliminating the need for separate systems and reducing overall complexity.
Data Source
AI summary
A content presenting method of the present disclosure includes: a history collecting step of collecting a viewing history of a user; a determining step of analyzing the viewing history to determine an active time segment in which an output section is in a state of being viewed; a data collecting step of collecting meta data assigned to a viewed content; an analyzing step of analyzing the meta data to extract a word representing the content; a profile generating step of generating, for each active time segment, a user profile based on the extracted word; a calculation step of calculating an estimated viewing time; and a playlist generating step of selecting contents based on the user profile generated correspondingly to the active time segment to be compatible with the estimated viewing time, to generate a playlist which defines an order in which the selected contents are played.