Display Device Content Selection via Viewer Affinity Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current display devices lack the ability to effectively customize image content based on the viewer's identity and affinity, leading to a lack of personalized and engaging image selection.
Innovation Solution
The system identifies viewer faces using facial recognition, matches them with corresponding user accounts, computes affinity scores based on social distance and co-occurrence within images, and selects images for display based on these predictions to create a personalized image playlist.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional random or chronological image selection is used, then device complexity is low, but user engagement and satisfaction deteriorate due to lack of personalization
Solution Approach 1:
The patent introduces a central system as an intermediary that handles the complex tasks of face recognition, identity matching, and affinity computation. The display device itself remains relatively simple, delegating the computationally intensive personalization logic to the central system, thus achieving content adaptability without significantly increasing device complexity
Solution Approach 2:
The system performs preliminary actions by pre-computing affinity scores and relationships between users and image subjects, storing these in a central database. When a user views images, the personalized selection is quickly generated by retrieving pre-computed data rather than performing complex real-time analysis, thus achieving personalization with minimal additional device complexity
2Adaptability or versatility
If basic image display without viewer identification is used, then ease of operation is high, but user engagement deteriorates due to generic content selection
Solution Approach 1:
The system automatically performs viewer identification and content customization without requiring manual user input or configuration. The face recognition and affinity-based selection processes occur autonomously, making the system appear simple to operate while delivering highly customized content experiences
Solution Approach 2:
The system incorporates feedback loops where user interactions with displayed images (such as time spent viewing, likes, or shares) are used to refine and update affinity scores in the central system, continuously improving personalization accuracy while maintaining ease of operation through automatic adjustments
3Measurement precision
If comprehensive face recognition and affinity computation are implemented, then image selection accuracy improves, but processing time increases
Solution Approach 1:
The system performs comprehensive face recognition and affinity computation in advance, building detailed user profiles and relationship maps in the central system before actual image selection is needed. This pre-computation approach enables highly accurate affinity predictions to be retrieved quickly during actual viewing sessions, resolving the contradiction between accuracy and processing time
Solution Approach 2:
The image collection is segmented and organized by subject faces and relationships in the central database, allowing the system to efficiently query and retrieve only the most relevant images based on computed affinities, rather than analyzing all images in real-time, thus maintaining high accuracy while reducing processing time
Data Source
AI summary
Method and device are described for customizing the content selection to present on a display device based on identifying the viewer of the device. In one embodiment, the present disclosure relates to selecting from among a group of digital images, those images that are most likely to be of interest to the viewer. In general, many of the images available to the display device will be comprised of images containing subject faces. Using the relationship information to predict subject affinity, the display device computes an image affinity for each image by accumulating the individual subject affinity predictions between the viewer and each subject identified in each image. The image affinities are used to select images for presentation on the display device.