Content Consumption Prediction via Application-Viewing Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Content providers face challenges in determining users' viewed programs when only providing applications, and vice versa, as they lack mechanisms to assess program viewership or application usage.
Innovation Solution
A system and method that extract viewing and application data to generate logs, construct a correlation model between viewing and application usage, and apply this model to predict content consumption patterns, enabling relevant content recommendations to users based on their expected viewing actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a content provider provides merely applications, then the content provider can deliver application content, but the content provider lacks a mechanism to determine what programs a user is viewing
Solution Approach 1:
The patent combines program viewing data and application usage data into a unified dataset to construct a correlation model. This merging allows the system to simultaneously analyze both types of information and generate comprehensive user behavior predictions without requiring separate independent systems.
Solution Approach 2:
The patent introduces a correlation model as an intermediary that indirectly infers program viewing information from application usage patterns. Instead of directly tracking program viewing, the model uses application data as a mediator to predict what programs users are likely watching, thus obtaining viewing information without direct measurement.
2Loss of information
If a content provider provides merely programs, then the content provider can deliver program content, but the content provider lacks a mechanism to determine what applications the user is utilizing
Solution Approach 1:
The correlation model serves as an intermediary that indirectly infers application usage information from program viewing patterns. By analyzing the relationship between programs users watch and applications they use, the system can predict application usage without directly tracking it, thus obtaining the information through the model's predictive capability.
Solution Approach 2:
The system uses the correlation model to generate predictions about user behavior that feed back into the content delivery system. This feedback loop allows the content provider to adjust program and application recommendations based on predicted user preferences, creating a closed-loop system that continuously improves personalization.
3Productivity
If the system constructs a correlation model between viewing log and application log, then the system can predict user behavior patterns, but the system requires processing and storing large amounts of data
Solution Approach 1:
The patent extracts only the essential features and patterns from the viewing and application logs that are necessary for building the correlation model. Rather than processing all raw data, the system identifies and extracts key behavioral indicators, reducing the effective data volume needed for model construction while maintaining prediction accuracy.
4Ease of operation
If the system provides content recommendations based on predicted viewing actions, then user satisfaction increases, but the system requires continuous data collection and model application
Solution Approach 1:
The system performs preliminary data collection and model construction during periods when data is naturally accumulating, preparing the correlation model in advance. This preliminary action allows the system to have predictions ready when needed, reducing the processing time required at the moment of content recommendation delivery.
Data Source
AI summary
Methods and systems for predicting content consumption are provided herein. An application log of a user, comprising a user's application data, and a viewing log of the user, comprising the user's viewing data (e.g., television programs watched by the user), may be evaluated over a time period to construct a model. The model may comprise a correlation between the viewing log and the application log during the time period (e.g., what applications the user interacts with while watching a program). Second application data, regarding application usage of a second user, may be extracted. The model may be applied to the second application data to identify an expected viewing action of the second user (e.g., what program the second user is likely to watch during the time period based upon applications used by the second user). The second user may be provided with content related to the expected viewing action.