Content Recommendation System Using Playing Time Inference

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional information systems struggle to accurately recommend content to users without transaction data, as they fail to consider the user's concern degree based on playing time, leading to potential misassociation rules and unsatisfactory recommendations.

Innovation Solution

A system and method that utilize a user-concerned information provision system with a fuzzy association rule inquiry algorithm, applying maximum and actual playing time to infer association relationships between contents, calculating support and association degrees, and providing associated content recommendations based on inferred relationships.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional association rule inquiry methods are used to recommend information, then the system can provide personalized recommendations, but the reliability of association rules deteriorates because user concern degree cannot be accurately measured

Engineering Contradiction:

Improvereliability of association rulesVSAvoiduser concern degree information

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The system performs preliminary action by measuring and recording user playing time before making recommendations. The playing time measurement unit continuously monitors how long users actually play recommended contents, and this data is stored in advance to be used for future association rule generation, ensuring that user concern degree is captured before recommendation decisions are made

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by using the measured playing time information to refine and improve association rules. The inference server uses playing time data to calculate support degrees and association degrees, continuously improving the reliability of recommendations based on actual user behavior feedback rather than relying solely on initial recommendation assumptions

Inventive Principle:

Principle #23Feedback

2Measurement precision

If association rules are generated without considering playing time, then the system operation is simple, but the precision of recommendation deteriorates due to wrong association rules

Engineering Contradiction:

Improveprecision of user concern measurementVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces complex manual analysis of user behavior with automated measurement and inference mechanisms. The playing time measurement unit automatically tracks user engagement, and the inference server automatically generates association rules based on this data, substituting mechanical complexity with automated computational processes that improve measurement precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The playing time measurement unit acts as an intermediary between the content delivery and the recommendation system. It captures actual user engagement data and translates it into quantifiable metrics that the inference server can use to generate accurate association rules, serving as a bridge that converts raw user behavior into actionable recommendation insights

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If the system provides more personalized recommendations based on user behavior, then user satisfaction improves, but the complexity of data processing increases

Engineering Contradiction:

Improveuser satisfactionVSAvoiddata processing complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system extracts only the most relevant feature from user behavior data - playing time - rather than attempting to analyze all possible user interactions. By focusing on this single key metric, the system achieves personalized recommendations that improve user satisfaction while avoiding the complexity of processing multiple behavioral dimensions

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS8117135B2Concerned information recommendation system and method considering user's watching or listening time and maximum playing time of contents

Publication Date: 2012.02.14 STRIPE INC

AI summary

A user-concerned information recommendation system and method considering user's watching or listening time and the maximum playing time of contents are disclosed. The user-concerned information provision system includes a plurality of user terminals to provide contents transmitted from an external server to a user, a user-concerned information inference server to infer an association relationship between the contents based on information of maximum playing time and actual playing time of the contents provided to the user terminals, and a content provision server to provide a content requested by an arbitrary one of the user terminals and other contents associated with the requested content according to the inferred association relationship to the arbitrary one of the user terminals when receiving a request of the content from the arbitrary one of the user terminals, thereby providing more accurate user-concerned information to the user.