ML Classification of Broken Application Links via Presentation Duration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately identify and remove broken application links, which can cause application crashes and user frustration, especially when links point to unavailable or incorrect content, and are inefficient due to the limitations of manual or automated crawlers.
Innovation Solution
A machine learning-based system that classifies application links as broken or working by analyzing presentation durations following user interactions, grouping links by prefix patterns, and using a machine learning model to predict link status, thereby reducing network timeouts and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual or automated crawlers are used to identify broken links, then link detection can be performed, but accuracy is insufficient and resource usage is high
Solution Approach 1:
The patent replaces traditional mechanical crawling systems with a machine learning-based detection system. The ML model analyzes presentation duration data to classify links as broken or working, eliminating the need for resource-intensive automated crawlers while achieving higher accuracy in link status detection.
Solution Approach 2:
The patent introduces presentation duration data as an intermediary indicator to infer link status. Instead of directly testing link connectivity through crawling, the system uses the duration for which content is presented after link activation as a proxy signal to predict whether a link is broken, thereby improving detection accuracy without the resource consumption of traditional crawling.
2Reliability
If broken links are not accurately identified and removed, then application links remain operational, but application crashes and user frustration increase
Solution Approach 1:
The patent performs preliminary detection and classification of broken links before they cause application crashes. By continuously monitoring presentation durations and using the ML model to identify broken links in advance, the system can remove or fix these links proactively, preventing the harmful effects of crashes and user frustration before they occur.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying broken network connections. In one aspect, a system includes front-end server(s) that receive data specifying, for multiple different user interactions with one or more application links that link to a given application, presentation durations specifying how long application content linked to by the application link was presented following the multiple different user interactions with the application link(s). Back-end server(s) that communicate with the front end server(s) can classify each application link as broken or working based on application of a machine learning model to the presentation durations for the application link. The machine learning model can be generated using labeled training data. The back-end server(s) can generate and output an alert identifying an application link as a broken link based on the application link being classified as broken by the machine learning model.