Website Interaction Issue Detection for Abandonment-Causing Attributes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for identifying issues in digital interactions on websites, such as software bugs or interface flaws, are inefficient and inaccurate, as they rely on user feedback and activity monitoring, which cannot pinpoint specific webpage attributes causing user abandonment.
Innovation Solution
A detection system analyzes suspect sessions to identify underperforming stages and attributes, calculating conversion rates and under-conversion rates to determine suspect attributes that cause users to abandon sessions, allowing for targeted debugging and interface improvements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If user feedback and activity monitoring are used to identify issues, then overall website performance can be assessed, but specific webpage attributes causing user abandonment cannot be accurately determined
Solution Approach 1:
The patent segments the detection process into distinct components: session data collection, suspect session identification based on abandonment patterns, attribute extraction from suspect sessions, and performance comparison. This segmentation allows the system to focus computational resources on analyzing only the relevant portions of data that actually cause user abandonment, rather than processing all website interactions equally.
Solution Approach 2:
The patent applies local quality by directing detailed analysis specifically to suspect sessions (those exhibiting abandonment behavior) while using aggregate statistics for non-suspect sessions. The system extracts and analyzes attributes only from sessions that actually problematically, applying computational complexity only where needed rather than uniformly across all data.
2Loss of information
If traditional user feedback methods are used, then general user satisfaction can be measured, but technical details of issues cannot be explained
Solution Approach 1:
The patent introduces an intermediary detection system that acts as a mediator between user behavior data and technical issue identification. This system automatically extracts technical attributes from session data and correlates them with abandonment patterns, translating raw behavioral data into actionable technical insights without requiring users to directly report technical details.
Solution Approach 2:
The patent replaces the mechanical system of manual user feedback collection and technical analysis with an automated computational system that processes session data, identifies patterns, and extracts attributes algorithmically. This substitution eliminates the need for users to manually describe technical issues while maintaining ease of operation through automated processing.
3Productivity
If activity monitoring across entire webpage is implemented, then which webpages causing issues can be identified, but efficiency and speed of issue identification are reduced
Solution Approach 1:
The patent applies preliminary action by pre-identifying suspect sessions based on abandonment patterns before conducting detailed attribute analysis. This preliminary filtering step allows the system to focus subsequent analysis only on sessions that actually exhibit problematic behavior, significantly improving both speed and precision by avoiding analysis of normal sessions.
Solution Approach 2:
The patent implements partial action by analyzing only the specific attributes and stages relevant to suspect sessions rather than conducting comprehensive analysis of all session attributes. The system extracts only the necessary attributes from suspect sessions and compares them against aggregate statistics, performing just enough analysis to accurately identify issue-causing elements without unnecessary computational overhead.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
Techniques are described herein for identifying issues related to digital interactions. For example, a detection system may be provided to analyze suspect sessions to determine if one or more stages associated with the suspect sessions are underperforming compared to corresponding stages associated with similar sessions. The detection system may provide a user interface that allows a user to select one or more attributes that may be associated with one or more sessions. Selection of the one or more attributes may identify multiple sessions (referred to as suspect sessions herein). The one or more suspect sessions may be analyzed to determine whether one or more stages associated with the one or more suspect sessions are underperforming compared to corresponding stages associated with one or more other sessions determined to be similar to the one or more suspect sessions.