Granular Scroll Signal Modeling for Preference Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to accurately detect and understand subtle consumer preferences on digital surfaces due to the dynamic nature of user interactions, which are typically captured through coarse explicit signals that do not reflect nuanced behaviors.
Innovation Solution
A two-stage technique is employed where raw scrolling data is aggregated and condensed locally on the device, reducing data sent to the cloud, and cloud modeling is used on the condensed results to derive more accurate insights into user preferences, leveraging scalability and processing power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If raw scrolling data is captured and sent to the cloud for analysis, then user preference detection accuracy is improved, but data transmission costs and processing burden increase
Solution Approach 1:
The patent segments the data processing workflow into two distinct stages: local preprocessing on the user device and cloud-based analysis. Raw scrolling data is first processed locally to extract meaningful features and patterns, then only the processed results are transmitted to the cloud. This segmentation reduces the volume of data transmitted while preserving the information necessary for accurate user preference detection.
Solution Approach 2:
The patent applies preliminary action by performing data aggregation and feature extraction locally on the user device before cloud transmission. Scrolling behaviors are captured and processed in real-time on the device, converting raw data into condensed representations that retain user preference information while minimizing data size. This preliminary processing reduces the burden on cloud infrastructure and lowers transmission costs.
2Loss of information
If all raw interaction data is transmitted to the cloud, then comprehensive user preference analysis is achieved, but data storage and processing costs increase
Solution Approach 1:
The patent extracts essential features from raw scrolling data locally on the user device. Instead of transmitting complete raw datasets, the system identifies and extracts key behavioral patterns such as scrolling speed, direction changes, and pause durations. These extracted features are then sent to the cloud for analysis, maintaining the completeness of user preference information while dramatically reducing the quantity of data that needs to be stored and processed in the cloud.
3Measurement precision
If granular scrolling signals are captured, then user preference understanding is improved, but device processing complexity increases
Solution Approach 1:
The patent implements self-service by enabling the user device to autonomously process and aggregate scrolling data locally. The device performs feature extraction, pattern recognition, and data condensation without requiring complex centralized processing infrastructure. This self-service approach allows granular behavioral signals to be captured and processed with manageable device-side complexity, while still achieving high user preference detection accuracy.
Data Source
AI summary
Personalized experiences for a user are based on the input patterns of the user. Scrolling behavior on a touchscreen may be used to deliver personalized experiences. The point-by-point coarse scrolling data is aggregated and condensed on the user device being scrolled and the condensed data sent to a server for analysis to save bandwidth.