Document-Usage Footprint Clustering for Task Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional task-management systems face challenges in accurately detecting user tasks without relying on high user feedback or providing imprecise results, as they struggle to associate documents and applications with tasks and recognize task switching effectively.

Innovation Solution

A system that calculates document-usage footprints based on access frequencies and dwell times, applies spectral clustering to generate task representations, and uses user feedback to merge or split clusters for accurate task detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If explicit user input is required for task detection, then task detection accuracy is improved, but user burden increases

Engineering Contradiction:

Improvetask detection accuracyVSAvoiduser burden

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system performs self-service by automatically detecting user tasks through unsupervised learning from document access patterns, eliminating the need for explicit user input or feedback while maintaining accurate task detection

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses implicit feedback from document access patterns, dwell times, and usage footprints to automatically learn and refine task representations without requiring explicit user feedback or labels

Inventive Principle:

Principle #23Feedback

2Ease of operation

If unsupervised approaches are used for task detection, then user burden is reduced, but task detection accuracy deteriorates

Engineering Contradiction:

Improveuser burdenVSAvoidtask detection accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system transforms raw document access data into meaningful task representations by changing parameters through computing document-usage footprints, dwell times, and applying spectral clustering to reveal hidden task structures in the data

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system adds dimensional depth to task detection by computing multi-dimensional document-usage footprints that capture temporal patterns, access frequencies, and relationships across multiple documents and applications simultaneously

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Measurement precision

If document-usage footprints are calculated based on multiple time periods and dwell times, then task representation accuracy is improved, but system complexity increases

Engineering Contradiction:

Improvetask representation accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the analysis into distinct computational components: calculating dwell times for individual documents, computing document-usage footprints for each document, and applying spectral clustering to group documents into tasks, making the complex process manageable and interpretable

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS8290884B2Method for approximating user task representations by document-usage clustering

Publication Date: 2012.10.16 GENESEE VALLEY INNOVATIONS LLC

AI summary

Embodiments of the present invention provide a system for automatically creating a task representation associated with a user task. The system calculates usage footprints of a document based on other applications, documents, and people that have been accessed by the user within a predetermined time frame before and after the user accesses the document. After obtaining usage footprints of a number of documents, the system applies a clustering technique, such as spectral clustering, to create task representations, each including a collection (cluster) of documents and/or applications that are used for accomplishing a particular task. The system also filters the documents based on their average dwell times, and uses user feedback to merge or split different task clusters in order to provide accurate task representations.