Communication Content Extraction via Data Source Augmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to effectively identify and extract requests and commitments from electronic communications, often lacking sufficient information within the communication itself, necessitating the need for querying additional sources or user confirmation to determine task-related information.

Innovation Solution

A system that analyzes electronic communications to automatically extract requests and commitments by utilizing language analysis, machine learning models, and querying related data sources, such as calendars and databases, to determine the presence and properties of tasks, including identifying involved parties, deadlines, and locations, and providing additional information through data augmentation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the system relies solely on the electronic communication content to extract requests and commitments, then the extraction process is simple and fast, but the accuracy and completeness of task information is insufficient

Engineering Contradiction:

Improveaccuracy of task information extractionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary information extraction system that acts as a mediator between electronic communications and task management systems. This intermediary analyzes communication content, extracts requests and commitments, and queries additional data sources (calendars, databases, user profiles) to supplement incomplete information, thereby improving extraction accuracy without requiring direct integration between all communication platforms and task management systems

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by pre-querying related data sources (calendars, databases, user availability) before finalizing task extraction. This allows the system to proactively gather supplementary information that may be needed for accurate task identification, reducing the need for iterative queries and improving overall extraction completeness

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If the system queries multiple data sources to extract complete task information, then the accuracy of task extraction improves, but the time required for processing increases

Engineering Contradiction:

Improvecompleteness of task informationVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by selectively querying only the necessary data sources based on the specific communication context and identified task type. Rather than querying all available data sources for every extraction task, the system intelligently determines which sources are relevant, reducing unnecessary processing time while maintaining information completeness

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system performs preliminary queries to high-probability data sources first (such as calendar availability or recent project databases) before proceeding to less likely sources. This staged approach allows the system to often obtain sufficient information from a subset of sources, reducing average processing time while maintaining completeness when needed

Inventive Principle:

Principle #10Preliminary action

3Productivity

If the system automatically extracts tasks without user confirmation, then the productivity increases, but the reliability of extracted tasks decreases

Engineering Contradiction:

Improvetask extraction efficiencyVSAvoidaccuracy of task identification

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements feedback mechanisms where extracted tasks are presented to users for confirmation or correction. User feedback is then fed back into the extraction system to refine and improve future extraction accuracy. This creates a continuous improvement loop that maintains high productivity while progressively enhancing reliability through learned patterns from user corrections

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system applies partial user confirmation by seeking validation only for tasks with lower confidence scores or ambiguous characteristics. High-confidence extractions are automatically processed without user intervention, maintaining productivity, while selective confirmation is requested only when needed to improve reliability for uncertain cases

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10361981B2Automatic extraction of commitments and requests from communications and content

Publication Date: 2019.07.23 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A system that analyses content of electronic communications may automatically extract requests or commitments from the electronic communications. In one example process, a processing component may analyze the content to determine one or more meanings of the content; query content of one or more data sources that is related to the electronic communications; and based, at least in part, on (i) the one or more meanings of the content and (ii) the content of the one or more data sources, automatically identify and extract a request or commitment from the content. Multiple actions may follow from initial recognition and extraction, including confirmation and refinement of the description of the request or commitment, and actions that assist one or more of the senders, recipients, or others to track and address the request or commitment, including the creation of additional messages, reminders, appointments, or to-do lists.