Smart Reminder Generation via NLP Entity Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current reminder systems are inefficient and unreliable, as they do not provide autonomous reminders based on phone calls, device proximity, and voice identification triggers, leading to increased chances of forgetting tasks or missing deadlines.

Innovation Solution

A system and method for creating smart reminders that process user input using natural language processing to identify entities such as people, times, and locations, and trigger reminders based on events like incoming calls, network connections, or voice detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual reminders (sticky notes, timers, alarms) are used, then people can set reminders, but they consume time during the day and are unreliable

Engineering Contradiction:
Improvereminder reliabilityVSAvoidtime consumed for setting reminders
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system automatically analyzes incoming messages and call logs to generate smart reminders without requiring manual setup. The natural language processing system autonomously extracts entities, determines reminder types, and schedules reminders based on contextual cues from communications, making the reminder system self-serve the user's needs

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary analysis of communications to identify potential reminder opportunities before the user needs them. By processing messages and calls in real-time, the system prepares and queues smart reminders in advance, so they are ready to be presented to the user at the optimal moment without requiring reactive manual setup

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If sticky notes or electronic notes are used as reminders, then people can write down tasks, but they cannot easily locate the notes and may forget to act upon them

Engineering Contradiction:
Improveease of locating remindersVSAvoidreminder effectiveness
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system continuously monitors incoming communications and provides real-time feedback by presenting smart reminders when relevant contextual cues are detected. The feedback loop includes analyzing new messages/calls, matching them against stored reminder criteria, and immediately presenting appropriate reminders to the user, ensuring timely visibility and action

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system integrates multiple functions into a single smart reminder platform: message analysis, call log processing, entity extraction, reminder generation, and contextual triggering. This multi-functional approach consolidates various reminder methods (sticky notes, timers, alarms) into one universal system that automatically handles diverse reminder scenarios

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Extent of automation

If current reminder systems are used, then people can set manual reminders, but they do not provide autonomous reminders based on phone calls, device proximity, and voice identification triggers

Engineering Contradiction:
Improveautonomous reminder capabilityVSAvoidsystem complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The system replaces manual mechanical reminder setup with automated digital processing. Natural language processing algorithms automatically analyze communications, extract entities, and generate reminders without requiring manual configuration. The system substitutes human cognitive effort with automated text analysis and pattern recognition mechanisms

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The natural language processing system serves as an intermediary between raw communications (messages, calls) and the reminder generation mechanism. This intermediary layer analyzes the content, extracts meaningful entities, determines reminder parameters, and translates communication data into structured reminder objects, bridging the gap between unstructured inputs and actionable reminders

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3602346B1Smart reminder generation from input
Publication Date: 2024.08.28 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3602346B1 patent drawingFigure 1
  • EP3602346B1 patent drawingFigure 2
  • EP3602346B1 patent drawingFigure 3

AI summary

Smart reminders are generated from input according to lexical and contextual cues. The input may be entered into any suitable application via any suitable electronic device. The input may be processed by a natural language processor to determine whether to convert the input into a smart reminder. In this way, the input of the note may be parsed to identify entities, such as entities associated with one or more people, relevant time(s), action(s), instruction(s), etc., for creating the smart reminder. The identified entities may then be used as triggers for displaying the smart reminder at an appropriate time to a user. A trigger such as detecting a person associated with the input, e.g., by receiving an incoming call from the person, connecting to the same network as the person, receiving a text from the person, or detecting the voice of the person, may cause the smart reminder to be displayed.