Poll Intent Detection for Converting Informal Posts to Structured Polls

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing online services struggle to accurately classify user-generated content postings as informal polls, lacking analytics and privacy options, leading to suboptimal user experiences.

Innovation Solution

Employ supervised machine learning techniques to train models that predict whether a content posting is intended as a poll, converting informal polls to structured polls by identifying questions and answers, and providing a user interface for editing and configuring poll settings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users create informal polls through default content posting interfaces, then ease of operation is improved, but reliability and data quality deteriorate due to lack of structured format and analytics

Engineering Contradiction:

Improveease of creating pollsVSAvoidpoll data quality

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system automatically detects informal polls using machine learning models and performs self-service conversion to structured format without requiring user intervention. The ML model analyzes content postings, identifies poll intent, extracts questions and answers, and transforms them into structured poll objects with analytics capabilities enabled by default.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system segments the poll creation process into two distinct pathways: informal polls created through default interfaces and formal structured polls with analytics. By detecting and converting informal polls to structured format, the system maintains the simplicity of the original creation method while adding the reliability of structured data collection and analytics.

Inventive Principle:

Principle #1Segmentation

2Reliability

If users create formal structured polls with dedicated interfaces, then reliability and analytics capability are improved, but device complexity and ease of operation worsen

Engineering Contradiction:

Improvepoll data qualityVSAvoidinterface complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs automatic detection and conversion of informal polls to structured format through self-service mechanisms. Machine learning models analyze content postings, identify poll characteristics, and transform them into structured poll objects with analytics capabilities, eliminating the need for users to manually navigate complex poll creation interfaces.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by automatically converting informal polls to structured format before users can interact with them. This pre-processing ensures that polls gain analytics capabilities and structured data quality without requiring users to go through the complex formal poll creation process.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If machine learning models automatically convert informal polls to structured format, then reliability and analytics capability are improved, but processing time and computational resources increase

Engineering Contradiction:

Improvepoll classification accuracyVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system applies partial action by using machine learning models only for detecting poll intent and converting informal polls to structured format, rather than processing all content postings equally. The ML models focus specifically on identifying poll characteristics in informal posts, applying computational resources only where needed to maintain efficiency while improving reliability.

Inventive Principle:

Principle #16Partial or excessive action

4Adaptability or versatility

If the system provides analytics and privacy options for converted polls, then user experience and data utility are improved, but device complexity increases

Engineering Contradiction:

Improvepoll functionalityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies universality by enabling analytics and privacy options on both originally structured polls and converted informal polls through a unified poll object structure. The same analytics infrastructure and privacy controls serve both formal and converted informal polls, increasing adaptability without proportionally increasing complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12561606B2Techniques for poll intention detection and poll creation

Publication Date: 2026.02.24 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Described herein are techniques for using supervised machine learning to determine whether a content posting posted to a feed of an online service, has been posted with the intent that the content posting is a poll or survey. Upon making a determination that a content posting is or includes a poll, the content posting is further analyzed to identify within the content posting a question and/or answers to the question. The identified question and answers are then used to populate data fields associated with a formal or structured poll, and the end-user who posted the content posting is provided an option to convert the poll from a first content posting format to a second content posting format that is specifically for a formal or structured poll.