Conversation Content Enrichment With Real-Time Sentiment Tagging

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing communication systems fail to transform user opinions from oral conversations into manipulatable data for effective collaboration, lacking tools for sentiment detection, enrichment, and action stimulation.

Innovation Solution

A method and system that captures, segments, and converts voice messages into text, detects user sentiment, associates attributes, and displays enriched digital content, enabling real-time manipulation and action triggering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If oral conversations are captured and converted to text, then information can be stored and searched, but the opinions and sentiments of participants cannot be obtained in manipulatable data form

Engineering Contradiction:

Improveloss of participant opinionsVSAvoidcomplexity of sentiment detection system

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The conversation is segmented into individual contributions, each associated with specific sentiment attributes. This allows the system to process and analyze participant opinions in discrete, manipulatable units rather than treating the entire conversation as a single undifferentiated text stream.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Sentiment attributes act as an intermediary layer between the raw text contributions and the actionable insights. These attributes transform qualitative opinions into quantitative data that can be manipulated, searched, and used to trigger actions without requiring complex direct analysis of every conversation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If sentiment detection is performed automatically in real-time, then collaboration can be enhanced, but the system complexity and processing requirements increase

Engineering Contradiction:

Improvecollaboration effectivenessVSAvoidcomplexity of real-time processing system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

Sentiment attributes are detected and associated with contributions as they are created, rather than analyzing the entire conversation afterward. This preliminary action allows real-time enrichment of collaboration tools without requiring complex post-processing of complete conversation streams.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system automatically detects sentiments and associates attributes without requiring manual intervention or complex configuration. The sentiment detection process serves itself by continuously processing new contributions as they appear, reducing the need for external processing resources.

Inventive Principle:

Principle #25Self-service

3Loss of information

If contributions are enriched with sentiment attributes, then actionable insights can be derived, but data processing and storage requirements increase

Engineering Contradiction:

Improveloss of actionable insightsVSAvoidquantity of data to be processed

Core Design Contradiction:

Loss of informationVSQuantity of substance

Solution Approach 1:

Instead of processing entire conversations uniformly, the system applies sentiment analysis locally to individual contributions that meet specific criteria. This selective approach enriches only the necessary data points with sentiment attributes, reducing overall processing requirements while maintaining actionable insights.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system transforms qualitative sentiment information into standardized quantitative parameters (sentiment attributes). This parameter transformation allows rich information to be stored in a compact, manipulatable format that reduces storage requirements compared to storing full qualitative analyses.

Inventive Principle:

Principle #35Parameter changes

4Measurement precision

If silence detection is used to segment voice messages, then contributions can be identified accurately, but processing time may increase

Engineering Contradiction:

Improveprecision of contribution segmentationVSAvoidtime for segmentation processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system uses silence detection to quickly skip through non-speaking periods in voice messages, rapidly identifying contribution boundaries without analyzing every audio sample in detail. This allows accurate segmentation while minimizing processing time by focusing computational resources only on relevant speaking segments.

Inventive Principle:

Principle #21Skipping (Rushing through)

Data Source

PatentUS20260105097A1Method and system for enriching digital content representative of a conversation

Publication Date: 2026.04.16 100 BREVETS POUR LA FRENCH TECH

AI summary

The method (3000) of enriching digital content representative of a conversation comprises:in an iterative manner:a step (3005) of capturing an audio signal representative of a voice message,a step (3010) of segmenting the voice message into a segment, said segmentation step comprising a silence detection step, the segment being obtained as a function of the detection of a silencea step (3015) of converting the audio segment into text, called “contribution”, anda step (3020) of storing, in a memory, a contribution,then:a step (3025) of detecting user sentiment towards at least one stored contributiona step (3030) of associating, in a memory and in relation to at least one stored contribution, at least one attribute corresponding to at least one detected sentiment anda step (3035) of displaying at least one stored contribution and at least one attribute with respect to said at least one contribution.