Communication Session UI for Real-Time Word Definitions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

User interfaces in communication sessions often fail to provide real-time definitions for unfamiliar words, leading to communication barriers and distractions as users seek external sources for explanations, disrupting the discussion flow.

Innovation Solution

Implementing an automated speech recognition system and a large language model to generate and present definitions of unfamiliar words in real-time during a communication session, tailored to the user's attributes and context, using a user interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If users search for explanations of unfamiliar words during the conversation, then they can understand the word, but it causes distractions and loss of attention to the discussion

Engineering Contradiction:
Improvecomprehension of unfamiliar wordsVSAvoidattention to discussion
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary action by automatically detecting unfamiliar words and providing their explanations before the user needs to search for them. The explanation is prepared and presented in advance, eliminating the need for users to interrupt the discussion to look up words externally.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system acts as an intermediary between the user and the unfamiliar word by providing automated explanations through the user interface. This mediator function allows users to understand words without leaving the interface or breaking their focus on the discussion.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If users leave the interface to search for word explanations, then they can find definitions, but it disrupts the discussion flow

Engineering Contradiction:
Improvedefinition of unfamiliar wordsVSAvoidflow of discussion
Core Design Contradiction:
Loss of informationVSStability of the object's composition

Solution Approach 1:

The system provides self-service by automatically generating and displaying explanations of unfamiliar words within the interface. Users receive the information they need without manual intervention to search external sources, and the discussion flow remains uninterrupted.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The explanation is prepared and presented in advance within the interface, so users do not need to leave to search for definitions. This preliminary provision of information maintains the stability and continuity of the discussion flow.

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If real-time definitions are provided for all words, then user comprehension is enhanced, but it increases device complexity and processing requirements

Engineering Contradiction:
Improveuser comprehensionVSAvoidprocessing system complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system applies local quality by providing definitions selectively rather than for all words. It identifies and provides explanations only for unfamiliar words based on user profile and context analysis, reducing unnecessary processing while maintaining comprehension enhancement where needed.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system changes parameters by adjusting the level of information provision based on user attributes, word importance, and context. This selective approach optimizes processing requirements while maintaining effective comprehension support.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS20260073136A1User interface for communication sessions
Publication Date: 2026.03.12 FUJITSU LTD
  • US20260073136A1 patent drawing
  • US20260073136A1 patent drawing
  • US20260073136A1 patent drawing

AI summary

According to an aspect of at least one embodiment, a method to improve a user interface may include obtaining transcript data include one or more words from a transcription of speech in the audio data. The transcript data may be generated by automated speech recognition technology from the audio data. The transcript data and criteria may be provided to a large language model configured to analyze the transcript data based on the criteria to select a word from the transcript data. A definition of the selected word may also be generated by the large language model. The selected word and the definition of the selected word may be obtained. The audio data may be broadcasted by a device and the selected word and the definition of the selected word may be presented on a display of the device with the broadcasting of the audio data.