Software Functionality Modification via Intent and Image Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current software applications are unable to accurately and efficiently process implicit input such as environmental noises, user utterances, and facial expressions, leading to increased computational resource demands and potential misunderstandings in modifying functionality.

Innovation Solution

Employing natural language processing and image analysis models to determine the semantic meaning of implicit input, allowing software applications to modify functionality based on user intent and environmental data, offloading processing to remote computing platforms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If software applications use complex sequences of explicit input to modify functionality, then functionality can be changed, but computational resource requirements increase and accuracy may still be insufficient

Engineering Contradiction:
Improveaccuracy of interpreting user inputVSAvoidcomplexity of input sequences
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical input processing (keyboard, mouse, touch) with an AI-based natural language processing system. The software application uses an AI model to directly interpret the semantic meaning of implicit input such as user utterances and environmental data, substituting complex sequences of explicit interactions with a single natural language command that the AI processes to determine user intent and modify functionality accordingly.

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

2Productivity

If software applications process implicit input using traditional methods, then processing can occur, but accuracy is insufficient and computational resources are wasted

Engineering Contradiction:
Improveefficiency of processing implicit inputVSAvoidaccuracy of interpreting implicit input
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent changes the processing parameters by introducing AI-based semantic analysis. Instead of using traditional pattern matching or keyword-based processing of implicit input, the system employs an AI model that analyzes the semantic meaning, context, and intent behind user utterances and environmental data, significantly improving both the accuracy of interpretation and the efficiency of processing by reducing unnecessary computational steps.

Inventive Principle:
Principle #35Parameter changes

3Ease of operation

If software applications require complex sequences of explicit input, then functionality can be modified, but user interaction becomes less natural and more resource-intensive

Engineering Contradiction:
Improvenaturalness of user interactionVSAvoidcomputational resource consumption
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent substitutes traditional mechanical interaction sequences (multiple clicks, menu navigation, form filling) with natural language processing. Users can interact with the software using spoken commands or natural text input that the AI interprets to determine intent, making interactions more natural while reducing computational resources by eliminating the need for complex multi-step explicit input sequences.

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

Data Source

PatentEP4621770A1Modifying software functionality based on determining utterance intent with a natural language model and/or identifying objects in an image with a a natural language model or an image analysis model
Publication Date: 2025.09.24 GAMES GLOBAL OPERATIONS LTD
  • EP4621770A1 patent drawingFigure 1
  • EP4621770A1 patent drawingFigure 2
  • EP4621770A1 patent drawingFigure 3

AI summary

An implementation may involve: receiving audio input that contains utterances; determining, by a speech-to-text engine that receives the audio input, a textual representation of the utterances; providing, to a natural language model, a request to determine an intent of the textual representation of the utterances, wherein the request indicates that the intent is to be selected from a plurality of predefined intents; receiving, from the natural language model, the intent; determining, based on the intent, an action; and based on the action, modifying operation of a software application.