Aural Input Solution Generation via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Human conversations often fail to capture the true best-fit solution to a problem due to overlapping conversation, memory or comprehension errors, leading to suboptimal problem-solving outcomes.
Innovation Solution
Implementing a system that uses machine learning techniques to parse aural inputs from multiple human speakers, derive solution sentiments and constraints, and generate solutions in real-time, with the ability to update solutions based on additional inputs through an audio and graphical interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If human speakers engage in conversation to solve problems, then solutions can be generated through discussion, but overlapping conversation and memory errors lead to loss of information and reduced accuracy
Solution Approach 1:
The patent introduces an intermediary system comprising audio sensors, speech-to-text converters, and machine learning engines that mediate between human speakers and the problem-solving process. This intermediary captures, processes, and structures conversation data, preventing information loss from overlapping speech and memory errors while maintaining natural collaborative problem-solving productivity
Solution Approach 2:
The patent replaces the mechanical human memory and recall system with an automated digital system that uses audio capture, transcription, and machine learning to store and retrieve conversation information. This substitution eliminates memory errors and comprehension errors while preserving the collaborative nature of problem-solving
2Measurement precision
If machine learning engines process and analyze aural inputs in real-time, then solution accuracy improves, but system complexity increases
Solution Approach 1:
The patent segments the complex processing task into distinct functional modules: audio capture by microphones, speech-to-text conversion, term extraction, sentiment analysis, constraint identification, and solution generation. Each module handles a specific aspect of processing, improving accuracy while managing complexity through modular architecture
Solution Approach 2:
The machine learning engines perform multiple functions including speech recognition, natural language processing, sentiment analysis, and constraint extraction within a unified system. This multi-functionality reduces overall system complexity by consolidating diverse processing tasks into integrated components rather than separate systems
3Reliability
If the system captures and processes all aural inputs from multiple speakers, then completeness of problem understanding improves, but processing time and computational resources increase
Solution Approach 1:
The system performs partial processing by initially focusing on extracting key terms and sentiments from aural inputs, then progressively refining the analysis as more data becomes available. This approach provides timely preliminary results while continuing to process complete information in the background, balancing completeness with processing time
Solution Approach 2:
The system performs preliminary speech-to-text conversion and term extraction as aural inputs are received, preparing data structures in advance for subsequent sentiment analysis and solution generation. This preliminary processing reduces the computational burden during critical decision-making moments while ensuring complete information is captured
Data Source
AI summary
Techniques for generating solutions from aural inputs include identifying, with one or more machine learning engines, a plurality of aural signals provided by two or more human speakers, at least some of the plurality of aural signals associated with a human-perceived problem; parsing, with the one or more machine learning engines, the plurality of aural signals to generate a plurality of terms, each of the terms associated with the human-perceived problem; deriving, with the one or more machine learning engines, a plurality of solution sentiments and a plurality of solution constraints from the plurality of terms; generating, with the one or more machine learning engines, at least one solution to the human-perceived problem based on the derived solution sentiments and solution constraints; and presenting the at least one solution of the human-perceived problem to the two or more human speakers through at least one of a graphical interface or an auditory interface.