Generative AI Support Feedback for Unknown Software Issues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing software products face challenges with previously-unknown problems, shortcomings, or limitations that are not efficiently addressed by current human interaction-based reporting systems, leading to slow or absent product improvement suggestions.
Innovation Solution
Implementing a system that leverages generative artificial intelligence (GAI) to analyze customer interactions, identify issues, and generate design alterations or recommend existing features to rectify these problems, using a large language model (LLM) to synthesize solutions or code changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If human interactions are used to report product problems, then customer feedback can be collected, but the process is slow and may not capture previously-unknown problems effectively
Solution Approach 1:
The system enables automatic self-monitoring of product performance by having the software product itself generate and transmit interaction records without requiring manual human intervention. The product serves itself by automatically detecting and reporting its own problems to development teams.
Solution Approach 2:
The system establishes an automated feedback loop where interaction records from customer usage are continuously monitored, analyzed by GAI models, and fed back to product development teams. This closed-loop feedback mechanism enables real-time detection and response to previously-unknown problems.
2Extent of automation
If generative AI models are used to analyze interaction records, then automated problem identification is achieved, but system complexity increases
Solution Approach 1:
The system introduces GAI models as intermediary components that bridge the gap between raw interaction records and actionable product feedback. These models act as mediators that automatically interpret, analyze, and synthesize complex interaction data without requiring direct human analysis.
Solution Approach 2:
The GAI models serve multiple functions within the system: they analyze interaction records, identify problems, detect patterns, and generate recommendations. This multi-functionality reduces the need for separate specialized components, thereby managing complexity while achieving comprehensive automation.
3Manufacturing precision
If detailed design and technology recommendations are provided, then product improvement quality increases, but the volume of information to process increases
Solution Approach 1:
The system extracts only the most critical and actionable information from vast amounts of interaction records using GAI models. By focusing on identifying previously-unknown problems and generating specific design recommendations, the system filters out redundant information and delivers high-quality feedback that directly impacts product improvement.
Solution Approach 2:
The system transforms raw interaction data into structured improvement recommendations by changing the representation and organization of information. GAI models rephrase and restructure feedback to highlight key issues and solutions, making the information more manageable and actionable for development teams.
Data Source
AI summary
Systems/techniques that facilitate automatic product support systems and methods via generative artificial intelligence (GAI) and customer interactions are provided. In various embodiments, a system can access an electronic interaction record pertaining to a software product. In various aspects, the system can synthesize, via execution of GAI on the electronic interaction record, first text that describes a problem afflicting the software product. In various instances, the system can determine, based on executing the GAI on the first text, whether there is an available software feature in an available software feature repository that addresses or solves the problem. In various cases, the system can, in response to a determination that there is no available software feature that addresses or solves the problem, synthesize, via execution of the GAI on the first text, a recommended design alteration to the software product that would address or solve the problem.