Generative AI Product Support for Automated Software Issue Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing software products face challenges in identifying and addressing previously-unknown problems, shortcomings, or limitations encountered by end-users post-deployment, with current solutions relying on slow and inefficient human interactions for product improvement suggestions.

Innovation Solution

A system utilizing generative artificial intelligence (GAI) analyzes customer interactions to detect issues, identifies relevant software features or generates design alterations to rectify problems, and provides automated recommendations for product improvements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If human interactions are used to report and analyze product problems, then product improvement suggestions can be obtained, but the process is slow and inefficient

Engineering Contradiction:

Improveproduct improvement suggestion speedVSAvoidtime for problem detection and solution provision

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces the mechanical human interaction system with an automated electronic system using machine learning models. The system automatically analyzes electronic interaction records (emails, chat logs, tickets) to detect product problems, eliminate human manual analysis, and accelerate the feedback loop from weeks/days to hours/minutes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically analyzing customer interaction records and generating improvement suggestions without requiring human intervention. The machine learning models autonomously process data, identify patterns, and produce actionable insights, making the system self-sufficient in the problem detection and analysis process.

Inventive Principle:

Principle #25Self-service

2Productivity

If automated systems are implemented to detect product problems, then productivity and speed are improved, but system complexity increases

Engineering Contradiction:

Improveautomated problem detection efficiencyVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent divides the complex automated system into distinct modular components: an electronic interaction record access component, a machine learning model component, and a suggestion generation component. Each module performs a specific function, making the overall complex system manageable through segmentation and independent development/deployment of each component.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary machine learning model that bridges raw electronic interaction records and actionable improvement suggestions. This intermediary layer processes and transforms unstructured data into structured insights, simplifying the interface between data collection and decision-making processes.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If comprehensive analysis of electronic interaction records is performed, then problem detection accuracy is improved, but computational resources and processing time increase

Engineering Contradiction:

Improveproblem detection accuracyVSAvoidcomputational energy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by training the machine learning model on a representative subset of electronic interaction records rather than processing every single record in real-time. The model learns from comprehensive training data but applies optimized inference to new records, balancing thoroughness with computational efficiency.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent performs preliminary action by pre-training the machine learning model offline on extensive historical interaction records. This preliminary training phase comprehensively analyzes patterns and relationships, so that during actual operation, the model can quickly apply learned knowledge without requiring exhaustive real-time computation.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250371504A1Automatic product improvement systems and methods via generative artificial intelligence and customer interactions

Publication Date: 2025.12.04 GE PRECISION HEALTHCARE LLC

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.