Telemetry-Driven Software Backlog Prioritization With Generative AI
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing software development prioritization methods rely heavily on subjective qualitative techniques, leading to biased and sub-optimal prioritization of product backlog items (PBIs) due to reliance on heuristics and varying reliability of in-person interviews and customer surveys.
Innovation Solution
A system utilizing a trained machine learning model to predict user behavior based on telemetry data, combined with a generative AI model to generate feature summaries, determines similarities between software development items and model features, and prioritizes PBIs based on quantitative data-driven impact on user retention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If subjective qualitative techniques (heuristics, interviews, surveys) are used for prioritization, then ease of operation is improved, but reliability and objectivity deteriorate due to bias and varying reliability
Solution Approach 1:
The patent replaces subjective human judgment mechanisms (interviews, surveys, heuristics) with an automated machine learning system that processes telemetry data objectively. The ML model computes prioritization scores based on quantitative user behavior patterns, eliminating human bias while maintaining operational simplicity through automated scoring and ranking of PBIs.
Solution Approach 2:
The patent introduces machine learning models and telemetry data analysis as intermediary components between raw user behavior data and prioritization decisions. These intermediaries transform subjective qualitative assessments into objective quantitative metrics, mediating the transition from biased human judgment to reliable data-driven prioritization.
2Reliability
If data-driven ML models and generative AI are implemented, then prioritization reliability and objectivity are improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent segments the complex prioritization system into distinct modular components: telemetry data collection modules, ML model training modules, feature extraction modules, generative AI summarization modules, and prioritization scoring modules. Each component handles a specific aspect of the process, making the overall system more manageable and easier to implement despite its sophistication.
Solution Approach 2:
The patent creates a universal prioritization framework that can process multiple types of telemetry data, work with different ML models, and generate prioritization scores for various PBI types through a single integrated system. The generative AI component serves multiple functions including feature summarization, pattern recognition, and priority justification generation, reducing the need for separate specialized systems.
Data Source
AI summary
Systems, methods, devices, and computer readable storage media described herein provide techniques for prioritizing software development using a trained model. In an aspect, model features are determined based on analysis of user behavior with respect to a software application. A software development prioritization (SDP) system determines data associated with the model features and utilizes a generative artificial intelligence (AI) model to summarize the model features based on the determined data. The SDP system determines, based on the summaries, a similarity between software development items and the model features and prioritizes one of the software development items over another based on the determined similarities. In a further embodiment, the SDP system causes a software development task corresponding to the prioritized software development item to be performed before another software development task corresponding to a different software development item. In an aspect, model features are determined utilizing a trained machine learning model.