ML Video Query System for Software Lifecycle Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for providing learning in the flow of work are time-consuming and difficult to implement in a work setting, leading to missed learning opportunities.

Innovation Solution

A method and system for performing a video query using context information acquired through a software life cycle tool, involving the use of machine learning models to remove noise, generate queries, retrieve and rank video segments from a learning repository, and display relevant content to users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If conventional methods (manual searching, reading reference materials, conferring with professionals) are used to provide learning in the flow of work, then learning content can be accessed, but the process is time-consuming and difficult to implement in a work setting

Engineering Contradiction:

Improvetime spent on manual searchesVSAvoidease of implementing learning in work setting

Core Design Contradiction:

Loss of timeVSEase of operation

Solution Approach 1:

The system performs preliminary actions by automatically capturing context information from the software life cycle tool and pre-processing it through machine learning models to generate queries and retrieve relevant video segments before the user needs the learning content. This eliminates the need for manual searching at the moment of need.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables self-service by automatically retrieving and presenting learning content without requiring users to manually search reference materials or consult with professionals. The machine learning models autonomously process context information, generate queries, and deliver relevant video segments directly to users.

Inventive Principle:

Principle #25Self-service

2Productivity

If context information is acquired through software life cycle tools and processed by machine learning models, then relevant learning content can be quickly retrieved, but the system complexity increases

Engineering Contradiction:

Improvespeed of accessing learning contentVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments the complex task of learning content retrieval into distinct functional components: context information acquisition from software life cycle tools, noise removal by the first ML model, query generation by the first ML model, video segment retrieval by the second ML model, and ranking by the second ML model. This modular segmentation manages complexity while maintaining high productivity.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12222984B1System and method for providing video query

Publication Date: 2025.02.11 JPMORGAN CHASE BANK NA

AI summary

A method and system for providing a video query are disclosed. The method includes acquiring context information, training a first machine learning (ML) model using historical data of the software life cycle tool, and removing, by the first ML model, noise from the context information for generating a query including at least one keyword. Once the query is generated, executing, by a second ML model, the query to retrieve at least one video segment from a learning repository. Scoring and ranking is then performed on the at least one video segment. The ranked video segment is then transmitted, to the user interface of the software life cycle tool, and displayed in an ad-hoc manner.