Automated Support Query Generation from Source Code Context

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Automated support systems often fail to provide accurate solutions to users experiencing software errors due to the lack of appropriate keywords in user queries, as users may not know the correct keywords to identify the solution.

Innovation Solution

The method involves generating a support query based on context information from the source code of the application encountering an error, which can be either hard-coded or generated using a template with variables, to create a precise query that can be used by automated support systems to retrieve solutions from a knowledge database.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users enter queries manually into automated support systems, then users can access potential solutions without communicating with a real person, but users may not know the correct keywords to identify the solution

Engineering Contradiction:

Improveease of useVSAvoidquery accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system automatically generates the support query using context information from the error and source code, eliminating the need for users to manually construct accurate technical queries. The application itself serves to create the query that it then submits to the support system.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system introduces an intermediary query generation process that translates raw error context into formatted support queries with appropriate keywords. This intermediary layer bridges the gap between user errors and support database searches.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If automated support systems rely on user-provided queries, then users have access to support solutions, but the solutions may not be accurate due to lack of context information

Engineering Contradiction:

Improvesupport efficiencyVSAvoidsolution accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs preliminary actions by collecting and analyzing context information from the error and source code before submitting the query to the support system. This preliminary data gathering ensures the query contains sufficient information for accurate solution retrieval.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from the error context and source code analysis to refine and format the support query, ensuring it contains the necessary keywords and information for accurate solution matching in the support database.

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If users with less technical knowledge attempt to formulate support queries, then they can access automated support, but they cannot produce accurate queries to identify solutions

Engineering Contradiction:

Improveuser accessibilityVSAvoidquery precision

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system performs the query formulation task automatically using the error context and source code, making the process self-serving and eliminating the need for users to possess technical query formulation skills.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Instead of requiring users to translate their problems into technical queries, the system inverts the process by automatically generating the query from the error context, reversing the traditional query formulation direction.

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS11893589B2Automated support query

Publication Date: 2024.02.06 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Support queries are automatically provided. An error is identified during execution of an application. A support query for the error is produced using the source code for the application with the support query including context information for the error. The support query is displayed to a user.