Conversational Configuration Templates for Software Package Setup

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Configuring software packages is a time-consuming and costly process that is prone to manual errors and requires domain-specific knowledge, making it dependent on subject matter experts and delaying the configuration process.

Innovation Solution

Leveraging collaborative foundation models to orchestrate software configuration, utilizing a configuration system that includes a knowledge base, UI/UX module, and multiple foundation models to generate and refine configuration templates based on conversational queries, reducing reliance on manual processes and subject matter experts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual configuration processes are used, then flexibility and customization are possible, but time consumption and error rates increase

Engineering Contradiction:
Improveconfiguration accuracyVSAvoidconfiguration time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-defining configuration templates with common software settings and parameters. These templates are prepared in advance based on typical enterprise requirements, allowing the system to quickly instantiate configurations without manual setup of each parameter from scratch, thereby reducing configuration time while maintaining accuracy through pre-validated template structures.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary configuration management system that acts as a mediator between users and software packages. This intermediary layer provides automated template selection, parameter validation, and configuration generation capabilities, reducing manual errors while maintaining the flexibility to customize configurations when needed, thus improving both accuracy and efficiency.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If domain experts manually configure software, then high accuracy is achieved, but dependency on experts and cost increase

Engineering Contradiction:
Improveconfiguration efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system enables self-service configuration by allowing users to select from pre-defined templates and make simple customizations without requiring domain expertise. The automated system handles complex parameter validation, consistency checks, and configuration generation, empowering non-experts to efficiently configure software while the system manages the complexity internally through intelligent algorithms and structured template systems.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If customized configurations are created manually, then specific requirements are met, but error propagation increases

Engineering Contradiction:
Improveconfiguration flexibilityVSAvoidconfiguration reliability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system implements feedback mechanisms that automatically validate configuration parameters against defined rules and constraints. When users customize configurations based on specific requirements, the system provides real-time feedback on potential errors, conflicts, or invalid settings, allowing users to correct issues before deployment. This feedback loop maintains configuration flexibility while preventing error propagation through automated validation and consistency checking.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20260056732A1Computer-implemented method, computer program product and computer system for configuring software packages
Publication Date: 2026.02.26 ACCENTURE GLOBAL SOLUTIONS LTD
  • US20260056732A1 patent drawing
  • US20260056732A1 patent drawing
  • US20260056732A1 patent drawing

AI summary

Methods, systems, and computer-readable storage media for generating configuration templates. For generating the configuration templates, conversational queries are generated. Based on conversational responses to the conversational queries, a task context and a task intent are determined using a first foundation model to identify software packages to be configured to perform tasks. Based on the task context, the task intent, and the conversational responses, a workflow template is generated using a second foundation model. Further, based on conversational responses, configuration fields of the workflow template for subtasks of each task are refined using a third foundation model. Based on the configuration fields of the workflow template, configuration fields of the configuration template for each task are generated using a fourth foundation model.