Spanning Content Trees for Generative AI Network Configuration Support

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing support content for network configurations is manually created, often outdated, lacks personalization, and is not tailored to user skills or enterprise-specific needs, leading to high abandonment rates and inefficient configuration processes.

Innovation Solution

A spanning content tree generator uses generative AI to create personalized, up-to-date support content by leveraging user personas and network information, generating targeted content through a closed-loop feedback system that includes AI models like LLMs to automate configuration tasks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual support content creation is used, then content can be customized to specific needs, but the process is time-consuming and produces generic content that does not adapt to user skills or enterprise-specific needs

Engineering Contradiction:

Improvecontent personalizationVSAvoidcontent creation time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system enables self-service content generation where the AI model automatically creates personalized support content based on user profiles, skill levels, and enterprise information without requiring manual customization for each user scenario

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes content parameters dynamically by adjusting complexity, depth, and formatting based on detected user skill levels and enterprise-specific parameters, transforming generic content into personalized content automatically

Inventive Principle:

Principle #35Parameter changes

2Reliability

If manual support content creation is used, then content can be reviewed for accuracy, but the content becomes outdated and does not reflect current network configurations

Engineering Contradiction:

Improvecontent accuracyVSAvoidcontent freshness

Core Design Contradiction:

ReliabilityVSDuration of action of stationary object

Solution Approach 1:

The system incorporates feedback loops where network device information and configuration changes are automatically fed back into the AI model to update support content, ensuring accuracy remains high while content stays current

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary content generation based on current network configurations before users need support, ensuring content is always up-to-date without requiring manual updates for each configuration change

Inventive Principle:

Principle #10Preliminary action

3Ease of manufacture

If generic support content is provided, then content creation is simplified, but user engagement decreases and configuration completion rates are low

Engineering Contradiction:

Improvecontent production simplicityVSAvoidconfiguration completion rate

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The system applies local quality by tailoring content characteristics to match specific user needs, skill levels, and enterprise contexts, making each piece of content optimally suited to its intended audience rather than using uniform generic content

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system introduces dynamics by making content adaptable and responsive to user interactions, skill levels, and contextual information, transforming static generic content into dynamic personalized content that adjusts in real-time

Inventive Principle:

Principle #15Dynamics

4Adaptability or versatility

If AI-generated content is used, then content personalization and up-to-date information are achieved, but the system complexity increases

Engineering Contradiction:

Improvecontent customizationVSAvoidsystem structure complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system uses an AI model as an intermediary component that sits between network devices and users, automatically handling content generation and personalization while shielding users from underlying system complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The AI model serves multiple functions including content generation, personalization, updating, and adaptation, consolidating what would otherwise require multiple separate systems into a single multi-functional component

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12395410B2Spanning content tree for intellectual capital creation and configuration completion function through generative artificial intelligence prompt pipeline

Publication Date: 2025.08.19 CISCO TECHNOLOGY INC

AI summary

Methods for providing spanning content tree for generating on-demand, persona-based, and journey-aware support content using machine learning. The methods involve obtaining input data related to a configuration or an operation of one or more assets in an enterprise network and based on the input data, obtaining network information about the one or more assets of the enterprise network and base support content that includes information about configuring or operating the one or more assets in the enterprise network. The methods further involve performing generative artificial intelligence learning on the base support content using the network information to generate targeted support content specific to the input data and the one or more assets of the enterprise network. The methods further involve providing the targeted support content for changing the configuration or the operation of the one or more assets in the enterprise network.