Automated Support Tree Generation for SaaS Issue Deflection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic support systems for resolving user issues in SaaS environments are inefficient due to the need for extensive expert time to manually update questions and solutions, leading to a backlog of unresolved issues and suboptimal support trees that do not utilize all historical data, resulting in higher ticket rates and increased expert time expenditure.
Innovation Solution
The development of systems and methods that automatically generate support trees by analyzing historical data to determine most used solutions, generating correlations, clusters, and keywords, and creating nodes that provide optimized questions and solutions, allowing for efficient deflection of user issues through a user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If experts manually create and update support trees based on their experience, then the support tree can be generated, but the expert time required increases significantly and the system cannot keep up with rapidly changing SaaS issues
Solution Approach 1:
The system automatically generates support trees by analyzing historical support interactions, tickets, and resolutions without requiring expert intervention. The automated support tree generation system processes historical data, identifies patterns, and creates optimized support trees independently, eliminating the need for experts to manually create and update support trees while keeping pace with changing SaaS issues
Solution Approach 2:
The system continuously analyzes historical support data in advance to pre-generate and update support trees before new issues arise. By processing historical tickets, resolutions, and interactions proactively, the system maintains an up-to-date support tree that reflects the latest solutions without requiring reactive expert updates when new issues emerge
2Reliability
If experts manually determine questions and solutions for support trees, then the support tree can be created, but the completeness and optimization of deflection responses deteriorates due to limited expert experience
Solution Approach 1:
The system leverages all historical support data including tickets, resolutions, interactions, and expert notes to create a universal knowledge base that encompasses all past issues and solutions. This comprehensive data utilization ensures that the generated support tree contains complete and optimized deflection responses covering the full range of historical support cases, not just those known to individual experts
Solution Approach 2:
The system continuously analyzes historical support interactions and ticket resolutions to learn from past outcomes and improve support tree quality. By processing feedback from resolved tickets and successful deflections, the system refines its understanding of effective questions and solutions, ensuring increasingly complete and optimized responses over time
3Reliability
If the support tree is manually updated by experts, then the current issues can be addressed, but the system falls behind as more updates and SaaS issues arise quickly
Solution Approach 1:
The system continuously and automatically processes historical support data, analyzes patterns, and updates the support tree in an ongoing manner without interruption. This continuous automated operation ensures the support tree remains current with all new SaaS issues and resolutions as they occur, maintaining reliability while keeping pace with rapid changes without periodic manual intervention
Solution Approach 2:
The system replaces the manual mechanical process of expert-driven support tree creation with an automated computational system. By substituting expert manual work with automated data processing and analysis, the system can adapt to new issues at the speed of data generation rather than the slower pace of manual expert updates, maintaining both reliability and speed
Data Source
AI summary
Programs, systems, and methods for generating a support tree for automated resolution of user issues. In some embodiments, historical data may be obtained from a history of support interactions including historical issues and solutions to the historical issues. Most used solutions may be determined and stored with associated historical issues. Clusters of issues and solutions may be generated and labeled for generation of support tree nodes. Furthermore, solutions may be correlate such that a plurality of solutions may be provided for the resolving user issues. In some embodiments, issue data indicative of user issues may be provided by users. As the user provides issue data, deflections between nodes on the support tree may narrow a field of potential solutions to one or more solutions to be provided to the user.