Cloud Console Question Generation From User Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The overwhelming volume and dynamic nature of cloud service documentation create a daunting task for users to find relevant information, leading to frustration and decreased productivity, especially for new users, due to information overload and lack of intuitive navigation.
Innovation Solution
A specialized question generation system leveraging foundation models, fine-tuned on user trajectory information and cloud service-specific documentation, generates personalized questions and links to relevant resources, reducing cognitive burden and enhancing user satisfaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If comprehensive documentation is provided to cover all cloud services and features, then information completeness is improved, but information overload and navigation difficulty increase
Solution Approach 1:
The system segments the overwhelming documentation into personalized question modules based on user trajectory. Instead of presenting all documentation at once, it divides information into relevant segments matched to specific user actions and contexts, making navigation manageable and targeted.
Solution Approach 2:
The system introduces an intermediary layer (the question generation model) between the user and the documentation. This intermediary automatically generates personalized questions based on user trajectory, serving as a mediator that filters and directs users to relevant information without requiring them to navigate the entire documentation structure.
2Loss of information
If detailed documentation is provided for all services, then information completeness is improved, but user frustration and cognitive burden increase
Solution Approach 1:
The system applies local quality by providing different levels of information detail to different users based on their specific needs and trajectory. Instead of uniform detailed documentation for all users, it tailors the information quality and depth to match each user's context, reducing cognitive burden while maintaining completeness for those who need it.
Solution Approach 2:
The system enables self-service by automatically generating personalized questions based on user trajectory without requiring users to manually search or filter documentation. The system serves itself by using its own trajectory data to create relevant questions, eliminating the need for users to navigate through frustrating documentation structures.
3Stability of the object's composition
If static documentation is maintained, then documentation stability is improved, but relevance to dynamic user needs deteriorates
Solution Approach 1:
The system introduces dynamics by making documentation delivery adaptive to user trajectory. While the underlying documentation remains stable, the system dynamically generates personalized questions based on real-time user actions and context, allowing the same stable documentation to serve multiple adaptive purposes for different users.
Solution Approach 2:
The system changes parameters by transforming static documentation into dynamic personalized questions. It modifies the presentation parameters (from static text to generated questions) based on user trajectory parameters, maintaining documentation stability while adapting its delivery to meet varying user needs.
4Measurement precision
If users manually search through documentation, then search thoroughness is improved, but time consumption and productivity loss increase
Solution Approach 1:
The system performs preliminary action by pre-generating personalized questions based on user trajectory before users need to search. Instead of waiting for users to manually search through documentation, the system proactively creates relevant questions and presents targeted information, maintaining search thoroughness while eliminating time-consuming manual navigation.
Data Source
AI summary
A method includes accessing user trajectory information associated with a user account, wherein the user trajectory information corresponds to a first session, the first session including user interactions with a cloud computing provider, generating, by a large language model, a plurality of questions based on the user trajectory information, generating, for at least a subset of the plurality of questions, a plurality of answers corresponding to the at least the subset of the plurality of questions, wherein an answer of plurality of answers corresponds to a resource of the cloud computing provider, receiving, from a user device associated with the user account, an indication that the user account has started a second session, and responsive to receiving the indication, causing display of the at least the subset of the plurality of questions and corresponding answers on the user device.