Personalized Input Suggestions Using User Files and Search History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chatbot interfaces provide user-agnostic input suggestions, which are not personalized to individual users, leading to relevance issues and increased computational resources for follow-up queries.
Innovation Solution
A system that generates personalized input suggestions by leveraging user-specific file information and previous search queries, using AI models to predict relevant files and classify search queries, and surfaces these suggestions in query interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If user-agnostic input suggestions are provided, then the system is simple to implement, but the relevance and accuracy of suggestions deteriorates
Solution Approach 1:
The system performs preliminary actions by collecting user-specific data (files, search queries, chat interactions) before generating input suggestions. This advance preparation of user context enables the generation of personalized suggestions that are both relevant and accurate, resolving the contradiction between implementation simplicity and suggestion quality.
Solution Approach 2:
The system applies local quality by using user-specific data sources (individual file access patterns, personal search history, private chat content) to generate personalized suggestions for each user. This localized approach to data utilization improves relevance and accuracy while maintaining a unified system architecture.
2Measurement precision
If personalized input suggestions are generated using user-specific data, then the relevance and accuracy of suggestions improves, but the device complexity increases
Solution Approach 1:
The system segments the personalization process into distinct functional modules: a data collection module that gathers user-specific files and interactions, a processing module that analyzes this data, and a suggestion generation module that creates personalized inputs. This segmentation manages complexity by organizing functions into separate, manageable components.
Solution Approach 2:
The system introduces an intermediary processing layer between raw user data and generated suggestions. This intermediary module processes and structures user-specific data (files, search queries, chat history) into a format suitable for suggestion generation, thereby managing system complexity while enabling personalized output.
3Measurement precision
If user-specific files and search queries are processed, then the personalization quality improves, but the computational resources required increases
Solution Approach 1:
The system extracts only the most relevant features from user-specific data sources rather than processing entire datasets. It identifies and extracts key elements such as frequently accessed files, dominant search query patterns, and relevant chat topics, thereby reducing computational resource requirements while maintaining personalization quality.
Solution Approach 2:
The system applies partial action by processing a subset of available user data that is most indicative of user preferences and needs. Rather than analyzing all user files and interactions equally, it focuses on representative samples that provide sufficient personalization signal, thus optimizing the balance between personalization quality and computational cost.
Data Source
AI summary
Systems and methods for generating personalized input suggestions for query interfaces are described. The query interfaces can include chat interfaces (such as chatbot interfaces) and web browsers, for example. In some cases, the system generates personalized input suggestions for a particular user by identifying a set of files that are predicted to be relevant to the user and providing information about each of the files in a prompt to an artificial intelligence (AI) model. The AI model generates a response based on the prompt, and the system surfaces the response in a query interface as an input suggestion. In some cases, the system generates personalized input suggestions (e.g., using an AI model) for a particular user based on the user's search history and classifies each of the generated input suggestions with a label. The system selects input suggestions for surfacing in a query interface based on the label.