Proactive Contextual Search Query Identification for Meetings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search technologies require explicit user input for search queries, which can be cumbersome and impractical in real-time interactions, such as electronic meetings.
Innovation Solution
A computing system performs proactive searches by analyzing user context, identifying keywords through natural language processing, and mapping them to relevant domains to provide search results without explicit user input, enabling real-time presentation of relevant content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional search technologies require explicit user input for search queries, then search accuracy is improved, but user convenience and operational efficiency deteriorate
Solution Approach 1:
The system performs preliminary actions by proactively identifying search queries from user interactions (such as transcribing spoken words in meetings, analyzing document content, or monitoring email communications) before the user explicitly formulates a search query. This allows the system to anticipate user information needs and prepare search results in advance, thereby improving user convenience without sacrificing search accuracy through explicit user input
2Reliability
If conventional search technologies require explicit user input for search queries, then search intent clarity is improved, but productivity and time efficiency deteriorate
Solution Approach 1:
The system performs preliminary search actions by analyzing user context (such as ongoing meetings, open documents, or email threads) and executing searches before the user explicitly requests them. This preliminary action maintains search intent clarity through context analysis while significantly improving productivity by eliminating the time users would spend formulating and submitting explicit search queries
Solution Approach 2:
The system provides self-service by automatically identifying search queries and executing searches based on inferred user intent from contextual data. This eliminates the need for users to manually input search queries, thereby improving productivity while maintaining reliable search intent determination through automated context analysis and machine learning algorithms
Data Source
AI summary
A computing system obtains text that relates to an experience of a user and determines a search intent based upon the text and a context of the user, where the context is determined based upon activity history of the user in a plurality of applications. The computing system identifies potential keywords in the text and identifies a search domain in a plurality of search domains based upon the potential keywords. The computing system computes a confidence score for each of the potential keywords based upon the search domain, the context, and prior search queries of the user. The computing system identifies keywords from amongst the potential keywords based upon the confidence scores and executes a search over an index based upon the keywords, where the index indexes user content of the user and content of an enterprise. The computing system presents search results for the search to the user.