Intent-Detected Inline File Search for Uninterrupted Document Creation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inline search menus for attaching files in document creation interrupt the user's train of thought by requiring them to suspend typing to interact with the menu, especially when relevant files are not readily available or are from third-party applications with different login information and interfaces.
Innovation Solution
A system that automatically determines user intent during document creation, generates a prompt, and displays a ranked list of files for attachment based on relevance, seamlessly integrating files from both first-party and third-party applications without interrupting the user's workflow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the system displays an inline search menu for file attachment, then the user can attach files to documents, but the user's train of thought is interrupted and productivity decreases
Solution Approach 1:
The system proactively detects user intent to attach files by analyzing the document context and automatically generates a ranked list of suggested files before the user needs to search. This preliminary preparation eliminates the need for users to interrupt their workflow to manually search for files, as the relevant files are already presented when needed.
Solution Approach 2:
The system autonomously monitors the document creation process, detects when file attachment is likely needed based on contextual analysis, and automatically presents relevant file suggestions. This self-service approach removes the burden from users to actively search for files, allowing them to simply select from pre-presentation options.
2Ease of operation
If the system presents a list of recent files, then file attachment is convenient, but relevant files from third-party applications are not included
Solution Approach 1:
The system extends file search capability across multiple data sources including local files, cloud storage, and third-party applications through a unified interface. The contextual file suggestion system aggregates files from diverse sources based on document relevance, eliminating the need for users to switch between different applications or login systems.
Solution Approach 2:
The system introduces an intermediary layer that sits between the user and multiple file sources, translating diverse file formats and access methods into a unified suggestion list. This intermediary automatically handles authentication and data retrieval from third-party applications, presenting a seamless experience to users.
3Measurement precision
If the user manually searches for files in storage, then the desired file can be found, but the user loses concentration and enters a distinct operational task
Solution Approach 1:
The system performs preliminary analysis of the document context and proactively identifies likely candidate files before the user needs to search. By pre-computing and ranking relevant files based on contextual signals, the system eliminates the time users would spend searching and reduces concentration loss by presenting options in advance.
Solution Approach 2:
The system continuously monitors document creation activities and provides real-time feedback through contextual file suggestions. This feedback loop allows the system to adapt to user needs dynamically, presenting relevant files at the optimal moment without requiring users to initiate separate search operations.
Data Source
AI summary
Systems and methods are provided for automatically determining an intent of a user based on an intent model to attach a file to a document, prompting the user to confirm the intent using a predetermined character in an inline nudge, generating and displaying an inline menu with an interactive list of ranked files as a suggestion for attachment. The disclosed technology uses the intent for specifying a scope of the inline search. The intent model for attaching content maintained by third-party applications uses a combination of an embeddings model and an N-gram model with limited seed queries and determines the intent based on intent scores associated with respective third-party applications. The present disclosure ranks respective candidate content based on a degree of relevance to the intent. The user selects one or more content from the list for attaching to the document.