US Patent Application 17724001. INLINE SEARCH BASED ON INTENT-DETECTION simplified abstract

From WikiPatents
Jump to navigation Jump to search

INLINE SEARCH BASED ON INTENT-DETECTION

Organization Name

Microsoft Technology Licensing, LLC


Inventor(s)

Thomas Constantin of Seattle WA (US)


Matthew Sledge Epstein of Redmond WA (US)


TszYan C Zogg of Sammamish WA (US)


Lutfi Ilke Kaya of Seattle WA (US)


Christopher Andrews Jung of Seattle WA (US)


Ragavenderan Venkatesan of Mill Creek WA (US)


Ming Wu of Kirkland WA (US)


Zhiguo Yu of Issaquah WA (US)


INLINE SEARCH BASED ON INTENT-DETECTION - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 17724001 Titled 'INLINE SEARCH BASED ON INTENT-DETECTION'

Simplified Explanation

This abstract describes a technology that automatically determines a user's intention to attach a file to a document. It prompts the user to confirm their intention using a specific character, and then generates and displays a list of ranked files as suggestions for attachment. The technology uses an intent model to specify the scope of the search for attachment content from third-party applications. The system ranks the suggested files based on their relevance to the user's intention, and the user can select one or more files from the list to attach to the document.


Original Abstract Submitted

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.