Invention Grant
- Patent Title: Message analysis using a machine learning model
-
Application No.: US15853189Application Date: 2017-12-22
-
Publication No.: US10659399B2Publication Date: 2020-05-19
- Inventor: Jakob Nicolaus Foerster , Matthew Sharifi
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Shumaker & Sieffert, P.A.
- Main IPC: H04L12/28
- IPC: H04L12/28 ; H04L12/58 ; G06F17/27 ; G06N20/00 ; G06Q10/10

Abstract:
A method includes receiving a received message and a draft reply message to the received message, the received message including a received message component, the received message component representing one or more of a question, a request, and a subject. The method also includes parsing the received message to detect the received message component and parsing the draft reply message into one or more reply message components, identifying, using one or more machine learning models, informational components associated with the received message component and the one or more reply message components by at least applying the machine learning module to the received message component and each reply message component of the one or more reply message, and identifying, based on the one or more informational components, one or more deficient components in the subject draft reply message, and outputting, for display, information about the one or more deficient components.
Public/Granted literature
- US20190199656A1 MESSAGE ANALYSIS USING A MACHINE LEARNING MODEL Public/Granted day:2019-06-27
Information query