CRAFTING FEEDBACK DIALOGUE WITH A DIGITAL ASSISTANT
First Claim
1. A system for personalizing a digital assistant, the system comprising:
- a processing unit;
a memory communicatively coupled to the processing unit, the memory maintaining activity logs corresponding to one or more components of one or more user devices; and
a digital assistant, executed by the processing unit, the digital assistant further executed to;
process the activity logs maintained in the memory;
generate one or more questions corresponding to the processed activity logs;
conduct a natural language conversation as a learning session based on the one or more questions;
receive user input during the learning session based on the one or more questions;
identify sentiment associated with at least one facet of the user input; and
update a user profile based on the user input and the identified sentiment of the user input.
1 Assignment
0 Petitions
Accused Products
Abstract
Examples described herein dynamically personalize a digital assistant for a specific user, creating a personal connection between the digital assistant and the user. The digital assistant accesses user activity and generates queries based on the user activity. The digital assistant facilitates natural language conversations as machine learning sessions between the digital assistant and the user using the one or more queries to learn the user'"'"'s preferences and receives user input from the user during the learning session in response to the queries. The digital assistant dynamically updates a personalized profile for the user based on the user input during the natural language conversations.
170 Citations
20 Claims
-
1. A system for personalizing a digital assistant, the system comprising:
-
a processing unit; a memory communicatively coupled to the processing unit, the memory maintaining activity logs corresponding to one or more components of one or more user devices; and a digital assistant, executed by the processing unit, the digital assistant further executed to; process the activity logs maintained in the memory; generate one or more questions corresponding to the processed activity logs; conduct a natural language conversation as a learning session based on the one or more questions; receive user input during the learning session based on the one or more questions; identify sentiment associated with at least one facet of the user input; and update a user profile based on the user input and the identified sentiment of the user input. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A mobile device comprising:
-
a processing unit; a memory communicatively coupled to the processing unit; and a digital assistant executed by the processing unit to; process activity logs maintained on the memory; identify one or more areas of desired feedback based on the activity logs; generate one or more questions corresponding to the one or more areas of desired feedback; initiate a natural language conversation based on the one or more questions; receive user input during the natural language conversation based on the one or more questions; and perform at least one task related to a user preference based on the user input. - View Dependent Claims (8, 9, 10, 11, 12, 13)
-
-
14. A method for digital assistant personalization, the method comprising:
-
accessing, by a digital assistant implemented on a computing device, activity logs; generating one or more queries based on the accessed activity logs; initiating a natural language conversation as a machine learning session between the digital assistant and a user using the one or more queries; receiving user input during the natural language conversation in response to the one or more queries; and updating a personalized profile associated with the user based on the user input to personalize the digital assistant. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
Specification