US Patent Application 17744440. DYNAMICALLY ADAPTING GIVEN ASSISTANT OUTPUT BASED ON A GIVEN PERSONA ASSIGNED TO AN AUTOMATED ASSISTANT simplified abstract
DYNAMICALLY ADAPTING GIVEN ASSISTANT OUTPUT BASED ON A GIVEN PERSONA ASSIGNED TO AN AUTOMATED ASSISTANT
Organization Name
Inventor(s)
Thushan Amarasiriwardena of Alameda CA (US)
Roberto Pieraccini of Zurich (CH)
Gianluca Martini of Zurich (CH)
DYNAMICALLY ADAPTING GIVEN ASSISTANT OUTPUT BASED ON A GIVEN PERSONA ASSIGNED TO AN AUTOMATED ASSISTANT - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 17744440 Titled 'DYNAMICALLY ADAPTING GIVEN ASSISTANT OUTPUT BASED ON A GIVEN PERSONA ASSIGNED TO AN AUTOMATED ASSISTANT'
Simplified Explanation
This abstract describes a technology that allows an automated assistant to adapt its output based on a specific persona assigned to it. The assistant's output, which can include both text and visual cues, can be generated specifically for the assigned persona or can be dynamically adapted to match the persona. This technology utilizes large language models to ensure that the assistant's output reflects the assigned persona accurately.
Original Abstract Submitted
Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.
