Speculative task flow execution
AR Raux, J Leach - US Patent 11,984,124, 2024 - Google Patents
An example process includes: receiving a natural language input having a start time and
including first and second portions respectively received from the start time to a first time and …
including first and second portions respectively received from the start time to a first time and …
Generating multi-perspective responses by assistant systems
In one embodiment, a method includes receiving a user query from a client system
associated with a first user, determining a plurality of dialog-intents, each being asso ciated …
associated with a first user, determining a plurality of dialog-intents, each being asso ciated …
Predictive injection of conversation fillers for assistant systems
E Koukoumidis, MR Hanson, MM Agsen - US Patent 11,245,646, 2022 - Google Patents
6,665,640 B1 6,901,364 B2 6,968,333 B2 6,990,513 B2 7,069,215 B1 7,080,004 B2
7,124,123 B1 7,158,678 B2 7,397,912 B2 7,467,087 B1 7,624,007 B2 7,702,508 B2 …
7,124,123 B1 7,158,678 B2 7,397,912 B2 7,467,087 B1 7,624,007 B2 7,702,508 B2 …
Techniques for incremental computer-based natural language understanding
EV Doggett, A Modi, N Nocon - US Patent 11,749,265, 2023 - Google Patents
Various embodiments disclosed herein provide techniques for performing incremental
natural language understanding on a natural language understanding (NLU) system. The …
natural language understanding on a natural language understanding (NLU) system. The …
Ephemeral content digests for assistant systems
B Nelson, V Natarajan, SCP Mei, W Yang - US Patent 12,198,413, 2025 - Google Patents
In one embodiment, a method includes, by one or more computing systems, receiving, by an
assistant xbot associated with the one or more computing systems, a user request for a …
assistant xbot associated with the one or more computing systems, a user request for a …
Processing multimodal user input for assistant systems
V Natarajan, SCP Mei, Z Zuo - US Patent 11,676,220, 2023 - Google Patents
In one embodiment, a method includes receiving a user input based on a plurality of
modalities at the client system, wherein at least one of the modalities of the user input is a …
modalities at the client system, wherein at least one of the modalities of the user input is a …
Dialog state tracking for assistant systems
In one embodiment, a method includes, by one or more computing systems, receiving, from
a client system, an input in a multi-turn message thread, parsing the input to identify a …
a client system, an input in a multi-turn message thread, parsing the input to identify a …
Multiple wake words for systems with multiple smart assistants
In one embodiment, a method includes by a client system associated with a user, receiving,
at the client system, a user input from the user, parsing, by the client system, the first user …
at the client system, a user input from the user, parsing, by the client system, the first user …
Active listening for assistant systems
LH Martinson, D Levison, HW Black… - US Patent …, 2024 - Google Patents
In one embodiment, a method includes receiving a first user input comprising a wake word
associated with an assistant xbot from a first client system, setting the assistant xbot into a …
associated with an assistant xbot from a first client system, setting the assistant xbot into a …
Task execution based on real-world text detection for assistant systems
In one embodiment, a method includes accessing visual signals comprising images
portraying textual content in a real-world environment associated with a first user from a …
portraying textual content in a real-world environment associated with a first user from a …