/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents method to track what users tell voice assistants

This filing describes a way for voice assistants to figure out what information a user has provided during a conversation. It uses neural networks to match user speech to specific data fields, or 'slots,' and assigns a probability score to each possible answer.

Why it mattersThis helps assistants better understand complex requests by tracking exactly what details have been confirmed in a conversation.

In the filing’s own words

Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.

What exactly they claim (claim 1)

1. A method implemented by one or more processors, comprising: identifying a conversation context of an electronic dialog that includes an automated assistant and a user, the conversation context including a user utterance, of the user, that is provided during the electronic dialog; identifying, based on the conversation context, a textual descriptor for a slot instantiated in the electronic dialog, wherein the textual descriptor is a natural language description of parameters that can be defined by candidate values for the slot; processing, using one or more neural networks: the conversation context, including the user utterance, and the textual descriptor for the slot, wherein processing the textual descriptor for the slot is responsive to identifying the textual descriptor based on the conversation context; determining, based on output generated based on the processing the conversation context and the textual descriptor for the slot using the one or more neural networks: a given value, of the candidate values for the slot; and performing a further action based on the given value for the slot.

Facts

Company
Google (GOOGLE LLC)
Official title
DETERMINING STATE OF AUTOMATED ASSISTANT DIALOG
Publication number
US20260290334A1
Application number
19689451
Filed
May 27, 2026
Published
Sep 24, 2026
Inventors
3
Claims
18

Classified under

G10L 15/197 Physics & computingG06N 3/08 Physics & computingG10L 15/16 Physics & computingG10L 15/1815 Physics & computingG10L 15/22 Physics & computingG10L 15/30 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.