AmazonGranted patentAI & softwareInterest 6/10

Amazon patents chatbot tech that remembers past conversation turns

Amazon has been granted a patent for a system that helps chatbots understand multi-turn conversations by combining current user input with details from previous exchanges. The method uses a specific framework to encode user speech and merge it with contextual signals like past intents and active topics to determine the next step in the dialogue.

Why it mattersThis improves how conversational agents handle complex, back-and-forth interactions by ensuring they do not lose track of the conversation's state.

In the filing’s own words

Systems, methods, and apparatuses for contextual natural language understanding are detailed. An exemplary method includes receiving a user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent; encoding the user utterance into a sequence of tokens using an encoder that is independent of an intent classification and slot labelling (ICSLH); and obtaining, using the ICSLH, an intent classification and one or more slot labels from the encoded user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog, the contextual information associated with each turn of the one or more previous turns including a previous intent, a previous dialog act, an active context, and an elicited slot.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: receiving a user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent; providing to a contextual natural language understanding (cNLU) framework: the user utterance, and contextual information associated with one or more previous turns of the multi-turn chat dialog, the contextual information associated with each turn of the one or more previous turns including a previous intent, a previous dialog act, an active context, and an elicited slot; and obtaining, from the contextual natural language understanding framework, an intent classification and one or more slot labels by: encoding the user utterance using an encoder of an encoder subnetwork of the cNLU framework, wherein encoding the user utterance is independent of an intent classification and slot labelling head (ICLSH) subnetwork, in an ICSLH of the ICSLH subnetwork, generating embeddings for the contextual information, generating an intent contextual signal and a slot label contextual signal from the generated embeddings, fusing the encoded user utterance provided by the encoder subnetwork and contextual signals, and generating the intent classification and the one or more slot labels from the fused encoded user utterance based on context provided by the contextual signals; providing the intent classification and the one or more slot labels to a dialog manager of the multi-turn chat dialog to determine a next dialog; and providing the next dialog in the multi-turn chat dialog to the user.

Facts

Company
Amazon (Amazon Technologies, Inc.)
Official title
Scalable machine learning inference
Patent number
US12792841B1
Application number
18067290
Filed
Dec 16, 2022
Granted
Nov 10, 2026
Inventors
14
Claims
20

Classified under

G06F 40/35 Physics & computingG06F 40/117 Physics & computingG06F 40/126 Physics & computingG06F 40/284 Physics & computing

More from Amazon 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.