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.
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 & computingMore from Amazon in AI & software
- Amazon patents system that cites sources for AI answers Sep 29, 2026
- Amazon patents voice assistants that adjust personality based on your mood Nov 3, 2026
- Amazon patents tech to swap words in movies using actor's voice Sep 8, 2026
- Amazon patents ML tool to add graphics to live sports from moving cameras Sep 15, 2026
- Amazon patents shopping assistant that remembers your search filters Oct 6, 2026
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.