Amazon patents live meeting summaries that shrink as they grow
Amazon describes a system that creates a summary of a meeting as it happens by feeding small pieces of the conversation into a large language model. To keep the summary short and useful, the system checks if the text gets too long and then asks the model to rewrite it into a tighter version.
In the filing’s own words
The present disclosure generally relates to systems and methods for generating and evaluating a transcript summary based on a transcript of an active meeting. A summary generation system may generate a summary based on an active meeting while minimizing latency and the number of calls to a large language model. The summary generation system may provide each transcript chunk of a transcript as input into an LLM for summarization and append to a transcript summary. In addition, the summary generation system may determine whether the transcript summary of the transcript has reached a threshold, such as a length or word count threshold. If the threshold has been reached, the summary generation system may input the transcript summary into the LLM to generate a revised transcript summary. The revised transcript summary may replace the existing transcript summary.
What exactly they claim (claim 1)
1. A system, comprising: a memory to store computer-executable instructions; and a processor in communication with the memory, wherein the computer-executable instructions, when executed by the processor, cause the processor to at least: receive a transcript chunk of a transcript of an active meeting; provide the transcript chunk and a first prompt as input into a machine learning model; determine, using the machine learning model, a chunk summary corresponding to the transcript chunk; append the chunk summary to a transcript summary of the transcript of the active meeting to form a revised transcript summary; determine that a summary threshold has been reached based on the revised transcript summary; provide the revised transcript summary and a second prompt as input into the machine learning model in response to the summary threshold being reached; determine, using the machine learning model, a new transcript summary; and replace the revised transcript summary with the new transcript summary.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- Real-time summarization large language model
- Patent number
- US12737533B1
- Application number
- 18605660
- Filed
- Mar 14, 2024
- Granted
- Sep 15, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06F 40/166 Physics & computingMore from Amazon in AI & software
- Amazon patents system that cites sources for AI answers Sep 29, 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
- Amazon patents system where AI agents split tasks and talk to each other Oct 20, 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.