Amazon patents privacy filters for AI data retrieval
Amazon describes a system that checks privacy tags on data before feeding it to an AI model. It compares these tags with the source of the extra information to remove any private details that do not match the allowed access levels.
In the filing’s own words
Systems and methods are provided to perform retrieval-augmented generation for machine learning models using filtered contextual data. A system can identify data associated with a machine learning model. The data may be associated with one or more first identifiers that may indicate a user, a user computing device, a model, etc. associated with the data. In response to determining that the data satisfies one or more parameters, the system can identify a need for contextual data. The system can compare the one or more first identifiers associated with the data to one or more second identifiers associated with the contextual data. Based on the comparison, the system can filter the contextual data to obtain filtered contextual data. The system may provide the filtered contextual data to the machine learning model for generation of an output.
What exactly they claim (claim 1)
1. A system comprising: data processing hardware; and memory in communication with the data processing hardware, the memory storing instructions, wherein execution of the instructions by the data processing hardware causes the data processing hardware to: identify at least one of a first input to a machine learning model or a first output of the machine learning model; identify one or more first tags associated with operation of the machine learning model based on the at least one of the first input or the first output, wherein the one or more first tags indicate a privacy-based authorization or a privacy-based restriction associated with the operation of the machine learning model; determine that the at least one of the first input or the first output satisfies one or more parameters associated with provision of contextual data to the machine learning model; obtain, from a data store that is external to the system, contextual data based on determining that the at least one of the first input or the first output satisfies the one or more parameters associated with the provision of contextual data to the machine learning model; compare the one or more first tags associated with the operation of the machine learning model with one or more second tags associated with the contextual data; identify at least a portion of the contextual data based on the contextual data and comparing the one or more first tags associated with the operation of the machine learning model with the one or more second tags associated with the contextual data, wherein the at least a portion of the contextual data comprises private data, and wherein the at least a portion of the one or more second tags are different from the one or more first tags; filter the contextual data to remove the at least a portion of the contextual data and obtain filtered contextual data; and provide, to the machine learning model, the filtered contextual data, wherein the machine learning model generates a second output based on the filtered contextual data.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- RETRIEVAL-AUGMENTED GENERATION FOR MACHINE LEARNING MODELS USING FILTERED CONTEXTUAL DATA
- Publication number
- US20260300261A1
- Application number
- 19096153
- Filed
- Mar 31, 2025
- Published
- Oct 1, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06F 16/2365 Physics & computingG06F 16/2272 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.
