US 2026/0300261 A1Published application

Retrieval-augmented generation for machine learning models using filtered contextual data

AssigneeAmazon Technologies, Inc.

InventorsMatthew Richard Schwartz, Garrett Ryan Galloway, John Miller, Zinnur Gucu

Life of this patent

Estimating the term…

Loading patent…

Abstract

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.

Claims20

Dependent claims

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.

9 more elements

A method comprising:

identifying at least one of a first input to a machine learning model or a first output of the machine learning model;
identifying 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;
determining 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;
identifying 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;
comparing 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;
obtaining filtered contextual data based on the contextual data and based on 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;
and
providing, to the machine learning model, the filtered contextual data, wherein the machine learning model generates a second output based on the filtered contextual data.

5 more elements

One or more non-transitory computer-readable media including computer-executable instructions, wherein execution of the computer-executable instructions by a computing system including a processor causes the computing system 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 identifiers associated with operation of the machine learning model based on the at least one of the first input or the first output;
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;
in response to 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, obtain filtered contextual data based on the one or more first identifiers associated with the operation of the machine learning model and one or more second identifiers associated with the 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.

3 more elements

Dependencies are inferred from the claim text.