Domain mapping for privacy preservation
AssigneeAmazon Technologies, Inc.
InventorsRagav Venkatesan, Gurumurthy Swaminathan
Life of this patent
Estimating the term…
Abstract
Implementations detailed herein include description of a computer-implemented method. In an implementation, the computer-implemented method including training a machine learning model using domain mapped third party data; and performing inference using the machine learning model by: receiving scoring data, domain mapping the received scoring data using a domain mapper that was used to generate the domain mapped third party data, and applying the machine learning model to the domain mapped received scoring data to generate an output result.
Claims20
A computer-implemented method comprising:
- requesting third party data from a repository hosted by a web services provider;
- receiving domain mapped third party data from the web services provider, the web services provider to utilize a domain mapper to generate the domain mapped third party data;
- allocating resources of the web services provider to train a machine learning model using the received domain mapped third party data;
- training the model using the received domain mapped third party data using on the allocated resources of the web services provider;
- generating at least one container including the model and the domain mapper used to generate the domain mapped third party data;
- allocating resources of the web services provider to perform inference using the container;
- performing inference using the allocated resources of the web services provider by:
- receiving scoring data,
- domain mapping the received scoring data using the domain mapper,
- applying the machine learning model to the domain mapped received scoring data to generate an output result, and
- providing the output result.
A computer-implemented method comprising:
- training a machine learning model using domain mapped third party data;
- and
- performing inference using the machine learning model by:
- receiving scoring data,
- domain mapping the received scoring data using a domain mapper that was used to generate the domain mapped third party data, and
- applying the machine learning model to the domain mapped received scoring data to generate an output result.
A system comprising:
- an endpoint implemented by a first one or more electronic devices;
- and
- a web services model repository service implemented by a second one or more electronic devices, the web services model repository service including instructions that upon execution are to cause:
- a training a machine learning model using domain mapped third party data, and
- a performance of inference using the machine learning model of the endpoint by:
- receiving scoring data,
- domain mapping the received scoring data using a domain mapper that was used to generate the domain mapped third party data, and
- applying the machine learning model to the domain mapped received scoring data to generate an output result.
Dependencies are inferred from the claim text.