Selective content generation
AssigneeSpaceCraft, Inc.
InventorsMichael John Cafarella, Ian M. Richter, Alexis R. Haraux
Life of this patent
Estimating the term…
Abstract
In one implementation, a method of generating content is performed at a device having one or more processors and non-transitory memory. The method includes obtaining a database including a plurality of elements. The method includes generating a prompt to select one of the plurality of elements that satisfies one or more criteria regarding a topic of interest. The method includes submitting the prompt to a foundational model trained on a training dataset. The method includes receiving, from the foundational model in response to the prompt, content including a selected one of the plurality of elements.
Claims20
A method comprising:
- obtaining a database including a plurality of elements;
- generating a prompt to select one of the plurality of elements that satisfies one or more criteria regarding a topic of interest;
- submitting the prompt to a foundational model trained on a training dataset;
- and
- receiving, from the foundational model in response to the prompt, content including a selected one of the plurality of elements.
A device comprising:
- non-transitory memory;
- and
- one or more processors to:
- obtain a database including a plurality of elements;
- generate a prompt to select one of the plurality of elements that satisfies one or more criteria regarding a topic of interest;
- submit the prompt to a foundational model trained on a training dataset;
- and
- receive, from the foundational model in response to the prompt, content including a selected one of the plurality of elements.
A non-transitory memory storing one or more programs, which, when executed by one or more processors of a device, cause the device to:
- obtain a database including a plurality of elements;
- generate a prompt to select one of the plurality of elements that satisfies one or more criteria regarding a topic of interest;
- submit the prompt to a foundational model trained on a training dataset;
- and
- receive, from the foundational model in response to the prompt, content including a selected one of the plurality of elements.
Dependencies are inferred from the claim text.