Methods and mechanisms for using machine learning to generate production control scenarios
AssigneeApplied Materials, Inc.
InventorsDavid Everton Norman, Paul Hoad
Life of this patent
Estimating the term…
Abstract
A system configured to receive, by a processing device, a query related to a desired production scenario of a substrate fabrication facility and generate a prompt based on the query. The prompt comprises data related to the query and data related to one or more data structures used by a production model to generate production scenario options. The prompt is provided as input to a trained machine learning model and an output of the trained machine learning model is obtained. The output comprises modification data associated with the one or more data structures to be used by the production model to generate the desired production scenario.
Claims20
A method, comprising:
- receiving, by a processing device, a query related to a desired production scenario of a substrate fabrication facility;
- generating a prompt based on the query, wherein the prompt comprises data related to the query and data related to one or more data structures used by a production model to generate production scenario options;
- providing the prompt as input to a trained machine learning model;
- and
- obtaining an output of the trained machine learning model, the output comprising modification data associated with the one or more data structures to be used by the production model to generate the desired production scenario.
A system, comprising:
- a memory device;
- and
- a processing device, operatively coupled to the memory device, to perform operations comprising:
- receiving a query related to a desired production scenario of a substrate fabrication facility;
- generating a prompt based on the query, wherein the prompt comprises data related to the query and data related to one or more data structures used by a production model to generate production scenario options;
- providing the prompt as input to a trained machine learning model;
- and
- obtaining an output of the trained machine learning model, the output comprising modification data associated with the one or more data structures to be used by the production model to generate the desired production scenario.
A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device operatively coupled to a memory, performs operations comprising:
- receiving a query related to a desired production scenario of a substrate fabrication facility;
- generating a prompt based on the query, wherein the prompt comprises data related to the query and data related to one or more data structures used by a production model to generate production scenario options;
- providing the prompt as input to a trained machine learning model;
- and
- obtaining an output of the trained machine learning model, the output comprising modification data associated with the one or more data structures to be used by the production model to generate the desired production scenario.
Dependencies are inferred from the claim text.