Back to results
US 11,509,794 B2Granted
Machine-learning command interaction
AssigneeHewlett-Packard Development Company, L.P.
InventorsChristian Perone, Thomas Paula, Roberto Pereira Silveira
Life of this patent
Estimating the term…
Abstract
Examples disclosed herein relate to receiving a query via a chat interaction, translating the received query into one of a set of predefined commands according to a trained machine-learning model, and providing a result of the one of the set of predefined commands to the chat interaction.
Claims16
A system, comprising:
- a memory storing:
- a language model engine to:
- translate a received query into one of a set of predefined commands according to a trained model, the set of predefined commands populated based on a function listing via an application programming interface of the system;
- and
- an interaction engine to:
- receive the query from a user,
- receive the predefined command from the language model engine,
- execute the predefined command using the application programming interface of the system, and
- provide a response to the query to the user according to the execution of the predefined command received from the language model engine.
6 more elements
A method comprising:
- receiving a query via a chat interaction of a device;
- translating the received query into one of a set of predefined commands according to a trained machine-learning model, the set of predefined commands populated based on a function listing via an application programming interface of the device;
- executing the one of the set of predefined commands using the application programming interface of the device;
- and
- providing a result of the execution of the one of the set of predefined commands to the chat interaction.
2 more elements
A non-transitory machine readable medium storing instructions executable by a processor to:
- train a machine-learning model comprising a plurality of vector-represented word embeddings extracted from a plurality of natural language documents;
- create a set of predefined commands associated with a printing device, the set of predefined commands populated based on a function listing via an application programming interface of the printing device;
- extract a vector representation of each of the set of predefined commands according to the machine-learning model;
- receive a query from a user via a chat interface;
- identify a semantically closest one of the set of predefined commands to the received query according to the machine-learning model;
- execute the one of the set of predefined commands using the application programming interface of the printing device;
- and
- provide a response to the query according to the execution of the one of the set of predefined commands via the chat interface.
5 more elements
Dependencies are inferred from the claim text.