Enjoy your
FREE PREVIEW which shows only 2022 data and 25 documents. Contact
Patent Forecast for full access.
AI Biotech/Diagnostics: Cardio
Search All Patents in AI Biotech/Diagnostics: Cardio
Patent US10909990
Issued 2021-02-02
Methods And Systems For Speech Signal Processing
Methods and systems for speech signal processing an interactive speech are described. Digitized audio data comprising a user query from a user is received over a network in association with a user identifier. A protocol associated with the user identifier is accessed. A personalized interaction model associated with the user identifier is accessed. A response is generated using the personalized interaction model and the protocol. The response is audibly reproduced by a voice assistance device.
Much More than Average Length Specification
View the Patent Matrix® Diagram to Explore the Claim Relationships
USPTO Full Text Publication >
- 1. A system configured to enable a user to obtain information related to a medical protocol using an audible query, comprising:
a network interface; at least one processing device operable to:
generate a profile for a user using user data indicating:
how much information the user wants regarding medical treatments associated with the user, and
access a medical care record associated with the user, the medical care record comprising a first medical protocol including patient care instructions, the patient care instructions including:
a first patient care instruction associated with a first time period, and
a second patient care instruction associated with a second time period;
generate a first personalized interaction model using:
the user profile, and
the user medical care record comprising a first medical protocol including patient care instructions;
update the first personalized interaction model at least partly in response to a detection of a new medical care record or a modification of the first medical care record;
receive over a network using the network interface digitized audio data comprising a user query from a user, the digitized audio data streamed in real time from a user device;
receive over the network using the network interface an identifier associated with the digitized audio data;
utilize the identifier associated with the digitized audio data to access the first personalized interaction model generated using the user profile and the user medical care record;
use a natural language processing engine to:
translate the digitized audio data to text;
identify, from the translated digitized audio data, a user intent associated with the query, wherein identification of the user intent associated with the query comprises determining what computerized service the query corresponds to;
identify, from the translated digitized audio data, a variable associated with the user intent;
access from computer readable memory the first medical protocol;
access, using a computer resource, a current date and time;
identify one or more patient care instructions included in the first medical protocol associated with a specified date range and/or time period, that corresponds to the current date and/or time;
utilize:
the first personalized interaction model,
the first medical protocol,
the current date and/or time,
the identified one or more patient care instructions,
the variable associated with the user intent, and
the computerized service identified using the user intent, to generate a response to the user query; and
enable the response to the user query to be transmitted to and audibly reproduced by the user device.
- 19. A computerized method, the method comprising:
generating a profile for a user using user data indicating:
how much medical information the user wants regarding medical issues associated with the user;
accessing a medical care record associated with the user, the medical care record comprising a first medical protocol including patient care instructions, the patient care instructions including:
a first patient care instruction associated with a first time period, and
generating a first personalized interaction model using:
the user profile, and
the user medical care record comprising a first medical protocol including patient care instructions;
receiving over a network using a network interface digitized audio data comprising a user communication from a user, the digitized audio data received in real time from a user device; receiving over the network using the network interface data identifying the user; utilizing the data identifying the user to access the first personalized interaction model generated using the user profile and the user medical care record; using a natural language processing engine to:
translate the digitized audio data to text;
identify a user intent associated with the user communication;
identify a variable associated with the user intent;
identifying, using the user intent identified using the natural language processing engine, what computerized service to invoke; accessing from computer readable memory the first medical protocol associated with the user; accessing, using a computer resource, a current date and time; parsing the first protocol to identify one or more patient care instructions included identified in the first medical protocol associated with a specified date range and/or time period, that corresponds to the current date and/or time; utilizing:
the first personalized interaction model,
the first medical protocol,
the identified one or more patient care instructions,
the variable associated with the user intent, and
the computerized service identified using the user intent, to generate a response to the user communication; and
causing the response to the user communication to be transmitted to and audibly reproduced by the user device.
