Personal assistant computing system monitoring

• US 10,229,755 B1
• Filed: 06/01/2018
• Issued: 03/12/2019
• Est. Priority Date: 10/11/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Anumalasetty, Kiran K., Ayyagari, Phani Kumar V. U., Bhide, Manish A.
• Primary Examiner(s): Le, Linh Giang
• Application Number:
  US15/995,605
• Time in Patent Office: 284 Days
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/05 Word boundary detection
• CPC Class Codes: G10L 15/083 Recognition networks G10L15/142, G10L15/16 take precedence
• CPC Class Codes: G10L 25/21 the extracted parameters being power information
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A computing system is configured to process at least one voice input of a user and output an audio result. The computing system comprises at least one microphone configured to receive the voice input from the user. The computing system further comprises at least one processor configured to at least interpret the voice input and generate the audio result. The computing system also comprises an output speaker device configured to output the audio result. The audio result includes a description of whether one or more behavioral health states associated with the user have been detected.

Claims

1. A system comprising:

a memory; and

a processor in communication with the memory, the processor configured to obtain program instructions from the memory that cause the processor to perform a method comprising;

downloading, in response to a user selection, a health plugin for a behavioral health application installed on the user'"'"'s mobile device, the selected health plugin configured for use with the behavioral health application in monitoring a first type of health state, the health plugin selected for download from among a plurality of health plugins that are each configured for use with the behavioral health application in monitoring a respective type of health state of a corresponding plurality of types of health states;

registering, in response to the downloading and based on user health attributes that the selected health plugin is configured to monitor, a plurality of sensor devices to the behavioral health application, wherein the plurality of sensor devices include a microphone and an accelerometer;

registering, in response to the downloading and based on remedial actions that the selected health plugin is configured to initiate, a plurality of output devices to the behavioral health application, wherein the plurality of output devices include a speaker and a treadmill;

querying, by the behavioral health application, a health record service for historical data about the user that is associated with the health attributes that the selected health plugin is configured to monitor;

generating, based on the queried historical data, a Bayesian network configured to utilize a directed acyclic graph to predict triggering causes of health event episodes of the user that are associated with the first type of health state;

detecting, by the registered plurality of sensor devices, real-time information about the health attributes of the user, wherein the detecting the real-time information includes detecting, by the microphone, a volume level of the user'"'"'s voice and further includes detecting, by the accelerometer, movements of the user;

determining, by the behavioral health application and based on the detected information, that a first health event episode is occurring;

using the Bayesian network to predict a triggering cause of the first health episode;

selecting, based on the predicted triggering cause, a particular remedial action; and

initiating, by the behavioral health application, the selected remedial action by activating at least one of the plurality of registered output devices to generate outputs for completing the selected remedial action, wherein the activating the at least one of the plurality of registered devices includes causing the speaker to play a particular song and further includes causing the treadmill to become activated.