Methods and systems for audio call detection

• US 10,417,385 B2
• Filed: 12/27/2016
• Issued: 09/17/2019
• Est. Priority Date: 12/31/2015
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: Kusens, Michael, Kusens, Neil
• Primary Examiner(s): Patel, Dhaval V
• Application Number:
  US15/391,095
• Publication Number:
  US 20170193180A1
• Time in Patent Office: 994 Days
• Field of Search: 3405731, 34053912, 340692, 340501, 340 105, 340541, 348 1401, 348 77, 348143, 348135
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G08B 21/02 Alarms for ensuring the safety of persons
• CPC Class Codes: G08B 21/0461 integrated or attached to an item closely associated with the person but not worn by the person, e.g. chair, walking stick, bed sensor
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

Systems and methods allow caregivers, central monitoring, and/or other persons to monitor whether a patient or another person has generated a call, such as an audio call. The systems and methods work by detecting audio within one or more audio detection zones, which are predefined areas surrounding the patient or other person to be monitored. The systems and methods detect when a command/keyword is spoken in the audio detection zone and generate an appropriate alert to an appropriate role.

Claims

1. One or more non-transitory computer storage media storing computer-readable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations comprising:

communicatively coupling one or more motion and sound sensors to a network;

displaying a visual representation of motion and sound data on a visual display apparatus communicatively coupled to the network from the one or more motion and sound sensors communicatively coupled to the network;

defining both an audio detection zone within a predetermined distance relative to a location of a first person to be monitored within a monitored environment and an audio ignore zone outside of the audio detection zone and within the monitored environment, wherein audio in the audio ignore zone is not identified, and wherein the location of the first person is identified using an identification apparatus configured to use skeletal figures, blob tracking, or facial tracking;

identifying audio detected in the audio detection zone by the first person; and

providing an alert when the audio detected in the audio detection zone includes one or more inputs.

2. The computer storage media of claim 1, further comprising configuring a remote visual display to provide a live visual display of the motion data.

3. The computer storage media of claim 1, wherein the identification apparatus is further configured to identify and distinguish a voice of the first person from any other voice spoken using voice recognition.

4. The computer storage media of claim 1, wherein the identification apparatus is further configured to identify the location of the first person using an electronic transmitter on the first person'"'"'s person, wherein the electronic transmitter is an active or passive Bluetooth, infrared, RFID, ultrasonic, or other wired or wireless transmitter.

5. The computer storage media of claim 1, further comprising logging the alert in a database.

6. The computer storage media of claim 5, wherein the database is configured to receive unknown inputs.

10. The method of claim 6, providing the alert to an appropriate role based on the one or more inputs.

7. A method for monitoring patient calls, the method comprising:

obtaining motion and sound data from one or more sensors in a room with a patient, wherein the one or more sensors includes an identification apparatus configured to identify a location of the patient using skeletal figures, blob tracking, or facial tracking;

generating a visual display of the motion and sound data;

identifying the patient in the visual display;

configuring an audio detection zone around the patient based on the motion and sound data;

ignoring audio from any area outside of the audio detection zone, wherein audio is not identified from the area outside of the audio detection zone;

detecting one or more inputs originating from the audio detection zone; and

generating an alert corresponding to the one or more inputs.

8. The method of claim 7, wherein the audio detection zone is an area that is a predefined distance around the patient to be monitored within a monitored environment, wherein the predefined distance includes one or more of a horizontal or vertical axes distance or a depth measurement.

9. The method of claim 7, further comprising identifying the area outside of the audio detection zone as audio ignore zones.

11. The method of claim 7, wherein the alert is delivered to a monitoring apparatus physically remote from the room.

12. The method of claim 7, further comprising identifying a skeletal figure of the patient to identify a location of the patient, wherein the audio detection zone moves with the patient.

13. A method for monitoring caregiver calls, the method comprising:

electronically receiving sound sensor data from one or more sensors positioned in a room with a patient and at least one caregiver;

identifying a location of the at least one caregiver using skeletal figures, blob tracking, or facial tracking the at least one caregiver;

identifying an area surrounding the at least one caregiver as an audio detection zone based on the location of the at least one caregiver;

ignoring audio from any area other than the audio detection zone, wherein audio is not identified from the any area other than the audio detection zone; and

monitoring the audio detection zone for one or more inputs spoken by the at least one caregiver within the audio detection zone based on the sound sensor data.

14. The method of claim 13, further comprising providing an alert when the one or more inputs are detected within the audio detection zone.

15. The method of claim 13, wherein the audio detection zone is an area that is a predefined distance around the at least one caregiver, wherein the predefined distance includes one or more of a horizontal or vertical axes distance or a depth measurement.

16. The method of claim 13, further comprising monitoring movements of the skeletal figure.

17. The method of claim 13, further comprising identifying an area surrounding the patient as a second audio detection zone.