Vitalchat, Inc.

American Well Corporation

Ghafran Abbas

A monitoring device obtains an image stream of at least a part of a room of a patient. The monitoring device identifies, from a first image of the image stream, first states of the part of the room. The monitoring device identifies, from a second image of the image stream, second states of the part of the room. The monitoring device compares the first states to the second states to identify a change indicating an active state. The monitoring device transmits, in response to identifying the active state, a notification to a server. The server transmits, in response to receiving the notification, an alert to a user device associated with a healthcare provider.

Patient room real-time monitoring and alert system

In some embodiments, an apparatus includes a memory and a processor. The processor is configured to receive an intent command from a control device. The processor is configured to identify, based on the intent command, a first portion of an image captured by a first image capture device and to identify, using video analytics, a second portion of the image captured by the first image capture device. The second portion is included in an image captured by a second image capture device at a first time. The processor is configured to calculate an offset between the first portion and the second portion using the image captured by the first image capture device. The processor is configured to send a signal to adjust using the offset the second image capture device to capture an image including the first portion at a second time after the first time.

Methods and apparatus for remote camera control with intention based controls and machine learning vision state management

A system includes a server, a user device, and a monitoring device. The monitoring device is configured to identify a first active state based on a comparison of a first image to a second image, which are views of the monitored environment; and, in response to identifying the first active state, transmit a first notification that includes the second image to the server. The server is configured to transmit the second image to the user device. The user device is configured to display a plurality of images; and update, in response to receiving the second image, the plurality of images so that the second image replaces at least one image of the plurality of images; receive a request to display an image stream on the user device; transmit, to the server, a request to provide the image stream; and replace the second image with the image stream.

Attention focusing for multiple patients monitoring

A system includes a server, a user device, and a monitoring device. The monitoring device can be configured to obtain an image stream of at least a part of the room, where the image stream includes a first image and a second image that is subsequent to the first image in the image stream; identify first states based on the first image; identify second states based on the second image; compare the first states to the second states to identify a first active state; and, in response to identifying the first active state, transmit a first notification to the server. The first notification can include the second image. The server can be configured to, responsive to receiving the first notification, transmit the second image to the user device. As mentioned above, active states encompass active states and persistent states.

Devices, systems, and methods for real-time video processing and video-based user-interfacing via a videobot are provided. In an aspect, a first compute device receives a videobot deployment request with respect to a communication session with a user at a second compute device. A videobot is provisioned in response to the videobot deployment request to provide a real-time, video-based user-interface between the user and the videobot via the second compute device. A multimedia stream associated with the videobot is sent to the second compute device to cause the second compute device to render the videobot during the communication session. A live multimedia stream associated with the user is received from the second compute device. A user gesture event indicative of patient intake information is detected in connection with an act by the user during the communication session based on at least one video frame of the live multimedia stream.

Systems and methods for video-based user-interaction and information-acquisition

A device that includes a processor and a plurality of network interfaces. The plurality of network interfaces include a first network interface and secondary network interfaces. The first network interface is a currently enabled network interface for connecting the device to a service. The secondary network interfaces are currently inactive interfaces for connecting the device to the service. The processor is configured to send a heartbeat request to a heartbeat responder via the first network interface; determine whether a response is received from the heartbeat responder to the heartbeat request; and, in response to determining that the response to the heartbeat request was not received, deactivate the first network interface, and set a second network interface of the secondary network interfaces as the currently enabled network interface for connecting the device to the service.

Device-level network switching

A method for teleconferencing between a monitoring device and a user device includes establishing an audio channel connection between the user device and the monitoring device of a remote user; displaying an entry code on a display of the monitoring device; obtaining from a user of the monitoring device a verbal confirmation of the entry code; and, in response to receiving the entry code from the remote user, enabling a camera of the monitoring device. In response to the verbal confirmation, the entry code is sent to the remote user. Enabling the camera of the monitoring device establishes an audio-visual connection between the user device and the monitoring device.

Door-knocking for teleconferencing

A method for controlling a camera that is showing a view of a monitored environment includes receiving, from a user, a user command to change the view of the monitored environment; converting the user command to a camera command, where the camera command includes a change to at least one of a pan setting, a tilt setting, or a zoom setting of the camera; storing, after receiving the user command, a current position of the camera, where the current position includes at least one of a current pan position, a current tilt position, or a current zoom position; controlling, after storing the current position, the camera according to the camera command; receiving, from the user, a back command; and restoring, responsive to the back command, the camera to the current position.

Camera pan, tilt, and zoom history

A system for monitoring a room of a patient includes a server and a monitoring device. The monitoring device is configured to obtain at a first time a first image of at least a part of the room; identify a first state of the patient based on first image; obtain at a second time a second image of the at least the part of the room; identify a second state of the patient based on the second image; and, in response to the first state being different from the second state, sending a first notification to the server. The server is configured to, in response to receiving the first notification, set a monitored condition of the patient to a first value.

Hospital bed state detection via camera

Teleconferencing between a monitoring device and a user device includes receiving a first request to establish a first audio-visual conference from the user device of a remote user; in response to the first request, performing steps including enabling an audio channel of the monitoring device to receive audio input from the user device and disabling a camera of the monitoring device; displaying, on a display of the monitoring device, an entry code; receiving, from the user device of the remote user, an entered code; and in response determining that the entered code is equal to the entry code, enabling the camera of the monitoring device.

Growing community of inventors

Ashburn, VA, United States of America

Ghafran Abbas