System and method for presence and pulse detection from wireless signals

A system for detecting a user, the system comprising:

• one or more connected devices located in a sensing area;
• and
• a cloud server that:
• generates a baseline condition based on one or more captures by the one or more connected devices when the user is not present in the sensing area;
• receives activity data and engagement level data associated with the user from the one or more connected devices, wherein a channel frequency response between the one or more connected devices indicates a breathing condition associated with the user;
• stores the activity data and the engagement level data for a plurality of time periods;
• identifies one or more time periods in the plurality of time periods where the stored user activity data and the stored engagement level data are correlated,
• compares current activity data and current engagement level data to identify one or more cycles, wherein the identified cycles correspond to one or more time periods where the activity data and the engagement level data repeat,
• detects a deviation in the current activity data from the identified cycles,
• increments an alert score associated with the user,
• determines the alert score is above a predefined threshold, and
• sends an alert to a device associated with the user.

A non-transitory, computer-readable storage medium having embodied thereon instructions executable by one or more processors to perform a method for detecting a user, the method comprising:

• generating a baseline condition based on one or more captures by one or more connected devices in a sensing area when the user is not present in the sensing area;
• receiving activity data and engagement level data associated with the user from the one or more connected devices in all the sensing area, wherein a channel frequency response between the one or more connected devices indicates a breathing condition associated with the user;
• storing the activity data and the engagement level data for a plurality of time periods;
• identifying one or more time periods in the plurality of time periods where the stored user activity data and the stored engagement level data are correlated;
• comparing current activity data and current engagement level data to identify one or more cycles, wherein the identified cycles correspond to one or more time periods where the activity data and the engagement level data repeat;
• detecting a deviation in the current activity data from the identified cycles;
• incrementing an alert score associated with the user;
• determining the alert score is above a predefined threshold;
• and
• sending an alert to a device associated with the user.