US 11,455,522 B2Granted

Detecting personal danger using a deep learning system

AssigneeInternational Business Machines Corporation

InventorsSteven A. Cordes, Michael S. Gordon, Nigel Hinds, Maja Vukovic

Life of this patent

Estimating the term…

Loading patent…

Abstract

A mobile electronic device such as a smartphone is used in conjunction with a deep learning system to detect and respond to personal danger. The deep learning system monitors current information (such as location, audio, biometrics, etc.) from the smartphone and generates a risk score by comparing the information to a routine profile for the user. If the risk score exceeds a predetermined threshold, an alert is sent to the smartphone which presents an alert screen to the user. The alert screen allows the user to cancel the alert (and notify the deep learning system) or confirm the alert (and immediately transmit an emergency message). Multiple emergency contacts can be designated, e.g., one for a low-level risk, another for an intermediate-level risk, and another for a high-level risk, and the emergency message can be sent to a selected contact depending upon the severity of the risk score.

Claims14

Dependent claims

A method of detecting personal danger comprising:

receiving a request from a user to monitor the user's safety using a mobile communications device of the user, by executing first instructions in a computer system;
receiving a routine profile specifically associated with the user wherein the routine profile is based on past environmental information previously provided by the user at different times according to a routine of the user, by executing second instructions in the computer system;
receiving current environmental information from the mobile communications device, by executing third instructions in the computer system;
using a deep learning system to generate a current numeric risk score by comparing the current environmental information to the routine profile, wherein a magnitude of the current numeric risk score indicates relative danger, wherein a lower risk score is indicative of relative safety and a higher risk score is indicative of relative danger, by executing fourth instructions in the computer system;
determining that the current numeric risk score exceeds a first predetermined risk threshold value, by executing fifth instructions in the computer system;
initiating transmission of an alert signal with the current numeric risk score to the mobile communications device in response to said determining;
receiving a cancel signal from the user via the mobile communications device in response to the alert signal, wherein the cancel signal prevents the transmission of the alert signal;
determining, in response to receiving the cancel signal from the mobile communications device, that the current numeric risk score exceeds a second predetermined risk threshold value specifying that cancel signals are disregarded for any numeric risk scores exceeding the second predetermined risk threshold value, wherein the second predetermined risk threshold value is greater than the first predetermined risk threshold value;
and
overriding, in response to determining that the current numeric risk score exceeds the second predetermined risk threshold value, the cancel signal by proceeding to transmit the alert signal with the current numeric risk score to a contact of the user.

7 more elements

A computer system comprising:

one or more processors which process program instructions;
a memory device connected to said one or more processors;
and
program instructions residing in said memory device for detecting personal danger by:
receiving a request from a user to monitor the user's safety using a mobile communications device of the user,
receiving a routine profile specifically associated with the user wherein the routine profile is based on past environmental information previously provided by the user at different times according to a routine of the user,
receiving current environmental information from the mobile communications device,
using a deep learning system to generate a current numeric risk score by comparing the current environmental information to the routine profile, wherein a magnitude of the current numeric risk score indicates relative danger, wherein a lower risk score is indicative of relative safety and a higher risk score is indicative of relative danger,
determining that the current numeric risk score exceeds a first predetermined risk threshold value,
initiation transmission of an alert signal with the current numeric risk score to the mobile communications device in response to said determining,
receiving a cancel signal from the user via the mobile communications device in response to the alert signal, wherein the cancel signal prevents the transmission of the alert signal,
determining, in response to receiving the cancel signal from the mobile communications device, that the current numeric risk score exceeds a second predetermined risk threshold value specifying that cancel signals are disregarded for any numeric risk scores exceeding the second predetermined risk threshold value, wherein the second predetermined risk threshold value is greater than the first predetermined risk threshold value;
and
overriding, in response to determining that the current numeric risk score exceeds the second predetermined risk threshold value, the cancel signal by proceeding to transmit the alert signal with the current numeric risk score to a contact of the user.

11 more elements

A computer program product comprising:

a computer readable storage medium;
and program instructions residing in said storage medium for detecting personal danger by:
receiving a request from a user to monitor the user's safety using a mobile communications device of the user,
receiving a routine profile specifically associated with the user wherein the routine profile is based on past environmental information previously provided by the user at different times according to a routine of the user,
receiving current environmental information from the mobile communications device,
using a deep learning system to generate a current numeric risk score by comparing the current environmental information to the routine profile, wherein a magnitude of the current numeric risk score indicates relative danger, wherein a lower risk score is indicative of relative safety and a higher risk score is indicative of relative danger,
determining that the current numeric risk score exceeds a first predetermined risk threshold value,
initiating transmission of an alert signal with the current numeric risk score to the mobile communications device in response to said determining,
receiving a cancel signal from the user via the mobile communications device in response to the alert signal, wherein the cancel signal prevents the transmission of the alert signal,
determining, in response to receiving the cancel signal from the mobile communications device, that the current numeric risk score exceeds a second predetermined risk threshold value specifying that cancel signals are disregarded for any numeric risk scores exceeding the second predetermined risk threshold value;
and
overriding, in response to determining that the current numeric risk score exceeds the second predetermined risk threshold value, the cancel signal by proceeding to transmit the alert signal with the current numeric risk score to a contact of the user.

9 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/816,771Filed 17 Nov 2017
Published: US 2019/0156191 A123 May 2019
Granted: 27 Sep 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification26 codes

G08B 31/00
Predictive alarm systems characterised by extrapolation or other computation using updated historic
G06N 3/006
Artificial life, i.e. computing arrangements simulating life: based on simulated virtual individual or collective life forms, e.g. social…
G06N 3/0499
Architecture, e.g. interconnection topology: feedforward networks
G06N 3/08
Neural networks: learning methods