# US 2021/0280065 A1 · Contextual event awareness via risk analysis and notification delivery system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0280065 A1
- Document ID: US20210280065A1
- Status: Published application
- Kind: A1
- Application number: 16/808,635
- Filed: 2020-03-04
- Published: 2021-09-09
- Earliest claimed: 2020-03-04
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Shikhar Kwatra; Jeremy R. Fox; Zachary James Goodman; H. Ramsey Bissex; Ernest Bernard Williams, JR.
- Web page: https://patentgrep.com/patent/US20210280065A1

## CPC

- G08G 1/005: including pedestrian guidance indicator
- G08G 1/166: {for active traffic, e.g. moving vehicles, pedestrians, bikes}
- G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N 3/096: Transfer learning
- G06N 20/00: Machine learning
- G08G 1/162: {event-triggered}
- G06N 3/08: Learning methods
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In an approach for contextual event awareness, a processor receives contextual information including motion and sound detection. A processor analyzes the contextual information to determine a proximity sequencing including context of an event. A processor applies machine learning to the proximity sequencing to form a risk assessment based on the context of the event impacting a user. A processor determines that the risk assessment exceeds a predetermined threshold. A processor provides a notification of a risk to the user.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, by one or more processors, contextual information including motion and sound detection;
analyzing, by one or more processors, the contextual information to determine a proximity sequencing including context of an event;
applying, by one or more processors, machine learning to the proximity sequencing to form a risk assessment based on the context of the event impacting a user;
determining, by one or more processors, that the risk assessment exceeds a predetermined threshold; and
providing, by one or more processors, a notification of a risk to the user.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the risk assessment is based on a neural network with a classifier determining a significance of the event and deploying an ameliorative notification strategy.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the neural network is a deep neural network, the deep neural network including a convolutional neural network and a recurrent neural network.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein the event is categorized, based on the machine learning, as interesting based on a user profile and a learned pattern history.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, further comprising:
utilizing feedback received from the user to determine the significance of the event.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
transferring information about the risk to a second user in a vicinity of the user via an ad-hoc network.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein providing the notification includes delivering the notification selected from a group consisting of: an augmented reality displayed message, a haptic vibration, and audio.

### Claim 8

A computer program product comprising:
one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to receive contextual information including motion and sound detection;
program instructions to analyze the contextual information to determine a proximity sequencing including context of an event;
program instructions to apply machine learning to the proximity sequencing to form a risk assessment based on the context of the event impacting a user;
program instructions to determine that the risk assessment exceeds a predetermined threshold; and
program instructions to provide a notification of a risk to the user.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the risk assessment is based on a neural network with a classifier determining a significance of the event and deploying an ameliorative notification strategy.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the neural network is a deep neural network, the deep neural network including a convolutional neural network and a recurrent neural network.

### Claim 11 (depends on 9)

The computer program product of claim 9, wherein the event is categorized based on the machine learning as interesting based on a user profile and a learned pattern history.

### Claim 12 (depends on 9)

The computer program product of claim 9, further comprising:
program instructions, stored on the one or more computer-readable storage media, to utilize feedback received from the user to determine the significance of the event.

### Claim 13 (depends on 8)

The computer program product of claim 8, further comprising:
program instructions, stored on the one or more computer-readable storage media, to transfer information about the risk to a second user in a vicinity of the user via an ad-hoc network.

### Claim 14 (depends on 8)

The computer program product of claim 8, wherein program instructions to provide the notification include program instructions to deliver the notification selected from a group consisting of: an augmented reality displayed message, a haptic vibration, and audio.

### Claim 15

A computer system comprising:
one or more computer processors, one or more computer readable storage media, and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to receive contextual information including motion and sound detection;
program instructions to analyze the contextual information to determine a proximity sequencing including context of an event;
program instructions to apply machine learning to the proximity sequencing to form a risk assessment based on the context of the event impacting a user;
program instructions to determine that the risk assessment exceeds a predetermined threshold; and
program instructions to provide a notification of a risk to the user.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein the risk assessment is based on a neural network with a classifier determining a significance of the event and deploying an ameliorative notification strategy.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein the neural network is a deep neural network, the deep neural network including a convolutional neural network and a recurrent neural network.

### Claim 18 (depends on 16)

The computer system of claim 16, wherein the event is categorized based on the machine learning as interesting based on a user profile and a learned pattern history.

### Claim 19 (depends on 16)

The computer system of claim 16, further comprising:
program instructions, stored on the one or more computer-readable storage media, to utilize feedback received from the user to determine the significance of the event.

### Claim 20 (depends on 15)

The computer system of claim 15, further comprising:
program instructions, stored on the one or more computer-readable storage media, to transfer information about the risk to a second user in a vicinity of the user via an ad-hoc network.
