# US 2022/0067603 A1 · Risk assessment apparatus and related methods

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

- Number: US 2022/0067603 A1
- Document ID: US20220067603A1
- Status: Published application
- Kind: A1
- Application number: 17/459,828
- Filed: 2021-08-27
- Published: 2022-03-03
- Earliest claimed: 2020-08-31
- Assignees: altumAI Inc.
- Applicants: altumAI Inc.
- Inventors: Lars Evensen Skari; Simon Prowse; Douglas Turk
- Web page: https://patentgrep.com/patent/US20220067603A1

## CPC

- G06Q 10/0635: Risk analysis of enterprise or organisation activities
- G06F 1/163: {Wearable computers, e.g. on a belt}
- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06Q 10/06395: {Quality analysis or management}
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

In one aspect, a device agnostic system for providing a fully connected worker risk assessment is disclosed. The system includes an interface and data model for capturing and interpreting one or more variables associated with a worker's body motion and non-body motion related data. The system further includes a processor for aggregating, assessing, and interpreting the one or more input variables to perform a fully connected worker risk assessment based on not only the worker's movement, but also non-movement related data. The processor further provides an output based on the processed one or more input variables to provide a fully connected risk assessment and solutions relating to the same.

## Claims

### Claim 1

A device agnostic system for providing a fully connected worker risk assessment comprising:
an interface and a data model for capturing and interpreting one or more input variables associated with a worker's body motion and other non-body motion related data; and
a processor for:
aggregating, assessing, and interpreting the one or more input variables to perform a fully connected worker risk assessment based not only on the worker's movement, but also non-movement related data; and
providing output based on the processed one or more input variables to provide a fully connected risk assessment and solutions relating to same.

### Claim 2 (depends on 1)

The system of claim 1 wherein the input for inputting one or more input variables associated with other non-body motion related data comprises one or more of the following inputs: worker specific input, employer specific input, environment input, temporal input, yield or throughput input, and/or commodity input.

### Claim 3 (depends on 2)

The system of claim 2 wherein the input for inputting one or more input variables associated with other non-body motion related data includes worker specific input which includes at least one of the following worker metrics: age, years of experience in role, biometrics, gender, location, role, industry, pre-existing conditions, symptoms.

### Claim 4 (depends on 2)

The system of claim 2 wherein the input for inputting one or more input variables associated with other non-body motion related data includes employer specific input which includes at least one of the following employer metrics: Assessment of slip/trip/fall hazards, heat illness prevention preparedness or the maturity of the employer's safety plan and processes.

### Claim 5 (depends on 2)

The system of claim 2 wherein the input for inputting one or more input variables associated with other non-body motion related data includes environment input which includes at least one of the following: temperature, humidity, heat index, air quality, including particle matter (non-biological), biological matter and chemical pollutants, UV exposure, and/or sound exposure.

### Claim 6 (depends on 2)

The system of claim 2 wherein the input for inputting one or more input variables associated with body motion related data includes at least one of the following: bending (forward, backward, sideways) and twisting behavior (count, duration), walking (steps, duration), running (steps, duration), stillness, smoothness, repetitive motion, slips, trips, falls, squatting, jumping, heavy lifting and/or physical exertion.

### Claim 7 (depends on 6)

The system of claim 6 wherein processing the one or more input variables to perform a fully connected risk assessment comprises using pattern recognition to determine the body motion related data.

### Claim 8 (depends on 7)

The system of claim 7 wherein the processor utilizes machine learning to continually evolve the system over time.

### Claim 9 (depends on 7)

The system of claim 7 wherein the processor utilizes a Gausian or Hidden Markov model for modeling the one or more input variables to perform the pattern recognition to determine the body motion related data.

### Claim 10 (depends on 1)

The system of claim 1 wherein providing output based on the processed one or more input variables comprises providing a collaboration with a system user to provide a fully connected risk assessment and solutions relating to same.

### Claim 11 (depends on 10)

The system of claim 10 wherein the collaboration includes a review of individual worker's risk assessment and a team of multiple workers risk assessments to provide a fully connected risk assessment and solutions relating to same.

### Claim 12

A non-transitory computer readable medium including instructions which, when executed, cause performance of a method by a processor for determining an activity safety metric, the non-transitory computer readable medium comprising:
first instructions for receiving input data of a plurality of activity condition variables, the input data including motion data received from a data collection device;
second instructions for identifying one or more motion segments within the motion data;
third instructions for associating the one or more motion segments with one or more motion types stored in memory, the association based at least in part on a comparison with motion type data stored in memory, the motion type data determined to correspond to one or more motion types; and
fourth instructions for determining a metric indicative of the safety of an activity associated with the input data based at least in part on the input data and the motion types associated with the one or more motion segments.

### Claim 13 (depends on 12)

The non-transitory computer readable medium of claim 12, wherein the motion type data is based at least in part on previously recorded input data.

### Claim 14 (depends on 12)

The non-transitory computer readable medium of claim 12, wherein the metric indicative of a safety of the activity is a metric indicative of the risk of injury.

### Claim 15 (depends on 12)

The non-transitory computer readable medium of claim 12, further comprising: fifth instructions for generating one or more models representative of normal activity conditions based at least in part on the input data received over time.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, further comprising: sixth instructions for comparing the input data with the one or more models representative of normal activity conditions to identify an abnormal activity condition.

### Claim 17 (depends on 12)

The non-transitory computer readable medium of claim 12, wherein the motion data is derived from an output of one or more motion sensors of the data collection device.

### Claim 18 (depends on 12)

The non-transitory computer readable medium of claim 12 further comprising: fifth instructions for communicating information pertaining to the metric to a user device.

### Claim 19 (depends on 12)

The non-transitory computer readable medium of claim 12, wherein the information pertaining to the metric includes one or more of a risk score, a factor causing a change to the metric, information pertaining to how to improve the metric, and an award based on the metric.
