Browse Prior Art Database

Applying pattern keys to people control, particularly during emergence situations

IP.com Disclosure Number: IPCOM000209084D
Publication Date: 2011-Jul-27
Document File: 2 page(s) / 37K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes how the known technology of pattern keys can be used to identify people moving in potentially dangerous ways in an emergency situation. In such a situation people will generally gather towards an exit point or a point of safety, however there is potential for panic resulting in people moving into potentially dangerous locations. The use of pattern keys would help to predict peoples end location before they reach it allowing for emergency personal to reach and help them at the earliest possible time.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 55% of the total text.

Page 01 of 2

Applying pattern keys to people control , particularly during emergence situations

What is a pattern key:

    Pattern keys are generated from large stores of data. The data is typically collected over a significant period of time and is structured as a large number of decision points with paths through these points. Common routes through the data are pulled out and refined to generate a sub list of decision points. The pattern key consists of the sub list of decision points and an end point.

    The pattern key is small in size so can easily be transferred between devices. They are used to predict endpoints (or destinations) at the earliest possible time by matching their list of decision points against decisions in live data. The major strength of pattern keys is their ability to perform live predictions with very little processing, allowing them to run on even the most weakly powered mobile device or embedded device. Standard systems are processor intensive, as they must traverse complex neural nets of data on the fly in order to constantly evaluate the situation and make predictions.

Using Pattern Keys to identify human movement

    This idea involves producing pattern keys from previous data on the movements of people around the airport in emergency situations, so that as people are tracked, early warning systems can spot people moving in the wrong ways as early as possible. This would allow someone to be sent to head them off before they get to their predicted destination. It could also identify people moving in suspicious patterns.

    The users of this invention would monitor and store the movement of people. This would include things such as, direction and speed. Each of these actions would be stored as a node in a larger neural net, with the users actions making a path between certain nodes. Once a large amount of data has been captured for that individual, the neural net of data would be processed (using known techniques) to produce pattern keys. These keys would contain a number of nodes and a destination node, where it can be accurately predicted that if the nodes are all visited by the user, it can be accurately predicted that the user will then visit the destination node.

    This prediction could then be used for a wide range of things - identifying people moving the wrong direction in an emergency situation, detecting suspicious movement to prevent crime, detecting people in distress, Away from emergency systems, an example could be its use for opening more supermarket tills before a high volume of customers result in long queues.

    A simple example of such a pattern key might be that during an emergency situation in an airport, the terminal requires evacuation. The monitors match peoples movement to known pattern keys, which relate to routes out of the building. If a person's movement does not match such a p...