Browse Prior Art Database

Method and System for Enabling Social tipoff for Relating Crimes into a Case Using Crowd Source Technology

IP.com Disclosure Number: IPCOM000243613D
Publication Date: 2015-Oct-05
Document File: 1 page(s) / 76K

Publishing Venue

The IP.com Prior Art Database

Abstract

Method and System is disclosed for enabling social tipoff for relating crimes into a case using crowd source technology.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 76% of the total text.

Page 01 of 1

Method and System for Enabling Social tipoff for Relating Crimes into a Case Using Crowd Source Technology

Disclosed is method and system for enabling users to suggest a case containing several related crimes.

Crowd sourcing allows third parties to contribute to achieving an objective. By allowing users to propose relationships between crimes, the suggestions can be analyzed to speed up the process of finding related crimes in order to build a case. One of the issues is that different suggestions might not agree 100%, which makes it difficult to

relate cases that contain different sets of crimes. When several cases contain the same crimes, the agreement between several suggested cases could aid an investigator find relationships more quickly.

The system divides the problem into two distinct stages: a case proposal stage and a proposal analysis stage. Once multiple cases have been proposed, the system reduces the number of proposed cases to identify best proposals.

Once several cases have been suggested, a dissimilarity matrix is computed across the dataset such as Crimes, Person of Interest and Suggested Cases (Proposed).

The dissimilarity matrix is used to project the data onto a 2 dimensional plane using Multidimensional scaling (MDS) while preserving the distances as best as possible. Once the suggested cases are plotted, standard clustering algorithms can be applied.

In a situation where several cases have been proposed with equal agreeability, the most prob...