SYSTEM FOR CHARACTERIZING GEOGRAPHICAL LOCATIONS BASED ON MULTI SENSORS ANONYMOUS DATA SOURCES

• US 20150018020A1
• Filed: 07/11/2014
• Published: 01/15/2015
• Est. Priority Date: 07/15/2013
• Status: Active Grant

• Current Assignee: Deutsche Telekom AG
• Original Assignee: Deutsche Telekom AG
• Inventors: ELOVICI, Yuval, MIMRAN, Dudu, CHIZI, Bark, BINUN, Alexander, BIXENSPANER, Moshe, ACKERMAN, Pavel
• Granted Patent: US 9,609,483 B2
• Time in Patent Office: Days
• US Class Current: 455/457
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/08 User group management

Abstract

System and method for characterizing a geographical location by finding the behavioral patterns of groups of users of mobile devices being in the vicinity of the geographical location. Accordingly, after an examined Point of Interest is determined, signaling data related to the users is aggregated over a limited period of time, from the cellular network they use. The location, including change in the location of the users, is continuously calculated and cross-checked with anonymous multi-sensors with data records from external data sources. Then the mobility patterns of users are derived and the users are classified to groups according to the cross-checking results. Finally, the geographical location is characterized according to the mobility patterns and the classification.

Claims

1. A method for characterizing a geographical location by finding the behavioral patterns of groups of users of mobile devices being in the vicinity of said geographical location, comprising:

a) determining an examined Point of Interest (POI);

b) aggregating, over a limited period of time, signaling data related to said users, from the cellular network(s) they use;

c) continuously calculating the location including changes in the location of said users;

d) cross-checking the location data with anonymous multi-sensors having data records from external data sources;

e) deriving the mobility patterns of users and classifying said users to groups according to the cross-checking results; and

f) characterizing said geographical location according to said mobility patterns and the classification.

2. A method according to claim 1, wherein the aggregated information is related to a group of users having common characteristics.

3. A method according to claim 1, wherein user'"'"'s identity details, collected from the aggregated signaling data are erased after the limited period of time lapses.

4. A method according to claim 1, wherein the Multi Sensors Data Sources comprise one or more of the following:

Call Data Records (CDRs);

Infrastructure data including geographical properties;

Location Data Records (LDRs);

CRM data;

Static Geographical Data Sets;

Dynamical datasets that has geographical nature.

5. A method according to claim 1, wherein the mobility patterns of users are summed during aggregation by using statistical models, while periodically re-summing said mobility patterns.

6. A method according to claim 5, wherein the statistical models include:

Voronoi spaces;

server estimation method.

7. A method according to claim 1, wherein the aggregation includes:

aggregations of movements;

aggregations of analyzed properties.

8. A method according to claim 1, wherein the point of interest

a street;

a particular address;

a shop.

9. A system for characterizing a geographical locations by finding the behavioral patterns of groups of users of mobile devices being in the vicinity of said geographical location, comprising:

a) a plurality of anonymous multi-sensors having data records from external data sources;

b) a database for aggregating, over a limited period of time, signaling data related to said users, from the cellular network they use;

c) processing means for calculating the location including change in the location of said users;

d) a privacy watcher module for replacing all original identities of users by syntactic identities, while changing the identities every predetermined time;

e) a signaling location provider for translating the signaling records of the cellular provider into geographical location coordinates;

f) an aggregation and fusion engine for connecting the different data types which were aggregated, into a unified data set;

g) an actionable insight provider for receiving and processing said unified data set and for providing insights regarding.

10. A system according to claim 9, wherein the actionable insight provider includes;

a) a periodical reports module for issuing periodical reports that provide an answer to predefined business questions;

b) a Report Generator module, for allowing enable the user to create individual reports and to formulates individual business questions;

c) an Algorithm Engine module for supporting insight for predicting, verifying and discovering behavioral patterns;

d) an Alerts Mechanism module, for allowing the user to define an event and to attached an alert to it; and

e) a Visual Exploration Interface module, for discovery and exploration by allowing the user to browse all outputs from the insight provider in order to gain more knowledge.