US 11,790,257 B2
Incident prediction system
Remco Theodorus Johannes Muijs, Meteren (NL)
Assigned to SIGNIFY HOLDING B.V., Eindhoven (NL)
Appl. No. 16/62,838
Filed by SIGNIFY HOLDING B.V., Eindhoven (NL)
PCT Filed Dec. 12, 2016, PCT No. PCT/EP2016/080589
§ 371(c)(1), (2) Date Jun. 15, 2018,
PCT Pub. No. WO2017/102629, PCT Pub. Date Jun. 22, 2017.
Claims priority of application No. 15200091 (EP), filed on Dec. 15, 2015.
Prior Publication US 2019/0026643 A1, Jan. 24, 2019
Int. Cl. G06F 3/048 (2013.01); G06N 7/01 (2023.01); G08B 31/00 (2006.01); G08B 21/22 (2006.01); G06Q 50/26 (2012.01); G06N 5/04 (2023.01)
CPC G06N 7/01 (2023.01) [G08B 21/22 (2013.01); G08B 31/00 (2013.01); G06N 5/04 (2013.01); G06Q 50/265 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A non-military incident prediction system, the system comprising:
a crowd detection interface for receiving a plurality of mobile device identifiers of a plurality of electronic mobile devices from a crowd detection unit, wherein the plurality of electronic mobile devices correspond to a plurality of non-military persons in a pre-determined geographic region during a time threshold;
an incident database wherein a plurality of weight factors is associated with a plurality of previously received and stored mobile device identifiers, wherein the weight factors are computed based on a proximity of associated electronic mobile devices of the previously received and stored mobile device identifiers to a position of at least one historic incident that occurred in the past;
a prediction subsystem configured for:
i) comparing the presently received mobile device identifiers and the previously received and stored mobile device identifiers to identify one or more matches between at least one of the presently received mobile device identifiers and the previously received and stored mobile device identifiers to obtain one or more weight factors associated with the presently received mobile device identifiers, wherein the one or more weight factors are obtained from an initial weight factor and a time decay factor, the one or more weight factors are periodically reduced towards a default weight factor that is different from the initial weight factor by applying the time decay factor to the one or more weight factors, the time decay factor is below the default weight factor, and each of the one or more weight factors is raised when a plurality of the received mobile device identifiers are detected in the pre-determined geographic region vicinity of an active incident,
ii) totaling the one or more weight factors so as to obtain a total weight factor,
iii) generating prediction data of an occurrence of the incident based on the total weight factor,
wherein the prediction subsystem is further configured for modifying the total weight factor based on at least one situational weight factor, the at least one situational weight factor being further calculated based on one from the list of: weather conditions, day or night time, weekdays, period of a city event and type of a city event.