Systems and methods to identify home addresses of mobile devices
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
H04W-068/00
G01S-005/02
H04W-004/02
G01S-005/00
H04W-008/02
출원번호
US-0594010
(2015-01-09)
등록번호
US-9291700
(2016-03-22)
발명자
/ 주소
Rose, Elena
Dixon, Mark Christopher
Ching, Kevin Toshio
Milenkiy, Veronica
출원인 / 주소
NinthDecimal, Inc.
대리인 / 주소
Greenberg Traurig LLP
인용정보
피인용 횟수 :
5인용 특허 :
9
초록▼
Systems and methods including a database storing the identifiers of cells representing residential parcels of real estate properties. Mobile devices determine the coordinates of their locations during a period of time using a location determination system, such as a global positioning system. The co
Systems and methods including a database storing the identifiers of cells representing residential parcels of real estate properties. Mobile devices determine the coordinates of their locations during a period of time using a location determination system, such as a global positioning system. The coordinates are converted to cell identifiers to look up corresponding residential parcels that have been visited by the mobile devices. A server generates a visitation data set for each residential parcel visited by each mobile device, including different types of frequencies of the mobile device visiting the residential parcel (e.g., night, weekend). A server filters the residential parcels based on visitation frequencies to identify home candidates and then further filters the home candidates based on the count of mobile devices having the home candidates. A home parcel, and thus its address, is identified from the filtered home candidate(s) for each mobile device.
대표청구항▼
1. A method implemented in a computing device, the method comprising: receiving, in the computing device, data identifying a set of location instances in a period of time, each respective location instance of the location instances identifying: a mobile device,a location of the mobile device, anda t
1. A method implemented in a computing device, the method comprising: receiving, in the computing device, data identifying a set of location instances in a period of time, each respective location instance of the location instances identifying: a mobile device,a location of the mobile device, anda timestamp of the location of the mobile device in the period of time identifying, by the computing device, a set of regions in which the location instances are located;computing, by the computing device, a visitation dataset for each respective region visited by each respective mobile device, wherein the visitation dataset identifies a plurality of frequencies of visitations of different types;filtering, by the computing device, regions visited by the respective mobile device to identify one or more region candidates as a home of the respective mobile device; andin response to a determination that the respective mobile device has more than one region candidate resulting from the filtering, selecting by the computing device the home of the respective mobile device from the more than one region candidate, based at least in part on a score computed from the visitation dataset, wherein the score is based on a ratio between: a function of a count of different days of location instances of the respective mobile device that are located within the respective region but have timestamps outside working hours; anda function of a count of different days of location instances of the respective mobile device that are located within the respective region and have timestamps in weekends. 2. The method of claim 1, wherein the score is based on a count of different days of location instances of the respective mobile device that are located within the respective region but have timestamps outside working hours. 3. The method of claim 1, wherein the score is based on a count of different days of location instances of the respective mobile device that are located within the respective region and have timestamps in weekends. 4. The method of claim 1, wherein the score is based on a weight determined based on recency of location instances of the respective mobile device in the respective region. 5. The method of claim 1, wherein the score is based on a weight determined based on a total number of different regions that have location instances of the respective mobile device. 6. The method of claim 1, wherein the score is based on a weight determined based on whether the respective region has been previously identified as the home of the mobile device. 7. The method of claim 1, wherein the set of regions are limited to and defined by parcel boundaries of land in residential areas; and the method further comprises: breaking a tie in the score based on visitations to an area of a predetermined width surrounding a boundary of each respective residential region but not within boundaries of residential regions. 8. The method of claim 7, further comprising: storing a set of cell identifiers of a hierarchical grid system having grid lines aligned with numbers of digits of precision in longitudinal and latitudinal coordinates on the earth, including store each respective cell identifier of the set of cell identifiers in association with a set of region identifiers identifying one or more regions that are at least partially in a cell identified by the respective cell identifier;wherein the identifying of the set of regions in which the location instances are located includes, for the respective location instance in the set of location instances in the period of time: converting to a cell identifier the location of the mobile device identified in the respective location instance;searching in the set of cell identifiers for a match of the cell identifier converted from the location of the mobile device identified in the respective location instance;retrieving a set of region identifiers associated with the match identified via the searching; andidentifying the respective location instance as being within one or more regions identified by the set of region identifiers retrieved via the searching. 9. The method of claim 1, wherein the visitation dataset includes: a count of different days of location instances of the respective mobile device located within the respective region;a count of different days of location instances of the respective mobile device that are located within the respective region and have timestamps in night hours; anda count of different days of location instances of the respective mobile device that are located within the respective region and have timestamps in weekends. 10. The method of claim 9, wherein the night hours are between 7 pm to 8 am of a day; and the weekends are Saturdays and Sundays. 11. The method of claim 9, wherein the filtering is based on a threshold computed based at least in part on: a count of location instances of different mobile devices located in the respective region; anda count of different mobile devices of location instances located in the respective region. 12. The method of claim 11, wherein in response to a determination that the filtering produces no region candidate for the respective mobile device, relaxing a criterion of the filtering. 13. The method of claim 11, wherein the threshold is computed based further on an average count of different mobile devices of location instances located in the respective region and neighboring regions of the respective region. 14. The method of claim 11, wherein the respective region is not selected as a region candidate when the threshold is higher than both the count of different days of location instances of the respective mobile device that are located within the respective region but have timestamps in night hours; andthe count of different days of location instances of the respective mobile device that are located within the respective region but have timestamps in weekends. 15. A method implemented in a computing device, the method comprising: receiving, in the computing device, data identifying a set of location instances in a period of time, each respective location instance of the location instances identifying: a mobile device,a location of the mobile device, anda timestamp of the location of the mobile device in the period of time identifying, by the computing device, a set of regions in which the location instances are located;computing, by the computing device, a visitation dataset for each respective region visited by each respective mobile device, wherein the visitation dataset identifies a plurality of frequencies of visitations of different types;filtering, by the computing device, regions visited by the respective mobile device to identify one or more region candidates as a home of the respective mobile device; andin response to a determination that the respective mobile device has more than one region candidate resulting from the filtering, selecting by the computing device the home of the respective mobile device from the more than one region candidate, based at least in part on a score computed from the visitation dataset, wherein the selecting of the home of the respective mobile device includes: identifying a first subset of the one or more region candidates, wherein each region candidate in the first subset having a count of different mobile devices less than a first threshold; andselecting the home of the respective mobile device from the first subset based on the score. 16. The method of claim 15, further comprising: determining, by the computing device, a count of different mobile devices having location instances in each of the regions;wherein the selecting of the home of the respective mobile device is further based on the count of different mobile devices having location instances in each of the regions. 17. The method of claim 15, wherein the selecting of the home of the respective mobile device further includes, in response to a determination that the first subset is empty: identifying a second subset of the one or more region candidates, wherein each region candidate in the second subset having a count of different mobile devices less than a second threshold greater than the first threshold; andselecting the home of the respective mobile device from the second subset based on the score. 18. A non-transitory computer storage medium storing instructions configured to instruct a computing device to perform a method, the method comprising: receiving, in the computing device, data identifying a set of location instances in a period of time, each respective location instance of the location instances identifying: a mobile device,a location of the mobile device, anda timestamp of the location of the mobile device in the period of time;identifying, by the computing device, a set of regions in which the location instances are located;computing, by the computing device, a visitation dataset for each respective region visited by each respective mobile device, wherein the visitation dataset identifies a plurality of frequencies of visitations of different types;filtering, by the computing device, regions visited by the respective mobile device to identify one or more region candidates as a home of the respective mobile device; andin response to a determination that the respective mobile device has more than one region candidate resulting from the filtering, selecting by the computing device the home of the respective mobile device from the more than one region candidate, based at least in part on a score computed from the visitation dataset;wherein the filtering is based on a threshold computed based at least in part on: a count of location instances of different mobile devices located in the respective region; anda count of different mobile devices of location instances located in the respective region. 19. A computing device, comprising: at least one microprocessor; andmemory storing instructions configured to instruct the at least one microprocessor to: receive, in the computing device, data identifying a set of location instances in a period of time, each respective location instance of the location instances identifying a mobile device, a location of the mobile device, and a timestamp of the location of the mobile device in the period of time;identify, by the computing device, a set of regions in which the location instances are located, wherein the set of regions are limited to and defined by parcel boundaries of land in residential areas;compute, by the computing device, a visitation dataset for each respective region visited by each respective mobile device, wherein the visitation dataset identifies a plurality of frequencies of visitations of different types;filter, by the computing device, regions visited by the respective mobile device to identify one or more region candidates as a home of the respective mobile device;in response to a determination that the respective mobile device has more than one region candidate resulting from the filtering, select by the computing device the home of the respective mobile device from the more than one region candidate, based at least in part on a score computed from the visitation dataset; andbreak a tie in the score based on visitations to an area of a predetermined width surrounding a boundary of each respective residential region but not within boundaries of residential regions.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (9)
Milton, Stephen; McCall, Duncan, Apparatus and method for profiling users.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.