IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0529682
(2014-10-31)
|
등록번호 |
US-9547666
(2017-01-17)
|
발명자
/ 주소 |
- Ching, Kevin
- Sokol, Grigory
- Azizi, Ahmad Fairiz
- Gain, Luke
- Zhyshko, Yury
- Dixon, Mark
- Abusaidi, Robert
- McKenzie, Kevin
- Klein, John Raymond
- Blyukher, Leonid
- Pittelkau, Jeff
- Staas, David
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
0 인용 특허 :
8 |
초록
▼
Location graph-based derivation of user attributes is disclosed. In various embodiments, location data associated with a user, such as a current and/or past location at which the user has been, is received. A user attribute data associated with the location data is determined and used to update a us
Location graph-based derivation of user attributes is disclosed. In various embodiments, location data associated with a user, such as a current and/or past location at which the user has been, is received. A user attribute data associated with the location data is determined and used to update a user profile associated with the user.
대표청구항
▼
1. A method, comprising: storing, in a computing apparatus, a first set of location data, the first set of location data identifying: a plurality of predetermined first locations, anda set of attributes of past users who have visited the plurality of predetermined first locations and thus associated
1. A method, comprising: storing, in a computing apparatus, a first set of location data, the first set of location data identifying: a plurality of predetermined first locations, anda set of attributes of past users who have visited the plurality of predetermined first locations and thus associated with the plurality of predetermined first locations in the computing apparatus;receiving, in the computing apparatus, user location data, the user location data identifying a plurality of second locations at which a mobile device of a user is observed;mapping, by the computing apparatus, the plurality of second locations of the mobile device to corresponding locations in the plurality of predetermined first locations, wherein each of the plurality of second locations of the mobile device is mapped to a corresponding location in the plurality of predetermined first locations in the first set of location data;identifying, by the computing apparatus based on the mapping and the first set of location data stored in the computing apparatus, first attributes of past users who have visited the corresponding locations in the plurality of predetermined first locations, where the first attributes are, in the first set of location data, associated with the corresponding locations to which the plurality of second locations of the mobile device are mapped;updating, by the computing apparatus, a profile of the user by adjusting the profile of the user, using a weighted algorithm, based on the first attributes that are identified, via the mapping, from the first set of location data, wherein in response to further user location data of the mobile device being mapped into further predetermined locations in the plurality of predetermined first locations that are identified in the first set of location data, the updating of the profile is repeated for the further predetermined locations, based on the weighted algorithm and further attributes associated in the first set of location data with the further predetermined locations, to incrementally improve accuracy of the profile; anddetermining, by the computing apparatus, confidence levels of attributes in the user profile including the first attributes identified via the mapping. 2. The method of claim 1, wherein a first attribute is associated with a pattern of being at a subset of the plurality of predetermined first locations; and the method further comprises: determining whether the plurality of second locations of the mobile device as being mapped to the corresponding locations in the plurality of predetermined first locations include the pattern;wherein the updating includes: in response to a determination that the plurality of second locations of the mobile device as being mapped to the corresponding locations in the plurality of predetermined first locations include the pattern, updating the user profile to include the first attribute. 3. The method of claim 2, wherein the pattern is based at least in part on times of visiting locations in the subset of the plurality of predetermined first locations. 4. The method of claim 1, wherein each location of the plurality of predetermined first locations corresponds to a predefined geographic area. 5. The method of claim 1, wherein the updating includes updating a confidence level of a first attribute in the profile of the user based on a detection of a location in the plurality of second locations of the mobile device being within a location in the plurality of predetermined first locations that is related to the first attribute. 6. The method of claim 1, further comprising: receiving a request from a second user having a profile, the request identifying a current location of the second user; andupdating the first set of location data based on the profile of the second user. 7. The method of claim 6, further comprising: determining a corresponding location in the plurality of predetermined first locations in the first set of location data;wherein the updating the first set of location data includes updating attributes associated with the corresponding location in the plurality of predetermined first locations based on the profile of the second user. 8. A non-transitory computer storage medium storing instructions configured to instruct a computing apparatus to perform a method, the method comprising: storing, in the computing apparatus, a first set of location data, the first set of location data identifying: a plurality of predetermined first locations, anda set of attributes of past users who have visited the plurality of predetermined first locations and thus associated with the plurality of predetermined first locations in the computing apparatus;receiving, in the computing apparatus, user location data, the user location data identifying a plurality of second locations at which a mobile device of a user is observed;mapping, by the computing apparatus, the plurality of second locations of the mobile device to corresponding locations in the plurality of predetermined first locations, wherein each of the plurality of second locations of the mobile device is mapped to a corresponding location in the plurality of predetermined first locations in the first set of location data;identifying, by the computing apparatus based on the mapping and the first set of location data stored in the computing apparatus, first attributes of past users who have visited the corresponding locations in the plurality of predetermined first locations, where the first attributes are, in the first set of location data, associated with the corresponding locations to which the plurality of second locations of the mobile device are mapped;updating, by the computing apparatus, a profile of the user by adjusting the profile of the user, using a weighted algorithm, based on the first attributes that are identified, via the mapping, from the first set of location data wherein in response to further user location data of the mobile device being mapped into further predetermined locations in the plurality of predetermined first locations that are identified in the first set of location data, the updating of the profile is repeated for the further predetermined locations, based on the weighted algorithm and further attributes associated in the first set of location data with the further predetermined locations, to incrementally improve accuracy of the profile; anddetermining, by the computing apparatus, confidence levels of attributes in the user profile including the first attributes identified via the mapping. 9. The medium of claim 8, wherein a first attribute is associated with a pattern of being at a subset of the plurality of predetermined first locations; and the method further comprises: determining whether the plurality of second locations of the mobile device as being mapped to the corresponding locations in the plurality of predetermined first locations include the pattern;wherein the updating includes: in response to a determination that the plurality of second locations of the mobile device as being mapped to the corresponding locations in the plurality of predetermined first locations include the pattern, updating the user profile to include the first attribute. 10. The medium of claim 9, wherein the pattern is based at least in part on times of visiting locations in the subset of the plurality of predetermined first locations. 11. The medium of claim 8, wherein each location of the plurality of predetermined first locations corresponds to a predefined geographic area. 12. The medium of claim 8, wherein the updating includes updating a confidence level of a first attribute in the profile of the user based on a detection of a location in the plurality of second locations of the mobile device being within a location in the plurality of predetermined first locations that is related to the first attribute. 13. The medium of claim 8, wherein the method further comprises: receiving a request from a second user having a profile, the request identifying a current location of the second user; andupdating the first set of location data based on the profile of the second user. 14. The medium of claim 13, wherein the method further comprises: determining a corresponding location in the plurality of predetermined first locations in the first set of location data;wherein the updating the first set of location data includes updating attributes associated with the corresponding location in the plurality of predetermined first locations based on the profile of the second user. 15. A computing apparatus, comprising: at least one processor;a memory storing instructions configured to instruct the at least one processor to: store, in the computing apparatus, a first set of location data, the first set of location data identifying: a plurality of predetermined first locations, anda set of attributes of past users who have visited the plurality of predetermined first locations and thus associated with the plurality of predetermined first locations in the computing apparatus;receive, in the computing apparatus, user location data, the user location data identifying a plurality of second locations at which a mobile device of a user is observed;map, by the computing apparatus, the plurality of second locations of the mobile device to corresponding locations in the plurality of predetermined first locations, wherein each of the plurality of second locations of the mobile device is mapped to a corresponding location in the plurality of predetermined first locations in the first set of location data;identify, by the computing apparatus based on the mapping and the first set of location data stored in the computing apparatus, first attributes of past users who have visited the corresponding locations in the plurality of predetermined first locations, where the first attributes are, in the first set of location data, associated with the corresponding locations to which the plurality of second locations of the mobile device are mapped;update, by the computing apparatus, a profile of the user by adjusting the profile of the user, using a weighted algorithm, based on the first attributes that are identified, via the mapping, from the first set of location data, wherein in response to further user location data of the mobile device being mapped into further predetermined locations in the plurality of predetermined first locations that are identified in the first set of location data, updating of the profile is repeated for the further predetermined locations, based on the weighted algorithm and further attributes associated in the first set of location data with the further predetermined locations, to incrementally improve accuracy of the profile; anddetermine, by the computing apparatus, confidence levels of attributes in the user profile including the first attributes identified via the mapping. 16. The computing apparatus of claim 15, wherein: a first attribute is associated with a pattern of being at a subset of the plurality of predetermined first locations;the instructions are further configured to instruct the at least one processor to determine whether the plurality of second locations of the mobile device as being mapped to the corresponding locations in the plurality of predetermined first locations include the pattern; andthe profile of the user is updated to include the first attribute in response to a determination that the plurality of second locations of the mobile device as being mapped to the corresponding locations in the plurality of predetermined first locations include the pattern. 17. The computing apparatus of claim 16, wherein the pattern is based at least in part on times of visiting locations in the subset of the plurality of predetermined first locations. 18. The computing apparatus of claim 15, wherein the profile of the user is updated via updating a confidence level of a first attribute in the profile of the user based on a detection of a location in the plurality of second locations of the mobile device being within a location in the plurality of predetermined first locations that is related to the first attribute. 19. The computing apparatus of claim 15, wherein the instructions are further configured to instruct the at least one processor: receive a request from a second user having a profile, the request identifying a current location of the second user; andupdate the first set of location data based on the profile of the second user. 20. The computing apparatus of claim 19, wherein the instructions are further configured to instruct the at least one processor: determine a corresponding location in the plurality of predetermined first locations in the first set of location data; andupdate attributes associated with the corresponding location in the plurality of predetermined first locations based on the profile of the second user to update the first set of location data.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.