Points of interest in a location sharing system
Systems, and methods for predicting that a user is located at a labeled place corresponding to a point of interest. A server computer accesses historical data comprising location data, and wireless network data collected from a plurality of client devices of a plurality of users over a period of time. For one or more labeled places, the data points corresponding to one of the users being located at the labeled place are identified. A labeled dataset is generated by tagging the identified data points with a label corresponding to the corresponding labeled place. A machine learning model is trained on the labeled dataset, so that when current location data are receiving from a client device of a user, it is possible to determine, using the trained machine learning model, whether the user is located at one of the one or more labeled places.
1. A method comprising:
accessing, at a server computer using one or more processors of the server computer, historical data collected from at least one client device of at least one user over a period of time, the historical data comprising a plurality of data points, each data point comprising location data, and wireless network data;
identifying, by the one or more processors, based on the location data and the wireless network data, first data points of the plurality of data points corresponding to the at least one user being located at a labeled place;
generating, using the one or more processors, a labeled dataset by tagging the first data points with a label corresponding to the labeled place;
training, using the one or more processors of the server computer, a machine learning model on the labeled dataset;
receiving, at the server computer, from a first client device associated with a first user, an electronic communication containing current location data;
determining, by the one or more processors using the trained machine learning model, that the first user is located at the labeled place; and
based on determining that the first user is located at the labeled place; initiating transmission of data to a second client device by attaching the data to a message accessible for a predetermined duration of time, the data indicating the labeled place at which the first user is located for display on a display screen of the second client device.
2. The method of claim 1 , wherein the wireless network data comprises wireless local area network (WLAN) information of one or more WLAN networks available to the at least one client device.
3. The method of claim 2 , wherein identifying the first data points comprises:
parsing the WLAN information to identify a name of the one or more WLAN networks; and
determining that the at least one user was located at the labeled place; at least partially, based on the name of one of the WLAN networks matching a name of the labeled place.
4. The method of claim 1 , wherein the wireless network data comprises MILAN information of a WLAN the at least one client device is connected to.
5. The method of claim 1 , wherein determining that the first user is located at the labeled place further comprises:
computing, using the trained machine learning model, a probability of the first user being located at the labeled place; and
determining that the first user is located at the labeled place based on the probability exceeding a preset threshold.
6. The method of claim 1 , wherein the historical data further comprises venue metadata of the labeled place.
7. The method of claim 1 , wherein the historical data further comprises checking in data of one or more of the at least one user at the labeled place.
8. The method of claim 1 , wherein the machine learning model is trained using a gradient boosting.
9. A system, comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
accessing historical data collected from at least one client device of at least one user over a period of time, the historical data comprising a plurality of data points; each data point comprising location data, and wireless network data;
identifying based on the location data and the wireless network data, first data points of the plurality of data points corresponding to the at least one user being located at a labeled place;
generating a labeled dataset by tagging the first data points with a label corresponding to the labeled place;
training a machine learning model on the labeled dataset;
receiving from a first client device associated with a first user, an electronic communication containing current location data;
determining, using the trained machine learning model, that the first user is located at the labeled place; and
based on determining that the first user is located at the labeled place, initiating transmission of data to a second client device by attaching the data to a message accessible for a predetermined duration of time, the data indicating the labeled place at which the first user is located for display on a display screen of the second client device.
10. The system of claim 9 , wherein the wireless network data comprises wireless local area network (WLAN) information of one or more WLAN networks available to the at least one client device.
11. The system of claim 10 , wherein identifying the first data points comprises:
parsing the WLAN information to identify a name of the one or more WLAN networks; and
determining that the at least one user was located at the labeled place, at least partially, based on the name of one of the WLAN networks matching a name of the labeled place.
12. The system of claim 9 , wherein the wireless network data comprises WLAN information of a WLAN the at least one client device is connected to.
13. The system of claim 9 , wherein determining that the first user is located at the labeled place further comprises:
computing, using the trained machine learning model, a probability of the first user being located at the labeled place; and
determining that the first user is located at the labeled place based on the probability exceeding a preset threshold.
14. The system of claim 9 , wherein the historical data further comprises venue metadata of the labeled place.
15. The system of claim 9 , wherein the historical data further comprises checking in data of one or more of the at least one user at the labeled place.
16. The system of claim 9 , wherein the machine learning model is trained using a gradient boosting.
17. A non-transitory computer-readable medium comprising instructions, which when executed by a computing device, cause the computing device to perform operations comprising:
accessing historical data collected from at least one client device of at least one user over a period of time, the historical data comprising a plurality of data points, each data point comprising location data, and wireless network data;
identifying based on the location data and the wireless network data, first data points of the plurality of data points corresponding to the at least one user being located at a labeled place;
generating a labeled dataset by tagging the first data points with a label corresponding to the labeled place;
training a machine learning model on the labeled dataset;
receiving from a first client device associated with a first user, an electronic communication containing current location data;
determining, using the trained machine learning model, that the first user is located at the labeled place; and
based on determining that the first user is located at the labeled place, initiating transmission of data to a second client device by attaching the data to a message accessible for a predetermined duration of time, the data indicating the labeled place at which the first user is located for display on a display screen of the second client device.
18. The non-transitory computer-readable medium of claim 17 , wherein the wireless network data comprises wireless local area network (WLAN) information of one or more WLAN networks available to the at least one client device.
19. The non-transitory computer-readable medium of claim 18 , wherein identifying the first data points comprises:
parsing the WLAN information to identify a name of the one or more WLAN networks; and
determining that the at least one user was located at the labeled place, at least partially, based on the name of one of the WLAN networks matching a name of the labeled place.
20. The non-transitory computer-readable medium of claim 17 , wherein the wireless network data comprises WLAN information of a WLAN the at least one client device is connected to.