User presence determination
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for presence determination. One of the methods includes for one or more user devices having one or more associated users, determining a current location of a user, wherein the current location is associated with a particular space of a plurality of different spaces, wherein the determining includes: computing a plurality of location results, wherein each location result is computed using a distinct process of a plurality of processes; and evaluating the plurality of location results to determine a current space of the user; wherein the determining is performed by one or more of, a particular user device, a terminal device, or a server system.
1. A method comprising:
for one or more user devices having one or more associated users, determining a current location of a user, wherein the current location is associated with a particular space of a plurality of different spaces, wherein the determining includes:
computing a plurality of location results, wherein each location result is computed using a distinct process of a plurality of processes, and wherein a first process of the plurality of processes produces a lag result that represents location results for a past time, and wherein at least a second process of the plurality of processes produces a real-time result that represents location results for a current time, wherein the real-time result is characterized as having less confidence than the lag result; and
evaluating the plurality of location results, including the lag result and real-time results, to determine a current space of the user,
wherein the determining is performed by one or more of, a particular user device, a terminal device, or a server system.
2. The method of claim 1 , wherein determining the current location of the user includes obtaining a plurality of data points.
3. The method of claim 2 , further comprising performing calibration for the plurality of different spaces prior to obtaining the plurality of data points.
4. The method of claim 1 , wherein the determining is based on votes generated for the location result computed for each of the plurality of processes.
5. The method of claim 1 , wherein in response to determining the current location is a space of the plurality of different spaces that has not been calibrated, mapping the space.
6. The method of claim 1 , wherein each process of the plurality of processes is trained, and wherein the training includes comparing a location of a user computed using a particular process with a location of the user computed using a baseline process.
7. The method of claim 6 , wherein each process of the plurality of processes is associated with a particular weight, wherein the particular weight is determined based on a confidence of the computed location of the process determining during the training.
8. The method of claim 6 , wherein the training includes monitoring one or more of RSSI data and accelerometer data for a user device.
9. The method of claim 1 , wherein a process of the plurality of processes comprises generating scan tables of RSSI values between terminal devices over time.
10. The method of claim 9 , wherein changes in the scan tables provide an indication that the calibration is incorrect due to movement of one or more terminal devices.
11. The method of claim 1 , wherein a process of the plurality of processes comprises tracking user device movement in a space to predict whether the user device is going to leave the space.
12. The method of claim 11 , wherein in response to a determination that the user device in a space is not moving includes initiating one or more low power modes for the process.
13. The method of claim 1 , wherein a process of the plurality of processes comprises detecting signal dampening that exceeds a threshold value and using the detected signal dampening to provide an offset to a baseline process for determining user device location.
14. The method of claim 13 , wherein user device orientation is used to interpret signal dampening.
15. The method of claim 14 , wherein training the process includes performing machine learning to understand a relationship between user device orientation and how it effects incoming RSSI data.
16. The method of claim 1 , wherein a process of the plurality of processes comprises using proximity and motion detectors to provide a vote on the location of a user when the user device is not present.
17. The method of claim 1 , wherein one or more of the processes include a reactive specification that determines which user device of a plurality of user devices to provide a vote for as the location of a user.
18. The method of claim 1 , wherein the determination of the current user location is performed on one or more of the user device, a remote server in communication with the user device, or one or more terminal devices located in respective spaces of the plurality of different spaces.
19. The method of claim 1 , comprising adjusting one or more settings of one or more terminal devices based on the determination of the current location of the user.
20. The method of claim 1 , further comprising:
in response to determining the space corresponding to the current user location, establishing a connection with one or more terminal devices in the space; and
presenting information on the user device indicating equipment coupled to respective terminal devices that are closest to the location of the user.
21. The method of claim 1 , wherein the determined current location is used to determine a predicted change from one space to another space.