Abstract: Intent-based reminders are provided. A user is enabled to initiate a reminder request based on an intent to enter or leave a given location. In a geofence training process, a plurality of geofences are created for plotting a path and subsequently tracking the user's traversal of the path for inferring the user's intent to depart or enter the location. A signal strength of a WLAN is recorded at each geofence. As the user traverses the path, a determination is made as to whether a predetermined percentage of the geofences is triggered in a sequential order by comparing the signal strength of the WLAN against the recorded WLAN signal strengths at the geofences. In some examples, signal strengths of neighboring WLANs are recorded and used to filter out false triggers. When a determination is made that the user's intent is to depart or enter the location, a reminder is provided.

Abstract: The methods described herein are configured to collect profile data on a device, scan for access points based on the profile data, and update a machine learning (ML) component based on feedback from the scan. Profile data is collected on a device as input to the ML component and a scan pattern is generated by the ML component based on the collected profile data, the scan pattern including a scan frequency, a scan iteration count, and a channel hint. A scan for access points is run in accordance with the generated scan pattern and the ML component receives feedback including a scanning result based on the scan for access points. ML component is then updated based on the scanning result, the scan pattern, and the profile data. Improving the ML component and thereby, the scanning efficiency of the device provides consistent network connection and improved battery performance.

Abstract: The methods described herein are configured to collect profile data on a device, scan for access points based on the profile data, and update a machine learning (ML) component based on feedback from the scan. Profile data is collected on a device as input to the ML component and a scan pattern is generated by the ML component based on the collected profile data, the scan pattern including a scan frequency, a scan iteration count, and a channel hint. A scan for access points is run in accordance with the generated scan pattern and the ML component receives feedback including a scanning result based on the scan for access points. ML component is then updated based on the scanning result, the scan pattern, and the profile data. Improving the ML component and thereby, the scanning efficiency of the device provides consistent network connection and improved battery performance.

Abstract: Intent-based reminders are provided. A user is enabled to initiate a reminder request based on an intent to enter or leave a given location. In a geofence training process, a plurality of geofences are created for plotting a path and subsequently tracking the user's traversal of the path for inferring the user's intent to depart or enter the location. A signal strength of a WLAN is recorded at each geofence. As the user traverses the path, a determination is made as to whether a predetermined percentage of the geofences is triggered in a sequential order by comparing the signal strength of the WLAN against the recorded WLAN signal strengths at the geofences. In some examples, signal strengths of neighboring WLANs are recorded and used to filter out false triggers. When a determination is made that the user's intent is to depart or enter the location, a reminder is provided.