Summarizing social interactions between users

1. A computer-implemented method comprising:

receiving, with one or more hardware processors, a signal stream from at least one of a hardware sensor and a virtual detector;

filtering, with the one or more hardware processors, the signal stream and outputting filtered signal stream including data defining human-understandable actions;

identifying activities associated with a first user from the filtered signal stream;

summarizing the first user's activities;

determining that the first user is within proximity to a second user if a distance between the first user and the second user is shorter than a predetermined distance;

determining a degree of separation between the first user and the second user in a social network;

determining a time elapsed since a last interaction between the first user and the second user;

classifying the first user's relationship with the second user as being a first type of relationship, a second type of relationship or a third type of relationship;

responsive to having the first type of relationship, generating a first summary for the first user that includes a notification that the second user is nearby, a last interaction with the second user and recent interactions with the second user;

responsive to having the second type of relationship, generating a second summary for the first user that includes the notification that the second user is nearby, the last interaction with the second user and events that the first user and the second user share in common; and

responsive to having the third type of relationship, generating a third summary for the first user that includes the notification that the second user is nearby and events that the first user and the second user share in common.

2. The method of claim 1 , wherein the first, second and third summaries include action items that the first user owes the second user.

3. The method of claim 1 , wherein the first, second and third summaries include important events that occurred to the first user that the second user might be interested in hearing about.

4. The method of claim 1 , wherein the first, second and third summaries include a name of a mutual connection and an event that the mutual connection attended.

5. The method of claim 1 , wherein the first, second and third summaries include a recent post on a social network that was created by the second user.

6. The method of claim 1 , wherein the first user and the second user have not met and the information about the last time the first user interacted with the second user is a shared event that they attended.

7. The method of claim 1 , further comprising determining what information to provide in the summary to the first user about the second user based on privacy settings.

8. The method of claim 1 , wherein determining that the first user is within proximity to the second user is based at least in part on data received from at least one of the hardware sensor and the virtual detector.

9. A system comprising:

one or more hardware processors;

a processing unit stored on a memory and executable by the one or more hardware processors, the processing unit configured to receive a signal stream from at least one of a hardware sensor and a virtual detector;

a filter engine coupled to the processing unit and configured to filter the signal stream and outputting filtered signal stream including data defining human-understandable actions;

an activity identifier coupled to the filter engine and configured to identify activities associated with a first user from the filtered signal stream; and

a summary engine coupled to the activity identifier and configured to: summarize the first user's activities, determine that the first user is within proximity to a second user if a distance between the first user and the second user is shorter than a predetermined distance, determine a degree of separation between the first user and the second user in a social network and a time elapsed since a last interaction, classify the first user's relationship with the second user as being a first type of relationship, a second type of relationship or a third type of relationship; responsive to having the first type of relationship, generate a first summary for the first user that includes a notification that the second user is nearby, a last interaction with the second user and recent interactions with the second user; responsive to having the second type of relationship, generate a second summary for the first user that includes the notification that the second user is nearby, the last interaction with the second user and events that the first user and the second user share in common; and responsive to having the third type of relationship, generate a third summary for the first user that includes the notification that the second user is nearby and events that the first user and the second user share in common.

10. The system of claim 9 , wherein the first, second and third summaries include action items that the first user owes the second user.

11. The system of claim 9 , wherein the first, second and third summaries include important events that occurred to the first user that the second user might be interested in hearing about.

12. The system of claim 9 , wherein the first, second and third summaries include a name of a mutual connection and an event that the mutual connection attended.

13. The system of claim 9 , wherein the first, second and third summaries include a recent post on a social network that was created by the second user.

14. The system of claim 9 , wherein the first user and the second user have not met and the information about the last time the first user interacted with the second user is a shared event that they attended.

15. The system of claim 9 , further comprising a privacy engine coupled to the summary engine, the privacy engine configured to determine what information to provide in the summary to the first user about the second user based on privacy settings.

16. The system of claim 9 , wherein determining that the first user is within proximity to the second user is based at least in part on data received from at least one of the hardware sensor and the virtual detector.