Determining a user habit

1. A method implemented by one or more processors, comprising:

identifying a plurality of past activity occurrences, of a user, that are each based on prior user input at a given application of a computing device of the user;

determining a group of the past activity occurrences based on the past activity occurrences of the group, each of the past activity occurrences defining a corresponding interaction entity interacted with during a corresponding one of the past activity occurrences;

determining a plurality of habit interaction entities that conform to the corresponding interaction entities of the group of the past activity occurrences;

determining one or more habit trigger indicators based on features of the past activity occurrences of the group;

associating a user habit with the user, the user habit including the plurality of habit interaction entities and one or more of the habit trigger indicators;

subsequent to associating the user habit with the user:

determining that current user activity conforms to the one or more habit trigger indicators; and

in response to determining that the current user activity conforms to the one or more habit trigger indicators:

automatically causing a recommendation to be presented at the computing device or an additional computing device of the user,

wherein the recommendation is based on the plurality of habit interaction entities of the user habit, and

wherein the recommendation includes a corresponding selectable element associated with each of the plurality of habit interaction entities;

in response to receiving a selection of a first corresponding selectable element, of the corresponding selectable elements of the recommendation, that is associated with a first habit interaction action entity, of the plurality of habit interaction entities:

causing the computing device or the additional computing device to perform the action directed to first habit interaction action associated with the first corresponding selectable element.

2. The method of claim 1 , further comprising:

ranking the recommendation, relative to one or more other recommendations, based on determining that the current user activity conforms to the one or more habit trigger indicators;

wherein automatically causing the recommendation to be presented comprises automatically causing the recommendation to be presented based on the ranking.

3. The method of claim 1 , further comprising:

determining a location habit trigger indicator based on location features of the occurrences of the past activity occurrences of the group;

wherein the user habit further includes the location habit trigger indicator.

4. The method of claim 3 , wherein automatically causing the recommendation to be presented is further based on determining that a current location, of the computing device or the additional computing device, conforms to the location habit trigger indicator.

5. The method of claim 1 , further comprising:

determining a temporal habit trigger indicator based on temporal features of the occurrences of the past activity occurrences of the group;

wherein the user habit further includes the temporal habit trigger indicator.

6. The method of claim 5 , wherein automatically causing the recommendation to be presented is further based on determining that a current time, of the computing device or the additional computing device, conforms to the temporal habit trigger indicator.

7. The method of claim 1 , further comprising: in response to receiving a selection of a second corresponding selectable element, of the corresponding selectable elements of the recommendation, that is associated with a second habit interaction action entity, of the plurality of habit interaction entities:

causing the computing device or the additional computing device to perform the action directed to second habit interaction action associated with the second corresponding selectable element.

8. The method of claim 1 , wherein the action that is performed the computing device or the additional computing device and that is directed to a given one of the plurality of habit interactions comprises one of: a phone call action, a text message action, or an email action.

9. The method of claim 1 , wherein automatically causing the recommendation to be presented at the computing device or the additional computing device comprises automatically causing the recommendation to be presented at the additional computing device.

10. A system comprising:

at least one processor; and

memory storing instructions that, when executed, cause the at least one processor to:

identify a plurality of past activity occurrences, of a user, that are each based on prior user input at a given application of a computing device of the user;

determine a group of the past activity occurrences based on the past activity occurrences of the group, each of the past activity occurrences defining a corresponding interaction entity interacted with during a corresponding one of the past activity occurrences;

determine a plurality of habit interaction entities that conform to the corresponding interaction entities of the group of the past activity occurrences;

determine one or more habit trigger indicators based on features of the past activity occurrences of the group;

associate a user habit with the user, the user habit including the plurality of habit interaction entities and one or more of the habit trigger indicators;

subsequent to associating the user habit with the user:

determine that current user activity conforms to the one or more habit trigger indicators; and

in response to determining that the current user activity conforms to the one or more habit trigger indicators:

automatically cause a recommendation to be presented at the computing

device or an additional computing device of the user,

wherein the recommendation is based on the plurality of habit interaction entities of the user habit, and

wherein the recommendation includes a corresponding selectable element associated with each of the plurality of habit interaction entities;

in response to receiving a selection of a first corresponding selectable element, of the corresponding selectable elements of the recommendation, that is associated with a first habit interaction action entity, of the plurality of habit interaction entities:

cause the computing device or the additional computing device to perform the action directed to first habit interaction action associated with the first corresponding selectable element.

11. The system of claim 10 , wherein the instructions further cause the at least one processor to:

rank the recommendation, relative to one or more other recommendations, based on determining that the current user activity conforms to the one or more habit trigger indicators;

wherein the instructions to automatically cause the recommendation to be presented comprise instructions to automatically cause the recommendation to be presented based on the ranking.

12. The system of claim 10 , wherein the instructions further cause the at least one processor to:

determine a location habit trigger indicator based on location features of the occurrences of the past activity occurrences of the group;

wherein the user habit further includes the location habit trigger indicator.

13. The system of claim 12 , wherein automatically causing the recommendation to be presented is further based on determining that a current location, of the computing device or the additional computing device, conforms to the location habit trigger indicator.

14. The system of claim 10 , wherein the instructions further cause the at least one processor to:

determining a temporal habit trigger indicator based on temporal features of the occurrences of the past activity occurrences of the group;

wherein the user habit further includes the temporal habit trigger indicator.

15. The system of claim 14 , wherein automatically causing the recommendation to be presented is further based on determining that a current time, of the computing device or the additional computing device, conforms to the temporal habit trigger indicator.

16. The system of claim 1 , wherein the instructions further cause the at least one processor to:

in response to receiving a selection of a second corresponding selectable element, of the corresponding selectable elements of the recommendation, that is associated with a second habit interaction action entity, of the plurality of habit interaction entities:

cause the computing device or the additional computing device to perform the action directed to second habit interaction action associated with the second corresponding selectable element.

17. The system of claim 10 , wherein the action that is performed the computing device or the additional computing device and that is directed to a given one of the plurality of habit interactions comprises one of: a phone call action, a text message action, or an email action.

18. A non-transitory computer-readable storage medium storing instructions that, when executed, cause at least one processor to perform operations, the operations comprising:

identifying a plurality of past activity occurrences, of a user, that are each based on prior user input at a given application of a computing device of the user;

determining a group of the past activity occurrences based on the past activity occurrences of the group, each of the past activity occurrences defining a corresponding interaction entity interacted with during a corresponding one of the past activity occurrences;

determining a plurality of habit interaction entities that conform to the corresponding interaction entities of the group of the past activity occurrences;

determining one or more habit trigger indicators based on features of the past activity occurrences of the group;

associating a user habit with the user, the user habit including the plurality of habit interaction entities and one or more of the habit trigger indicators;

subsequent to associating the user habit with the user:

determining that current user activity conforms to the one or more habit trigger indicators; and

in response to determining that the current user activity conforms to the one or more habit trigger indicators:

automatically causing a recommendation to be presented at the computing device or an additional computing device of the user,

wherein the recommendation is based on the plurality of habit interaction entities of the user habit, and

wherein the recommendation includes a corresponding selectable element associated with each of the plurality of habit interaction entities

in response to receiving a selection of a first corresponding selectable element, of the corresponding selectable elements of the recommendation, that is associated with a first habit interaction action entity, of the plurality of habit interaction entities:

causing the computing device or the additional computing device to perform the action directed to first habit interaction action associated with the first corresponding selectable element.