Sending Notifications to Users Based on Users' Notification Tolerance Levels

1 . A method comprising: by one or more first computing devices,

accessing a notification to be pushed to a second computing device associated with a user;

computing a score for the notification based at least in part on a current level of tolerance of the user to notifications pushed to the second computing device; and

if the score is above a predetermined threshold, then pushing the notification to the second computing device.

2 . The method of claim 1 , wherein the score for the notification is further based on a current likelihood that the user interacts with the notifications pushed to the second computing device.

3 . The method of claim 1 , wherein the notification is one of a plurality of notifications, and the method further comprising:

for each of the plurality of notifications, computing a score for the notification based at least in part on the current level of tolerance of the user to notifications pushed to the second computing device;

if the score of at least one of the plurality of notifications is above the predetermine threshold, then pushing one or more top-scored notifications whose scores are above the predetermine threshold to the second computing device.

4 . The method of claim 1 , further comprising:

monitoring and collecting one or more activities performed by the user in connection with one or more notifications pushed to the second computing device;

constructing a notification-interaction profile for the user based on the one or more activities; and

constructing a notification-tolerance profile for the user based on the one or more activities.

5 . The method of claim 1 , further comprising:

for each of a plurality of users associated with a plurality of second computing devices respectively,

monitoring and collecting one or more activities performed by the user in connection with one or more notifications pushed to the second computing device;

constructing a notification-interaction profile for the user based on the one or more activities performed by the user; and

constructing a notification-tolerance profile for the user based on the one or more activities performed by the user;

categorizing the plurality of users into one or more user groups; and

for each of the one or more user groups,

aggregating the one or more activates performed by each user in the user group;

constructing a notification-interaction profile for the user group based on the aggregated activities; and

constructing a notification-tolerance profile for the user based on based on the aggregated activities.

6 . The method of claim 1 , wherein the notification is an advertisement associated with an advertiser, and the method further comprising:

determining a charge to the advertiser for pushing the advertisement to the second computing device based at least in part on the current level of tolerance of the user to the notifications pushed to the second computing device.

7 . The method of claim 6 , wherein charge to the advertiser for pushing the advertisement to the second computing device is further based on the current likelihood that the user interacts with the notifications pushed to the second computing device.

8 . The method of claim 6 , further comprising constructing a model comprising one or more notification-interaction profiles and one or more notification-tolerance profiles for one or more users respectively,

wherein the charge to the advertiser for pushing the advertisement to the second computing device is determined by the model in real time.

9 . A first system comprising:

a memory comprising instructions executable by one or more processors; and

the one or more processors coupled to the memory and operable to execute the instructions, the one or more processors being operable when executing the instructions to:

access a notification to be pushed to a second system associated with a user;

compute a score for the notification based at least in part on a current level of tolerance of the user to notifications pushed to the second system; and

if the score is above a predetermined threshold, then push the notification to the second system.

10 . The first system of claim 9 , wherein the score for the notification is further based on a current likelihood that the user interacts with the notifications pushed to the second system.

11 . The first system of claim 9 , wherein the notification is one of a plurality of notifications, and the one or more processors are further operable when executing the instructions to:

for each of the plurality of notifications, compute a score for the notification based at least in part on the current level of tolerance of the user to notifications pushed to the second system;

if the score of at least one of the plurality of notifications is above the predetermine threshold, then push one or more top-scored notifications whose scores are above the predetermine threshold to the second system.

12 . The first system of claim 9 , wherein the one or more processors are further operable when executing the instructions to:

monitor and collect one or more activities performed by the user in connection with one or more notifications pushed to the second system;

construct a notification-interaction profile for the user based on the one or more activities; and

construct a notification-tolerance profile for the user based on the one or more activities.

13 . The first system of claim 9 , wherein the one or more processors are further operable when executing the instructions to:

for each of a plurality of users associated with a plurality of second systems respectively,

monitor and collect one or more activities performed by the user in connection with one or more notifications pushed to the second system;

construct a notification-interaction profile for the user based on the one or more activities performed by the user; and

construct a notification-tolerance profile for the user based on the one or more activities performed by the user;

categorize the plurality of users into one or more user groups; and

for each of the one or more user groups,

aggregate the one or more activates performed by each user in the user group;

construct a notification-interaction profile for the user group based on the aggregated activities; and

construct a notification-tolerance profile for the user based on based on the aggregated activities.

14 . The first system of claim 9 , wherein the notification is an advertisement associated with an advertiser, and the one or more processors are further operable when executing the instructions to:

determine a charge to the advertiser for pushing the advertisement to the second system based at least in part on the current level of tolerance of the user to the notifications pushed to the second system.

15 . The first system of claim 14 , wherein charge to the advertiser for pushing the advertisement to the second system is further based on the current likelihood that the user interacts with the notifications pushed to the second system.

16 . The first system of claim 14 , wherein the one or more processors are further operable when executing the instructions to construct a model comprising one or more notification-interaction profiles and one or more notification-tolerance profiles for one or more users respectively,

wherein the charge to the advertiser for pushing the advertisement to the second system is determined by the model in real time.

17 . One or more computer-readable non-transitory storage media embodying software operable when executed by one or more first computer systems to:

access a notification to be pushed to a second computer system associated with a user;

compute a score for the notification based at least in part on a current level of tolerance of the user to notifications pushed to the second computer system; and

if the score is above a predetermined threshold, then push the notification to the second computer system.

18 . The media of claim 17 , wherein the notification is one of a plurality of notifications, and the software is further operable when executed by the one or more first computer systems to:

for each of the plurality of notifications, compute a score for the notification based at least in part on the current level of tolerance of the user to notifications pushed to the second computer system;

if the score of at least one of the plurality of notifications is above the predetermine threshold, then push one or more top-scored notifications whose scores are above the predetermine threshold to the second computer system.

19 . The media of claim 17 , wherein the software is further operable when executed by the one or more first computer systems to:

monitor and collect one or more activities performed by the user in connection with one or more notifications pushed to the second computer system;

construct a notification-interaction profile for the user based on the one or more activities; and

construct a notification-tolerance profile for the user based on the one or more activities.

20 . The media of claim 17 , wherein the notification is an advertisement associated with an advertiser, and the software is further operable when executed by the one or more first computer systems to:

determine a charge to the advertiser for pushing the advertisement to the second computer system based at least in part on the current level of tolerance of the user to the notifications pushed to the second computer system.