Automated generation of suggestions for personalized reactions in a social network

• US 8,589,407 B2
• Filed: 06/17/2011
• Issued: 11/19/2013
• Est. Priority Date: 06/17/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bhatia, Ashish
• Primary Examiner(s): Wong, Leslie
• Application Number:
  US13/163,331
• Publication Number:
  US 20120323928A1
• Time in Patent Office: 886 Days
• Field of Search: 707/723, 707/732, 707/767, 707/999.01, 707/999.003, 707/999.006, 707/999.007, 707/999.107, 707/748, 707/758, 709/203, 709/219
• US Class Current: 707/748
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

A system and method for automatic generating suggestions for personalized reactions or messages. A suggestion generation module includes a plurality of collector modules, a credentials module, a suggestion analyzer module, a user interface module and a decision tree. The plurality of collector modules are coupled to respective systems to collect information accessible by the user and important to the user from other systems such as e-mail systems, SMS/MMS systems, micro blogging systems, social networks or other systems. The information from these collector modules is provided to the suggestion analyzer module. The suggestion analyzer module cooperates with the user interface module and the decision tree to generate suggested reactions or messages for the user to send. The suggested reactions or messages are presented by the user interface module to the user. The user interface module also displays the original message, other information about the original message such as others'"'"' responses, and action buttons for sending, discarding or ignoring the suggested message.

Claims

1. A method for generating a personalized reaction, the method comprising:

collecting, using one or more computing devices, interaction items associated with a first user and accessible to the first user from one or more data sources, the one or more data sources including a social network, the interaction items including an online user post and a user reaction;

processing, using one or more computing devices, the collected interaction items to produce one or more labels for the collected interaction items;

ranking, using one or more computing devices, each collected interaction item based on the labels and based on the first user'"'"'s prior reactions to other interaction items and the respective labels of the first user'"'"'s prior reactions;

determining that the online user post satisfies a threshold likelihood of being important or interesting to the first user; and

automatically generating, using one or more computing devices, a suggested personalized reaction to the online user post on behalf of the first user, the suggested personalized reaction based on one or more labels associated with the online user post.

2. The method of claim 1 comprising initializing at least one of the one or more data sources.

3. The method of claim 2 wherein initializing the at least one of the one or more data sources includes collecting and storing a first user'"'"'s credentials to access the data source being initialized.

4. The method of claim 1 wherein the one or more data sources include one or more of another social network, an e-mail system, a micro blogging system, a SMS system, a MMS system, an instant messaging system, and another on-line communication system.

5. The method of claim 1 wherein collecting information from the social network includes retrieving a social graph, messages posted and messages read.

6. The method of claim 1 wherein collecting information from the one or more data sources includes:

collecting information from a plurality of data sources; and

correlating the collected information.

7. The method of claim 1 further comprising:

correlating the collected information;

weighing the correlated collected information; and

wherein a ranking is based upon a label and weight for each reaction; and

wherein the generating step selects a reaction with a highest rank.

8. The method of claim 1 further comprising:

presenting a suggested personalized reaction to the first user;

receiving input from a user;

determining whether the input is to send the suggested personalized reaction; and

modifying a suggestion analyzer based on the received input when the input was to send the suggested personalized reaction.

9. The method of claim 8 wherein modifying the suggestion analyzer includes updating a decision tree based upon the suggested personalized reaction being sent.

10. The method of claim 1 further comprising:

presenting a suggested personalized reaction to the first user;

receiving input from a user;

determining whether the input is to ignore the suggested personalized reaction; and

modifying a suggestion analyzer when the input was to ignore the suggested personalized reaction.

11. The method of claim 1 further comprising:

presenting a suggested personalized reaction to the first user;

receiving input from a user;

determining whether the input is to discard the suggested personalized reaction; and

modifying a suggestion analyzer when the input was to discard the suggested personalized reaction.

12. An apparatus for generating a suggested personalized reaction, the apparatus comprising:

one or more processors;

a collector module, stored on a memory and executable by the one or more processors, for collecting interaction items accessible to a first user from an electronic communication system, the interaction items including an online user post and a user reaction, the collector module coupled to receive interaction items from the electronic communication system;

a suggestion analyzer module for processing the collected interaction items to produce one or more labels for the collected interaction items, ranking each collected interaction item based on the labels and the first user'"'"'s prior reactions to other interaction items and the respective labels of the first user'"'"'s prior reactions, determining that the online user post satisfies a threshold likelihood of being important or interesting to the first user, and automatically generating a suggested personalized reaction to online user post on behalf of the first user, the suggested personalized reaction based on the one or more labels associated with online user post; and

a user interface module for presenting the suggested personalized reaction and related information and for receiving input from the first user, the user interface module coupled to receive the suggested personalized reaction from the suggestion analyzer module, the user interface module configured to receive input from the first user.

13. The apparatus of claim 12 comprising a second collector module for collecting information of the first user from a second electronic communication system, wherein the electronic communication system is different from the second electronic communication system.

14. The apparatus of claim 12 wherein the electronic communication system is one from the group of a social network, an e-mail system, a micro blogging system, a SMS system, a MMS system, an instant messaging system, and another on-line communication system.

15. The apparatus of claim 12 wherein the collector module retrieves any information in the electronic communication system accessible to the first user whether the information is private or public.

16. The apparatus of claim 12 further comprising a credentials module for receiving, storing and providing credentials related to the first user'"'"'s access of the electronic communication system, the credentials module coupled to receive input from the first user and coupled to provide information to the collector module.

17. The apparatus of claim 12 wherein the suggestion analyzer module correlates information collected by the collector module, weighs the correlated collected information and labels and ranks weighted information to generate the suggested personalized reaction.

18. The apparatus of claim 12 further comprising an initialization module for initializing a suggestion generation module with information that allows the collector module to access the electronic communication system, the initialization module coupled to receive input from the first user.

19. The apparatus of claim 12 further comprising a data storage for storing information collected by the collector module for use by the suggestion analyzer module, the data storage coupled to the collector module and the suggestion analyzer module.

20. The apparatus of claim 12 further comprising a decision tree for processing responses to suggested reaction and providing modification to weight to the suggestion analyzer module, the decision tree coupled to receive user responses from the user interface module and coupled to output modifications to the suggestion analyzer module.

21. The apparatus of claim 12 wherein the decision tree is an artificial intelligence-based decision tree.