Method and system for exploring a personal interest space

1. A method, implemented on a machine having at least one processor, storage, and a communication platform connected to a network for exploring a personal interest space, the method comprising:

obtaining information related to a personal interest space associated with a user, wherein the personal interest space comprises at least one channel of content that the user is interested in and is used to automatically recommend content to the user;

constructing a decision tree having multiple nodes, each of which is associated with at least some of a plurality of channels of content, one or more of a plurality of users interested in the at least some channel, and at least one question, wherein the one or more users associated with each of the multiple nodes are learned, via machine learning based on training data recording online activities of the plurality of users, the decision tree includes a sub-tree for the user with at least one node having the user associated therewith and corresponding to the at least one channel of content included in the personal interest space of the user;

determining a time to explore further interest of the user based on a criterion related to growth of the personal interest space of the user;

exploring, at the time, the further interest of the user by:

identifying a first node of the decision tree associated with a first channel of content included in the personal interest space associated with the user,

determining a question for the user attached to the first node in connection with the first channel of content and directed to a second channel of content that is currently not included in the personal interest space,

obtaining an answer to the question from the user,

identifying, based on the answer, a second node in the decision tree associated with the second channel of content, and

updating the personal interest space associated with the user based on the second channel of content associated with the second node of the decision tree; and

automatically recommending, to the user, content related to channels of content in the updated personal interest space.

2. The method of claim 1 , further comprising:

asking the user the question at the determined timing.

3. The method of claim 1 , wherein the question for the user is selected from a plurality of questions in connection with the first node based on the information related to the personal interest space and/or a profile of the user.

4. The method of claim 1 , wherein the second node is identified by traversing down the decision tree from the first node based on the answer to the question.

5. The method of claim 1 , wherein the training data related to the plurality of users with respect to the plurality of channels of content comprises a plurality of vectors, each of which is indicative of a level at which a respective one of the plurality of users is interested in each of the plurality of channels.

6. The method of claim 5 , wherein the decision tree is created by a training model based on the plurality of vectors.

7. The method of claim 1 , wherein the sub-tree for the user is created based on the information related to the personal interest space and/or a profile of the user.

8. A system for exploring a personal interest space, comprising:

a hardware processor;

a user understanding unit implemented on the processor and configured for obtaining information related to a personal interest space associated with a user, wherein the personal interest space comprises at least one channel of content that the user is interested in and is used to automatically recommend content to the user;

a decision tree selecting unit implemented on the processor and configured for constructing a decision tree having multiple nodes, each of which is associated with at least some of a plurality of channels of content, one or more of a plurality of users interested in the at least some channel, and at least one question, wherein the one or more users associated with each of the multiple nodes are learned, via machine learning based on training data recording online activities of the plurality of users, the decision tree includes a sub-tree for the user with at least one node having the user associated therewith and corresponding to the at least one channel of content included in the personal interest space of the user;

a question initiating unit implemented on the processor and configured for identifying a first node of the decision tree associated with a first channel of content included in the personal interest space associated with the user;

a questioning timing unit implemented on the processor and configured for determining a time to explore further interest of the user based on a criterion related to growth of the personal interest space of the user;

a question selecting unit implemented on the processor and configured for exploring, at the determined time, the further interest of the user by

identifying a first node of the decision tree associated with a first channel of content included in the personal interest space associated with the user,

determining a question for the user attached to the first node in connection with the first channel of content and directed to a second channel of content that is currently not included in the personal interest space,

obtaining an answer to the question from the user, and

identifying, based on the answer, a second node in the decision tree associated with the second channel of content; and

a user interest updating module implemented on the processor and configured for updating the personal interest space associated with the user based on the at least a second channel of content associated with the second node of the decision tree, where the updated personal interest space is used to recommend, to the user, content related to the channels of content in the updated personal interest space.

9. The system of claim 8 , wherein the question for the user is selected from a plurality of questions in connection with the first node based on the information related to the personal interest space and/or a profile of the user.

10. The system of claim 8 , wherein the second node is identified by traversing down the decision tree from the first node based on the answer to the question.

11. The system of claim 8 , wherein the training data related to the plurality of users with respect to the plurality of channels of content comprises a plurality of vectors, each of which is indicative of a level at which a respective one of the plurality of users is interested in each of the plurality of channels.

12. The system of claim 11 , wherein the decision tree is created by a training model based on the plurality of vectors.

13. The system of claim 8 , wherein the sub-tree for the user is created based on the information related to the personal interest space and/or a profile of the user.

14. A non-transitory, machine-readable medium having information recorded thereon for exploring a personal interest space, wherein the information, when read by a machine, causes the machine to perform the steps of:

obtaining information related to a personal interest space associated with a user, wherein the personal interest space comprises at least one channel of content that the user is interested in and is used to automatically recommend content to the user;

constructing a decision tree having multiple nodes, each of which is associated with at least some of a plurality of channels of content, one or more of a plurality of users interested in the at least some channel, and at least one question, wherein the one or more users associated with each of the multiple nodes are learned, via machine learning based on training data recording online activities of the plurality of users, the decision tree includes a sub-tree for the user with at least one node having the user associated therewith and corresponding to the at least one channel of content included in the personal interest space of the user;

determining a time to explore further interest of the user based on a criterion related to growth of the personal interest space of the user;

exploring, at the time, the further interest of the user by:

identifying a first node of the decision tree associated with first channel of content included in the personal interest space associated with the user,

determining a question for the user attached to the first node in connection with the first channel of content and directed to a second channel of content that is currently not included in the personal interest space,

obtaining an answer to the question from the user,

identifying, based on the answer, a second node in the decision tree associated with the second channel of content, and

updating the personal interest space associated with the user based on the second channel of content associated with the second node of the decision tree; and

automatically recommending, to the user, content related to channels of content in the updated personal interest space.

15. The medium of claim 14 , wherein the information, when read by the machine, further causes the machine to:

asking the user the question at the determined timing.

16. The medium of claim 14 , wherein the question for the user is selected from a plurality of questions in connection with the first node based on the information related to the personal interest space and/or a profile of the user.

17. The medium of claim 14 , wherein the second node is identified by traversing down the decision tree from the first node based on the answer to the question.

18. The medium of claim 14 , wherein the training data related to the plurality of users with respect to the plurality of channels of content comprises a plurality of vectors, each of which is indicative of a level at which a respective one of the plurality of users is interested in each of the plurality of channels.

19. The medium of claim 18 , wherein the decision tree is created by a training model based on the plurality of vectors.

20. The medium of claim 14 , wherein the sub-tree for the user is created based on the information related to the personal interest space and/or a profile of the user.