Intelligent intent detection from social network messages

• US 8,918,354 B2
• Filed: 10/03/2011
• Issued: 12/23/2014
• Est. Priority Date: 10/03/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Karnik, Shardool, Li, Xiaolong, Sundaram, Partha
• Primary Examiner(s): Chang, Li-Wu
• Assistant Examiner(s): BUSS, BENJAMIN J
• Application Number:
  US13/251,294
• Publication Number:
  US 20130085970A1
• Time in Patent Office: 1,177 Days
• Field of Search: 706/12, 706/14, 706/45
• US Class Current: 706/45
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

An intent engine that automatically detects user intent from messages of a social network (e.g., messages with questions to ask) and outputs intent data. The engine is intelligent in that it can process natural language input such as questions and terms. The user is then directed to an answer page filtered according to the intent data and which provides answers related to a question, for example. The intent engine can be designated (e.g., tagged, or “friended”) and then linked into a specialized relationship (e.g., a “friend”). Accordingly, in one example, a URL link is constructed that points to the answer page, with filters configured based on the intent data. The URL is then sent back to the user as a friendly response. When the user selects the link, the user is presented with an answer page that provides answers which match the user intent derived from the user messages.

Claims

1. A system, comprising:

an intent component configured to detect user intent of a user from messages of the user on a social network, to determine questions posed by the user in the messages, the intent component assigned a status of the social network that enables access to the user messages of the social network;

a results component configured to return results comprising answers to the questions posed by the user, the results returned based on the user intent, the results being provided on an answers page; and

a microprocessor configured to execute computer-executable instructions associated with at least one of the intent component or the results component.

2. The system of claim 1, wherein a uniform resource locator is constructed to point to the answers page that includes the answers to the questions posed by the user on the social network.

3. The system of claim 1, wherein the social network messages are used as training data for the intent component, which is an intent engine.

4. The system of claim 1, wherein the intent component improves the results to the user based on feedback of the user.

5. The system of claim 1, wherein the results component creates the answers page and the intent component creates a link to the answers page, the link provided to the user to access the results.

6. The system of claim 5, wherein the results are filtered based on the detected intent.

7. The system of claim 1, wherein the intent component analyzes the social network messages and determines top popular domains in the messages.

8. The system of claim 7, wherein the intent component processes the top domain messages to refine results to the user.

9. A method comprising acts of:

designating access to user messages of a user of a social network to an intent engine via a social status;

detecting user intent of the user from the user messages using the intent engine to determine a question posed by the user in the messages;

creating results by outputting answers to the question posed by the user, the results based on the user intent;

providing the results to the user on an answers page; and

configuring at least one processor that executes instructions stored in memory to perform the acts of designating, detecting, providing, and creating.

10. The method of claim 9, further comprising creating the results as answers to the question posed by the user, which is a natural language question.

11. The method of claim 9, further comprising filtering the results based on the user intent.

12. The method of claim 9, further comprising collecting the messages to train the intent engine.

13. The method of claim 9, further comprising computing top domains based on the user messages.

14. The method of claim 9, further comprising refining the results based on domains derived from the user messages.

15. The method of claim 9, further comprising processing user feedback to improve the results.

16. The method of claim 9, further comprising enabling the user to designate the social status to a search engine that employs intent detection.

17. A method comprising acts of:

designating access to user messages of a user of a social network to an intent engine via a social status;

detecting user intent of the user from the user messages to determine a user question posed by the user in the messages using the intent engine;

filtering answers to the user question based on the user intent;

presenting the answers on an answer page;

generating a navigation link to the answer page;

returning the navigation link to the user;

presenting the answer page to the user in response to selection of the navigation link by the user; and

configuring at least one processor that executes instructions stored in memory to perform the acts of designating, detecting, filtering, presenting, generating, and returning.

18. The method of claim 17, further comprising generating the answers and processing user feedback to improve quality of answers.

19. The method of claim 17, further comprising computing domains from the user intent and determining facet information for the domains.

20. The method of claim 17, further comprising presenting the answers based on the social network and a non-social network.

21. A computer-readable storage medium comprising instructions that when executed by a hardware processor, cause the processor to perform acts comprising:

designating access to user messages of a user of a social network to an intent engine via a social status;

detecting user intent of the user from the user messages using the intent engine to determine a question posed by the user in the messages;

creating results by outputting answers to the question posed by the user, the results based on the user intent; and

providing the results to the user on an answers page.