Method and apparatus for automatically generating headlines based on data retrieved from a network and for answering questions related to a headline

• US 8,429,148 B1
• Filed: 11/01/2005
• Issued: 04/23/2013
• Est. Priority Date: 11/01/2005
• Status: Active Grant

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Douglas, Shona, Feng, Junlan, Gilbert, Mazin
• Primary Examiner(s): Kim, Charles
• Assistant Examiner(s): MINA, FATIMA P
• Application Number:
  US11/264,650
• Time in Patent Office: 2,730 Days
• Field of Search: 707/3, 707/708, 707/770, 707/771, 707/776, 707/796
• US Class Current: 707/708
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06F 2216/03 Data mining
• CPC Class Codes: G06F 40/14 Tree-structured documents parsing G06F40/205; validation G06F40/226
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

Disclosed is a web server that includes a headlines module for automatically generating headlines based on data retrieved from a network (e.g., World Wide Web). The web server also includes an interactive agent for generating responses to inquiries relating to the headlines based on the data.

Claims

1. A web server comprising:

a memory storing computer program instructions;

a processor communicatively coupled to the memory, the processor configured to execute the computer program instructions, which, when executed on the processor, cause the processor to host;

a headlines module for automatically generating headlines based on data retrieved from a network;

an interactive agent for generating responses to a current inquiry received from a user based on the data retrieved from a network, a previous inquiry from the user, and an answer to the previous inquiry generated by the interactive agent, wherein the interactive agent comprises;

a search engine for searching for relevant data, in the data retrieved from a network, pertaining to the current inquiry and the previous inquiry;

a question answer system for responding to the current inquiry and the previous inquiry; and

a virtual dialog agent for conversing with the user to perform tasks and exchange information with the user;

a data mining module for extracting data from web pages in the data retrieved from a network, converting the data from web pages to a structured format, assigning attributes to data from each web page, and determining if data from each web page is newsworthy based on calculation of a measure of significance of the attributes with respect to a predetermined standard; and

a call router for associating a telephone number of an agent knowledgeable in subject matter of the current inquiry with the current inquiry and initiating a telephone call to the telephone number,

wherein the previous inquiry is related to one of the headlines, the current inquiry is related to the answer to the previous inquiry, the headlines are based on information that has changed from a first point in time to a second point in time and data determined to be newsworthy from each web page, and the headlines vary according to the current inquiry, the previous inquiry, and the answer to the previous inquiry.

2. The web server of claim 1 wherein the current inquiry and the previous inquiry are related to data converted to the structured format by the data mining module.

3. The web server of claim 1 wherein the call router communicates with the data mining module to obtain the telephone number.

4. The web server of claim 1 wherein the headlines module selects the headlines based on data having a particular characteristic.

5. The web server of claim 4 wherein the particular characteristic further comprises a geographic location.

6. The web server of claim 1 wherein the attributes further comprise time, name of a person, name of a place, name of a service, and name of a product.

7. The web server of claim 1 further comprising an animated agent to provide assistance to a user.

8. The web server of claim 1 wherein the current inquiry and the previous inquiry are in the form of one of natural language queries, keywords, and keyword search patterns.

9. A method for operating a web server comprising:

retrieving data from a network by extracting the data from web pages and converting the data to a structured format;

assigning attributes to data from each web page;

determining if data from each webpage is newsworthy based on calculation of a measure of significance of the attributes with respect to a predetermined standard;

automatically generating headlines at a web server based on the data;

receiving a current inquiry from a user;

generating a response, by an interactive agent, to the current inquiry based on the data, a previous inquiry from the user, and an answer to the previous inquiry generated by the web server;

searching, by the interactive agent, for relevant data pertaining to the current inquiry and the previous inquiry using a search engine;

responding, by the interactive agent, to the current inquiry and the previous inquiry via a question and answer system;

conversing, by the interactive agent, with the user by a virtual dialog agent to perform tasks and exchange information with the user;

associating a telephone number of an agent knowledgeable in subject matter of the current inquiry with the current inquiry; and

initiating a telephone call to the telephone number in response to a request to make the telephone call,

wherein the previous inquiry is related to one of the headlines, the current inquiry is related to the answer to the previous inquiry, the headlines are based on information that has changed from a first point in time to a second point in time and data determined to be newsworthy, and the headlines vary according to the current inquiry, the previous inquiry, and the answer to the previous inquiry.

10. The method of claim 9 further comprising extracting structured data from web pages retrieved from the network.

11. The method of claim 9 further comprising searching the data from the network.

12. The method of claim 9 further comprising receiving user feedback relating to the response.

13. The method of claim 9 further comprising selecting the headlines based on data having a particular characteristic.

14. A web server comprising:

a processor; and

a memory to store computer program instructions, the computer program instructions when executed on the processor cause the processor to perform operations comprising;

retrieving data from a network by extracting the data from web pages and converting the data to a structured format;

assigning attributes to data from each web page;

determining if data from each webpage is newsworthy based on calculation of a measure of significance of the attributes with respect to a predetermined standard;

automatically generating headlines based on the data;

receiving a current inquiry from a user;

generating a response to the current inquiry based on the data, a previous inquiry from the user, and an answer to the previous inquiry generated by the web server, the generating comprising;

searching for relevant data pertaining to the current inquiry and the previous inquiry;

responding to user inquires in a question and answer format; and

conversing with a user to perform tasks and exchange information with the user;

associating a telephone number of an agent knowledgeable in subject matter of the current inquiry with the current inquiry; and

initiating a telephone call to the telephone number in response to a request to make the telephone call,

wherein the previous inquiry is related to one of the headlines, the current inquiry is related to the answer to the previous inquiry, the headlines are based on information that has changed from a first point in time to a second point in time and data determined to be newsworthy, and the headlines vary according to the current inquiry, the previous inquiry, and the answer to the previous inquiry.

15. The web server of claim 14 wherein the inquiry is related to the structured data.

16. The web server of claim 14 further comprising searching the data.

17. The web server of claim 14 further comprising receiving user feedback relating to the response.

18. The web server of claim 14 further comprising selecting the headlines based on data having a particular characteristic.