SERVICE PLATFORM TO SUPPORT AUTOMATED CHAT COMMUNICATIONS AND METHODS FOR USE THEREWITH

• US 20170019356A1
• Filed: 07/16/2015
• Published: 01/19/2017
• Est. Priority Date: 07/16/2015
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gilbert, Mazin E.
• Granted Patent: US 10,805,244 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/046 Interoperability with other network applications or services
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Aspects of the subject disclosure may include, for example, a service platform that receives a chat request from a client device associated with a user. A chat database of previous chat sessions associated with other users is searched based on the chat request to identify a previous chat session corresponding to the chat request. Chat data corresponding to the previous chat session is retrieved from the chat database and sent to the client device. Other embodiments are disclosed.

Claims

1. A service platform comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate the following;

receiving a chat request from a client device associated with a user;

searching a chat database of previous chat sessions associated with other users, based on the chat request, to identify at least one previous chat session corresponding to the chat request;

retrieving chat data corresponding to the at least one previous chat session from the chat database; and

sending the chat data to the client device.

2. The service platform of claim 1 wherein the memory further stores executable instructions that, when executed by the processor, facilitate:

establishing a chat session between the user and a live agent when at least one previous chat session corresponding to the chat request cannot be identified.

3. The service platform of claim 2 wherein the at least one previous chat session includes a predetermined number of previous chat sessions and wherein the chat session between the user and the live agent is established when less than the predetermined number of previous chat sessions corresponding to the chat request are identified.

4. The service platform of claim 1 wherein identifying the at least one previous chat session corresponding to the chat request includes:

determining a confidence that the at least one previous chat session corresponds to the chat request; and

determining that the confidence corresponding to the at least one previous chat session exceeds a confidence threshold.

5. The service platform of claim 1 wherein searching the chat database includes identifying at least one word associated with the chat request and text mining the chat database based on the at least one word.

6. The service platform of claim 5 wherein identifying the at least one previous chat session corresponding to the chat request includes evaluating at least one term frequency and inverse document frequency associated with the at least one word and the at least one previous chat session.

7. The service platform of claim 1 wherein the memory further stores executable instructions that, when executed by the processor, facilitate:

receiving a user indication; and

establishing a chat session between the user and a live agent in response to the indication.

8. The service platform of claim 7 wherein the memory further stores executable instructions that, when executed by the processor, facilitate:

collecting chat data associated with the chat session;

anonymizing the chat data associated with the chat session; and

storing the chat data associated with the chat session in the chat database.

9. The service platform of claim 8 wherein the memory further stores executable instructions that, when executed by the processor, facilitate:

cleaning the chat data to improve readability and to remove inappropriate content.

10. The service platform of claim 1 wherein the client device is a mobile communication device and wherein the chat request is entered via user speech.

11. A method comprising:

receiving, at a service platform, a chat request from a client device associated with a user;

searching a chat database of previous chat sessions associated with other users, based on the chat request, to identify a plurality of previous chat sessions corresponding to the chat request;

retrieving chat data corresponding to the plurality of previous chat sessions from the chat database; and

sending the chat data to the client device.

12. The method of claim 11 further comprising:

establishing a chat session between the user and a live agent when a plurality of previous chat sessions corresponding to the chat request cannot be identified.

13. The method of claim 12 wherein the plurality of previous chat sessions include a predetermined number of previous chat sessions and wherein the chat session between the user and the live agent is established when less than the predetermined number of previous chat sessions corresponding to the chat request are identified.

14. The method of claim 11 wherein identifying the plurality of previous chat sessions corresponding to the chat request includes:

determining a confidence that each of the plurality of previous chat sessions corresponds to the chat request; and

determining that the confidence corresponding to each of the plurality of previous chat sessions exceeds a confidence threshold.

15. The method of claim 11 wherein searching the chat database is further based on one of:

demographic data corresponding to the user, a previous chat corresponding to the user or a time of day.

16. The method of claim 15 wherein identifying the plurality of previous chat sessions corresponding to the chat request includes evaluating at least one term frequency and inverse document frequency associated with at least one word associated with the chat request and the plurality of previous chat sessions.

17. The method of claim 11 further comprising:

receiving a user indication that the chat data fails to satisfy the chat request; and

establishing a chat session between the user and a live agent in response to the user indication.

18. The method of claim 17 further comprising:

collecting chat data associated with the chat session;

anonymizing the chat data associated with the chat session; and

storing the chat data associated with the chat session in the chat database.

19. The method of claim 18, wherein chat data is selected for storage based on at least one policy related to agent performance.

20. A machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

receiving a chat request from a client device associated with a user;

searching a chat database of previous chat sessions associated with other users, based on the chat request, to identify at least one previous chat session corresponding to the chat request;

retrieving chat data corresponding to the at least one previous chat session from the chat database; and

sending the chat data to the client device.