Service platform to support automated chat communications and methods for use therewith

• US 10,805,244 B2
• Filed: 07/16/2015
• Issued: 10/13/2020
• 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.
• Primary Examiner(s): Follansbee, John A
• Assistant Examiner(s): Do, Lam T
• Application Number:
  US14/801,609
• Publication Number:
  US 20170019356A1
• Time in Patent Office: 1,916 Days
• 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;

storing chat data for each of a plurality of previous chat sessions in a chat database of previous chat sessions;

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

searching the chat database of previous chat sessions, based on the chat request, to identify a subset of the plurality of previous chat sessions that includes multiple ones of the plurality of previous chat sessions that correspond to the chat request, wherein the subset of the plurality of previous chat sessions corresponding to the chat request are associated with other users, wherein identifying the subset of the plurality of previous chat sessions corresponding to the chat request includes;

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

determining that the confidence corresponding to the subset of the plurality of previous chat sessions exceeds a confidence threshold;

when the subset of the plurality of previous chat sessions includes at least a predetermined number of previous chat sessions that are associated with other users;

determining a ranking of the subset of the plurality of previous chat sessions based on the confidence determined for each of the subset of the plurality of previous chat sessions;

selecting exactly the predetermined number of highest ranked previous sessions from the subset of the plurality of previous chat sessions in accordance with the ranking;

retrieving a set of multiple chat data by retrieving chat data corresponding to only chat data of the exactly the predetermined number of highest ranked previous chat sessions from the chat database; and

sending the set of multiple chat data to the client device; and

when less than the predetermined number of previous chat sessions corresponding to the chat request are identified in the subset of the plurality of previous chat sessions;

establishing a chat session between the user and a live agent when less than the predetermined number of previous chat sessions corresponding to the chat request are identified in the subset of the plurality of previous chat sessions; and

adding chat data for the chat session between the user and the live agent to the chat database upon completion of the chat session between the user and the live agent.

2. The service platform of claim 1, wherein a media format of the chat session between the user and the live agent is controlled via an agent terminal associated with the live agent, further comprising:

facilitating operation of the chat session between the user and the live agent via a first media; and

escalating the chat session between the user and the live agent to operate via a second media;

wherein the first media includes text, and wherein the second media includes voice and video.

3. The service platform of claim 1, wherein determining the ranking of the subset of the plurality of previous chat sessions is further based on at least one of:

demographics of the user, or geographic location of the client device.

4. The service platform of claim 1, wherein the chat data of each of the plurality of previous chat sessions in the chat database includes text corresponding to each of the plurality of previous chat sessions, wherein searching the chat database includes identifying at least one word associated with the chat request and text mining the chat data of the plurality of previous chat sessions in the chat database based on the at least one word, and wherein identifying the subset of the plurality of previous chat sessions 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 subset of the plurality of previous chat sessions.

5. The service platform of claim 1, wherein the chat data for each of the plurality of previous chat sessions includes text collected in each of the plurality of previous chat sessions, and wherein each of the set of multiple chat data includes text collected in a corresponding one of the subset of the plurality of previous chat sessions.

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

collecting chat data associated with the chat session between the user and the live agent;

anonymizing the chat data associated with the chat session;

cleaning the chat data to improve readability and to remove inappropriate content, wherein the anonymized and cleaned chat data is added the chat database; and

retrieving the chat data corresponding to the chat session between the user and the live agent and sending the chat data to another client device for review by a subsequent user based on another chat request received from the another client device associated with the subsequent user.

7. The service platform of claim 1, wherein sending the chat data to the client device includes:

sending each of the set of multiple chat data to the client device one at a time for review by the user in accordance with an automated chat session; and

terminating the automated chat session in response to a user indication by the user that the chat request has been satisfied.

8. 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.

9. A method comprising:

establishing a plurality of chat sessions;

storing chat data for a subset of the plurality of chat sessions in a chat database of previous chat sessions as a plurality of previous chat sessions based on completion of each of the plurality of chat sessions;

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

searching the chat database of previous chat sessions, based on the chat request, to identify a subset of the plurality of previous chat sessions that includes multiple ones of the plurality of previous chat sessions that correspond to the chat request, wherein the subset of the plurality of previous chat sessions corresponding to the chat request are associated with other users, wherein identifying the subset of the plurality of previous chat sessions corresponding to the chat request includes;

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

determining that the confidence corresponding to the subset of the plurality of previous chat sessions exceeds a confidence threshold;

when the subset of the plurality of previous chat sessions includes at least a predetermined number of previous chat sessions that are associated with other users;

determining a ranking of the subset of the plurality of previous chat sessions based on the confidence determined for each of the subset of the plurality of previous chat sessions;

selecting exactly the predetermined number of highest ranked previous sessions from the subset of the plurality of previous chat sessions in accordance with the ranking;

retrieving a set of chat data by retrieving chat data corresponding to only chat data of the exactly the predetermined number of highest ranked previous chat sessions from the chat database; and

sending the set of chat data to the client device; and

when less than the predetermined number of previous chat sessions corresponding to the chat request are identified in the subset of the plurality of previous chat sessions;

establishing a chat session between the user and a live agent when less than the predetermined number of previous chat sessions corresponding to the chat request are identified in the subset of the plurality of previous chat sessions; and

adding chat data for the chat session between the user and the live agent to the chat database upon completion of the chat session between the user and the live agent.

10. The method of claim 9 wherein storing chat data for one of the subset of the plurality of chat sessions in the chat database of previous chat sessions is based on a corresponding live agent identifying the one of the subset of the plurality of chat sessions as a candidate for inclusion in the chat database via an agent terminal.

11. The method of claim 9, wherein a media format of the chat session between the user and the live agent is controlled via an agent terminal associated with the live agent, further comprising:

facilitating operation of the chat session between the user and the live agent via a first media; and

escalating the chat session between the user and the live agent to operate via a second media;

wherein the first media includes text, and wherein the second media includes voice and video.

12. The method of claim 9 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.

13. The method of claim 12 wherein identifying the subset of 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 subset of the plurality of previous chat sessions.

14. The method of claim 9 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 the live agent in response to the user indication.

15. The method of claim 14 further comprising:

collecting chat data associated with the chat session between the user and the live agent; and

anonymizing the chat data associated with the chat session, wherein the anonymized chat data is added the chat database.

16. The method of claim 15, further comprising selecting the chat data associated with the chat session between the user and the live agent for storage in the chat database based on at least one policy related to agent performance of the live agent.

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

storing chat data for each of a plurality of previous chat sessions in a chat database of previous chat sessions;

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

searching the chat database of previous chat sessions, based on the chat request, to identify a subset of the plurality of previous chat sessions that includes multiple ones of the plurality of previous chat sessions that correspond to the chat request, wherein the subset of the plurality of previous chat sessions corresponding to the chat request are associated with other users, wherein identifying the subset of the plurality of previous chat sessions corresponding to the chat request includes;

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

determining that the confidence corresponding to the subset of the plurality of previous chat sessions exceeds a confidence threshold;

when the subset of the plurality of previous chat sessions includes at least a predetermined number of previous chat sessions that are associated with other users;

determining a ranking of the subset of the plurality of previous chat sessions based on the confidence determined for each of the subset of the plurality of previous chat sessions;

selecting exactly the predetermined number of highest ranked previous sessions from the subset of the plurality of previous chat sessions in accordance with the ranking;

retrieving a set of chat data by retrieving chat data corresponding to only chat data of the exactly the predetermined number of highest ranked previous chat sessions from the chat database; and

sending the set of chat data to the client device; and

when less than the predetermined number of previous chat sessions corresponding to the chat request are identified in the subset of the plurality of previous chat sessions;

establishing a chat session between the user and a live agent when less than the predetermined number of previous chat sessions corresponding to the chat request are identified in the subset of the plurality of previous chat sessions; and

adding chat data for the chat session between the user and the live agent to the chat database upon completion of the chat session between the user and the live agent.