Method and apparatus for analyzing leakage from chat to voice

• US 9,350,863 B2
• Filed: 04/28/2015
• Issued: 05/24/2016
• Est. Priority Date: 01/08/2013
• Status: Active Grant

• Current Assignee: [24]7.ai, Inc.
• Original Assignee: 24/7 Customer Incorporated
• Inventors: Sri, R. Mathangi, Hardeniya, Nitin Kumar, Srivastava, Vaibhav, Vijayaraghavan, Ravi
• Primary Examiner(s): NGUYEN, QUYNH H
• Application Number:
  US14/698,709
• Publication Number:
  US 20150237206A1
• Time in Patent Office: 392 Days
• Field of Search: 379/93.17, 709/229
• US Class Current: 1/1
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: H04M 2207/203 composed of PSTN and data network, e.g. the Internet
• CPC Class Codes: H04M 3/5133 Operator terminal details
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5191 interacting with the Internet
• CPC Class Codes: H04M 7/0045 where the text-based messaging service is an instant messaging service

Abstract

The customer experience is enhanced by detecting leakage-to-voice from chats and providing recommendations to operations, chat agents, and customers. A chat is classified into leakage-to-voice or leakage-to-text chat and actionable recommendations are then provided to operations, chat agents, and customers based on the leakage information. Once leakage is identified, various other insights are extracted from chats and such insights are fed into the knowledge-base. Such insights also used in agent training and are provided to chat agents as recommendations. This results in a better customer experience.

Claims

1. A computer implemented method for improving a customer experience, comprising:

receiving information stored in a knowledge base, said information generated by applying a model based on chat-related information and chat leakage information, said model generated by analyzing said chat leakage information to obtain said chat-related information from at least one chat session between a customer and an agent to determine factors that have contributed to said chat leakage and by identifying customer leakage information from said chat session to another channel, said analyzing including applying specific filters for text chat categorization; and

using said information to train agents and make recommendations to agents and managers for presentation to a customer to improve the customer'"'"'s experience and accordingly prevent or reduce chat leakage.

2. The method of claim 1, wherein chats that are identified as having leakage are classified into leakage-to-voice or leakage-to-text chats.

3. The method of claim 1, further comprising:

said chat agent performing any of providing solutions to customer issues and redirecting said chat to other channels to resolve said customer issues.

4. The method of claim 1, further comprising:

said chat agent checking information related to the customer, said information comprising any of the customer'"'"'s journey, the customer'"'"'s communication history, the customer'"'"'s interests, and other information associated with the customer.

5. The method of claim 4, wherein the customer'"'"'s journey comprises any of:

identity of chat agents, either a voice or a text chat agent, who interacted with the customer before the customer visited a specific chat agent;

a path taken by the customer to reach a chat agent;

the customer'"'"'s Web-log journey; and

other customer information.

6. The method of claim 4, wherein the customer'"'"'s journey comprises any of a virtual journey, a literal journey, an assisted journey, a guided journey, and a combination thereof.

7. The method of claim 1, wherein a channel to which leakage occurs is identified.

8. The method of claim 1, wherein sample production data is used to build said model.

9. The method of claim 1, wherein a chat text is used to build an anchor.

10. The method of claim 9, wherein channel names referred in the chat text are used to build said anchor.

11. The method of claim 9, wherein, after said anchor is built, positive hits generated during anchor building in connection with edit-distance are used to obtain a temporary categorization of a team/department.

12. The method of claim 11, wherein business analysts using business sense for each team/department and customer needs perform an initial grouping of a portion of teams/departments.

13. The method of claim 11, wherein a service layer is applied to fine tune category mapping of said team/department;

and a model that includes a final category for each team/department name is generated.

14. The method of claim 13, wherein said category comprises a categories grouping for each team/department name based on edit distance.

15. The method of claim 11, wherein, after said anchor is built, said chat data is categorized into said team/department names using said filters.

16. The method of claim 15, wherein specific filters are applied for voice categorization.

17. The method of claim 15, wherein said filters and said team/department names occur in a periphery of a predefined number of words;

wherein said voice and text chat filters create dummy data having a periphery of said predefined number of words, instead of using an entire agent chat text; and

wherein said dummy data are provided with a dummy identifier.

18. The method of claim 15, wherein a priority index is provided to control each of said filters.

19. The method of claim 18, wherein a grid editor provides said priority to said filters.

20. The method of claim 9, wherein said chat text is any of text provided by said customer and by said agent.

21. The method of claim 15, wherein a noun extraction process is performed in which a part-of-speech (pos) tagger is used to tag lines in the chat based on pos information.

22. The method of claim 21, wherein a first noun from the line of chat text is extracted based on the hypothesis that most of the time the product name is mentioned as the first noun.

23. The method of claim 15, wherein a concordance words with the anchors is looked-up;

wherein said concordance comprises any of direction (left window/right window/around window) and the window size; and

wherein based on the direction, positive hits are generated by the anchor building process.

24. The method of claim 15, wherein a noun phrase extraction process is performed in which a part-of-speech (pos) tagger is used to tag lines in the chat text based on pos information.

25. The method of claim 24, wherein a first noun from the line of chat text is extracted based on the hypothesis that most of the time the product name is mentioned as the first noun.

26. The method of claim 15, wherein a stop word removal process is performed to remove stop words from the chat text.

27. The method of claim 15, wherein a get unique word process is performed to remove multiple occurrences of the same team/department names.

28. The method of claim 15, wherein a surface-similarity process is performed in which a surface similarity measure is used to determine edit-distance at a word level or at a character level;

and

wherein team/department names are grouped in a category of the team/department based on similar words.

29. The method of claim 15, wherein the agent'"'"'s names are included as a variable for use in evaluating the agents'"'"' performance.

30. The method of claim 29, wherein chat agent performance data is mapped with a customer satisfaction score (CSAT) driver and;

based thereon, actionable recommendations are provided to operations and agents.

31. The method of claim 1, wherein contextual information is passed to a voice channel.

32. The method of claim 1, wherein insights are passed from one channel to a next channel.

33. The method of claim 1, wherein leakage is detected and substantially all contextual and other relevant information is extracted from a chat interaction when there is a customer dropout during a chat and the agent cannot solve the customer problem;

and

wherein said relevant information is summarized and said summarized information is passed to a voice referral.

34. The method of claim 1, wherein information regarding leakage is passed to a Web-log journey to predict leakage at the start of a subsequent customer journey when leakage in a current chat is detected;

and

wherein recommendations are provided to said agent at the start of said subsequent chat, based on leakage detected in said current chat.

35. The method of claim 1, wherein said model is used to provide off line training analysis.

36. An apparatus for improving a customer experience, comprising:

a processor implemented user interface configured for receiving information stored in a knowledge base, said information generated by applying a model based on chat-related information and chat leakage information, said model generated by analyzing said chat leakage information to obtain said chat-related information from at least one chat session between a customer and an agent to determine factors that have contributed to said chat leakage and by identifying customer leakage information from said chat session to another channel, said analyzing including applying specific filters for text chat categorization; and

wherein said information is used to train agents and make recommendations to agents and managers for presentation to a customer to improve the customer'"'"'s experience and accordingly prevent or reduce chat leakage.