Recursive Adaptive Interaction Management System

• US 20090171668A1
• Filed: 12/28/2007
• Published: 07/02/2009
• Est. Priority Date: 12/28/2007
• Status: Active Grant

• Current Assignee: Genesys Cloud Services Incorporated
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Sneyders, Dave, Galvin, Brian, Perlmutter, S. Michael
• Granted Patent: US 9,092,733 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 25/72 for transmitting results of analysis
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 3/5133 Operator terminal details
• CPC Class Codes: H04M 3/5141 Details of processing calls and other types of contacts in an unified manner unified messaging in packet-switching networks H04L51/56
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

Abstract

A management system for guiding an agent in a media-specific dialogue has a conversion engine for instantiating ongoing dialogue as machine-readable text, if the dialogue is in voice media, a context analysis engine for determining facts from the text, a rules engine for asserting rules based on fact input, and a presentation engine for presenting information to the agent to guide the agent in the dialogue. The context analysis engine passes determined facts to the rules engine, which selects and asserts to the presentation engine rules based on the facts, and the presentation engine provides periodically updated guidance to the agent based on the rules asserted.

Claims

1. A management system for guiding an agent in a media-specific dialogue, comprising:

a conversion engine for instantiating ongoing dialogue as machine-readable text, if the dialogue is in voice media;

a context analysis engine for determining facts from the text;

a rules engine for asserting rules based on fact input; and

a presentation engine for presenting information to the agent to guide the agent in the dialogue;

wherein the context analysis engine passes determined facts to the rules engine, which selects and asserts to the presentation engine rules based on the facts, and the presentation engine provides periodically updated guidance to the agent based on the rules asserted.

2. The system of claim 1 wherein a first script is provided to the agent as the dialogue begins, the guidance influences the dialogue, and the system continues to analyze and provide updated guidance during the dialogue.

3. The system of claim 1 wherein the agent is enabled to configure ways in which the presentation engine presents information.

4. The system of claim 1 comprising a back-end process wherein facts determined from the dialogue are used to elicit further information, processing based on the further information is conducted while dialogue continues, and after processing new information is presented to the agent.

5. The system of claim 1 wherein characteristics known for a specific agent are used in preparing presentation to the agent.

6. The system of claim 1 wherein prompts presented to the agent are annotated with indicia indicating importance or other characteristic of the prompts,

7. The system of claim 1 wherein the agent is enabled to tag prompts with feedback to the system, which feedback alters further presentation to the agent.

8. The system of claim 1 wherein analysis includes one or more indications of volume, inflection, sentence structure, rate of dialogue, other than text, and these indications are interpreted by the rules engine to select and assert rules.

9. The system of claim 1 wherein prestored knowledge of one or both of the agent and a party to the dialogue other than the agent is used to influence the content and nature of information provided to the agent.

10. The system of claim 1 wherein the agent is an interactive voice response system, and guidance to the agent is selection of voice responses by the IVR.

11. A method for guiding an agent in a media-specific dialogue, comprising steps of:

(a) if the dialogue is voice, converting the voice to machine-readable text;

(b) analyzing the text by context analysis engine and determining facts from the text;

(c) passing the determined facts to a rules engine and asserting rules based on the fact input; and

(d) presenting new guidance information to the agent to guide the agent in the dialogue.

12. The method of claim 11 wherein a first script is provided to the agent as the dialogue begins, the guidance influences the dialogue, and the system continues to analyze and provide updated guidance during the dialogue.

13. The method of claim 11 wherein the agent is enabled to configure ways in which the presentation engine presents information.

14. The method of claim 11 comprising a back-end process wherein facts determined from the dialogue are used to elicit further information, processing based on the further information is conducted while dialogue continues, and after processing new information is presented to the agent.

15. The method of claim 11 wherein characteristics known for a specific agent are used in preparing presentation to the agent.

16. The method of claim 11 wherein prompts presented to the agent are annotated with indicia indicating importance or other characteristic of the prompts,

17. The method of claim 11 wherein the agent is enabled to tag prompts with feedback to the system, which feedback alters further presentation to the agent.

18. The method of claim 11 wherein analysis includes one or more indications of volume, inflection, sentence structure, rate of dialogue, other than text, and these indications are interpreted by the rules engine to select and assert rules.

19. The method of claim 11 wherein prestored knowledge of one or both of the agent and a party to the dialogue other than the agent is used to influence the content and nature of information provided to the agent.

20. The method of claim 11 wherein the agent is an interactive voice response system, and guidance to the agent is selection of voice responses by the IVR.