System for conditional answering of requests

• US 7,774,292 B2
• Filed: 11/09/2004
• Issued: 08/10/2010
• Est. Priority Date: 11/10/2003
• Status: Active Grant

• Current Assignee: Avaya Incorporated
• Original Assignee: Conversive, Inc.
• Inventors: Williams, Robert W., Rappaport, Robert, McBride, Aaron Joseph, Brennan, Christopher, Romero, Jeremy
• Primary Examiner(s): Sparks; Donald
• Assistant Examiner(s): Tran; Mai T
• Application Number:
  US10/984,362
• Publication Number:
  US 20050125370A1
• Time in Patent Office: 2,100 Days
• Field of Search: 706/47, 704/9, 704/270, 704/275
• US Class Current: 706/47
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

Disclosed is a method and system for the use of virtual robots (Bots) to assist in the answering of inquiries from persons over the Internet, telephone, wireless, or other form of electrical, digital, or electronic communication. Such method and system consists of (1) a Bot processor consisting of (a) a connection interface capable of receiving, directly or indirectly, inputs from a user in natural or machine language, which the Bot processor then responds to in natural or machine language, and (b) an engine capable of recognizing an input and providing a response; and (2) a service desk consisting of (a) a human being, (b) a connection interface that connects directly or indirectly to the Bot processor and to the front end, and (c) a display where the human being can see, in humanly comprehensible form, information transmitted by the user and/or the Bot processor.

Claims

1. A computer system that provides a response to an input entered by a user in a system for autonomously processing the input, comprising:

a service desk comprised of one or more agents;

a connection interface;

an engine configured to;

receive the input from the user via the connection interface;

generate a first provisional response in response to a criteria being triggered, wherein the criteria is a load on the system as defined by an amount of the one or more agents available to communicate with the user and transmit the first provisional response to the user;

generate a second provisional response if the first provisional response has not been generated;

recognize the input based upon a rule;

retrieve a pattern of the rule that most closely matches the input, wherein the closeness of matching is based upon a number of words that are common between the input and the pattern;

obtain a confidence factor of the closeness of matching by;

getting instructions relating to message traffic density, wherein message traffic density is defined as the amount of messages routed within the system; and

getting code and executing the code to compare the pattern to the input;

compare the confidence factor to a designated level and;

designate the second provisional response as a final response when the confidence factor is greater than the designated level and send the final response to the user;

transmit the second provisional response to the service desk when the confidence factor is less than the designated level, wherein the service desk is configured to;

receive the second provisional response;

receive input from the one or more agents, wherein the agent input causes the engine to;

 

designate that the second provisional response is the final response;

or

 

edit the second provisional response into the final response;

or

 

discard the second provisional response and designate an alternative response as the final response;

send the final response to the engine; and

transmit the final response to the user;

a front end section connected to the connection interface;

a bot processor including the engine and the connection interface, wherein the service desk is connected between the front end section and the bot processor; and

a message distributor interconnecting the front end section, the bot processor, and the service desk, wherein the message distributor routes the messages therebetween.

2. The computer system according to claim 1, wherein the service desk further includes a display.

3. The computer system according to claim 1, wherein the criteria further includes a specified time period.

4. The computer system according to claim 1, wherein the criteria further includes an event.

5. The computer system according to claim 1, wherein the criteria further includes a system setting.

6. The computer system according to claim 1, wherein determining the closeness of matching is further based upon a number of letters that are common between the input and the pattern.

7. The computer system according to claim 1, wherein determining the closeness of matching is further based upon a number of synonyms that are common between the input and the pattern.

8. The computer system according to claim 1, wherein determining the closeness of matching is further based upon a number of regular expressions that are common between the input and the pattern.

9. The computer system according to claim 1, wherein the step of getting the confidence factor further includes the step of producing the confidence factor based upon a value assigned to the input, the response, the rule, or the pattern.

10. The computer system according to claim 9, wherein the value is a constant.

11. The computer system according to claim 9, wherein the value is determined by an algorithm assigned to the input, the response, the rule, or the pattern, respectively.

12. The computer system according to claim 9, wherein more than one value is used in producing the confidence factor.