Expert system adapted dedicated internet access guidance engine

• US 7,031,951 B2
• Filed: 07/19/2001
• Issued: 04/18/2006
• Est. Priority Date: 07/19/2000
• Status: Active Grant

• Current Assignee: Concentrix CVG Customer Management Delaware LLC (Synnex Corporation)
• Original Assignee: Convergys Information Management Group, Inc.
• Inventors: Erickson, Charles R., Mancisidor, Rod, Gilpin, Gordon
• Primary Examiner(s): Knight, Anthony
• Assistant Examiner(s): Holmes, Michael B.
• Application Number:
  US09/909,241
• Publication Number:
  US 20020116243A1
• Time in Patent Office: 1,734 Days
• Field of Search: 706/60, 706/925, 706/8, 705/7
• US Class Current: 706/60
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence

Abstract

An expert system adapted dedicated Internet access guidance engine. The invention allows an agent to interact with a customer and to provide selection and recommendation of data network products and/or services for the customer. The invention allows for the use of agents of varying skill levels, including relatively low skill level, without suffering deleterious performance. The dedicated Internet access guidance engine is operable to perform selection and rating of Internet access products and/or services to provide a solution that meets the needs of a customer. The dedicated Internet access guidance engine is operable to select recommended solutions from among a number of potential solutions that may include compatible solutions. The dedicated Internet access guidance engine is one of the underlying engines within the expert system that allows the agent to provide real time interaction with a customer and to provide a real time recommended solution to that customer.

Claims

1. A method for recommending a product to a customer, the method comprising:

a) presenting a set of problem questions to a customer, the set of problem questions including one or more questions presented to determine one or more product needs of the customer;

b) receiving a set of problem answers from the customer, the set of problem answers including one or more answers to the set of problem questions, the one or more answers corresponding to the one or more product needs of the customer;

c) determining a problem domain based at least in part on the set of problem answers;

d) presenting a set of needs questions to the customer, the set of needs questions including one or more questions corresponding to the determined problem domain;

e) receiving a set of needs answers from the customer, the set of needs answers including one or more answers to the set of needs questions, each needs answer corresponding to at least one of the one or more product needs of the customer;

f) transforming at least a part of the set of needs answers into one or more values to represent a set of product traits, the one or more values comprising at least one of a fuzzy value or a crisp value, at least a portion of the one or more values corresponding to at least one of the one or more product needs of the customer;

g) processing at least one of the one or more values to produce one or more product recommendations, wherein the one or more product recommendations correspond to the determined problem domain, wherein at least a portion of the step of processing is performed on a computer processor using fuzzy logic; and

h) providing at least one of the one or more product recommendations to the customer.

2. The method of claim 1, wherein at least one of the set of problem questions or the set of needs questions is presented to the customer in part by a human agent.

3. The method of claim 1, wherein the step of providing at least one of the one or more product recommendations to the customer is performed in part by a human agent.

4. The method of claim 1, further comprising:

providing one or more explanations to the customer, at least one of the one or more explanations corresponding to at least one of the one or more products being recommended, the at least one of the one or more explanations comprising at least one reason as to why a corresponding product is being recommended.

5. The method of claim 1, wherein the one or more product recommendations includes one or more products that are designated as not recommended.

6. The method of claim 5, further comprising:

providing one or more explanations to the customer, at least one of the one or more explanations corresponding to the one or more products that are designated as not recommended, the at least one of the one or more explanations comprising at least one reason as to why a corresponding product is being not recommended.

7. The method of claim 1, wherein the step of processing further comprises rating each of the products being recommended according to at least a portion of the needs answers.

8. The method of claim 7, wherein a certain number of product traits correspond to the one or more product needs of the customer, wherein the step of rating comprises determining the certain number of product traits corresponding to the one or more product needs of the customer.

9. The method of claim 8, wherein a plurality of product recommendations are produced, the step of processing further comprising providing a ranking for each product of the produced product recommendations, wherein the ranking is conducted in accordance with the determined certain number of product traits corresponding to the one or more product needs of the customer.

10. The method of claim 7, wherein each rating is selected from the group consisting of recommended, compatible, and not recommended.

11. The method of claim 1, wherein the one or more needs of the customer comprise telecommunications needs relating to at least one of cost, ability to host a website, reliability, or bandwidth.

12. The method of claim 11, wherein the needs relating to bandwidth include needs relating to at least one of e-mail, web browsing, website hosting, file transfer, or voice over internet protocol applications.

13. The method of claim 11, wherein the needs relating to reliability are characterized by values including at least one of a maximum value indicative of internet use by the customer or a maximum value indicative of a data type transmitted via the internet by the customer.

14. The method of claim 1, wherein at least one of the values is a crisp value comprising at least one of an integer value or a Boolean value.

15. The method of claim 1, wherein the step of transforming further comprises transforming at least one crisp value to a transformed fuzzy value to represent at least one of the product traits with the transformed fuzzy value.

16. The method of claim 1, wherein each trait of the product traits is defined by z fuzzy sets and s fuzzy sets.

17. The method of claim 1, wherein each customer has a physical location, wherein the step of processing includes processing information corresponding to the physical location of the customer in addition to the at least one of the one or more values.

18. The method of claim 1, wherein the step of processing further comprises accessing one or more product catalogs to compare at least a portion of the values to information stored in the one or more product catalogs.

19. The method of claim 18, wherein each product catalog comprises a database comprising information relating to a plurality of products.

20. The method of claim 19, wherein the information comprises available products, supported products, and compatible products.

21. The method of claim 19, wherein each product is provided by a product provider, wherein the catalog is configured to permit each product provider to provide updates to the information corresponding to at least one product provided by the product provider.

22. The method of claim 1, further comprising adding customer information to a customer profile, the customer profile being stored in a computer readable medium.

23. The method of claim 22, wherein the customer information comprises at least one of the one or more product needs of the customer, financial information about the customer, and products being used by the customer.

24. The method of claim 1, wherein the step of processing further comprises accessing a customer profile associated with the customer, the customer profile comprising information relating to the customer, wherein the customer profile is stored in a computer readable medium, wherein the one or more product recommendations are produced at least in part in accordance with the information in the customer profile.

25. The method of claim 1, further comprising attributing a weight to at least one of the one or more values.

26. The method of claim 25, wherein the weight represents a weight accorded by the customer to the product need corresponding to the weighted value.

27. A method for recommending a product to a customer, the method comprising:

a) presenting a GUI to a human agent, the GUI including one or more fields for entry by the agent of information relating to a customer'"'"'s product needs;

b) receiving input from the agent via the GUI, the input comprising information relating to a customer'"'"'s product needs;

c) processing the received input through fuzzy logic to produce one or more product recommendations corresponding to the customer'"'"'s product needs, the step of processing comprising transforming at least a part of the information relating to a customer'"'"'s product needs into at least one of a fuzzy value or a crisp value; and

d) displaying an output to the agent via the GUI, the output comprising the one or more product recommendations.

28. The method of claim 27, wherein the output further comprises one or more explanations, each explanation corresponding to at least one of the one or more product recommendations.

29. The method of claim 27, wherein the customer'"'"'s product needs and the one or more product recommendations relate to telecommunications.

30. The method of claim 27, further comprising attributing a weight to at least one of the at least one of a fuzzy value or a crisp value.

32. The method of claim 29, wherein the output further comprises one or more explanations, each explanation corresponding to at least one of the one or more product recommendations.

33. The method of claim 29, wherein the customer'"'"'s product needs and the one or more product recommendations relate to telecommunications.

31. A method for recommending a product to a customer, the method comprising:

a) presenting a set of questions to a customer via a human agent, the set of questions comprising one or more questions relating to the customer'"'"'s product needs;

b) receiving a set of answers from the customer via the agent in response to the set of questions, the answers comprising one or more answers relating to the customer'"'"'s product needs;

c) entering information corresponding to the set of answers into a computer system via a GUI, the information being entered by the agent;

d) receiving output from the computer system, the output being displayed to the agent via the GUI, the output being produced by the computer system, wherein the output is produced by the computer system via a process comprising;

i) transforming at least a part of the set of answers into one or more values to represent a set of product traits, the one or more values comprising at least one of a fuzzy value or a crisp value, at least a portion of the one or more values corresponding to at least one of the one or more product needs of the customer, and

ii) processing at least one of the one or more values to produce one or more product recommendations, wherein at least a portion of the step of processing is performed on a computer processor using fuzzy logic within the computer system,

wherein the output comprises one or more product recommendations corresponding to the customer'"'"'s needs; and

e) presenting at least a portion of the output to the customer via the agent.