System and method for aiding product design and quantifying acceptance

• US 8,423,323 B2
• Filed: 09/21/2006
• Issued: 04/16/2013
• Est. Priority Date: 09/21/2005
• Status: Expired due to Fees

• Current Assignee: Icosystem Corp.
• Original Assignee: Icosystem Corp.
• Inventors: Bonabeau, Eric
• Primary Examiner(s): Alhija, Saif
• Assistant Examiner(s): GEBRESILASSIE, KIBROM K
• Application Number:
  US11/534,035
• Publication Number:
  US 20070067212A1
• Time in Patent Office: 2,399 Days
• Field of Search: 703/1, 703/2, 705/10, 705/26, 707/6
• US Class Current: 703/1
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Methods and systems for designing new products such as perfumes comprise having existing products in a product field rated according to product attributes; assigning each of the existing products a location in a multi-dimensional space according to the ratings; locating the existing products in a second multi-dimensional space; choosing reference products, which sample the second space, from among the existing products; having a consumer survey of the reference products conducted; creating a map of consumer responses in the second multi-dimensional space; and designing the new product based on the map of consumer responses.

Claims

1. In a computer system comprising at least one input device, at least one output device, and at least one processor, a method for designing a new product, comprising:

a) receiving through the at least one input device ratings of a first plurality of existing products in a product field according to a second plurality of attributes;

b) assigning in the at least one processor each of said first plurality of existing products a location in a first space having said second plurality of dimensions, according to said existing product'"'"'s ratings with respect to said second plurality of attributes;

c) locating said first plurality of existing products in a second space of a third plurality of dimensions using multidimensional scaling;

d) choosing a fourth plurality of reference products which sample said second space of said third plurality of dimensions, from among said first plurality of existing products;

e) receiving through the at least one input device consumer responses to a consumer survey concerning said fourth plurality of reference products;

f) creating in the at least one processor a map of consumer responses in said second space of said third plurality of dimensions;

g) based on said map of consumer responses in said second space of said third plurality of dimensions, finding by means of the at least one processor at least one desirable location in said first space having said second plurality of dimensions; and

h) outputting through the at least one output device an identification of said at least one desirable location, whereby said new product is designed based upon said map of consumer responses;

wherein said second plurality of dimensions is equal in quantity to said second plurality of attributes and greater in quantity than said third plurality of dimensions.

2. The method of claim 1, wherein the product field is perfumes.

3. The method of claim 1, wherein each rating of one of said first plurality of existing products according to one of said second plurality of attributes of said existing product is a number from 0 to 1.

4. The method of claim 1, wherein said second plurality of ratings of each of said first plurality of existing products according to said second plurality of attributes of said existing product are normalized.

5. The method of claim 1, wherein the step of locating said first plurality of existing products in said second space of said third plurality of dimensions further comprises using interactive evolutionary computing.

6. The method of claim 1, wherein said fourth plurality of reference products which sample said second space of said third plurality of dimensions is chosen from among said first plurality of existing products using bootstrapping.

7. The method of claim 1, wherein said consumer survey comprises information about at least one demographic variable of a plurality of surveyed consumers.

8. The method of claim 1, wherein said map of consumer responses comprises a map of consumer ratings of one characteristic of said fourth plurality of reference products.

9. The method of claim 8, wherein said one characteristic is consumer acceptance of said reference products.

10. The method of claim 8, wherein said map of consumer ratings of one characteristic of said fourth plurality of reference products is created by using a graphical method.

11. The method of claim 10, wherein the graphical method is a neural network.

12. The method of claim 8, wherein said map of consumer ratings of one characteristic of said fourth plurality of reference products is created by using a genetic algorithm.

13. The method of claim 8, wherein said step of finding at least one desirable location in said first space having said second plurality of dimensions comprises:

a) locating an unpopulated region in said second space of said third plurality of dimensions, wherein a consumer rating of said one characteristic is predicted by said map to be high, and

b) locating a corresponding region in said first space having said second plurality of dimensions.

14. The method of claim 13, wherein said step of locating said corresponding region in said first space having said second plurality of dimensions comprises using multidimensional scaling.

15. The method of claim 14, wherein said step of locating said corresponding region in said first space having said second plurality of dimensions further comprises using a genetic algorithm.

16. The method of claim 8, wherein said step of finding at least one desirable location in said first space having said second plurality of dimensions comprises:

a) receiving by means of the at least one input device an initial design for said new product comprising values for said new product with respect to each of said second plurality of product attributes;

b) locating said initial design in said second space of said third plurality of dimensions;

c) finding a location in said second space of said third plurality of dimensions which is in a vicinity of said initial design and which is predicted by said map to have a greater value of said consumer rating of a desired product characteristic than said initial design; and

d) finding a corresponding location in said first space having said second plurality of dimensions.

17. The method of claim 16, wherein the step of locating said initial design in said second space of said third plurality of dimensions comprises using-multidimensional scaling.

18. The method of claim 16, wherein the step of locating said initial design in said second space of said third plurality of dimensions comprises using interpolation.

19. The method of claim 16, further wherein the step of finding said location in said second space of said third plurality of dimensions which is in said vicinity of said initial design and which is predicted by said map to have said greater value of said consumer rating of said desired product characteristic comprises using a gradient ascending algorithm.

20. The method of claim 19, wherein the step of finding said location in said second space of said third plurality of dimensions which is in said vicinity of said initial design and which is predicted by said map to have said greater value of said consumer rating of said desired product characteristic comprises using a genetic algorithm.

21. The method of claim 16, wherein the step of locating said corresponding location in said first space having said second plurality of dimensions comprises using multidimensional scaling.

22. The method of claim 21, wherein the step of locating said corresponding location in said first space having said second plurality of dimensions further comprises using a genetic algorithm.

23. The method of claim 1, wherein said map of consumer responses comprises a map of consumer ratings of a plurality of characteristics of said fourth plurality of reference products.

24. The method of claim 23, further comprising generating said map of consumer ratings of said plurality of characteristics of said fourth plurality of reference products in said first space having said second plurality of dimensions based upon said map of consumer ratings of said plurality of characteristics of said fourth plurality of reference products in said second space of said third plurality of dimensions.

25. A system, comprising at least one processor in communications with at least one input device and at least one output device, the at least one processor having instructions for causing the at least one processor to:

a) receive through the at least one input device ratings of a first plurality of existing products in a product field according to a second plurality of product attributes,

b) assign each of said first plurality of existing products a location in a first space having said second plurality of dimensions, according to said existing product'"'"'s ratings with respect to said second plurality of product attributes;

c) locate said first plurality of existing products in a second space of a third plurality of dimensions using multidimensional scaling;

d) choose a fourth plurality of reference products which sample said second space of said third plurality of dimensions, from among said first plurality of existing products;

e) receive through the at least one input device consumer responses to a consumer survey concerning said fourth plurality of reference products,

f) create in said second space of said third plurality of dimensions a map of said consumer responses to said consumer survey concerning said fourth plurality of reference products;

g) based on said map of consumer responses in said second space of said third plurality of dimensions, find at least one desirable location in said first space having said second plurality of dimensions; and

h) output through the at least one output device an identification of said at least one desirable location;

wherein said second plurality of dimensions is equal in quantity to said second plurality of attributes and greater in quantity than said third plurality of dimensions.

26. The system of claim 25, wherein the product field is perfumes.

27. The system of claim 25, wherein each rating of one of said first plurality of existing products according to one of said second plurality of product attributes is a number from 0 to 1.

28. The system of claim 25, wherein said second plurality of ratings of each of said first plurality of existing products according to said second plurality of product attributes are normalized.

29. The system of claim 25, wherein the step locating said first plurality of existing products in said second space of said third plurality of dimensions further comprises using interactive evolutionary computing.

30. The system of claim 25, wherein said fourth plurality of reference products which sample said second space of said third plurality of dimensions is chosen from among said first plurality of existing products using bootstrapping.

31. The system of claim 25, wherein said consumer survey comprises information about at least one demographic variable of a plurality of surveyed consumers.

32. The system of claim 25, wherein said map of consumer responses comprises a map of consumer ratings of one characteristic of said fourth plurality of reference products.

33. The system of claim 32, wherein said one characteristic is consumer acceptance of said reference products.

34. The system of claim 32, wherein said map of consumer ratings of one characteristic of said fourth plurality of reference products is created by using a graphical method.

35. The system of claim 34, wherein the graphical method is a neural network.

36. The system of claim 32, wherein said map of consumer ratings of one characteristic of said fourth plurality of reference products is created by using a genetic algorithm.

37. The system of claim 32, wherein said step of finding at least one desirable location in said first space having said second plurality of dimensions comprises:

a) locating an unpopulated region in said second space of said third plurality of dimensions, wherein a consumer rating of said one characteristic is predicted by said map to be high, and

b) locating a corresponding region in said first space having said second plurality of dimensions.

38. The system of claim 37, wherein said step of locating said corresponding region in said first space having said second plurality of dimensions comprises using multidimensional scaling.

39. The system of claim 38, wherein said step of locating said corresponding region in said first space having said second plurality of dimensions further comprises using a genetic algorithm.

40. The system of claim 32, wherein said step of finding at least one desirable location in said first space having said second plurality of dimensions by comprises:

a) receiving by means of the at least one input device an initial design for a new product comprising values for said new product with respect to each of said second plurality of product attributes;

b) locating said initial design in said second space of said third plurality of dimensions;

c) finding a location in said second space of said third plurality of dimensions which is in a vicinity of said initial design and which is predicted by said map to have a greater value of said consumer rating of a desired product characteristic than said initial design; and

d) finding a corresponding location in said first space having said second plurality of dimensions.

41. The system of claim 40, wherein the step of locating said initial design in said second space of said third plurality of dimensions comprises using multidimensional scaling.

42. The system of claim 40, wherein the step of locating said initial design in said second space of said third plurality of dimensions comprises using interpolation.

43. The system of claim 40, wherein the step of finding said location in said second space of said third plurality of dimensions which is in said vicinity of said initial design and which is predicted by said map to have said greater value of said consumer rating of said desired product characteristic comprises using a gradient ascending algorithm.

44. The system of claim 43, wherein the step of finding said location in said second space of said third plurality of dimensions which is in said vicinity of said initial design and which is predicted by said map to have said greater value of said consumer rating of said desired product characteristic comprises using a genetic algorithm.

45. The system of claim 40, wherein the step of locating said corresponding location in said first space having said second plurality of dimensions comprises using multidimensional scaling.

46. The system of claim 45, wherein the step of locating said corresponding location in said first space having said second plurality of dimensions further comprises using a genetic algorithm.

47. The system of claim 25, wherein said map of consumer responses comprises a map of consumer ratings of a plurality of characteristics of said fourth plurality of reference products.

48. The system of claim 47, further comprising the at least one processor having instructions for causing the at least one processor to generate said map of consumer ratings of said plurality of characteristics of said fourth plurality of reference products in said first space having said second plurality of dimensions based upon said map of consumer ratings of said plurality of characteristics of said fourth plurality of reference products in said second space of said third plurality of dimensions.