Method and apparatus for evolutionary design

• US 7,016,882 B2
• Filed: 04/26/2004
• Issued: 03/21/2006
• Est. Priority Date: 11/10/2000
• Status: Expired due to Term

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: Affinnova, Inc. (RR Donnelley & Sons Company)
• Inventors: Afeyan, Noubar B., Ficici, Sevan G., Malek, Kamal M., Bufton, Nigel J.
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US10/831,881
• Publication Number:
  US 20040204957A1
• Time in Patent Office: 694 Days
• Field of Search: 706/13, 707/203, 318/568.11
• US Class Current: 706/13
• CPC Class Codes: G06F 2111/06 Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
• CPC Class Codes: G06F 2111/08 Probabilistic or stochastic CAD
• CPC Class Codes: G06F 30/00 Computer-aided design [CAD]
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The invention involves generating and presenting, typically electronically, a number of design alternatives to persons who are participating in the design, selection, or market research exercise. The participants (referred to as “selectors”) transmit data indicative of their preferences among or between the presented design alternatives, and that data is used to derive a new generation of design alternatives or proposals. The new designs are generated through the use of a computer program exploiting a genetic or evolutionary computational technique. The process is repeated, typically for many iterations or cycles.

Claims

1. A method of selecting a preferred one or a preferred group of decision objects, each decision object comprising a form of a product with a market value, each decision object further comprising a plurality of attributes, the method comprising the steps of:

(a) presenting, over an electronic network, to a plurality of selectors, one or more groups of decision objects comprising a plurality of combinations of attributes;

(b) obtaining information from a selector expressing a selector preference among the presented decision objects;

(c) using the information to evolve a derived group of decision objects comprising one or more different combinations of attributes;

(d) iterating steps (a) through (c), using a derived group from step (c) until a stopping criterion is achieved; and

(e) upon achieving the stopping criterion, selecting one or a group of preferred decision objects.

2. The method of claim 1 wherein the stopping criterion is achieved when the derived group of decision objects ceases to change significantly after an iteration.

3. The method of claim 1 wherein step (b) comprises obtaining data indicative of which decision objects within the presented group are preferred by said selector.

4. The method of claim 1 wherein step (b) comprises obtaining data indicative of which decision objects within the presented group are not preferred by said selector.

5. The method of claim 1 comprising the additional step of identifying a subset of selectors having similar preferences.

6. The method of claim 1, wherein step (b) comprises obtaining data indicative of relative preference of a selector from among presented decision objects.

7. The method of claim 1 wherein the data indicative of a preference includes data indicative of the confidence of a selector in its preference expression.

8. The method of claim 1, wherein step (b) comprises obtaining data indicative of a rating assigned to at least some of the presented decision objects by at least one selector.

9. The method of claim 1, wherein step (b) comprises obtaining data indicative of a preference as between a presented decision object and a previously presented decision object.

10. The method of claim 1, wherein different selectors are presented with different groups of decision objects.

11. The method of claim 1, wherein each selector comprises a person or a group of persons.

12. The method of claim 1 comprising using a genetic or evolutionary computational algorithm to evolve some or all of the derived decision objects.

13. The method of claim 1 wherein the decision objects comprise advertising material.

14. The method of claim 1 wherein the decision objects comprise packaging material.

15. The method of claim 1 wherein the decision objects comprise manufactured consumer goods.

16. The method of claim 1 wherein, for each iteration, each selector is presented with a group of decision objects substantially different from the groups presented to the other selectors.

17. An electronic network comprising a plurality of computers for design of one or a group of decision objects, each decision object comprising a form of a product with a market value, each decision object further comprising a plurality of attributes, the network being configured to:

(a) present one or more groups of decision objects comprising a plurality of combinations of attributes to a plurality of selectors;

(b) obtain data from a selector indicative of a selector preference from among the presented decision objects;

(c) use the data to evolve a derived group of decision objects comprising one or more different combinations of attributes;

(d) iterate steps (a) through (c), using a derived group from step (c) until a stopping criterion is achieved; and

(e) upon achieving the stopping criterion, output data informing a decision to select one or a group of preferred decision objects.

18. The network of claim 17 wherein the stopping criterion comprises convergence of a group of decision objects.

19. The network of claim 17 further configured to identify a subset of the plurality of selectors having similarity among expressed decision object preferences.

20. The network of claim 17 configured to obtain data indicative of relative preference of a selector from among presented decision objects.

21. The network of claim 17 configured to obtain data indicative of the confidence in an expressed selector preference.

22. The network of claim 17 configured to obtain data indicative of a rating assigned to at least some of the presented decision objects.

23. The network of claim 17 configured to obtain data from a selector indicative of the selector'"'"'s preference as between a presented decision object and a previously presented decision object.

24. The network of claim 17 configured to present each selector with a different group of decision objects.

25. The network of claim 17 configured to use a genetic or evolutionary computational algorithm to evolve some or all of the decision objects.

26. The network of claim 17 configured to enrich a generation of decision objects with objects comprising at least one preferred attribute.

27. The network of claim 17 configured to reduce the incidence of decision objects comprising at least one disfavored attribute.

28. The network of claim 17 configured to present groups of decision objects comprising advertising material, packaging material, or manufactured consumer goods.

29. The network of claim 17 wherein, for each iteration, each selector is presented with a group of decision objects substantially different from the groups presented to the other selectors.

30. A method of selecting one or more preferred decision objects, each decision object representing a form of a product, the method comprising the steps of:

(a) presenting, over an electronic network, to a plurality of selectors, one or more groups of the decision objects;

(b) obtaining information from a selector about the selector'"'"'s preference among the presented decision objects;

(c) using the obtained information to evolve at least some of the presented decision objects and thereby generate one or more derived decision objects;

(d) repeating steps (a) through (c), using at least some of the one or more derived decision objects from step (c), until a stopping condition is met; and

(e) upon achieving the stopping condition, selecting one or more of the remaining derived decision objects as the one or more preferred decision objects,

wherein the product comprises a mass produced good, a consumer good, a manufactured good, a service, advertising material, packaging material, apparel, footwear, a computer, a telephone, a chair, a seat, an automobile, a bicycle, a home, a building, a boat hull, or a billboard.

31. The method of claim 30 wherein step (b) comprises obtaining information indicative of which decision objects among the presented decision objects are preferred by the selector.

32. The method of claim 30 wherein step (b) comprises obtaining information indicative of which decision objects among the presented decision objects are not preferred by the selector.

33. The method of claim 30 wherein different selectors are presented with different groups of decision objects.

34. The method of claim 30 wherein each selector comprises a person or a group of persons.

35. The method of claim 30 comprising using a genetic or evolutionary computational technique to generate the derived decision objects.

36. A system for selecting one or more preferred decision objects, each decision object representing a form of a product, the method comprising the steps of:

(a) means for presenting, over an electronic network, to a plurality of selectors, one or more groups of the decision objects;

(b) means for obtaining information from a selector about the selector'"'"'s preference among the presented decision objects;

(c) means for using the obtained information to evolve at least some of the presented decision objects and thereby generate one or more derived decision objects;

(d) means for repeating the functions of means (a) through (c), using at least some of the one or more derived decision objects from step (c), until a stopping condition is met; and

(e) means for, upon achieving the stopping condition, selecting one or more of the remaining derived decision objects as the one or more preferred decision objects,

wherein the product comprises a mass produced good, a consumer good, a manufactured good, a service, advertising material, packaging material, apparel, footwear, a computer, a telephone, a chair, a seat, an automobile, a bicycle, a home, a building, a boat hull, or a billboard.

37. A system for selecting one or more preferred decision objects, each decision object representing a form of a product, the system comprising one or more server computers for communicating with a plurality of client computing devices over a computer network, each of the client computing devices having one of a plurality of selectors associated with that client computing device, the one or more server computers for presenting at least one group of the decision objects to each of the selectors via the client computing devices and over the network, the one or more server computers also for obtaining information about each of the selector'"'"'s preferences among the presented at least one group of the decision objects from each of the selectors via the client computing devices and over the network, the one or more server computers also for using the obtained information and a genetic or evolutionary computational technique to generate one or more derived decision objects, the one or more server computers also for repeating the presenting, obtaining, and using functions with at least one of the one or more derived decision objects until a stopping condition is met and then selecting one or more of the remaining derived decision objects as the one or more preferred decision objects, wherein the product comprises a mass produced good, a consumer good, a manufactured good, a service, advertising material, packaging material, apparel, footwear, a computer, a telephone, a chair, a seat, an automobile, a bicycle, a home, a building, a boat hull, or a billboard.

38. A method of identifying one or more preferred decision objects, each decision object representing a form of a product, the method comprising the steps of:

(a) presenting, over an electronic network, to a plurality of selectors, one or more groups of the decision objects;

(b) obtaining information from a selector about the selector'"'"'s preference among the decision objects of at least one of the presented groups of the decision objects;

(c) using the obtained information to generate at least one derived group of the decision objects;

(d) repeating steps (a) through (c), using the at least one derived group from step (c), until a stopping condition is met; and

(e) after achieving the stopping condition, identifying one or more of the remaining derived decision objects as the one or more preferred decision objects and effecting a sale of one or more of the forms of the product represented by the one or more preferred decision objects.

39. The method of claim 38 wherein step (b) comprises obtaining information indicative of which decision objects among the presented decision objects are preferred by the selector.

40. The method of claim 38 wherein step (b) comprises obtaining information indicative of which decision objects among the presented decision objects are not preferred by the selector.

41. The method of claim 38 wherein different selectors are presented with different groups of decision objects.

42. The method of claim 38 wherein each selector comprises a person or a group of persons.

43. The method of claim 38 comprising using a genetic or evolutionary computational technique to generate the at least one derived group of the decision objects.

44. A system for identifying one or more preferred decision objects, each decision object representing a form of a product, the method comprising the steps of:

(a) means for presenting, over an electronic network, to a plurality of selectors, one or more groups of the decision objects;

(b) means for obtaining information from a selector about the selector'"'"'s preference among the decision objects of at least one of the presented groups of the decision objects;

(c) means for using the obtained information to generate at least one derived group of the decision objects;

(d) means for repeating the functions of means (a) through (c), using the at least one derived group from step (c), until a stopping condition is met; and

(e) means for, after achieving the stopping condition, identifying one or more of the remaining derived decision objects as the one or more preferred decision objects and effecting a sale of one or more of the forms of the product represented by the one or more preferred decision objects.

45. A method of identifying a decision object from a plurality of decision objects, each decision object representing a form of a product having a market value, the method comprising the steps of:

(a) presenting, over an electronic network, to a plurality of selectors, one or more groups of the decision objects;

(b) obtaining information from a selector about the selector'"'"'s preference among the presented decision objects;

(c) using the obtained information to evolve and generate a derived group of decision objects; and

(d) repeating steps (a) through (c), using a derived group from step (c), to arrive at a decision object representing a form of the product with an optimized market value.

46. A method of selecting one or more preferred decision objects, each decision object comprising a form of a product or service, each decision object further comprising a plurality of attributes, the method comprising the steps of:

(a) presenting, over an electronic network, to a plurality of selectors, one or more groups of the decision objects;

(b) obtaining information from a selector about the selector'"'"'s preference among one of the presented groups of the decision objects;

(c) using the obtained information to evolve at least some of the presented decision objects and thereby generate one or more derived decision objects;

(d) iterating steps (a) through (c), using a derived group from step (c) until a stopping criterion is achieved; and

(e) upon achieving the stopping criterion, selecting one or a group of preferred decision objects for further development, manufacture, use, or sale,

wherein each of the attributes comprises a structural, functional, stylistic, or economic feature of the product or service.

47. The method of claim 46 wherein each of the attributes comprises cost, color, color combination, dominant color, background color, dimension, size, shape, aspect ratio, style, strength, length, width, thickness, weight, pattern, texture, softness, content feature, theme, option, choice of material, distribution of materials, size of print, presence or absence of pictorial material, or pictorial content.

48. The method of claim 46 wherein each of the attributes comprises an element of the product or service that are optional.

49. The method of claim 46 wherein each of the attributes comprises an element of the product or service that has many values or many subtypes.