System and method for retrieving information according to improved matching criteria

• US 6,708,174 B1
• Filed: 12/20/2000
• Issued: 03/16/2004
• Est. Priority Date: 12/20/2000
• Status: Expired due to Term

• Current Assignee: Blue Yonder Group, Inc. (Panasonic Holdings Corporation)
• Original Assignee: i2 Technologies Incorporated (Panasonic Holdings Corporation)
• Inventors: Tenorio, Noel
• Primary Examiner(s): Mizrahi, Diane D.
• Assistant Examiner(s): ABEL JALIL, NEVEEN
• Application Number:
  US09/742,851
• Time in Patent Office: 1,182 Days
• Field of Search: 707/5, 707/102, 707/104, 707/10, 707/1, 707/3, 707/100, 707/7, 348/10
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions

Abstract

A system for retrieving information for a user includes a database containing values for one or more parameters of one or more available items, each available item with corresponding parameter values. A matching server receives values for one or more parameters of a target item, these parameters being organized into subsets. The matching server applies the parameter values for the target item against the database and, for each available item and each parameter subset of the target item, computes a distance between the parameter values for the available item and the parameter values for the target item. For each of the parameter subsets, the matching server then applies a weight to the distance to compute a weighted distance for the parameter subset. The matching server computes an overall distance between the available item and the target item based on the weighted distances for the parameter subsets and returns results to the user reflecting the overall distance for the available item. The user may be a buyer and the overall distance for the available item may allow the buyer to make a purchasing decision with respect to the available item.

Claims

1. A system for retrieving information for a user, comprising:

a database containing values for a plurality of parameters of a plurality of available items, each available item having corresponding parameter values; and

a matching server operable to receive values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets, the matching server further operable to;

apply the parameter values for each of the plurality of parameter subsets for the target item against the database;

for at least one available item and for each of the plurality of parameter subsets of the target item, compute a distance between the parameter values for the parameter subset for the available item and the parameter values for the parameter subset for the target item according to a distance measure specified for the parameter subset, the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

for each of the plurality of parameter subsets, apply a weight to the distance to compute a weighted distance for the parameter subset;

compute an overall distance between the available item and the target item according to the weighted distances for the plurality of parameter subsets; and

return results to the user reflecting the overall distance for the available item.

2. The system of claim 1, wherein the weighted distances are summed over all the parameter subsets to compute the overall distance for the available item.

3. The system of claim 1, wherein the weight for each parameter subset is user-specified according to needs of the user.

4. The system of claim 3, wherein the matching server is further operable to determine the weights for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

5. The system of claim 1, wherein:

the distance for a first parameter subset is computed as an absolute error between the associated parameter values for the available and target items;

the distance for a second parameter subset is computed as a mean-square error between the associated parameter values for the available and target items; and

the weighted distances for the first and second parameter subsets are summed to compute the overall distance for the available item.

6. The system of claim 1, wherein the distance for a parameter subset is computed to reflect a user preference selected from the group consisting of:

exact matches between the parameter values for the available and target items and, where no exact match is possible for a parameter, a minimum difference between the values for the available and target items for that parameter;

close matches between the parameter values for the available and target items for all parameters simultaneously, where an exact match is not required for any parameter; and

an exception prohibiting exact matches between the parameter values for the available and target items.

7. The system of claim 1, wherein the user is a buyer and the overall distance for the available item allows the buyer to make a purchasing decision with respect to the available item.

8. The system of claim 1, wherein the matching server is operable to compute overall distances for a plurality of available items and to rank the available items according to their overall distances, the results returned to the user indicating at least the available item having the smallest overall distance.

9. The system of claim 1, wherein the available items are selected from the group consisting of:

parts, components, products, or other tangible items;

services;

real property; and

web pages or other documents.

10. The system of claim 1, further comprising a marketplace associated with the matching server.

11. The system of claim 1, wherein the distance L_n for a parameter subset is computed as:

$L_n={\sqrt{\frac{\underset{k}{\overset{K}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{<br><br>{\mathrm{available}}_k-{\mathrm{target}}_k<br><br>}^n}{K}}}^n$

where K is number of parameters in the subset, available_k is the value for the available item for the kth parameter, target_k is the value for the target item for the kth parameter, the summation is over all K parameters in the subset, and n is the order of the distance measure.

12. The system of claim 11, wherein the value of n for each parameter subset is user-specified according to needs of the user.

13. The system of claim 12, wherein the matching server is further operable to determine the values of n for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

40. The method of claim 13, wherein the distance L_m for a parameter subset is computed as:

$L_n={\sqrt{\frac{\underset{k}{\overset{K}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{<br><br>{\mathrm{available}}_k-{\mathrm{target}}_k<br><br>}^n}{K}}}^n$

where K is number of parameters in the subset, available_k is the value for the available item for the kth parameter, target_k is the value for the target item for the kth parameter, the summation is over all K parameters in the subset, and n is the order of the distance measure.

41. The method of claim 40, wherein the value of n for each parameter subset is user-specified according to needs of the user.

42. The method of claim 41, wherein the values of n are determined for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

14. A system for retrieving information for a user, comprising:

a database containing values for one or more parameters of one or more available items, each available item having corresponding parameter values; and

a matching server operable to receive values for one or more parameters of at least one target item, the parameters for the target item being organized into one or more subsets, the matching server further operable to;

apply the parameter values for the target item against the database;

for at least one available item and for each parameter subset of the target item, compute a distance between the parameter values for the available item and the parameter values for the target item;

for each parameter subset, apply a weight to the distance to compute a weighted distance for the parameter subset;

compute an overall distance between the available item and the target item according to the weighted distances for the parameter subsets; and

return results to the user reflecting the overall distance for the available item;

the distance L_n for a parameter subset being computed as;

$L_n={\sqrt{\frac{\underset{k}{\overset{K}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{<br><br>{\mathrm{available}}_k-{\mathrm{target}}_k<br><br>}^n}{K}}}^n$

where K is number of parameters in the subset, available_k is the value for the available item for the kth parameter, target_k is the value for the target item for the kth parameter, the summation is over all K parameters in the subset, and n is the order of the distance measure.

15. The system of claim 14, wherein the value of n for each parameter subset is user-specified according to needs of the user.

16. The system of claim 15, wherein the matching server is further operable to determine the values of n for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

17. A system for retrieving information for a user, comprising:

means for storing values for a plurality of parameters of a plurality of available items, each available item having corresponding parameter values; and

means for receiving values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets;

means for applying the parameter values for each of the plurality of parameter subsets for the target item against the database;

means, for at least one available item and for each of the plurality of parameter subsets of the target item, for computing a distance between the parameter values for the parameter subset for the available item and the parameter values for the parameter subset for the target item according to a distance measure specified for the parameter subset the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

means, for each of the plurality of parameter subsets, applying a weight to the distance to compute a weighted distance for the parameter subset;

means for computing an overall distance between the available item and the target item according to the weighted distances for the plurality of parameter subsets; and

means for returning results to the user reflecting the overall distance for the available item.

18. Software for retrieving information for a user, the software embodied in a computer-readable medium and when executed operable to:

receive values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets;

apply the parameter values for each of the plurality of parameter subsets for the target item against a database containing values for a plurality of parameters of a plurality of available items, each available item having corresponding parameter values;

for at least one available item and for each of the plurality of parameter subsets of the target item, compute a distance between the parameter values for the parameter subset for the available item and the parameter values for the parameter subset for the target item according to a distance measure specified for the parameter subset, the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

for each of the plurality of parameter subsets, apply a weight to the distance to compute a weighted distance for the parameter subset;

compute an overall distance between the available item and the target item according to the weighted distances for the plurality of parameter subsets; and

return results to the user reflecting the overall distance for the available item.

19. The software of claim 18, wherein the distance L_n for a parameter subset is computed as:

$L_n={\sqrt{\frac{\underset{k}{\overset{K}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{<br><br>{\mathrm{available}}_k-{\mathrm{target}}_k<br><br>}^n}{K}}}^n$

where K is number of parameters in the subset, available_k is the value for the available item for the kth parameter, target_k is the value for the target item for the kth parameter, the summation is over all K parameters in the subset, and n is the order of the distance measure.

20. The software of claim 19, wherein the value of n for each parameter subset is user-specified according to needs of the user.

21. The software of claim 20, further operable to determine the values of n for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

22. The software of claim 18, wherein the weighted distances are summed over all the parameter subsets to compute the overall distance for the available item.

23. The software of claim 18, wherein the weight for each parameter subset is user-specified according to needs of the user.

24. The software of claim 23, further operable to determine the weights for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

25. The software of claim 18, wherein:

the distance for a first parameter subset is computed as an absolute error between the associated parameter values for the available and target items;

the distance for a second parameter subset is computed as a mean-square error between the associated parameter values for the available and target items; and

the weighted distances for the first and second parameter subsets are summed to compute the overall distance for the available item.

26. The software of claim 18, wherein the distance for a parameter subset is computed to reflect a user preference selected from the group consisting of:

exact matches between the parameter values for the available and target items and, where no exact match is possible for a parameter, a minimum difference between the values for the available and target items for that parameter;

close matches between the parameter values for the available and target items for all parameters simultaneously, where an exact match is not required for any parameter; and

an exception prohibiting exact matches between the parameter values for the available and target items.

27. The software of claim 18, wherein the user is a buyer and the overall distance for the available item allows the buyer to make a purchasing decision with respect to the available item.

28. The software of claim 18, operable to compute overall distances for a plurality of available items and to rank the available items according to their overall distances, the results returned to the user indicating at least the available item having the smallest overall distance.

29. The software of claim 18, wherein the available items are selected from the group consisting of:

parts, components, products, or other tangible items;

services;

real property; and

web pages or other documents.

30. The software of claim 18, wherein the software is executed at a marketplace.

31. A method for retrieving information from a user, comprising:

receiving values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets;

applying the parameter values for each of the plurality of parameter subsets for the target item against a database containing values for a plurality of parameters of a plurality of available items, each available item having corresponding parameter values;

for at least one available item and for each of the plurality of parameter subsets of the target item, computing a distance between the parameter values for the parameter subset for the available item and the parameter values for the parameter subset for the target item according to a distance measure specified for the parameter subset, the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

for each of the plurality of parameter subsets, applying a weight to the distance to compute a weighted distance for the parameter subset;

computing an overall distance between the available item and the target item according to the weighted distances for the plurality of parameter subsets; and

returning results to the user reflecting the overall distance for the available item.

32. The method of claim 31, wherein the weighted distances are summed over all the parameter subsets to compute the overall distance for the available item.

33. The method of claim 31, wherein the weight for each parameter subset is user-specified according to needs of the user.

34. The method of claim 33, wherein the weights are determined for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

35. The method of claim 31, wherein:

the distance for a first parameter subset is computed as an absolute error between the associated parameter values for the available and target items;

the distance for a second parameter subset is computed as a mean-square error between the associated parameter values for the available and target items; and

the weighted distances for the first and second parameter subsets are summed to compute the overall distance for the available item.

36. The method of claim 31, wherein the distance for a parameter subset is computed to reflect a user preference selected from the group consisting of:

exact matches between the parameter values for the available and target items and, where no exact match is possible for a parameter, a minimum difference between the values for the available and target items for that parameter;

close matches between the parameter values for the available and target items for all parameters simultaneously, where an exact match is not required for any parameter; and

an exception prohibiting exact matches between the parameter values for the available and target items.

37. The method of claim 31, wherein the user is a buyer and the overall distance for the available item allows the buyer to make a purchasing decision with respect to the available item.

38. The method of claim 31, wherein the overall distances are computed for a plurality of available items, the method further comprising ranking the available items according to their overall distances, the results returned to the user indicating at least the available item having the smallest overall distance.

39. The method of claim 31, wherein the available items are selected from the group consisting of:

parts, components, products, or other tangible items;

services;

real property; and

web pages or other documents.

43. A method for retrieving information from a user, comprising:

receiving values for one or more parameters of at least one target item, the parameters for the target item being organized into one or more subsets;

applying the parameter values for the target item against a database containing values for one or more parameters of one or more available items, each available item having corresponding parameter values;

for at least one available item and for each parameter subset of the target item, computing a distance between the parameter values for the available item and the parameter values for the target item;

for each parameter subset, applying a weight to the distance to compute a weighted distance for the parameter subset;

computing an overall distance between the available item and the target item according to the weighted distances for the parameter subsets; and

returning results to the user reflecting the overall distance for the available item;

the distance L_n for a parameter subset being computed as;

$L_n={\sqrt{\frac{\underset{k}{\overset{K}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{<br><br>{\mathrm{available}}_k-{\mathrm{target}}_k<br><br>}^n}{K}}}^n$

where K is number of parameters in the subset, available_k is the value for the available item for the kth parameter, target_k is the value for the target item for the kth parameter, the summation is over all K parameters in the subset, and n is the order of the distance measure.

44. The method of claim 43, wherein the value of n for each parameter subset is user-specified according to needs of the user.

45. The method of claim 44, wherein the values of n are determined for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.

46. A system for retrieving information for a user, comprising:

a database containing values for a plurality of parameters of each of a plurality of available items, each available item having corresponding parameter values; and

a matching server operable to receive values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets, the matching server further operable to;

apply the parameter values for each of the plurality of parameter subsets for the target item against the database;

for each of a plurality of the available items and for each of the plurality of parameter subsets of the target item, compute a distance between the parameter values for the parameter subset for the particular available item and the parameter values for the parameter subset for the target item according to a user-specified distance measure that the user deems appropriate for the user'"'"'s particular information needs, the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

for each of the plurality of parameter subsets, apply a user-specified weight to the distance to compute a weighted distance for the parameter subset;

compute an overall distance between each available item and the target item according to the weighted distances for the plurality of parameter subsets;

rank the available items according to their overall distances; and

return results to the user indicating at least the available item having the smallest overall distance.

47. The system of claim 46, wherein the user is a buyer and the results returned to the buyer allow the buyer to make a purchasing decision with respect to the available item.

48. Software for retrieving information for a user, the software embodied in a computer-readable medium and operable to:

receive values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets;

apply the parameter values for each of the plurality of parameter subsets for the target item against a database containing values for a plurality of parameters of each of a plurality of available items, each available item having corresponding parameter values;

for each of a plurality of the available items and for each of the plurality of parameter subsets of the target item, compute a distance between the parameter values for the parameter subset for the particular available item and the parameter values for the parameter subset for the target item according to a user-specified distance measure that the user deems appropriate for the user'"'"'s particular information needs, the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

for each of the plurality of parameter subsets, apply a user-specified weight to the distance to compute a weighted distance for the parameter subset;

compute an overall distance between each available item and the target item according to the weighted distances for the plurality of parameter subsets;

rank the available items according to their overall distances; and

return results to the user indicating at least the available item having the smallest overall distance.

49. The software of claim 48, wherein the user is a buyer and the results returned to the buyer allow the buyer to make a purchasing decision with respect to the available item.

50. A method for retrieving information for a user, comprising:

receiving values for a plurality of parameters of at least one target item, the parameters for the target item being organized into a plurality of parameter subsets;

applying the parameter values for each of the plurality of parameter subsets for the target item against a database containing values for a plurality of parameters of each of a plurality of available items, each available item having corresponding parameter values;

for each of a plurality of the available items and for each of the plurality of parameter subsets of the target item, computing a distance between the parameter values for the parameter subset for the particular available item and the parameter values for the parameter subset for the target item according to a user-specified distance measure that the user deems appropriate for the user'"'"'s particular information needs, the distance measure specified for at least one parameter subset being different than the distance measure specified for at least one other parameter subset;

for each of the plurality of parameter subsets, applying a user-specified weight to the distance to compute a weighted distance for the parameter subset;

computing an overall distance between each available item and the target item according to the weighted distances for the plurality of parameter subsets;

ranking the available items according to their overall distances; and

returning results to the user indicating at least the available item having the smallest overall distance.

51. The method of claim 50, wherein the user is a buyer and the results returned to the buyer allow the buyer to make a purchasing decision with respect to the available item.

52. Software for retrieving information for a user, the software embodied in a computer-readable medium and when executed operable to:

receive values for one or more parameters of at least one target item, the parameters for the target item being organized into one or more subsets;

apply the parameter values for the target item against a database containing values for one or more parameters of one or more available items, each available item having corresponding parameter values;

for at least one available item and for each parameter subset of the target item, compute a distance between the parameter values for the available item and the parameter values for the target item;

for each parameter subset, apply a weight to the distance to compute a weighted distance for the parameter subset;

compute an overall distance between the available item and the target item according to the weighted distances for the parameter subsets; and

return results to the user reflecting the overall distance for the available item;

the distance L_n for a parameter subset being computed as;

$L_n={\sqrt{\frac{\underset{k}{\overset{K}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{<br><br>{\mathrm{available}}_k-{\mathrm{target}}_k<br><br>}^n}{K}}}^n$

where K is number of parameters in the subset, available_k is the value for the available item for the kth parameter, target_k is the value for the target item for the kth parameter, the summation is over all K parameters in the subset, and n is the order of the distance measure.

53. The software of claim 52, wherein the value of n for each parameter subset is user-specified according to needs of the user.

54. The software of claim 53, further operable to determine the values of n for one or more parameter subsets based on one or more words, as opposed to numbers, received from the user.