Method for evaluating processes with a number of characteristic features

• US 20040122818A1
• Filed: 01/27/2003
• Published: 06/24/2004
• Est. Priority Date: 07/27/2000
• Status: Abandoned Application

• Current Assignee: Active Mining AG
• Original Assignee: Active Mining AG
• Inventors: Schrodl, Holger, Hitzelberger, Robert
• Application Number:
  US10/351,694
• Publication Number:
  US 20040122818A1
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions

Abstract

The invention relates to an automated procedure, in particular a computerized procedure for evaluating processes marked by characteristic features in computer-based networked environments. The procedure includes the following steps: establishing a feature tree to represent the set of all features, whereby the features are linked with the weighting assigned to each feature and a functional assigned to each feature to form a process-related feature set; storing the feature trees in a data bank; structuring the range of values of each feature by calculating at least three defined parameters; mapping the individual feature value on a target interval; weighting the mappings by multiplying the individual values of the mappings by the weighting of each feature within the feature tree; evaluating the individual processes by linking the weighted mappings and comparing the additions with each other.

Claims

1. A computerized procedure for evaluating processes marked by characteristic features in computer-based, networked environments, comprising:

a. establishing at least one feature tree to represent a set of all features, whereby the features are linked with a weighting assigned to each feature and with a functional assigned to each feature to form a process-related feature set;

b. storing the at least one feature tree in a data bank;

c. structuring a range of values of each feature by calculating at least three defined parameters;

d. mapping on individual feature value on a target interval;

e. weighting the mappings by multiplying individual values of the mappings by the weighting of each feature within the feature tree; and

,

f. evaluating the individual processes by means of linking the weighted mappings and comparing the linked mappings with each other.

2. The procedure according to claim 1 wherein the means of linking the weighted mappings includes adding the weighted mappings.

3. The procedure according to claim 1 wherein the weighting represents a valence of each feature within the process-related feature set.

4. The procedure according to claim 1 wherein the weightings have values that are real numbers in a defined interval and are selected such that the sum of all weightings is constant.

5. The procedure according to claim 4 wherein the weightings have values that are real numbers in a [0,1] interval and are selected such that the sum of all weightings is 1.

6. The procedure according to claim 1 wherein the target interval corresponds to a [0,100] interval.

7. The procedure according to claim 1 wherein the functional of each feature is selected as incrementally continuous.

8. The procedure according to claim 7 wherein each functional has a value that is real in a [0,100] range.

9. The procedure according to claim 1 wherein the at least three defined parameters for structuring the range of values of each feature include a virtual default value, a minimum of the value range, and a maximum of the value range.

10. The procedure according to claim 9 wherein to determine the virtual default value from among all existing values of a feature, a geometric mean is formed, which is mapped to 50 with the associated functional.

11. The procedure according to claim 9 wherein to determine the virtual default value from among all existing values of a feature, a harmonic mean is formed, which is mapped to 50 with the associated functional.

12. The procedure according to claim 9 wherein to determine the virtual default value from among all existing values of a feature, an arithmetic mean is formed, which is mapped to 50 with the associated functional.

13. The procedure according to claim 9 wherein to determine the virtual default value, a median of all existing values of a feature is formed which is mapped to 50 with the associated functional.

14. The procedure according to claim 9 wherein to determine the minimum of the value range of each feature, a virtual minimum is calculated as a measure of the accumulation of the low values of the feature in question in the vicinity of the smallest value, whereby the minimum of the value range, which is mapped by the evaluation functional to the lower limit of the target interval, is formed by the minimum of the lowest value and the virtual minimum.

15. The procedure according to claim 14 wherein to determine the maximum of the value range of each feature, a virtual maximum is calculated as a measure of the accumulation of the high values of the feature in question in the vicinity of the highest value, whereby the maximum of the value range, which is mapped by the evaluation functional to the upper limit of the target interval, is formed by the maximum of the highest value and the virtual maximum.

16. The procedure according to claim 15 wherein to calculate the virtual minimum, a fluctuation of the given values is deducted from the virtual default value to form the virtual minimum, and to calculate the virtual maximum, a fluctuation of the given values is added to the virtual default value to form the virtual maximum.

17. The procedure according to claim 15 wherein to map the individual feature values to the target interval, the value range [minimum, virtual default value] is mapped to a [0,50] interval, and the value range [virtual default value, maximum] is mapped to a [50,100] interval, whereby the two value ranges are mapped via the functional of each feature.

18. The procedure according to claim 15 wherein to map the individual feature values to the target interval, the target interval is segmented into a part of higher valence and a part of lower valence, whereby the two segments are disjunct, and an interval [minimum, virtual default value] is mapped to the part of lower valence, and an interval [virtual default, maximum] is mapped to the part of higher valence.

19. The procedure according to claim 1 wherein to weight the mappings of the feature through the associated functional of the feature to the target interval, individual results of the functional of the feature in question are multiplied by the weighting of the individual feature within the feature tree.

20. The procedure according to claim 1 wherein to evaluate the individual processes, the weighted mappings of the individual features are added through their functional to its target interval, which defines a metric on the set of the processes and establishes a sequence.