Decision support system, method and article of manufacture

• US 5,844,817 A
• Filed: 09/08/1995
• Issued: 12/01/1998
• Est. Priority Date: 09/08/1995
• Status: Expired due to Term

• Current Assignee: Technology Evaluation Centers Inc.
• Original Assignee: Arlington Software Corporation
• Inventors: Lobley, Donald J., Robins, Edward S.
• Primary Examiner(s): Teska, Kevin J.
• Assistant Examiner(s): ROBERTS, ANDREW S
• Application Number:
  US08/525,064
• Time in Patent Office: 1,180 Days
• Field of Search: 364/578, 395/50, 395/75, 395/76, 395/77
• US Class Current: 703/2
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 99/00 Subject matter not provided for in other groups of this subclass

Abstract

A decision support system, including a decision model, provides an indication, either of itself or in combination with a weighted average of the scores assigned to the decision model factors, of the degree to which the pattern of contribution scores corresponds to a benchmark pattern. This indication, referred to as a matching index, can be calculated according to a class of matching index functions, including those based on regression-correlation and Bayesian pattern matching and cost/loss concepts. The matching index also allows the designation of model factors as `Must Have` or `Must Not Have` factors, and asymmetric functions for special circumstances. The decision support system can be used to assist in the control of a variety of systems and/or processes and/or in the analysis of information, wherever patterns of information may assist in the selection of an alternative from amongst a set of decision alternatives.

Claims

1. A computer-implemented decision support machine for comparing two alternatives, which alternatives are physical objects or physical activities, said machine comprising:

memory means for storing a decision data structure having a plurality of decision factors, each said decision factor having a weight assigned thereto, the plurality of weighted factors comprising a predetermined two-dimensional benchmark pattern;

input means for inputting a first plurality of scores for a first competing alternative to the decision factors of said decision data structure, and for inputting a second plurality of scores for a second competing alternative to the decision factors of said decision data structure;

processing means for (i) transforming the first plurality of scores into a first two-dimensional contribution pattern, (ii) transforming the second plurality of scores into a second two-dimensional contribution pattern, (iii) pattern-matching the first contribution pattern and the benchmark pattern to produce a first matching index, and (iv) pattern-matching the second contribution pattern and the benchmark pattern to produce a second matching index; and

output means comprising a graphical display to output on said display at least one output signal corresponding to at least one of the first and second matching indexes to provide a comparison of said competing alternatives.

2. A decision support machine according to claim 1 wherein said processing means comprises a processor which controls a controlled process, and wherein said input means comprises at least one sensor monitoring said controlled process.

3. A decision support machine according to claim 2 wherein each said alternative comprises an operating mode of said controlled process.

4. A decision support machine according to claim 1 wherein said processing means performs a linear regression of said first and second plurality of scores.

5. A decision support machine according to claim 1 wherein said processing means performs a Bayesian cost analysis of said first and second plurality of scores.

6. A decision support machine according to claim 1 wherein said processing means computes a weighted average for each said first and second plurality of scores, and wherein said output means outputs on said display at least one weighted signal corresponding to at least one of the weighted averages.

7. A decision support machine according to claim 6 wherein said display displays both the at least one output signal and the at least one weighted signal.

8. A decision support machine according to claim 1 wherein said memory means stores two benchmark patterns each of which corresponds to one of said alternatives, and wherein said processing means pattern-matches each contribution pattern against both of the two benchmark patterns.

9. A decision support machine according to claim 8 wherein said processing means comprises a processor which controls a controlled process, and wherein said input means comprise a at least one sensor monitoring said controlled process.

10. A decision support machine according to claim 9 wherein each said alternative comprises an operating mode of said controlled process, each said alternative having a benchmark pattern associated therewith.

11. A decision support system for use with a controlled process or system, comprising:

means to store a model of said process or system, said model comprising a plurality of factors which are to be considered in controlling said process or system, each said factor having a weight assigned thereto;

means to assign a score to each of said plurality of factors, each said score providing an indication of how said system or process meets criteria associated with said respective factor;

means to determine a contribution pattern for said plurality of factors;

means to store at least two benchmark patterns each representing a possible alternative for controlling said process or system;

means to pattern-match the contribution pattern with said at least two benchmark patterns and to provide an indication of the degree of correspondence between said contribution pattern and each of said at least two benchmark patterns and to select the possible alternative with the highest degree of said correspondence; and

graphical display means to display said provided indication.

12. A decision support system according to claim 11 wherein said means to assign a score comprises one or more sensors responsive to said process or system being controlled.

13. A decision support system according to claim 12 wherein said degree of correspondence is determined with Bayesian cost techniques.

14. A decision support system according to claim 12 wherein said degree of correspondence is determined with correlation-regression techniques.

15. A computer-readable storage medium for storing a program which, when processed by a computer, causes the computer to compare two alternatives which are physical objects or physical activities, the program causing the computer to perform the following functions:

storing a decision data structure having a plurality of decision factors, each decision factor having a weight assigned thereto, the plurality of weighted factors comprising a predetermined two-dimensional benchmark pattern;

inputting a first plurality of scores for a first competing alternative to the decision factors of said decision data structure;

inputting a second plurality of scores for a second competing alternative to the decision factors of said decision data structure;

transforming the first plurality of scores into a first two-dimensional contribution pattern;

transforming the second plurality of scores into a second two-dimensional contribution pattern;

pattern-matching the first contribution pattern and the benchmark pattern to produce a first matching index;

pattern-matching the second contribution pattern and the benchmark pattern to produce a second matching index; and

outputting on a computer display at least one output signal corresponding to at least one of the first and second matching indexes to provide a comparison of said competing alternatives.

16. A storage medium according to claim 15, wherein said program further causes said computer to calculate a first weighted average corresponding to the first plurality of scores, and to calculate a second weighted average corresponding to the second plurality of scores, and to output at least one weighted average signal corresponding to at least one of the first and second weighted averages.

17. A storage medium according to claim 15, wherein said program further causes said computer to output a signal which causes said computer display to display, in overlapping fashion, the first contribution pattern and the benchmark pattern.

18. A decision support method for comparing two alternatives which are physical objects or physical activities, comprising the steps of:

storing a decision data structure having a plurality of decision factors, each decision factor having a weight assigned thereto, the plurality of weighted factors comprising a predetermined two-dimensional benchmark pattern;

inputting a first plurality of scores for a first competing alternative to the decision factors of said decision data structure;

inputting a second plurality of scores for a second competing alternative to the decision factors of said decision data structure;

transforming the first plurality of scores into a first two-dimensional contribution pattern;

transforming the second plurality of scores into a second two-dimensional contribution pattern;

pattern-matching the first contribution pattern and the benchmark pattern to produce a first matching index;

pattern-matching the second contribution pattern and the benchmark pattern to produce a second matching index; and

outputting on a computer display at least one output signal corresponding to at least one of the first and second matching indexes to provide a comparison of said competing alternatives.

19. A machine for comparing the attributes of two physical objects of a single class of physical objects, comprising:

an input device for inputting a first plurality of scores corresponding to attributes of a first physical object, and for inputting a second plurality of scores corresponding to attributes of a second physical object;

a memory for storing a predetermined two-dimensional benchmark pattern corresponding to a predetermined plurality of attributes for the single class of physical objects;

a processor for (i) transforming the first plurality of scores into a first two-dimensional contribution pattern, (ii) transforming the second plurality of scores into a second two-dimensional contribution pattern, (iii) two-dimensional pattern-matching the first contribution pattern and the benchmark pattern to produce a first matching index, (iv) two-dimensional pattern-matching the second contribution pattern and the benchmark pattern to produce a second matching index, (v) calculating a first weighted average corresponding to the first plurality of scores, (vi) calculating a second weighted average corresponding to the second plurality of scores; and

a graphical display connected to said processor and operable to display the first and second matching indexes and the first and second weighted averages.

20. A machine according to claim 19, wherein said processor operates said graphical display to display the first contribution pattern and the benchmark pattern in an overlapping manner.