Nonlinear fuzzy logic decision algorithm

Abstract

The invention provides a nonlinear fuzzy logic decision algorithm which comprises a definition and six steps. A definition decision model is as follows: the decision is a seven-element set (I, X, R, D, p, M and A), and the meanings are respectively a decision influencing factor set, a fuzzy language variable set, a fuzzy rule set, a decision machine, an executive main body and an action set. The five steps are respectively as follows: carrying out fuzzification on decision influencing factors by adopting a typical function method; calculating a fuzzy conclusion by adopting a specialist experience method and a membership degree precomputation algorithm; carrying out defuzzification on the fuzzy conclusion by adopting a centroid method to obtain a decision probability; making a decision according to the decision probability; and generating an action set for the decision. In the algorithm, the membership degree precomputation algorithm is adopted to optimize the fuzzy rule, thus the algorithm can be used for efficiently simulating uncertain intelligent decisions in a strategy type computer game.

Description

technical field [0001] The invention relates to the field of computer game artificial intelligence, especially non-deterministic decision-making intelligence. Background technique [0002] With the rapid development of computer technology, the computer game industry has become the most important profit growth point in the IT industry. How to simulate human intelligence in computer games, especially non-deterministic decision-making intelligence, and increase the entertainment and interactivity of computer games has attracted more and more attention from the industry and academia. [0003] Some important artificial intelligence technologies have been produced in the industry. However, these technologies have not yet formed a complete theoretical system, and are still dominated by deterministic intelligence. Non-deterministic intelligence technologies are still in the development period. The biggest feature of human intelligence is its fuzziness, that is, uncertainty. When h...

AI Technical Summary

Problems solved by technology

[0003] Some important artificial intelligence technologies have been produced in the industry. However, these technologies have not yet formed a complete theoretical system, and are still dominated by deterministic intelligence. Non-deterministic intelligent technologies are still in the development period.

Images