A knowledge acquisition method of decision information system based on formal vector

Abstract

The invention discloses a knowledge acquisition method of a decision information system of a decision information system based on a formal vector. The method takes the decision formal background as aresearch object and defines a formal vector for describing the potential knowledge of the information system. By introducing the idea of granularity, formal vectors in different granularity spaces areobtained from coarse to fine, and a formal vector tree is constructed based on parent-child vector relation, which realizes the visualization of rule acquisition process. In the process of acquiringthe simplest rule, the relation between the conditional form vector and the decision form vector is used to extract the simplest rule, which simplifies the decision process of the rule. Whether the rules cover the whole universe or not is set as the termination condition, so that there is no redundancy between the rules, which ensures the minimum number of rules and accelerates the convergence speed of the algorithm; Due to the use of fewer rules and the minimization of the rule length, the algorithm also has a higher recognition rate.

Description

technical field [0001] The invention relates to the fields of knowledge acquisition and knowledge reduction in artificial intelligence, in particular to a method for acquiring knowledge of a decision information system based on a formal vector. Background technique [0002] With the advent of the era of big data and the further development of the network, information plays an increasingly important role in the related research of computer and information systems. Information system is the main research object of machine learning, and decision information system is an important form of information system. [0003] Knowledge representation is neither a data format nor a programming language. It is different from a data structure. It is a way that is easy for computers to process to represent the knowledge of the human brain. Compared with artificial intelligence, the relationship between knowledge and data The difference is that knowledge can be reasoned about. Knowledge acq...

AI Technical Summary

Problems solved by technology

In recent years, many scholars have used FCA to conduct extensive research on the rule extraction of decision tables: for complete decision tables, Li Jinhai et al. proposed a non-redundant rule acquisition algorithm, which avoids the calculation of operators, and to a certain extent The complexity of the algorithm is reduced, but in some cases, there are still redundant attributes in the acquired rules; Miao Duoqian et al. have granulated the attributes and objects in the formal background, reducing the scale of the formal background, It reduces the complexity of the algorithm, but the granulation makes the algorithm lose the accuracy of knowledge reduction to a certain extent; Shao Mingwen and others studied the If-then rule based on the formal concept analysis, and proposed a non-redundant rule acquisition algorithm, and The method is equally applicable to inconsistent decision-making formal contexts

Images