Artificial intelligence behavior in dynamic knowledge base

We have much information to be processed in order to get various systems. For getting a desired output, we have now many kinds of AI methods and techniques, which may be able to handle an input information intelligently. However, those methods and techniques are not so flexible enough to get a proper output to an input when an output is not a desired one. That is to say, when the present methods have once produced an output, it will be the final one and it cannot be changed whatever an output's expectation is. In this situation the systems need to have some kind of dynamic knowledge base behavior in treatment, which gives more proper an output to an input. So in this paper, the following themes are discussed: 1) communication method among processes in a system, 2) general mechanism of dynamic behavior of AI and knowledge base, and 3) system structure.