Online Analytical Mining Research And Application Of Information Analysis System

On-line analytical mining (OLAM) is a promising direction in the field of data analysis. The appearance of OLAM is to realize the expectation that on-line analytical processing (OLAP) and data mining (DM) have their own advantages and disadvantages, data analysis can work better if OLAP and DM are integrated with each other.In the case of conventional analysis, if user adopts OLAP to analytical issues, he has to suppose what will happen. Then OLAP will execute a dimensional analysis for the supposition and analysis result will prove supposition is right or not. Obviously, due to users' subjectivity, analysis range decided by users will influent results more or less; there are also some disadvantages if adopting DM. DM will execute mining task automatically after algorithm is determined and user cannot intervene the whole process. This is too blind. Therefore, if integrate OLAP into DM, data analysis will become more efficient and more commercially valuable.Up to now, OLAM has been in its infancy phase. There are still not sophisticated theory foundation and systematical architecture of OLAM. Moreover, OLAM products on the market are developed by different software manufacture according on their own understanding of OLAM. Those products are in a state of chaos. Actually, research on OLAM lags behind its application.On such premise, the paper complete jobs as follows:1. Introduce relative theory and main techniques of OLAM;2. Based on self-experience and others research for reference, an OLAM-based information system is put forward. Then discuss the architecture of OLAM. Finally, give come advices for the implementation of OLAM-based information system;3. Present an implementation example of OLAM-based information system — logistic guarantee aided decision system for certain army.