The origin of knowledge mining

In the 1990s, with the appearance and development of the Internet,

Before implementing knowledge mining, we must know the knowledge state.

As well as the emergence and application of Intranet, Extranet and VPNVirtualPrivatenetwork, the whole world is connected into a small global village, where people can exchange data and information online and work together across time and space. In this way, what is displayed in front of people is not limited to the huge database of the department, the unit and the industry, but the ocean of information. When the amount of data is extremely increasing, if there is no effective way to extract useful information and knowledge through computers and information technology, people are helpless in the face of the information ocean. Only 7% of the data in large enterprise databases have been well utilized. In this way, compared with "data surplus" and "information explosion", people feel "information poverty" and "datainjail", and JohnNaisbett exclaimed "Wearedrowningininformation, butstarvingforknowledge". In the face of endless data, people need a technology to get rid of the rough and keep the fine, and to get rid of the false and keep the true from the data Wang Yang. Knowledge Discovery from Database (KDD) and its core technology came into being.

The so-called knowledge mining is the process of extracting hidden, previously unknown and potentially applicable information from the database. Knowledge mining is the core of KDD. The difference between knowledge mining and traditional analysis tools is that knowledge mining uses discovery-based methods and uses algorithms such as pattern matching to determine important relationships between data.