Knowledge extraction involves using structured and unstructured sources to create a cohesive knowledge bank. It can speed up formal knowledge sharing by reusing existing knowledge in new formats. Data mining can be used to create new sources for specific purposes, which can eventually be used to meet new usage needs.
Knowledge extraction is the process of using various sources of information to create a cohesive knowledge bank. As part of this approach, mining will often draw on a range of both structured and unstructured sources. When successful, knowledge extraction results in robust data that can be easily read and interpreted by a given program, allowing the end user to use that formal knowledge for any purpose they desire.
Different sources can be used in the knowledge extraction process. In the context of structured sources, data can be extracted from various types of relational databases or from some type of extensible markup language or XML source. Unstructured sources, such as images, different forms of word processing documents, spreadsheets, and even text captured on notepad-style programs can be used as part of the extraction process. As long as the sources are readable by the program used to manage the knowledge extraction process, they can be used as sources that expand the potential of the project that is being carried out through the extraction and allow the usability of the final knowledge produced.
There are several common applications that occur with knowledge extraction. A frequent example is the ability to take data from an unstructured source and incorporate it into some type of structured knowledge source. Extracting data found in relational databases and using it to create new documents, or using electronic documents to import data into relational databases, is another example of how this type of extraction can speed formal knowledge sharing without the need to manually enter the data that it is already available from some other source. This reuse of existing knowledge in a new format is often very useful in a number of scenarios, making it possible to use that knowledge in ways that may not have been possible with the existing source. In this way, the user can create sources that are ideal for a number of different applications rather than only those relevant to the original seat of formal knowledge.
With the use of data mining you can take advantage of a vast data warehouse, easily importing and exporting data to create a new source that can be used for a specific purpose. These new sources in turn also find a place in the data warehouse and can eventually be used in the creation of new extracts that are used to meet new usage needs. With this in mind, knowledge extraction can be seen as a very useful tool that helps make the most of all the resources currently available, simplifying many of the tasks involved in sharing that formal knowledge.
Protect your devices with Threat Protection by NordVPN
