Abstract-This paper presents issues related to a process of the automatic summarization of the text documents connected with economic knowledge performed by the cognitive agents in an integrated management information system. In contemporary companies, the unstructured knowledge is essential, mainly due to the possibility of obtaining better flexibility and competitiveness of the organization. Therefore more often the decision are taken in the enterprises on the basis of the summaries. The first part of the paper shortly presents the state-of-the-art in the considered field; next, the summarization process in the Cognitive Integrated Management Information System is characterized; the case study related with the summaries generating agent is presented in the last part of this paper.
I. INTRODUCTIONN contemporary companies the unstructured knowledge is essential, mainly due to the possibility of obtaining better flexibility and competitiveness of the organization. The unstructured knowledge supports structuralized knowledge to a high degree. It is mainly stored in natural language, so it is processed with symbols (not numbers). One example of unstructured knowledge is experts' opinion about a predicted currency trading. Some experts may argue that the exchange rate of the currency will rise, others that it will decrease, and still others that it will remain unchanged. In addition, expert opinions include the reasons for these predictions. The number of such opinions in the Internet is usually very large (hundreds, thousands of the opinions). An investor who makes a decision, for example, on the financial markets, needs to analyze and summarize these opinions to formulate the correct decision. However, the manual realization of these processes is extremely difficult, and often impossible, due to time constraints [14]. Thus, often the processes of the analysis and summarization of the text documents are made automatically by computer systems, including the integrated management information systems. They may be constructed, for example, on the basis of the number of the cognitive agents [16]. Generally speaking, the cognitive agent is a smart program that not only concludes on the basis of the data received, takes specific actions to achieve the desired objective (this can be, for example, decision support), but also learns at the same time gaining experience. An example of a cognitive agent's architecture is The Learning Intelligent Distribution Agent (LIDA) [35]. This is a hybrid architecture that allows for symbolic and emergent knowledge processing and uses the semantic net with node and links activation level (the "slipnet") [19] to represent a knowledge.Broadly understood, the analysis of the text documents is mainly based on document retrieval, information extraction, text mining and natural language processing. Summarization, instead, can include the contents of a document or set of documents. The basic idea of summarization is to get a summary that contains the most important information from the source doc...