The paper presents the evolution of concepts, an overview of research and applications pertaining to reliability in construction production, the use of reserves, robust itineraries, and contingency of time and cost. It describes areas of management advisory systems in relation to the cycle of risk analysis. The article also presents the main trends in different approaches to risk management in construction and construction project processes, such as reliability of production, discount methods, methods of reporting, integrated management together with trends towards standardisation of the investment process management. The discussion is embedded in the specific context: the achievements of trilateral academic colloquia, with participation of Lithuania, Germany and Poland, and a review of work by Professor Kapliński, the chair of the Polish delegation to the aforementioned colloquia. Santrauka Straipsnyje pateikiama koncepcijų raida, mokslinių tyrimų ir taikomųjų programų, susijusių su statybos produkcijos pati-kimumu, atsargų, patikimų maršrutų bei laiko ir lėšų naudojimo nenumatytais atvejais, apžvalga. Aprašomos valdymo konsultavimo sistemų sritys, atsižvelgiant į rizikos analizės ciklą. Straipsnyje taip pat apžvelgiamos pagrindinės skirtingų požiūrių į rizikos valdymą statybos ir statybos projektavimo procesų metu tendencijos, pavyzdžiui, gamybos patikimumo, diskonto metodai, atskaitomybės metodai, integruotas valdymas bei investicinio proceso valdymo standartizavimo ten-dencijos. Diskusija pateikiama specifiniame trišalio akademinio bendradarbiavimo, dalyvaujant Lietuvai, Vokietijai ir Lenkijai, bei Lenkijos delegacijos pirmininko profesoriaus Kapliński pasiekimų kontekste.

This article presents the possibilities of using mining techniques in building Decision Support Systems. One of the biggest problems is the issue of gaining data and knowledge, their mutual representation and reciprocal usage. Data and knowledge make up the resources of the system and are its key link. It has been estimated that 70% to 80% of the sources available for general use are text documents. The text mining technique is defined as a process aiming to extract previously unknown information from text resources (e.g. technological cards). The fundamental feature of text mining is the ability to converse text documents in formal form, which opens up great possibilities of conducting further analysis. This article presents chosen IT tools using text mining technique, along with the elements of the text mining analysis. The main objectives are the simplification of the process of knowledge acquisition, its automation and shortening as well as the creation of ready‐made models containing knowledge. Previous tests with knowledge acquisition (surveys, questionnaires) were time‐consuming and exacting for experts. Santrauka Straipsnyje pateikiamos informacijos rinkimo metodu pritaikymo galimybės sprendimų paramos sistemoms statyboje. Daugiausia problemų sukelia informacijos gavimas, tinkamas jos atvaizdavimas ir naudojimas. Duomenys yra pagrindinis sistemos išteklius. Nustatyta, kad nuo 70 iki 80 % visu turimų bendrojo naudojimo informacijos šaltinių yra tekstiniai dokumentai. Tekstines informacijos rinkimo technika yra suprantama kaip procesas, kuriuo siekiama išgauti anksčiau nežinoma informacija iš tekstiniu dokumentu (pavyzdžiui, technologiniu kortelių). Pagrindine šios technikos savybė ‐ galimybė tekstinių dokumentų informacija pateikti formalizuota forma, tai atveria plačiu galimybių tolesnei analizei. Šiame straipsnyje pateikiamos pasirinktos IT priemonės, naudojamos tekstinei informacijai rinkti. Autoriaus tikslas ‐ su paprastinti informacijos rinkimą, ji automatizuoti ir sutrumpinti, sukurti informacija apimančius modelius. Ankstesni informacijos kaupimo metodai (apklausos, anketos) reikalavo daug ekspertų darbo ir laiko.

The study presents a model for the evaluation of construction projects from the point of view of the client (e.g. developer company). The problem lies in choosing the best solution from the point of view of many criteria. The proposed model is based on a multi-criteria comparative analysis using fuzzy logic. The first part of the paper presents a selection of criteria describing the construction project along with their description. The set of attributes describing the analysed object was determined on the basis of the synthesis of specific proposals for the parameters of construction projects. The set of criteria has been divided into two groups: technical, technological and organisational criteria and separately the economic criteria. Then, the number of variables describing the observations was checked using principal component analysis (PCA). Course of action was presented in the event of multiple criteria analysis using the fuzzy set theory. Both the weights and the evaluations of individual criteria were modelled using membership functions due to the fact that when describing a construction project, or the validity of the criteria of describing variables, they are approximate. An analysis of the correlation of selected project criteria was presented. The proposed decision support model of assessing a construction project makes possible to compare various variants based on 11 factors identified. The use of fuzzy logic has enabled more accurate description of the phenomenon analysed when the exact parameters of the project in the planning and preparation stage of the project are not known.

The article presents the problem of knowledge in knowledge-based systems, such as advisory systems used in construction engineering. The unique characteristics of construction engineering translate directly into unique characteristics of knowledge resources, which is evident in the potential sources of knowledge. Many of them are not open, uncertain, fuzzy, of different credibility, and incomplete. One of the knowledge sources is the mental models of experts working in specific fields of construction engineering. Based on the knowledge acquisition sessions that have been completed, it can be concluded that only a certain part of the knowledge contained in mental models has been acquired. In order to ensure more completeness of the knowledge and explain the mechanism of inference, the KBANN (Knowledge Based Artificial Neural Network) algorithm was used, which enables extracting rules that are not a part of the original state of knowledge using trained neural networks. This method effectively supports the process of construction of advisory systems