||Purpose: With this paper a data driven model of knowledge representation for use in construction information technology (CIT) is introduced as a novel implementation and it is effectively implemented by artificial intelligence methods. Although for CIT knowledge base systems as a general framework is available where the user can place the information. Such systems are eventually mere data warehouses or in a more sophisticated form they are decision support systems in the form of rule based expert systems. However, in the case of a framework structure to organise the knowledge base is difficult and cumbersome task to establish an effective product. In the case expert systems, the inference is deductive and therefore the effectiveness of the system is limited to the prescribed rules. Therefore in place of high level data base management software like Prolog ©, the integration of new computational information processing methods and technologies into CIT would be much informative and therefore they are much effective and finally desirable. From the viewpoint of computation, CIT the data are rather soft requiring special methods and techniques to deal with. In this respect, computational intelligence is one of the emerging technologies, which provides CIT with ample possibilities and techniques for the enhancement of CIT products. Computational intelligence is a part of artificial intelligence (AI) and can be defined as a branch of soft computing methodologies including Expert Systems, Fuzzy Logic, Artificial Neural Networks and Evolutionary Computation.Methodology: For the CIT data soft computing methods are invoked. Soft Computing is an emerging approach to computing which parallels the remarkable ability of the human mind to reason and learn in an environment of uncertainty and imprecision. In plain terms, it is the processing of uncertain information with the methods, methodologies, and paradigms of artificial NN, fuzzy logic and evolutionary algorithms. The equivalence of neural networks and fuzzy logic applications is well established. However, the effectiveness of either method is still dependent on the application itself. Each method has its strong merits. However, in general, best performance is obtained when both methods are used in hybrid form. Especially neural system can cope with complex systems while it is relatively difficult for fuzzy systems. On the contrary, it is easier to deal with linguistic variables by fuzzy systems. Such a hybrid model is implemented in the knowledge model accomplished.Results: A novel concept of soft computing in CIT is introduced using actual building design data for design evaluation. The knowledge base contains all the local and global information and their inherent relationships among themselves. The knowledge representation is performed by means of a series of fuzzy systems having their both fuzzy input space and output space. The associations between the spaces are established by learning techniques of AI using the data at hand. Such an 'intelligent' knowledge base can make inference resulting in 'intelligent' due outcomes, which are not explicitly coded, in advance. In other words this is an inductive and computational inference for decision-making compared to conventional knowledge base systems where inference is deductive prescribed by rules.Conclusions: The soft computing in CIT is an important step for processing the relevant effectively and efficiently. In this respect, the paper describes ongoing advanced research and its verifications by actual data at hand.