Explaining the theoretical model of automatic design intelligence performance in the process of arranging spaces with a hierarchical approach and regional divisions

One of the steps in designing an architectural plan is planning for the division and arrangement of spaces, as such examining all possible examples of arranging spaces to produce a plan to achieve the desired architecture is one of the concerns of designers and users of residential spaces. But it will not be possible to carry out such a process in a limited time with low cost, high efficiency, and taking into account all the very extensive and fluid rules and regulations, by specialized manpower. Therefore, the purpose of this study is to explain the theoretical model of divisions and arrangement of spaces by the automatic design intelligence of architectural plans, based on constraints, criteria, standards, needs, and common dimensions of urban parts using mathematical formulas and data methods. Mining has been done to create diverse cellular structures to present the arrangement of spaces. Accordingly, the research method is based on distinctive research and quantitative analysis, along with the use of machine learning algorithms which is based on the approach of hierarchical structure, regional division, and spatial allocation. Furthermore, the results of this research show that a theoretical model can be presented with computational methods, machine learning algorithms, programming language, and a common urban land matrix, which leads to the creation of elementary intuitions in machines and for the validation of production samples. Based on the modules of squares and rectangles, it is possible to calculate the slope of diameters and sides to be vertical and to prove the parallelism of the design lines.