Since entering the 21st century, the construction industry has developed faster and faster, and more and more technologies have been applied in the construction industry. BIM technology (Building Information Modeling) was born in this environment. The application of BIM technology can greatly improve the efficiency of cost management and help achieve the goal of cost management. But through BIM to realize project cost management, there is still no good solution. In order to solve this problem, this paper puts forward the concept of WBS structure applied to construction projects by studying the BoQ (Bill of Quantities) list based on BIM, and proposes the numbering method of the structure. The WBS (Work Breakdown Structure) structure proposed in this paper divides more than 5000 cost objects into 133 projects according to the type of work and project schedule. This structure helps to realize the application of BIM in project cost management. Although this article has studied more than 5000 data of three projects, it does not think that it can cover all cost objects in the existing construction industry. The purpose of this article is to propose a solution for cost and Process Control using BIM-based BoQ data.

BIM (Building Information Model/Modeling) is attracting attention not only as a unit technology, but also as a factor that can promote the transformation of the entire construction industry process. This study aims to investigate the status and cases of policy introduction and legalization of BIM in foreign countries for the advancement of their own construction industry, and to discover policy implications that can be applied to Korea. The first survey uncovered policy elements, and based on this, the second survey conducted an in-depth survey of experts in actual BIM service and research activities. Looking at each priority, BIM standardization, mandating BIM in projects, payment standard establishment, and PQ additional points were given the highest level of importance.

Recently, starting with smart construction research, interest in technology that automates construction site management using artificial intelligence technology is increasing. In order to automate construction site management, it is necessary to recognize objects such as construction equipment or workers, and automatically analyze the relationship between them. For example, if the relationship between workers and construction equipment at a construction site can be known, various use cases of site management such as work productivity, equipment operation status monitoring, and safety management can be implemented. This study derives a real-time object detection platform architecture that is required when performing construction site management using deep learning technology, which has recently been increasingly used. To this end, deep learning models that support real-time object detection are investigated and analyzed. Based on this, a deep learning model development process required for real-time construction site object detection is defined. Based on the defined process, a prototype that learns and detects construction site objects is developed, and then platform development considerations and architecture are derived from the results.

In construction sites, policies are changing considering the convergence of 3D scanning and BIM. In order to respond to this, it is urgent to develop guidelines for systematic collaboration methods that take into account the perspectives of practitioners. By participating in the delivery process using 3D scanning technology, tasks such as ordering, field scanning are defined in terms of mutual communications. Also, the collaboration process is about communications between off-site and on-site, such as feed-back using data and documents. In the future, we will propose guidelines based on such collaborative process models.

The 'public agency oil joint purchase system' was introduced to lower public sector oil prices and contribute to the stability of the overall consumer oil market. The present study used spatial regression to analyze the factors affecting domestic gasoline price, focusing on the impact of potential implicit collusion among gas stations in determining domestic gasoline prices. Also, this study investigated the effect the location characteristics of the market convention gas stations and government offices on the pressure of price competition in the market and the gasoline price at general gas stations. To summarize the results of the spatial lag model (SLM), the individual characteristics of gas stations such as convenience stores (+), self-fuelling (-), commercial areas (+), subway stations (+), population density (-), and sales (-) are correlated to gasoline prices at gas stations, and the institutional location factors of gas stations (+) affected the average of 9 won per liter, 11 won per liter. In order to solve these problems, the establishment of a monitoring system reflecting the location characteristics of the region and the ongoing review of the system should be carried out. In addition, separate, expanded and promotional measures should be prepared for the convenience of general and public oil buyers.

In the process of designing a building, the process of expressing the designer's ideas through images is essential. However, it is expensive and time consuming for a designer to analyze every individual case image to generate a hypothetical design. This study aims to visualize the basic design draft sketch made by the designer as a real image using the Generative Adversarial Network (GAN) based on the continuously accumulated architectural case images. Through this, we proposed a method to build an automated visualization environment using artificial intelligence and to visualize the architectural idea conceived by the designer in the architectural planning stage faster and cheaper than in the past. This study was conducted using approximately 20,000 images. In our study, the GAN algorithm allowed us to represent primary materials and shades within 2 seconds, but lacked accuracy in material and shading representation. We plan to add image data in the future to address this in a follow-up study.