I-Corps: Scheduling software to enable visualization of changes for the construction industry

这个I-Corps项目的更广泛的影响/商业潜力是开发一种软件工具，它将帮助团队有效地管理变更及其对项目进度和资源的负面影响。当前低效的管理和缺乏工具来最小化变更带来的负面影响，损害了项目及其涉众的现金流。变更还会大大延迟项目并导致成本超支。最近的一项研究表明，美国建筑业每年在变更订单上花费500亿美元。除了花费在改变的直接成本上的钱，例如材料和资源，由于时间的低效使用和缺乏优化的计划程序，这些成本中的大部分都被浪费了。减少变化对工期和成本的影响是至关重要的，可以帮助建筑公司为他们的项目和环境制定可持续发展战略。此外，由纳税人的钱资助的基础设施项目可能会利用这一工具作为其价值工程机制的一部分，以获得更多的相同水平的资源配置。这个I-Corps项目是基于一种基于人工智能（AI）的可视化方法的开发，该方法可以帮助项目团队有效地管理任何项目的变更事件。当前的可视化工具不具备在所有三个方面分析变更顺序的影响的能力：时间、空间和资源。所提出的方法利用先进的自然语言处理（NLP）和机器学习来标记和表征变化事件数据，从而利用对进度、工作空间和资源的集成方法。与传统方法相比，这些先进的人工智能驱动的计算技术可以帮助项目团队在很短的时间内对变更进行可视化、审查和计划。更具体地说，该方法使用意大利面图可视化变更事件对相关计划活动的单个和累积的直接和间接影响，其中意大利面线和变更事件是根据底层资源的使用进行颜色编码的。它还可视化了空间和资源的利用，潜在的冲突和由于变化事件的影响而过度利用。目标是创建一系列计划选项，以允许项目团队选择最小化成本和持续时间影响的顺序。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is the development of a software tool that would help teams to effectively manage changes and their negative impacts on project schedules and resources. The current inefficient management and lack of tools to minimize negative impacts from changes hurts the cash flow of a project and its stakeholders. Changes also delay projects significantly and lead to cost overruns. A recent study showed that the US construction industry spends $50 billion on change orders annually. Aside from the money spent on the direct cost of the change, such as materials and resources, much of these costs are wasted due to an inefficient use of time and lack of optimized planning procedures. Reducing the impacts of changes on duration and cost is paramount and may help construction companies to develop sustainability strategies for their projects and the environment. Further, infrastructure projects funded by taxpayers’ money may leverage this tool as part of their value engineering mechanisms to gain more with the same level of resource allocation.This I-Corps project is based on the development of an artificial intelligence (AI)-based visualization method that may assist project teams to effectively manage change events on any project. Current visualization tools do not have the capacity to analyze the impact of change orders on all three fronts: temporal, spatial, and resources. The proposed method leverages the integrated approach towards schedule, workspace, and resources using advanced natural language processing (NLP) and machine learning to label and characterize change events data. These advanced AI-driven computational techniques may help project teams to visualize, review, and plan for changes within a fraction of time as compared to traditional methods. More specifically, this method visualizes the individual and cumulative direct and indirect impacts of change events on associated schedule activities using spaghetti graphs in which spaghetti lines and the change events are color coded by the usage of underlying resources. It also visualizes the utilization of space and resources, the underlying conflicts and over utilization due to the impacts of change events. The goal is to create an array of planning options to allow project teams to choose a sequence that minimizes both cost and duration impact.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.