Synchronized Document Panes for Faster Construction Submittal Review
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of reviewing and processing submittals in construction projects is lengthy and tedious, often leading to incomplete or inaccurate reviews that can affect project quality, schedules, and budgets, due to the voluminous nature of project documents and the need for extensive human effort to ensure compliance with project requirements.
Innovation Solution
A system and method utilizing AI models, specifically Large Language Models (LLMs) with prompt engineering and user-specific training, to break down queries into smaller chunks, compare submittal documents against project requirements, and provide a tripartite interface for efficient and accurate submittal review, incorporating features like optical character recognition and user-specific insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual review methods are used, then review accuracy can be maintained through expert judgment, but review time becomes excessively long and productivity is low
Solution Approach 1:
The patent segments the review process into distinct phases: AI-powered document analysis, requirement matching, compliance checking, and human expert validation. This segmentation allows automated processing of routine tasks while preserving human judgment for complex decisions, thereby improving both speed and accuracy simultaneously
Solution Approach 2:
The patent introduces an AI system as an intermediary between the submittal documents and human reviewers. This intermediary performs preliminary analysis, identifies compliance issues, and prepares draft reviews, which human experts then validate and refine. This intermediary role significantly reduces review time while maintaining accuracy through human oversight
2Reliability
If comprehensive document analysis is performed to ensure complete compliance checking, then review accuracy improves, but the time and resources required increase significantly
Solution Approach 1:
The patent performs preliminary actions by having the AI system conduct comprehensive document analysis, requirement extraction, and compliance checking before human reviewers begin their work. This preliminary processing ensures that all compliance issues are identified in advance, allowing human experts to focus only on validation and complex judgment calls, thereby reducing overall review time while maintaining completeness
Solution Approach 2:
The patent replaces manual mechanical review processes with AI-powered automated analysis systems. The AI system efficiently processes voluminous project documents, extracts requirements, and performs compliance checking at speeds impossible for human reviewers, thereby ensuring comprehensive checking without proportionally increasing review duration
3Loss of information
If human experts manually review voluminous project documents, then understanding of project requirements can be achieved, but the complexity of the review process increases and requires extensive expertise
Solution Approach 1:
The patent implements self-service by enabling the AI system to autonomously analyze project documents, extract requirements, and identify compliance issues without requiring deep human expertise for these routine tasks. The system serves itself by performing preliminary analysis and preparation, freeing human experts from manual document review and reducing the complexity barrier for effective compliance checking
4Measurement precision
If traditional submittal review processes are used, then thorough evaluation can be performed, but the quantity of documents to be reviewed creates a bottleneck that reduces overall productivity
Solution Approach 1:
The patent creates digital copies and representations of project documents and requirements that can be efficiently processed by AI systems. These digital representations enable automated analysis, matching, and compliance checking of voluminous documents without requiring proportional increases in human review capacity, thereby maintaining evaluation thoroughness while dramatically improving review throughput
Data Source
AI summary
A platform that generates submittal reviews electronically for various construction projects. Embodiments include receiving project submittals by the reviewer, inputting the submittal in a web application interface, receiving the output in a specific format, reviewing the submittal review generated then downloading the reviewed submittal and handing it to a subsequent party for review. In some embodiments, during project initialization, project specifications and drawings are ingested. The project specifications and drawings are processed to extract relevant content, which is used to perform each submittal review. Artificial intelligence (AI) models are prompted through a series of dependent prompt engineered queries. The queries to the AI are broken into preconfigured pieces which improves the accuracy of the AI model. In order to break down the AI queries, the platform builds a program structure around making required calls to an AI API that are tuned for a particular program goal.