Ertas for Construction BOQ Extraction

The Challenge

Construction projects rely on Bills of Quantities (BOQ) — detailed lists of materials, labor, and equipment needed for a project — as the foundation for cost estimation, tendering, and project management. BOQs are typically embedded in complex documents: tender packages with hundreds of pages, engineering specifications with nested references, and price schedules in inconsistent formats from different contractors. Extracting structured BOQ data from these documents is a manual process that takes quantity surveyors days or weeks per project.

The challenge is compounded by the diversity of BOQ formats across different standards (NRM, SMM7, POMI), countries, and trades. A civil works BOQ uses different measurement units and item descriptions than an MEP (mechanical, electrical, plumbing) BOQ. Subcontractor quotes often use their own item numbering and description conventions that do not map directly to the project BOQ structure. Generic data extraction tools cannot handle this domain because construction terminology is highly specialized — terms like 'preliminaries,' 'provisional sums,' 'prime cost items,' and 'daywork rates' have specific meanings that determine how line items should be classified and priced.

The Solution

Ertas enables construction firms and quantity surveying practices to fine-tune extraction models on their specific BOQ formats, measurement standards, and trade conventions. With Ertas Studio, teams train models on annotated BOQ documents — where each document is paired with the structured data that quantity surveyors extracted from it — teaching the model to identify line items, quantities, units, rates, and specifications across the formats they actually encounter.

The fine-tuned model handles the real-world messiness of construction documents: merged table cells, multi-line item descriptions, nested sub-items, cross-references to specification clauses, and provisional sum items that need special treatment. Deployed through Ertas Cloud or locally, the model processes incoming tender documents and outputs structured BOQ data in the firm's standard format — ready for import into cost estimation software. For tender comparison, the model normalizes different subcontractor formats into a common structure, enabling side-by-side comparison that previously required hours of manual reformatting.

Key Features

Example Workflow

A quantity surveying firm processes 40 tender packages monthly, each containing 100-500 page BOQ documents across multiple trades. The team annotates 3,000 BOQ pages from historical projects with structured extractions — item numbers, descriptions, quantities, units, and rates — and uploads them to Ertas Vault. Using Ertas Studio, they fine-tune a model specializing in their primary trades: civil works, structural steel, and MEP. When a new tender package arrives, the document is OCR-processed and sent to the extraction model, which outputs structured BOQ data in the firm's standard template format. Quantity surveyors review the extraction, correcting any errors and handling items that require professional judgment (provisional sums, alternative specifications). BOQ extraction time drops from 3 days per tender to 4 hours, allowing the firm to bid on 50% more projects without additional staff. The structured data feeds directly into their cost estimation software, eliminating manual data entry errors.