Azure-Based Software Product for Intelligent Invoice Data Capture
About Our Client
The Client is a US-based provider of supplier relationship management software for mid-market and large businesses, with around 200,000 active users worldwide.
Challenge
The Client had a cloud product for accounts payable management and wanted to enrich it with a new module for intelligent invoice data capture to meet its customers' growing demand for further A/P automation. The module had to be fast and stable even under heavy load and to scale easily on demand.
For this, the Client sought a trustworthy tech partner experienced in distributed, modular software development and artificial intelligence to take over the full-cycle product development.
Solution
INNERLUXES's cross-functional team of a business analyst, web developers, and QA experts built the new module and integrated it with the Client's Azure-hosted product. Invoice processing worked as follows:
- Invoices arrived via integrated software (e.g., a vendor portal) or were emailed directly to the system as PDFs or scanned documents.
- Invoice data (vendor name, invoice number, date, PO number, description, quantity, unit price, and more) was extracted with OCR.
- Integrated Azure Cognitive Services classified and structured the extracted data and validated its completeness and accuracy.
- Invoices were then routed for approval and payment.
To enable easy scaling and granular improvements, the team decomposed the module into decentralized microservices. Azure Service Fabric handled service communication, discovery, monitoring, provisioning, and updating, and supported local testing in the complex microservices environment — keeping the module reliable, highly available, and fault-tolerant.
Results
The new module enabled smart, paperless invoice processing — improving accuracy and reducing the time spent on data entry and correction. The Client strengthened the loyalty of existing users, significantly expanded its audience, and saw the module perform stably as its customer base kept growing.
Technologies and Tools
.NET Core 3.1, React, Azure Service Fabric, Azure Service Bus, Azure Application Insights, Azure Cognitive Services, Azure SQL Database, Azure Virtual Machine Scale Sets, Azure Virtual Network, Azure Application Gateway, Azure Load Balancer, Azure Key Vault, Azure Storage, Azure Content Delivery Network (CDN).