Intelligent automation technology provider ABBYY has just dropped a new API for AI-driven optical character recognition it says will be more accurate than tools that rely on open source AI models.
The company introduced the ABBYY Document AI API today at an AI Summit it organized in Austin, Texas, saying it enables developers to transform unstructured business documents into more accurate structured data with a few lines of code.
“Developers struggle with extracting reliable data from documents and will often begin with general large language models for this process,” Amy Machado, senior research manager of Enterprise Content and Knowledge Management Strategies at IDC, said in a statement distributed at the event. “However, they quickly face challenges with hallucinations, data inconsistencies, and errors in document processing, and often lack support for multiple languages, handwriting recognition and complex document structures. There is a need for purpose-built solutions specifically designed for document processing that prioritizes easy integration, flexibility, scalability, accuracy, and consistency.”
ABBYY says its Document AI API is a solution that serves those needs by pre-training the tools to extract data from documents during processes including KYC, account openings, customs clearance, invoice processing, expense management and order processing.
发布者：Dr.Durant，转转请注明出处：https://robotalks.cn/abbyy-unveils-api-for-ai-driven-ocr/
