Features & Roadmap

Ability to detect, scan and comprehend a variety of documents

AISAY can process documents such as handwritten notes, printed articles, multilingual text, and structured/unstructured documents. Unlike traditional Optical Character Recognition (OCR) systems, AISAY can provide structured responses for documents such as images (JPEG, PNG, TFIF) and PDF files. For documents issued by local entities (businesses, governments, and institutions), AISAY can even fine-tune the documents prior to processing.

AISAY supports the following document types, but other document types can be supported on request.

1. ID Documents such as NRIC/employment pass/S pass/work permit/dependent pass/long-term visit pass/student pass/driver’s license/11B or passports (machine-readable)
2. Agreements and contracts
3. Invoices/receipts/delivery orders
4. Bank statements

System support for documents with data classification of up to RESTRICTED/SENSITIVE NORMAL

AISAY is under active development and can support processing of documents with security and data classification of up to RESTRICTED/SENSITIVE NORMAL. Moving forward, more document types will be supported.

Improved data accuracy with pre-filled forms

AISAY allows users to pre-fill digital forms with key information retrieved from uploaded documents. This reduces manual form filling, which tends to be error-prone, and ensures that government agencies and businesses receive a higher quality input of data.

Seamless verification of data fields across multiple documents

Agency officers may need to verify information across different documents for processing purposes. In the case of grant processing, with AISAY’s Document Matching API services, we can ascertain whether a field ( e.g. Company Name) matches across bank statements, invoices and receipts to reduce the need for manual eye-balling.

Automation of workflows with document matching API services and confidence scores

Confidence scores allow users to determine the level of human intervention required at a task. Workflows with high confidence scores may be automated, which will reduce the need for manual interventions.

Scalable solution for large file sizes

AISAY is hosted serverless on the Cloud, so scaling in volume can be handled. It can cater for large file sizes due to its ability to run extraction processes asynchronously.

• Partner with agencies to develop custom AI models that support the data extraction of a wide range of document types, aimed at automating processes and enhancing system efficiency.
• Build an advanced document classification model capable of accurately detecting and identifying various document types to ensure precise document handling.
• Targeted launch of a new web application by Q4 2024 for Public Officers to leverage AISAY services, enabling efficient processing of bulk documents through an intuitive drag-and-drop interface.