Provides enhanced support for hybrid digital mailroom solutions by classifying and extracting PDF documents created from faxes and office documents using Kofax Capture import connectors. The system utilizes the PDF text layer so that the need for OCR is eliminated. With this capability, organizations can deploy Kofax Transformation Modules as a single solution to handle all documents, paper or electronic.
Allows different configurations for different processing steps – such as classification and extraction of forms, and extraction of correspondence – reducing both solution complexity and configuration and maintenance costs. Each configuration can be created and maintained separately, so the solution is easier to manage.
Supports parallel development of configuration files, which allows multiple developers to work on the same solution at the same time, reducing timescales and allowing specialized skills to be leveraged more efficiently.
Provides a new separation benchmarking tool and improves the classification and extraction benchmarking tools, adding the ability to easily compare results before and after making changes to classification settings. The benchmarking data serves administrators in determining if performance has improved. This capability helps to ensure that the highest accuracy is achieved and maintained on all document types, thereby increasing ROI.
Provides a new tool to identify and resolve conflicts between documents used for extraction training, thereby improving learning and performance and delivering greater extraction accuracy without the need to add new training samples.
Supports matching and validation of extracted data against databases containing millions of records using a dedicated server. Features super-fast query response support for very large databases with 64-bit support, automatic update of data sources, load balancing across multiple servers, automatic scheduled database updates, and other high availability features.
Supports multi-purchase order invoices to increase automatic matching and straight-through processing rates, thereby reducing processing costs and providing additional learning options.
Validation client allows users to attach "sticky notes" to documents to pass information and comments to users of downstream business applications, improving efficiency by reducing the need for emails, phone calls or other communications.
Supports custom layouts and buttons, domain login, single sign-on, and annotations; preserves user defined settings such as username at login screen and UI settings between sessions; and provides a comprehensive set of batch editing options – all to improve ease of use, user experience, productivity and processing speed.
Provides new project settings to make it easier to provide a fully localized interface to users, including both menu items and labels.
Provides a new docking feature that can place the document image at the left, right, top or bottom to make maximum use of screen real estate and user workflow patterns. Enables users to override the default image position and zoom settings to suit their preference and preserve their settings for next time.
Clustering capability for KTM 6.0 minimizes the time to locate, identify, organize, label and file samples of each document type used for KTM training. Point it at a large directory of unsorted, unstructured document images and after a few mouse clicks it produces an organized file/folder training set you can use for content classification learning in KTM Project Builder. What used to take days or weeks, now takes just a few minutes!