IBM Software Information Management. Automating information capture with advanced, intelligent document recognition technology

Similar documents
IBM Software Datacap Taskmaster Capture

Cognitive enterprise archive and retrieval

IBM Tivoli Endpoint Manager for Software Use Analysis

IBM Tivoli Endpoint Manager for Lifecycle Management

Manage more data, meet healthcare regulations and improve availability

IBM Rational Systems Developer, Version 7.0

Planning and design for smarter cities

Building smart products: best practices for multicore software development

Advanced Recognition

Make smart business decisions when they matter most September IBM Active Content: Linking ECM and BPM to enable the adaptive enterprise

Innovative solutions to simplify your business. IBM System i5 Family

Achieve greater efficiency in asset management by managing all your asset types on a single platform.

IBM _` iseries systems Retail

Oracle Financials Cloud

IBM Sterling B2B Integrator

THE SOCIAL ENTERPRISE

IBM Sterling Order Management drop ship capabilities

Synergy Document Management. Maximize Your Time and Minimize Your Clutter

Module 2 - Kofax Capture Overview

IBM Tivoli Monitoring

ENTERPRISE CONTENT MANAGEMENT

IBM Tivoli Composite Application Manager for Applications Diagnostics

IBM Cognos Controller

ORACLE FUSION FINANCIALS CLOUD SERVICE

IBM Sterling Gentran:Server for Windows

Next generation Managed Print Services

The Five Phases of Capture Where do you land in the capture continuum?

Advanced Capture and Automated Indexing. Tom Hoffman, National Channel Account Manager Capture Solutions, Hyland Software

Work better, faster and smarter

ABBYY FLEXICAPTURE. Smart Capture for Smarter Processes

The journey to procurement excellence

Streamline your Business Processes with Barcodes:

TOPCALL SOLUTION FOR CONTENT CAPTURE & DELIVERY

Infor SunSystems. Grow with flexibility. Integrate

IBM Emptoris Rivermine Telecom Expense Management solutions

Infor CloudSuite Business

Reining in Maverick Spend. 3 Ways to Save Costs and Improve Compliance with e-procurement

Creating High-Speed Content Archival and Retrieval Solutions Using IBM Content Manager OnDemand IBM Redbooks Solution Guide

Designed to Deliver Value

Speed to Value with Documentum xcelerated Composition Platform

Oracle CPQ Cloud Solutions for enterprises and Fast Growing Companies

EngageOne INTERACTIVE COMMUNICATIONS. An Advanced Interactive Technology Solution for a New Era of Enterprise Communications

The Benefits of a Unified Enterprise Content Management Platform. An Oracle White Paper February 2007

IBM Grid Offering for Analytics Acceleration: Customer Insight in Banking

NetSuite Software Case Studies. Copyright 2017, Oracle and/or its affiliates. All rights reserved.

Automate your document processing and data capture.

RECEIVABLES360 INTEGRATED RECEIVABLES FOR CORPORATIONS

Objectif Lune. From Surviving to Thriving. How digital tools can assist print service providers

IBM Planning Analytics

Optimizing Asset Value and Performance with Enterprise Content Management

IBM z/tpf To support your business objectives. Optimize high-volume transaction processing on the mainframe.

What's Shaping the Future of Enterprise Content. Management? JOHN O MELIA

Adobe Experience Manager Forms

A white paper discussing the advantages of Digital Mailrooms

Xerox DocuShare 7.0 Content Management Platform. Enterprise content management for every organization.

OpenText Captiva. Redefine Your Business Through Intelligent Enterprise Capture

IBM Cognos TM1. Highlights. IBM Software Business Analytics

Billing Strategies for. Innovative Business Models

2 Business Processes and Forms with Office SharePoint Server 2007

IBM Web Content Solutions

Bankia gains innovative insights to boost competitiveness

IBM Cognos Express Breakthrough BI and planning for workgroups and midsize organizations

Can I reduce manual data entry by using an automated information capture system?

Technical Information

Help Reduce Paper with nq360 Document Scanning and Routing

Quick Facts. Driven by Science. 3 Locations. 26 Years. R&D & Innovation Teams. 42 Country Footprint. 9 Languages.

IBM WebSphere Information Integrator Content Edition Version 8.2

IBM Business Analytics

IBM MaaS360 Content Suite

Security intelligence for service providers

Accelerate Results with an Intelligent Scanning Strategy

Arcadia Operating: Intelligent Well File Streamlines Acquisition Process

Skelta. Document Management Solution. Business Process Management for All POWERED BY SKELTA BPM.

Solutions. Cash & Logistics Intelligent and Integrated Solutions to Optimize Currency Levels, Reduce Expenses and Improve Control

The Smart SOA approach: Innovate, accelerate, differentiate To support your business objectives. Smart SOA: The experienced approach.

Process Automation for Accounts Payable O R A C L E W H I T E P A P E R N O V E M B E R

KODAK i4850 Scanner Kodak Alaris Capture Pro Software Services by Kodak Alaris

IBM Tivoli OMEGAMON XE for. WebSphere Business Integration. Optimize management of your messaging infrastructure. Highlights

Session 2.9: Tivoli Process Managers

Network and Route Performance Management

Smart Mortgage Lending

BPO and Service Bureau Operations

Enabling Collaboration in Insurance

{ One Platform Solution Document Scanning }

Seize Opportunities. SAP Solution Overview SAP Business Suite

Sage MAS 90 and 200 Product Update 2 Delivers Added Value!

PeopleSoft Time and Labor

BEST PRACTICES IN AP AUTOMATION

Oracle Human Resources includes local extensions for more than 19 countries contain legislative and cultural functionality for each country.

A New Approach to Managing Information: An Introduction to Advanced Case Management. Session Number Jeff Douglas, Sr. Product Manager, IBM

The Case for Dynamic Publishing

Oracle Business Intelligence Publisher 12c

ORACLE FINANCIAL SERVICES DATA WAREHOUSE

A technical discussion of performance and availability December IBM Tivoli Monitoring solutions for performance and availability

Nuance Power PDF is PDF uncompromised.

Document Capture Solution

JD Edwards UPK Pre-built Content for EnterpriseOne 9.2

Sage ERP Solutions I White Paper

Unleash the Power of Mainframe Data in the Application Economy

Transcription:

IBM Software Information Management Automating information capture with advanced, intelligent document recognition technology

2 Automating information capture with advanced, intelligent document recognition technology Introduction Information is one of the most valuable assets for businesses, second only to the people who make up the organization itself. Therefore, the better companies can manage and leverage the information housed inside the walls of the company, the more value they can gain from that information. Ultimately, by developing and implementing business and technology strategies that can in effect unlock the business value of their information, companies can achieve sustainable competitive advantage. Valuable information that employees and customers depend on exists in countless places across the enterprise in databases, on employee hard drives, in e-mails, and elsewhere. Yet even with the advent of technology and digital formats, companies still count on paper in the form of documents for many of their internal processes as well as communications and transactions with the outside world. In fact, documents continue to drive a large percentage of any company s business processes. Day to day, businesses rely heavily on the information comprising paper documents such as contracts, application forms, orders, policies and practices, correspondence, and reports. Availability of the information in these structured and unstructured documents is critical to daily business functions. Poorly managed, hard-to-access and especially digitally unavailable data and information originating in documents greatly reduce the value of key business information. Companies need the right information, from anywhere in the company, at the right time to make the right decisions. Therefore, many companies turn to enterprise content management (ECM) solutions for managing content, while at the same time optimizing business processes and enabling compliance. Increasingly, organizations benefiting from ECM processes are beginning to recognize the need for advanced information capture technologies to scan their documents so they can capture, secure and distribute information based on specific business process needs. To manage capture costs and see the best return on their ECM investments, organizations must be able to extract information automatically from documents into an automated business process. To enable successful business transactions and regulatory compliance, companies must accurately and appropriately process important information using three key automated functions of advanced data capture: recognition, classification and separation. The most sophisticated information capture technologies eliminate the costly manual processes associated with most capture solutions, enabling businesses to automatically process documents that have varying degrees of structure. With intelligent capture capabilities, companies can leverage advanced document recognition, classification, separation and indexing to efficiently move the content into the workflow, database or content management system. IBM FileNet Capture Advanced Document Recognition (Capture ADR), solves the paper problem by automatically capturing, recognizing, classifying, correcting, validating, reviewing, separating and committing data on forms and in documents. The result is accelerated business processes and the transformation of paper documents into accurate, retrievable information accessible from local desktops and remote sites across the organization.

IIBM Software 3 Information capture business challenges Though companies inherently depend on them, paper documents present sizeable costs and risks to organizations. Regardless of the size of an organization or whether or not the company is experiencing growth, paper nonetheless continually increases in volume, since business processes and transactions both require and create documents on a daily basis. Yet paper is cumbersome and expensive to use and store. Remote workforces face particular challenges with information stored on paper because they need instant access to information. Additionally, upholding corporate policies and maintaining regulatory compliance can be difficult or virtually impossible with massive amounts of information in paper form spread across the organization. Companies face many challenges associated with information management, and especially managing paper documents, forms and e-documents, and turn to information capture solutions when they need to: Find an intelligent method for centralizing information management when information and workers are dispersed across the organization. Eliminate growing paper storage and retrieval expenses. Reduce the cost and error rate associated with manual data entry. Eliminate slow manual access to stored information. Contend with data that arrives in multiple forms and formats. Capture business-critical data at multiple locations. Drawbacks of existing capture solutions Businesses make the initial ECM investment to improve business process efficiency. In these purchasing decisions, capture is often an afterthought because the benefits are seen in terms of managing content, rather than getting content into the system. However, though an estimated 80 percent of the initial investment for ECM solutions is in the platform and only 20 percent is in the capture functionality, 80 percent of the ongoing total cost of ownership for an ECM investment is in the capture function, because so much of the capture process is still done manually. Businesses can expand their batch capture solutions to include intelligent capture technologies to extract key information embedded in countless types of documents. Yet, depending on the methods and technologies used by businesses, the information capture process can be costly and time consuming. Companies can spend considerable time and money sorting the documents prior to scanning. In document preparation, scan operators typically have to print and insert document separator sheets and manually classify the documents in order to extract critical data and metadata. Because manual processes are subject to errors, manual separation can lead to the need for further, corrected separation and identification. Also, teams of individuals often have to index documents and content manually before committing the documents to their target repositories. Classification and recognition functions can also fall short. Batch capture solutions feature rules-based classification but not analytics-based and text-level classification, which limits classification to those documents that fall within established, preset rules. In addition, most information capture platforms feature one or two optical character recognition (OCR) engines, whereas a multiple-engine configuration provides higher recognition rates. Many information capture solutions have significantly lower performance committal rates than others, committing fewer documents to their targeted repositories than the more advanced solutions can deliver in the same amount of time.

4 Automating information capture with advanced, intelligent document recognition technology ECM solutions, including information capture and intelligent capture solutions when from a variety of vendors can be difficult to integrate within the ECM platform. So there is a distinct advantage to leveraging a capture solution delivered by the ECM platform vendor, given the obvious potential for tighter integration across the ECM deployment. Advanced document recognition: Automation through intelligent capture The high volume of content today s organizations contend with calls for an enterprise-wide document capture solution that can increase data integrity, reduce costs, improve departmental efficiency and help meet strategic business objectives. A sophisticated, automated intelligent capture solution can enable businesses to greatly improve information capture efficiencies. With a flexible, intelligent capture solution, companies can automate the classification, sorting and separation of paper and electronic documents, along with the extraction and validation of the information they contain. To align with business and content management objectives, organizations can customize their new solution at time of installation and over time as requirements and business processes evolve. Or if looking for enhanced batch capture capabilities, they can upgrade their existing information capture solution to a more powerful document and data capture solution through adding intelligent capture technologies. With an intelligent capture solution, companies can increase document processing capacity while reducing head count. They can also increase accuracy and speed when processing forms and other documents. Plus, the solution can reduce or eliminate costly and time-consuming manual document processing steps, such as presort, separator page insertion and data entry. A key advantage of the leading capture technologies is automatically separating multipage documents and eliminating the need for separator sheets in document preparation. The importance of capture solution flexibility Flexibility of the capture solution is directly proportional to the degree of solution intelligence, as typical solutions often restrict forms processing. Documents come in various forms, on a continuum of structured, semistructured and unstructured forms. On this continuum, structured forms can be recognized with the greatest of ease, with unstructured being the most difficult to recognize and classify. This variance can hinder or even prevent automated document processing. However, the introduction of advanced intelligence in software makes it possible to automate most of the capture process for these different types of forms. Through advanced capture automation, companies have the tools to recognize structured, semistructured and unstructured forms for automated input into business processes, significantly increasing productivity and reducing operating costs. With the right technology, businesses can extract data from preprinted forms as well as correspondence and other unstructured documents of varying page length. Intelligent capture solutions automatically classify documents by type based on content or format. They can consistently and accurately index documents for improved records management. Additionally, they help ensure data accuracy with built-in validation throughout the capture process, improving document case handling and customer service. Recognition, classification and separation Handling paper documents is extremely costly for organizations, considering that processing these documents typically involves manual labor for photocopying, filing, searching for filed documents, recreating lost documents, and more. For these reasons, high-volume document scanning to convert thousands and even millions of paper pages into usable digital information makes incredibly good business sense. Yet for organizations that scan and capture their documents, many spend excessive time and money sorting the documents prior to scanning, adding document separation sheets, and manually

IIBM Software 5 classifying the documents to enable functional data extraction. Businesses can benefit from automating key information capture processes often performed inefficiently and typically performed manually. The more automated the image capture capabilities of the capture solution, the greater the short-term and long-term cost savings and return on the ECM investment. Recognition Recognition is the automatic extraction of data from documents, which involves searching intelligently for the information needed. An unattended application, typically installed and run as a Microsoft Windows Service, performs the recognition function. Automated recognition expedites business processes and can automatically initiate transactions, for reduced processing time, increased productivity and lower operational costs. Classification During classification, documents are classified automatically by content, and then are routed to the correct business process or workflow queue without the need for presorting. This greatly reduces document handling costs. The capture process involves various classification methods, and multiple classification methods can be used together, though occur sequentially. These include the following: Image classification Based on the overall layout and structure of a document, this involves classifying by such document features as lines, boxes, logos and placement of text. Text classification Based on detailed analysis of the text content of the document and page. Rules-based classification Performed by searching for specific data or keywords independent of layout. Templated classification Determined by the presence of one or more marks, barcodes or items of text in predefined locations in the document. Separation The recognition process involves using form factors and content to determine how a batch of pages is split into separate documents. In an advanced separation process, batches of single- and multiple-page documents are scanned without the need for preprinted separator sheets to be inserted during document preparation. Automated separation eliminates printing costs by eliminating separator pages, and reduces batch preparation time and its associated costs, while improving data quality in the capture process. Broad application of information capture technology For organizations wanting to automate their intelligent capture processes, their information capture solution should support a wide variety of languages, business use cases, user environments and content input. Users in many industries can take advantage of flexible, scalable information capture technologies, including the fields of energy, financial services, government, insurance, healthcare, manufacturing, oil and gas, professional services, pharmaceutical, retail and telecommunications. Many industries are adopting intelligent capture capabilities to streamline processes, improve operational efficiencies and reduce costs through many different applications of the technology. Several examples include the following applications: Invoice processing Information capture technology provides the building blocks for the payables application and associated invoices. With free-form processing, there is no need to set up form templates for each invoice type. To allow invoicing flexibility, the solution leverages database lookups for any additional required fields. Records management Through intelligent capture processes, companies can apply business rules, automate records classification and extract meaningful content from documents for use in records management even before the content reaches the ECM repository. By automatically indexing important documents while at the same time accelerating the declaration process, businesses can reduce human error and help ensure compliance.

6 Automating information capture with advanced, intelligent document recognition technology Mortgage processing This typically paper-heavy process involves many types of documents, such as loan origination applications, tax escrow requests, property appraisals, and more. Capture technologies can intelligently classify and separate these documents when scanning, as well as verify that all necessary documents are included in the customer s file. Plus, powerful free-form technology can extract and repurpose any inherent data during the lifecycle of the process. Mail room Paper documents, including countless types of forms, invoices and correspondence, can bury those tasked with ensuring that these mailbag items get delivered to their proper destinations. Though the days of manually sorting all mail are a thing of the past, sophisticated capture technology can enable more intelligent mail room capabilities than ever before. Intelligent capture performs the classification, separation and free-form extraction to automatically identify each document type and then automatically route individual pieces to the appropriate workflow process. IBM FileNet Capture ADR: Automating the capture process IBM FileNet Capture Advanced Document Recognition, an extension to IBM FileNet Capture Professional, adds powerful capabilities for automatically extracting data from images efficiently and cost-effectively. The solution provides advanced document recognition, classification, and separation, enabling the automated processing of documents to be managed through IBM FileNet ECM platforms. IBM FileNet Capture ADR can either extend the capabilities of IBM FileNet Capture Professional or serve as a standalone application. IBM FileNet Capture ADR can extend the capabilities of IBM FileNet Capture Professional, and allow businesses to maximize operator efficiency and reduce costs through: Extracting handwritten and machine-printed data, as well as bar codes, check boxes and tabular data. Capturing all types of documents regardless of format, including structured, semistructured and unstructured types. Identifying boundaries between multiple unstructured documents in a single batch, replacing the traditional process of inserting separator pages. Quickly and easily reviewing documents prior to extraction to help ensure correct classification and separation. Validating documents and data at the document, field and character level, with single character correction capability. IBM FileNet Capture ADR automatically captures, recognizes, classifies, corrects, validates, reviews, separates and commits data on forms and documents through automated intelligent capture capabilities. Capture ADR offers core recognition technologies, including OCR, intelligent character recognition (ICR) and optical mark reading. The solution enables sophisticated capture functions, such as address extraction, on-the-fly data location, spreadsheet analysis, intelligent data learning, data validation and checksum. Additionally, Capture ADR offers important capabilities including page segmentation, forms layout and background removal. Automating key capture processes By eliminating costly capture processes, IBM FileNet Capture ADR streamlines the image capture process and enables companies to automatically process documents that are structured, or have little structure or even no structure at all. The advanced recognition, classification, separation and indexing capabilities transform handwritten and printed data from scanned images in fixed and free-form documents into valuable, usable enterprise-wide information.

IIBM Software 7 Automatic capture and recognition of data from documents Capture ADR provides automated recognition through OCR, ICR, database lookups and data validation. The solution generates straight-through processing, speeding up business processes and initiating transactions automatically. This results in reduced processing time and operational costs, along with increased productivity. Automatic classification of documents by content The Capture ADR solution automatically assigns a type to each document, either for exporting the document to the final repository or for use during extraction. By routing documents to the correct target business process or workflow queue without the need for presorting, Capture ADR reduces document handling costs. Companies can configure Capture ADR to classify documents directly or as a result of page classification and document separation. Automatic separation of multipage documents Separation of documents can be a significant expense in a high-volume capture system. Though most separation processes consist of manually inserting separator sheets to distinguish between the beginning of one document and the start of the next, Capture ADR solves this costly problem for companies by using software, rather than labor, to separate documents. The solution scans and separates batches of multipage documents without having to insert preprinted separator sheets between the documents. This eliminates printing costs, and reduces batch preparation time and the resources needed to perform manual indexing. Automatic indexing of documents Capture ADR simplifies the indexing process by capturing index data from each document, dramatically reducing the need for costly manual keying and enabling powerful search for the captured information and documents. This reduces the ongoing cost of running any document management system by improving information retrieval functions. The automation payoff For businesses taking advantage of ECM solutions to optimize business processes, enable compliance and make better decisions faster, IBM FileNet Capture ADR can provide additional benefits. Capture ADR provides greater return on investment than traditional key to image applications by automating human-intensive processes with easy-to-use business rules and advanced analytics. The solution also facilitates content-enabled business process management applications by extracting important data from anywhere on an image. Advanced, automated recognition, classification and separation capabilities streamline and greatly improve the capture process, reduce costs and enhance the value of information originating in paper documents. Labor costs go down with fewer data entry operators needed for the capture process. Overhead costs are reduced with the streamlined workforce in turn lowering equipment and workstation requirements. Employee productivity rises through the elimination of repetitive tasks along with a significantly greater number of forms processed per operator. Decreased absenteeism and reduced workers compensation costs result from fewer operator repetitive stress injuries. Simplified operator readability enables higher data accuracy. With quicker access to sound data and faster turnaround of deliverables, cash flow is accelerated, especially when improved capture efficiencies translate to faster time to market.

Conclusion Accurate, readily accessible business information is integral to every organization s daily business functions. Yet information buried in business documents such as contracts, invoices, applications and many others can present challenges for companies. Consequently, today s competitive organizations and government agencies are developing strategies and establishing systems that meet business use needs and can handle the influx of data and enormous volume of content scattered across the enterprise in countless paper documents. IBM FileNet Capture ADR enables businesses to meet the growing demands created by time-sensitive, mission-critical processes that involve paper documents. Enterprises with a high volume of documents of multiple types and extensive document-extraction needs will benefit from Capture ADR and can see significant business advantages including repetitive task elimination, increased productivity, quicker turnaround, reduced operating costs, and a greater return on their ECM and intelligent capture investments. Then, these organizations can ensure that information remains a valuable asset rather than a costly, cumbersome deterrent to business success. Copyright IBM Corporation 2010 IBM Corporation Software Group 3565 Harbor Boulevard Costa Mesa, CA 92626-1420 U.S.A. Produced in the United States of America March 2010 All Rights Reserved IBM, the IBM logo, ibm.com, and FileNet are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the Web at Copyright and trademark information at ibm.com/legal/copytrade.shtml Microsoft and Windows are registered trademarks of Microsoft Corporation in the United States, other countries or both. Java and all Java-based trademarks are trademarks Sun Microsystems, Inc. in the United States, other countries or both. Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both. UNIX is a registered trademark of The Open Group in the United States and other countries. References in this publication to IBM products or services do not imply that IBM intends to make them available in all countries in which IBM operates. The information contained in this documentation is provided for informational purposes only. While efforts were made to verify the completeness and accuracy of the information contained in this documentation, it is provided as is without warranty of any kind, express or implied. In addition, this information is based on IBM s current product plans and strategy, which are subject to change by IBM without notice. IBM shall not be responsible for any damages arising out of the use of, or otherwise related to, this documentation or any other documentation. Nothing contained in this documentation is intended to, nor shall have the effect of, creating any warranties or representations from IBM (or its suppliers or licensors), or altering the terms and conditions of the applicable license agreement governing the use of IBM software. Each IBM customer is responsible for ensuring its own compliance with legal requirements. It is the customer s sole responsibility to obtain advice of competent legal counsel as to the identification and interpretation of any relevant laws and regulatory requirements that may affect the customer s business and any actions the customer may need to take to comply with such laws. IBM does not provide legal advice or represent or warrant that its services or products will ensure that the customer is in compliance with any law. Please Recycle IMW14025-USEN-01