Solution Use Cases
Information Transparency and Discovery
In the legal profession, words are currency, and outcomes can make or break a client. Improving eDiscovery results is no longer wishful thinking, but is required.
Concept Searching technologies provide the ability to automatically identify concepts, or phrases, in semi-structured and unstructured text. In turn, this enables legal professionals to search on concepts, phrases, topics, and subjects, and retrieve relevant results. Since search criteria are based on multi-word terms that represent meaning, the documents retrieved may be similar or related in nature, but may not even contain the search words used.
The technologies can isolate the key meanings normally expressed as proper nouns, nouns phrases, and verb phrases. Although linguistic products can do this, their performance is highly variable, depending upon the vocabulary and language in use. Concept Searching technologies are based on a statistical, language-independent model that can accept queries in natural language with the user typing words, phrases, or whole sentences. The system then analyzes the natural language query to extract the keywords and phrases, to identify the main concepts and retrieve content that is highly relevant.
conceptTaxonomyManager is an easy-to-use, yet powerful taxonomy tool that creates the framework to classify content based on concepts to one or more nodes in the taxonomy.
Features that enable subject-matter experts to interact with the taxonomy can simplify ongoing maintenance. For example, automatically generating compound term clues from the document corpus, dynamically showing the effect of changes on the taxonomy, and class weighting influenced by parent, child and sibling can reduce taxonomy development and ongoing maintenance time by 66 to 80 percent.
For out-of-the-box features, training is not required and legal professionals and end users can begin searching immediately.
Achieving Knowledge Content Enrichment and Optimization of Browser-based Access to Information Retrieval.
This legal firm was willing to think outside the box. Taking its cue from other industries, it was able to build an innovative and best-of-breed solution using Concept Searching solutions, tailored specifically to the needs of the firm and legal professionals.
With over 300 lawyers, not including support staff, the client’s goals included:
- Maximizing contribution of knowledge content
- Streamlining the process of profiling knowledge content
- Maximizing knowledge content enrichment and findability
- Improving visibility of hot topics, and identifying content gaps
- Ensuring full respect of any barriers around knowledge content, imposed both at submission and retrospective stages
- Optimizing browser-based access to knowledge content
The firm selected Concept Searching software not only for its automatic metadata generation, auto-classification, and taxonomy management, but also for the ability for it to be easily integrated with a variety of diverse software applications.
Improving information transparency and information retrieval were major goals of the firm. Using the conceptClassifier platform, it was able to eliminate end user tagging, which is typically subjective and erroneous at best. This was replaced with the automatic generation of rich, multi-term metadata that represents a concept, phrase, subject, or topic, using multi-word terms. Auto-classification of content and taxonomy management tools designed for the business professional completed the solution.
This new search and retrieval functionality enables teams to leverage their content, to deliver comprehensive, just-in-time knowledge
Information On Demand, Regardless of Where it Resides. Internal and External Knowledge Assets, Expertise Location, and Breaking News are All at Legal Professionals’ Fingertips.
Knowledge management has always been a nebulous term and hard to justify internally. For this UK-based legal firm, knowledge management became a valuable tool that was easily quantified. Transforming information into corporate knowledge, it became the focal point of retained corporate memory.
Why were corporate memory and knowledge assets important?
- Inability to reuse or repurpose content appropriate to new matter, escalating time and costs
- Unable to find the expertise needed to add value, resulting in incomplete information
- Research hampered by the inability to find relevant information, impacting productivity and accuracy
The firm implemented highly granular, expert search, providing legal professionals with not only relevant knowledge assets for reuse and repurposing in search results, but with highly granular information about current and past colleagues with expertise in specific subject areas.
The solution also encompassed the delivery of information legal professionals needed from diverse repositories, including subscription-based content. One search interface was provided, but with views customized for each end user. Internal, external, and subscription repositories are at end users’ fingertips. Breaking news on topics of interest are delivered in the preferred manner, such as audible or visual notification.
Corporate memory shouldn’t be elusive. It should be real, available, valued, and used. For this to happen, it must be captured and accessible. Most often, it’s not.
Valuable content sometimes gets lost after a case or matter is closed. Content assets often contain information for repurposing and reuse. These assets contribute to the formation of corporate memory. They are often forgotten or can’t be found again, rendering them of no value.
Retiring baby boomers take with them their knowledge and expertise. Capturing access to a retiree’s legacy can be of value for years afterwards, through expertise profiles that contain content at a granular level, such as written materials and non-confidential communications. In fact, expertise profiles can, and should, be used for all professionals.
The ability to reuse and repurpose content is a significant time saving and productivity aid. Since Concept Searching technologies retrieve information based on concepts and identify related content, additional benefits are reuse, repurposing, and expertise location, all lowering costs.
Some refer to it as deletion. But it’s more than that. What about that one document that contains value? Don’t you want to keep it?
Content optimization is the process of removing information from active systems, through deletion or archiving, and identifying duplicates, near duplicates, undeclared records, and data privacy exposures. It eliminates obsolete and trivial content, which has been saved but is of no value.
Concept Searching recommends that content optimization is done on a quarterly basis. It is estimated that 69 percent of an organization’s content can, and should, be deleted.
Did you know?
- 25 percent of content is duplicate
- 10 percent has no business value
- 90 percent of documents are never accessed after creation
- 65 percent of documents are accessed only once
And the risks are:
- PII, PHI, and PCI data breaches
- Uncontrolled intellectual property
- Unmanaged documents of record
- Unsecured confidential company information
Content optimization not only reduces storage but dramatically improves information retrieval, as it eliminates false positives and irrelevant information from retrieval results
Thanks to Content Optimization, this Law Firm is able to Continually Ensure Confidentiality, Content Security, Compliance, and Information Governance.
This US-based law firm runs content optimization quarterly. Initially used to cleanse its corpus of terabytes of content before migration to SharePoint, the quarterly process is now done as simply maintenance.
What were the challenges?
- Managing and maintaining terabytes of content, costing time and money
- Search performance impacted by results including content that should be deleted, such as duplicates and revisions, which degraded relevance and productivity
- Uncertain whether data privacy and confidential information was available to those unauthorized, jeopardizing client confidentiality and compliance
- No method to offer defensible deletion with full audit capability
The solution uses workflow rules that can be defined by business users or the IT team, and any abnormalities in documents can be identified.
For example, when used for data privacy, it will identify any documents that contain privacy or confidential information, a feature extremely important to the firm. In addition, any compliance or information governance requirement can be flagged, and workflow items can be automatically moved to different repositories for disposition. Privacy and confidential information can be moved to a repository to have portability disabled.
The content optimization also significantly improves search outcomes.
With Terabytes of Documents, there isn’t Enough Time or Money to Evaluate Every Document in Order to Determine its Value. Intelligent Migration Solves that Problem.
One of the largest legal firms in the Southeastern US wanted to organize and migrate terabytes of content. Simply moving content from one system to another didn’t make sense. Understanding that it was not feasible to evaluate every document to determine its value, the firm turned to Concept Searching for help.
What were the challenges?
- Documents existed in multiple places, with different revisions
- Decisions needed to be made on archive versus deletion for compliance
- Records were undeclared
- Potential privacy and confidential information exposures were unknown
- Poor search and retrieval performance
The firm was able to reduce both the time and cost of migration. Migration went smoothly, and an added benefit was improved search in SharePoint. Due to the concept and phrase identification capabilities of the Concept Searching technologies, multi-word terms are fed into the SharePoint search index, significantly improving the speed and accuracy of search.
Migration projects typically have questionable success rates. You are migrating a vital portion of your business. Are you willing to accept failure?
Occurring after content optimization, intelligent migration identifies the content to be moved, and an administrator defines where it will be moved. Concept Searching technology generates concepts before the actual migration. Temporary taxonomies are used to refine the content by concept, client, or topic, within specific taxonomies. This effectively groups like content, so when migrated it retains the likeness or similarity of related documents.
An intelligent approach to migration can be achieved. As content is migrated, it is analyzed for organizationally-defined descriptors and vocabularies, which will automatically classify the content to taxonomies, or optionally to the SharePoint Term Store, and automatically apply organizationally-defined workflows, to process the content to the appropriate repository for review and disposition.
This has an added benefit after migration, improving information retrieval and providing the taxonomy hierarchy to end users as a navigational aid, offering like topics in the taxonomy for selection and exploration, so further refining their initial queries.
Digital Evidence and Investigations
Hopefully you’ll never need digital evidence, nor will your clients. But if you do, you want it to be accurate, thorough, and fast.
Using conceptSearch and the conceptClassifier platform together is valuable for digital investigations and eDiscovery, when analyzing semi-structured and unstructured data. The solution enables teams to find evidence needed to support or eliminate threats. This reduces cost and time, and improves accuracy.
conceptSearch, a heavyweight search engine, is typically not used by the general public, as the level of functionality and precision it offers is not necessarily required. It is used most often by government agencies, for intelligence gathering or specific healthcare applications.
In certain instances where digital evidence gathering is required, this optional component product can be used to identify highly specific text, detailing where, when, and how often the search string occurs, and perhaps more importantly, what it means.
Finding the Needles in the Haystack to Defend or Determine Fault in the Collection of Digital Evidence.
As a startup over ten years ago, this eDiscovery company has grown to be the leader in eDiscovery solutions. Providing end-to-end legal and technology consulting services to Am Law 200 law firms, Fortune 500 corporations, and government agencies, it often encountered the need to produce digital evidence.
What were the challenges?
- Poor tools
- Inability to search any repository for evidence
- Inability to search on concepts, phrases, or keywords
- Unable to automatically identify inter-related content
The organization began using Concept Searching solutions to investigate digital crime, and collect digital evidence. It embedded the automatic metadata generation search and auto-classification technologies into its suite of eDiscovery and forensic solutions.
The unique technologies, which automatically generate ‘concepts from content,’ proved invaluable in information collection, establishing audit trails, and building a holistic, all-inclusive view of the issues under investigation.
Keeping Confidential Information Protected, and Inaccessible to Those Without a Need to Know.
Just about all software solutions will identify data privacy information, some standard and some financial, which needs to be protected. This legal firm had a requirement, as most legal organizations do, to protect private and confidential client information. With over 300 lawyers and a large support staff, confidentiality of client and firm information was of utmost importance.
The challenges faced included:
- Inability to identify and protect data privacy occurrences
- Inability to identify and protect any confidential client or firm related confidential information from those without authorization
- Real-time identification and updating of security profiles
- Ability to review occurrences and handle dispositions
- Prevent portability of data privacy and confidential content
Using the conceptClassifier platform and conceptTaxonomyWorkflow, the firm was able to address all its challenges. The knowledge, innovation, and legal team found setting up workflows easy and intuitive. These workflows contained descriptors and text associated with the unique confidential information and data privacy content that needed protecting.
Data Privacy and Protection of Confidential Information
Protect confidential information, and reduce the 68 percent of breaches caused by your end users.
Maintaining security and limiting access to internal as well as external documents have been made that much more difficult with the rapid increase in security breaches – from ransomware, malware, and internal negligence. The legal profession is not immune to breaches, and must at least meet the requisite requirements to keep information secure and inaccessible to those without the need to know.
Included in taxonomy management components are standard descriptors, available in most security packages. However, confidential information exists that is unique to an organization.
Workflows that are easily defined by business professionals can be created, to automatically identify organizationally-defined confidential information, when content is ingested or created, and then route it to a secure repository, where download is prohibited. The appropriate administrator of the repository can evaluate the quarantined content, and handle its disposition.
When identified words appear during indexing, those documents are removed from access and await disposition. Workflows also operate in real time, immediately identifying when an unauthorized user is within a document where those terms are present. This ensures a robust redaction process, so content can be isolated immediately. This also takes place when users upload or create documents that have the potential to cause breaches, or that lack appropriate security.