ElinarAI helps you to get better results
Elinar’s Artificial Intelligence
Elinar has been heavily involved with advanced topics in text analytics for over a decade. We have also extensive expertise in text analytics and inherent problems associated with linguistics, dictionaries, and regular expressions. These things, to name only a few, have enabled us to take unstructured data analytics to the next level.
Elinar has a solid background in augmenting IBM Watson NLU®, IBM Watson Explorer®, IBM StoredIQ®, and IBM Datacap®. These utilize AI to provide AI-augmented enterprise content analytics and management solutions. Our own R&D on unstructured data AI started 5 years ago. This work ultimately resulted in significant Elinar IP: ElinarAI
ElinarAI’s core capabilities are:
Complex feature extraction from unstructured data. For example, ElinarAI is able to:
- Extract order or invoice lines.
- Identify damaged parts and the reason for damage from field service men reports.
- Identify the reason for a customer’s anger based on a customer complaint.
- Create a structure in a medical record; identify the reason for a doctor’s visit and identify which medication was ordered.
- Extract complex personal data from a document.
- Help with redaction tasks; ElinarAI can discover what needs to be redacted from a record.
Advanced classification of a document or business record.
As such, ElinarAI is able to:
- Learn and create virtually any type of classification, for example, security classification.
- Use multi-valued complex classifications, such as which body part was injured.
- Mix complex classification systems together; for example, there can be dozens of classification categories (e.g. MRI, X-ray, specialist appointment, GP appointment, nurse appointment, injured body part, and so on).
ElinarAI uses supervised learning. It learns from samples that can either be obtained automatically from an existing business process/system or generated manually by humans.
ElinarAI contains all the necessary tools for training data preparation, AI training, and scalable inferencing. Our solution is not a framework that requires deep involvement from corporate IT developers. Instead, it allows the business to create AI training data in an intuitive environment. And once the training data has been created (or provided), ElinarAI provides inferencing using the simple but secure REST interface, which can be used by any corporate process.
ElinarAI is an AI framework that combines Deep Learning with Advanced Text Analytics using ElinarNER or IBM Watson NLU®. Elinar has specialized industry modules available for several industries and use-cases:
ElinarAI for Legal
Administrative Law, Case Law, Civil Law; virtually any kind of legal problem can be solved using ElinarAI.
ElinarAI can be trained to understand a specific legal context. In this context, ElinarAI can extract general and situational parameters from the matter (for example administrative decision or a court case). This is what we call a meta-structure for a legal case. When case meta-structure is known it is possible to automate case processing or decision making using traditional Business Rules.
ElinarAI is a form of supervised learning; this means that before using AI, training data must be compiled. This can be exported from an existing IT system or manually generated by humans. Before this training can take place a sufficient Meta-Structure for the problem must be identified. This is work for Legal Professionals who understand the domain of the legal matter.
Meta-Structure creation is always a balance between accuracy and effort; more detailed Meta-Structure will yield more accurate results but will require more training data and effort to generate training data will be higher. We are currently working with a legal researcher who is creating a systematic methodology for assessing legal Meta-Structure complexity vs. expected outcomes. Do not hesitate to contact us for more information about this research.
ElinarAI for Big Data and Analytics
One major challenge of unstructured data is that it is very difficult to use as part of corporate analytics due to the unstructured nature.
Unfortunately, nowadays 70% of corporate data is unstructured and this leaves huge gaps into corporate analytics capabilities. For some (simple) use cases traditional Text Analytics offers excellent approaches but in the long run text analytics is very simple and requires constant maintenance for even mediocre results. When the data is “not apparent” in the text it becomes very expensive or impossible to create understanding using traditional text analytics.
This is why ElinarAI combines text analytics with Deep Learning to create human-like cognition on unstructured data. This allows corporate analytics to tap into a vast, near-endless vat of knowledge called unstructured data – business documents, records, consumer complaints – nearly anything can be part of corporate analytics!
Talk more with our expert:
+358 50 361 1038