Knowledge learning Engine
Knowledge learning Engine KENT
Knowledge Extraction from Natural Language Text (KENT) extracts knowledge from structured and non-structured data and learns and md dialogue processing. The feature of knowledge automatic extraction engine alone can be used to extract useful knowledge information from product manuals, contracts, etc.
< Knowledge extraction and knowledge graph generation example >
- Ensemble AI-based high-precision knowledge extraction
The knowledge learning engine applies ensemble AI technology in which rule-based knowledge extraction and deep learning-based knowledge extraction combine to extract knowledge from documents. In general, knowledge extraction has low rates of extraction accuracy, so to overcome the limitations, large-scale knowledge graph, inference technique, and deep learning algorithm are used, thus providing a high level of performance available in real world services.
- An automatic large-scale knowledge generation and validation
The knowledge learning engine can be linked with the knowledge graph, which allows the extracted knowledge to be converted into a knowledge graph form. This extraction and conversion process can be automated to generate a large amount of knowledge from large documents, or to quickly extract and validate knowledge from data entered in real time
- Flexible application according to various data types
The knowledge learning engine can generate knowledge extraction models for both modified structured/semi-structured documents, such as HTML code, table data, and modified forms, unstructured documents such as manuals or news articles. Based on the free applicability of the document type, various types of knowledge documents in various domains, such as finance, law and medicine, can be customized.
Main features and specifications
The knowledge learning engine consists of KENT Server which is responsible for knowledge extraction through the knowledge learning feature and the operation management server that allows learning models and tasks to be managed on the web.
< Knowledge learning engine system construction >
- Automatic knowledge extraction task management feature
With one system, it provides a feature of automatic knowledge extraction task management in which knowledge extraction can be learned from various types of knowledge resources. System users can create and register various automatic knowledge extraction tasks according to their goals and manage learning models for each task.
- Knowledge extraction feature
The knowledge learning engine extracts knowledge from documents based on learning models. If the extracted knowledge needs to be linked to a knowledge graph, it identifies the objects in the document and connects the identified objects with the existing knowledge graph objects or create new objects in the knowledge graph. It identifies relationship information between objects created based on contextual information. It provides features so that these processes can be learned.
- Knowledge extraction results supervision feature
If it is in input document but is not reflected in knowledge extraction result or if it is a wrong extraction, it provides an inspection feature to correct the result or add unextracted knowledge. The results of the supervision are reflected in the knowledge learning model, influencing the knowledge extraction results of subsequent documents, to allow continuous quality improvement.
- Knowledge learning generation and management feature
The knowledge learning engine manages neural network models for knowledge extraction via learning management tools, and provides features for learning, applying, and testing.
- Automatic knowledge extraction model evaluation feature
It provides a feature to evaluate whether the model performs knowledge extraction accurately, after a model for automatic knowledge extraction is created. The model evaluation feature allows the user to verify the accuracy of the automatic knowledge extraction model and perform model optimization.
Main engine screen
< Automatic knowledge extraction model evaluation > < Knowledge extraction results supervision >
< Knowledge extraction feature > < Knowledge learning model generation and management >