Muscat has announced Empower, a knowledge management solution based on its Linguistic Inference technology for conducting more accurate corporate data searches.
Linguistic Inference uses the structure of language to find matching patterns rather than convert language into mathematical patterns. Muscat claims this simplifies the search process by allowing users to express a simple definition of the knowledge area they are interested in. Empower then interacts with the user to refine its understanding of this interest area so that, eventually, it can expand the user's knowledge base by suggesting new topics.
Muscat claims that people are generally unable to completely and unambiguously describe what it is they are looking for at the start of a search and need to refine their searches by giving feedback on the results of their initial searches. Linguistic Inference uses natural language techniques to pinpoint information more accurately and allows users to locate knowledge in a large repository even if the initial results are incomplete or ambiguous.
Empower also includes personalised intelligent agents that can be sent out to search for new topics that may be of interest to the user. These agents can be reviewed periodically and retrained by adding ideas or excluding outdated concepts to allow the agent to learn the user's preferences and interests.
Chris Nowell, Muscat's chief executive, said: "Empower is designed not just to find a match to a user's search but to work with them to understand the information available and match the user's interests accurately through iterative and dynamic interaction. It's about filtering out irrelevant detail and pinpointing the information that starts the knowledge creation process."
THE TECHNOLOGY BEHIND LINGUISTIC INFERENCE
Data Collection - continuously review the underlying information set to identify both new and changed data
Concept Extraction - identify and extract the conceptual essence of each textual object in the information set
Interest Recognition - identify the essence of a user's initial information needs, no matter how incomplete or ambiguous
Probabilistic Concept Correlation - correlate the concept defined by the user, or inferred from the user's behaviour, with the concepts extracted from the information set
Review - work with the user to help them improve their own understanding and specification of their needs by allowing them to critically review the current results.
Cotton seedling freezes to death as Chang'e-4 shuts down for the Moon's 14-day lunar night
Fortnite easily out-earns PUBG, Assassin's Creed Odyssey and Red Dead Redemption 2 in 2018
Meteor showers as a service will be visible for about 100 kilometres in all directions
Saturn's rings only formed in the past 100 million years, suggests analysis of Cassini space probe data
New findings contradict conventional belief that Saturn's rings were formed along with the planet about 4.5 billion years ago