Inside organizations, knowledge and experience are accumulated over the time and buried in medium like documents and emails. When a new task takes place, even if the past knowledge and experience cannot directly solve the problem, they are usually somehow useful. Through knowledge engineering, the experience could be summarized into a data structure that facilitates convenient consultation, thus improving efficiency and reducing dependency on key experts.
Magi has the toolset to assist some key tasks, such as the summarization of documents and information inquiries, in knowledge engineering.
- Magi Zero and Magi One can provide a model to extract the unstructured information in documents with little or no training samples, enabling knowledge to be sorted into forms like database that is easier to search.
- Leliel is capable of handling complex inquiries such as natural language questions by analyzing the question, identifying intent, complementing grammar components, etc., which could enable more convenient comparison with existing data and better ranking based on semantic relationship.
- Tabris can match questions semantically with answers instead of naively matching keywords, the results of which is considered to be more relevant and helpful.
- Magi HQ can be used to set up the entire Magi system inside an organization, and can bring the searching experience like magi.com to all of the members.