All Data Harmony modules that include M.A.I. (Machine Aided Indexer) are driven by patented natural language processing methods for rigorous document analysis and exceptional subject categorization. M.A.I. is a versatile engine for text analysis that also achieves metadata extraction for document processing.
Consider two prime examples: the Semantic Fingerprinting managed Web service handles entity extraction and corresponding name-matching for persons and institutions. The Metadata Extractor managed Web service extracts bibliographic information, publishing metadata, and subject keywords from tagged PDF documents, returning an XML version of the document with new metadata elements including an autosummarized abstract.
Thesaurus Master standalone module and XIS (XML Intranet System) are powered by other Data Harmony technologies. These applications are also available as integrated modules with their capabilities combined with those of M.A.I.
MAIstro gives you the opportunity to import, build, test, modify and administer a controlled vocabulary (or vocabularies) oriented for your organization’s information, without a difficult learning curve – for one thing, the rules that govern indexing are accessible to non-programmers. Syntax for the MAI Rule Builder is straightforward and intuitive. In fact, the essential components a person needs to understand to work on Data Harmony rule building can be learned in about one day!
Integrate your controlled vocabulary(ies) – taxonomy, thesaurus, authority lists, and/or ontology – for the benefit of the organization’s users. Powered by M.A.I. (Machine Aided Indexer), Data Harmony has convenient interfaces for users to precisely tag their content objects with the hierarchical terminology of a business sector, academic discipline or classification system.