Identifying possible contexts for a source of unstructured data

摘要

Potential clues are identified from an unstructured data source. The potential clues are each associated with one or more contexts. A first set of potential contexts for the unstructured data source are determined based on the potential clues. A confidence value for each potential context in the set of the potential contexts is calculated based on the potential clues. A second set of potential contexts is returned from the first set of potential contexts.

主权项

1. A computer program product for identifying potential contexts for an unstructured data source, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
identifying potential clues from the unstructured data source, the potential clues each associated with one or more contexts; determining a first set of potential contexts for the unstructured data source based on the potential clues; calculating an associated confidence value for each potential context in the first set of the potential contexts based on the potential clues; returning a second set of potential contexts from the first set of potential contexts, the second set of potential contexts comprising at least a first context with a highest confidence value; identifying a first concept which is not consistent with the first context; and modifying the first concept to be consistent with the first context, wherein modifying the first concept comprises at least one alteration of the first concept from the group consisting of spelling, grammar, and format.