Automatic capture of information from audio data and computer operating context

Abstract

A computer system provides an automated tool that processes audio data and data about computer operating context to automatically capture information, such as information from conversations and meetings. The computer operating context can include, for example, environmental data sensed, or other contextual information maintained or tracked, by the computer. The audio data and computer operating context are processed by the computer to detect starting conditions for data extraction. After detecting a starting condition, the processor initiates speech processing on the audio information to generate corresponding text data. The processor processes the text data using text filters that define salient patterns in the text data. Such salient patterns can correspond to, for example, tasks to be performed, follow-up appointments and other events, messages to be sent, important points or notes, and the like. Such automatic processing improves user productivity in tracking valuable information from meetings and other conversations.