Abstract: A method for discovering relationships among elements of a transactional conversation includes tagging a transcribed representation of the conversation to identify elements of the conversation and structuring the tagged conversation according to a specified format to produce a structured, tagged representation of the conversation. A set of structured, tagged conversation representations is then analyzed to discover a relationship between a first conversation element and a second conversation element. Tagging the conversation may include evaluating a portion of the conversation, assigning the portion a message type, and assigning a data value to an attribute defined by the message type. The message type may be defined by a conversation policy, wherein the conversation policy identifies conversation elements including conversation states and message types that transition the conversation among the conversation states.

Abstract: A method and apparatus for creating new representations of a conversational policy or conversation are shown. The conversational policy or a specific conversation can be displayed in a tabular form, which emphasizes order and timing. Representing the policy as a ‘filmstrip’ or series of interactions can make writing the conversational policy more understandable.

Abstract: A method and apparatus for taking a visual or verbal representation of a conversational policy and translating the representation into an XML file. The XML file can then be output in one or more formats, such as code used in a policy, a Word version of the XML file, or a visual representation of the XML file.