摘要:
A method and system for addressing disambiguation issues in interactive applications by creating a disambiguation system for generating complex grammars that includes homonym detection and grouping, and provides optimization feedback that eliminates time-consuming and repetitive iterative steps during the grammar generation portion of the interactive application configuration.
摘要:
A method for constructing speech elements within an interface can include a step of identifying a visual interface having multiple visual elements. Visual selectors can be presented proximate each of the visual elements. The visual selectors can permit a user to input a speech control type for the associated visual element. For each presented visual selector, a speech element having a speech control type specified in the visual selector can be automatically generated.
摘要:
Embodiments in accordance with the invention can include a new method (500) and system (100) for testing code within a speech application. A test file (101) can be automatically generated to verify the functionality of a new section of code (172) presented within a graphical call flow builder application (156). In one arrangement, a user can specify through a wizard two points on a path identifying the code section to be tested. The wizard can generate a test file (101) and can configure a path (151) to a new subpath (152) and automatically assign predetermined values to graphical call flow prompts along the path. In this manner, the new code section is reached under the same path conditions for allowing repeatable testing. The system can include a test harness (110) configured to test a new code section from within a context of the speech application, and a test controller (120) for transitioning to the new code section. The test controller can run the test harness within the speech application to evaluate a functionality of the new code section.
摘要:
A method (300) and system (100) is provided to add the creation of examples at a developer level in the generation of Natural Language Understanding (NLU) models, tying the examples into a NLU sentence database (130), automatically validating (310) a correct outcome of using the examples, and automatically resolving (316) problems the user has using the examples. The method (300) can convey examples of what a caller can say to a Natural Language Understanding (NLU) application. The method includes entering at least one example associated with an existing routing destination, and ensuring an NLU model correctly interprets the example unambiguously for correctly routing a call to the routing destination. The method can include presenting the example sentence in a help message (126) within an NLU dialogue as an example of what a caller can say for connecting the caller to a desired routing destination. The method can also include presented a failure dialogue for displaying at least one example that failed to be properly interpreted to ensure that ambiguous or incorrect examples are not presented in a help message.
摘要:
A method, system and apparatus for graphically managing the development of a dynamic call router. In this regard, a graphical tool for creating a dynamic call router can include a language model engine such as a natural language understanding language model engine, a call routing object coupled to the language model engine and referencing a call route termination object in a canvas, and a call flow palette having one or more call flow elements configured for arrangement in the canvas. The graphical tool further can include at least one statement represented graphically in the canvas.
摘要:
A method, system and apparatus for text grouping in a disambiguation process. A text grouping method for use in a disambiguation process can include producing a phonetic representation for each entry in a text list, sorting the list according to the phonetic representation, grouping phonetically similar entries in the list, and providing the sorted list with the groupings to the disambiguation process. The producing step can include producing a phonetic representation for each word in the text list. The producing step also can include producing a phonetic representation for each phrase in the text list.