Abstract: A conversation management system provides a conversational computing interface that manages verbal exchanges between a computer (e.g., artificial intelligence) and a human operator. In a medical embodiment, conversational input from the computing system is generated based on medical knowledge, uses deep learning algorithms, and/or intelligently tracks the state of a conversation so as to the most relevant data to the user.

Abstract: A conversation management system provides a conversational computing interface that manages verbal exchanges between a computer (e.g., artificial intelligence) and a human operator. In a medical embodiment, conversational input from the computing system is generated based on medical knowledge, uses deep learning algorithms, and/or intelligently tracks the state of a conversation so as to the most relevant data to the user.

Abstract: An utterance is analyzed to identify an absence of a known invocation phrase. A skill set is constructed in response to the absence, the skill set including a first skill corresponding to the utterance and a first skill score corresponding to a likelihood that the first skill corresponds to the utterance. The first skill score is adjusted, based on the presence of the first skill in a skill history, where the skill history stores a set of history skills in an order of recency of use of each history skill in the set of history skills. The first skill score is adjusted, based on an association of the first skill with a default installed skill. An installed skill is selected, based on the adjusted first skill score, the installed skill performing an action in response to the utterance.

Abstract: A computer-implemented method includes: receiving a web service definition file that identifies multiple web services; parsing the web service definition file; identifying respective voice commands to associate with each of the multiple web service based on the parsing; generating a skillset utterances file that maps the respective voice commands to the multiple web services; generating a skillset implementation file that maps the multiple web services to a respective set of instructions, wherein each of the respective set of instructions is used to invoke a corresponding web service; receiving an input voice command from a user via a user device; identifying a particular web service, of the multiple web services, associated with the input voice command based on information included in the skillset utterances file; and invoking the particular web service in accordance with the set of instructions associated with the particular web service included in the skillset implementation file.

Abstract: An utterance is analyzed to identify an absence of a known invocation phrase. A skill set is constructed in response to the absence, the skill set including a first skill corresponding to the utterance and a first skill score corresponding to a likelihood that the first skill corresponds to the utterance. The first skill score is adjusted, based on the presence of the first skill in a skill history, where the skill history stores a set of history skills in an order of recency of use of each history skill in the set of history skills. The first skill score is adjusted, based on an association of the first skill with a default installed skill. An installed skill is selected, based on the adjusted first skill score, the installed skill performing an action in response to the utterance.

Abstract: A conversation management system provides a conversational computing interface that manages verbal exchanges between a computer (e.g., artificial intelligence) and a human operator. In a medical embodiment, conversational input from the computing system is generated based on medical knowledge, uses deep learning algorithms, and/or intelligently tracks the state of a conversation so as to the most relevant data to the user.

Abstract: A conversation management system provides a conversational computing interface that manages verbal exchanges between a computer (e.g., artificial intelligence) and a human operator. In a medical embodiment, conversational input from the computing system is generated based on medical knowledge, uses deep learning algorithms, and/or intelligently tracks the state of a conversation so as to the most relevant data to the user.

Abstract: A computer-implemented method includes: receiving a web service definition file that identifies multiple web services; parsing the web service definition file; identifying respective voice commands to associate with each of the multiple web service based on the parsing; generating a skillset utterances file that maps the respective voice commands to the multiple web services; generating a skillset implementation file that maps the multiple web services to a respective set of instructions, wherein each of the respective set of instructions is used to invoke a corresponding web service; receiving an input voice command from a user via a user device; identifying a particular web service, of the multiple web services, associated with the input voice command based on information included in the skillset utterances file; and invoking the particular web service in accordance with the set of instructions associated with the particular web service included in the skillset implementation file.

Abstract: A method of providing customized information to a customer. In an embodiment, the method of providing customized information to a customer such as a car rental customer includes receiving at least one customer preference. Next, data is accessed in accordance with the at least one customer preference. Such data in accordance with the at least one customer preference is written to a storage device which is delivered to the customer. This information may also be provided wirelessly via the Internet so that this information may be up-dated in real time.