Abstract: The present disclosure relates to resolving natural language ambiguities with respect to a simulated reality setting. In an exemplary embodiment, a simulated reality setting having one or more virtual objects is displayed. A stream of gaze events is generated from the simulated reality setting and a stream of gaze data. A speech input is received within a time period and a domain is determined based on a text representation of the speech input. Based on the time period and a plurality of event times for the stream of gaze events, one or more gaze events are identified from the stream of gaze events. The identified one or more gaze events is used to determine a parameter value for an unresolved parameter of the domain. A set of tasks representing a user intent for the speech input is determined based on the parameter value and the set of tasks is performed.

Abstract: The present disclosure relates to resolving natural language ambiguities with respect to a simulated reality setting. In an exemplary embodiment, a simulated reality setting having one or more virtual objects is displayed. A stream of gaze events is generated from the simulated reality setting and a stream of gaze data. A speech input is received within a time period and a domain is determined based on a text representation of the speech input. Based on the time period and a plurality of event times for the stream of gaze events, one or more gaze events are identified from the stream of gaze events. The identified one or more gaze events is used to determine a parameter value for an unresolved parameter of the domain. A set of tasks representing a user intent for the speech input is determined based on the parameter value and the set of tasks is performed.

Abstract: The present disclosure relates to resolving natural language ambiguities with respect to a simulated reality setting. In an exemplary embodiment, a simulated reality setting having one or more virtual objects is displayed. A stream of gaze events is generated from the simulated reality setting and a stream of gaze data. A speech input is received within a time period and a domain is determined based on a text representation of the speech input. Based on the time period and a plurality of event times for the stream of gaze events, one or more gaze events are identified from the stream of gaze events. The identified one or more gaze events is used to determine a parameter value for an unresolved parameter of the domain. A set of tasks representing a user intent for the speech input is determined based on the parameter value and the set of tasks is performed.

Abstract: A machine, method and computer-readable medium for presenting one or more users with suggestions of items from a choice space, wherein the items chosen for presentation are based upon explicit and/or observed preferences of the user. The present invention contemplates use in any number of paradigms involving large user choice spaces, including those relating to the internet and on-line arenas, as well as those relating to television.

Abstract: A method for enhancing a user interface with a computer based training tool comprising the steps of listing domain objects on a display; listing domain object values in response to a selection of one of the domain objects; generating a plurality of inquiries in response to a user selection of one of the domain object values; replying with a predetermined answer; identifying a new domain object value in the predetermined answer; and adding to the plurality of inquiries a new inquiry which incorporates both the selected domain object value and the new domain object value.

Abstract: A method and apparatus for formulating and responding to an inquiry through an interface which is topically organized. The dialogue system interface is comprised of various topical objects wherein each domain object has a set of object values. Selection of a desired object value of a domain object yields a set of potential inquiries, corresponding to the selected value, for selection. A selected inquiry is transmitted to an underlying system for formulation of a response. The formulated response of the underlying system is then transmitted to the user through the dialogue system interface. The dialogue system generates and displays further domain objects, object values, and inquiries that are logically anticipated from the selected inquiry.

Abstract: A method and apparatus for providing computer-assisted implicit and explicit assistance. If no implicit assist actions are desired or indicated, a logical process is initiated to determine whether explicit assistance should be undertaken. If implicit assistance is indicated, a list of action alternatives is displayed for the user. If explicit assistance is desired by the user, particular object(s) from which the assistance may be inferred are entered into an assistance operation. An attempt is made to recognize possible intents expressed by the objects entered into the assistance process. If no user intent is, in fact, recognized, the assist operation is usually terminated. If a possible intent is recognized, the actual intent is hypothesized. A check is further undertaken, to determine whether a hypothesis is in fact available. If no hypothesis is found, the process permits the user to supply a proposed action. If no hypothesis is found and no user action is proposed, assistance efforts terminate.

Abstract: A method and apparatus for processing natural language and deducing meaning from a natural language input characterized by the steps of (a) receiving an ordered string of word objects having a natural language meaning, (b) selecting a word window length, and (c) successively moving the word window along the ordered string and analyzing the meaning of a substring of word objects that fall within the word window. The substring is removed from the ordered string if the substring has a recognized meaning, until all substrings of the ordered string that fit within the window have been analyzed. In a step (d), the word window length is reduced and step (c) is repeated until only an unrecognized residual of the ordered string remains. The meaning of the substring is analyzed by mapping the substring against a database using one or more mapping routines.

Abstract: A method for deducing user intent and providing computer implemented services characterized by the steps of: a) noticing a significant new event occurring within the computer system; b) deducing an intent from the significant new event and from the context in which the new event occurred; and c) providing a service based upon the new event and its context. Significant events are those which the computer might be able to assist a user, and can be determined by matching the event into a database of recognizable events to make a significant observation. The deduction step takes a delimited set of significant observations and attempts to match the set against a number of intent templates. If there are multiple matches to the intent templates, the matches are ranked and a best guess is made to determine a deduced intent. Service is provided fulfilling all preconditions of a plan associated with the deduced intent, and by sequentially executing the steps of the plan.

Abstract: A method and apparatus for processing natural language and deducing meaning from a natural language input characterized by the steps of (a) receiving an ordered string of word objects having a natural language meaning, (b) selecting a word window length, and (c) successively moving the word window along the ordered string and analyzing the meaning of a substring of word objects that fall within the word window. The substring is removed from the ordered string if the substring has a recognized meaning, until all substrings of the ordered string that fit within the window have been analyzed. In a step (d), the word window length is reduced and step (c) is repeated until only an unrecognized residual of the ordered string remains. The meaning of the substring is analyzed by mapping the substring against a database using one or more mapping routines.

Abstract: A method and apparatus for providing computer-assisted implicit and explicit assistance. If no implicit assist actions are desired or indicated, a logical process is initiated to determine whether explicit assistance should be undertaken. If implicit assistance is indicated, a list of action alternatives is displayed for the user. If explicit assistance is desired by the user, particular object(s) from which the assistance may be inferred are entered into an assistance operation. An attempt is made to recognize possible intents expressed by the objects entered into the assistance process. If no user intent is, in fact, recognized, the assist operation is usually terminated. If a possible intent is recognized, the actual intent is hypothesized. A check is further undertaken, to determine whether a hypothesis is in fact available. If no hypothesis is found, the process permits the user to supply a proposed action. If no hypothesis is found and no user action is proposed, assistance efforts terminate.

Abstract: A method and apparatus for processing natural language and deducing meaning from a natural language input characterized by the steps of (a) receiving an ordered string of word objects having a natural language meaning, (b) selecting a word window length, and (c) successively moving the word window along the ordered string and analyzing the meaning of a substring of word objects that fall within the word window. The substring is removed from the ordered string if the substring has a recognized meaning, until all substrings of the ordered string that fit within the window have been analyzed. In a step (d), the word window length is reduced and step (c) is repeated until only an unrecognized residual of the ordered string remains. The meaning of the substring is analyzed by mapping the substring against a database using one or more mapping routines.

Abstract: A method for deducing user intent and providing computer implemented services characterized by the steps of: a) noticing a significant new event occurring within the computer system; b) deducing an intent from the significant new event and from the context in which the new event occurred; and c) providing a service based upon the new event and its context. Significant events are those which the computer might be able to assist a user, and can be determined by matching the event into a database of recognizable events to make a significant observation. The deduction step takes a delimited set of significant observations and attempts to match the set against a number of intent templates. If there are multiple matches to the intent templates, the matches are ranked and a best guess is made to determine a deduced intent. Service is provided fulfilling all preconditions of a plan associated with the deduced intent, and by sequentially executing the steps of the plan.