System and method for adapted interactive experiences
Natural language grammars interpret expressions at the conversational human-machine interfaces of devices. Under conditions favoring engagement, as specified in a unit of conversational code, the device initiates a discussion using one or more of TTS, images, video, audio, and animation depending on the device capabilities of screen and audio output. Conversational code units specify conditions based on conversation state, mood, and privacy. Grammars provide intents that cause calls to system functions. Units can provide scripts for guiding the conversation. The device, or supporting server system, can provide feedback to creators of the conversational code units for analysis and machine learning.
1 . A method comprising:
delivering, unbidden, speech via a conversational human-machine interface, the speech defined within a selected interactive experience unit, the selected interactive experience unit selected from a plurality of interactive experience units, each of said plurality of interactive experience units comprising a natural language grammar;
maintaining, for the conversational human-machine interface, a current conversation state variable;
receiving within a microphone of the conversational human-machine interface a natural language expression from a user responsive to the speech delivered from the conversational human-machine interface;
interpreting the natural language expression according to the natural language grammar defined within the selected interactive experience unit; and
providing an advertisement to the user, content of the advertisement customized based on the interpretation of the natural language expression;
detecting, via one or more sensors of the conversational human-machine interface, one or more conditions associated with the user environment or device status, the conditions comprising an absence of an ongoing modal dialog,
wherein detecting the absence of the ongoing modal dialog comprises:
monitoring an audio channel of the conversational human-machine interface to detect an active automatic speech recognition (ASR) session;
determining whether a speech-recognition grammar is currently engaged;
processing proximity-sensor and ambient-sound measurements to determine whether the user is present and whether private conditions exist;
combining the monitored ASR session state and the sensor measurements according to a dialog-state rule set stored in memory; and
determining that an introductory speech delivered only when (i) no ASR session is active, (ii) the conversational human-machine interface is in a non-modal state, and (iii) a privacy threshold level is satisfied, thereby preventing dialog-state collisions and improving continuity of human-machine interaction during voice-based operation; and
responsive to detecting that the one or more conditions are satisfied, automatically delivering the introductory speech to the user via the conversational human-machine interface, the speech being defined by the selected interactive experience unit.
2 . The method of claim 1 wherein the current conversation state variable represents one or more keywords or related words.
3 . The method of claim 1 wherein the current conversation state variable represents a domain.
4 . The method of claim 1 further comprising detecting a current mood value, wherein the speech is influenced by the current mood value.
5 . The method of claim 1 further comprising receiving a current mood value, wherein the speech is influenced by the current mood value.
6 . The method of claim 1 further comprising determining whether the conversational human-machine interface is in a private listening environment, wherein the speech is conditioned on whether the conversational human-machine interface is in the private listening environment.
7 . The method of claim 6 wherein determining whether the conversational human-machine interface is in a private listening environment is by means of detecting presence of people.
8 . The method of claim 1 , further comprising:
performing voice activity detection; and
delivering the introductory message of an experience unit associated, wherein delivering the introductory message is conditioned on no voice activity being detected.