Browse Prior Art Database

Quantitative Voice Response System to Submit Contextual Relevant Mixed Voice and Body Gestures

IP.com Disclosure Number: IPCOM000254251D
Publication Date: 2018-Jun-14
Document File: 4 page(s) / 284K

Publishing Venue

The IP.com Prior Art Database

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 53% of the total text.

Quantitative Voice Response System to Submit Contextual Relevant Mixed Voice and Body Gestures

While speaking many people include body language such a hand gestures and facial expressions. Different people have different types of body language while they are speaking or submitting voice commands to an AI voice response system. There is a need for a voice response system that can receive voice and video input to process a mixture of voice commands and body language, and use body language as validation mechanism for voice commands. Disclosed is a method and system for an AI voice response system to analyze and learn context of quantitative body language gestures to determine if the body language gestures should be submitted as input along with voice commands. In accordance with the method and system disclosed herein, the AI voice response system includes a voice system integrated with a cognitive system to receive video or image input from camera for analysis. The camera can be built-in to the voice response system or in cameras within the environment to capture video or images of the user’s body gestures. The voice system is also integrated with one or more wearable devices of the user such as ring device, smartwatch, wristband, cloth made of electronic textile, electronic tattoo or any other IoT enabled devices. The wearables devices detect and map to quantitative gestures for a given user and context. The cognitive system learns context of specific quantitative user body language and voice commands and stores the learned gestures of specific user for correlated context of voice command in a gesture repository. The cognitive system is configured to analyze learned gestures and voice commands to determine if gestures should be submitted as quantitative input with voice commands. Figure 1 depicts an exemplary scenario wherein a user is submitting a voice command along with performing contextual and quantitative body language gesture expressing the specific users meaning of “less sugar” in Tea. The quantitative meaning of “less sugar” with a gesture can have different meaning for different users or context. The method and system disclosed herein identifies contextual meaning of the body language and correlates the same with the voice command using the cognitive system.

Figure 1

Figure 2 illustrates a flow chart of the method steps for processing a mixture of voice commands and body language in accordance with the method and system disclosed herein.

Figure 2

To begin with the system is trained and calibrated to learn the quantitative gestures for

given voice commands. Thereafter, during runtime, the AI voice response system integrated with cameras in an environment listens to user speech and voice commands and captures user body language gestures with the speech. Additionally, sensors from the wearables devices capture body / hand movements with the speech. In an embodiment, the system streams voice and body language gestures for continuous ana...