Google has patented a smart glasses assistant that makes suggestions based on user gaze, voice input


Google has been granted a patent for an automated assistant that can be used to make suggestions to a user wearing smart glasses and customize them based on what the user is seeing, or their verbal instructions. While Google was previously working on a pair of smart glasses that relied on augmented reality (AR) technology, the company reportedly abandoned its ‘Project Iris’ AR smart glasses last year, in favor of creating similar hardware for OEM partners. had left. It’s unclear at the moment whether the company will launch a pair of AR glasses based on the technology described in its latest patent.

Google’s Assistant for smart glasses can identify environmental features of interest to the user

In a document published on the website of the World Intellectual Property Organization (WIPO) (via 91Mobiles) titled “Adapting assistive suggestions provided on computerized glasses according to changes in user vision and/or other user input”, the company ” Describes the use of “automated” assistants that can adapt to the audio and video input provided by a pair of smart glasses to the user.

Google’s patent document shows the Adaptive Assistant in action (tap to enlarge)
Photo credit: WIPO/Google

The company says the automated assistant will be able to make suggestions on the smart glasses’ displays, and users will be able to select these options with technology that tracks the user’s “gaze.” This suggests that the device will be equipped with some form of eye tracking that can be used by the assistant.

When a user looks elsewhere, the Assistant will be able to use the camera and microphone on the smart glasses to dynamically “adapt” its suggestions based on the user’s viewpoint and their verbal instructions, respectively.

Google provides an example of a user wearing glasses while exploring a foreign city. This tool will provide suggestions to restaurants based on their gaze direction (Figure 2B). Users will be able to invoke the Assistant by tapping the glasses or using a wake phrase.

According to the document, the Assistant will also limit the number of suggestions seen on the smart glasses’ display, as too many suggestions could obstruct the wearer’s view. These suggestions can be selected based on gestures, or using spoken commands. The patent also reveals that the Assistant can interface with other applications on the device.

The company also describes the ability to “offload computational tasks” to a server device that will enable the smart glasses to “conserve computational resources” – effectively providing additional battery life. This means that the assistant can be hosted on a server or smart glasses, while the processes related to the operation of the assistant can occur on any device.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *