# US 2019/0318450 A1 · Dynamic adaptation of device interfaces in a voice-based system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318450 A1 - Document ID: US20190318450A1 - Status: Published application - Kind: A1 - Application number: 15/973,456 - Filed: 2018-05-07 - Published: 2019-10-17 - Earliest claimed: 2018-04-17 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Jian Wei Leong - Web page: https://patentgrep.com/patent/US20190318450A1 ## CPC - G06T 3/18: Image warping, e.g. rearranging pixels individually - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06T 3/608: by skew deformation, e.g. two-pass or three-pass rotation - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06F 40/205: Parsing - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Implementations relate to dynamic adaptation of images for projection by a projector, based on one or more properties of user(s) that are in an environment with the projector. The projector can be associated with an automated assistant client of a client device. In some versions of those implementations, a pose of a user in the environment is determined and, based on the pose, a base image for projecting onto a surface is warped to generate a transformed image. The transformed image, when projected onto a surface and viewed from the pose of the user, mitigates perceived differences relative to the base image. ## Claims ### Claim at position 1 -20. (canceled) ### Claim 21 A system to generate interfaces in an audio-based networked system, comprising: a computing device comprising one or more processors and a memory, the one or more processors configured to execute: a natural language processor to: receive an input audio signal detected by a sensor at a client device; parse input audio signal to identify a first request in the input audio signal and a keyword associated with the first request; a content selector component to: select a first base digital component based on at least the first digital component request; select a second base digital component based on at least the keyword associated with the first digital component request; and a transformation component to: determine a distance between the client device and a projection surface; determine, based on the distance between the client device and the projection surface, transformation parameters for the first base digital component and the second base digital component, the transformation parameters configured to correct a skew of images projected onto the projection surface; generate a first transformed image based at least on the transformation parameters and the first base digital component and a second transformed image based at least on the transformation parameters and the second digital component; and transmit the first transformed image and the second transformed image to the client device for projection onto the projection surface. ### Claim 22 (depends on 21) The system of claim 21, comprising the transformation component to: generate a first set of transformation parameters for the first digital component; and generate a second set of transformation parameters for the second digital component. ### Claim 23 (depends on 21) The system of claim 21, comprising the transformation component to: determine a first pose of a first user; and determine the transformation parameters based on the first pose of the first user. ### Claim 24 (depends on 23) The system of claim 23, comprising the transformation component to: determine a second pose of the first user; and determine updated transformation parameters based on the second pose of the first user. ### Claim 25 (depends on 21) The system of claim 21, comprising the transformation component to: determine a first distance between a first user and the projection surface; and determine the transformation parameters based on the first distance between the first user and the projection surface. ### Claim 26 (depends on 21) The system of claim 21, wherein the transformation parameters comprise at least one of a rotation adjustment, a scale adjustment, and a skew adjustment. ### Claim 27 (depends on 21) The system of claim 21, comprising the transformation component to: determine, based on a first pose of the user, a predetermined size for a projection of the first transformed image; and generate the transformation parameters based on the predetermined size for the projection of the first transformed image. ### Claim 28 (depends on 21) The system of claim 21, comprising the content selector component to: select the first base digital component based on a first pose of a first user. ### Claim 29 (depends on 21) The system of claim 21, comprising the content selector component to: select the first base digital component based on the distance between the client device and the projection surface. ### Claim 30 (depends on 21) The system of claim 21, comprising the transformation component to: determine a first pose of a first user is within a threshold distance of the projection surface; and generate the first base digital component to include one or more interactive interface elements based on the first pose of the first user being within the threshold distance. ### Claim 31 (depends on 21) The system of claim 21, comprising: the transformation component to determine a first pose of a first user and a second pose of a second user; and the content selector component to select the first digital component based on the first pose of the first user and the second digital component based on the second pose of the second user. ### Claim 32 A method to generate interfaces in an audio-based networked system, comprising: receiving, by a natural language processor executed by one or more processors of a computing device, an input audio signal detected by a sensor at a client device; parsing, by the natural language processor, the input audio signal to identify a first request in the input audio signal and a keyword associated with the first request; selecting, by a content selector component of the computing device, a first base digital component based on at least the first digital component request; selecting, by the content selector component, a second base digital component based on at least the keyword associated with the first digital component request; determining, by a transformation component executed by the one or more processors of the computing device and based on sensor data from the client device, a distance between the client device and a projection surface; determining, by the transformation component, based on the distance between the client device and the projection surface, transformation parameters for the first base digital component and the second base digital component, the transformation parameters configured to correct a skew of images projected onto the projection surface; generating, by the transformation component, a first transformed image based at least on the transformation parameters and the first base digital component and a second transformed image based at least on the transformation parameters and the second digital component; and transmitting, by the transformation component, the first transformed image and the second transformed image to the client device for projection onto the projection surface. ### Claim 33 (depends on 32) The method of claim 32, comprising: generating, by the transformation component, a first set of transformation parameters for the first digital component; and generating, by the transformation component, a second set of transformation parameters for the second digital component. ### Claim 34 (depends on 32) The method of claim 32, comprising: determining, by the transformation component, a first pose of a first user; and determining, by the transformation component, the transformation parameters based on the first pose of the first user. ### Claim 35 (depends on 34) The method of claim 34, comprising: determining, by the transformation component, a second pose of the first user; and determining, by the transformation component, updated transformation parameters based on the second pose of the first user. ### Claim 36 (depends on 32) The method of claim 32, comprising: determining, by the transformation component, a first distance between a first user and the projection surface; and determining, by the transformation component, the transformation parameters based on the first distance between the first user and the projection surface. ### Claim 37 (depends on 32) The method of claim 32, wherein the transformation parameters comprise at least one of a rotation adjustment, a scale adjustment, and a skew adjustment. ### Claim 38 (depends on 32) The method of claim 32, further comprising: determining, by the transformation component and based on a first pose of the user, a predetermined size for a projection of the first transformed image; and generating, by the transformation component, the transformation parameters based on the predetermined size for the projection of the first transformed image. ### Claim 39 (depends on 32) The method of claim 32, comprising: determining, by the transformation component, a first pose of a first user is within a threshold distance of the projection surface; and generating, by the transformation component, the first base digital component to include one or more interactive interface elements based on the first pose of the first user being within the threshold distance. ### Claim 40 (depends on 32) The method of claim 32, comprising: determining, by the transformation component, a first pose of a first user and a second pose of a second user; and selecting, by the content selector component, the first digital component based on the first pose of the first user and the second digital component based on the second pose of the second user.