# US 2022/0044087 A1 · Machine-readable label generator > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0044087 A1 - Document ID: US20220044087A1 - Status: Published application - Kind: A1 - Application number: 17/244,032 - Filed: 2021-04-29 - Published: 2022-02-10 - Earliest claimed: 2020-08-09 - Assignees: the dtx company - Applicants: The DTX Company - Inventors: Patrik Andrew Devlin; Corey Benjamin Daugherty; Ahmad Askarian; David Shing; Neil Wayne Cohen; Saul Lewis Stetson; Richard Przekop - Web page: https://patentgrep.com/patent/US20220044087A1 ## CPC - G06K 19/06037: {multi-dimensional coding} - G06F 16/9554: {by using bar codes} - G06K 19/06075: {the marking containing means for error correction} - G06K 19/06103: {the marking being embedded in a human recognizable image, e.g. a company logo with an embedded two-dimensional code} - G06K 19/06131: {the marking comprising a target pattern, e.g. for indicating the center of the bar code or for helping a bar code reader to properly orient the scanner or to retrieve the bar code inside of an image} - G06K 19/0614: {the marking being selective to wavelength, e.g. color barcode or barcodes only visible under UV or IR (methods or arrangements for sensing record carriers using a selected wavelength, see G06K7/12)} - G06K: GRAPHICAL DATA READING (image or video recognition or understanding G06V); PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Software tools disclosed herein may allow a user to enter design choices that alter an aesthetic appearance of a machine-readable label such that modules included in the label deviate from a standardized definition for the modules. Such alterations may include changes in size, color and orientation of modules. The alterations may allow a user to create machine-readable labels having unique aesthetic appearances. A software engine may ensure that, despite the aesthetic design choices entered by a user, the generated machine-readable label is reliably scannable. ## Claims ### Claim at position 1 1-37. (canceled) ### Claim 38 An artificial intelligence (“AI”) method for generating a quick-response (“QR”) code, the method comprising: receiving an image; identifying a color in the image; and generating a quick response (“QR”) code based on the color. ### Claim 39 (depends on 38) The AI method of claim 38 further comprising computing how to apply the color to a module of the QR code such that the QR code is associated with a threshold level of error correction. ### Claim 40 (depends on 39) The AI method of claim 39 wherein generating the QR code comprises generating a data zone that: triggers a target action when scanned; and is scannable within a target time window. ### Claim 41 (depends on 38) The AI method of claim 38 wherein generating the QR code comprises generating an environmental zone based on the color. ### Claim 42 (depends on 38) The AI method of claim 38 further comprising: extracting a set of design choices from the image; and generating the QR code comprises: computing how the set of design choices impact human aesthetic judgment; and altering at least one member of the set of design choices based on how the set of design choices impacts human aesthetic judgment. ### Claim 43 (depends on 38) The AI method of claim 38 wherein generating the QR code further comprises applying a mask pattern that ensures the QR code does not include a threshold number of adjacent modules having the color. ### Claim 44 (depends on 38) The AI method of claim 38 wherein generating the QR code further comprises computationally altering the color. ### Claim 45 (depends on 44) The AI method of claim 44 wherein computationally altering the color comprises changing hue, tint, shade, tone, saturation, lightness, chromaticity or intensity associated with the color. ### Claim 46 (depends on 38) The AI method of claim 38 further comprising: applying computational aesthetic techniques to define an aesthetic appearance associated with the image; and generating the QR code based on the aesthetic appearance. ### Claim 47 (depends on 46) The AI method of claim 46 wherein the aesthetic appearance includes a modification to the color. ### Claim 48 (depends on 46) The AI method of claim 46 wherein generating the QR code based on the aesthetic appearance comprises computing a color for each module in the QR code such that the QR code conforms to the aesthetic appearance. ### Claim 49 (depends on 38) The AI method of claim 38 wherein generating the QR code comprises computing a shape and size of each module within the QR code. ### Claim 50 A software platform for generating a quick-response (“QR”) code, the software platform comprising: a user interface programmed to receive an image; and an artificial intelligence (“AI”) software engine that generates a machine-readable label based on the image, the machine-readable label comprising a data zone that includes error correction code capable of restoring a threshold percentage of instructions encoded in the data zone. ### Claim 51 (depends on 50) The software platform of claim 50 wherein the AI software engine incorporates a color in the image into the machine-readable label. ### Claim 52 (depends on 50) The software platform of claim 50 wherein the AI software engine generates the machine-readable label by: applying a machine-generated change to a color included in the image; and incorporating the machine-generated change into the machine-readable label. ### Claim 53 (depends on 50) The software platform of claim 50 wherein the AI software engine computes a color for each module in the machine-readable label. ### Claim 54 (depends on 50) The software platform of claim 50 wherein the AI software engine: alters one or more of: hue, tint, shade, tone, saturation, lightness, chromaticity and intensity of a color included in the image; and includes alterations to the color in the machine-readable label. ### Claim 55 (depends on 50) The software platform of claim 50 wherein the AI software engine computes a color for each module in the machine-readable label by computing how the color impacts human aesthetic judgment. ### Claim 56 (depends on 50) The software platform of claim 50 wherein the AI software engine generates the machine-readable label that is scannable within a threshold time limit and the error correction code is capable of restoring at least 15% of instructions encoded in the data zone. ### Claim 57 (depends on 50) The software platform of claim 50 wherein the AI software engine: generates an environmental zone for the machine-readable label; and to a human eye, the environmental zone appears to be a contiguous extension of the data zone. ### Claim 58 (depends on 50) The software platform of claim 50 wherein: the data zone comprises a timing pattern and an alignment pattern; and the instructions encoded in the data zone, when scanned, trigger a target action. ### Claim 59 An artificial intelligence (“AI”) method for generating a quick-response (“QR”) code, the method comprising: receiving user-input design choices; computationally generating an aesthetic appearance that includes a change to at least one of the user-input design choices; and generating a quick response (“QR”) code based on the aesthetic appearance, wherein the QR code includes a data zone having error correction code that is capable of restoring at least 15% of instructions encoded in the data zone. ### Claim 60 (depends on 59) The AI method of claim 59 wherein computationally generating the aesthetic appearance comprises altering a color included in the user-input design choices. ### Claim 61 (depends on 59) The AI method of claim 59 wherein generating the QR code based on the aesthetic appearance comprises determining a color of each module in the QR code such that the QR code conforms to the aesthetic appearance. ### Claim 62 (depends on 59) The AI method of claim 59 wherein: computationally generating the aesthetic appearance comprises defining how the user-input design choices impact human aesthetic judgment; and generating the QR code based on how the user-input design choices impact human aesthetic judgment. ### Claim 63 (depends on 59) The AI method of claim 59 wherein the user-input design choices comprise an image. ### Claim 64 (depends on 59) The AI method of claim 59 wherein computationally generating the aesthetic appearance comprises modifying the user-input design choices such that readability of the QR code by a scanning device is enhanced over applying the user-input design choices without the change included in the aesthetic appearance. ### Claim 65 (depends on 59) The AI method of claim 59 wherein generating the QR code based on the aesthetic appearance comprises generating an environmental zone for the QR code and a data zone of the QR code based on the aesthetic appearance. ### Claim 66 (depends on 59) The AI method of claim 59 wherein generating the aesthetic appearance comprises changing hue, tint, shade, tone, saturation, lightness, chromaticity or intensity associated with a color included in the user-input design choices. ### Claim 67 (depends on 65) The AI method of claim 65 wherein the data zone comprises a timing pattern, an alignment pattern and encoded instructions that, when scanned, trigger a target action.