# US 2019/0318331 A1 · Methods for determining user experience (ux) effectiveness of atms > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318331 A1 - Document ID: US20190318331A1 - Status: Published application - Kind: A1 - Application number: 16/455,809 - Filed: 2019-06-28 - Published: 2019-10-17 - Earliest claimed: 2018-02-12 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: David K. WURMFELD - Web page: https://patentgrep.com/patent/US20190318331A1 ## CPC - G06Q 20/1085: {involving automatic teller machines [ATMs]} - G06N 20/00: Machine learning - G06Q 20/405: {Establishing or using transaction specific rules} - G06Q 20/3265: {characterised by personalisation for use} - G06Q 30/0201: Market modelling; Market analysis; Collecting market data - G06Q 30/0203: Market surveys; Market polls - G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Computer implemented system and methods are provided for evaluating the effectiveness of personalized automated teller machines. In some embodiments, the system may include a camera, an automated teller machine comprising a user interface based on a user profile and at least one server geographically remote from the automated teller machine. The server may be configured to receive a recorded user interaction, receive transaction data, determine an emotion state, extract environmental data, determine a quality indicator for the recorded user interaction, update a user profile, and transmit to the automated teller machine the updated user profile. ## Claims ### Claim 1 A system configured to generate a user interface based on a user profile, the system comprising: a display device configured to display an interface; a non-transitory memory storing computer-readable instructions; and at least one processor, execution of the instructions by the processor causing the at least one processor to: receive image data associated with a recorded interaction of a user with the interface; receive interaction data indicative of a process associated with the interface; apply image processing to the image data to determine an emotion state for the user during the recorded interaction; determine a quality indicator for the recorded interaction based on a correlation of the emotion state for the user and the interaction data, wherein the quality indicator is indicative of the user's satisfaction while interacting with the interface; and update a user profile based on the determined quality indicator for the recorded interaction, the updated profile being configured to effect adjustment of at least one parameter of the interface to alter the interface to affect the user's satisfaction while interacting with the interface. ### Claim 2 (depends on 1) The system of claim 1 wherein the interaction data further comprises transaction information, wherein the transaction information comprises transaction type data, time of day data, temperature data, timing data, keystroke data, button data, age group data, and language data. ### Claim 3 (depends on 1) The system of claim 1, wherein the interaction data further comprises environmental data, the environmental data comprising at least one of weather data, and time of day data. ### Claim 4 (depends on 1) The system of claim 1, wherein the display device comprises an automated teller machine. ### Claim 5 (depends on 1) The system of claim 1, wherein determining the quality indicator for the recorded interaction further causes the processor to: apply a machine learning algorithm to the interaction data trained on historical interaction data. ### Claim 6 (depends on 5) The system of claim 5, wherein the application of the machine learning algorithm causes the processor to: generate one or more quality indicator parameters by training the machine learning algorithm on historical interaction data; and apply the generated one or more quality indicator parameters. ### Claim 7 (depends on 1) The system of claim 1, wherein the user profile further comprises at least one of a height, a language, a gender, an age, an address, and an income. ### Claim 8 (depends on 1) The system of claim 1, wherein the determined emotion state is at least one of anger, happiness, sadness, disgust, surprise, and fear. ### Claim 9 (depends on 1) The system of claim 1, wherein the quality indicator is at least one of a binary value, a categorical value and a numerical value. ### Claim 10 (depends on 1) The system of claim 1, wherein the processor is further configured to: determine an emotion state for a user for each of a plurality of distinct aspects of the recorded interaction and determine a quality indicator for each of the distinct aspects. ### Claim 11 A method for generating a user interface based on a user profile, the method comprising: receiving image data associated with a recorded interaction of a user with an interface of a display device; receiving interaction data indicative of a process associated with the interface; applying image processing to the image data to determine an emotion state for the user during the recorded interaction; determining a quality indicator for the recorded interaction based on a correlation of the emotion state for the user and the interaction data, wherein the quality indicator is indicative of the user's satisfaction while interacting with the interface; and updating a user profile based on the determined quality indicator for the recorded interaction, the updated profile being configured to effect adjustment of at least one parameter of the interface to alter the interface to affect the user's satisfaction while interacting with the interface. ### Claim 12 (depends on 11) The method of claim 11, wherein the interaction data further comprises transaction information, wherein the transaction information comprises transaction type data, time of day data, temperature data, timing data, keystroke data, button data, age group data, and language data. ### Claim 13 (depends on 11) The method of claim 11, wherein the interaction data further comprises environmental data, the environmental data comprising at least one of weather data, and time of day data. ### Claim 14 (depends on 11) The method of claim 11, further comprising: displaying the updated user profile on an automated teller machine. ### Claim 15 (depends on 11) The method of claim 11, wherein determining the quality indicator for the recorded interaction further comprises: applying a machine learning algorithm to the interaction data trained on historical interaction data. ### Claim 16 (depends on 11) The method of claim 11, wherein applying the machine learning algorithm further comprises: generating one or more quality indicator parameters by training the machine learning algorithm on historical interaction data; and applying the generated one or more quality indicator parameters. ### Claim 17 (depends on 11) The method of claim 11, wherein the user profile further comprises at least one of a height, a language, a gender, an age, an address, and an income. ### Claim 18 (depends on 11) The method of claim 11, wherein the determined emotion state is at least one of anger, happiness, sadness, disgust, surprise, and fear. ### Claim 19 (depends on 11) The method of claim 11, wherein the quality indicator is at least one of a binary value, a categorical value and a numerical value. ### Claim 20 (depends on 11) The method of claim 11, further comprising: determining an emotion state for a user for each of a plurality of distinct aspects of the recorded interaction and determine a quality indicator for each of the distinct aspects.