# US 12,118,209 B2 · Systems for real-time intelligent haptic correction to typing errors and methods thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,209 B2 - Document ID: US12118209B2 - Status: Granted - Kind: B2 - Application number: 18/521,582 - Filed: 2023-11-28 - Published: 2024-03-21 - Granted: 2024-10-15 - Earliest claimed: 2020-11-05 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Abdelkader M'hamed Benkreira; Nimma Bhusri; Tyler Maiman - Web page: https://patentgrep.com/patent/US12118209B2 ## CPC - G06F 3/04886: by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus - G06F 3/016: {Input arrangements with force or tactile feedback as computer generated output to the user} - G06F 3/04186: {Touch location disambiguation} - G06F 3/0488: using a touch-screen or digitiser, e.g. input of commands through traced gestures - G06F 18/241: relating to the classification model, e.g. parametric or non-parametric approaches - G06F 40/216: using statistical methods - G06F 40/232: Orthographic correction, e.g. spell checking or vowelisation - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/30: Semantic analysis - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 20/00: Machine learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06F 2203/04803: Split screen, i.e. subdividing the display area or the window area into separate subareas - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/045: Combinations of networks - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Systems and methods of the present disclosure enable context-aware haptic error notifications. The systems and methods include a processor to receive input segments into a software application from a character input component and determine a destination. A context identification model predicts a context classification of the input segments based at least in part on the software application and the destination. Potential errors are determined in the input segments based on the context classification. An error characterization machine learning model determines an error type classification and an error severity score associated with each potential error and a haptic feedback pattern is determined for each potential error based on the error type classification and the error severity score of each potential error of the one or more potential errors. And a haptic event latency is determined based on the error type classification and the error severity score of each potential error. ## Claims ### Claim 1 A method comprising: utilizing, by at least one processor, an error characterization machine learning model to determine an error type classification associated with one or more potential errors in at least one input segment from a character input component of a user computing device; determining, by the at least one processor, a haptic event latency associated with a delay for triggering haptic feedback after the one or more potential errors; and instructing, by the at least one processor, the user computing device to produce the haptic feedback after the haptic event latency. ### Claim 2 (depends on 1) The method of claim 1, further comprising determining, by the at least one processor, a context classification of the at least one input segment comprising: i) a type associated with a software application of the user computing device, and ii) a business or personal distinction associated with the software application. ### Claim 3 (depends on 1) The method of claim 1, further comprising communicating, by the at least one processor, an operating system (OS) event to an OS of the user computing device after the haptic event latency of each potential error to cause the OS to cause the user computing device to produce the haptic feedback. ### Claim 4 (depends on 1) The method of claim 1, wherein the haptic feedback comprises a selection of a vibration pattern from a set of vibration patterns included in an operating system (OS) of the user computing device. ### Claim 5 (depends on 1) The method of claim 1, wherein the character input component comprises a virtual keyboard on a touchscreen of the user computing device. ### Claim 6 (depends on 2) The method of claim 2, further comprising: utilizing, by the at least one processor, an error sensitivity model to determine an error sensitivity score representing a degree of sensitivity to errors based at least in part on the context classification; and generating, by the at least one processor, the haptic feedback based on the error sensitivity score. ### Claim 7 (depends on 2) The method of claim 2, wherein: the error type classification of a potential error of the one or more potential errors comprises a transaction amount error; and the error characterization machine learning model is trained to identify the transaction amount error based at least in part on a user input history of transaction amount inputs associated with the context classification of the at least one input segment. ### Claim 8 (depends on 2) The method of claim 2, wherein: the error type classification of a potential error of the one or more potential errors comprises a form field error associated with a user input to a data field of a form in the software application; and the error characterization machine learning model is trained to identify the form field error based at least in part on a user input history of user inputs to the data field associated with the context classification of the at least one input segment. ### Claim 9 (depends on 1) The method of claim 1, wherein the haptic event latency comprises a time-based latency causing the haptic feedback at a predetermined amount of time after detection of the one or more potential errors. ### Claim 10 (depends on 1) The method of claim 1, wherein the haptic event latency comprises an event-based latency causing the haptic feedback at an input of the at least one input segment matching a predetermined input event after detection of the one or more potential errors. ### Claim 11 A system comprising: at least one processor in communication with a non-transitory computer readable medium having software instructions stored thereon, wherein the at least one processor is configured to, upon execution of the software instructions, perform steps to: utilize an error characterization machine learning model to determine an error type classification associated with one or more potential errors in at least one input segment from a character input component of a user computing device; determine a haptic event latency associated with a delay for triggering haptic feedback after the one or more potential errors; and instruct the user computing device to produce the haptic feedback after the haptic event latency. ### Claim 12 (depends on 11) The system of claim 11, wherein the at least one processor is further configured to implement the software instructions causing the at least one processor to perform steps to determine a context classification of the at least one input segment comprising: i) a type associated with the software application, and ii) a business or personal distinction associated with an electronic destination and the software application, wherein the at least one input segment is communicated by the software application, via the user computing device to the electronic destination. ### Claim 13 (depends on 11) The system of claim 11, wherein the at least one processor is further configured to implement the software instructions causing the at least one processor to perform steps to communicate an operating system (OS) event to an OS of the user computing device after the haptic event latency of each potential error to cause the OS to cause the user computing device to produce the haptic feedback. ### Claim 14 (depends on 11) The system of claim 11, wherein the haptic feedback comprises a selection of a vibration pattern from a set of vibration patterns included in an operating system (OS) of the user computing device. ### Claim 15 (depends on 11) The system of claim 11, wherein the character input component comprises a virtual keyboard on a touchscreen of the user computing device. ### Claim 16 (depends on 12) The system of claim 12, wherein the at least one processor is further configured to implement the software instructions causing the at least one processor to perform steps to: utilize an error sensitivity model to determine an error sensitivity score representing a degree of sensitivity to errors based at least in part on the context classification and the electronic destination, wherein the at least one input segment is communicated by the software application, via the user computing device to the electronic destination; and generate the haptic feedback based on the error sensitivity score. ### Claim 17 (depends on 12) The system of claim 12, wherein: the error type classification of a potential error of the one or more potential errors comprises a transaction amount error; and the error characterization machine learning model is trained to identify the transaction amount error based at least in part on a user input history of transaction amount inputs associated with the context classification of the at least one input segment. ### Claim 18 (depends on 12) The system of claim 12, wherein: the error type classification of a potential error of the one or more potential errors comprises a form field error associated with a user input to a data field of a form in the software application; and the error characterization machine learning model is trained to identify the form field error based at least in part on a user input history of user inputs to the data field associated with the context classification of the at least one input segment. ### Claim 19 (depends on 11) The system of claim 11, wherein the haptic event latency comprises a time-based latency causing the haptic feedback at a predetermined amount of time after detection of the one or more potential errors. ### Claim 20 (depends on 11) The system of claim 11, wherein the haptic event latency comprises an event-based latency causing the haptic feedback at an input of the at least one input segment matching a predetermined input event after detection of the one or more potential errors.