# US 2025/0095388 A1 · User predictive mental response profile and application to automated brain interface control > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0095388 A1 - Document ID: US20250095388A1 - Status: Published application - Kind: A1 - Application number: 18/964,792 - Filed: 2024-12-02 - Published: 2025-03-20 - Earliest claimed: 2018-05-14 - Assignees: NeuCogs Ltd. - Applicants: NeuCogs Ltd. - Inventors: Miriam REINER; Shay HILEL; Zeev HADAR - Web page: https://patentgrep.com/patent/US20250095388A1 ## CPC - G06V 20/597: {Recognising the driver's state or behaviour, e.g. attention or drowsiness} - B60W 40/08: related to drivers or passengers - B60W 60/0051: {from occupants to vehicle} - G05D 1/0055: {with safety arrangements} - G05D 1/617: Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards (arrangements for controlling the position or course of two or more vehicles for avoiding collisions therebetween G05D1/693; arrangements for reacting to or preventing system or operator failure G05D1/80) - G06V 40/176: {Dynamic expression} - G06V 40/18: Eye characteristics, e.g. of the iris - G06V 40/19: Sensors therefor - G06V 40/23: {Recognition of whole body movements, e.g. for sport training} - G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES ## Abstract User predictive mental response profiles updating and usage, comprising receiving a plurality of images captured by one or more imaging sensors deployed to monitor one or more eyes of a user, analyzing at least some of the plurality of images to identify one or more eye dynamics signal patterns preceding one or more abnormal events occurring in an environment of the user, updating a response profile of the user based on an association of one or more of the abnormal event and the one or more of the identified eye dynamics signal patterns, and providing information based on the updated response profile of the user. The provided information is configured to enable one or more processing units to predict an imminent abnormal event based on an eye dynamics signal of the user. An action may be initiated by the one or more processing units to affect the environment accordingly. ## Claims ### Claim 1 A method for updating response profiles of users, the method comprising: operating for capturing a plurality of images thereby at least one imaging sensor deployed to monitor at least one eye of a user; receiving and analyzing at least some of the plurality of images to identify at least one eye dynamics signal pattern preceding at least one abnormal event occurring in an environment viewed by the user, the at least one eye dynamics signal pattern is identified according to a function of a change in frequencies of pupil fluctuations over time, wherein values of the function are determined using an energy ratio between frequencies in different ranges; updating a response profile of the user based on an association of the at least one abnormal event and the identified at least one eye dynamics signal pattern; and communicating with at least one processing unit for providing thereto information based on the updated response profile of the user, the provided information is configured to enable the at least one processing unit to predict an imminent abnormal event based on an eye dynamic signal pattern of the user. ### Claim 2 (depends on 1) The method of claim 1, further comprising: analyzing at least some of the plurality of images to identify at least one additional eye dynamics signal pattern succeeding the at least one abnormal event; and in response to the identified at least one additional eye dynamics signal pattern occurring within a selected time window after the at least one abnormal event, forgoing updating the response profile of the user using the identified at least one eye dynamics signal pattern. ### Claim 3 (depends on 1) The method of claim 1, further comprising: in response to the identified at least one eye dynamics signal pattern occurring within a first selected time window prior to the at least one abnormal event, making a first update to the response profile of the user; and in response to the identified at least one eye dynamics signal pattern occurring within a second selected time window prior to the at least one abnormal event, making a second update to the response profile of the user, wherein the second update differs from the first update and the second selected time window differs from the first selected time window. ### Claim 4 (depends on 1) The method of claim 1, further comprising, in response to the identified at least one eye dynamics signal pattern occurring within a selected time window prior to the at least one abnormal event, forgoing updating the response profile of the user using the identified at least one eye dynamics signal pattern. ### Claim 5 (depends on 1) The method of claim 1, wherein the at least one imaging sensor comprises at least one of: an infrared imaging sensor and a thermal imaging sensor. ### Claim 6 (depends on 1) The method of claim 1, wherein the plurality of images is captured during a member selected from the group consisting of: simulations presented to the user; and real world activities of the user. ### Claim 7 (depends on 1) The method of claim 1, wherein the at least one eye dynamics signal pattern describes eye dynamics which is a member of a group consisting of: a dilatation level of a pupil of the at least one eye, a contraction level of the pupil of the at least one eye, a pupillary response time of a pupil of the at least one eye, a frequency of movement of the at least one eye, a gaze vector of the at least one eye and a saccade. ### Claim 8 (depends on 1) The method of claim 1, wherein the at least one abnormal event includes at least one of: an environment change event, an irregular objects' behavior event, an object falling event, a potential collision event, a potential life threatening event, and a potential injury damage event. ### Claim 9 (depends on 1) The method of claim 1, further comprising updating the response profile of the user according to at least one other response profile created for at least one other user sharing at least one common attribute with the user. ### Claim 10 (depends on 1) The method of claim 1, further comprising updating the response profile of the user to associate the at least one abnormal event with at least one other dynamics pattern of the user identified to precede the at least one abnormal event, wherein the at least one other dynamics pattern relates to bodily dynamics comprising at least one of: a facial expression of the user, a limb gesture of the user, a bodily gesture of the user, and a body pose of the user. ### Claim 11 (depends on 1) The method of claim 1, further comprising updating the response profile of the user based on at least one user state parameter derived from an analysis of fluctuations of a pupil of the at least one eye detected in the at least some of the plurality of images, the at least one user state parameter is indicative of at least one of: a physiological state of the user, a cognitive state of the user and an emotional state of the user. ### Claim 12 (depends on 1) The method of claim 1, wherein analysis of the at least some of the plurality of images to identify the at least one eye dynamics signal pattern comprising computing at least one eye dynamics signal according to at least one member selected from the group consisting of: a slope of change in eye movement by at least one of a first and second derivative, a magnitude of change in eye movement, and a distribution of frequencies of pupil fluctuations. ### Claim 13 (depends on 1) The method of claim 1, wherein analysis of the at least some of the plurality of images to identify the at least one eye dynamics signal pattern comprising computing at least one eye dynamics signal, applying a threshold to extract one or more peaks of the at least one eye dynamics signal computed, and identifying the at least one eye dynamics signal pattern based on the one or more peaks extracted. ### Claim 14 (depends on 1) The method of claim 1, wherein the energy ratio is between low frequencies in a range of 0 Hz to 0.08 Hz or 0.04 Hz to 0.15 Hz and high frequencies in a range of 0.15 Hz to 0.8 Hz or 0.16 Hz to 0.4 Hz. ### Claim 15 (depends on 1) A method for automated control using response profiles of users updated by performing the method of claim 1, comprising: operating for capturing a first another plurality of images thereby at least one imaging sensor deployed to monitor at least one eye of a user; receiving and analyzing at least some of the first another first plurality of images to identify at least one eye dynamics signal pattern, the at least one eye dynamics signal pattern is identified according to a function of a change in frequencies of pupil fluctuations over time, wherein values of the function are determined using an energy ratio between frequencies in different ranges; using the identified at least one eye dynamics signal pattern to predict at least one imminent abnormal event based on a response profile of the user; and using the at least one processing unit for initiating at least one action for addressing an interaction involving at least one of the user and other objects in the environment according to the predicted at least one abnormal event. ### Claim 16 (depends on 15) The method of claim 15, further comprising: operating for capturing a second another plurality of images thereby the at least one imaging sensor after the identification of the at least one eye dynamics signal pattern; receiving and analyzing at least some of the second another plurality of images to identify at least one additional eye dynamics signal pattern, the at least one additional eye dynamics signal pattern is identified according to a function of a change in frequencies of pupil fluctuations over time, wherein values of the function are determined using an energy ratio between frequencies in different ranges; calculating an elapsed time between an occurrence of the at least one eye dynamics signal pattern and an occurrence of the at least one additional eye dynamics signal pattern; in response to a first calculated elapsed time, using the at least one processing unit for initiating at least one additional action for addressing the interaction; and in response to a second calculated elapsed time, using the at least one processing unit for forgoing initiating the at least one additional action for addressing the interaction, where the second calculated elapsed time is shorter than the first calculated elapsed time. ### Claim 17 (depends on 15) The method of claim 15, further comprising adjusting the at least one action according to at least one of: a physiological state of the user, a cognitive state of the user and an emotional state of the user. ### Claim 18 (depends on 15) The method of claim 15, further comprising determining the at least one abnormal event according to at least one other dynamics pattern predicted to precede the at least one abnormal event in the response profile of the user, wherein the at least one other dynamics pattern relates to bodily dynamics comprising at least one of: a facial expression of the user, a limb gesture of the user, a bodily gesture of the user and a body pose of the user. ### Claim 19 (depends on 15) The method of claim 15, further comprising using the at least one processing unit for initiating at least one second action for addressing the interaction according to a response of the user to the at least one action, the response of the user is determined according to an analysis of at least one image captured by the at least one imaging sensor after the at least one action is initiated. ### Claim 20 A system for updating response profiles of users, the system comprising: at least one processor configured to: operate to capture a plurality of images thereby at least one imaging sensor deployed to monitor at least one eye of a user; receive and analyze at least some of the plurality of images to identify at least one eye dynamics signal pattern preceding at least one abnormal event occurring in the environment viewed by the user, the at least one eye dynamics signal pattern is identified according to a function of a change in frequencies of pupil fluctuations over time, wherein values of the function are determined using an energy ratio between frequencies in different ranges; update a response profile of the user based on an association of the at least one abnormal driving event and the identified at least one eye dynamics signal pattern; and communicate with at least one processing unit to provide thereto information based on the updated response profile of the user, the provided information is configured to enable the at least one processing unit to predict an imminent abnormal event based on an eye dynamics signal pattern of the user.