# US 11,443,645 B2 · Education reward system and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,645 B2 - Document ID: US11443645B2 - Status: Granted - Kind: B2 - Application number: 16/688,172 - Filed: 2019-11-19 - Published: 2020-03-19 - Granted: 2022-09-13 - Earliest claimed: 2017-04-26 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: James R. Kozloski; Shikhar Kwatra; Rosanna S. Mannan; Emily A. Ray - Web page: https://patentgrep.com/patent/US11443645B2 ## CPC - G09B 5/02: with visual presentation of the material to be studied, e.g. using film strip - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 20/00: Machine learning - G09B 5/00: Electrically-operated educational appliances (working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F) - G09B 7/00: Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F) - G09B 19/00: Teaching not covered by other main groups of this subclass (teaching or practice apparatus for gun-aiming or gun-laying F41G3/26) - G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A reward learning system includes a user interface configured to receive modes of user information related to a state of the user. A cognitive computing system includes a reward system. The reward system includes a dynamically upgraded profile model of the user which is updated in accordance with the user information related to the state. The reward system is updated by machine learning employing feedback from user responses measured by the user interface and searched information by the cognitive computing system. The reward system includes an increasing reward protocol based on learned user preferences and responses and rewarded in accordance with user achievements. ## Claims ### Claim 1 A reward learning system, comprising: a user interface configured to receive a plurality of modes of user information related to a state of the user; a cognitive computing system having a processor and memory including a reward system, the reward system being updated by machine learning employing feedback from user responses measured by the user interface, and determined independent causes in state data for ensemble feature vectors from the state of the user; the reward system including a reward protocol based on learned user preferences and responses and rewarded in accordance with user achievements. ### Claim 2 (depends on 1) The system as recited in claim 1, wherein the user interface includes a camera to evaluate and measure, in real-time, the state of the user. ### Claim 3 (depends on 1) The system as recited in claim 1, wherein the state of user is stored in a state feature vector including multiple dimensions associating with different features with states of the user. ### Claim 4 (depends on 3) The system as recited in claim 3, wherein the states of the user and changes to the states of the user are employed to evaluate rewards in the reward protocol. ### Claim 5 (depends on 1) The system as recited in claim 1, wherein the reward protocol includes a reward feature vector which stores all possible reward scenarios specific to the user. ### Claim 6 (depends on 5) The system as recited in claim 5, wherein the reward feature vector includes rewards associated with the state of the user as determined using machine learning. ### Claim 7 (depends on 5) The system as recited in claim 5, wherein the reward feature vector includes rewards granted unpredictably to the user. ### Claim 8 (depends on 1) The system as recited in claim 1, wherein the searched information includes information independently researched by the cognitive system. ### Claim 9 (depends on 1) The system as recited in claim 1, wherein the plurality of modes of user information is selected from the group consisting of speech recognition, gesture recognition, user supplied data, measured data and network searched data. ### Claim 10 A reward learning system, comprising: a user interface configured to receive a plurality of modes of user information related to a state of the user; a cognitive computing system including a processor and memory coupled to the processor, the memory including a reward system stored therein, the reward system including: a state feature vector including multiple dimensions associating different features with states of the user, wherein the states of the user and changes to the states of the user are employed to evaluate rewards in a reward protocol; the reward protocol including a reward feature vector which stores all possible reward scenarios specific to the user; a machine learning module incorporated within the cognitive computing system, the machine learning module associating rewards with states in accordance with positive stimulation of the user based on determined independent causes in state data for ensemble feature vectors from the state of the user. ### Claim 11 (depends on 10) The system as recited in claim 10, wherein the reward feature vector includes rewards associated with the state of the user as determined using machine learning. ### Claim 12 (depends on 10) The system as recited in claim 10, wherein the reward system includes an increasing reward protocol based on learned user preferences and responses and rewarded in accordance with user achievements. ### Claim 13 (depends on 10) The system as recited in claim 10, wherein the user interface includes a camera to evaluate and measures, in real-time, the state of the user. ### Claim 14 (depends on 10) The system as recited in claim 10, wherein the reward feature vector includes rewards associated with the state of the user as determined using machine learning. ### Claim 15 (depends on 14) The system as recited in claim 14, wherein the reward feature vector includes rewards granted unpredictably to the user. ### Claim 16 (depends on 10) The system as recited in claim 10, wherein the user information includes information independently researched by the cognitive system. ### Claim 17 (depends on 10) The system as recited in claim 10, wherein the plurality of modes of user information is selected from the group consisting of speech recognition, gesture recognition, user supplied data, measured data and network searched data. ### Claim 18 A method for reward-based learning, comprising: interfacing with a user to receive a plurality of modes of user information related to a state of the user; evaluating the user information with machine learning of a cognitive computing system to determine a reward protocol to award learning achievements by the user; updating the reward protocol using the state of the user and the machine learning including determined independent causes in state data for ensemble feature vectors from the state of the user; and unpredictably rewarding the user in accordance with the reward protocol when goals are achieved. ### Claim 19 (depends on 18) The method as recited in claim 18, wherein interfacing with the user includes imaging the user with a camera to evaluate and measure in real-time the state of the user. ### Claim 20 (depends on 18) The method as recited in claim 18, wherein the state of user is stored in a state feature vector including multiple dimensions by associating with different features with states of the user, wherein the states of the user and changes to the states of the user are employed to evaluate rewards in the reward protocol.