# US 2026/0100142 A1 · Intuitive graph guided question-answer for interactive education experiences > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0100142 A1 - Document ID: US20260100142A1 - Status: Published application - Kind: A1 - Application number: 18/831,236 - Filed: 2024-10-04 - Published: 2026-04-09 - Earliest claimed: 2024-10-04 - Inventors: Nicholas X. Wang - Web page: https://patentgrep.com/patent/US20260100142A1 ## CPC - G09B 7/06: of the multiple-choice answer-type, i.e. where a given question is provided with a series of answers and a choice has to be made from the answers - G06N 20/00: Machine learning - 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 An intuitive optimized method for answering a question with graphical guided steps includes: setting or adjusting an Intuitive Level Metric (ILM); receiving a question with multiple choice answers; generating a causal graph corresponding to the question; transforming both the question and the causal graph into a concatenated text stream and embedding; inputting the embedded stream into an ILM-optimized machine learning module to generate an output text; processing the output text stream to generate an answer and a list of pairs of text steps and drawing commands; processing the list of pairs sequentially, first rendering the text step and then creating a drawing based on the command; and outputting the final answer choice. ## Claims ### Claim 1 A method for providing an answer, comprising: receiving a question with a plurality of multiple choice answers; generating a casual graph from the question with the multiple choice answers; generating an answer choice and a list of pairs of text steps and drawing commands based on the causal graph; and outputting the answer choice, one or more text steps and one or more drawings based on the drawing commands. ### Claim 2 (depends on 1) The method according to claim 1, further comprising: providing an Intuitive Level Metric (ILM); optimizing a machine learning model using the ILM. ### Claim 3 (depends on 2) The method according to claim 2, wherein the machine learning model is optimized by optimizing a loss function of the ILM, the loss function for optimizing ILM is L=a*Etext+b*Ecmd+C*Estep+d*Ecolor, wherein Etext, Ecmd, Estep and Ecolor respectively represent errors in text answer, command, number of steps in the text answer, and number of drawing colors. ### Claim 4 (depends on 1) The method according to claim 1, wherein the step of generating an answer choice comprises: transforming the question and the casual graph into a concatenated text stream; feeding the concatenated text stream into the ILM optimized machine learning model to generate an output text stream; processing the output text stream to generate the answer choice and the list of pairs of text steps and drawing commands. ### Claim 5 (depends on 1) The method according to claim 1, wherein the step of outputting the answer choice, the one or more text steps and one or more drawings based on the drawing commands comprises: processing the list of pairs of text steps to render text steps and create drawings based on the drawing commands; output the answer choice; and outputting in interleaved mode by displaying a text step followed by a drawing, if drawing commands are available for that step, and repeating this process iteratively until all text steps in the list are completed. ### Claim 6 (depends on 2) The method according to claim 2, wherein setting or adjusting the ILM includes: determining an importance level of the text answer versus a graphical illustration; determining a level of detail in describing the steps to solve the problem; and determining a level of colorfulness of the graphical illustration. ### Claim 7 (depends on 1) The method according to claim 1, wherein generating the causal graph corresponding to the question comprises: generating a sub-graph of a master graph corresponding to a current subject based on the question. ### Claim 8 (depends on 4) The method according to claim 4, wherein transforming the question and the causal graph into the concatenated text stream comprises: transforming the causal graph into a transformed causal graph text stream including a raw text format following a predefined syntax; concatenating the question in raw text format with the transformed causal graph text stream into the concatenated text stream; and embedding the concatenated text stream into a format that a GPT model that is cable of understanding and processing. ### Claim 9 (depends on 2) The method according to claim 2, wherein inputting the embedded stream into an ILM-optimized machine learning module to generate an output text comprises: preparing training data with ground truth sample questions, associated causal graph data, step-by-step text answers, and associated graph drawing commends; training a machine learning model by minimizing a loss function that aims to optimize the highest ILM level; and inputting the embedded stream into the trained model to generate output text stream. ### Claim 10 (depends on 4) The method according to claim 4, further comprises: extracting the answer from the output text stream; and extracting the list of pairs of text steps and drawing commands from the output text stream. ### Claim 11 (depends on 4) The method according to claim 4, further comprises: processing the list of pairs in a sequential order; rendering the text step in each pair as a current step; and rendering a drawing based on the commend in the same pair, wherein the drawing is used to enhance the text step and make the answer more intuitive. ### Claim 12 An intuitive optimized device for answering a question with graphical guided steps, comprising: a memory storing program instructions; and a processor coupled with the memory and configured to execute the program instructions to: set or adjust an Intuitive Level Metric (ILM); receive a question with multiple choice answers; generate a causal graph corresponding to the question; transform both the question and the causal graph into a concatenated text stream and embedding; input the embedded stream into an ILM-optimized machine learning module to generate an output text; process the output text stream to generate an answer and a list of pairs of text steps and drawing commands; process the list of pairs sequentially, first rendering the text step and then creating a drawing based on the command; and output the final answer choice. ### Claim 13 An intuitive optimized system for answering a question with graphical guided steps, comprising: a terminal device configured to: set or adjust an Intuitive Level Metric (ILM); receive a question with multiple choice answers; send the request to a cloud server; receive a text stream from the cloud server; process the received text stream to generate an answer and a list of pairs of text steps and drawing commands; process the list of pairs sequentially, first rendering the text step and then creating a drawing based on the command; and output the final answer choice; wherein the cloud server is configured to: receive the question from the terminal device; generate a causal graph corresponding to the question; transform both the question and the causal graph into a concatenated text stream and embedding; input the embedded stream into an ILM-optimized machine learning module to generate an output text; and send the text stream to the terminal device. ### Claim 14 (depends on 13) The system according to claim 13, wherein: the terminal device communicates with the cloud server through HTTP API.