# US 2026/0100140 A1 · Artificial Intelligence-based Exam Question Generating Method and System > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0100140 A1 - Document ID: US20260100140A1 - Status: Published application - Kind: A1 - Application number: 19/071,785 - Filed: 2025-03-06 - Published: 2026-04-09 - Earliest claimed: 2024-10-08 - Assignees: ViewSonic International Corporation - Applicants: ViewSonic International Corporation - Inventors: Hsin-Yu Lin; I-Hsin Chen; Yu-Ming Lu; Kevin-Kuo Chu; Yun-Cheng Hsin; Shun-Ta Wang; Chin-Shou Lin; Wang-Fat Ho - Web page: https://patentgrep.com/patent/US20260100140A1 ## CPC - G09B 7/00: Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F) - G06N 5/027: {Frames} - G06N 20/00: Machine learning - G09B 7/02: of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student - 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 exam question generating method, based on artificial intelligence (AI), includes receiving at least one reference material input by a user; receiving at least one exam parameter input by the user; and generating a plurality of exam question rules through an AI model, and generating at least one exam question that complies with the plurality of exam question rules based on the at least one reference material and the at least one exam parameter; wherein the AI model has undergone a pre-training process, and the pre-training process includes setting at least one educational material as a training dataset; and analyzing the training dataset to induce the plurality of exam question rules. ## Claims ### Claim 1 An exam question generating method, based on artificial intelligence (AI), comprising: receiving at least one reference material input by a user; receiving at least one exam parameter input by the user; and generating a plurality of exam question rules through an AI model, and generating at least one exam question that complies with the plurality of exam question rules based on the at least one reference material and the at least one exam parameter; wherein the AI model has undergone a pre-training process, and the pre-training process comprises: setting at least one educational material as a training dataset; and analyzing the training dataset to induce the plurality of exam question rules. ### Claim 2 (depends on 1) The exam question generating method of claim 1, wherein the at least one reference material is selected from one or more of an image, a video, an audio file, a text document, and a webpage link. ### Claim 3 (depends on 1) The exam question generating method of claim 1, wherein the at least one exam parameter is selected from one or more of a subject domain, an exam question type, a learning objective or a learning checkpoint, an educational level, and a language proficiency level. ### Claim 4 (depends on 1) The exam question generating method of claim 1, wherein the at least one educational material is selected from one or more of at least one educational theory, at least one language proficiency standard, at least one textbook, a plurality of exam questions, and open-source materials. ### Claim 5 (depends on 4) The exam question generating method of claim 4, wherein the at least one educational theory is selected from one or more of Bloom's taxonomy or the 12-Year Basic Education Curriculum Guidelines and Implementation Regulations, and the at least one language proficiency standard is selected from one or more of Lexile Framework and Common European Framework of Reference for Languages. ### Claim 6 (depends on 1) The exam question generating method of claim 1, wherein the step of analyzing the training dataset to induce the plurality of exam question rules in the pre-training process comprises: inducing a plurality of exam question types and a plurality of key points of exam based on the training dataset; inducing a plurality of words that comply with at least one language proficiency standard based on the at least one language proficiency standard; and inducing the plurality of exam question rules based on the plurality of exam question types, the plurality of key points of exam, and the plurality of words. ### Claim 7 (depends on 6) The exam question generating method of claim 6, wherein the AI model uses the plurality of words that comply with the at least one language proficiency standard to generate the at least one exam question. ### Claim 8 (depends on 6) The exam question generating method of claim 6, wherein the at least one language proficiency standard is selected from one or more of Lexile Framework and Common European Framework of Reference for Languages. ### Claim 9 (depends on 1) The exam question generating method of claim 1, further comprising outputting the at least one exam question in a format. ### Claim 10 (depends on 9) The exam question generating method of claim 9, wherein the format is selected from one or more of text, image, audio, video, and interactive interface. ### Claim 11 An exam question generating system, based on artificial intelligence (AI), comprising: a data input module, configured to receive at least one reference material input by a user; a parameter selection module, configured to receive at least one exam parameter input by the user; and an AI model, coupled to the data input module and the parameter selection module, configured to generate a plurality of exam question rules, and generate at least one exam question that complies with the plurality of exam question rules based on the at least one reference material and the at least one exam parameter; wherein the AI model has undergone a pre-training process, and the pre-training process comprises: setting at least one educational material as a training dataset; and analyzing the training dataset to induce the plurality of exam question rules. ### Claim 12 (depends on 11) The exam question generating system of claim 11, wherein the at least one reference material is selected from one or more of an image, a video, an audio file, a text document, and a webpage link. ### Claim 13 (depends on 11) The exam question generating system of claim 11, wherein the at least one exam parameter is selected from one or more of a subject domain, an exam question type, a learning objective or a learning checkpoint, an educational level, and a language proficiency level. ### Claim 14 (depends on 11) The exam question generating system of claim 11, wherein the at least one educational material is selected from one or more of at least one educational theory, at least one language proficiency standard, at least one textbook, a plurality of exam questions, and open-source materials. ### Claim 15 (depends on 14) The exam question generating system of claim 14, wherein the at least one educational theory is selected from one or more of Bloom's taxonomy or the 12-Year Basic Education Curriculum Guidelines and Implementation Regulations, and the at least one language proficiency standard is selected from one or more of Lexile Framework and Common European Framework of Reference for Languages. ### Claim 16 (depends on 11) The exam question generating system of claim 11, wherein the step of analyzing the training dataset to induce the plurality of exam question rules in the pre-training process comprises: inducing a plurality of exam question types and a plurality of key points of exam based on the training dataset; inducing a plurality of words that comply with at least one language proficiency standard based on the at least one language proficiency standard; and inducing the plurality of exam question rules based on the plurality of exam question types, the plurality of key points of exam, and the plurality of words. ### Claim 17 (depends on 16) The exam question generating system of claim 16, wherein the AI model uses the plurality of words that comply with the at least one language proficiency standard to generate the at least one exam question. ### Claim 18 (depends on 16) The exam question generating system of claim 16, wherein the at least one language proficiency standard is selected from one or more of Lexile Framework and Common European Framework of Reference for Languages. ### Claim 19 (depends on 11) The exam question generating system of claim 11, further comprising an output module, coupled to the AI model, configured to output the at least one exam question in a format. ### Claim 20 (depends on 19) The exam question generating system of claim 19, wherein the format is selected from one or more of text, image, audio, video, and interactive interface.