{"id":1441,"date":"2026-06-14T03:18:33","date_gmt":"2026-06-13T19:18:33","guid":{"rendered":"https:\/\/aifed.now\/conference\/?page_id=1441"},"modified":"2026-06-14T03:18:33","modified_gmt":"2026-06-13T19:18:33","slug":"%e4%b8%bb%e9%a1%8c%e4%b8%80%ef%bc%9a%e6%95%99%e5%b8%ab%e8%b3%a6%e8%83%bd-%e6%a5%8a%e6%99%ba%e7%90%a8-%e6%95%b8%e4%bd%8d%e5%8c%96%e5%ad%b8%e7%bf%92%e5%96%ae%e4%bd%9c%e6%a5%ad%e6%89%b9%e6%94%b9","status":"publish","type":"page","link":"https:\/\/aifed.now\/conference\/?page_id=1441","title":{"rendered":"\u4e3b\u984c\u4e00\uff1a\u6559\u5e2b\u8ce6\u80fd \/ \u694a\u667a\u7428 \/ \u6578\u4f4d\u5316\u5b78\u7fd2\u55ae\u4f5c\u696d\u6279\u6539\u7cfb\u7d71"},"content":{"rendered":"<\/p>\n

\u6578\u4f4d\u5316\u5b78\u7fd2\u55ae\u4f5c\u696d\u6279\u6539\u7cfb\u7d71<\/h3>\n<\/p>\n
\n

\"\u694a\u667a\u7428\"<\/p>\n

\u8b1b\u8005\/Speaker\uff1a<\/strong> \u694a\u667a\u7428, YANG ZHI KUN <\/span> <\/p>\n<\/div>\n

<\/p>\n

\n

\u9ad8\u4e2d\u6559\u5e2b\u65e5\u5e38\u9762\u81e8\u5927\u91cf\u5b78\u7fd2\u55ae\u6279\u6539\u5de5\u4f5c\uff0c\u4e00\u4efd\u5b78\u7fd2\u55ae\u5f9e\u6574\u7406\u3001\u8a55\u95b1\u5230\u8f38\u51fa PDF \u5b78\u7fd2\u6b77\u7a0b\uff0c\u5f80\u5f80\u8017\u6642\u6578\u5c0f\u6642\u4ee5\u4e0a\u3002\u91cd\u8907\u7684\u6587\u5b57\u56de\u994b\u3001\u7acb\u53ef\u5e36\u4fee\u6b63\u3001\u684c\u9762\u88ab\u4f5c\u696d\u6df9\u6c92\uff0c\u4e0d\u50c5\u640d\u8017\u6559\u5e2b\u5fc3\u529b\uff0c\u4e5f\u5f71\u97ff\u5b78\u7fd2\u6b77\u7a0b\u6a94\u6848\u7684\u5448\u73fe\u54c1\u8cea\u3002
\n\u672c\u7814\u7a76\u8a2d\u8a08\u4e00\u5957\u300c\u6578\u4f4d\u5316\u5b78\u7fd2\u55ae\u4f5c\u696d\u6279\u6539\u7cfb\u7d71\u300d\uff0c\u63a1\u7528 Python 3 + PyQt5 + PyMuPDF + SQLite \u67b6\u69cb\uff0c\u5c07\u6559\u5e2b\u6279\u6539\u6d41\u7a0b\u62c6\u89e3\u70ba\u5169\u689d\u4e3b\u7dda\uff1a\u9801\u9762\u6574\u7406\uff08\u652f\u7dda A\uff09\u63d0\u4f9b\u4e94\u78bc\u5ea7\u865f\u5feb\u6377\u6a19\u8a18\u3001\u81ea\u52d5\u8df3\u9801\u3001\u9801\u9762\u65cb\u8f49\u8207\u7fa4\u7d44\u5408\u4f75\uff1b\u8a55\u6539\u4f5c\u696d\uff08\u652f\u7dda B\uff09\u6574\u5408\u5370\u7ae0\u7e2e\u5716\u7246\u3001\u7f50\u982d\u8a55\u8a9e\u5feb\u6377\u9215\uff0c\u4e26\u4ee5\u5411\u91cf\u65b9\u5f0f\u5c07 A4 \u539f\u7a3f\u7121\u640d\u758a\u5408\u81f3 A3 \u756b\u5e03\u8f38\u51fa\u3002
\n\u7cfb\u7d71\u6700\u5927\u7279\u8272\u70ba\u300c\u985e\u4f3c\u904a\u6232\u5b58\u6a94\uff0f\u8f09\u5165\u7684\u4efb\u52d9\u7ba1\u7406\u6a5f\u5236\u300d\uff1a\u6559\u5e2b\u53ef\u96a8\u6642\u4e2d\u65b7\u6279\u6539\uff0c\u4e0b\u6b21\u96d9\u64ca\u8f09\u5165\u5373\u53ef\u7e8c\u505a\uff0c\u9032\u5ea6\u3001\u5370\u7ae0\u8a2d\u5b9a\u3001\u8a55\u8a9e\u7d00\u9304\u5b8c\u6574\u4fdd\u7559\uff1b\u9072\u4ea4\u8207\u88dc\u4ea4\u4f5c\u696d\u53ef\u4e2d\u9014\u8ffd\u52a0\uff0c\u65b0\u6a94\u6848\u9644\u52a0\u81f3\u4efb\u52d9\u5c3e\u7aef\u3001\u81ea\u52d5\u6b78\u5165\u540c\u5b78\u865f\u7fa4\u7d44\uff0c\u5fb9\u5e95\u89e3\u6c7a\u50b3\u7d71\u6279\u6539\u6d41\u7a0b\u300c\u4e00\u65e6\u4e2d\u65b7\u4fbf\u96e3\u4ee5\u63a5\u7e8c\u300d\u7684\u75db\u9ede\u3002
\n\u7d93 50\u4efd\u9ad8\u4e2d\u7269\u7406\u5b78\u7fd2\u55ae\u5be6\u6e2c\uff0c\u6279\u6539\u6642\u9593\u7531 3 \u5c0f\u6642\u7e2e\u77ed\u81f3 1 \u5c0f\u6642\uff0c\u7acb\u53ef\u5e36\u7528\u91cf\u6b78\u96f6\uff0c\u4e26\u7a69\u5b9a\u7522\u51fa\u53ef\u76f4\u63a5\u4e0a\u50b3\u5b78\u7fd2\u6b77\u7a0b\u7684 A3 PDF \u6a94\u6848\u3002\u7cfb\u7d71\u958b\u767c\u968e\u6bb5\u501f\u52a9 AI \u5354\u4f5c\u5b8c\u6210\uff0c\u4f46\u4f7f\u7528\u7aef\u4e0d\u4f9d\u8cf4\u7db2\u8def\u3001\u4e0d\u6d88\u8017 token\uff0c\u4efb\u4f55\u6559\u5e2b\u96d9\u64ca\u5373\u53ef\u555f\u7528\uff0c\u5177\u5099\u96f6\u6210\u672c\u3001\u96f6\u9580\u6abb\u3001\u96f6\u4f9d\u8cf4\u7684\u63a8\u5ee3\u7279\u6027\u3002<\/p>\n

\u00a0<\/p>\n\n

High school teachers routinely face a heavy worksheet grading workload. Processing a single batch \u2014 from sorting and evaluating to producing PDF learning portfolios \u2014 typically consumes several hours. Repetitive written feedback, correction fluid usage, and desk clutter not only drain teachers' energy but also compromise the visual quality of student portfolio records.
\nThis study presents a Digital Worksheet Grading System, built on Python 3 with PyQt5, PyMuPDF, and SQLite. The grading workflow is divided into two parallel tracks: page organization (Track A) offers five-digit seat-number quick tagging, auto page-advancing, page rotation, and group merging; grading (Track B) integrates a visual stamp gallery, canned-comment shortcuts, and lossless A4-to-A3 vector composition.
\nThe system's defining feature is its game-like save \/ load task management: teachers can interrupt grading at any moment and resume seamlessly with a single double-click, with progress, stamp settings, and comment records fully preserved. Late submissions and supplementary worksheets can be appended mid-task and are automatically grouped under the corresponding student ID, eliminating the long-standing pain point that \"once interrupted, grading is hard to resume.\"
\nField testing on 50 physics worksheets reduced grading time from 3 hours to 1 hour, eliminated correction fluid use, and produced consistently high-quality A3 PDFs ready for portfolio submission. While the development phase was supported by AI-assisted programming, the end-user application requires no network connection and consumes no tokens \u2014 any teacher can launch it with a single double-click, achieving zero-cost, zero-barrier, and zero-dependency adoption.<\/p>\n

\u00a0<\/p>\n<\/div>\n

\u00a0<\/p>\n

\n