Empowering University Ideological and Political Education Teaching Innovation with Digital Intelligence Technology

As the wave of digital transformation sweeps the globe and the national education digitalization strategic action is deeply implemented, university ideological and political education courses are facing unprecedented opportunities for innovation. Big data, intelligent algorithms, virtual reality, and other digital intelligence technologies have become the “smart code” for enhancing the effectiveness of ideological and political education. The challenges faced by traditional ideological and political education classrooms—such as abstract content, one-way indoctrination, and lagging evaluation—form a clear tension with the differentiated, flexible, and scenario-based learning needs of the “post-00s” youth, which can be effectively resolved through the application of digital intelligence technologies. General Secretary Xi Jinping emphasized, “Adhere to reform and innovation, promote the integrated construction of ideological and political education in universities, middle schools, and primary schools, and improve the targetedness and appeal of ideological and political education courses. Enhance the ability to educate people through the internet, and solidly carry out school ideological and political work and ideological work in the internet era.” Accelerating the modernization of education and implementing the fundamental task of fostering virtue through education urgently requires exploring the practical path of empowering university ideological and political education teaching innovation with digital intelligence technology.

随着数字化转型浪潮席卷全球和国家教育数字化战略行动深入实施，高校思政课正迎来前所未有的创新机遇，大数据、智能算法、虚拟现实等数智技术成为提升思想政治教育实效性的“智慧密码”。传统思政课堂面临的内容抽象、单向灌输、评价滞后等挑战，与“00后”青年差异化、灵活化、场景化的学习需求形成明显张力，这恰恰能够通过数智技术的应用得到有效解决。习近平总书记强调，“坚持改革创新，推进大中小学思想政治教育一体化建设，提高思政课的针对性和吸引力。提高网络育人能力，扎实做好互联网时代的学校思想政治工作和意识形态工作”。加快推进教育现代化，落实好立德树人根本任务，迫切需要探索数智技术赋能高校思政课教学创新的现实路径。

Optimize and integrate teaching resources to promote targeted teaching. Digital intelligence technology provides a new solution for university ideological and political education courses to solve problems such as differentiated teaching objects and blurred teaching effects. It helps to transform ideological and political education teaching from “flood irrigation” to “precise drip irrigation” through the systematic integration and personalized supply of course resources. Knowledge graph technology can be used to achieve structured integration of teaching elements. Define key concepts, establish hierarchical relationships and logical connections, closely link textbook content on the same theme with real cases and video explanations, and set up dynamic access points for new policies and hot events, making abstract theories concrete into an interactive three-dimensional knowledge network. Multi-dimensional digital portraits and personalized algorithm recommendations can be used to enhance the targetedness of teaching practice. Integrate multi-source information such as online test results and online learning behaviors to construct multi-dimensional portraits of students’ cognitive levels, value orientations, and behavioral characteristics, accurately locate students’ theoretical weaknesses, value confusions, interests, and needs, and then automatically generate differentiated teaching plans. Based on collaborative filtering and deep learning algorithms, match personalized learning resources for students. For example, for students with vague understanding of the theory of surplus value, focus on pushing relevant explanatory videos; push the “Chinese Aerospace Spirit” thematic video to students in related majors or those interested in aerospace technology. AI teaching assistant systems can be used to enhance teaching efficiency. Carry out human-machine collaborative teaching, where AI teaching assistants can undertake basic tasks such as imparting background knowledge and assisting classroom discussions. Deploy AI teaching assistants based on large language models to achieve round-the-clock intelligent Q&A and interactive feedback. For example, answer hot and difficult questions through interactive dialogue, record high-frequency points of confusion, and help teachers continuously optimize teaching design.

优化整合教学资源，推动精准施教。数智技术为高校思政课破解教学对象差异化、教学效果模糊化等难题提供了新方案，有助于通过课程资源系统化整合与个性化供给，使思政课教学从“大水漫灌”向“精准滴灌”转变。可采用知识图谱技术实现教学要素结构化整合。定义关键概念，并建立层级关系和逻辑关联，将同主题的教材内容、现实案例和视频讲解紧密衔接，设置新政策、热点事件的动态接入口，使抽象理论具象化为可交互的立体知识网络。可使用多维数字画像与个性化算法推荐，增强教学实践针对性。整合在线测试结果、线上学习行为等多源信息，为学生构建认知水平、价值取向、行为特征的多维画像，精准定位学生的理论薄弱点、价值困惑点、兴趣点与需求点，进而自动生成差异化教学方案。基于协同过滤和深度学习算法，为学生匹配个性化的学习资源。例如，针对剩余价值理论认知模糊的学生，重点推送相关解析视频；将“中国航天精神”专题视频推送给相关专业或对航天科技感兴趣的学生。可运用AI助教系统提升教学效能。开展人机协同教学，AI助教可承担背景知识传授、辅助课堂讨论等基础工作。部署基于大语言模型的AI助教，实现全天候智能问答与互动反馈。例如，通过交互式对话解答热点难点问题，记录高频次疑惑点，帮助教师不断优化教学设计。

Construct a “multi-dimensional interaction—value resonance” teaching model. Driven by digital intelligence technology, university ideological and political education teaching is transforming from one-way indoctrination to deep interaction. By creating immersive scenarios, building dialogue bridges, and simulating social practice, it achieves the organic unity of knowledge transmission and value identification, promoting deep understanding and internalization. Immersive scenarios can be constructed based on virtual simulation technology to consolidate students’ value consensus. Break through the limitations of time and space, create a mixed-reality classroom, and achieve the concrete reconstruction of historical situations. College students can experience revolutionary historical scenes immersively through MR devices. For example, by participating in a “land reform meeting” in a virtual scene and having in-depth exchanges with virtual peasant representatives, their understanding of the mass line can transform from abstract conceptual cognition to emotional identification. Use digital twin technology to reconstruct real-life scenarios, allowing students to intuitively experience the achievements of socialist modernization. Students can “visit” rural revitalization demonstration villages built on digital twin platforms through VR devices, closely observe modern agricultural facilities, characteristic industrial layouts, etc., and deepen their understanding of the goal of common prosperity for all people. A teacher-student dialogue network can be built through real-time interactive systems. Embed bullet comments in course PPTs, where students can engage in viewpoint collisions on the teacher’s lecture content and interactive questions. The AI system automatically categorizes and generates debate focus points and keywords, and the teacher promptly responds to controversial points and points of concern. Construct an open, autonomous, and decentralized multi-modal teacher-student interaction scenario, allowing students to internalize the learned theories through experience, interaction, reflection, and empathy. Human-machine collaborative decision-making training can be carried out, enabling students to form identification with national strategies in the process of cooperatively solving practical problems. Introduce a decision-making simulation system, design scenarios based on hot policies, allow students to express viewpoints and submit decision plans in specific situations, and the AI system analyzes and displays the short-term and long-term impacts of different decisions on different groups through data modeling, visualization tools, etc.

构建“多维交互—价值共鸣”的教学模式。在数智技术驱动下，高校思政课教学正从单向灌输向深度交互转型，通过创设沉浸式场景、搭建对话桥梁、模拟社会实践，实现知识传递与价值认同的有机统一，推动入脑入心。可依托虚拟仿真技术构建沉浸式场景，凝聚学生价值共识。突破时空限制，打造混合现实课堂，实现历史情境的具象化重构。大学生可通过MR设备身临其境地感受革命历史场景，例如，通过参与虚拟场景中的“土地改革会议”，与虚拟农民代表进行深入交流，将对群众路线的理解从抽象的概念认知转变为情感认同。运用数字孪生技术重建现实情景，让学生直观体验社会主义现代化建设成果。学生可通过VR设备“实地”参观数字孪生平台搭建的乡村振兴示范村，近距离观摩现代化农业设施、特色产业布局等，深化对全体人民共同富裕目标的领会。可通过实时交互系统建设师生对话网络。在课程PPT中嵌入弹幕，学生可针对教师讲解内容和互动问题进行观点碰撞，AI系统自动归类生成辩论焦点和关键词，教师及时对争议点、关注点进行回应。构建开放、自主和去中心化的多模态师生互动场景，让学生在体验、交互、反思和共情中内化所学理论。可开展人机协同决策训练，使学生在合作解决实际问题中形成对国家战略的认同。引入决策模拟系统，基于热点政策设计剧情，让学生在特定情境下表达观点和提交决策方案，AI系统通过数据建模、可视化工具等分析和展示不同决策对不同群体的长短期影响。

Build an intelligent teaching evaluation and feedback system. Digital intelligence technology can solve the problems of subjectivity and lag in the evaluation of university ideological and political education courses through multi-modal data collection, intelligent evaluation tools, instant feedback mechanisms, etc., promoting the upgrading of the ideological and political education model. Implement comprehensive and whole-process data information collection to lay a solid foundation for precise evaluation. Use electronic sign-in systems, smart cameras, wearable devices, digital platforms, etc., to record students’ learning status, learning behaviors, learning outcomes, and other information throughout the process, including attendance rate, interaction frequency, collaboration ability, thinking activity, quality of questions and speeches, chapter test scores, etc. Collect the number, quality, and results of students’ participation in extracurricular social practice through mobile terminals, and dynamically track their practical abilities. Use intelligent platforms or tools to build a human-machine collaborative precise evaluation system. Develop digital and intelligent teaching platforms to reduce the subjectivity and errors of manual evaluation and improve the accuracy and efficiency of evaluation. Adopt paperless examination platforms, where the AI system automatically scores objective question types and generates error analysis reports. In addition, the AI system can structure indicators such as logic, terminology standardization, knowledge point matching, and value orientation, leverage its natural language rapid processing capability to conduct preliminary evaluations of subjective questions, and provide a strong reference for teachers’ final evaluations. Establish a multi-dimensional teacher evaluation system supporting student evaluation, peer evaluation, supervisor evaluation, and teacher self-evaluation. The AI system integrates scoring data, generates teaching quality reports, and proposes improvement suggestions. Establish an instant feedback mechanism to provide information support for teaching optimization. Conduct “in-class micro-surveys,” push online survey questionnaires at the end of the course, quickly collect students’ questions and suggestions focusing on teaching methods, teaching content, teaching effects, etc., so that teachers can promptly grasp teaching difficulties and pain points. Develop an academic big data monitoring platform, analyze data such as homework completion rates and knowledge point mastery, help teachers identify students with learning difficulties, and provide targeted tutoring.

打造智能化教学评价与反馈体系。数智技术能够通过多模态数据采集、智能评价工具、即时反馈机制等破解高校思政课评价的主观性、滞后性困境，推动思想政治教育模式升级。可实施全方位全过程数据信息采集，夯实精准评价基础。利用电子签到系统、智能摄像头、可穿戴设备、数字化平台等全程记录学生的学习状态、学习行为、学习成果等信息，包括出勤率、互动频率、协作能力、思维活跃度、提问和发言质量、章节测试成绩等。通过移动终端收集学生参与课外社会实践的次数、质量及成果，对其实践能力进行动态跟踪。可使用智能平台或工具构建人机协同精准评价体系。开发数智化教学平台，减少人工评价的主观性和误差，提高评价的准确性和效率。采用无纸化考试平台，AI系统自动对客观题型进行判分，并生成错题分析报告。此外，AI系统还可将逻辑性、术语规范性、知识点匹配度、价值观导向等指标结构化，发挥自然语言快速处理能力，对主观题进行初评，为教师终评提供有力参考。建立支持学生评、同行互评、督导评、教师自评的多维度教师评价系统，AI系统综合评分数据，生成教学质量报告，并提出改进建议。建立即时反馈机制，为教学优化提供信息支持。可开展“随堂微调查”，在课程结束时推送在线调查问卷，聚焦教学方法、教学内容、教学效果等层面快速收集学生的疑问和建议，使教师及时掌握教学难点和痛点。开发学业大数据监测平台，分析作业完成率、知识点掌握等数据，帮助教师识别学习困难学生，提供有针对性的辅导。

(Author: Ke Meng, Special Researcher of the Shanghai Research Center for Xi

（作者：柯萌，系上海市习近平新时代中国特色社会主义思想研究中心特约研究员、同济大学马克思主义学院助理教授）

Online editor: Tongxin

网络编辑：同心