Lanxum wanted to make Chinese-language learning more engaging and personalized, but it needed a structured way to connect teaching content, teacher knowledge, dialogue, and student guidance instead of relying on static materials and manual customer support.
Reported impact
Lanxum turned static Chinese-learning materials into a conversational and recommendable teaching system, improving resource reuse, student engagement, and service efficiency while laying a foundation for more immersive AI teaching experiences.
Lanxum and Baidu AI Cloud built an education-oriented AI stack that starts with a Chinese teaching-research knowledge graph and extends into virtual teachers and intelligent dialogue. Teaching videos, lesson plans, notes, question banks, and teacher-training materials are organized as connected entities in a graph so relationships between concepts become searchable and reusable. On top of that, Baidu's virtual-human and voice-synthesis capabilities create interactive 'famous teacher' personas that can explain lessons, answer questions, and eventually support drama-style teaching. An intelligent voice-dialogue system connected to the knowledge graph supports pre-class preparation, post-class Q&A, and course recommendation, which also reduces the load on human service staff. Rather than treating AI as a single tutoring feature, the implementation links content structuring, persona generation, dialogue, and recommendation so Lanxum can reuse the same knowledge foundation across both teaching and student-service workflows.
Teaching assets such as videos, question banks, lesson plans, notes, and training materials are ingested into the knowledge graph and connected as reusable entities. The virtual teacher and dialogue system retrieve from that graph to answer student questions, guide preview and review sessions, and recommend courses through conversational interaction.
Baidu helps Lanxum create virtual teachers using visual and voice-synthesis capabilities (original: 借助虚拟视觉能力和语音合成技术，打造特定真人或动漫形象的声音、表情作为名师形象).
Lanxum and Baidu are jointly using AI to reinvent Chinese-language teaching (original: 立思辰与百度智能云正在联手实践，通过AI技术赋能语文教学).
Teaching videos, question banks, lesson plans, and notes are organized into a dedicated knowledge graph (original: 通过将教学资料（包含课程视频、教学培训、题库、教案、笔记等）理建设，纳入知识图谱中).
The intelligent dialogue system supports pre-class preview, post-class Q&A, and course recommendations while reducing human customer-service cost (original: 可实现更智能的课前预习和课后答疑…也可以作为人工客服的角色，根据学生的知识能力和问题需求为学生推荐适合的课程).
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Baidu AI Cloud Sample Oct 13, 2025 Kaoshibao (Shanghai Juxian Network Technology Co., Ltd.) Kaoshibao needed to use new AI interaction and content technologies to improve personalized learning, lower content-production costs, and make very large question banks easier to ingest, search, and explain. "Zero-basis" users improved certificate pass rates 35%. Intelligent Search and Generation Component · Multimodal Recognition · Qianfan AppBuilder Baidu AI Cloud Sample Jun 23, 2025 Tongji University Tongji University needed a domestic AI stack with stronger computing and model-tooling support for embodied intelligence, multimodal models, autonomous perception and multi-agent research. BaiGe AI Heterogeneous Compute Platform · Kunlun P800 · Qianfan AppBuilder Baidu AI Cloud Sample May 15, 2025 Shanghai Jiao Tong University Shanghai Jiao Tong University wanted to connect frontier AI techniques with real research workflows so faculty could use scientific data, models and computing resources more efficiently instead of relying on years of… A molecular SMILES query can return reaction processes, conditions and literature links in about 5 seconds. AI Middle Platform · BaiGe Heterogeneous Compute Platform · Data Middle Platform 