Alibaba Cloud Milvus Builds Knowledge Graphs and Wiki from Documents
Alibaba Cloud’s Milvus can organize enterprise documents into sourced knowledge graphs and Wiki pages for verification, maintenance, retrieval, and AI question answering, according to a vendor-oriented report. The demonstrated workflow defines objects and relationships through a graph schema, optionally uses AI to generate that schema, and builds the graph and Wiki independently before combining them in an answer. The example uses fictional after-sales materials to test battery warranty coverage, Hangzhou service availability, and application guidance.
The report presents a concrete enterprise workflow for combining structured policy relationships, human-readable guidance, source citations, and AI question answering, although the evidence comes from a single vendor-oriented article using fictional data.
一家办公设备商的客服，收到一条咨询：
“笔记本买了18个月，电池充不进电。整机还在保，电池能免费换吗？我在杭州，能上门吗？”
客服需要同时查看产品说明、保修条款、服务范围和申请指引，确认电池适用的期限、杭州可提供的服务，以及申请入口。信息分在不同文档里，一次答复往往需要多次查找。
阿里云向量检索服务 Milvus 版的知识构建能力，可以将企业文档组织成有来源的知识图谱和 Wiki，供团队查证、阅读和维护，并用于检索与 AI 问答。
下面用一组虚构售后资料，看看如何在控制台定义业务对象、构建图谱和 Wiki，再用同一条咨询检查回答。图谱与 Wiki 可以分别构建，按业务需要使用。