Enterprise Knowledge Search
Zhicheng Technology needed to turn large, messy, high-frequency industrial data into an AI-consumable asset base and agent platform while keeping graph queries, writes, and service uptime within strict manufacturing requirements.
Reported impact
Zhicheng eliminated downtime, improved industrial data-model efficiency, and gave customers a faster way to build private industrial knowledge graphs and AI applications.
Zhicheng Technology built an industrial data-asset and agent-development platform with Huawei Cloud so manufacturers can turn raw operational data into LLM-ready industrial applications. At the ingestion and availability layer, ECS and CCE provide dual-site resilience, remote disaster recovery, and rolling updates so the platform stays online while factories keep streaming data. For the graph layer, Huawei Cloud linkX handles billion-scale daily node and edge updates and millisecond queries across dense industrial relationships. On top of that, iDME contributes industrial knowledge models and data-connection capabilities, while Zhicheng’s own knowledge-compression and large-model logic transform raw plant data into consumable assets. The result is a stack where industrial source data is stored, modeled, queried, compressed, and then exposed to domain agents through Chuntie Fusion and Chuntie Cognite, replacing static dashboards with interactive AI applications for manufacturing users.
Factory data streams into ECS/CCE-backed services, where linkX stores and updates dense industrial graphs in near real time. iDME and Zhicheng's compression logic convert those graphs into structured data assets, which are then exposed through Chuntie Fusion and Chuntie Cognite for industrial-agent use.
"Huawei Cloud ECS and CCE give the service dual-site active-active resilience, remote disaster recovery, and no-downtime updates. (original: 志丞科技利用华为云的强大的服务基础设施，让产品拥有优秀的可靠性保障。保证双城双活，异地容灾，应用不停机更新。)"
"With iDME, Zhicheng can build private factory knowledge graphs and industrial data assets at one click; customer engineering R&D efficiency improved tenfold, line-management cost fell 25%, and decision efficiency rose 50%. (original: 通过与iDME合作，可实现一键完成数十万级工厂私域数据图谱与工业数据资产搭建。目前已服务2家大型工业企业，帮助客户在工程研发效率提升数10倍，产线管理成本下降25%，数据决策效率提升50%。)"
"Zhicheng provides an industrial digital engine that pairs manufacturing raw data with large models to build high-availability data assets and then produce manufacturing agents for business terminals. (original: 志丞科技提供面向工业制造业的数智引擎，以制造业原始数据搭配大模型构建高可用数据资产，继而通过大模型进行适合业务终端使用的制造业Agent应用生产。)"
"linkX supports hundred-million-scale daily node and edge updates with millisecond query needs, producing large-model-consumable content together with Zhicheng's knowledge-compression module. (original: 使用华为云linkX解决海量行业图数据的查询和更新问题，支持每天亿级别的节点、边的更新，同时达成毫秒级查询需求，配合志丞科技知识压缩模块，快速生产大模型可消费的数据内容。)"
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
Huawei Cloud Sample Archived · Dec 14, 2024 Kuakua Jingling (夸夸菁领) Kuakua Jingling needed a secure, always-on platform for AI digital employees that could handle sensitive government and enterprise workflows while supporting fast model iteration and tenant-specific knowledge. 7x24 automated execution capability DDoS protection service · ModelArts · Pangu large model Huawei Cloud Sample Archived · Jul 22, 2024 Suwen Technology Suwen Technology needed to process large volumes of multilingual market and technology data, keep its AI research platform stable, and make large-model answers fast enough for enterprise users without maintaining a… AI model deployment and execution efficiency improved by more than 15x GaussDB · Huawei Cloud GPU compute resources · OBS 
MongoDB Sample Sep 9, 2026 Squary AI Squary AI needed to eliminate slow, outage-prone legal search infrastructure that combined MongoDB with OpenSearch and hurt document review speed, cost, and trust. At Quatrini Law Group, Squary AI analyzed more than 460,000 pages and saved over 400 attorney and paralegal hours. Amazon Bedrock · Claude · MongoDB Atlas 