How China Mobile’s Centralized AIOps Platform Achieved Top‑Tier Evaluation

Intelligent Operations (AIOps) applies AI technologies such as machine learning and data science to IT operations, extracting and analyzing massive, fast‑growing data to support operational management. Gartner describes AIOps as a loosely coupled, scalable approach that is becoming the future trend of DevOps on the operations side.

On December 26, 2022, the China Academy of Information and Communications Technology announced the latest batch of AIOps standards assessment results, awarding China Mobile Information’s “China Mobile Centralized AIOps” project an Excellent‑level rating for the three modules of Alarm Convergence, Fault Self‑Healing, and Root‑Cause Analysis under the "Cloud Computing Intelligent Operations (AIOps) Capability Maturity Model – Part 2: System and Tool Technical Requirements" standard.

The project aims to build a comprehensive intelligent operation capability platform that covers all managed objects, links multiple AIOps scenarios, and creates a full‑cycle fault governance system (prevention, assisted repair, and post‑mortem). It has been deployed across 11 provinces, ensuring stable operation of mobile services and serving as an open‑source tool for other IT systems.

Q: Please introduce yourself and the project you evaluated.

Chen Lihua, senior expert at China Mobile Information Technology Center, explained that the center’s vision is to become a key engine for digital transformation and high‑quality development, focusing on smart operation systems, middle‑platform empowerment, technology innovation, and IT governance. The centralized AIOps platform targets world‑class capabilities, achieving full coverage of managed objects, multi‑scenario linkage, and a global intelligent fault governance system.

Q: How do you feel about passing the AIOps standard assessment?

He noted that AIOps is the future of operations, representing a human‑machine collaborative model in the digital age. The platform achieved Excellent‑level ratings for alarm convergence, root‑cause analysis (first among carriers), and fault self‑healing (industry first), confirming two years of construction, operation, and optimization.

Q: What considerations led your company to participate in the assessment?

China Mobile Information built a big‑data operation foundation covering hosts, networks, databases, and applications, then applied machine‑learning algorithms and expert knowledge to create detection, alarm, diagnosis, and self‑healing capabilities, all of which received Excellent‑level evaluations.

Abnormal detection module builds dynamic threshold monitoring to address traditional monitoring’s slow response to failures.

Alarm convergence module uses text algorithms to solve alarm storms.

Root‑cause localization module leverages call‑chain data to identify abnormal nodes and rank root causes.

Fault self‑healing module constructs an automated toolchain enabling one‑click fault repair.

Q: What changes has the assessment brought to your enterprise and team?

The assessment provided comprehensive feedback on system capabilities, offering guidance for future development, and fostered team growth through cross‑disciplinary collaboration among operation, big‑data, and algorithm experts.

Q: What are your next steps for AIOps work?

The three‑fold plan includes: (1) extending operational contributions to business view, using intelligent algorithms to trace fault propagation and visualize global status; (2) creating a closed‑loop operation knowledge graph covering detection to self‑healing and building an anomaly case museum; (3) promoting AIOps to other IT systems to improve overall service quality and efficiency.

Q: What is your view on the future development of AIOps?

He believes AIOps is the direction of operations, aligning with the era’s needs and empowering operators with AI‑driven diagnostic decisions, supporting the challenges of big data and cloud‑native environments.

Intelligent Operations (AIOps) Capability Maturity Model, jointly developed by the China Academy of Information and Communications Technology, the Cloud Computing Open Source Industry Alliance, the Efficient Operations Community, dbaplus, BATJ, and leading internet and telecom enterprises, has become the first domestic and international standard for intelligent operations, with eight modules now open for assessment: abnormal detection, fault prediction, alarm convergence, root‑cause analysis, fault self‑healing, fault prevention, capacity prediction, and knowledge‑base construction.