eService

AI Drives IT Management Transformation

Building intelligent management system in Huawei cloud, offering rich services based on Huawei's 30-year digital management technologies, providing one-stop with fully-connected management, making IT O&M more intelligent.

Why eService?

With massive O&M data from the complete series of IT devices and analytics technologies of EI intelligent platform, Huawei collaborates with global partners and has accumulated rich O&M experience. Using machine learning technology makes the eService intelligent O&M brain smarter. eService aims to be your most trustable partner, and facilitates your IT O&M management with low cost and high reliability, thus achieving greater business success.

Advantages

Proactive Prediction

Risky disk prediction: Predicts risky disks, finds and resolves the source of the issue, and improves reliability of the storage system.
Health score: Evaluates the device health status and scores devices accordingly.
Capacity and performance predictions: Identifies overloaded and idle resources, and provides multiple capacity planning solutions; offers real-time insights into anomalies and predicts performance bottlenecks to resolve performance problems.

Rapid Response

Monitors all IT device 24/7, reports device faults, and creates service requests automatically.
Automatically analyzes problems and provides solutions, based on the global fault mode library.
Presents the troubleshooting process in a visualized manner.

Automatic Reporting

Predicts the capacity trend and generates a capacity evaluation report in terms of the optimal performance or cost effectiveness.
Automatically generates monthly O&M reports and periodically pushes reports after subscription.
Identifies service fluctuation rules and determines the time window for service changes, assisting users with proper service planning.

Scenarios

Health Evaluation

Capacity Planning

Performance Insight

Risky Disk Identification

Supports real-time evaluation, in-depth analysis, and proactive prevention of device faults.

Monitors devices 24/7 and analyzes the health status of devices and services in terms of system, hardware, configuration, capacity, and performance.
Based on expert experience, builds a device health score system and gives a health score to clearly show the device health status.
Automatically generates monthly O&M reports and periodically pushes reports after subscription.

Monitors how capacity is being used, predicts the capacity trend, and provides the capacity expansion solution.

Predicts the capacity trend in the next year and provides the optimal capacity expansion solution for lower cost and better performance.
Identifies overloaded resources and supports capacity warning to improve reliability.
Identifies idle resources and provides optimal reclaiming suggestions to improve resource utilization.

Analyzes performance bottlenecks, monitors performance fluctuation, and detects performance anomalies.

The training model based on tens of billions of feature data records from all series of IT devices makes the prediction results of the performance insight system more accurate.
Detects performance anomalies in real time and resolves performance risks in the subhealth period. Predicts future service trends and identifies performance bottlenecks.
Identifies service fluctuation rules, recommends the time window for service changes, and assists users with proper service planning.

Predicts risky disks based on AI and gets to the root of the problem.

Collects information about millions of disks, analyzes tens of billions of feature data records based on expert experience, and extracts multiple reasoning models through machine learning.
Through continuous online training + prediction + verification, adapts to new scenarios constantly and sets up a mature and stable model.
Identifies risky disks 14 days in advance so that disk faults are not reactively rectified but proactively prevented, improving reliability.

Security

The information security condition complies with the ISO/IEC 27001:2013 standard, and obtains the ISO 27001 Information Security Management System Certification.
No service data of devices is collected and only the O&M information is obtained. Data transmission records can be traced. The detailed information items to be collected are listed in the Letter of Authorization on the Deployment of Huawei OceanStor eService and Processing of [Customer]'s Data.
Multiple data encryption technologies and patented technologies ensure data security and reliability.

AI推动IT管理变革

华为云端智能运维平台，以服务形式分享华为30年沉淀的数字化管理技术，一站式全联接，让IT运维更智能

为何使用 eService？

华为拥有全系列IT设备的海量运维数据和云EI智能平台的分析技术，携手全球合作伙伴，积累了丰富的运维经验。利用机器学习技术，让智能运维大脑越来越聪明。eService力争成为您最值得信赖的合作伙伴，助您简化IT运维管理，低成本/高可靠，从而取得更大的商业成功。

产品优势

主动预测

风险盘预测：提前预测风险盘，切断问题源头，提高存储系统可靠性。
容量/性能预测，识别过载/空闲资源，多策略的容量规划方案；实时异常检查，预测未来性能瓶颈，告别性能问题。
通过健康评分，综合评估设备健康状态。

快速响应

7*24小时监控， IT设备全覆盖，设备故障自动上报并建单。
通过全球故障模式库，自动分析，给出问题解决方法。
问题处理过程可视化呈现。

自动报告

提前预测容量趋势，分别基于性能最优/成本最优维度，自动生成容量评估报告。
智能识别业务潮汐规律，确定业务变更的时间窗口，提供方案，指导用户合理规划业务。
自动生成月度运维报告，订阅后，定期推送。

场景介绍

健康评估

容量规划

性能洞察

风险盘识别

实时评估、深度分析、主动预防设备故障

7*24小时监控设备，从系统、硬件、配置、容量、性能五个维度，分析设备和业务的健康状况，构建云端深度巡检能力。
结合专家经验，构建设备健康度评分体系，综合打分，设备健康状态一目了然。
云端自动生成月度运维报告，订阅后，定期推送。

容量监控，精准识别过载或闲置资源；提前预测容量趋势，提供最优扩容方案。

预测未来一年的容量趋势，从成本和性能角度给出最优扩容方案。
识别过载资源，提前进行容量预警，提升可靠性。
识别闲置资源，提供最优回收建议，提高资源利用率。

性能瓶颈智能分析，性能潮汐识别，确保设备性能平稳；性能异常实时检测，告别性能问题。

全系列IT设备、百亿级特征数据训练模型，使性能洞察智能分析系统，预测结果更为精准。
实时检测性能异常，在亚健康期解决性能风险。预测未来业务趋势，识别性能瓶颈。
智能识别业务潮汐规律，推荐最佳业务变更时间窗口，指导用户合理规划业务。

基于AI推理，提前预测风险硬盘，切断问题源头

收集百万块硬盘信息，结合专家经验分析百亿级可靠性特征数据，通过机器学习提取多种推理模型。
持续在线训练+预测+验证，不断适应新场景，构建成熟稳定的模型。
提前14天识别风险盘，让硬盘故障从被动处理转化为主动预防，提升可靠性。

产品安全

通过ISO/IEC 27001:2013标准，并获得《信息安全管理体系认证证书ISO27001 》，以及国家电子计算机质量监督检验中心认证，并出具《安全认证书》。
不碰设备的业务数据，只获取相关运维信息，数据记录可追溯，详细收集的信息条目均列在《授权协议书》中。
多种数据加密技术和专利技术，确保数据安全可靠。