Customer Service Automation · Predictive Maintenance
State Grid Shandong needed to make AI practical across customer service, line safety and internal document work in an enormous utility environment where traditional business processes were slow and heavily manual.
Reported impact
Shandong moved AI from isolated demos into live utility scenarios, cutting wait times, improving line-inspection accuracy and adding automation to internal operations.
State Grid Shandong used Baidu AI Cloud to build an AI middle platform that could serve both infrastructure operations and customer-facing energy services. In the service hall, the platform supports self-service kiosks and facial-recognition-based identity verification so users can handle common electricity tasks without waiting in line. In grid operations, the same AI foundation powers a transmission-channel visualization platform that recognizes construction vehicles, smoke, fire and foreign objects in complex outdoor scenes, turning camera feeds into safety alerts. In office operations, the utility also added intelligent writing capabilities that extract local热点 information, recommend writing materials and help polish content for internal communications. Technically, the platform combines Baidu's AI models with a packaged training and deployment environment so multiple power-utility scenarios can share the same governance and runtime base. That made AI useful across both the customer journey and the production side of the electric grid.
Kiosk sessions, face-recognition checks, camera feeds and office-document requests all flow through the AI middle platform, which serves recognition outputs, safety alerts and writing assistance back into Shandong's customer and operations workflows.
Customers can use the intelligent service kiosk to complete 22 common electricity services, reducing average time by 70% (original: “智能业务办理一体机”……更名、过户等22项常见用电业务，用户平均花费时间节省70%).
The AI middle platform also provides intelligent writing support for internal documents and information releases (original: 百度“AI中台”提供了智能写作能力，建立人工智能辅助写作组件).
The transmission-channel visualization platform improved construction-vehicle recognition from 80% to 95%, smoke from 70% to 90% and wire-foreign-object recognition from 60% to 80% (original: 各类施工车辆识别准确率由原来的80%提升到95%，烟火识别准确率由70%提升到了90%，导线异物识别准确率由60%提升到了80%).
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 Jan 8, 2026 State Grid Corporation of China State Grid's 95598 service center faced heavy call volumes, limited channels, and rising pressure during demand peaks and outages, making it difficult to maintain service quality and scale customer support efficiently… Average daily interaction volume is 25 million messages. AI Base Platform · AI Operations Platform · Baidu AI Cloud Intelligent Customer Service Baidu AI Cloud Sample Jun 27, 2025 China Southern Power Grid Guangdong Customer Service Center (广东电网客服中心) Guangdong's power-customer service operation needed a more intelligent service backbone for its 24x7 hotline and digital channels so it could improve intent understanding, reduce handling time, and give agents better… Agent handling efficiency improves 5x. Intelligent Customer Service · Intelligent IVR · Power Customer Service Large Model Baidu AI Cloud Sample May 16, 2025 Guangdong Power Grid Guangdong Power Grid needed to modernize customer-service operations with better intent understanding and a self-improving knowledge base because legacy customer-center knowledge was outdated, hard to search, and unable… Intent Recognition · Knowledge Graph · Multi-turn Dialogue 