Customer Service Automation
China Telecom needed a differentiated anti-harassment service that could protect subscribers from nuisance calls, preserve privacy and service quality expectations, and scale across a nationwide telecom operation without relying on manual call handling.
Reported impact
China Telecom expanded an AI-powered call-protection service across multiple provinces, improved harassment-call interception accuracy, and gave subscribers a less disruptive way to manage unwanted calls and missed-call follow-up.
China Telecom worked with Baidu AI Cloud to build an AI anti-harassment assistant on top of Baidu AI Cloud Intelligent Customer Service. The service intercepts suspicious promotional or nuisance calls, answers them on the user's behalf, identifies the caller's purpose through speech recognition and intent analysis, and compiles a summary for later delivery to the subscriber. The same platform also upgrades missed-call reminders by handling unanswered calls, determining caller intent, and sending structured follow-up information back to the user. Architecturally, the customer-service stack provides the serving layer, speech recognition converts live audio into text, and intent analysis classifies call purpose so the system can decide what to report. Delivery is integrated with official-account and SMS channels, giving customers a less disruptive way to decide whether to call back or ignore the request.
Incoming suspicious calls are routed into the AI assistant, where speech recognition transcribes the conversation and intent analysis determines why the caller is calling. The platform then generates a summary and delivers it to subscribers through official-account or SMS notifications so they can choose whether to call back or ignore the request.
China Telecom and Baidu AI Cloud built an AI anti-harassment intelligent customer service assistant that uses speech recognition and intent analysis to answer and intercept nuisance calls automatically (original: 中国电信联合百度智能云打造AI防骚扰智能客服，通过语音识别与意图分析技术实现骚扰电话自动应答拦截).
The missed-call reminder service was also upgraded so the assistant can answer when the user's phone cannot connect, determine caller intent, and send the result to the user (original: 对『未接通来电提醒』进行服务升级，当用户电话无法接通时，智能客服助手自动接听，智能应答，了解来电方的意图，并发送给用户).
The service covers 8 provinces and 1.5 million users, and the harassment interception rate rose to 98% (original: 覆盖8省150万用户，骚扰拦截率提升至98%).
The summaries are regularly delivered to users through official-account or SMS messages so they can decide whether to call back or ignore the contact (original: 定期通过公众号/短信的方式将汇总信息发送给用户知晓，进而进行回拨或者忽略).
When a number is identified as a promotional or nuisance caller, the assistant answers on the user's behalf, understands the sales content, and summarizes it for later delivery (original: 当判断来电号码为推销/骚扰电话时，代替用户接听电话，了解推销内容概要并汇总).
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 China Mobile Online (中移在线) China Mobile Online needed faster and deeper customer-intent insight than manual sampling and call listening could provide so it could support precision marketing, real-time service intervention, and low-threshold model… Clustering analysis timeliness is reduced to less than 1 hour from about 3 hours. Customer-Agent-Business Profiling Engine · Real-time Intelligent Insight Platform · Real-time Knowledge Push Engine Baidu AI Cloud Sample May 15, 2025 China Unicom (中国联通) China Unicom needed to cut the cost of serving customers across hotline and online channels, break down siloed service systems, and modernize aging provincial deployments without compromising support quality for a very… China Unicom's user base exceeded 400 million as of November 2018. AI Operations Platform · Enterprise Knowledge Graph · Keyue Intelligent Customer Service Enterprise Edition 
Cognizant Sample Archived · Oct 9, 2026 Cox Communications Cox Communications needed to modernize a high-volume chatbot and IVR estate so customers could get accurate, relevant answers across preferred channels without overloading live support teams. 17% improvement in first-contact resolution for chatbot Gemini Enterprise for Customer Experience (CX) · Google Cloud Contact Center as a Service (CCaaS) · Google Dialogflow CX 