Customer Service Automation
China Life P&C needed a scalable way to collect, analyze, and act on large volumes of customer NPS survey data across policy, claims, and value-added service touchpoints, especially the unstructured feedback that traditional analysis tools could not process in real time.
Reported impact
China Life P&C created an AI-driven customer-experience management loop that detects dissatisfied customers quickly, improves follow-up precision, and gives management direct visibility into customer sentiment and service hotspots.
China Life P&C upgraded its NPS platform with Baidu AI Cloud by combining PaddlePaddle models, the BML full-featured AI development platform, and Sugar BI. Customer surveys are triggered in real time through WeChat or SMS at insurance touchpoints such as underwriting, claims, and value-added services, producing both structured scores and unstructured text feedback. PaddlePaddle-based sentiment models, tuned for the insurer's scenarios, quantify customer emotion, identify hotspots in the customer journey, and detect dissatisfaction or complaint signals. BML then serves as the one-stop cognitive-computing platform used to deploy the models and publish real-time services for sentiment scoring and keyword analysis.
NPS questionnaires are pushed through WeChat or SMS at customer touchpoints, and the resulting structured scores plus free-text comments flow into the unified NPS system. PaddlePaddle sentiment models classify emotion and issues, BML exposes those results as real-time services, and dashboards plus work orders route low-score cases to business staff for immediate follow-up.
China Life P&C upgraded its NPS system with AI from strategy to operations, making customer feedback more intelligent and visualized (original: 国寿财险携手百度智能云升级打造了NPS系统…实现了智能化、可视化的客户反馈).
PaddlePaddle capabilities in natural-language recognition and customer-sentiment modeling let the insurer locate customer-experience hotspots, quantify customer emotion, trigger follow-up on negative sentiment, and capture positive feedback (original: 借助国产深度学习框架百度飞桨…国寿财险可以快速从所有客户触点反馈的结构化与非结构化数据中定位客户体验热点问题、量化计算客户情感、自动触发负面情绪客户的跟进服务).
The insurer tuned a sentiment-recognition model on PaddlePaddle and achieved more than 95% accuracy (original: 基于百度飞桨…开发了NPS客户主观反馈情感识别模型，情感识别模型的准确率超过95％).
The low-score handling process runs as a closed loop from questionnaire push to big-data recognition, work-order creation, business follow-up, and continuous model optimization (original: 构建了低分预警处理流程…形成了完整的敏捷化的客户体验管理闭环).
Using BML, China Life P&C deployed real-time services for sentiment quantification and keyword calculation to capture dissatisfaction and complaints quickly (original: 国寿财险还基于百度智能云BML建模工具，打造了一站式的认知计算平台…发布了NPS客户主观反馈情感量化实时计算服务和NPS客户主观反馈关键词实时计算服务).
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 Jun 30, 2025 Industrial Bank Co., Ltd. (兴业银行股份有限公司) Industrial Bank wanted its digital-service channels to deliver better customer experience, broader self-service coverage, and more precise operations as customers moved online, but legacy service models could not scale… Average daily handled volume reached nearly 100,000 calls. Baidu AI Cloud Intelligent Customer Service · Intelligent Speech · Smart Outbound Calling Baidu AI Cloud Sample Jun 27, 2025 CITIC Financial Holdings CITIC Financial Holdings needed to make its wealth-management platform more intelligent and scenario-driven so customer-service and wealth-adviser interactions could scale across a very large client base. End-to-end question-answering accuracy exceeded 85%. Baidu AI Cloud Keyue · Knowledge Expansion Scheme · Knowledge Flywheel Baidu AI Cloud Sample May 16, 2025 Shanghai Pudong Development Bank Shanghai Pudong Development Bank needed a scalable, contactless way to deliver personalized wealth-management guidance and everyday banking service to a very large retail customer base without forcing customers to wait… If Xiaopu serves 10,000 customers per day for 20 minutes each, it saves 3,333 labor hours per day. AI Middle Platform Solution · High-Precision User Profiling · Knowledge Middle Platform 