Customer Service Automation
Home Credit needed to reduce contact-center operating costs, keep service levels stable during pandemic disruption, and standardize telemarketing, collections, and customer-service interactions as part of a broader digital-transformation program.
Reported impact
Home Credit maintained service continuity during pandemic disruption, fully standardized AI collections talk tracks, improved intent recognition, reduced labor cost, and strengthened the digital foundation for wider omnichannel financial-service operations.
Home Credit and Baidu AI Cloud built an Intelligent Customer Service 2.0 stack that spans telemarketing, collections, and customer-service workflows. The deployment starts with Baidu's language-understanding layer, which classifies user intent, emotion, and attitude so each call can be routed into the right conversation flow. On top of that, a task-oriented conversation engine manages entity substitution, clarification, pronoun resolution, and guided prompts to make automated dialogues feel more natural. Voice robots then handle high-volume service work, which proved critical when pandemic disruption reduced available agents. In collections, the platform enforces standardized scripts and can play different voices for different customer situations, while human agents focus on harder exceptions. The result is a shared AI service layer that improves efficiency and supports Home Credit's online-plus-offline digital-transformation strategy.
Calls from telemarketing, collections, and customer-service channels enter the intelligent customer-service layer, where language-understanding models classify intent and sentiment. The task-oriented engine then selects the right flow, fills entities and clarifications, and the voice-robot service delivers standardized responses or passes complex cases to human agents.
During the pandemic, Baidu's intelligent customer service played a major role by letting Home Credit use large numbers of voice robots to serve customers (original: 受疫情的影响，在没有部署远程呼叫中心之前，缺少大量的坐席人员去服务客户，在这个困难时期，百度智能云-智能客服发挥了巨大的作用，捷信用大量的语音机器人服务客户).
Home Credit worked with Baidu AI Cloud across telemarketing, collections, and customer service to build a new financial-service ecosystem (original: 捷信与百度智能云通力合作中，用电销、催收、客户服务等业务全流程，打造金融服务新生态).
Intent recognition accuracy reached 92%, AI script standardization reached 100%, and labor costs fell 40% (original: 意图识别准确率达92%；AI话术标准化率100%；人力成本降低40%).
The collections workflow keeps scripts completely standardized and can play suitable voices for different customers (original: 话术可以做到完全的规范。智能客服不仅对于同一问题的不同表述都能做到统一回答，还能够根据不同客户选择播放合适的声音).
The upgraded intelligent customer service can accurately identify user intent, emotion, and attitude and uses a task-oriented conversation engine for entity replacement, clarification, coreference, and dialogue guidance (original: 不仅能实现用户意图、情感和态度的精准识别，还能由任务式会话引擎驱动可实现实体替换、澄清、指代和会话引导).
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 