Customer Service Automation · Enterprise Knowledge Search
Xi'an traffic police needed a scalable way to handle rising traffic-service inquiries, relieve hotline pressure, remove information silos between frontline officers and functional departments, and standardize both public answers and internal business guidance.
Reported impact
Xi'an traffic police created a round-the-clock traffic-service assistant that improved answer accuracy, reduced hotline strain, standardized service responses, and gave internal staff a more efficient way to access governed policy and process knowledge.
Xi'an Public Security Bureau Traffic Management Department built the large-model assistant 'Yong'anjun' with Baidu AI Cloud using Qianfan AppBuilder and Qianfan ModelBuilder. The system centers on a modular knowledge-base design: one layer supports standardized external answers for vehicle administration, traffic restrictions, and traffic violations, while another organizes internal regulations, business rules, and file lookup for officers. Qianfan ModelBuilder provides the large-model reasoning used to interpret questions and return high-accuracy responses, and Qianfan AppBuilder organizes the online service flows delivered through the agency's WeChat public account. The deployment gives citizens a 24/7 consultation channel and turns the knowledge base into a shared service backbone that reduces 122 hotline load, unifies response language across departments, and assists internal traffic-law enforcement and operations.
Citizen and officer questions enter Yong'anjun through the WeChat public account and related service channels. Qianfan-backed workflows retrieve governed content from modular external and internal knowledge bases, generate answers for traffic services or law-enforcement guidance, and return the result to users while reducing hotline and manual consultation load.
Before the project, the agency faced three major challenges: a single consultation channel with heavy hotline pressure, information barriers between frontline and functional departments, and inconsistent answer wording for external services (original: 主要面临以下三大挑战：一是服务群众交通业务咨询手段单一，电话热线压力大。二是一线与职能处室存在信息壁垒，对外服务效率低下。三是对外服务解答口径不一致).
The service reached 96% accuracy, runs 24 hours a day, and handles more than 1,000 consultations per day (original: 实现96%准确率的24小时在线业务咨询，日均服务超1000次).
The solution uses modular knowledge-base construction and management to create both a standardized external service Q&A base and an internal rules-and-process knowledge base (original: 通过模块化知识库的搭建和管理，打造西安支队对外服务标准问答知识库和对内统一业务规章规范知识库).
Xi'an traffic police and Baidu AI Cloud launched 'Yong'anjun,' the first intelligent traffic-service system in Shaanxi traffic management to use large-model technology (original: 西安公安交警联合百度智能云推出全国首个交管大模型智能助手“永安君”).
Yong'anjun officially launched at the end of January 2025 and became a milestone in smart travel services for Xi'an traffic police (original: “永安君”于2025年1月底正式上线…成为西安公安交警在智能化出行服务方面新的里程碑).
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 Sep 24, 2025 All-China Federation of Trade Unions The All-China Federation of Trade Unions needed a unified AI foundation that could support legal aid, rights protection, and other worker services at national scale instead of leaving union service digitization… Delivery cycle fell from 3-6 months to under 1 month. Qianfan AppBuilder · Qianfan ModelBuilder · Union Industry Model 
Google Cloud Sample Archived · Oct 2, 2026 Hawaii DCCA The Hawaii Department of Commerce and Consumer Affairs (DCCA) serves a vital mission: protecting residents while ensuring a level playing field that promotes fair business competition across the state. Reclaiming Time: Streamlined operations and reduced manual work across 52 state boards and commissions by… Cloud Storage · Contact Center AI Platform · Customer Experience Agent Studio Baidu AI Cloud Sample Dec 29, 2025 Hualvwang Hualvwang needed a way to help ordinary users describe legal issues more precisely, retrieve relevant legal knowledge faster and scale personalized legal-service triage across a very large user base. Daily ERNIE invocation peaks exceeded 10 million. Qianfan AppBuilder · Qianfan ModelBuilder · Recommended Questions 