How Amap’s Big Data Powers Smart City Traffic – Insights from CCF‑GAIR 2019

Background

After years of building smart traffic, city brain, and smart city platforms, many data silos have begun to interconnect, yet two major challenges remain: unlocking the value of accumulated big data for urban services, and supporting intelligent decision‑making for city managers.

Amap’s Big Data Capabilities

Amap operates China’s largest person‑place relationship data platform. In October 2018 its daily active users (DAU) surpassed 100 million, making it the first travel app to reach that milestone, and its monthly active users now exceed 400 million.

The platform provides real‑time traffic data for all prefecture‑level cities (except a few remote regions) with road‑level accuracy above 90 %. It also supplies location services to over 300 000 third‑party apps such as e‑commerce and news platforms.

Enabling Digital City Construction

Smart Traffic : By integrating traffic data, Amap offers a “city brain” that coordinates traffic signals, predicts congestion, and suggests police‑recommended detour routes. During the 2019 Spring Festival travel rush, collaboration with more than 40 traffic management bureaus reduced vehicle flow on congested segments by 23 %, increased average speed by 31 %, cut travel time by 56.9 %, and generated nearly 20 million route plans for over 7.75 million users.

Emergency Vehicle Assistance : The “One‑Road Escort” service informs ambulances of the fastest routes to hospitals and signals traffic lights to give them priority. In a documented case in Hangzhou, an ambulance reached a hospital in 8 minutes—almost twice as fast as the usual time.

Smart Highway : Leveraging video feeds and AI, Amap detects incidents and congestion on highways in real time, automatically updating ETA estimates and routing suggestions. Predictive analytics also identify high‑risk road segments; for example, a “three‑urgency” metric (sudden acceleration, deceleration, lane change) flags sections with a three‑fold higher fatality rate.

Beyond traffic, Amap’s data supports tourism management by forecasting visitor volumes at scenic spots, providing real‑time queue lengths for attractions, and offering dynamic parking information.

Conclusion

Amap’s extensive location‑based data and AI‑driven services form a comprehensive data foundation that powers smart traffic, emergency response, highway safety, and tourism planning, ultimately making urban life safer and more efficient.