BestHub
Sign in
Tagged articles
7 articles
Page 1 of 1
Baidu Geek Talk
Baidu Geek Talk
Sep 17, 2025 · Artificial Intelligence

How Baidu Maps Achieves Ultra‑Accurate ETA with AI and Traffic Big Models

This article explains how Baidu Maps' ETA system evolved from simple static calculations to AI‑driven predictive models, detailing the four development stages, the underlying pre‑trained traffic large model, end‑to‑end route prediction techniques, and real‑world applications such as commuting, airport transfers, event management, and holiday travel.

AIETAMap Navigation
0 likes · 8 min read
How Baidu Maps Achieves Ultra‑Accurate ETA with AI and Traffic Big Models
Baidu Maps Tech Team
Baidu Maps Tech Team
Jun 30, 2025 · Artificial Intelligence

How Baidu Maps Uses AI to Deliver Ultra‑Accurate ETA Predictions

This article explains how Baidu Maps' ETA system evolved from simple static calculations to AI-driven predictive models, detailing the four development stages, the underlying pre‑trained traffic large model, end‑to‑end route time prediction, and real‑world applications such as commuting, airport transfers, and holiday travel.

AIETATraffic Prediction
0 likes · 8 min read
How Baidu Maps Uses AI to Deliver Ultra‑Accurate ETA Predictions
Amap Tech
Amap Tech
Jun 9, 2020 · Artificial Intelligence

Deep Learning Approach for Route ETA Prediction in Navigation

The article proposes a deep‑learning framework that uses an LSTM to predict segment‑level travel times and fully‑connected layers to aggregate them into a full‑route ETA, demonstrating on Beijing data a 28.2% MSE reduction and superior accuracy over traditional regressors by capturing temporal and network dependencies.

ETALSTMPrediction
0 likes · 7 min read
Deep Learning Approach for Route ETA Prediction in Navigation
Meituan Technology Team
Meituan Technology Team
Feb 21, 2019 · Artificial Intelligence

Deep Learning-Based ETA Estimation in Meituan's Delivery System

Meituan’s delivery ETA system progressed from linear regression to DeepFM, enriching user, rider, merchant, and spatiotemporal features, employing an asymmetric loss and business‑rule integration to favor early arrivals, adding a tail‑adjustment term, and is engineered with Spark‑assembled TFRecords, multi‑GPU TensorFlow training, and remote‑served TensorFlow Java inference achieving sub‑5 ms TP99 latency.

ETALong TailTensorFlow Serving
0 likes · 15 min read
Deep Learning-Based ETA Estimation in Meituan's Delivery System
Didi Tech
Didi Tech
Jun 16, 2018 · Artificial Intelligence

AI and Big Data in Didi’s Mapping Services – Insights from WGDC 2018

At WGDC 2018, Didi’s mapping division revealed how its AI‑driven platform leverages massive real‑time travel data, machine‑learning and deep‑learning models—including a new ETA estimator, demand‑supply forecasting, and reinforcement‑learning order allocation—to deliver ultra‑accurate pick‑up points, route planning, and destination predictions, while opening de‑identified data and research topics to academia.

AIBig DataETA
0 likes · 6 min read
AI and Big Data in Didi’s Mapping Services – Insights from WGDC 2018
Meituan Technology Team
Meituan Technology Team
Nov 23, 2017 · Artificial Intelligence

Improving Food Delivery ETA Prediction with GBDT Feature Construction

By training Gradient Boosted Decision Trees on offline delivery data, extracting leaf‑node indices as one‑hot features, and merging them with merchant, traffic, and weather information, the study reduces overall ETA MAE by 3.4%, raises N‑minute accuracy by 2.2 points, and achieves larger gains for high‑value orders, demonstrating that GBDT‑derived features markedly improve food‑delivery time predictions.

ETAGBDTfood delivery
0 likes · 13 min read
Improving Food Delivery ETA Prediction with GBDT Feature Construction