0 views collected around this technical thread.
Douyin has introduced a ride‑hailing feature that aggregates third‑party services like Gaode Taxi, offering a limited set of functions while highlighting the strategic shift toward an aggregation model and its potential impact on the competitive landscape of Chinese ride‑hailing platforms.
This article introduces the open‑source Python library TRACC, explains how to install it, prepare destination and travel‑cost data, and walk through a step‑by‑step workflow—including code snippets—to compute potential, passive, and minimum travel‑cost accessibility metrics for urban areas.
This article introduces the open‑source Python library TRACC, explains its accessibility metrics, shows how to install it, prepare destination and travel‑cost data, and provides step‑by‑step code examples for calculating potential, passive, and minimum‑travel‑cost accessibility in a city such as Boston.
This article presents the challenges of travel‑related product search, explains why traditional rule‑based sorting is insufficient, and describes how Alibaba Flypig’s team built a deep‑learning based personalized ranking system—including architecture, model variants, experimental results, and future optimization directions—to improve conversion rates for flight and ticket searches.
The Hybrid Spatio‑Temporal Graph Convolutional Network (H‑STGCN) integrates planned traffic flow from navigation data via a domain transformer and a compound adjacency matrix, enabling graph‑based spatio‑temporal modeling that consistently outperforms baselines in real‑world traffic forecasting and reduces severe ETA errors.
At the IJCAI conference, Didi’s CTO unveiled the company’s AI‑powered “Smart Brain,” which embeds deep‑learning‑driven features—from optimal dispatch and 2% driver‑earnings gains to 11% ETA error reduction and multi‑option route selection—while emphasizing human‑centric design, open services for partners, and large‑scale safety‑risk analytics.
The Didi Computer Vision in Transportation workshop teaches fundamentals, advanced domain‑adaptation and lightweight model techniques, and real‑world applications such as driver identification and driving‑scenario analysis, delivered by Didi AI Labs experts, emphasizing practical use cases and cutting‑edge research.
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.
The article describes how the Super Bus platform leverages unsupervised DBSCAN clustering and a Graham‑scan convex‑hull algorithm, combined with a data‑center and distributed processing framework, to automatically generate compliant service zones that match user demand while improving efficiency and scalability.
The article details how the Transportation Division’s data warehouse grew from a simple SQL‑based solution to a multi‑layer, big‑data platform handling petabyte‑scale data with daily 10 TB increments, describing the technical and business architecture, ETL strategies, and future roadmap.