Didi Global’s patent describes a unified learning approach for large-scale ride-hailing, utilizing offline and online state value networks trained on historical vehicle trajectories. The method optimizes vehicle dispatching by retraining the online network more frequently than the offline network. GlobalData’s report on Didi Global gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
According to GlobalData’s company profile on Didi Global, V2I communication was a key innovation area identified from patents. Didi Global's grant share as of April 2024 was 36%. Grant share is based on the ratio of number of grants to total number of patents.
Unified learning approach for large-scale ride-hailing
A recently granted patent (Publication Number: US11967239B2) discloses a computer-implemented method for optimizing vehicle dispatching through the use of offline and online state value networks. The method involves training an offline state value network based on historical vehicle trajectories, initializing an online state value network for dispatching vehicles, and ensembling the two networks to improve dispatching efficiency. The online state value network is retrained more frequently than the offline network, ensuring real-time adaptation to changing conditions. The method also includes training the offline network by extracting vehicle state transitions, determining vehicle state values, and updating network parameters to minimize errors.
Furthermore, the patent describes a system comprising processors and computer-readable memories configured to execute the method for optimizing vehicle dispatching. The system involves obtaining offline and online state value networks, dispatching vehicles based on the online network, and retraining the online network using data from the dispatching period. By ensembling the online and offline networks, the system aims to enhance the accuracy and effectiveness of vehicle dispatching operations. The method and system outlined in the patent offer a comprehensive approach to improving the efficiency and performance of vehicle dispatching systems through the integration of offline and online state value networks.
To know more about GlobalData’s detailed insights on Didi Global, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
