Didi Global has patented a system and method to prevent driver attrition in transportation hailing services. The technology uses virtual trajectories of incentives like coupons to optimize an incentive policy through reinforcement learning. The system includes a joint policy simulator, discriminator, and incentive server to enhance driver engagement. 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

Report-cover

Premium Insights Didi Global Inc - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

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 January 2024 was 33%. Grant share is based on the ratio of number of grants to total number of patents.

Optimized incentive policy for preventing fading drivers in transportation system

Source: United States Patent and Trademark Office (USPTO). Credit: Didi Global Inc

A recently granted patent (Publication Number: US11861643B2) discloses a transportation hailing system that includes a network of client devices and transportation devices, each executing applications for engaging and offering transportation services, respectively. The system incorporates an incentive system with a joint policy simulator, discriminator, reinforcement learning system, and incentive server. The joint policy simulator generates simulated actions for drivers based on state and action data, while the reinforcement learning system provides an optimized incentive policy. The incentive server communicates selected incentives to drivers according to the optimized policy, with the joint policy model being generated through a training process involving sample data from drivers.

Furthermore, the patent details a method within the transportation hailing system to motivate drivers, involving storing state and action data for each driver, generating simulated actions using a joint policy model, determining rewards, providing an optimized incentive policy, and communicating selected incentives to drivers. The method includes generating a ranking priority of drivers based on their actions and states, with the incentive server allocating incentives based on this ranking and an incentive budget over a specified period. The system allows for equal allocation or favoring of certain periods within the budget, with the selected incentives potentially being coupons for drivers to redeem after a set number of services. The reinforcement learning aspect operates through a policy gradient method, and historical trajectories are selected based on drivers classified as fading drivers.

To know more about GlobalData’s detailed insights on Didi Global, buy the report here.

Premium 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

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.