Grab has been granted a patent for a method that utilizes historical transport trip data and a trained neural network to generate synthetic transport trips. This process aids in developing a control scheme for managing transport systems effectively. GlobalData’s report on Grab gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Grab, was a key innovation area identified from patents. Grab's grant share as of June 2024 was 10%. Grant share is based on the ratio of number of grants to total number of patents.
Method for controlling transport systems using synthetic trip data
The patent US12039469B2 outlines a method for controlling a transport system through the use of neural networks and synthetic data generation. The process begins with the determination of an input dataset that consists of historical transport trip data. A neural network is then trained to create an invertible mapping of these trips to latent representations, ensuring that the distribution of these representations meets a predetermined fitting criterion based on a specified latent representation base distribution. Following this, a set of latent representations is sampled from the base distribution, and each sampled representation is mapped back to a transport trip using the trained neural network. This results in the generation of synthetic transport trips, which are subsequently used to determine a control scheme for the transport system.
Further claims detail the specifics of the neural network's configuration, including the use of a trainable function for mapping and its inverse. The training process involves maximizing the likelihood of the latent representations and adjusting the neural network's weights, typically through gradient descent. The base distribution can be a multidimensional Gaussian or uniform distribution, and the method allows for the incorporation of parameters that specify trip characteristics. The control scheme can be developed by training a control policy or evaluating existing schemes using the synthetic trips. The transport system's control may involve managing vehicle movements within a geographic region, thereby optimizing service delivery based on the generated data. Additionally, the patent encompasses a server computer and a non-transitory computer-readable medium designed to execute the described method.
To know more about GlobalData’s detailed insights on Grab, 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.
