USPTO Patent Grant: Routing Decision Method and System Based on Traffic Prediction

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted patent US12587941B2 for a routing decision method and system based on traffic prediction. The patent, assigned to Nanjing University Of Posts And Telecommunications, details a system for optimizing data packet forwarding paths using predictive routing models.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12587941B2, titled "Routing decision method and system based on traffic prediction." This patent, assigned to Nanjing University Of Posts And Telecommunications, covers a method for analyzing data links and nodes to train a routing selection model. The model is then applied to determine an optimal forwarding path for data packets within a target network area, aiming to improve network efficiency and data transmission.

This patent grant signifies the formal recognition of an invention in the field of network routing and traffic prediction, likely involving AI or machine learning components. While not a regulatory rule imposing obligations on companies, it establishes intellectual property rights for the assignee. Companies operating in network infrastructure, telecommunications, or AI-driven systems should be aware of this patent, particularly if their technologies involve similar predictive routing mechanisms, to avoid potential infringement.

Source document (simplified)

← USPTO Patent Grants

Routing decision method and system based on traffic prediction

Grant US12587941B2 Kind: B2 Mar 24, 2026

Assignee

Nanjing University Of Posts And Telecommunications

Inventors

Yongan Guo, Dequan Yu, Hao She, Qijie Qian

Abstract

Disclosed are a routing decision method and system based on traffic prediction. The method is used for obtaining each data link to be analyzed between a starting point and an ending point of a direct connection or an indirect connection for forwarding data packets to be forwarded in a target network area, and each node respectively included in each data link to be analyzed; when the target network area receives the data packets to be forwarded, training and obtaining a routing selection model corresponding to said packets for each data link to be analyzed for the direct connection or the indirect connection between the starting point and the ending point in the target network area, respectively; and applying the routing selection model to obtain an optimal forwarding path corresponding to said data packets, and forwarding said data packets.