Baidu Patent for Point-of-Interest Recommendation System

ChangeBridge: Patent Grants - Business Methods (G06Q)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted Baidu a patent for a point-of-interest recommendation system. The patent details a method for training recommendation models by adjusting initialization parameters based on current and target returns from recommendation requests. This grant is a routine intellectual property action.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12585984B2 to BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD. for a point-of-interest recommendation system. The patent describes a method for training recommendation models by obtaining training data, determining initialization parameters, calculating current and target returns for recommendation requests, and adjusting parameters based on the difference between these returns to achieve final model parameters.

This patent grant is a routine intellectual property action and does not impose new regulatory obligations on businesses. Companies operating in the technology sector, particularly those involved in recommendation systems or AI-driven services, may find the technical details of the patented method of interest for competitive analysis or innovation. No immediate compliance actions are required by this patent grant.

Source document (simplified)

← USPTO Patent Grants

Point-of-interest recommendation

Grant US12585984B2 Kind: B2 Mar 24, 2026

Assignee

BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventors

Hao Liu, Weijia Zhang, Dejing Dou, Hui Xiong

Abstract

A training method for a point-of-interest recommendation model and a method for recommending a point of interest are provided. An implementation solution includes: obtaining training data including a plurality of point-of-interest recommendation requests; determining initialization parameters of the point-of-interest recommendation model; for a first point-of-interest recommendation request among the plurality of point-of-interest recommendation requests, determining a current return for the first point-of-interest recommendation request by utilizing the point-of-interest recommendation model, and determining, based on a second point-of-interest recommendation request initiated after the first point-of-interest recommendation request is completed, a target return for the first point-of-interest recommendation request by utilizing the point-of-interest recommendation model; and adjusting the initialization parameters of the point-of-interest recommendation model based on a difference between the current return and the target return for the first point-of-interest recommendation request, to obtain final parameters of the point-of-interest recommendation model.