Method for Determining Node of Decision Tree Using Multi-Modal Feature Fusion

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected April 1st, 2026

Summary

USPTO granted Dell Products L.P. Patent US12592071B2 covering a method for determining nodes in decision trees using multi-modal feature fusion. The patent (20 claims) enables AI systems to combine features from different input modalities to determine more accurate user intentions along decision tree paths.

View original document View source feed page

What changed

USPTO issued Patent US12592071B2 to Dell Products L.P. on March 31, 2026. The patent covers methods for determining target nodes in decision trees by combining multiple features from different modalities corresponding to input information, generating multi-modal feature representations, and determining associated target paths and nodes indicating questions or answers. The technology enables richer and more accurate user intention determination through feature fusion.

This is a routine patent grant announcement with no compliance obligations or regulatory requirements. No action is required from manufacturers or technology companies. Patent grants do not create new regulatory obligations but establish intellectual property rights that may affect competitive R&D strategies.

Source document (simplified)

← USPTO Patent Grants

Method, device, and computer program product for determining node of decision tree

Grant US12592071B2 Kind: B2 Mar 31, 2026

Assignee

Dell Products L.P.

Inventors

Zijia Wang, Zhisong Liu, Jiacheng Ni, Zhen Jia

Abstract

Embodiments of the present disclosure relate to a method, a device, and a computer program product for determining a node of a decision tree. The method includes determining multiple features of multiple modals corresponding to input information. The method further includes generating a multi-modal feature representation by combining the multiple features of the multiple modals. The method further includes determining a target path in a decision tree that is associated with the multi-modal feature representation, the decision tree comprising multiple nodes. The method further includes determining, in the target path based on the multi-modal feature representation, a target node associated with the input information and used to indicate a question or an answer. This method enables the fusion of feature representations corresponding to input information of different modals to determine a multi-modal feature representation. In this way, it is possible to determine richer and more accurate user intentions.