Electronic device for acquiring target modality on basis of at least one modality, and control method therefor
The electronic device integrates cross-modality dependency information and neural networks to efficiently process and restore biometric data, addressing computational overhead and functional limitations.
WO2026121605A1 Publication Date: 2026-06-11SAMSUNG ELECTRONICS CO LTD
5 Cites 0 Cited by
Patent Information
- Application Number
- PCT/KR2025/018316
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-12-02
- Filing Date
- 2025-11-07
- Publication Date
- 2026-06-11
AI Technical Summary
Technical Problem
Conventional electronic devices process biometric modalities independently, leading to increased computational overhead and limitations in functionality without a camera.
Method used
An electronic device configured with a processor that utilizes cross-modality dependency information and a neural network model to integrate and process multiple biometric modalities, enabling efficient modality acquisition and restoration.
Benefits of technology
Reduces computational load and enhances functionality by leveraging cross-modality dependencies to acquire and restore biometric data, even in resource-constrained devices without a camera.
✦ Generated by Eureka AI based on patent content.
Abstract
This electronic device comprises: a memory for storing cross-modality dependencies information including information related to a correlation between modalities, a neural network model and instructions; and at least one processor including processing circuitry, wherein the at least one processor individually or collectively executes the instructions so that the electronic device can: acquire a first modality of a first type from among a plurality of modality types; identify, on the basis of a context, information corresponding to the first type and a second type among the cross-modality dependencies information; and acquire a second modality of the second type by inputting, into the neural network model, the first modality and the identified information.
Need to check novelty before this filing date? Find Prior Art