Electro-optical mapping system and method for electronic intelligent model

By combining the electronic side module and the optical computing module, the cross-domain mapping problem from the electronic intelligent model to the optical computing system is solved, enabling efficient deployment and stable operation of the optical computing system and improving its applicability and reliability.

CN121996022APending Publication Date: 2026-05-08SHANGHAI JIAOTONG UNIV
1 Cites 0 Cited by

Patent Information

Application Number
CN202610283526.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-10
Publication Date
2026-05-08

AI Technical Summary

Technical Problem

Existing technologies struggle to efficiently and reliably map electronic intelligent models to optical computing systems without large-scale retraining, leading to cross-domain mapping and physical constraint problems that limit the application of optical computing systems in complex intelligent tasks.

Method used

An electro-optical mapping system and method for electronic intelligent models are provided, including an electronic side module, a cross-domain transformation module, and an optical computing module. Optical computing parameters are generated through semantic feature encoding, cross-domain transformation, and physical constraint mapping to realize the functional reproduction of the electronic intelligent model.

Benefits of technology

This enables the optical computing system to efficiently complete the computational tasks of the electronic intelligent model without changing the structure of the electronic model, thereby improving the versatility and applicability of the optical computing system and reducing deployment and maintenance costs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an electronic intelligent model-oriented electro-optical mapping system and method, and the system comprises a semantic feature extraction module which is used for carrying out the semantic feature coding of an input image, text or multi-modal data, and outputting a semantic feature representation representing the calculation capability of an electronic intelligent model; the optical parameter generation module is used for generating optical calculation parameters for driving the optical calculation module according to the semantic feature representation under the condition of introducing a physical constraint condition of the target optical calculation module; and the optical calculation module is used for executing optical calculation based on the optical calculation parameters so as to reproduce the corresponding calculation capability of the electronic intelligent model in a function or calculation behavior level and realize mapping of the electronic intelligent model to the optical calculation system. According to the application, the efficient mapping and reliable deployment of the electronic intelligent model to the optical computing system can be realized without directly mapping the complete digital weight of the electronic model.
Need to check novelty before this filing date? Find Prior Art