A power graph paper processing method and device, electronic equipment and storage medium

CN122157298APending Publication Date: 2026-06-05NEUSOFT CORP

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner: NEUSOFT CORP
Filing Date: 2026-03-04
Publication Date: 2026-06-05

AI Technical Summary

Technical Problem

In existing technologies, the text detection accuracy of power drawings is insufficient, and the binding logic lacks semantic constraints, resulting in low accuracy of text and graphic element binding. Furthermore, the lack of global management and information completion affects the accuracy of power grid planning, design, and intelligent operation and maintenance.

Method used

A text detection model is built using a dedicated training dataset. Combining electrical semantics, business numbering rules, and topology, a candidate set is generated through multi-dimensional constraints. The model is then bound in stages according to device priority, including bus pre-deduplication, type semantic adaptation, spatial distance filtering, and global one-to-one binding, to ensure binding accuracy.

Benefits of technology

It improves the accuracy of binding key equipment in power drawings, reduces the conflict rate of repeated text binding, enhances the robustness of the method in complex scenarios, supports the generation of high-quality structured data, and improves the accuracy and efficiency of power grid planning and intelligent operation and maintenance.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN122157298A_ABST

Patent Text Reader

Abstract

Embodiments of the present application disclose a power graph paper processing method and device, electronic equipment and a storage medium. The method comprises the following steps: firstly, a target power graph paper is identified, and a to-be-processed text set and a to-be-processed graph element set are determined, the to-be-processed text set comprising at least one text, and the to-be-processed graph element set comprising at least one graph element; secondly, a candidate set is generated based on the to-be-processed text set and the to-be-processed graph element set, the candidate set comprising at least one target graph element and candidate text associated with each target graph element; and finally, based on the candidate set, the priority of the equipment represented by each graph element is determined in sequence, and the text to be bound by each graph element is determined to establish the binding relationship between the graph elements and the texts of the power graph paper. The power graph paper is processed by using the method in the embodiments of the present application, and the accuracy of the text and graph element binding in the power graph paper recognition process can be improved.

Need to check novelty before this filing date? Find Prior Art