Power grid fault handling plan semantic modeling system and method based on deep learning

Abstract

The invention discloses a power grid fault handling plan semantic modeling system and method based on deep learning, and the method comprises the steps: completing the vectorization expression of a fault handling plan text through a word vector module, and completing the extraction of all entity components in the fault handling plan text through a plan entity recognition module and a plan relation extraction module; and adopting a plan intention understanding module to complete intention discrimination of different disposal fragments in the fault disposal plan, and completing selection of different equipment type lists based on different intentions, so that rapid mapping of the equipment is completed. The modules are used in cooperation, key information extraction in the fault handling plan can be rapidly and accurately achieved, the problems that when the fault handling plan is electronized, the manual extraction level and the intelligent level are low, and when faults are handled, the efficiency is extremely low due to the fact that a fault handling plan document depends on manual browsing are solved, Compared with a general plan extraction mode, the method is more reasonable, and the accuracy is greatly improved.

Description

technical field [0001] The invention relates to the cross field of natural language processing and power grid regulation, and in particular to a deep learning-based semantic modeling system and method for power grid fault handling plans. Background technique [0002] With the rapid development of the UHV AC / DC hybrid power grid, the scale of the power grid continues to expand, the operation mode is flexible and changeable, the power grid control business is becoming more and more complex, and the work intensity of the control personnel is also increasing. has put forward higher requirements. Especially in the case of a fault in the power grid, it is required to solve the fault quickly and ensure the stability of power supply, which puts forward higher requirements for the fault handling system of the power grid. At present, the methods and solutions for troubleshooting power grid faults mainly rely on dispatchers to handle faults according to the grid fault disposal plan co...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a semantic modeling system and method for power grid fault handling plans based on deep learning, which solves the problem that fault handling mainly depends on manual experience and has a low level of intelligence. The system can quickly and accurately extract power grid The key information in the fault plan provides support for subsequent applications such as power grid fault handling and plan verification

Images