Power system dispatcher grade evaluation system based on text classification

A power system and grade evaluation technology, applied in the field of grade evaluation system, can solve the problems of consuming a lot of manpower and material resources, low efficiency, and low accuracy, and achieve the effects of reducing manual pressure, solving low efficiency, and improving efficiency

Pending Publication Date: 2021-10-08
GUIZHOU POWER GRID CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: to provide a power system dispatcher grade evaluation system based on text classification, to solve the problem that the existing technology consumes a lot of manpower and material resources and is inefficient for power system dispatcher grade evaluation. At the same time, the current method based on classification Technical issues such as low accuracy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Power system dispatcher grade evaluation system based on text classification
  • Power system dispatcher grade evaluation system based on text classification
  • Power system dispatcher grade evaluation system based on text classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] A power system dispatcher grade evaluation system based on text classification (see figure 1 ),it includes:

[0034] Data acquisition module: collect dispatcher text data from the database system, and build a training data set;

[0035] Data preprocessing module: preprocess the collected dispatcher text data;

[0036]Model training and fine-tuning module: use the pre-training model BERT to digitize the text representation of the pre-processed text information, connect and build a fully connected network of 1 layer after the BERT model, and perform model training and fine-tuning based on the training data set to obtain a classification model;

[0037] Ability level prediction module: Score the classification model based on the pre-trained model BERT on the test set to test the effect.

[0038] 1) Deep learning models require a large amount of labeled data, but there is no public labeled data set about dispatchers of academic systems in the domestic electric power field...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a power system dispatcher grade evaluation system based on text classification, and the system comprises a data collection module which collects dispatcher text data information from a database system, and builds a training data set; a data preprocessing module which is used for preprocessing the collected dispatcher text data information; a model training and fine tuning module which is used for performing text representation digitization on the preprocessed text information by using a pre-training model BERT, connecting and constructing a one-layer full-connection network behind the BERT model, and performing model training and fine tuning based on a training data set to obtain a classification model; and an ability level grade prediction module which is used for scoring a classification model based on a pre-training model BERT on a test set so as to test an effect. The technical problems that in the prior art, power system dispatcher grade evaluation consumes a large amount of manpower and material resources and is low in efficiency, and a current classification-based method is low in accuracy are solved.

Description

technical field [0001] The invention belongs to the technical field of software, in particular to a text classification-based power system dispatcher grade evaluation system. Background technique [0002] The power system dispatcher refers to the monitor, command and control of the power system operation. The dispatcher exercises the command power in accordance with the prescribed dispatch scope, and the objects of command are the on-duty dispatcher of the next-level dispatching organization, the duty chief of the power plant and the duty chief of the substation. The main responsibility of the dispatcher is to ensure the safe and economical operation of the power system, and to supply the required electricity, electric energy and thermal energy to users reliably and in compliance with quality standards. Dispatchers should have the knowledge and good quality corresponding to their work, and undergo strict training. The professional quality and technical level of dispatchers...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06Q50/06G06F16/35G06F40/289G06N3/04
CPCG06Q10/06398G06Q50/06G06F16/35G06F40/289G06N3/045
Inventor 张云菊郭明史虎军杨强张玉罗邢苗苗石启宏
Owner GUIZHOU POWER GRID CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products