Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text error correction method and system in power grid field scheduling scene

A text error correction and field technology, applied in the field of text error correction systems, can solve the problems of inability to act in the field of scheduling, and the performance of related algorithms is general, and achieve the effect of improving the accuracy of text error correction.

Pending Publication Date: 2021-03-19
CHINA SOUTHERN POWER GRID COMPANY
View PDF11 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Currently on the market, Baidu, Tencent, and JD.com have related text error correction products, but because the power grid field is particularly special, it is difficult to achieve its effect without targeted adjustments. For example, there are some open source products, such as Chinese word automatic error correction Cn_Speck_Checker and Autochecker&autocorrecter for Chinese, etc. At present, the performance of related algorithms in various self-test data sets is still average, and it is even more difficult to use them in the field of scheduling.

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
  • Text error correction method and system in power grid field scheduling scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] A text error correction method in the power grid field dispatching scene of the present invention, the process scheme also needs three preliminary preparations, namely named entity recognition model, entity knowledge base, maintenance of pinyin dictionary and text files based on a large number of call records The probability model for training, the probability model can be n-gram or LSTM similar deep learning model, what the present invention adopts is Transformer+Bi-LSTM, the input of this model is a sentence, in a sentence, some specified types will be set, If the entity is of a related type, it is replaced by the object type to be input as a feature word, and the output is the probability of each word.

[0053] After the preparatory work is completed, take "Well, ah, check the Xiazhongshan substation, whether the sister and brother switch on the neutral point arrester on the 1-acre bus is a monk" as an example, see figure 1 As shown, the process of text error correct...

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 text error correction method and system in a power grid field scheduling scene, and the method comprises the steps: carrying out the word segmentation and named entity recognition of sentences in a text, and obtaining a word segmentation set and a named entity set; performing entity linking on the named entity set and a knowledge base to determine real information of entities; performing word boundary correction on the word segmentation set by using the named entity identification set to update the word segmentation set; adding pinyin features to each word in the wordsegmentation set to generate a new word segmentation set; inputting the new word segmentation set into a probability model to obtain the probability of occurrence of each word, and determining suspicious wrongly written characters according to the probability; obtaining a candidate set of the word from a pinyin dictionary according to the pinyin of the suspicious wrongly written character; substituting the candidate words in the candidate set into sentences one by one, regenerating features, substituting the features into the probability model, and determining the optimal candidate accordingto the probability. Suspicious wrongly written characters are positioned in combination with the probability model, so that the text error correction efficiency can be improved.

Description

technical field [0001] The invention belongs to the technical field of power grid dispatching, and in particular relates to a text error correction method in the dispatching scene of the power grid field, and also relates to a text error correction system in the dispatching scene of the power grid field. Background technique [0002] In dispatching scenarios, a large amount of work needs to be communicated, inquired or given work orders through telephone and other voice methods. Now related work is facing the problem of intelligent recommendation, and one of the most important links is voice translation, while dispatching and its on-site staff , distributed in various parts of the country, the local dialects and the staff's own vocal cord pitch problems have brought great troubles to the voice translation work, and it is even difficult to overcome, and the language used in the field in the dispatching scene is relatively complicated, but the requirements for accuracy are very...

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): G06F40/295G06F40/232G06Q50/06G06N3/04G06N3/08
CPCG06F40/295G06F40/232G06Q50/06G06N3/08G06N3/045G06N3/044Y04S10/50
Inventor 孙雁斌辛阔范展滔程哲吴小刚张坤单政博陈兴望王子强许士锦吕耀棠
Owner CHINA SOUTHERN POWER GRID COMPANY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products