Check patentability & draft patents in minutes with Patsnap Eureka AI!

Group-Level KKS Coding Automatic Mapping Method Based on Supervised Sequence Generation Network

A technology for sequence generation and encoding, applied in the field of group-level KKS encoding automatic mapping, to reduce work intensity, facilitate extraction and reconstruction, and achieve generalization.

Active Publication Date: 2021-11-02
浙江浙能数字科技有限公司 +1
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the current group-level KKS standardized coding mapping task is still a very challenging data governance task

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
  • Group-Level KKS Coding Automatic Mapping Method Based on Supervised Sequence Generation Network
  • Group-Level KKS Coding Automatic Mapping Method Based on Supervised Sequence Generation Network
  • Group-Level KKS Coding Automatic Mapping Method Based on Supervised Sequence Generation Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 of the present application provides a method such as figure 1 and figure 2 The group-level KKS encoding automatic mapping method based on the supervised sequence generation network is shown:

[0048] Step 1, through such as Figure 6 The collection device shown collects the old KKS code list and new KKS code list ,in code for old KKS, code for the new KKS, The total number of old KKS codes or new KKS codes; analyze the coding characteristics and build general word segmentation rules; technicians list part of the old KKS codes And part of the new KKS code list Match to get the mapping table ;According to the old KKS encoding list , New KKS code list and the mapping table Construct KKS encoded dataset ;The standard code (new KKS code) and the factory-side code (old KKS code) are automatically mapped through the model, and the factory-side code is used as input for model training;

[0049] Step 2. The general word segmentation rules ...

Embodiment 2

[0055] On the basis of Embodiment 1, Embodiment 2 of the present application provides a specific implementation of step 5 in Embodiment 1:

[0056] Step 5.1, the training set Randomly sample and divide into groups to form batch data, and use the batch data as the input (training data) of the sequence generation network model ;

[0057] Step 5.2, constructing an encoding network based on a long short-term memory network (LSTM), the encoding network consists of an embedding layer and an LSTM encoding layer:

[0058]

[0059] In the above formula, Indicates that the embedding layer will sequentially generate the input value of the network model Convert to a fixed-size dense vector ; Indicates that the LSTM encoding layer will dense vector Perform matrix calculation through the forget gate, retain gate and output gate inside the long short-term memory network to obtain sequence features ;

[0060] Step 5.3, constructing a decoding network based on a long short-t...

Embodiment 3

[0066] On the basis of Embodiment 1 and Embodiment 2, Embodiment 2 of the present application provides such figure 1The application of group-level KKS coding automatic mapping method based on supervised sequence generation network in a group data standardization project is shown:

[0067] Step 1, through the acquisition unit, its structure is as follows Figure 6 As shown, the acquisition code list is obtained and , analyze the original KKS code of the power plant. The code rule contains letters, numbers and special characters. The new KKS code rule contains letters and numbers. The general word segmentation rule divides the old and new codes according to different types of characters. matching to get the mapping table , to build a KKS encoded dataset , the data set contains 22000 sets of matched codes;

[0068] Step 2. Segment the KKS coded data set with the general word segmentation rules obtained in step 1, extract the professional codes and special characters in ...

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 relates to a group-level KKS code automatic mapping method based on a supervised sequence generation network, comprising the steps of: collecting an old KKS code list and a new KKS code list through a collection device; performing word segmentation on a KKS code data set by a general word segmentation rule. The beneficial effects of the present invention are: the standard code and the factory-side code are automatically mapped through the model to ensure that the dictionary can be quickly matched under the condition of dynamic update; the factory-side code is used as input for model training to obtain a sequence generation network model; The long-short-term memory network is introduced into the sequence generation network model to construct the encoding network and the decoding network. The encoding network and the decoding network are centrally symmetrical, which facilitates the extraction and reconstruction of KKS encoding features; it solves the mapping problem under different encoding rules and avoids Due to the change of the original KKS code, the measurement points of other production systems cannot be read, which reduces the work intensity and realizes the generalization of the underlying data.

Description

technical field [0001] The invention belongs to the field of power plant information technology, and in particular relates to a group-level KKS coding automatic mapping method based on a supervised sequence generation network. Background technique [0002] KKS is the abbreviation of power plant identification system, which originated from the German Kraftwerk-Kennzeichen System, which is used to identify various systems, equipment, components, and measuring points in power plants to facilitate standardized management of complex power production. Most domestic power plants use KKS codes to manage equipment and measuring points at the beginning of plant construction, and the effect is remarkable. However, with the transformation of power plant equipment, the code rules cannot quickly adapt to the latest production process, resulting in a large number of manually written KKS codes. Coding exists in coding systems. At the same time, it also greatly limits the innovation of the ...

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 Patents(China)
IPC IPC(8): G06F40/126G06F40/242G06N3/04
CPCG06F40/126G06F40/242G06N3/044
Inventor 傅骏伟郭鼎王豆张震伟孟瑜炜俞荣栋吴林峰雪小峰罗一凡
Owner 浙江浙能数字科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com