Heterogeneous graph neural network-based discipline and inspection clue multi-label classification method
A neural network and classification method technology, applied in the field of text multi-label classification, can solve the problems of limited text representation ability, low classification efficiency, node update of different edge information and node type information, etc., to improve classification efficiency and reduce classification time. , the effect of improving the ability to express
Pending Publication Date: 2022-07-08
INNER MONGOLIA AGRICULTURAL UNIVERSITY
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] This application provides a multi-label classification method for discipline inspection clues based on a heterogeneous graph neural network, which is used to solve the problem of low classification efficiency in the existing multi-label classification method for discipline inspection clues, which limits the ability to express text and cannot be classified according to different edges. Technical Issues for Node Updates with Information and Node Type Information
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0037] For ease of understanding, see Figure 1 to Figure 4 , an embodiment of a multi-label classification method for discipline inspection clues based on a heterogeneous graph neural network provided by this application, including:
[0038] Step 101 , constructing a text multi-label classification model based on a t...
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
Login to View More Abstract
The invention discloses a discipline and inspection clue multi-label classification method based on a heterogeneous graph neural network, a text multi-label classification model based on a text heterogeneous graph is constructed and utilized for classification, and the classification efficiency is improved. Preprocessing the text, and constructing a heterogeneous graph structure; initializing vector representations of different types of nodes in the heterogeneous graph structure, inputting the obtained node vector representations and the heterogeneous graph structure into a heterogeneous graph neural network, and inputting the obtained sentence node vector representations into a BILSTM neural network, and inputting the obtained content vector representation and sentence node vector representation into a full-connection network after passing through an attention mechanism, and outputting a label classification result, thereby realizing node updating aiming at different side information and node type information. The technical problems that according to an existing discipline and inspection clue multi-label classification method, the classification efficiency is low, the representation ability of a text is limited, and node updating cannot be conducted according to different side information and node type information are solved.
Description
technical field [0001] The present application belongs to the technical field of text multi-label classification, and in particular relates to a multi-label classification method for discipline inspection clues based on a heterogeneous graph neural network. Background technique [0002] Disciplinary inspection clues are clues and materials accepted by the discipline inspection and supervision organs that reflect the suspected violation of party discipline, administrative discipline, and national laws and regulations by party organizations, party members, and administrative supervision objects. It mainly includes: clues of petition cases approved and forwarded by leaders; clues of relevant units or individuals suspected of violating discipline discovered by disciplinary inspection and supervision organizations at all levels in the process of handling cases; clues sent; information about the case collected and mastered by other parties, etc. Disciplinary clues are usually man...
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
Login to View More IPC IPC(8): G06F16/35G06N3/04G06N3/08
CPCG06F16/35G06N3/08G06N3/044G06N3/045
Inventor 陈俊杰高静左东石樊昊
Owner INNER MONGOLIA AGRICULTURAL UNIVERSITY