Information extraction method and device and communication message classification method and device
A communication message and information extraction technology, applied in the field of deep learning, can solve problems such as interference and inability to communicate message classification, and achieve the effect of efficient classification, avoiding influence, and improving accuracy and efficiency.
Active Publication Date: 2021-11-09
北京中科海芯科技有限公司
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The Chinese language itself has the characteristics of flexible and changeable words, and in the multi-party conversation scenario, there is often interference of irrelevant information in the communication messages of multi-party users, which makes it impossible to efficiently and accurately extract information from the communication messages of multi-party users. It is also unable to efficiently classify the communication messages of multiple users
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
[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments It is a part of the embodiments of the present disclosure, but not all of the embodiments, and in the case of no conflict, the implementation modes and the features of the implementation modes in the present disclosure can be combined with each other. Based on the embodiments in the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present disclosure.
[0031] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as ...
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 relates to the technical field of deep learning, in particular to an information extraction method and device and a communication message classification method and device. For communication messages of multiple users in the same session, core messages in the communication messages of the multiple users are screened based on the importance of the communication messages and the context semantic relevance, and then each group of core messages are labeled, so that the influence of irrelevant communication messages in the communication messages of the multiple users on a labeling process can be avoided, and the labeling precision and efficiency can be improved. On the basis, the communication messages of the multiple users can be efficiently classified according to the obtained labeling information.
Description
technical field [0001] The present disclosure relates to the technical field of deep learning, and in particular to an information extraction method and device, and a communication message classification method and device. Background technique [0002] Information Extraction (Information Extraction, abbreviated as IE), also known as Event Extraction (abbreviated as EE), usually refers to extracting specific factual information from natural language text. [0003] The Chinese language itself has the characteristics of flexible and changeable words, and in the multi-party conversation scenario, there is often interference of irrelevant information in the communication messages of multi-party users, which makes it impossible to efficiently and accurately extract information from the communication messages of multi-party users. It is also impossible to efficiently classify the communication messages of multiple users. Contents of the invention [0004] In order to efficiently...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/30G06F40/284G06F40/166
CPCG06F40/30G06F40/284G06F40/166
Inventor 资康莉贾耀仓宫相坤陈维伟
Owner 北京中科海芯科技有限公司