Chinese medical text information matching method and system based on twin neural network
A neural network and text information technology, applied in the field of Chinese medical text information matching based on twin neural network, can solve problems such as information matching, and achieve the effect of solving information loss and improving matching effect.
Pending Publication Date: 2022-02-08
HANGZHOU DIANZI UNIV
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a kind of medical Chinese text information matching method based on long short-term memory network, thus solve the problem of prior art Chinese medical information matching
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
[0027] In order to make the above objects, features and advantages of the present invention more comprehensible, specific implementations of the present invention will be described in detail below in conjunction with the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention can be implemented in many other ways different from those described here, and those skilled in the art can make similar improvements without departing from the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below. The technical features in the various embodiments of the present invention can be combined accordingly on the premise that there is no mutual conflict.
[0028] Such as figure 1 As shown, in a preferred embodiment of the present invention, a kind of Chinese medical text information matchin...
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 Chinese medical text information matching method and system based on a twin neural network. According to the method and system, a twin neural network for realizing medical Chinese text information matching is constructed by adopting a bidirectional long-short-term memory network, so that long-distance and short-distance dependencies can be captured at the same time, expressions of two sentences in a question pair are output as sentence vectors, and a similarity score is calculated; and matching judgment of the question pairs can be realized by obtaining the similarity score. The deep learning model of multi-semantic document expression not only considers the similarity degree of final expression vectors, but also can effectively solve the problem of information loss generated in the process of compressing the whole sentence by a traditional deep learning model of single-semantic document expression through multi-granularity matching, and the matching effect is improved.
Description
technical field [0001] The invention relates to the technical field of medical information, in particular to a Chinese medical text information matching method based on a twin neural network. Background technique [0002] With the vigorous development of the field of natural language question answering, the field of medical question answering has gradually become one of the hot spots. More and more users conduct inquiries and consultations through medical service platforms on the Internet. The field mainly provides question retrieval services through search engines. The search method based on exact matching cannot understand the semantics of the query and may cause ambiguity in the results. In the field of text matching, it is an effective method to train semantic matching models through supervised corpora, but in Chinese medical There is a lack of corresponding medical information matching data in the text field. The traditional manual supervised corpus method is not only m...
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): G06F16/35G06F16/332G06F40/211G06F40/30G06N3/04G06N3/08
CPCG06F16/35G06F16/3329G06F40/211G06F40/30G06N3/049G06N3/08G06N3/044G06N3/045
Inventor 黄孝喜童伟王荣波谌志群姚金良
Owner HANGZHOU DIANZI UNIV