Method and system for automatic recognition of medical text terms based on long-term and short-term memory network
A long-short-term memory and automatic recognition technology, applied in the field of machine learning, can solve problems such as insufficient recall rate, unrecognizable terms, and low precision rate, and achieve the effect of improving precision rate and recall rate, improving accuracy rate, and improving accuracy rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] A preferred embodiment of a method for automatic recognition of medical text terms based on a long-short-term memory network of the present invention, comprising:
[0030] Use pre-trained word vectors to represent each word in the medical text sentence to obtain training data;
[0031] Input the training data into the two-way long-short memory network to obtain the label category with the highest probability of each word in the medical text sentence;
[0032] Input the output result of the label category with the highest probability of each text into the conditional random field, and use the Viterbi algorithm to calculate the label sequence with the highest joint probability.
[0033] As an example in this embodiment, a long short-term memory network and a conditional random field will be used, which require a large amount of tagging training data. In the manual tagging process of word sequences in medical texts, the commonly used BIO scheme for word tagging will be use...
Embodiment 2
[0053] A preferred embodiment of a medical text term automatic recognition system based on a long short-term memory network of the present invention, comprising:
[0054] The word vector model unit is used to represent each word in the medical text sentence using a pre-trained word vector;
[0055] The two-way long-short-term memory network unit is used to input the training data into the two-way long-short-term memory network to obtain the label category with the largest probability of each character in the medical text sentence;
[0056] The conditional random field model unit is used to input the output result of the label category with the largest probability of each text into the conditional random field, and use the Viterbi algorithm to calculate the label sequence with the largest joint probability.
[0057] Such as Figures 1 to 2 As shown, two-way long short-term memory network + conditional random field model construction
[0058] Model Programming Framework: Pytho...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap