Unlock instant, AI-driven research and patent intelligence for your innovation.

A machine learning-based generative abstract method and device

A machine learning and generative technology, applied in the fields of instruments, natural language data processing, special data processing applications, etc., can solve problems such as low efficiency and inability to summarize the central idea of ​​​​the article

Pending Publication Date: 2019-04-23
六度云计算有限公司
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional method is inefficient and unable to summarize the central idea of ​​the article, while the related algorithms of applying machine learning can directly generate summary summary 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A machine learning-based generative abstract method and device
  • A machine learning-based generative abstract method and device
  • A machine learning-based generative abstract method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the specific implementation of the machine learning-based generative summarization method and device of the present invention will be further described in detail through the following examples and in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0024] The invention relates to the technical field of natural language processing, which is a means of natural language processing in the field to generate summary summary information. Specifically disclosed are a machine learning-based generative summarization method and device. Concretely, the present invention discloses a method of using machine learning technology, using the seq2seq method, comprising the following steps: step 1) data acquisition; step 2) data preprocessing; st...

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 machine learning-based generative abstract method. The method comprises the steps of obtaining the training related information; processing the acquired related information,and completing the division operation of the training data and the test data; performing training according to the training data to generate a model; and based on the model generated by training, calculating abstract summary information of the text input by the user. According to the method, the text information can be processed more efficiently by means of machine learning and artificial intelligence, the useful information is extracted, and the summary summary information of the abstract is obtained more accurately and quickly. The method has high application efficiency and usability. The invention also relates to a machine learning-based generative abstract device.

Description

technical field [0001] The present invention relates to the technical field of natural language, in particular to a machine learning-based generative summarization method and device. Background technique [0002] The Sequence-to-sequence (seq2seq) model is a very important and popular model in natural language processing technology. This technology breaks through the traditional fixed-size input problem framework and opens up the possibility of applying the classic deep neural network model to translation. It is the first of its kind for sequential tasks such as functional question answering, and has been proven to have a very good performance. To translate a language sequence into another language sequence, the whole process is done by using deep neural network LSTM (Long Short Memory Network), or RNN (Recurrent Neural Network). [0003] In the traditional summarization system, more attention is paid to extracting key sentences. The traditional method is inefficient and c...

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 Applications(China)
IPC IPC(8): G06F17/27G06F16/332
CPCG06F40/258G06F40/232G06F40/289
Inventor 田文平杨帆王迟梁从象秦曾昌
Owner 六度云计算有限公司