Model training method, text intent recognition method and device

An intention and model technology, applied in the field of text intention recognition devices, can solve the problems that the intention category cannot be automatically determined and the accuracy is not high

Active Publication Date: 2020-10-27
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the traditional machine learning-based intention recognition method has disadvantages such as low accuracy and the inability to automatically determine the intention category.

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
  • Model training method, text intent recognition method and device
  • Model training method, text intent recognition method and device
  • Model training method, text intent recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0069] refer to figure 1 , shows a flow chart of the steps of Embodiment 1 of a model training method of the present invention, which may specifically include the following steps:

[0070] Step 101, obtaining multiple text corpora;

[0071] In the embodiment of the present invention, the model may include a convolutional neural network model, the convolutional neural network model is equivalent to a classifier, and the category value set according to the user's input is output according to the trained convolutional neural network model; specifically , the convolutional neural network model can include a word embedding layer, a convolutional layer, a pooling layer and a fully connected layer. The word embedding layer is mainly use...

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 embodiment of the present invention provides a training method for a model, a method and a device for identifying text intentions, and obtains multiple text corpora; respectively performs word segmentation and entity recognition on the multiple text corpora, and obtains a seed dictionary and a vocabulary; The seed dictionary and the vocabulary are clustered to obtain a plurality of intent categories; in one training, one of the word vectors is mapped to a multidimensional matrix; the maximum convolution vector is obtained from the multidimensional matrix; input the maximum Convolve the vector to the fully connected layer; set the intention category as a hidden node of the fully connected layer, and output the category value; when the multiple word vectors are trained, obtain a model that has been trained multiple times; in the embodiments of the present invention, A method for determining intent categories based on word vectors is proposed. Compared with traditional manual setting and enumeration methods, it is good at discovering new intent categories; using the trained model makes the text intent recognition rate higher.

Description

technical field [0001] The invention relates to the technical field of computers, in particular to a model training method, a text intent recognition method, a model training device, and a text intent recognition device. Background technique [0002] Machine learning (Machine Learning, ML) is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. Specializes in the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. [0003] Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its application pervades all fields of artificial intelligence, mainly using induction and synthesis rather than deduction. Machine learning is the science of getting computers to behave w...

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 Patents(China)
IPC IPC(8): G06F16/35G06F16/36G06K9/62
CPCG06F16/35G06F16/374G06F18/214
Inventor 鲍新平丁希晨
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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