Dialogue system answer generation method and system

A dialogue system and word sequence technology, applied in the field of computer networks, can solve problems such as not considering external knowledge, uncontrollable process, poor quality, etc., to achieve the effect of reducing the degree of freedom, process controllable, and improving quality

Inactive Publication Date: 2019-07-16
INST OF ACOUSTICS CHINESE ACAD OF SCI
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the word sequences generated by these methods do not consider external knowledge, are c

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
  • Dialogue system answer generation method and system
  • Dialogue system answer generation method and system
  • Dialogue system answer generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0018] The present invention will be further described below in conjunction with the drawings.

[0019] In a dialogue system, the present invention processes the user input text, uses part of speech tagging, named entity recognition and other methods to extract keywords in the input text, and uses database query or neural network automatic generation methods to obtain expected answers containing keywords. Sequence, use the neural network model to construct sentences based on these keywords to generate answer text.

[0020] Such as figure 1 As shown, the method of the present invention includes the following steps:

[0021] Step S1). Cut multiple rounds of dialogue data into a single round of dialogue, and each round is expressed in the form of "user input-answer". And the data is divided into training set, development set and test set, used for training, verifying parameters and testing. For each round of dialogue (U,Y), U={u1,u2,...,uT-1,uT} is the word sequence entered by the 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 invention relates to a dialogue system answer generation method and system, and the method comprises the following steps of S1) cutting the multiple rounds of dialogue data according to each round, wherein each round of dialogue is expressed as (U, Y); S2) performing THE part-of-speech tagging and named entity identification on each word in the U to find a keyword sequence in the word sequence; and S3) obtaining a target keyword sequence by using a database query or neural network automatic generation method; For each target keyword, searching to obtain a word vector of the keyword; S4) carrying out model training, for all rounds of conversations in the training set, using a seq2seq model to obtain a predicted word sequence Y'; and S5) after the training is completed, inputting a sample into any user in the test sample, and performing the operation in the step S4) to obtain the predicted word sequence Y'. According to the method and the system, the content of the generated answer can be effectively controlled, and the quality of the answer is improved.

Description

technical field [0001] The invention relates to the field of computer networks, in particular to a dialogue system answer generation method and system. Background technique [0002] With the development of science and technology and the rise of the artificial intelligence industry, spoken dialogue systems that interact with natural language are in great demand in all aspects of society. Personal assistants such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo have emerged as the times require, bringing convenience to people's daily lives; smart customer service is also applied to leading companies in various service industries, reducing the number of manual customer service and Improve service quality; In the field of health care, medical dialogue systems and auxiliary diagnosis have attracted many start-up companies. Simplified medical dialogue systems such as Baidu Doctor have also gradually formed, guiding common diseases and providing preliminary diagnosis solutio...

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
IPC IPC(8): G06F16/9032G06F17/27
CPCG06F40/295G06F16/90332
Inventor 何峻青赵学敏颜永红
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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