Candidate answer statement generation and natural language selection method and system

A sentence and input sentence technology, applied in the field of computer and artificial intelligence, can solve problems such as inability to meet user needs, inability to migrate application scenarios, lack of versatility, etc., to ensure novelty and diversity, avoid illegal content generation, and improve novelty sexual effect

Active Publication Date: 2020-01-24
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of system generally adopts a human-designed framework process, which can retrieve specific natural language sentences from the database to realize human-computer interaction based on the judgment of user behavior status. The common problem of this type of system is that its design specific The process of the framework is not only time-consuming and labor-intensive, but also lacks versatility, and cannot be migrated to other application scenarios; in contrast, the goal of an open human-computer interaction system is to realize human-computer interaction in an open domain, and its interactive content is not limited to specific tasks , such as emotional escort robots
Although the establishment of models containing complex rules in an open interactive system is completely data-driven, without the need to manually design complex framework processes in the system, the existing human-computer interaction models still cannot meet the increasing user needs

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
  • Candidate answer statement generation and natural language selection method and system
  • Candidate answer statement generation and natural language selection method and system
  • Candidate answer statement generation and natural language selection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following describes the SARN-based candidate answer sentence generation and natural language selection method and system provided in the embodiments of the present invention in detail with reference to the accompanying drawings.

[0058] With the continuous progress of deep neural network technology and big data technology, open human-computer interaction systems have also been developed. The complex nonlinear mapping in the deep neural network provides a model basis for building an end-to-end human-computer interaction system, such as a sequence to sequence (Seq2Seq) cyclic neural network model.

[0059] Generally speaking, there are two main methods to establish an open human-computer interaction model, namely, retrieval model and generative model. Among them, the retrieval model refers to training the similarity matching model, and then returning the answer sentence ...

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 candidate answer statement generation and natural language selection method and system based on SARN. A SARN model comprises a coding network and a decoding network, and thegeneration method comprises the following steps: obtaining input statement features by using the coding network; and obtaining a corresponding candidate answer statement by using the decoding networkbased on the input statement features, wherein the decoding network adopts a random hidden variable factor to perform modeling for the diversity of the candidate answer statements.

Description

Technical field [0001] The invention relates to the field of computers and artificial intelligence, and in particular to a method and system for generating and natural language selection of candidate answer sentences based on SARN. Background technique [0002] With the continuous development of the field of artificial intelligence technology, the use of natural language to realize intelligent and personalized human-computer interaction has always been one of the most challenging research topics. Human-computer interaction technology based on natural language has a wide range of application scenarios, such as replacing humans with machines, liberating human resources, intelligent customer service, personal assistants, emotional escorts, and so on. [0003] A variety of smart interactive products have appeared in the existing technology, such as Microsoft Xiaobing, Apple Siri, Alibaba smart customer service, etc. According to application scenarios, natural language human-computer i...

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): G06F16/33G06F16/332G06N3/04G06N3/08
CPCG06F16/3329G06F16/3346G06F16/3344G06N3/08G06N3/045
Inventor 李亮杨士杰王树徽黄庆明
Owner INST OF COMPUTING TECH 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