Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Theme-enhanced chat robot reply generation method and device

A chatbot and topic technology, applied in the field of artificial intelligence, can solve the problems of insufficient reply content and incoherent reply, and achieve the effect of solving the problem of insufficient reply content, strengthening coherence, and reducing the probability of generation

Active Publication Date: 2019-07-30
WUHAN UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention provides a topic-enhanced chat robot reply generation method and device to solve or at least partially solve the technical problems of insufficient reply content and incoherent reply in the methods in the prior art

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
  • Theme-enhanced chat robot reply generation method and device
  • Theme-enhanced chat robot reply generation method and device
  • Theme-enhanced chat robot reply generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] This embodiment provides a topic-enhanced chat robot reply generation method, please refer to figure 1 , the method includes:

[0072] Step S1: Preprocessing the pre-acquired dialogue text.

[0073] Specifically, the dialog text can be obtained from a preset data source. Preprocessing the text, that is, the process of data screening and cleaning, makes it easier to obtain subsequent training sets.

[0074] In one embodiment, preprocessing the pre-acquired dialogue text includes:

[0075] Filter non-Latin characters and stop words in the pre-fetched dialogue text;

[0076] Convert all letters to lowercase and normalize special characters using regular expressions.

[0077] Specifically, special characters include time, numbers, and so on.

[0078] Step S2: According to the number of rounds of the dialogue text, the preprocessed dialogue text is sampled, and the sampled dialogue text is used as a dialogue training set.

[0079] Specifically, according to different a...

Embodiment 2

[0133] This embodiment provides a topic-enhanced chat robot reply generating device, please refer to Figure 5 , the device consists of:

[0134] Dialogue text preprocessing module 201, configured to preprocess the pre-acquired dialogue text;

[0135] The sampling module 202 is used to sample the preprocessed dialog text according to the number of rounds of the dialog text, and use the sampled dialog text as a dialog training set;

[0136] Topic extraction module 203, for utilizing CNN to carry out topic extraction to dialogue text, obtain text topic information;

[0137] Reply subject prediction module 204, for adopting MLP to carry out the prediction of reply subject to text subject information, predict and obtain reply subject information;

[0138] The chat robot dialogue reply generation module 205 is used to input the dialogue training set into the Seq2Seq generation model, and introduces the extracted text topic and the predicted reply topic into the Seq2S...

Embodiment 3

[0172] Based on the same inventive concept, the present application also provides a computer-readable storage medium 300, please refer to Figure 6 , on which a computer program 311 is stored, and the method in Embodiment 1 is implemented when the program is executed.

[0173] Since the computer-readable storage medium introduced in the third embodiment of the present invention is the computer-readable storage medium used to implement the topic-enhanced chat robot reply generation method in the first embodiment of the present invention, it is based on the introduction in the first embodiment of the present invention method, those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so details are not repeated here. All computer-readable storage media used in the method of Embodiment 1 of the present invention belong to the scope of protection of the present invention.

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 provides a theme-enhanced chat robot reply generation method and device, and the method comprises the steps: firstly, carrying out the preprocessing and sampling of a dialogue text, andobtaining a dialogue training set; secondly, performing topic extraction on the dialogue text by utilizing the CNN to obtain a text topic; utilizing the text theme, and predicting a reply theme through the MLP to obtain a predicted reply theme; and finally, inputting the dialogue training set into the Seq2Seq generation model, and introducing the text theme and the prediction reply theme into thegeneration model through Gate to assist the generation process so as to obtain the chat robot dialogue reply. The method can achieve the technical effects of reducing the generation probability of high-frequency general replies and enabling the nerve dialogue model to generate more coherent and abundant replies.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a topic-enhanced chat robot reply generation method and device. Background technique [0002] With the development of artificial intelligence technology, natural language processing (NLP) is widely used in many fields. Dialogue systems, sometimes called chatbots, are an extremely challenging task in the field of AI and natural language processing, aiming to generate fluent responses to conversational information in the form of natural language. Conversational systems can be divided into goal-driven dialogue systems and open-domain chatbots. The former helps people complete a specific task, while the latter focuses on open domains, such as human chatter, or computer game characters. Previous dialogue system research has mainly focused on goal-driven dialogue systems. Recently, open-ended chatbots have gained increasing attention in both academia and indu...

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): G06F16/332G06N3/04
CPCG06F16/3329G06N3/044G06N3/045H04L51/02
Inventor 彭敏韩玮光胡刚陈典李冬
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com