A chat robot system and chat method based on fuzzy neural network

A fuzzy neural network and chat robot technology, applied in the chat robot system and chat field, can solve problems such as difficulty in meeting chat needs, chat robots cannot learn, chat robot systems and methods do not appear, and achieve high-speed search and optimization error learning ability. Effect

Active Publication Date: 2021-06-29
CHINA THREE GORGES UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of chatting with the user, even if the user has told the wrong answer, the chat robot cannot learn from the error
[0006] 3. Human language is not precise keywords and data, often with ambiguity
However, the current chat machines obviously do not have such characteristics, making it difficult to meet people's chat needs
[0007] In China, with the development and progress of robotics and artificial intelligence technology, conditions have been provided for the development of a chat robot system and method based on fuzzy neural networks. However, there is currently no chat robot based on fuzzy neural networks in the market. system and method

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 chat robot system and chat method based on fuzzy neural network
  • A chat robot system and chat method based on fuzzy neural network
  • A chat robot system and chat method based on fuzzy neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 Shown, a kind of chat robot system based on fuzzy neural network, said system comprises:

[0059] The voice collection terminal 100 is installed on both sides of the chat robot head, and is used to receive dialogue information in the chatting process between the user and the chat robot (picking up the voice information in the chatting process in real time),

[0060] It adopts professional and sensitive symmetrical double pickup, which is composed of microphone, audio amplifier circuit, signal conditioner in sound card, sample holder and analog-to-digital converter. The obtained sound analog information is converted into a digital signal and stored in the disk. The microphone uses an electret condenser microphone, which works by utilizing a polymeric material diaphragm with permanent charge isolation. Using symmetrical double pickups, the position of the microphone determines the range of incoming sound, using acoustic phenomena to determine the positi...

Embodiment 2

[0163] Such as image 3 Shown: a kind of method that adopts above-mentioned chat robot system to carry out chatting, and this method comprises the following steps:

[0164] Step 1: After the robot is started, perform system initialization and self-inspection, and initially prevent the system from malfunctioning during the chat process.

[0165] Step 2: When the user chats with the robot, the initialization of the system collection mode has been completed, and the user's voice information is collected. The collected voice data has two purposes:

[0166] One, it is stored in fuzzy neural network training database 106 as input data in order to form fuzzy neural network learning sample,

[0167] 2. It is provided to the voice preprocessing module 101 for voice data preprocessing such as sampling, noise removal, endpoint detection, pre-emphasis, and windowing and framing.

[0168] Step 3: Extract feature parameters (sound intensity, loudness, pitch, period and pitch frequency) fr...

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

A chat robot system based on a fuzzy neural network, said system comprising: a voice collection terminal; a feature extraction module connected to the voice collection terminal; a matching search module with a sound model database connected to the feature extraction module; a fuzzy neural network analysis The module is connected with the matching search module; the speech post-processing module is connected with the matching search module; the speech playback module is connected with the speech post-processing module; wherein, the fuzzy neural network analysis module has a fuzzy neural network training database and a knowledge database. The present invention provides a fuzzy neural network-based chat robot system and chatting method, which uses technologies such as fuzzy recognition, pattern matching search and artificial neural network to simulate the fuzzy reasoning process of human brain thinking and language, and can make speeches according to context and emotional characteristics. Answer, and have self-learning ability in different scenarios.

Description

technical field [0001] The invention relates to the field of robot voice chatting, in particular to a fuzzy neural network-based chatting robot system and chatting method. Background technique [0002] Fuzzy neural network has received more and more attention in the computer field. With the development of science and technology and the improvement of living standards, people's demand for intelligent chat robots is gradually increasing, and their service requirements are also getting higher and higher. The chat robot system can be regarded as a combination of the robot industry and "Internet +", which is in line with the country's scientific research and industrialization development direction. [0003] However, the robot chat skills currently on the market still cannot meet the needs of the market, and almost all of them are keyword-based retrieval technologies. This model faces a huge obstacle on the road of machine development—the complexity of language, which is mainly ma...

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): G06F16/332G06F16/33G06F40/30G06N3/04
CPCG06F16/3329G06F16/3344G06F40/30G06N3/043
Inventor 蔡政英胡绍齐范红梅
Owner CHINA THREE GORGES UNIV
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