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

AI voice interaction method, apparatus and system

A voice interaction and voice technology, applied in voice analysis, reasoning methods, transmission systems, etc., can solve the problems of not equipped with speakers, the speaker array has slightly poor performance in picking up voice commands, and the user experience is not good.

Inactive Publication Date: 2018-09-21
SHENZHEN AUKEY SMART INFORMATION TECH CO LTD
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing Echo Dot is often not equipped with speakers itself, and needs to provide jacks and cables to connect with existing speakers, or connect to existing speakers through Bluetooth; moreover, Dot's speaker array is very good at picking up voice commands Slightly poor, especially when playing music or in a noisy environment, users need to shorten the distance between themselves and EchoDot to complete the activation, otherwise Echo Dot may not be able to quickly recognize commands, the user experience is not good, and it will cause inconvenience to use

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
  • AI voice interaction method, apparatus and system
  • AI voice interaction method, apparatus and system
  • AI voice interaction method, apparatus and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Please refer to figure 1 and figure 2 , the present application provides an AI voice interaction method, including:

[0046] Step S1: the earphone 20 acquires the user's voice, performs analog-to-digital conversion on the user's voice, obtains a digital voice signal and sends it out through wireless communication;

[0047] Step S2: the body 10 receives the digital voice signal sent by the earphone 20 through wireless communication, and sends it out through mobile data or WiFi;

[0048] Step S3: the cloud server 8 receives the digital voice signal sent by the main body 10 through mobile data or WiFi, and performs voice recognition and semantic analysis to it;

[0049] Step S4: if the semantic analysis result is related to making a call, the cloud server 8 sends a corresponding communication command to make the ontology 10 make a call; otherwise, the cloud server 8 performs corresponding Internet data processing according to the semantic analysis result, calls the corr...

Embodiment 2

[0075] refer to Figure 3 to Figure 8 , the present application provides an AI voice interaction device, including:

[0076] The main body 10 is a car charging type. The main body 10 includes: an upper body shell 3011, a lower body shell 3012 and a car charger plug 3013. The upper body shell 3011 and the lower body shell 301 are snapped together to form a body shell. The head 3014, the body lower shell 3012 are socketed on the spherical rotating head 3014, the body upper shell 3011 is embedded with an earphone groove 112, and the power output terminal 15 and the body magnetic attraction device 105 are arranged below the earphone groove 112, and the body shell is provided with There is a self-locking ejector 121, a main body PCB100, a charging module 138 and a main body battery 130, and the main body PCB100 is provided with a main body processor 100, a first communication module 11, a second communication module 12, a main body energy storage circuit 13 and an electric energy o...

Embodiment 3

[0101] refer to Figure 3 to Figure 5 ,as well as Figure 9 to Figure 11 , the present application provides an AI voice interaction device, including:

[0102] Body 10 is pendant type, and 10 body comprises: body front cover 4011, body back cover 4012 and necklace 4013, and pendant type body front cover 4011 and pendant type body back cover 4012 snap-fit ​​structure body shell, and this necklace 4013 is connected with body by suspension ring 4014 The shells are connected, and the front cover 4012 of the body is embedded with an earphone slot 112. Behind the earphone slot 112, there is an electric energy output terminal 15 and a magnetic suction device 105 for the body. The body shell is equipped with a self-locking ejector 121, a body PCB 100, and a charging module. 138 and the body battery 130 , the body processor 100 , the first communication module 11 , the second communication module 12 , the body energy storage circuit 13 and the power output circuit 14 are arranged on t...

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 an AI voice interaction method. The method comprises the following steps: obtaining user voice by using an earphone, receiving a digital voice signal sent by the earphone through wireless communication by using a main body, then sending the digital voice signal to a cloud server through mobile data or WiFi, performing, by the cloud server, voice recognition and semantic analysis on the digital voice signal, and causing the main body to make a call or issuing network data to the main body according to the analysis result, so that the earphone performs corresponding voicebroadcast according to the network data. Since the pickup effect of the earphone worn on the ear is better, and the most data processing is completed in the cloud server of the cloud, the voice recognition and the semantic analysis are more accurate, and the obtained network data resources are also more abundant. Correspondingly, the invention further provides a computer readable storage medium, and an AI voice interaction apparatus and system.

Description

technical field [0001] The present invention relates to the technical field of portable voice equipment, in particular to an AI voice interaction method, device and system. Background technique [0002] Echo (Echo Protocol, response protocol), Echo is the most commonly used data packet in routing and in the network. You can know which paths the current connection node has by sending echo packets, and the path length can be obtained through the round-trip time. Amazon's Echo Dot can listen, broadcast, connect with other devices and control them. Echo Dot, essentially Echo's "Mini-Me", is a cloud-based and voice-activated AI voice interaction device that can understand As a physical, ready-to-call Siri, users wake up the Echo Dot by saying her name or other key words. Echo Dot's built-in microphone array is always ready to monitor the sound from all around. Once the key words are recognized, the microphones will record any subsequent utterances and send them to Amazon's clou...

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): H04M1/60G10L15/22G10L15/30G06F17/27
CPCG10L15/22G10L15/30G10L2015/223G06F40/30H04M1/60A45C2011/001H04R1/1016H04R1/1041H04R5/033H04R2420/07H04R2460/17G06F3/165G06N5/04G10L15/1815H04L67/10H04W84/12H04W88/02
Inventor 邓超
Owner SHENZHEN AUKEY SMART INFORMATION TECH CO LTD
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