Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

System and method for customizing skills of intelligent loudspeaker box and storage medium

A smart speaker and self-defined technology, which is applied in speech analysis, speech recognition, instruments, etc., can solve the problems of not being able to dynamically increase or decrease speech skills, not being able to update speech skills independently, and not being able to realize customization, so as to reduce homogeneity Serious problems, adding interesting variety, effect of enriching variety

Inactive Publication Date: 2020-08-28
湖南华诺科技有限公司
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Embodiments of the present invention provide a system, method, and storage medium for customizing smart speaker skills, so as to solve problems in existing smart speakers that voice skills cannot be independently updated, voice skills cannot be dynamically increased or decreased, and voice skills are single and cannot be customized. question

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
  • System and method for customizing skills of intelligent loudspeaker box and storage medium
  • System and method for customizing skills of intelligent loudspeaker box and storage medium
  • System and method for customizing skills of intelligent loudspeaker box and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Embodiment 1, a system for customizing smart speaker skills. Such as figure 1 As shown, the system for customizing smart speaker skills includes a voice recognition module, a communication interface, a voice skill module, and a registration form; the voice recognition module, communication interface, voice skill module, and registry are respectively located on the smart speaker terminal; different voice skill business applications; the communication interface is used for information interaction between the voice recognition module and the voice skill module; the voice recognition module is used for recognizing and analyzing the voice commands sent by the user, and communicates with the voice command through the communication interface. The voice skill module performs information interaction; the registry is used to dynamically store and update key voice information of several different voice skill business applications. The registration form of the first embodiment is ...

Embodiment 2

[0039] Embodiment 2, a system for customizing smart speaker skills. Such as image 3 As shown, in the second embodiment, the speech recognition module includes a cloud platform speech engine. The voice engine of the cloud platform communicates with the smart speaker terminal through the network.

[0040] The second embodiment provides a method for customizing smart speaker skills. Such as Figure 4 As shown, the method includes the following steps:

[0041] S1) Start the smart speaker terminal, the user sends out a voice command to judge whether the grammar of the voice command is correct, if so, enter step S2); if not, repeat this step;

[0042] S2) Receive the voice command sent by the user through the voice engine, open the communication interface between the voice engine and the voice skill module, and use the voice engine to analyze the voice command to obtain the voice command analysis result; the voice engine is a cloud platform voice engine, cloud The platform voi...

Embodiment 3

[0046] Embodiment 3, a system for customizing smart speaker skills. In the third embodiment, the speech recognition module includes a local speech engine and a cloud platform speech engine. The voice engine of the cloud platform communicates with the smart speaker terminal through the network. The local voice engine is located on the smart speaker terminal.

[0047] Embodiment 3 also provides a method for customizing smart speaker skills. Such as Figure 5 As shown, the method includes the following steps:

[0048] S1) Start the smart speaker terminal, the user sends out a voice command to judge whether the grammar of the voice command is correct, if so, then enter step S2); if not, repeat this step;

[0049] S2) judge whether the network is connected, if so, then use the cloud platform speech engine as the speech engine executed in the subsequent steps, and enter step S3); if not, then use the local speech engine as the speech engine executed in the subsequent steps, ente...

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 the field of intelligent sound boxes, and discloses a system and method for customizing skills of an intelligent loudspeaker box, and a storage medium. The system comprises avoice recognition module, a communication interface, a voice skill module, and a registry. The communication interface is used for information interaction between the voice recognition module and thevoice skill module, the voice recognition module is used for recognizing and analyzing a voice instruction sent by a user and carrying out information interaction with the voice skill module through acommunication interface, and the registry is used for dynamically storing and updating key voice information of a plurality of different voice skill service applications. The voice engine and the voice skill service application are decoupled, and independent updating of the voice engine and independent updating and dynamic increasing and decreasing of the voice skill service application are achieved, the diversity of voice skills is enriched, the function of customizing voice skills is realized, the interesting diversity of the intelligent sound box terminal is increased, and the problem of serious homogenization is reduced.

Description

technical field [0001] The invention relates to the field of smart speakers, in particular to a system, method and storage medium for customizing smart speaker skills. Background technique [0002] For existing smart speakers, the speech engine and speech skills are usually provided by different solution providers, and the corresponding speech skills need to be executed after the speech engine performs speech recognition; the current common practice is to integrate the speech engine and speech skills together, such as speech The engine is connected to a fixed music service or a fixed weather query service, which leads to a serious problem of product homogeneity, making the product more single. This way, the voice skill business application cannot be updated independently, and the voice skill cannot be dynamically increased or decreased. , unable to customize voice skills. Contents of the invention [0003] Embodiments of the present invention provide a system, method, and...

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): G10L15/22G10L15/30G10L15/16
CPCG10L15/16G10L15/22G10L15/30G10L2015/223
Inventor 吴涛
Owner 湖南华诺科技有限公司
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
Eureka Blog
Learn More
PatSnap group products