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

A voice skill publishing method

A voice and skill technology, applied in the field of voice skill release, can solve the problems of long time consumption and heavy workload, and achieve the effect of reducing workload, reducing workload and shortening release cycle

Active Publication Date: 2020-12-15
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are defects that take a long time and a lot of work

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 voice skill publishing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] Such as figure 1 As shown, a voice skill release method, in which the voice skill is uploaded by the application developer to the cloud platform for the download and use of the terminal voice application, which can realize the registration and release of the voice skill in the cloud, and the end user can use it without upgrading, specifically including The following steps:

[0029] A. Abstract speech skills into three parts: intent, data and UI;

[0030] Wherein, the intention refers to a voice function and a typical voice saying corresponding to the voice function, and one voice function may correspond to multiple typical voice sayings. The data refers to a method for obtaining the required content or data in the speech skill, and the UI refers to a UI package for displaying the speech skill and processing user event logic;

[0031] B. Registration intention: describe the intention and the typical statement corresponding to the intention one by one; Ruyi figure 1 : ...

Embodiment 2

[0040] In this embodiment, taking the weather voice skill as an example, the implementation flowchart of publishing a weather voice skill is shown, which specifically includes the following steps:

[0041] S1. Register intent:

[0042] First of all, you need to define the weather according to your needs. This skill contains several intents, and it is assumed that there is only one intent to query the weather. Then the intent name is: query the weather, and the typical voice sayings are: "today's weather", "Beijing's weather", "Beijing's weather tomorrow".

[0043] S2. Registration data:

[0044] The intention only solves the understanding of the user's voice statement, knowing the intention and semantics of the user's "today's weather", but what is the "today's weather", such as whether there is rain or not, what is the temperature, and data is needed, and the specific weather For data, the third-party weather data interface needs to be registered with the system so that the...

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 discloses a method for releasing voice skills, comprising the following steps: A. abstracting the voice skills into three parts: intent, data and UI; B. intent to register: describing the intent and the typical statement corresponding to the intent; C. mapping the registered intention into semantics; D. registering a data interface; E. registering a UI program, wherein that UI program is used for completing the analysis of data and the display of the UI; F. Pre-release and release operations for voice skills. The voice skill issuing method of the invention can realize that the voice skill is issued in the cloud without upgrading the terminal software, thereby greatly reducing the workload and simultaneously shortening the issuing cycle.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence speech, in particular to a method for issuing speech skills. Background technique [0002] In recent years, with the rapid development of artificial intelligence, artificial intelligence voice technology has been sought after by the smart TV industry. Many TV manufacturers have released new TV products with voice interaction functions, and smart TV voice interaction has also become an attraction for consumers. one of the important factors. How to quickly release and launch various voice skills has become an important basis for the product to be ahead of competitors. [0003] In the field of AI voice dialogue, there is a key term: voice skills. A voice skill specifically refers to a function or a service provided through voice, for example, "checking the weather" is a voice skill, and "listening to music" is also a skill. Therefore, speech skills are an abstraction of speech func...

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): G06F8/60
CPCG06F8/60
Inventor 李足红刘世勇赵竹影周其军
Owner SICHUAN CHANGHONG ELECTRIC 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