Method determining semantic scene, system thereof and air conditioner

A technology of semantic scene and determination method, applied in the custom field of semantic scene, can solve problems such as poor user experience

Inactive Publication Date: 2019-01-08
GREE ELECTRIC APPLIANCES INC
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the current dialogue system is to add a complete set of corpus manually first, and then semantic analysis hits the entry or scene. When the scene does not exist, it cannot be hit. When a new scene is needed, the scene or word must be manually added from the background. , this situation makes the user experience extremely poor

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
  • Method determining semantic scene, system thereof and air conditioner
  • Method determining semantic scene, system thereof and air conditioner

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] This embodiment provides a method for determining a semantic scene, such as figure 1 As shown, the method of the present invention adds a layer of system-corpus combination system between the semantic analysis system and the corpus, so that the user can add the semantic scene that the user wants through voice, that is, the semantic scene can be customized.

[0029] In this case, it is necessary to add some particularly independent corpus entries without any coupling in the corpus. When users add custom scenes through voice, they can combine the corpus entries needed for custom scenes through the middle layer system (corpus automatic combination) Generate new semantic scenarios. The corpus described in this embodiment includes individual corpus and / or semantic scene.

[0030] The method of the present embodiment comprises the steps:

[0031] The semantic analysis system receives scene command sentences;

[0032] Parse the scene command statement, and compare the analy...

Embodiment 2

[0039] This embodiment provides a system for customizing semantic scenarios, such as figure 2 As shown, by adding a layer of system-corpus combination system between the semantic analysis system and the corpus, the user can add the semantic scene that the user wants through voice, that is, the semantic scene can be customized.

[0040] In this case, it is necessary to add some particularly independent corpus entries without any coupling in the corpus. When users add custom scenes through voice, they can combine the corpus entries needed for custom scenes through the middle layer system (corpus automatic combination) Generate new semantic scenarios. The corpus described in this embodiment includes individual corpus and / or semantic scene.

[0041] The system of the present embodiment includes a semantic analysis module, a separate corpus, a semantic scene module, and a corpus combination module;

[0042] The semantic analysis module is used to receive the command statement, a...

Embodiment 3

[0049] The present invention also provides an air conditioner. The operation mode of the air conditioner adopts the above method for determining the semantic scene to realize the user's self-definition of the air conditioner operation mode.

[0050] Correspondingly, the semantic scene includes starting up, shutting down, increasing wind speed, decreasing wind speed, alarm clock, weather forecast, and the like.

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 determining a semantic scene, a system and an air conditioner. By adding a corpus composition system between the semantic parsing system and the corpus, the user can customize the semantic scene. The method comprises the following steps of: receiving a command statement; parsing the command statement and comparing the parsing result with the corpus to determinewhether the command statement is an existing scene; if the command statement is an existing scenario, invoking the existing scenario; if the command sentence is not an existing scene, combining the corpus by the corpus combination system to form a new semantic scene, namely a user-defined scene, and the new semantic scene is stored in the corpus. By adding a corpus combination system between thesemantic analysis and the corpus, the invention can intelligently combine the scattered words in the corpus, thereby avoiding the phenomenon that the words cannot be hit due to the absence of the semantic scene, and generating the semantic scene required by the user.

Description

technical field [0001] The present invention relates to a method and system for customizing semantic scenes, in particular to a method and system for realizing user-defined operation modes of air conditioners applied to air conditioners, and through the method for determining semantic scenes to realize the user's self-definition of air conditioners The self-defined air conditioner of operating mode belongs to the technical field of corpus system expansion. Background technique [0002] A dialogue system is a computer system that can communicate with people. Its core is a semantic understanding unit, which often includes a huge text corpus. After the command sentence enters the semantic analysis system, it is identified, compared and matched with the corpus that contains the instruction set combination. After that, follow-up processing is performed on the semantic scenes that are successfully matched. [0003] However, the current dialogue system is to add a complete set of ...

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): G10L15/22G10L15/18F24F11/65
CPCF24F11/65G10L15/1815G10L15/22G10L2015/223
Inventor 康博贾巨涛尹兴东
Owner GREE ELECTRIC APPLIANCES INC
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