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

Semantic comprehension method, device and equipment and computer readable medium

A semantic understanding and computer technology, applied in the field of electronic information, can solve the problem of inaccurate understanding of sentences with multiple intentions

Active Publication Date: 2018-09-21
IFLYTEK CO LTD
View PDF8 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a semantic understanding method, device, device, and computer-readable medium, with the purpose of solving the problem of inaccurate understanding of multi-intent sentences

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
  • Semantic comprehension method, device and equipment and computer readable medium
  • Semantic comprehension method, device and equipment and computer readable medium
  • Semantic comprehension method, device and equipment and computer readable medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0101] Example 1: Turn on the air conditioner to play Anhui traffic radio

[0102] pos

example 2

[0103] Example 2: Navigate to Wanda Plaza and choose the fastest route

[0104] pos

example 3

[0105] Example 3: Check the price of No. 92 gasoline

[0106] pos

check

Inquire

One

under

92

number

steam

oil

of

price

grid

pos

pos

pos

pos

s

s

s

s

s

s

s

s

s

s

s

pos

[0107] Take Example 1 as an example. In the field label cmd_b corresponding to "打", cmd represents the name of the field category: command control, and b means that the position occupied by "打" in all words belonging to the cmd field is the starting position, that is, " Hit" is the first word in the cmd field.

[0108] In Example 3, the domain classification of each word is not determined, so the output is s.

[0109] Based on the first position information, it can be seen that after the domain label of each word is obtained, the first type of clause is divided.

[0110] In this embodiment, each word can be used as a vector to enter the domain discrimination model, and the length of the vector can be 100.

[0111] In the tables in each of the above examples, POS stands for separ...

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 a semantic comprehension method, device and equipment. According to preset domain classification, a to-be-understood statement is divided into a first kind of clauses, then according to preset intension classification, each first kind of clause is divided into a second kind of clauses, lastly, slot information is extracted from each second kind of clause, wherein each firstkind of clause belongs to a classification in the domain classification, and each second kind of clause belongs to a classification in the intention classification. The semantic comprehension method and device have the advantages that different dividing dimensions are adopted, according to a mode of dividing causes step by step, the slot information under multiple domains and multiple intentions can be obtained, so an understanding result of the more accurate multiple intentions can be obtained according to multi-intention statements.

Description

Technical field [0001] This application relates to the field of electronic information, in particular to a semantic understanding method and device, equipment, and computer readable medium. Background technique [0002] With the continuous breakthrough of artificial intelligence technology and the increasing popularity of various smart terminal devices, human-computer interaction appears more and more frequently in people's daily work and life. As one of the most convenient ways of interaction, voice interaction has become an important means of human-computer interaction. The human-computer interaction dialogue system is used in various smart terminal devices, such as: TVs, mobile phones, vehicles, smart homes, and robots. How to understand the user's intention is the most critical technology in the human-computer interactive dialogue system. [0003] Due to the diversity, complexity and ambiguity of human language, a sentence can often express multiple intentions. However, the c...

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): G06F17/30G06F17/27
CPCG06F40/289G06F40/30
Inventor 王兴宝蒋亚冲雷琴辉黄倪莎
Owner IFLYTEK CO LTD
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