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

Method for training man-machine interaction system based on natural intelligence

A human-computer interaction, natural technology, applied in the field of human-computer interaction system training, can solve the problems of inability to achieve semantic understanding, large labor costs, and high difficulty

Pending Publication Date: 2019-07-26
ICONTEK CORP
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, a sentence has 10 words, and the speech recognizer can achieve 90% accuracy, but if the error occurs in the key words (words), then the existing AI-NLP technology cannot achieve correct semantic understanding
In particular, in a noisy environment, since the accuracy of the speech recognizer will drop, it is more difficult to use AI-NLP technology to accurately understand semantics
On the other hand, since AI-NLP needs to manually build a large number of grammatical models and semantic models, it will generate huge labor costs

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 for training man-machine interaction system based on natural intelligence
  • Method for training man-machine interaction system based on natural intelligence
  • Method for training man-machine interaction system based on natural intelligence

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0153] Example 1: FSBNK27100000000860109558800000000000000000002zh-CN003

[0154] in,

[0155] The industry code is,

[0156] ·FS=Financial Service (main industry)

[0157] ·BNK=Bank (sub-industry)

[0158] The industry business code is,

[0159] ·2710000000=First-level industry business scope—2 (credit card)Secondary industry business scope—7(Adjustment of credit limit) Third-level industry business scope—1(Increase of credit limit)0000000(No more subdivided categories)

[0160] The institution code is,

[0161] 086010955880000000000000=country number 086 (China) 010 (Beijing) 955880000000000000 (ICBC Head Office)

[0162] Institution business code is,

[0163] 00000=no institutional business category (In this Y language information, there is no institutional business category defined by the institution "Industrial and Commercial Bank of China Headquarters", which means: this Y language information completely belongs to the industry business category and is common to th...

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 training a man-machine interaction system based on natural intelligence. The method comprises the steps of generating a character script corresponding to standardexpression, obtaining voice corresponding to the text script through a text voice conversion tool; converting each voice into secondary language information, wherein the magnitude order of the information granularity of the secondary language information is smaller than that of the information granularity of the characters; storing the secondary language information and the standard expression corresponding to the secondary language information in a database as pairing data; for existing paired secondary language information and standard expression in a database, the loop iteration is carriedout on various permutation combinations of the elements of the secondary language information and the standard expression or various permutation combinations of the elements of the standard expression; and a corresponding relationship is established between various permutation combinations of the elements of the secondary language information and various permutation combinations of the standard expression or / and the elements of the standard expression, more pairing data of the secondary language information and the standard expression are obtained, and the pairing data is stored in a database.

Description

technical field [0001] The present invention relates to a method for training a human-computer interaction system, in particular to a method for training a human-computer interaction system based on natural intelligence, as well as corresponding human-computer interaction equipment and human interaction system. Background technique [0002] Currently commonly used machine intelligence (MI, Machine Intelligence) technology mainly includes artificial intelligence (AI, Artificial Intelligence) technology. One of the more common ones is artificial intelligence-based Natural Language Processing (NLP, Natural Language Processing) technology. [0003] For natural language processing based on artificial intelligence (also referred to as AI-NLP for short), for the processed speech, it is necessary to convert speech from speech to text first, and then realize semantic understanding through the established grammatical model and semantic model. However, this approach is limited by the ...

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): G06F16/332G06F17/27G06Q30/02G06N3/04G06N3/08G10L15/18G10L15/22
CPCG06F16/3329G06Q30/0281G06N3/08G10L15/22G10L15/1822G06F40/30G06N3/045
Inventor 不公告发明人
Owner ICONTEK CORP
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com