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

Customized personalized semantic learning application method

An application method and personalized technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of slow recognition speed, inability to personalize recognition, and high error rate, so as to improve the recognition rate and recognition speed, realize Personalized recognition, the effect of reducing the error rate

Pending Publication Date: 2019-07-19
卢劲松
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous advancement of science and technology, semantic recognition technology has begun to be more and more applied to various smart terminals. However, due to various factors such as processor performance, algorithm model, and network bandwidth, the current semantic recognition is mainly for standard For complex situations such as various dialects or unclear pronunciation and inability to express through speech, there will be problems such as low recognition rate, high error rate, slow recognition speed, and inability to personalize recognition.

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
  • Customized personalized semantic learning application method
  • Customized personalized semantic learning application method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] The user first creates a personalized database and a common database, which contain the corresponding information of sound, text and images. The personalized database needs to be defined by the user, and the common database can use the existing database. When the user needs to express semantic information, the first input The information will first call the personality database for identification. If it is correctly identified, it will directly output the information; if it cannot be identified, it will automatically call the common database for identification. And choose whether to store the recognition result in the personality database, and output the semantic information after confirmation; if it cannot be recognized, the user needs to manually define the semantic information, and choose whether to store the recognition result in the personality database, and output the semantic information after confirmation; The process of storing the results in the personality dat...

Embodiment 2

[0030] The user first creates a personality database and a commonness database, which contain voice, sign language and their corresponding text information. The personality database needs to be defined by the user, and the commonness database can use the existing database. When the user needs to input sign language actions to express semantics , when you input your own body movement information through the image input device for the first time, it will first call the personality database for identification. If it is correctly identified, it will directly output the information; if it cannot be identified, it will automatically call the common database for identification. Output information; for partial recognition, the user needs to confirm whether the recognition is accurate, and choose whether to store the recognition result in the personality database, and output the semantic information after confirmation; if it cannot be recognized, the user needs to manually define the sem...

Embodiment 3

[0032] When users need to input their own specific voice or action to express semantics, they can input it through voice and image input devices, and then customize their semantics, and store the customized semantic information in the personality database to complete the learning process. When a specific voice or action is input again, the recognition result stored in the personality database will be called first for recognition, and then the corresponding semantic information will be output, and then translated into multiple languages ​​and texts as needed.

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 customized personalized semantic learning application method comprises the following steps: a) defining a personalized database; b) defining a common database; c) inputting information and callinga personalized database for identification; d) executing an operation according to the identification result of the personalized database; e) inputting information and calling a common database for identification; f) executing an operation according to a common database identification result; g) selecting whether the identification result is stored in a personalized database, executing the step aif the identification result is stored, and executing the step h if the identification result is not stored; and h) outputting corresponding semantic information. Compared with the prior art, the method has the advantages that sound, images, actions and the like can be converted into corresponding semantic information, specific sound, images and actions can be recognized into standard semantic information through custom semantics, semantic conversion between different types of information can be achieved, the recognition rate and the recognition speed can be effectively increased, the error rate is reduced, and personalized recognition is achieved.

Description

technical field [0001] The invention relates to the field of semantic recognition, in particular to the field of personalized customized semantic recognition learning. Background technique [0002] With the continuous advancement of science and technology, semantic recognition technology has begun to be more and more applied to various smart terminals. However, due to various factors such as processor performance, algorithm model, and network bandwidth, the current semantic recognition is mainly for standard For various dialects or complex situations such as unclear pronunciation and inability to express through speech, there will be problems such as low recognition rate, high error rate, slow recognition speed, and inability to personalize recognition. Contents of the invention [0003] Aiming at the above problems, the present invention provides an application method for personalized semantic learning that can be personalized and customized, and its technical scheme is a...

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): G06F17/27
CPCG06F40/30
Inventor 卢劲松
Owner 卢劲松
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