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

Short text semantic comprehension template generation method and semantic comprehension processing method and device

A technology for semantic understanding and template generation, applied in the field of natural language semantic understanding, it can solve problems such as insufficient support for actual production use, low accuracy of short text semantic understanding, and lack of actual production data.

Pending Publication Date: 2021-02-23
安徽迪科数金科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a short text semantic understanding template generation method, semantic understanding processing method and device, the purpose is to solve the lack of actual production data, in the prior art, the accuracy of short text semantic understanding is not high enough, and business integration is difficult, Not enough to support the problem of actual production use

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
  • Short text semantic comprehension template generation method and semantic comprehension processing method and device
  • Short text semantic comprehension template generation method and semantic comprehension processing method and device
  • Short text semantic comprehension template generation method and semantic comprehension processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The embodiment of the present application discloses a short text semantic understanding template generation method, semantic understanding processing method and device, which can be applied to electronic devices with human-computer intelligent interaction, such as smart dialogue, smart home and smart wearable devices.

[0082] In the following, the technical solution in the embodiment of the application will be clearly and completely described in conjunction with the accompanying drawings in the embodiment of the application, taking the intelligent collection robot system as an example. Obviously, the described embodiment is a part of the embodiment of the application, and Not all examples. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

[0083] figure 1 The short text semantic understanding template generation method disc...

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 short text semantic comprehension template generation method and device and a semantic comprehension processing method and device. The method comprises the steps of S1, collecting a first preset number of short texts to be subjected to semantic comprehension; S2, generating a preset basic semantic group set according to a first preset number of to-be-semantically understood short texts; S3, generating and / or optimizing a rule template set based on a first preset number of short texts to be semantically understood, and further generating and / or optimizing a matching template set corresponding to a preset basic semantic group set; and S4, generating a preset basic template group set corresponding to the preset basic semantic group set by combining the matching template set with the priority. According to the method, semantics contained in the short text to be semantically understood are divided into semantic groups which do not contain each other, and the understanding processing of the short text to be semantically understood expressed by the spoken natural language of the human port is realized in combination with the priority and the matching template, wherein various intentions of the short text are included, local semanteme is inconsistent with overall semanteme, and speech recognition causes processing of part of word errors.

Description

technical field [0001] The present application relates to the field of semantic understanding of natural language, in particular to a short text semantic understanding template generation method, semantic understanding processing method and device. Background technique [0002] Human-computer intelligent interaction through the recognition, understanding, and expression of human natural language has brought great convenience to people's lives. With the continuous improvement of speech recognition accuracy and generalization ability, human-computer intelligent interaction is gradually applied to various products and are familiar to the general public. One of the key technologies that affect the promotion and application and the public experience is the understanding of short texts of natural language after speech recognition. [0003] At present, short text understanding methods are roughly divided into methods based on matching templates and methods based on machine learnin...

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): G06F40/30G06F40/211G06F16/33G06F16/35
CPCG06F40/30G06F40/211G06F16/3344G06F16/35
Inventor 李晓霞
Owner 安徽迪科数金科技有限公司
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