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

Implementation method of universal semantic framework

A technology of general semantics and implementation methods, applied in the field of semantic recognition, can solve the problems of high development time cost and labor cost, waste of server resources, etc., and achieve the effect of reducing time cost and labor cost, and reducing waste.

Pending Publication Date: 2022-02-22
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problems of waste of server resources, high development time cost and labor cost in the existing semantic recognition framework, and proposes a method for realizing a general semantic recognition framework

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
  • Implementation method of universal semantic framework
  • Implementation method of universal semantic framework
  • Implementation method of universal semantic framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] The implementation method of the general semantic framework described in the embodiment of the present invention includes the following steps:

[0030] Step 1. When the framework starts for the first time, obtain the configuration components of each skill from Redis in the database, and check whether each configuration component conforms to the general configuration specification. The above configuration information is loaded into the Metadata of the framework, and corresponding error messages are generated for configuration components that do not conform to the general configuration specification;

[0031] Specifically, the framework in this embodiment adopts the Sanic startup method, such as figure 2 As shown, when the framework runs for the first time, the configuration components of each skill will be obtained from Redis in the database, and the specification check of each component will be performed. The components that pass the check will be loaded into the Inter...

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 relates to the technical field of semantic recognition, discloses an implementation method of a general semantic framework, and solves the problems of server resource waste and high development time cost and labor cost of the existing semantic recognition framework. The method comprises the following steps of: when a framework is started for the first time, obtaining configuration components of each skill from Redis of a database, checking whether configuration components conform to a general configuration specification, generating configuration information of corresponding skills for the configuration components conforming to the general configuration specification, and loading the configuration information to Metadata of the framework; calling a component initialization method to initialize the configuration components, and loading the configuration components into a memory after the initialization is completed; and developing an access interface, an addition skill interface, a deletion skill interface and an upgrade skill interface for the framework. The method not only reduces the waste of server resources, but also reduces the time cost and labor cost of development, and is suitable for semantic recognition.

Description

technical field [0001] The invention relates to the technical field of semantic recognition, in particular to a method for realizing a general semantic framework. Background technique [0002] The Rasa framework currently used for semantic recognition can undertake components such as caching, rules, and multi-rounds for semantic natural language understanding, and reply language components for dialogue management. Every time you optimize each skill iteration or launch a new skill, you need to stop the service and redeploy the project. When the following situations exist: you need to temporarily launch a time-sensitive skill (such as a holiday field), and you need to update it when the time limit expires. This skill is offline, and some skills need to be modified and adjusted frequently. Every time there is a small change, it needs to be re-deployed and online, which will affect the normal operation of the service. This not only wastes server resources, but also increases dev...

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): G06F40/30G06F40/205G06F16/33
CPCG06F40/30G06F40/205G06F16/3344
Inventor 童姝宇
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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