Business logic code-free development method based on natural language understanding and conversion

A technology for natural language understanding and code development, applied in the field of codeless development of business logic based on natural language understanding and transformation, it can solve problems such as less research on system function modules, reduce development thresholds, improve development efficiency, and reduce software development. and maintenance costs

Active Publication Date: 2021-12-14
716TH RES INST OF CHINA SHIPBUILDING INDAL CORP +1
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, there are many studies on generating front-end codes (such as pix2code, sketch) based on images, but there are few studies on how to quickly and automatically build system function modules based on the interaction mode of natural language

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
  • Business logic code-free development method based on natural language understanding and conversion
  • Business logic code-free development method based on natural language understanding and conversion
  • Business logic code-free development method based on natural language understanding and conversion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] Example 1, a code-free development method for business logic based on natural language understanding and conversion:

[0089] The first aspect is the development semantic extraction driven by natural language understanding. The core of development semantic extraction driven by natural language understanding is to extract key development elements for the next step of component matching. The invention treats the automatic extraction of key development elements in the natural language description as a sequence labeling problem. Through supervised training on massive natural language descriptions with annotations and code-free development requirements corpus, an efficient, high-accuracy, and high-generalization development semantic extraction model can be obtained. The model uses the BERT (Bidirectional Encoder Representation from Transformers, BERT) method to map the high-dimensional One-Hot Encoding (One-Hot Encoding) vector representing a word in a high-dimensional spac...

Embodiment 2

[0100] Example 2, an experiment of a code-free development method for business logic based on natural language understanding and transformation:

[0101] The code generation process is as follows figure 1 shown. Below, the implementation process of the method of the present invention is divided into four parts and explained in detail.

[0102] (1) Development Semantic Extraction Driven by Natural Language Understanding

[0103] In the present invention, the text input by the user has problems such as sparse text features, a small number of words but a large amount of information, complex semantics, and complex context. To solve this problem, the present invention adopts an intention recognition model of a bidirectional long-short-term memory network combined with an attention mechanism for semantic recognition.

[0104] Such as figure 2 As shown, suppose the input sequence is X=[x 1 , x 2 ,...,x n ], input X into the BiLSTM layer, and the hidden states before and after...

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 a business logic code-free development method based on natural language understanding and conversion, and belongs to the technical field of code-free development. On one hand, development semantic extraction driven by natural language understanding is carried out; key development elements in the natural language description are automatically extracted to serve as a sequence labeling problem to be processed; and supervised training is performed on massive tagged code-free development demand corpora described by natural languages to obtain a development semantic extraction model. On the other hand, a natural language code generation task is is performed; after the intention of the user is analyzed, the metadata is sent into a model engine, and a corresponding code generation model is called by the model engine; and the code generation task is converted into a machine translation task. The method can reduce the software development and maintenance cost, improve the development efficiency, reduce the influence of demand change on the system and prolong the life cycle of the system.

Description

technical field [0001] The invention relates to the technical field of code-free development, in particular to a code-free development method for business logic based on natural language understanding and transformation. Background technique [0002] The traditional integrated development environment (Integrated Development Environment, hereinafter referred to as "IDE") adopts various descriptive text languages. Development and progress, also began to appear some demand defects. On the one hand, in the process from development to production, the demand for participating workers is increasing, attracting a large number of non-software professionals in different fields. [0003] this [0004] Some non-professional users need a fast and convenient way to integrate into the development process as soon as possible; on the other hand, the development of software text language also affects the development efficiency of software developers to a certain extent. The probability of ...

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): G06F8/41G06F8/38G06N3/04G06N3/08
CPCG06F8/427G06F8/38G06N3/049G06N3/08G06N3/045Y02D10/00
Inventor 刘彩云胡昌平侍守创朱大鹏孟祥慈李红星王纪潼姜厚禄闫四洋胡翔宇徐雷左刚单文金吕从飞尹玉峰韩占港许永正董奇
Owner 716TH RES INST OF CHINA SHIPBUILDING INDAL CORP
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap