Unlock instant, AI-driven research and patent intelligence for your innovation.

Construction method of automatic classifier and method for identifying decision from software development text product

A technology of software development and construction method, which is applied in unstructured text data retrieval, character and pattern recognition, text database clustering/classification, etc. It can solve the problems of poor extraction effect and inability to extract effective information, and achieve good performance Effect

Active Publication Date: 2020-09-15
WUHAN UNIV +1
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention proposes a method for constructing an automatic classifier and a method for identifying decision-making from software development text products, which are used to solve or at least partially solve the technical problem that effective information cannot be extracted or the extraction effect is poor in the existing methods of the prior art

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
  • Construction method of automatic classifier and method for identifying decision from software development text product

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] The present embodiment provides a kind of construction method of automatic classifier, and this method comprises:

[0062] S1: Analyze the sentences in the software development text products, and identify the decision-making sentences and non-decision-making sentences. The decisions in the decision-making sentences include design decisions, demand decisions, management decisions, implementation decisions, and test decisions. Create a data set for automatic identification of decision-making based on the decision-making sentences and non-decision-making sentences;

[0063] S2: Preprocess the sentences in the data set, and use a variety of natural language processing methods to obtain effective sentence information corresponding to each natural language processing technology from the preprocessed data set;

[0064] S3: For the data set processed by S2, various feature extraction methods are used to extract the features of each sentence;

[0065] S4: Process the extracted ...

Embodiment 2

[0122] Based on the same inventive concept, this embodiment provides a method for identifying decision-making from software development texts, using the automatic classifier constructed in Embodiment 1 to identify decisions from software development texts to be decided.

[0123] Specifically, this embodiment is a specific application of the classifier. After the classifier is constructed in Embodiment 1, the constructed classifier can be used to make a decision on the recognition of the software development text product to be recognized.

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 construction method of an automatic classifier and a method for identifying a decision from a software development text product. The method comprises the following steps: 1,manually analyzing sentences in the software development text product, identifying decision sentences and non-decision sentences, and creating a data set for automatically identifying the decision; 2,preprocessing each sentence in the data set by using a plurality of data preprocessing technologies; 3, extracting text features by using a plurality of feature extraction technologies; 4, classifying the sentences by using a plurality of classification algorithms; and 5, combining different data preprocessing technologies, feature extraction technologies and classification algorithms in the steps 2, 3 and 4 to construct different classifiers. The method has the advantages that sentences in software development text products can be automatically classified, and a foundation is laid for employees to develop a system, and guidance is provided for software decision analysts.

Description

technical field [0001] The invention relates to the technical field of software engineering, in particular to a method for constructing an automatic classifier and a method for identifying decision-making from software development text products. Background technique [0002] When dealing with a large amount of data, the time cost for humans to manually analyze the data and mine the effective information they need is almost unacceptable. However, with the continuous development and improvement of machine learning, researchers and practitioners in various industries began to apply automation technology to obtain meaningful information from a large amount of data, and obtained considerable results. In this context, using automation technology to process a large amount of text information has become an important trend in the field of software engineering. [0003] Identifying decisions from software development textual artifacts is an important task in software engineering. Du...

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): G06F40/211G06F40/284G06F16/35G06K9/62
CPCG06F40/211G06F40/284G06F16/35G06F18/24155G06F18/2411
Inventor 梁鹏李雪莹滕峰杨晨王思嘉
Owner WUHAN UNIV