Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Software function demand classification method and system based on semantic hierarchical clustering

A technology of hierarchical clustering and software functions, applied in semantic analysis, computer components, natural language data processing, etc., can solve problems such as unintuitive accuracy, difficulty in grasping, and poor classification effect, and achieve intuitive classification effect and high classification number Adjustable, efficient effect

Pending Publication Date: 2021-02-26
JIANGSU XCMG CONSTR MASCH RES INST LTD
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the construction machinery industry mainly adopts manual classification for the classification of text function requirements, and the classification effect is poor. In view of the characteristics of many types of construction machinery and relatively accurate classification requirements, if there is no efficient and accurate classification method, only relying on manual classification is not only unintuitive Accuracy is also difficult to grasp

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
  • Software function demand classification method and system based on semantic hierarchical clustering
  • Software function demand classification method and system based on semantic hierarchical clustering
  • Software function demand classification method and system based on semantic hierarchical clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as Figure 1-5 As shown, a classification method of software functional requirements based on semantic hierarchical clustering is provided, including:

[0048] Step 1. Organize the functional requirements text into a standard text with nouns and verbs;

[0049] Since the collected requirements are stakeholder requirements expressed in natural language, the text description is relatively free and irregular, so it needs to be processed, specifically converted into a standard text with verbs plus nouns or nouns plus verbs. For example, stakeholder needs are: Diagnosing failure modes based on collected data can be transformed into diagnostic failure modes.

[0050] Step 2, segmenting the standard text after finishing;

[0051] To perform cluster analysis on Chinese texts, we first need to segment the text, for example, "winding pressure", we hope to segment it into "winding pressure". Python provides a special Chinese word segmentation tool "jieba", which can divide...

Embodiment 2

[0076] A classification system for software functional requirements based on semantic hierarchical clustering is provided, including:

[0077] Bag-of-words model modeling module: used to organize the functional requirement text into a standard text with nouns and verbs; perform word segmentation on the organized standard text; build a bag-of-words model on the text after word segmentation;

[0078] Cluster calculation is used to convert the word bag vector in the word bag model into a weight vector;

[0079] Perform cosine similarity calculation on the converted weight vector;

[0080] Cluster the weight vectors after cosine similarity calculation.

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 software function demand classification method based on semantic hierarchical clustering. The method comprises the following steps: arranging a function demand text into a standard text of noun adverbs; performing word segmentation on the sorted standard text; constructing a bag-of-words model for the text after word segmentation; converting a bag-of-words vector in the bag-of-words model into a weight vector; and carrying out cosine similarity calculation on the converted weight vector. Weight vector is clustered after receiving cosine similarity calculation. According to the method, the characteristics that a hierarchical clustering algorithm is high in calculation capacity, high in efficiency and adjustable in classification number are utilized, and the classification effect is visually and accurately displayed.

Description

technical field [0001] The invention belongs to the technical field of software requirement classification, and in particular relates to a method and system for classifying software function requirements based on semantic hierarchical clustering. Background technique [0002] With the increasingly intelligent, networked, digital and other functions of the construction machinery industry, and there are many types of models, the demand text described in natural language is also increasing. The quality of the demand text processing determines the development of construction machinery software. quality. However, the current processing method of demand text is still in the stage of manual classification. Manual classification has the disadvantages of high requirements for human classification experience, incomplete domain knowledge, large subjective influence, low classification efficiency, and difficulty in accurate classification. Accurate and efficient classification is the m...

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): G06F40/30G06F40/289G06K9/62
CPCG06F40/30G06F40/289G06F18/231G06F18/2413G06F18/22
Inventor 张腾飞刘建褚福常
Owner JIANGSU XCMG CONSTR MASCH RES INST LTD
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
Eureka Blog
Learn More
PatSnap group products