A mining method for app software user comments that reflect user intent

A technology of user comments and user intentions, applied in special data processing applications, instruments, calculations, etc.

Active Publication Date: 2022-05-17
KUNMING UNIV OF SCI & TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

How to accurately and efficiently obtain constructive APP software user intentions and fully mine the valuable information in software user comments is a problem that needs to be solved urgently in view of the large scale and fast update of user comment data.

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
  • A mining method for app software user comments that reflect user intent
  • A mining method for app software user comments that reflect user intent
  • A mining method for app software user comments that reflect user intent

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Example 1: as Figure 1-8 As shown, a method for mining user comments of APP software that reflects user intentions. First, the extraction rules of evaluation objects and evaluation opinions are defined, and the comment seeds are initialized on the basis of extracting the evaluation objects and evaluation opinions of user comments. The same or similar user reviews that reflect the same user intent category; then, through able verbs, software introduction and sentiment analysis, the user reviews that reflect the user intent among the user reviews that fail to match the review seeds are mined, and the candidate review pattern library is constructed. ; Finally, a representative new comment seed is extracted from the candidate comment pattern library constructed in each loop mining process, which is used for the next loop mining to realize the loop mining of user comments that reflect the user's intention, until the user who reflects the user's intention. The mining effect ...

Embodiment 2

[0048] Example 2: as Figure 1-8 As shown in the figure, a method for mining user reviews of APP software that reflects user intent, the specific steps are as follows:

[0049] Step1. Initialize data: there is 1 (s=1) comment seed in the comment seed database, and there are 6 (c=6) user comments after word segmentation in the comment database, time=1, m=1; among which user comments As shown in Table 1:

[0050] Table 1 APP software user comment form

[0051]

[0052] Initialize a comment seed in the comment seed repository 1 : seed 1 =; when initializing the comment seed, the extraction rules for the evaluation object and evaluation opinion are as follows: the evaluation object is the target entity for the opinion holder to express the emotion, usually Consists of one or more words. Mainly for nouns, verbs, and their combined forms, the evaluation object part-of-speech combination rules are established to extract evaluation objects. The extraction rules are shown in Ta...

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 method for mining user comments of APP software aimed at reflecting user intentions, and belongs to the field of analysis of APP software user intentions. The present invention firstly defines the extraction rules of evaluation objects and evaluation viewpoints, initializes the comment seeds on the basis of extracting the evaluation objects and evaluation viewpoints of user comments, and uses the comment seeds to mine the same or similar user comments that reflect the same user intention category; then Mining user comments that reflect user intentions in user comments that fail to match comment seeds through functional verbs, software profiles, and sentiment analysis, and constructing a candidate comment pattern library; finally, for the candidate comment patterns constructed during each cycle mining process The library extracts representative new comment seeds for the next cycle mining to realize the cycle mining of user comments reflecting user intentions until the mining effect of user comments reflecting user intentions converges.

Description

technical field [0001] The invention relates to an APP software user comment mining method for reflecting user intention, and belongs to the field of APP software user intention analysis. Background technique [0002] With the wide application of smart terminals, APP software has developed rapidly. APP software is characterized by a short development cycle, fast update speed, and fierce competition among products of the same category. In the increasingly fierce market competition, user-driven software evolution has more practical significance. The online user reviews of APP software have become an important resource for the acquisition of software user intentions by virtue of the advantages of covering a wide range of users, rich in content, and strong timeliness. For example, in order to classify user reviews according to software maintenance and evolution categories, Grano et al. divided user intent into four categories: information giving, information search, feature re...

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 Patents(China)
IPC IPC(8): G06F40/205G06F40/289G06F16/335
Inventor 姜瑛胡甜媛丁家满李凌宇汪海涛
Owner KUNMING UNIV OF SCI & TECH
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