Research On APP Software Defect Identification Method Based On User Feedback

At present,with the wide application of APP software,its quality is more and more concerned.App software is the software installed on the mobile intelligent terminal.Due to the popularity of mobile intelligent devices,the number of APP software has exploded,resulting in uneven quality of APP software.After the user has used the app software,some users will evaluate and grade the usage of the software.They are generated from different devices and different operating systems,which are user feedback on the usage of the app software.Many quality problems of APP software,such as slow response,black screen,crash,flash back,etc.,have been mentioned in a large number of user feedback.Therefore,mining the software defects in the feedback of APP users can provide reliable and objective analysis results for the later maintenance personnel of APP software.Although many scholars at home and abroad have made some achievements in the research of defect recognition in user feedback,there are still some problems worthy of further study,such as the large difference of common domain words and inapplicability of methods,which are: 1)currently,defect recognition based on user feedback is mostly oriented to a certain product or based on English context,which is applicable to general products Most of the researches on defects of APP software based on user feedback are mentioned from the perspective of user demand and satisfaction,and the granularity of research is too large for identifying defects of APP software;3)the existing software defect classification methods are used in the defect classification and analysis of APP software based on user feedback,which will result in The current scope is too large to apply.In view of the above problems,in order to obtain the defect information of APP software from a large number of user feedback,the main work of this paper includes:(1)According to the characteristics of APP user feedback,this paper puts forward the process of identifying and analyzing app software defects in user feedback,and proposes the method of combining user rating stars,defect words and defect sentence patterns to screen user comments with app software defects.(2)The defect structure of APP software is established to identify the defect of APP software in user comments.Due to the large amount of data and the large number of defect words in app user comments,this paper presents a method to update the defect words and defect structure.(3)Refer to other software defect classification methods,analyze the types of APP software defects in user comments,classify the app software defects,and grade the severity.(4)The prototype of APP software defect recognition system based on user feedback is implemented,and the feasibility and effectiveness of the whole method proposed in this paper are verified by experiments.