arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1007.5126cs.SE
收藏

需求变更返工努力的检验研究

Examining Requirements Change Rework Effort: A Study

Bee Bee Chua, June Verner

摘要:

虽然软件经理通常擅长新项目的评估,但是他们的返工计划经验往往很差。不一致或不正确的工作量估计会增加项目完成时间有问题的风险。在软件维护过程中不断地改变软件维护计划是一项艰巨的任务。我们提出的框架,在一个案例研究中验证,证实了需求变化所产生的变量遭受了一些问题,例如,使用的编码、最终用户参与和用户文档。我们的研究结果清楚地表明,由于意外错误与以下因素相关,对返工工作产生了重大影响:1)程序源代码行中描述的弱特性和属性,特别是在数据声明和数据语句中,2)开发人员和用户之间缺乏关于更改效果的沟通,以及3)用户文档不可用。为了控制返工工作,提出了变更请求表中的新标准。这些标准显示在一个建议的框架中;验证的案例研究越多,在确定工作量返工估计的结果时,结果就越可靠。

英文摘要:

Although software managers are generally good at new project estimation, their experience of scheduling rework tends to be poor. Inconsistent or incorrect effort estimation can increase the risk that the completion time for a project will be problematic. To continually alter software maintenance schedules during software maintenance is a daunting task. Our proposed framework, validated in a case study confirms that the variables resulting from requirements changes suffer from a number of problems, e.g., the coding used, end user involvement and user documentation. Our results clearly show a significant impact on rework effort as a result of unexpected errors that correlate with 1) weak characteristics and attributes as described in the program's source lines of code, especially in data declarations and data statements, 2) lack of communication between developers and users on a change effects, and 3) unavailability of user documentation. To keep rework effort under control, new criteria in change request forms are proposed. These criteria are shown in a proposed framework; the more case studies that are validated, the more reliable the result will be in determining the outcome of effort rework estimation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑