تجزیه و تحلیل تجربی در برنامه ریزی برنامه های آموزشی خودکار شرکت توسط تکنیک های داده کاوی
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|22196||2011||10 صفحه PDF||سفارش دهید||4660 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 38, Issue 5, May 2011, Pages 5841–5850
Under limited resources in corporation education training, to enhance human resources quality, making education training program planning more efficient is a significant issue in training future talents. In accordance with Taiwan TrainQuali System (TTQS), the basic training structure is ton specify P (Plan) and D (Design). Ensuing results will be easier and successful. From TTQS database of Bureau of Employment and Vocational Training, corporations in Taoyuan, Hsinchu and Miaoli winning Gold Medals (Group B) have gaps outside control line in P and D. Enhancement is needed in the gap. The paper aims at a certain company winning Gold Medals in Taoyuan, Hsinchu and Miaoli to locate hidden or unobvious information with data mining, which will help future education training course planning and design. The researchers use two-stage clustering (SOM and K-means) under data mining theory to collect personnel training data of Automobile Corporation A in Taiwan and China with data mining and analysis. The results under the two algorithms will serve as reference for future education training courses. In the end, in combination of back-propagation neural network to develop education training prediction model, the research offers reference for writing knowledge management system to enhance effects of personnel participation in training at corporations.
According to Lee and Wu (2007), in the knowledge economy age of the 21st century, talents are the major asset of an organization and the foundation to maintain competence: employees’ knowledge and skill levels decide the operation performance of a company. Whether investment of a company in training truly helps enhance employees’ competence and generates actual effects to reach the operation goal is the major evaluation of training results and the issue that enterprise owners and managerial persons care about. Cascio (1991) pointed out that, in human resources accumulation, scholars believed education training was the most direct investment tool in human resources. Lee (1997) believed human resources development focused on talent development and training as well as organization growth. To avoid waste of resources or becoming superficial work, a lot of corporations were concerned about how to build an education training mechanism to improve organization performance and enhance productivity ( Carlson, Bozeman, Kacmar, Wright, & McMahon, 2000). The researcher wishes to conduct analysis and evaluation with effective use of the database. With manpower prediction evaluation model, current education training model is modified and education training system is established to obtain most suitable prediction model to offer suggestions for employee education training, enhance employee categorization accuracy and reduce waste of human resources while improving efficiency of training course planning. The researcher analyzes variables of the case company education training database department category, employee ranks, and courses available. With data mining, the relation was understood. The researcher attempted to reach the following goals: 1. Analyzing past education training data with SOM and K-means to locate type of courses in the same nature as reference of future training course planning. 2. Establishing education training prediction model to explore training performance in light of practical viewpoints. 3. Verifying practical feasibility of education training prediction model in manufacture industry.
نتیجه گیری انگلیسی
The paper integrated SOM and K-means algorithms. Courses were divided into three classes. In the future, courses in similar nature can be arranged in a set of training courses to enhance education training effects to enable employees to take courses systematically, increase qualification rate, match job details and employees’ specialties and ambitions for higher job efficiency. In performance matrix, each unit still required to be improved. Production Management and Management Improvement were important to the production unit and required to be improved first. Marketing unit had most courses exceeding control limit. Core Function Training almost exceeded control limit. More resources were recommended to improve current conditions; in China, unit heads could improve courses that went over control limit. For example, production unit supervisor could add more resources in Development Management, Human Resources Management and Information Management to improve current conditions. With back-propagation neural network in data mining, prediction classification accuracy reached over 80% in Taiwan and China. Employees’ information could be put into data and analysis results of preceding training courses will serve as foundation of future course arrangement. Neural network could process a great amount of data in high speed and accuracy. The prediction model can be developed into a set of knowledge management system to get closer to practical needs. The researcher used data mining technology in scientific methods to extract human resources unit past decision experience and employee education training results into useful information and laws. In the future, entering employees’ education, age, seniority, ranks, departments and genders, training center personnel will be able to plan courses with benefits of system improvement and education training and will not be affected by personal emotions to make high efficiency education training courses.