With the popularization of computer and communication technologies, researchers have attempted to develop computer-assisted testing and diagnostic systems to help students improve their learning performance on the Internet. In developing a diagnostic system for detecting students' learning problems, it is difficult for individual teachers to address the exact relationships between the test items and the concepts. To cope with this problem, this study proposes an innovative approach to eliciting and integrating the weightings of test item-concept relationships from multiple experts. Based on the proposed approach, a testing and diagnostic system has been implemented; moreover, an experiment was conducted to evaluate the performance of our approach. By analyzing the results from four groups of students using learning suggestions provided by different models, it was found that the learning performance of the students who received learning suggestions by applying the innovative approach was significantly better than for those who received guidance based on the original model. (Contains 5 tables and 6 figures.)