Research on the classification of dimensional performance and feature extraction of primary school students' core literacy in science curriculum

The core competency-oriented curriculum reform has become an important issue in the current education field. In order to objectively evaluate the development status of primary school students' core literacy in science courses, this study used cluster analysis method to classify students' core literacy in science and its four dimensions into three different development levels based on the interview performance of 235 students. The results of discriminant analysis show that there are significant differences between the three types of student groups, and the classification accuracy reaches 94.5%, which fully verifies the scientificity and reliability of the classification standard. On this basis, combined with the specific performance of various types of students, this study quantitatively and qualitatively described the primary school science core literacy and its four dimensions of development level, and further revealed the stage characteristics of the development of primary school science core literacy. In addition, based on the performance criteria that have been constructed, this study deeply explores the development trajectory of students' science core literacy. Through descriptive statistics, analysis of variance (ANOVA), chi-square test and multinomial logistic regression analysis, it was found that students 'performance in science core literacy and its four dimensions showed a progressive trend with the improvement of grade, and there were significant differences between different grades. Specifically, the lower grade students mainly performed at the first level, the middle grade students mainly performed at the second level, and the upper grade students mostly achieved the third level. This finding not only verified the growth law of science core literacy, but also provided empirical support for the phased training objectives of primary school science education. **************** ACKNOWLEDGEMENTS**************** Thanks for the data support provided by National-level Innovation Program Project Fund "Research on Seedling Inspection Robot Technology Based on Multi-source Information Fusion and Deep Network" (No.: 202410451009); Jiangsu Provincial Natural Science Research General Project (No.: 20KJB530008); China Society for Smart Engineering "Research on Intelligent Internet of Things Devices and Control Program Algorithms Based on Multi-source Data Analysis" (No.: ZHGC104432); China Engineering Management Association "Comprehensive Application Research on Intelligent Robots and Intelligent Equipment Based on Big Data and Deep Learning" (No.: GMZY2174); Key Project of National Science and Information Technology Department Research Center National Science and Technology Development Research Plan (No.: KXJS71057); Key Project of National Science and Technology Support Program of Ministry of Agriculture (No.: NYF251050).