China’s village development confronts substantial challenges, inefficient land use due to the scattered village layout, sluggish development of village industries, and lack of proper planning for village development and construction, etc. Scientific classification of villages and village-based policy is the key to address these challenges. This study employs cell phone signaling big data to construct a population flow model based on particle swarm optimization algorithm This model takes into account spatial driving force and social connection strength as dual conditions. Also, it analyzes the settlement redistribution optimization scheme under the model through empirical research on Xiecun Township of Yuanping City, Shanxi Province, in order to classify villages scientifically and apply different strategies to village development according to the classification results. The findings of the study indicate that the area characterized by the densest distribution of optimized particle clusters, with good land conditions and high economic income, are classified as “cluster-enhanced villages”. Regions with the densest distribution of the initial particle distance factor and the densest distribution of optimized particle clusters are closer to the urban centers, which are better positioned to take advantage of the city’s financial and technological resources and continuously improve the added value of agricultural products, so they are classified as “peri-urban integrated villages”. Areas characterized by sparse distribution of optimized particle clusters need to actively cultivate the advantageous and characteristic industries in the countryside, and bolster transportation conditions and the protection of local culture, so as to realize the green development of urban and rural regional economy. Such areas are classified as “characteristic conservation villages”. In areas without optimized particle cluster distribution or areas with extremely sparse distribution of optimized particle clusters, the rational layout of urban and rural settlement spatial organization should be vigorously promoted, with emphasis on the enhancement of ecological environment, and they are classified as “relocated and annexed villages”. According to the results of village classification, corresponding strategies to promote the development of different types of villages are proposed in terms of spatial optimization, industrial upgrading and planning.

With the advent of the big data era, China’s higher education industry is facing a severe test. Using big data to optimize school edu_x005fcation management is an important measure for schools to demonstrate “people-oriented”, drive value with data, adapt to social development needs, and improve their own educational efficiency. In the context of big data, the management of student education in Chinese universities is developing towards a scientific, comprehensive, and personalized direction. Students should actively adapt to this situation, starting from building a solid platform foundation, improving the information literacy of management personnel, and strengthening security protection, effectively improving the quality and efficiency of student management work in higher education.

With the development of science and information, building an informatized army in a big data environment and building military data science has become the strategic goal of China’s military construction. To realize this goal, it is necessary to obtain the data advantage. As a result, the level of military data science construction has become an important symbol to measure the capacity of military informatization. For this reason, the article puts forward the idea of constructing the basic theoretical framework of military data science from three perspectives in view of the necessity of carrying out the exploration of military data science construction under the big data environment.

The era of big data has provided unprecedented educational opportunities. In recent years, with the deepening of education reform, the higher education model has changed fundamentally. Therefore, it is necessary to further improve the teaching leadership of teachers and cultivate qualified talents. This paper discusses the necessity of improving the teaching leadership in the background of big data, and discusses the effective measures to improve the teaching leadership in the era of big data.