This paper mines user behavior characteristics based on big data technology. This paper proposes a method for behavior slicing based on historical activity data, and insights into the personalized behavior characteristics. Firstly, the data is processed, and the classification is expanded on the basis of the parsed APP label types. Secondly, a time slicing method is proposed to reduce information loss, which integrates time, location, business type, and behavior into individual users. Then, based on slices of a day and a week, the paper analyzes user behavior and construct a portrait of user’s interest and preference. Finally, the periodic factor method is utilized to predict the behavior changes, forming the feature labels for users. Based on real business behaviors, this paper provides insight into user personality and effectively improves the authenticity and accuracy of prediction.

5G network consumes huge investment cost, including 5G network construction, 5G network operation and maintenance etc. Therefore, China Unicom and China Telecom take the initiative to jointly build the 5G network (wireless network sharing, independent construction mode of core network). Its aim is to reduce 5G overall investment cost, and rapidly realize the continuous and wide-area 5G service capability, as well as improve the network efficiency and asset operation efficiency. This paper focuses on the automatic data configuration model of 5G co-construction and shared base stations. By interacting with the core network and wireless network, this model can identify and match different 5G network modes such as SA and NSA (including dual-anchor scenarios and single-anchor scenarios). On this basis, the data required for automatic activation of the shared base stations is obtained from the wireless side and automatically configured on the core network side. This technology meets the practical needs of both sides for fast and efficient construction of 5G network. It can realize the automatic opening and fast on-line of co-construction and shared BS on the side of the core network.

EPS-Fallback is generally adopted for voice service in the coexistence period of 4/5G network. Its process is very complex and prone to failure. How to guarantee users perception is an important challenge. Based on multi-resources data, this paper proposes a fault diagnosis method for EPS-Fallback. It can effectively improve the fault diagnosis ability and the efficiency of network operation and maintenance. Also, it can save labor costs.