| With the rapid development of automobile industry in our country,the Internet of Vehicles technology has also developed rapidly.The application data of customers on the operation platform of Internet of vehicles is also increasing day by day.How to mine valuable information from the massive data,analyze the potential needs and hobbies of car owners,achieve fine and personalized operation service,and provide important digital operation service support for operators in Internet of vehicles business is a hot topic of current research.In this thesis,Sqoop,NiFi data acquisition technology and distributed data storage technology are applied to design and implement the big data platform of the Internet of Vehicles,and the improved collaborative filtering algorithm is applied to classify customers,and a valuable user label system is established.The main research contents are as follows:1.Based on the analysis of the actual development needs of the big data operation platform of the Internet of vehicles,this thesis focuses on the design and implementation of the Internet of Vehicles user label system based on collaborative filtering algorithm.According to the characteristics of the Internet of Vehicles user label,a label recommendation method based on collaborative filtering algorithm is proposed,and the corresponding design and implementation scheme is given.On this basis,combined with the overall goal of the big data operation platform of the Internet of Vehicles,the basic functional requirements such as real-time collection of on-board data,mass data storage and automatic expansion,and company operation index system were analyzed in detail,and the overall framework of the platform was designed,and the design ideas and functions of each module were given.2.Sqoop and NiFi data collection methods were adopted to realize the platform structured data collection and Jasper platform vehicle networking data collection;HDFS distributed file system,HIVE data warehouse,Star Rocks database,and Mysql relational database are used for data storage.Spark is used to process and analyze related data logic.The data from the analyzed iot user tags is then stored in Star Rocks;At the same time,collaborative filtering algorithm is applied to the generated label data to establish user label recommendation.Finally,Yonghong BI is applied to visualize the company’s operation indicator system and the user label system of Internet of vehicles.3.Based on the big data operation platform of Internet of vehicles implemented in this thesis,analyze the company’s internal e-commerce data,Internet of vehicles user data,card consumption data,logs and other data.The practical application shows that this thesis explains the application value of the big data operation platform of the Internet of vehicles to operators in the development of the Internet of vehicles business from the aspects of the company’s Internet of vehicles operation index system,Internet of vehicles user label system and so on,and provides effective suggestions for operators to expand the Internet of vehicles business. |
