Product Launch | The Transportation Big Data Training Lab empowering universities to cultivate versatile big data talents

The practice of transportation big data collection and processing includes five modules: data collection environment preparation, real-time business data collection, preprocessing of traffic flow data, synchronization of traffic accident data. It involves large-scale spatiotemporal data collection, real-time processing, and offline analysis, and utilizes appropriate technologies and tools to process and store data related to vehicle flow, speed, vehicle types, etc.

The practice of trasportation big data analysis and visualization includes seven modules: development of traffic flow data, real-time analysis of traffic flow data, analysis of traffic accident data, analysis of crowd spatial trajectory data, data source connection and dataset creation, MySQL data chart design and rendering, ClickHouse data chart design and rendering. It covers data integration and correlation, MySQL data correlation analysis, Flink real-time stream processing and window functions, ClickHouse data storage, Python data analysis, and Superset data visualization display, and other relevant technologies.

Through this project practice, students will understand the business meaning of traffic data and use data mining algorithms to discover valuable information and patterns hidden in the data. They will also learn how to present the findings using appropriate charts and visualizations. Students will become proficient in using technologies and tools such as Xshell, Xftp, Navicat, IDEA, MySQL, Hadoop, Kafka, ZooKeeper, JDK, Flink, FlinkCDC, Hbase, Phoenix, ClickHouse, Superset, Redis, Python, etc. This will enhance their problem-solving skills and proficiency in practical operations.

The practice of building and deploying the transportation big data platform aims to master the installation and configuration of Flink+ClickHouse and related components. It includes the installation and configuration of distributed storage system Hadoop and HDFS, real-time stream processing framework Flink, distributed columnar storage database HBase, relational database engine Phoenix based on HBase, real-time data transmission and processing tool Kafka, database ClickHouse for storing real-time analysis results, and in-memory database Redis, etc.

Through this project practice, students will gain hands-on experience and understand the installation requirements and steps of various tools. They will become familiar with setting and adjusting configuration files. Additionally, students will acquire the ability to solve problems and troubleshoot issues, enabling them to experience and master the basic tasks and related technologies involved in implementing and operating big data applications. Students will become proficient in using Linux, JDK, Hadoop, HDFS, YARN, Kafka, Redis, HBase, Flink, Phoenix, ClickHouse, and other technologies, enhancing their problem-solving skills and proficiency in practical operations.

The design of the practical teaching system in the training room is based on Neuedu's TOPCARES educational methodology. It is compatible with the talent cultivation system for big data and related majors in universities. The system incorporates elements of "new theories, new technologies, new tools, new applications, and new products" to provide a practical platform and industry project resources for the construction and reform of the practical teaching system in the fields of data science, big data technology, and computer science and technology with a focus on big data.

Students will gradually complete the practical arrangements based on the practical requirements and task steps assigned by the teacher. They can also learn and refer to the provided project documentation, enabling them to "learn by doing and do by learning."

Real-time statistics are conducted on various data including process tracking records, result data analysis, learning behavior data, practical training data, and performance data to comprehensively evaluate the teaching effectiveness of the course.
These data are collected and analyzed to provide a more detailed representation of students' mastery of specific skill points. This is achieved through the real-time statistical analysis of tiered scores in practical training, allowing for a more comprehensive presentation of the course's teaching effectiveness.

Constructing a practical skill-point and talent-job adaptive matching based on the target job competency model and core competency requirements enables students to have a model-based understanding of their abilities, intelligent learning, visualization of achievements, monitoring of the learning process, evaluation of talents, and matching them to suitable job positions.