Abstract: Soccer tactical analysis based on the positional data has shown that the team centroid method can be used to determine the geometric center of the team, space control can calculate individual playing area and dominant region, network analysis can measure the team's pass behavior, and machine learning algorithms can automatically identify the characteristics of team tactics. Given that the big data technology is promoting the study revolution in the field of soccer, the positional data can merely singly provide a spatial pattern analysis value, future research shall integrate varied information including training demands, cycle load, competition system, players' fitness and degree of fatigue. By virtue of processing and compressing data of physiology, psychology, position, coach, scout and audience into smaller variables in real time, coaches can be provided objective information and promote the prediction of performance results to some extent after data visualization and reporting. As a result, the new AI method of big data technology stack and deep learning technology is expected to provide a new approach for the study of soccer tactics.