Our School Team Won the Bronze in "Digital Intelligence Service Innovation Challenge Service Scheduling Competition" of Ali Tianchi

    On December  5, 2020, the final of "Alibaba Cloud Digital Intelligent Service  Innovation Challenge-Service Scheduling Competition" jointly organized  by Alibaba and Zhejiang University was successfully held in Hangzhou.  Under the guidance of Zhu Zongwei, the teacher of the Intelligent Cloud  Computing Center of Suzhou Research Institute,University of Science and  Technology of China, our representative team, which composed of second  year master students Ding Juntao, Liu Weihong, Zhai Wenjie and Tang Xin,  won the bronze medal in the competition.

Photo 1 Awarding Scene of the Competition

This service  scheduling competition has won extensive attention from both the  industry and academic field, and quite a few professors and industry  elites have been invited to serve as judges, including Jin Li, vice  president of Alibaba group; Professor Genke Yang, executive director of  Ningbo Institute of artificial intelligence, Shanghai Jiaotong  University; Professor Zhijiang Shao, Dean of School of control science  and engineering, Zhejiang University; Chenghuang Shen director of  Alibaba cloud intelligent global technology service department;  Mengchang Wang, senior algorithm expert of machine intelligence  technology of Dharma Institute;Yin Zhang,senior of Artificial  Intelligence Department of newbird network Algorithm experts, etc

Photo 2 Our Team Representative Team

The  contest problem comes from actual business scenario where AliYun Cloud  provides full-cycle technical services to many companies, government  agencies, and developers around the world. Among them, service  scheduling optimization is one of the cores of improving customer  experience. However, in face of immense service volume, largely  differentiated regions and languages, diverse customer issues, complex  service scenarios, and technical personnel with their own strengths, how  to ensure the rapid distribution of massive service while being able  t.o efficiently match service scenarios with the capabilities of  technical experts is a difficult point in the service scheduling  optimization algorithm. This service scheduling competition focuses on  the combination of production, research and learning, and provides  valuable experience for the development of "digital intelligence  service" industry in China.

The  competition has lasted three months and have attracted 1381 teams from  more than 100 universities and enterprises, including Tsinghua  University, Peking University, University of Science and Technology of  China, Zhejiang University, Shanghai Jiaotong University, Nanjing  University, Xi'an Jiaotong University, Huazhong University of Science  and Technology, National University of Defense Technology, etc. Our team  proposes a task scheduling method combining particle swarm optimization  and shallow neural network. We constructed a new operator to replace  the complex nonlinear relationship of deep neural networks and used  particle swarm optimization to solve the difficult problem of BP back  propagation in NP problem. Our team proceeded to the final since we won  the sixth place in the preliminary round and topped at the third place  in the second round. In the final, our team has been awarded the bronze  medal with the total score ranking as the fourth.

Photo 3 Gathering of the Representatives of the Organizer and Contestants