NL2SQL (natural language to structured query language) task aims to translate natural language queries into SQL (structured query language) executable by the database. A Chinese cross-domain NL2SQL algorithm enhanced by auxiliary tasks was proposed. Core idea was to perform multi-task training and improve the accuracy of the model by adding auxiliary tasks in the decoder and combining the prototype model. Auxiliary task was designed by modeling the database schema into a graph, predicting the dependency relations between the natural language queries and the nodes in the database schema graph, and explicitly modeling the dependency relations between the natural language query and the database schema. Through the improvement of auxiliary tasks, the model can better identify which tables/columns in the database schema are more effective for predicting the target SQL for specific natural language queries. Experimental results on the Chinese NL2SQL dataset DuSQL show that the algorithm after adding auxiliary tasks has achieved better results than the prototype model, and can better handle cross-domain NL2SQL task.

For the problem of workflow job scheduling, the critical path method was proposed to predict the execution time of the workflow and allocate resources. The parallel application directed acyclic graph was used to describe the relationships among the sub-jobs of a workflow in the workflow execution time prediction algorithm. Based on this order, the system resources were logically allocated to the sub-jobs. According to the characteristics and resource allocation information of sub-jobs, the gradient boosting decision tree-based algorithm was used to predict the execution time of sub-jobs, and the critical path of workflow was calculated. The sum of the completion time of all sub-jobs on the critical path is the execution time of the workflow. If the predicted workflow execution time satisfies the user′s requirements, job scheduling was executed according to the sub-job execution sequence and resource allocation scheme, and the workflow was executed. Comparative experiments show that the prediction errors of the execution time of two workflows are 5.72% and 1.57%, respectively. Compared with the default scheduling algorithm of Spark, the workflow scheduling algorithm reduces the completion time of the two workflows by 15.71% and 15.44%, respectively.