| 主权项 |
1. A method, in a data processing system, for performing load balancing of question processing in a Question and Answer (QA) system, implemented by the data processing system, having a plurality of QA system pipelines, the method comprising:
receiving, by the data processing system, an input question for processing by the QA system; determining, by the data processing system, a predicted question difficulty for generating an answer to the input question based on at least one feature extracted from the input question and a correlation of the at least one feature with a predicted level of question difficulty, wherein the predicted question difficulty is indicative of a predicted amount of time required to process the input question to generate an answer to the input question via a QA system pipeline in the plurality of QA system pipelines; and performing load balancing of question processing at least by: selecting, by the data processing system, a QA system pipeline from the plurality of QA system pipelines based on the predicted question difficulty; routing, by the data processing system, the input question to the selected QA system pipeline for processing; and processing, by the data processing system, the input question by the selected QA system pipeline to generate an answer for the input question. |
