An automatic question answering and knowledge summarization approach for Q&A services

Abstract

With regard to the drastic development of information technologies, the communication channels between enterprises and customers have become more and more complicated. Many enterprises have realized that electronic CRM mechanisms can provide efficient and cost‐effective customer services. In order to automatically answer customer queries via contact centers, this paper proposes an integrated model with automatic question answering and knowledge summarization mechanisms. The integrated model consists of six main phases including keyword distribution analysis, question correlation analysis, meaning unit (MU) analysis, information intensity analysis, MU correlation analysis and MU linkage. The basic idea of the model is to explore the correlation between the target question and FAQs based on their keyword distribution. According to the derived correlation, the candidate answers of the target question can be determined. Furthermore, based on the information intensity of MUs in the candidate answers, critical MUs are extracted and linked to derive the summarized answer to the target question. A web‐based platform is established and the proposed approach is evaluated via an LSP e‐training case. By application of the automatic question answering mechanism, interaction relationships between users and e‐platforms can be improved. The proposed model can be incorporated into CRM, e‐training, or knowledge management systems for efficient question answering and accurate information retrieval.