Decision Support for Knowledge Intensive Processes Using RL Based Recommendations

Author(s):  
Asjad Khan ◽  
Aditya Ghose ◽  
Hoa Dam

The domain of construction is a very knowledge-intensive domain with so many factors involved. This implies undertaking any action requires an understanding of the different factors and how best to combine them to achieve a favourable and optimal outcome. Thus decision-making has been extensively used in the domain of construction. The aim of this chapter is to undertake a review of various decision support systems and to provide insights into their applications in the domain of construction. Specifically, the principle of cost index, sub-work chaining diagram method, linear regression and cost over-runs in time-overrun context (CCOTOV) model and Markov decision processes (MDP), ontology and rule-based systems have been reviewed. Based on the review the Markov decision processes (MDP), ontology and rule-based systems were chosen as the more suitable for the cost control case considered in this study.


2010 ◽  
Vol 1 (1) ◽  
pp. 2281-2290 ◽  
Author(s):  
Obinna Anya ◽  
Hissam Tawfik ◽  
Atulya Nagar ◽  
Saad Amin

2021 ◽  
Vol 1 (2) ◽  
pp. 6-12
Author(s):  
Evgeniy Sergeevich Mityakov ◽  
Andrey Ivanovich Ladynin ◽  
Nina Maksimovna Shmeleva

Author(s):  
Qiao Li ◽  
Junming Liu

High level of knowledge and expertise are required in auditing, which makes it a knowledge-intensive professional service. Auditors' brainstorming meetings involve various topics on risks, which provide numerous valuable knowledge on how auditors identify and assess risks and achieve decisions. However, it is very difficult to retrieve useful knowledge from these meeting conversations. With the help of Natural Language Processing (NLP) techniques, this paper proposes an intelligent NLP-based audit plan knowledge discovery system (APKDS) that will continuously and automatically extract important knowledge from audit brainstorming discussions and provide decision support to auditors in future engagement cases.


Sign in / Sign up

Export Citation Format

Share Document