Chapter 4 Knowledge Base – Artificial Intelligence for Risk Management


Knowledge Base

Chapter Outline

  • Define the knowledge base for the AI project
  • Risk knowledge development
  • Objectives of the risk knowledge base
  • Identification of knowledge for risk
  • Knowledge acquisition for risk
  • Knowledge sharing

Key Learning Points

  • Learn and understand the knowledge base
  • Understand risk knowledge base development

Artificial intelligence (AI) can be used repeatedly in applications with different needs. Human resources departments in corporations have had difficulties capturing and using the human intelligence required in organizations. Knowledge and intelligence must be captured and used repeatedly. The captured knowledge and intelligence can be stored in the knowledge base, used to build a knowledge model, and train machines, so it can be used when necessary.

To capture and use human intelligence requires the development of an integrated information system. The idea is to develop an integrated system that can supply all the knowledge required by human experts. These integrated systems should be readily available and shareable. The integrated system should be used with strategic objectives in mind, leading to the development of AI.

Companies use AI to solve important challenges based on the information stored in the knowledgebase. As observed in life and business, human experts have cyclical demands. Similar approaches are applied to risk management that can be explored with use cases.

It is planned that the knowledgebase stores data, techniques, and algorithms that will be used to drive the AI integrated system. The integrated system will be introduced gradually in this approach. The objective of the AI integrated system is to focus on seeking mitigation solutions to risk in corporate settings. The objectives cause AI to consider using business rules that consists of “what if” questions. The AI considered strategic rules and logic to determine possible strategic mitigation solutions to using the data stored in the knowledgebase. The AI integrated system impacts knowledge objectives, identification of knowledge, knowledge acquisition, knowledge development, knowledge sharing, preservation of knowledge, fixing of knowledge, use of knowledge, evaluation of knowledge, measurement of knowledge, integration of the AI case-based knowledge representation of risk cases, identification of similarities, and connection of AI. All of these aspects are the building blocks of the knowledge base. is fundamentally built from inception to full-blown AI integrated systems using the knowledgebase.

Risk Knowledge Development

The purpose of this section is to generate the risk knowledge required, including ideas, models, skills, processes, and methods to train and learn. Machine-based learning has potential in various forms. With machine learning (ML), neural networks—pattern-based learning—will be used, enabling appropriate knowledge from a large amount of risk data, in turn enabling change of behavior of the captured data in the AI system.

Objectives of the Risk Knowledge Base

The level of skills and knowledge will be developed to use appropriate corporate objectives in the risk knowledgebase.

The objectives of risk in the knowledgebase follow:

  • To capture associated risks from the data, process, people, things (e.g., IoT), systems, and actions.
  • To determine occurrence.
  • To determine impact of risks.
  • To determine risk priority.
  • To allocate risk owner.
  • To determine risk mitigation.
  • To determine risk action.
  • To monitor risk continuously in real time and determine corrective actions.

Identification of Knowledge for Risk

The corporate setting will be used to model skills and knowledge that is appropriate to enable the AI to work well. This process requires mapping the collected risk knowledge. Every effort will be made to store the data in a form that will enable the data to be retrieved correctly. This AI system will allow access to collected data. Ultimately, the system should be able to build a corporate knowledge base capable of being extended with new risk data. The AI system will have the ability to prevent any loss of information, retain, and ensure all of the risk data up to date. The system will automatically be capable of building the knowledgebase. Subsequently, AI will be able to search for additional information externally.

Knowledge Acquisition for Risk

Risk data will be collected using formal and informal channels. The data will be used internally and externally. The collected data will enable suitable competencies of the AI system. The data will ultimately come from experts and will be used with statistical, ML algorithms.

Knowledge Sharing

Risk knowledge sharing is a critical part of the knowledge management cycle. It is important to realize that people, technology, and the corporate world are part of this phase. With AI knowledge sharing solutions, machine intelligence is capable of learning from other AI systems through real-time connectivity using real-time API. Discovering trends in a specific area, such as risk mitigation, can be effective. Another area where AI has been used efficiently is in the manufacture of vehicles. Humans have no need to go through the repetitive task of using the data. The computer system does the job efficiently without being overwhelmed. has real-time API access to solve knowledge sharing problems.