Elicitation of knowledge: learning of expert operators

Elicitation of knowledge: learning of expert operators

Elicitation (from the latin elicitus “induced” and elicere “to catch”) is a term associated with psychology that refers to the fluid transfer of information from one human being to another by means of language.

The knowledge elicitation applied to industry is a process by which valuable information and knowledge is collected and recorded from experts or people with experience in a particular area in the organization. Is a technique used to identify, extract and document the tacit knowledge (implicit) that is in the mind of the individuals or in the organizational processes. It is a way to collect and record the existing knowledge not available in formal documentation and is used in different fields such as knowledge- management, engineering, business, among others. The knowledge elicitation could be use inside the engineering field to optimize industrial processes, create expert systems, for apps based in AI, etc.

For example, if it were technologically possible to access the minds of workers as in the fictional series Severance, where a sinister biotech corporation, Lumon Industries, uses a medical procedure to separate work and non-work memories, this knowledge could be recorded and available for use, but it is also clear that this premise would raise significant ethical and legal concerns at this point in history, we do not know in the near future.

The knowledge elicitation is important for different reasons. In first place, allows organizations to document the existent knowledge of their employees and experts in an specific area.This can help to avoid re-invention of the wheel and improve efficiency in decision-making. Secondly, knowledge elicitation can also help to identify gaps in an organisation’s knowledge, enabling them to take action in advance. Thirdly, this elicitation process can help foster collaboration and knowledge sharing among an organisation’s employees.

The aim of elicitation is to obtain accurate and relevant information to aid decision-making, improve efficiency and support training and development. This information is used to develop optimal rules for expert performance that serve as the main input for the controls that can be programmed into a production process.

Knowledge elicitation is important for several reasons. Firstly (1), it allows organisations to document the existing knowledge of experts in a specific area. This can help to avoid re-invention of the wheel and improve efficiency in decision-making. Secondly (2), knowledge elicitation can also help to identify gaps in an organisation’s knowledge, allowing organisations to take action in advance. Thirdly (3), this elicitation process can help foster collaboration and knowledge sharing among an organisation’s employees.

The methodology for knowledge elicitation requires a series of steps to be followed:

  1. Requirements analysis: identifying the approach to knowledge-based systems.
  2. Conceptual modelling: creating a base of terminology used, defining interrelationships and constraints.
  3. Construction of a knowledge base: rules, facts, cases or constraints.
  4. Operation and validation: Operating using automated reasoning mechanisms.
  5. Return to requirements analysis if necessary or continue with the process.
  6. Enhancement and maintenance: Expanding knowledge as the system evolves, repeat throughout the life of the system.

Subsequently, it is necessary to analyse the knowledge collected, to determine which information is relevant and which is not, by distinguishing and separating the parts of a whole until its principles or elements are known, the result of which is high quality knowledge. The verification or detection of defects of the requirements previously analysed, normally by means of techniques such as formal reviews, checklists, etc.

The following elements are necessary for the correct development of the tendering process:


The different experts on the procces can have different point of views of a same theme, due to their experience, knowledge and even more subjective aspects such as mentality, way of focus difficulties, challenges, etc. Should be considered experts specialists in different stages, different infrastructures, equipment, products,etc.

The barriers that can appear in this type of exchange of information is that often contain complex ideas and associations, hard to comunicate in an easy way, with detail and organization, the use of a same language, such as concepts or specific vocabulary.

The knowledge elicitation has an objective search, research and help users or experts in the productive process in this case, to document their own needs by an on-site or online interview, group meetings, in situ studies, etc.


To acquire expert knowledge the best technique is carrying out a number of personal interviews, some of the disadvantages are; distance, time and people involved on this process, the paper or online questionnaires can be viable option that saves time and costs and it is made easier for all sections to be present, enabling the comparative and evaluation of the results.

The characteristics for a good questionnaire design: define the relevant information, good structuring with different sections organized by themes, organizes points from general to more detailed in each section, focusing on the idea of those section,it is avoid the introduction of tendencies, misunderstandings or mistakes, to realize the design with an expert of the domain to ensure that points are enough understandable to facilitate the answer.


The expected results are the actions to make by the operators when parameters deviations are produced, those answers and information collected are transform intop optimal needed rules to program authomatic controls about the process, and whre this rules are the main element. The obtention of rules is not an easy task, an iterative and heuristic process in several phases is recommended. For the validation it is necessary the comparative of the collected information at the databases with the answers of the operator to verify the actions when parameters deviations of the desired values are produced.

This optimal rules or also denominated if-then rules are part of the knowledge base, in particular of the relations base, that is the part of an expert system that contains the knowledge about the domain. In first place, the knowledge of the expert is obtained and it is codified in the relations base.

Finally, it is when fuzzy logic can be used for the design and implementation of an expert system, which is the logic that uses expressions that are neither totally true nor false, allowing to deal with imprecise information such as average height or low temperature, in terms of so-called “fuzzy” sets that are combined in rules to define actions: e.g. “if the temperature is high then cool down a lot”. This type of logic is necessary if one wants to better approximate the way of thinking of an expert, whose reasoning is not based on true and false values typical of classical logic, but requires extensive handling of ambiguities and uncertainties typical of human psychology.

Currently in CARTIF the expert elicitation knowledge of the plant operators are been used at the INTELIFER project, which main objective is the optimization of the process and of the products of a manufacturing line of NPK granulated fertilisers with support of the artificial intelligence.

The operation of these type of granulated fertilisers plants is controlled manualli and heuristically by expert operators, but that, despite of its skills and habilities, they can not avoid the high rates of recycle, frequent inestabilities and non-desired stops, as well as the limite quality of the products. Due to the extremely complex nature of the granulated process, which includes multistages, multiproduct, multivariables, is not lineal, coupled, stochastic. So that the situation before exposed has meant the scientific base for the defiition of the present project, being necessary the development of R&D activities in which, by the application of the artificial intelligence philosophy joint with a higher degree of sensorization and digitalization, is achieved to optimize this type of manufacturing processes.