How can I optimize learning

Personalized learning and how modern technology optimizes learning

Let us first define the term "personalized learning". This term refers to a number of methods and techniques for adapting learning processes to the learning style, personality, individual needs, background and educational background of an individual. Personalized learning can be written in German best translate with individualized learning.

Previous knowledge forms the basis of learning for every person. Research shows that learning outcomes improve significantly when learning is based on previous knowledge. In her bestseller "Mindful Learning: 101 Proven Strategies for Student and Teacher Success"Linda and Bruce Campbell show the important role the previous knowledge of the learner plays. If it is now known what knowledge a person already has, it can be built on and linked to in order to make learning more effective.

Take a look at the following example. My son recently asked me the following question about the gearshift in my manual car: “What is it and what do you need it for?” I thought for a moment and then explained it to him by referring to the gearshift on his bike because I knew about my son's previous knowledge, I was able to relate the new information to it and simply explain the new concept to him.

What would have happened if I had explained it to him from a purely mechanical point of view or on the basis of drawings with the engine, gearbox, etc.? He would probably have lost interest and resigned himself after half a minute, since he has no basic knowledge in this regard that one can build on. The result would have been that he would not have learned anything.

In summary, this means: If a person's previous knowledge is known and a new concept can be associated with it, much better results are achieved in terms of understanding and learning success.

Individualized learning in a company

Let's imagine a similar situation in a company. We have a new employee who has to learn how to use the new tool, the new technology or the new process. If the information is linked to a person's previous experience, this speeds up the learning process and leads to an increase in the employee's performance. This employee is like my son in the previous example. In my example, however, I was the one who knew about my son's level of knowledge and experiences, so I was able to establish a connection between the known and the still unknown so that he could understand the unknown more easily. Is there someone in the employee's environment who can take on this "parenting role", speaks their language and knows about the employee's previous knowledge? I bet that in most cases there isn't such a person. How can learning processes in the company be improved ensure that the employee does not lose interest and give up because the new concept is too complex to understand straight away and is in no way related to his or her previous experience?

The problem of traditional methods


One possibility of taking on the "parenting role" in a company is mentoring. A more experienced employee is placed at the side of a less experienced colleague as a consultant. Through his knowledge and his own experience, the mentor can understand the problems and difficulties of his protégé and the learning process and promote understanding. This model works wonderfully, but the limits are in the scalability.

Internal company intranet

Instead of providing the employee with someone to accompany their learning and understanding process, the responsibility lies with the employee himself to get answers to his questions. If the employee needs to learn something about new tools, technologies or processes in the company, he can consult the company's intranet, wiki or other information sources of the company. This is not a bad approach, because as you search for and apply the information you find, the employee may learn about similar things. However, this method is not optimal because the employee has to search through a lot of information that is not always relevant. And when he has found an answer, it is not always appropriate if it is not based on his previous knowledge.

The solution

You may be wondering, “What now? What better way to help an employee not only find the appropriate information, but also ensure that the answers build on their previous experience? "

In my opinion, a combination of sophisticated search and personalization modules is required here.

A search engine first restricts the possible sources of information (such as documents, websites, etc.) and a personalization module lists the information that is most relevant for the employee at the top, depending on their previous knowledge.

A search engine like Google, for example, is something we use every day. In the corporate environment, a separate search engine or some kind of advanced search engine that searches many different back-end systems and combines results could be used for each information system. But how can these results be more personalized or related to the employee's previous knowledge? Or to be more specific: How do we know what prior knowledge an employee has?

How can an employee's experience be digitized and made understandable for a machine?

● The first step in this direction is the creation of a list for each employee, which qualifications he already has and what level of knowledge he is. This can be done by the employee himself / herself, for example, by analyzing the text of his / her résumé or by filling out a simple form, which is divided into rows (qualifications) and columns (level of knowledge). While this information already provides some pointers, it is not very detailed. It is also a fairly static view that does not take into account further learning and experiences after listing these qualifications.

● It is better if the HR department collects information on the training courses attended, certificates completed and other formal learning outcomes in addition to the competence matrix that was created in the previous step. For the employee, this could significantly improve the relevance of the information found if the system knows his level of knowledge, which is updated accordingly when the employee has participated in formal learning units. As a result, newcomers are not shown information that requires expert knowledge, for example - and vice versa.

However, this is not enough to ensure that the search results are actually relevant and personalized. The personalization module requires far more granular data on the employee's level of knowledge, which learning methods he prefers, what is easy and what is difficult for him, which types of information are best suited for him, etc.

How can this information be digitized and analyzed?

● The last and most advanced option is a combination of the approaches described with a data collection on all learning activities that take place in real time. I'm talking about using the Experience API (xAPI) and Learning Record Store (LRS). xAPI enables the collection of detailed data on the employee's learning process in many locations.

If the company's intranet is xAPI-compatible, information can be gathered about opened pages and downloaded documents. The actions of an employee in a factory, which are logged with several sensors, can be collected as xAPI statements. If a company uses simulations or virtual / augmented reality (VR / AR) for training purposes, the actions and processes during the simulation can be logged and saved as xAPI statements. If a company uses a learning experience system like Valamis for training purposes, all actions of the user are automatically logged with xAPI.

How can the learning process be made even more personalized and effective?

If the personalization module has access to all data about the employee, the system could make more reasonable assumptions about the relevance of certain information for the employee. By analyzing the learning history it can crystallize which learning format is best suited for a person: for example, is it more effective to read an article or to listen to an audio contribution; Does the learner prefer long learning units in which a lot of material is presented, or should the learning unit be shorter and more practical; the learning needs depend on the time of day or the day of the week etc.

Even better results can be achieved by comparing the knowledge and experience of one employee with the experiences and similarities of other employees in terms of functions, qualifications or learning activities. Based on these similarities, the relevance of the information provided to the employee can be improved. This method is also well suited for new employees who have no previous history in the company. First, relevant introductory material is made available due to similarities such as function and department as well as the lack of learning history. By analyzing the learning history of previous newcomers, the system suggests additional information and material to the learner that has already been found to be important to other newcomers.

Of course, this is just the beginning. The loop needs to be closed to optimize the system and learning needs to be linked to the personalization module so that the relevance of the results gets better over time. Analyze learning activities, check which of the suggested results the employees choose, ask them whether they are satisfied with the available results, check detailed searches - all this leads to the optimization and continuous adaptation of the recommendation module using machine learning.


Making learning more personalized has a huge impact on learning outcomes. When new concepts are linked to a person's previous knowledge, it leads to better understanding and more effective learning.

Personalized learning in the corporate environment requires technological solutions that are cost-efficient and scalable. Technologies such as a combination of Experience API (xAPI) and Learning Record Store (LRS) enable the collection of granular data in digital form regarding the experiences of employees. This information can ultimately be used to personalize future learning activities through a combination of sophisticated search and personalization modules.

Of course, none of these technological solutions are perfect. However, if the gap between learning activity and resolution is closed, the quality of the answers learners receive will steadily improve. Employees don't have to figure out what information they need, they benefit from a truly personalized learning experience.