Personalized learning via task load optimization

#This invention relates generally to improvements in human information processing and learning. More specifically, this invention relates to a computer-implemented system and method for providing user-optimized training experiences.

#In cognitive psychology, the cognitive task load theory (CLT) suggests that the human information process involves three main parts: sensory memory, working memory, and long-term memory. According to this theory, humans generally perceive or interact with new, incoming information or stimuli using their five senses (i.e., sight, hearing, smell, touch, and taste) via the sensory memory. The sensory memory is the first level of memory and it captures a short-term snapshot of the information and acts as a first buffer against all of the stimuli that could possibly be perceived by a person. Once a stimulus is perceived, a person must pay attention or focus on that stimulus in order to pass the information from the sensory memory to the longer-term working memory. Otherwise, the information is quickly disregarded and forgotten. Thus, the decision to pay attention or to not pay attention to certain information serves as a second filter for stimuli. The amount of working memory available to process new information is limited. It is believed that the working memory can hold between five and nine items (or “chunks”) of information at any one time. Excess information is disregarded and forgotten. Moving information from working memory to long-term memory (i.e., encoding) requires the person to interact with the information numerous times, which is often called “rehearsal” of the information, and typically involves relating that information to past knowledge. Once information is stored in the long-term memory, further retrieval and rehearsal helps to prevent the decay of that memory (i.e., forgetting the information).

#It is common to present new information to users in the form of educational trainings and simulations. These simulations are used to not only present the information but to also rehearse that information in order to move it through the information process discussed above to the user's long-term memory and retention. For example, it is common for firefighters to learn and practice their firefighting skills through written coursework and tests as well as through live firefighting exercises and demonstrations. However, these trainings are typically static and are universal (i.e., identical) for each user and are, for that reason, not optimized for each user. Each user is typically given the same written materials and participates in the same firefighting exercise, which presents the same problem and the same operating conditions. This method has proven to be a moderately effective way to teach new information. However, because the training is not unique or personalized for each user, the results of the training are not optimized.

#Further advantages of the invention are apparent by reference to the detailed description when considered in conjunction with the figures, which are not to scale so as to more clearly show the details, wherein like reference numerals represent like elements throughout the several views, and wherein:

#FIG. 1 depicts a training system for generating, presenting, and personalizing a simulated training experience for a user of the training system according to an embodiment of the present invention;

#FIG. 2 illustrates an initialization process that may be used in initializing the training system shown in FIG. 1;

#Now, with reference to FIG. 1, there is shown a training system 100 for generating, presenting, and personalizing a simulated training experience for a user of the training system. The training system 100 includes a computer-based training simulator 102 for generating and providing the simulated training experience to the user. The training simulator 102 may be one or more of any type of general purpose computer, tablet, etc. that is suitably equipped for this purpose. The training simulator 102 is provided with a first machine learning algorithm (ML1), which may also be referred to as a “prediction program,” for calculating a predicted actual task load experienced by the user associated with the user's interaction with the simulated training experience. The training simulator 102 includes a second machine learning algorithm (ML2), which may also be referred to as a “training optimization program,” for providing a training experience recommendation that would cause the predicted actual task load to align or match a predicted optimal task load for achieving a specified training goal. The system 100 is configured to collect one or more of the following: biometric information, performance metric information, and task load information related to the user both during and/or after training activities carried out using the training simulator 102. This information is collected via an information collection means 104, which, as discussed further before, includes various types of sensors, etc. and is dependent on the nature of the information being collected. Finally, a display 106 is provided that displays the training experience to the user. In this case, the display 106 is a headset having built-in speakers and a built-in monitor (optionally, also including a microphone) for viewing displayed images and that might be used in connection with virtual reality (VR) or augmented reality (AR) games, presentations, etc. In the description that follows, the term “AR” refers to both AR and VR, unless otherwise noted. In certain preferred embodiments, the training system 100 may also include at least one other AR device 108 that is provided with and that works alongside the display 106 for interacting with the training content provided by the training simulator 102. For example, in the present case, the AR device 108 is illustrated as a fire nozzle or bale that may be used to interact with a fire fighting AR simulation (e.g., to fight fires). In other cases, additional and different AR devices 108 may be provided with the training system 100, depending on the nature of the training experience. For example, the AR device 108 might be a pistol in a shooting simulation or forceps or a scalpel or suture material in a surgical simulation. In each case, the AR device 108 is used to interact with the training simulation provided by the training simulator 102. The AR devices 108 may be equipped with speakers, microphones, lights, haptics, functional components (e.g., working trigger), etc. to allow for a realistic interaction of the user with the training experiences provided.

#Initialization

#Before it is used by users with actual training experiences, the training system 100 should be initialized by being trained for a specific user or group of users. Since each user reacts differently to different training tasks and training conditions, this initialization step helps to customize the training system 100 for a particular user, including by identifying how and to what extent a user's biometrics change in response to different tasks and conditions. This establishes a baseline or user profile for that user (or group of user) that can then later be used in tailoring actual training activities for optimizing the training for that particular user.