Method for providing learning content for a person by means of an electronic computer unit, computer program product, computer-readable storage medium and electronic computer unit

EP4463841A1Pending Publication Date: 2024-11-20SIEMENS AG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
EP2023733862
Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-06-14
Filing Date
2023-06-05
Publication Date
2024-11-20

AI Technical Summary

Technical Problem

Current methods for providing learning content lack technical implementations to effectively utilize emotional engagement and personalized delivery, relying on human performance and cognitive science methods without technological solutions.

Method used

An electronic computing device method that breaks down learning content into objectives and facts, generates narratives using machine learning, and adapts content and structure based on learning goals and user behavior, incorporating observation devices for real-time feedback and personalization.

Benefits of technology

Enhances learning absorption through automated, emotionally engaging, and personalized narrative delivery, increasing efficiency and effectiveness by adapting to user behavior and preferences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1.1
    Figure 1.1
Patent Text Reader

Abstract

The invention relates to a method for providing learning content (12) for a person (14) by means of an electronic computer unit (10), in which the learning content (12) is recorded by means of an input unit (16) of the electronic computer unit (10) and broken down into at least one learning objective (20) and at least one fact (22) by means of the electronic computer unit (10), and, according to the at least one learning objective (20) and the at least one fact (22), a narration (26) with the at least one learning objective (20) and the at least one fact (22) is generated by the electronic computer unit (10), and the narration (26) is output for the person (14) by means of an output unit (18) of the electronic computer unit (10). The invention also relates to a computer program product, a computer-readable storage medium and an electronic computer unit (10).
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Description

[0002] Method for providing learning content to a person by means of an electronic computing device, computer program product, computer-readable storage medium and electronic computing device

[0003] The invention relates to a method for providing learning content for a person by means of an electronic computing device according to the applicable patent claim 1.

[0004] It is already known that the limited absorption and storage capacity of the human brain can lead to problems in learning experiences. What is learned is usually only absorbed and retained sustainably if the information can be perceived and / or experienced in an emotional way.

[0005] Before the invention of writing, transmission was limited to oral transport, particularly the telling of frequently quoted stories around the campfire, and focused on drama in order to convey important content to the audience in a lasting way. Current solutions to the problem are based on human performance and can be found in the fields of education, motivational speakers and fiction, particularly written and audio books. In cognitive science, several methods are known that can be used as vehicles for imagination and stronger association, for example the so-called Loki method, which usually requires individual application by the learner. In particular, in the field of technology, no technical implementations are known or can be found.

[0006] The object of the present invention is to create a method, a computer program product, a computer-readable storage medium and an electronic computing device by means of which learning content can be provided or conveyed to a person in an improved manner.

[0007] This object is achieved by a method, a computer program product, a computer-readable storage medium, and an electronic computing device according to the independent patent claims. Advantageous embodiments are specified in the subclaims.

[0008] One aspect of the invention relates to a method for providing learning content for a person by means of an electronic computing device, in which the learning content is captured by means of an input device of the electronic computing device and broken down into at least one learning objective and at least one fact by means of the electronic computing device and, depending on the at least one learning objective and the at least one fact, a narration with the at least one learning objective and the at least one fact is generated by means of the electronic computing device and the narration is output to the person by means of an output device of the electronic computing device.

[0009] In particular, an electronic computing device can be provided by means of which the learning content can be provided or conveyed to the person in an improved manner. In particular, the learning content can be broken down into a learning objective and at least one fact, in particular a plurality of facts, and based on the specific learning objective and the specific fact, a narrative can be told, allowing the person to absorb the learning content in an emotionalized way. The person can thus absorb the learning content in an improved manner.

[0010] Narration can also be viewed as essentially similar to a story or a narrative.

[0011] In particular, the learning content or the cognitively existing information source is analyzed, broken down, structured and generated in several steps into a narrative with, for example, visualization in order to associate important facts of the original information with elements of the narrative and, for example, to anchor them visually.

[0012] In particular, the conversion of this learning content into narration can be realized automatically. Through automation, a generated narration is available in real time, and immediate responses can be made to user behavior. Furthermore, automation eliminates the costs of manual work and thus increases the efficiency of learning and the provision of learning content. An exemplary scientific basis for emotionalized learning can be found in the book "Lifelong Learning and Emotions: The Effects of Emotions on Educational Processes from a Relationship Theory Perspective" by Wiltrud Gieseke, 3rd edition of Adult Education and Lifelong Learning from 2016.

[0013] According to an advantageous embodiment, the learning content is broken down into at least the learning objective and the fact by means of machine learning on the electronic computing device. In particular, the electronic computing device can be designed to break down the learning objective and the fact using a neural network. For example, a trained neural network can be provided for this purpose, which in turn can carry out a corresponding decomposition on the basis of already existing learning content and narratives. In particular, the neural network can be designed as a learning neural network and, for example, also carry out corresponding changes in the future based on, for example, a success check. The neural network can, for example, be provided as a convoluted or folding neural network.Alternatively or additionally, the neural network can also be provided as a perceptron, as a feedforward neural network or as a recurrent neural network or generative adverserial networks (GANs). It has also proven advantageous if the narration is generated by means of machine learning of the electronic computing device depending on the learning objective and the fact. In particular, the electronic computing device can be trained via a neural network to generate the narration in accordance with the specifications, i.e. the learning objective and the fact. For example, a trained neural network can be provided for this purpose, which in turn can carry out the corresponding generation on the basis of already existing learning content and narrations.In particular, the neural network can be designed as a learning neural network and, for example, also implement appropriate changes in the future based on, for example, a success check. The neural network can be provided, for example, as a convoluted or folding neural network. Alternatively or additionally, the neural network can also be provided as a perceptron, a feedforward neural network, a recurrent neural network, or a generative adversarial network (GAN).

[0014] It has also proven advantageous to convert an aurally generated narration and / or a visually generated narration into a text-based narration and / or an aurally generated narration and / or a visually generated narration. For example, the narration can be generated in text form, such as prose, using the electronic computer. Alternatively or additionally, parts or all of the narration can be output aurally, i.e. on the basis of listening comprehension, for example in the form of an audio book. Furthermore, a visually generated narration can also be generated, for example in the form of images or a film, in particular with aural or text-based titles. This makes it possible to generate the narration on different levels of perception, which improves the telling of the narration and the teaching content.

[0015] It is also advantageous if the content of the narrative is determined using the electronic computing device. For example, the content may differ from the learning content. For example, the learning content may be a biology exercise about animals, while the content of the narrative, in turn, concerns a narrative from the animal kingdom, thus "hiding the learning content" within the content.

[0016] In a further advantageous embodiment, the content is adapted depending on the learning objective and / or the fact. In particular, this also makes it possible to adapt the content to the narrative or to adapt the content to the learning objective or the fact. For example, the learning content can be the transfer of specific knowledge, such as the precise structure of human extremities. A corresponding narrative with content can then be adapted to this, for example a hospital stay of a person with a broken arm, with the narration then in turn addressing the precise structure of the arm and thus conveying the learning content to the person, namely the structure of human extremities.

[0017] According to a further advantageous embodiment, a structure of the narrative is determined depending on the content and / or the learning objective and / or the fact. In particular, the narrative can therefore also have an introduction, main part and conclusion, so that a correspondingly improved transfer of knowledge can be emotionalized or emotion-based. In particular, the structure of the narrative can be determined depending on a preferred genre of the person. This enables the person to absorb the learning content better. Furthermore, it has proven advantageous if the person is observed by means of an observation device of the electronic computer device and if a success control with regard to the learning content is determined depending on a parameter characterizing and observed for the person.In particular, the electronic computing device can be configured to monitor effectiveness through user observation and can, in turn, adjust the corresponding parameters for effectiveness, allowing for improved learning content presentation in the future. By generating the observation device used, which is provided in particular in the form of attention monitoring, the effectiveness of the generated narrative can be measured and, if necessary, improved, for example, by modifying the reported preferences.

[0018] It has also proven advantageous if the observation device is provided as a camera for recording the person. For example, so-called eye tracking or interaction monitoring can be carried out using the camera or without a camera. For example, a mouse trail or a mouse movement profile can also be used for observation. The camera is purely an example and should not be seen as exhaustive; for example, reactions via the input device can also be recorded accordingly, or other parameters of the person, such as a pulse rate or body temperature, can be recorded in order to be able to carry out appropriate attention monitoring. Appropriate sensors or devices can be provided here, which in turn can then implement eye tracking, interaction monitoring, pulse measurement or temperature measurement.

[0019] Further forms of observation equipment can include a keyboard with pressure sensors, so that the learner's energetic and / or rapid keystrokes can be distinguished from hesitant, cautious keystrokes, and this distinction can be recorded and stored. Likewise, the use of a mouse, trackball, touchpad, touchscreen, stylus or pen, and / or joystick can be recorded and stored. Furthermore, the use of all types of "delete" entries or "delete operations" using keys, a mouse, a touchscreen, etc., can be recorded and analyzed.

[0020] Furthermore, data such as heart rate, pulse, blood pressure, and other physical data, which can be captured via wristwatches and / or cameras, can be fed into the system to record the learner's situation with various learning content. Furthermore, oxygen levels in the air, room temperature, etc., can be measured, and data can be generated, analyzed, compared, and fed into the system to optimize learning success.

[0021] Data for capturing the situation is generated via appropriately mounted recording devices, such as a camera, one or more microphones and / or field-effect microphones, pressure sensor(s), and movement tracking—course and speed—of an input device such as a mouse, touchscreen, stylus, trackball, or joystick. Preferably, the generated data is compared with the time course of the simultaneously running learning content and analyzed with regard to its content and the "normal," "calm" behavior of the learner(s) and / or other learners.

[0022] Carrying the time base to the data generated by the observation device(s) is optional but can be very valuable in terms of creating a time axis and / or a concentration profile.

[0023] Through appropriate video recording and optical and / or acoustic or otherwise generated data sets, the posture, gestures and / or movement profile of the learner in connection with the learning content can be automatically used to understand, grasp the learner's situation and adapt the learning content to the learner.

[0024] In this way, walking around the room, the type and frequency of head movements, facial expressions, micro-expressions, face recognition, twisting of the upper body, rolling of the eyes, yawing and / or nodding of the head, shrugging of the shoulders can be recorded, used as a data block and used to train a corresponding AI, which successively and dynamically adapts the learning content to the automatically recorded mood of the learner.

[0025] The data used to capture learners' situation while studying a learning content can also be used for motivation. When certain levels of agreement are reached, motivational actions are then automatically initiated.

[0026] Examples of these motivational actions are, for example, pop-ups of smileys, noises, clapping, music, offering a drink / sweet and / or fruit - which can be found in a refrigerator belonging to the system - and / or emojis that appear and reward the learner in a way that is relevant to the learning content and / or the learner, or simply a break when the system detects and / or analyses that the learner(s) are exhausted.

[0027] On the other hand, a tendency towards precrastination or procrastination can also be identified. By analyzing the recorded data on the learner's situation with the various learning content, it can be determined, for example, whether the learner shows less tendency towards anxious, hasty, or otherwise "conspicuous" behavior with one or another learning content. The timing of the learning content can then be automatically adjusted via AI so that the learner is always in the optimal mood for the respective learning content. Furthermore, the system can use gentle prompts to encourage a procrastinator, for example, to tackle the learning task. These can be playful prompts in the sense of gamification, as well as rewards such as "if you manage to do this today, then you will have the benefit" and / or it can be linked to motivational actions - see above.

[0028] It is also advantageous if an adaptation parameter is determined depending on the success control and if the adaptation parameter is taken into account when learning content is made available to the person in the future. For example, the observer's attention span can be determined. For example, it can be determined that the observer only had increased attention for five minutes and that from the fifth minute onwards the attention span decreased again. The adaptation parameter can therefore be designed in such a way that in future the learning content is only reduced to narratives which are five minutes long. Furthermore, other parameters can also be adjusted accordingly in order to be able to present the learning content in a correspondingly improved manner.

[0029] In a further advantageous embodiment, a personal profile is specified for the electronic computing device, and the narration is additionally narrated depending on the personal profile. Thus, the narration can be individually tailored to the individual. In particular, the personal profile can also be referred to as a user preference.

[0030] It has also proven advantageous if a person’s genre preference and / or association and / or prior knowledge are taken into account in a person profile. This means that the narrative or user preference and the person profile can be reliably generated. The corresponding preferences or associations and the prior knowledge can, for example, be realized on the basis of an observation of the person in a past period. Alternatively or additionally, the corresponding parameters, in particular the genre preference, the association and the prior knowledge can be specified by the person or by other people and thus made available to the electronic computing device. With the genre preference, it can, for example, be specified that the person prefers to watch crime series and / or cartoons. Such a genre can be taken into account accordingly.Furthermore, past experiences, such as a vacation, can be used to provide relevant learning content through associations. Furthermore, prior knowledge, such as a previously attended course, training, or degree, can be used to personalize the narrative.

[0031] The method presented is, in particular, a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means that cause an electronic computing device, when the program code means are processed by the electronic computing device, to perform a method according to the preceding aspect. The computer program product can also be referred to as a computer program.

[0032] Furthermore, the invention also relates to a computer-readable storage medium containing the computer program product.

[0033] Yet another aspect of the invention relates to an electronic computing device for providing learning content for a person, having at least one input device and one output device, wherein the electronic computing device is designed to carry out a method according to the preceding aspect. In particular, the method is carried out by means of the electronic computing device. The electronic computing device has, for example, processors, circuits, in particular integrated circuits, and other electronic components in order to be able to carry out corresponding method steps. In particular, the method is carried out by means of the electronic computing device.

[0034] Advantageous embodiments of the method are to be regarded as advantageous embodiments of the computer program product, the computer-readable storage medium, and the electronic computing device. The electronic computing device, in particular, comprises components enabling the corresponding method steps to be carried out.

[0035] For use cases or application situations that may arise during the method and which are not explicitly described here, it may be provided that, in accordance with the method, an error message and / or a request to enter user feedback is issued and / or a standard setting and / or predetermined initial state is set.

[0036] The following figure shows a schematic block diagram of an embodiment of an electronic computing device.

[0037] In the figure, identical or functionally equivalent elements are provided with the same reference symbols.

[0038] Fig. 1 shows a schematic block diagram according to one embodiment of an electronic computing device 10. The electronic computing device 10 is designed to provide learning content 12 for a person 14 and has at least one input device 16 and one output device 18.

[0039] In the method for providing the learning content 12 by means of the electronic computing device 10, the learning content 12 is captured by the input device 16 and broken down into at least one learning objective 20 and at least one fact 22 of the electronic computing device. The learning content 20 can be existing, unprocessed information or can be specified implicitly or explicitly. In particular, a so-called information extraction module 24 can be provided for this purpose, which in turn can be provided in particular as a neural network.

[0040] Depending on the at least one learning objective 20 and the at least one fact 22, a narrative 26 comprising the at least one learning objective 20 and the at least one fact 22 is generated by the electronic computing device 10. This can be carried out in particular in a narrative generation module 28, wherein the narrative generation module 28 can also be configured as a neural network. The narrative 26 is then output to the person 14 by the output device 18.

[0041] As already mentioned, the learning content 12 can be broken down into at least the learning objective 20 and the fact 22, in particular by means of machine learning of the electronic computing device 10, wherein the machine learning is represented in the present case in particular by the neural network or the information extraction module 24. Furthermore, as already mentioned, it can be provided that the narration 26 is generated by means of machine learning of the electronic computing device 10 depending on the learning objective 20 and the fact 22. In the present case, this is provided in particular via a neural network and is shown in particular by the narration generation module 28.

[0042] In particular, a content 30 or a corresponding storyline can be generated by means of the electronic computing device 10. In particular, the content 30 can be adjusted or adapted depending on the learning objective 20 and / or the fact 22, which is primarily shown in a mapping module 32. Furthermore, it can be provided that a structure 34 of the narrative 26 is determined depending on the content 30 and / or the learning objective 20 and / or the fact 22.

[0043] The narration 26 can in particular be text-based and / or auditory and / or visual.

[0044] Furthermore, it can be provided that the person 14 is observed by means of an observation device 36, which is designed in particular as a camera, of the electronic computing device 10 and, depending on a parameter 38 characterizing and observed by the person, for example, the attention of the person 14, a success check with regard to the learning content 12 is determined. The observation device 36 can in particular be an attention monitor and can be provided, for example, in the form of eye tracking.

[0045] Furthermore, it can be provided that an adaptation parameter 40 is determined as a function of the success control and the adaptation parameter 40 is taken into account in a future provision of a learning content 12, in particular a future learning content 12, for the person 14.

[0046] In the following exemplary embodiment, the adaptation parameter 40 can again be used for a person profile 42. Depending on this person profile 42 or user profile, the narration 26 can again be generated, whereby the person profile 42 can again be specified to the electronic computing device 10. The person profile 42 can again take into account a genre preference 44 and / or an association 46 and / or prior knowledge 48 of the person 14.

[0047] In particular, the figure shows that the cognitively existing information source or the learning content 12 is analyzed, broken down, structured and generated into the narrative 26 with, for example, visualization in several steps in order to associate important facts of the original information with elements of the narrative 26 and to anchor them visually.

[0048] In particular, an automotive attention warning system is proposed that uses measured input for hints and recommendations or is designed to deactivate auxiliary systems, but not to fundamentally change system functions. This means that in the automotive sector, the warning system only operates within predefined degrees of freedom, whereas the system outlined here generates completely different outputs if the expected user behavior fails to occur.

[0049] In particular, the transformation of the learning content 12 is thus automated in a first step. The generation of the narrative 26 is tailored to the respective user or person 14. The effectiveness of the generated narrative 26 can then be measured and, if necessary, improved via attention monitoring.

[0050] Through automation, a generated narrative 26 is available in real time, and immediate action can be taken to user behavior. Automation eliminates the costs of manual work and increases efficiency accordingly. Through the user customization step, the person 14 experiences a learning experience tailored to their cognitive abilities and personal preferences. Due to marginal cost issues, this can only be achieved through automation and evaluation. The system or electronic computing device 10 monitors the effectiveness through user observation and adapts / improves its own parameters for improved effectiveness of the customization.Information extraction uses methods of information retrieval such as natural language processing, learning and creation of knowledge graphs and ontologies as well as generative technologies such as natural language generation (NLG) and sequence-to-sequence transformation (Seq2Seq).

[0051] Reference symbol list

[0052] 10 Electronic computing device

[0053] 12 Learning content

[0054] 14 people

[0055] 16 Input device

[0056] 18 From output facility

[0057] 20 Learning Objective

[0058] 22 Fact

[0059] 24 Information extraction module

[0060] 26 History

[0061] 28 Story generation module

[0062] 30 Contents

[0063] 32 Mapping module

[0064] 34 Structure

[0065] 36 observation device

[0066] 38 parameters

[0067] 40 adjustment parameters

[0068] 42 person profile

[0069] 44 Genre preference

[0070] 46 Association

[0071] 48 Prior knowledge

Claims

Patent claims 1. Method for providing a learning content (12) to a person (14) by means of an electronic computing device (10), wherein the learning content (12) is recorded by means of an input device (16) of the electronic computing device (10) and is decomposed into at least one learning objective (20) and at least one fact (22) by means of the electronic computing device (10), and depending on the at least one learning objective (20) and the at least one fact (22), a narrative (26) with the at least one learning objective (20) and the at least one fact (22) is generated by means of the electronic computing device (10), and the narrative (26) is output to the person (14) by means of an output device (18) of the electronic computing device (10).

2. Method according to claim 1, characterized in that the learning content (12) is decomposed into at least the learning objective (20) and the fact (22) by means of machine learning of the electronic computing device (10).

3. Method according to claim 1 or 2, characterized in that the narration (26) is generated by means of machine learning of the electronic computing device (10) depending on the learning objective (20) and the fact (26).

4. Method according to one of the preceding claims, characterized in that a text-based narration (26) and / or an auditory narration (26) and / or a visual narration (26) is generated.

5. Method according to one of the preceding claims, characterized in that A method according to claim 5, characterized in that the content (30) of the narrative (26) is determined by means of the electronic computing device (10). A method according to claim 5 or 6, characterized in that a structure (34) of the narrative (26) is determined depending on the content (30) and / or the learning objective (20) and / or the fact (22). A method according to any of the preceding claims, characterized in that the person (14) is observed by means of an observation device (36) of the electronic computing device (10) and a success check with regard to the learning content (10) is determined depending on a parameter (38) that characterizes the person (14) and is observed. A method according to claim 8, characterized in that the observation device (36) is provided as a camera for capturing the person (14).A method according to claim 8 or 9, characterized in that an adjustment parameter (40) is determined depending on the success monitoring and the adjustment parameter (40) is taken into account when future learning content (12) is provided to the person (14). A method according to any of the preceding claims, characterized in that. A person profile (42) of the person (14) is specified to the electronic computing device (10), and the narration (26) is additionally generated depending on the person profile (42). A method according to one of the preceding claims, characterized in that the person profile (42) takes into account a genre preference (44) of the person (14) and / or an association (46) of the person (14) and / or prior knowledge (46) of the person (14). A computer program product with program code means which, when the program code means are executed by the electronic computing device (10), cause it to carry out a method according to one of claims 1 to 12. A computer-readable storage medium with a computer program product according to claim 13.Electronic computing device (10) for providing learning content (12) to a person (14) , comprising at least one input device (16) and one output device (18) , wherein the electronic computing device (10) is configured to perform a method according to one of claims 1 to 12.