ES2941817A1 - Personalization of content in digital books (Machine-translation by Google Translate, not legally binding) - Google Patents

Abstract

Personalization of content in digital books. The contents to be learned by students are usually presented through readings or images of digital books. After this reading, the teacher proposes exercises aimed at the comprehension problems that occur most frequently. However, not all students have the same comprehension problems, so it would be desirable if this comprehension could be evaluated and solved individually. To this end, the present invention describes a method and system for personalized presentation of textbook contents in digital format by means of a screen equipped with a camera that detects the movement of the eyes when reading and a software that allows determining what has been done. understood by the student and present those exercises that reinforce those specific areas for each student individually. (Machine-translation by Google Translate, not legally binding)

Description

DESCRIPTION

Personalization of content in digital books

TECHNIQUE SECTOR

The present invention relates to a method of presenting digital textbook content in a personalized and dynamic manner. More specifically, it describes a method for detecting comprehension problems about a text or an image presented in an educational environment and a proposal for solving such a problem. Therefore, the invention falls within the field of visualization of digital images and texts and has application in the field of learning.

BACKGROUND OF THE INVENTION

Currently, digital books are gaining ground on traditional paper books in all areas, especially affecting textbooks. Although the presentation of textbooks has changed to digital format, the way in which their content is displayed remains traditional, that is, texts accompanied by exercises that are offered in the same way to all students present in a classroom.

Thus, in the general development of a subject, the topics explained by teachers address content that is usually introduced to students through readings or images. After this initial reading, the teacher proposes exercises aimed at solving those comprehension problems that occur most frequently.

However, not all students have the same comprehension problems and, after a reading that contains relevant concepts or vocabulary on a particular topic, some students may have understood some aspects differently from others even though they all read the same text and saw the same images. That is, different understandings can be given from a common element; but the exercises on the proposed topic are usually the same for all students, without focusing on solving the problem that each one has in particular.

Therefore, it would be desirable that, starting from a common content presented in the classroom through a text, it would be possible to evaluate which part of this content presents difficulties for each student and thus be able to offer individually only the exercises that are going to reinforce and help understand that particular area, reviewing only those concepts that need reinforcement.

EXPLANATION OF THE INVENTION

The present invention describes a method and system for the personalized presentation of textbook contents that allows, from a common text, to detect the areas that cause comprehension difficulties for each student. To do this, starting from a book in digital format, the screen on which the student reads is equipped with a camera that detects the movement of the eyes when reading. These data are analyzed by an eye-tracker that determines what the student has not understood and shows (immediately or at the end of the reading) those exercises that reinforce those specific areas that each student has been able to understand individually. .

The digital textbook content personalized presentation system comprises a screen (for example, a tablet or a computer screen), an eyetracker, a processor equipped with software that analyzes the information recorded by the eye-tracker , and an associated corpus. in which are the resources created and/or selected by the teachers.

To do this, a text or images are displayed on the screen with the contents that are going to be treated. The text or images have identifiable elements, through a text marking system. It is necessary that there are adequate light conditions so that the camera can detect the eyes of the person reading the text or looking at the images. The eye-tracker records and evaluates the movement of the eyes on the marked items in the text or image, providing information on the comprehension of written language at the character, syllable, word, phrase or sentence level. Studying the time that the eyes stop in a certain area of the text or the number of regressions that occur on the same element, it is determined if there is confusion or lack of understanding in a specific point and the associated corpus is activated in which it is found. find the resources created or selected by the teacher to receive the appropriate reinforcement for the problem that has been found in the process of reading the text or viewing the image.

Thus, when the student reads the digital book on the screen, the eye-tracker follows his eye movements and will detect if he stops or returns to any point, indicating that he has problems with this specific element. Each item is connected to a repository with a collection of resources. These previously designed corpus-structured repositories respond to the different needs that you want to cover in a subject or topic. For example, let's imagine a text from a second language, it may have an associated corpus with vocabulary exercises classified into different themes and levels; and another additional corpus can collect grammar exercises of different difficulty. From this point on, once the student has finished reading the text and has had difficulty in any of the previously identified elements, the appropriate resources contained in the corresponding corpus are offered to help understand or reinforce this particular aspect of this particular student. That is, it is possible to identify and solve an individual problem starting from a common content.

The method developed allows the creation of itineraries so that learning can be carried out individually or as part of a group in a classroom. The method includes preparing teaching material, analyzing results collected by the eye-tracker and selecting exercises/reinforcement activities. For this, the method uses a program organized in three interconnected platforms; a first platform works as a front-end (visualization for students and teachers) and two platforms as backend (software related to the eye-tracker and software related to the corpus).

To prepare the texts/images in which the subject is introduced, once selected it is grouped into large areas of interest (AOI). These areas are identified in a process that is carried out with the eye-tracker software, which identifies those parts of the text or images that are going to be analyzed. Each AOI is assigned a unique identifier that has a double function: to classify that element in relation to the corresponding exercises and to identify the element to assign it a value in the results that are shown to the teacher after viewing the images or texts by from the student. On the other hand, the activities that are part of the corpus of exercises are tagged with another identifier that allows establishing a relationship between the AOI marked in the text and the corresponding exercise or reinforcement activity.

Once the material has been prepared, the student views it while the eye-tracker integrated into the device's camera (Tablet or computer) collects the following data:

- Total reading time

- Number of fixings

- Average fixing time

- Number of regressions

- Tempo of fixations that coincide with the AOIs identified in the text - AOIs whose fixation times are higher than the average

The results indicative of the need to perform a reinforcement exercise/activity in a given AOI may be:

a) There has been a higher than average fixation in an AOI in relation to the average number of fixations for the rest of the time

b) A regression to an AOI has occurred.

Both cases indicate that the cognitive effort for this AOI has been greater, requiring a longer processing time (above average fixation) or needing to return to the same point several times (regressions).

These data identified by the eye-tracker (number of regressions, average fixation time) are shown to the teacher. If data is obtained for several students, it is also possible to establish a comparison of the overall behavior of the group and of each student.

The acquisition, analysis of data and results are integrated into software that consists of three interconnected platforms: a front-end platform (students and teachers) and two back-end platforms, which are described below.

The front-end platform is for use by students and teachers and includes:

- Preparation of materials (texts/images/exercises)

- Loading of texts and images

- Visualization of texts and images

- Visualization of results

- Exercises

In the first place, the teacher can elaborate contents and define in them the areas of interest (AOI) to be evaluated. These contents are tagged with an identifier (ID) and are stored in the corpus associating them with a specific AOI.

From the text and image upload interface, the teacher can select texts and images (prepared and stored in the corpus) to show the students. These texts and images are accompanied by a description of the corresponding AOIs.

Students read the texts selected by the teacher on the screen of their Tablet or computer. The images and texts that are shown to the students do not have marks that would allow them to recognize the AOIs so that they do not interfere with reading. And once the reading is finished, the results are analyzed and the student will see on the screen the exercises related to the AOIs in which they have had difficulties.

These data displayed on the front-end are fed from the back-end to access the texts and exercises, offer the data and analyze the results.

The back-end platforms correspond to the eye-tracker software and the software in charge of managing the repositories or corpus containing exercises.

The eye-tracker software is installed on camera devices and collects the data needed to determine the difficulty of understanding texts and images. These data are the ones that are shown to the teacher (of each AOI if the ocular fixation time is higher or lower than the average number of fixations or if regressions have occurred in this AOI) and are linked to the AOI identifier that, at its time, it points to one of the sub-corpus that contains the texts and exercises.

The software in charge of managing the repositories or corpora containing exercises consists of two groups of corpora (Figure 6): the one that contains the predefined texts (in which the AOIs to which an ID has been assigned have been previously marked) and an "open" corpus in which to include the texts created and marked by the teacher (it offers the teacher the possibility of uploading their own texts by marking the AOIS with the tools provided by the eye-tracker). The corpus of exercises is stored within the "open" corpus, which is more complex (Figure 7), since it has to contemplate the types of areas and levels of interest in which the AOIs marked in the texts are classified and that are intended to reinforce in its implementation. In other words, the AOIs that are identified in the texts have to correspond to the study areas that the teaching materials address, as described above.

BRIEF DESCRIPTION OF THE DRAWINGS

To complete the description that is being made and in order to help a better understanding of the characteristics of the invention, a set of drawings is attached as an integral part of said description where, for illustrative and non-limiting purposes, it has been represented the process of implementing the described methodology:

Figure 1. Example of the selection of areas of interest, where the text areas to be evaluated are identified.

Figure 2. Example of presentation to the teacher of the analysis of the AOIs carried out by the student and the class group after reading a text.

Figure 3. List of texts / images available to the system for selection by the teacher.

Figure 4. Visualization of texts and images for the students, without marks that prevent their reading.

Figure 5. Example of an exercise as a student would see it after reading the text and selected according to the criteria of the method.

Figure 6. Corpus of texts with a subdivision in which they are grouped by the classification of defined work areas.

Figure 8. Summary of the described method.

PREFERRED EMBODIMENT OF THE INVENTION

The present invention is illustrated by the following examples, which are not intended to be limiting in scope.

Example 1.

This example shows the labeling of the texts and images that are part of the Areas of Interest (AOIs) of the corpus (Figure 1). The characteristics of these indicators (number of digits, indexing granularity) respond to a structure of the teaching materials included in the system. For example, A01.1.1. corresponds to word 1 of area of interest 1 within text 1; A01.1.1. corresponds to word 1 of area of interest 2 of text 1.

Example 2.

This example refers to the way in which the results of the reading of texts by the students are presented to the teacher.

Depending on the information needs, the results are presented individually or in groups (Figure 2), by areas of interest. The results can be presented in the form of tables or in the form of graphs.

Example 3.

An example of a list of texts or images that may be of interest to students is shown, and the teacher can select which of these areas to analyze for possible reinforcement (Figure 3). This element of content creation allows the teacher to upload texts or images that he wants to evaluate. These texts, in turn, are identified with an ID and are stored in the corpus. In turn, they are related to exercises or activities created by the teacher to reinforce the selected areas of interest.

Example 4.

This example refers to the visualization by the students of the texts and images selected by the teacher. As can be seen in Figure 4, this information is shown without recognizable marks of the AOIs so that they do not interfere with the reading.

Example 5.

Figure 5 shows an example of the visualization by the student of reinforcement exercises related to the AOIs in which you have had difficulty understanding.

Example 6.

A general example of the described method is shown: the selection of the text (1), its recovery from the text corpus (2), the text (3) that is shown to the students (in the figure they appear boxes but the students do not see this marked), the obtaining of results after the reading of texts by the students (4), the analysis of the same shown to the teacher (5), the selection of an exercise from the corpus according to the criteria obtained in the result (6) and the exercise related to the AOI (7).

Claims (7)

1. Method of personalized presentation of textbook contents through the claimed system that includes: - Prepare teaching material: to. Select teaching material made up of text and/or images b. Group material into areas of interest (AOI) c. Assign an identifier to each AOI d. Select reinforcement exercises and. Assign an identifier to each reinforcement exercise F. Create a corpus associated with the teaching material and the selected reinforcement exercises, relating the identifiers of each AOI with the corresponding reinforcement exercise identifiers of said AOI. - Show a student or group of students, on the screen of a digital device equipped with an eye-tracker, the prepared teaching material. - Record through the eye-tracker data of the movement of the student's eyes when studying each identified AOI. - Analyze the data recorded by the eye-tracker for each AOI and determine the AOI that have presented comprehension difficulties - Activate the corpus that contains reinforcement exercises to select those related to the AOI that have presented comprehension difficulties. - Present the selected reinforcement exercises to the student. 2. Method, according to claim 1, where the data recorded by the eye-tracker are the total reading time, the number of fixations on each AOI, the average time of fixations, the number of regressions and the time of fixations on each AOI. 3. Method, according to claim 1, wherein the analysis of data recorded by the eyetracker comprises determining for each AOI if there has been a higher than average number of fixations, a fixation time greater than the average, or one or more regressions. about said AOI. 4. Method, according to previous claims, where the corpus that contains exercises is activated for each AOI whose number of fixations, fixation time, or number of regressions is greater than the mean. 5. Personalized textbook content presentation system, according to the claimed method, comprising a screen (for example, a tablet or a computer screen), an eye-tracker, a processor equipped with software for processing data and an associated corpus containing created and/or selected teaching resources. 6. Personalized textbook content presentation system, according to claim 1, where the software consists of three platforms that communicate with each other: - A front-end platform is for use by students and teachers, which includes the preparation of teaching material (texts/images/exercises), the loading of texts and images, the visualization of texts and images, the visualization of results and exercises. - Two back-end platforms that correspond to the eyetracker software and the software in charge of managing the repositories or corpus containing exercises. 7. System, according to claim 5, where the corpus consists of a first group containing the predefined texts, in which the AOIs to which an identifier has been assigned have previously been marked; and a second group containing reinforcement exercises, also previously identified for each AOI.