A text readability evaluation system based on eye tracking technology

Abstract

The present application provides a text readability evaluation system based on eye tracking technology, the system includes: a computer, an eye tracking device, an artificial intelligence workstation and a first display, the computer includes a second display, wherein the computer performs the following steps: obtaining the focus area of ​​the subject captured by the eye tracking device when reading the informed consent form, wherein the informed consent form is displayed on the first display screen; judging whether the focus time of the subject looking at the focus area is greater than the preset first readable time; if the focus time of the subject looking at the focus area is greater than the preset first readable time, then displaying the annotation of the words to be explained in the text corresponding to the focus area on the second display screen; obtaining multiple text information of the informed consent form identified by the artificial intelligence workstation; and calculating the text readability score of the informed consent form according to the display times of the multiple text information and annotations of the informed consent form. The readability of the informed consent form can be determined more accurately.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a text readability evaluation system based on eye tracking technology. Background Art

[0002] The informed consent form is a document that proves that the subject voluntarily participates in medical research, clinical trials or other scientific and technological activities involving people. Its main purpose is to provide detailed information to participants, including the purpose, methods, potential risks and benefits of the research, to ensure that they voluntarily agree to participate on the premise of fully understanding all relevant information. The informed consent form is an important document to protect the rights and interests of the subjects, and it is also an important legal document to clarify the rights and responsibilities of all parties in the research process. The informed consent form needs to convey information to the subjects accurately and clearly, and its content should also be clearly stated and easy to read. However, since the text of the informed consent form in the medical field and other fields usually contains a large number of professional terms and complex sentence structures, it may be difficult for the general subjects to read and understand, which in turn affects the subjects' independent decision-making ability; interpreting all the professional content involved in the informed consent form will produce information overload, and the excessive length or dilution of the focus will indirectly lead to reading difficulties for the subjects. Therefore, evaluating the readability of the informed consent form and appropriately interpreting the professional content of the informed consent form will help enhance the readability of the informed consent form, thereby better protecting the informed rights and interests of the subjects.

[0003] At present, the readability evaluation methods for informed consent forms mainly include the Flesch-Kincaid scoring system, the SMOG score (Simple Measure of Gobbledygook SMOG), the Gunning Fog Index, etc., all of which are judged by breaking down the vocabulary of the informed consent form and comparing it with the total number of sentences or the number of professional (complex) words. On the one hand, these methods use English text as the evaluation object, and their scope of application is relatively limited; on the other hand, as mentioned in the above background, if the professional content is over-explained in order to improve the readability score, it will dilute the key points and also cause reading difficulties for the subjects.

[0004] Moreover, these traditional readability evaluation methods are mainly based on static text analysis. Although they can provide certain reference value for improving readability, they cannot reflect the subjects' actual understanding during the reading process in real time and dynamically. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a text readability evaluation system based on eye tracking technology, which can determine the text readability score of the informed consent form by capturing the subject's focus area through eye tracking equipment and analyzing the text of the informed consent form, thereby solving the problem in the prior art that the subject's actual understanding during the reading process cannot be reflected in real time and dynamically, and the readability of the informed consent form can be determined more accurately based on the subject's dynamic response.

[0006] In a first aspect, an embodiment of the present application provides a text readability evaluation system based on eye tracking technology, the system comprising: a computer, an eye tracking device, an artificial intelligence workstation and a first display, the computer comprising a second display, wherein the computer performs the following steps: obtaining a focus area of ​​a subject captured by the eye tracking device when reading an informed consent form, wherein the informed consent form is displayed on a first display screen; determining whether the focus time of the subject looking at the focus area is greater than a preset first readable time; if the focus time of the subject looking at the focus area is greater than the preset first readable time, displaying annotations of the to-be-explained words in the text corresponding to the focus area on the second display screen; obtaining multiple text information of the informed consent form identified by the artificial intelligence workstation; and calculating the text readability score of the informed consent form based on the multiple text information of the informed consent form and the number of times the annotation is displayed.

[0007] Optionally, the artificial intelligence workstation identifies multiple text information of the informed consent form through the following steps: based on natural language processing technology, each word in the informed consent form is identified and each word is numbered; each sentence in the informed consent form is identified and each sentence is numbered.

[0008] Optionally, the text readability score includes a static score and a dynamic score, wherein the computer calculates the static score of the informed consent form through the following steps: based on natural language processing technology, determining the total number of words, the number of complex words, the total number of terms and the number of explained terms corresponding to each word number in the text of the informed consent form; based on natural language processing technology, determining the total number of words and the total number of sentences corresponding to each sentence number in the text of the informed consent form; calculating the static score of the informed consent form based on the total number of sentences, the total number of words, the number of complex words, the total number of words, the total number of terms and the number of explained terms.

[0009] Optionally, the static score of the informed consent form is calculated by the following formula:

[0010]

[0011] Among them, α, β, and γ are adjustment coefficients.

[0012] Optionally, the computer further performs the following steps: determining whether the number of words to be explained that require word annotation in a single sentence is greater than a preset number; if the number of words to be explained that require word annotation in a single sentence is greater than a preset number, determining that the sentence is an annotated sentence to be explained.

[0013] Optionally, the computer calculates the dynamic score of the informed consent form through the following steps: calculating the dynamic score of the informed consent form based on the total number of sentences, the number of annotated sentences, the number of annotated words, the total number of words, and the total number of terms, wherein the number of gazed words is the number of words to be explained in the text.

[0014] Optionally, the dynamic score of the informed consent form is calculated by the following formula:

[0015]

[0016] Among them, α, β, and γ are adjustment coefficients.

[0017] Optionally, the computer further performs the following steps: calculating a first ratio based on the number of gazed sentences and the total number of sentences; calculating a second ratio based on the number of gazed words and the total number of words; determining whether the first ratio is greater than a first standard ratio, and determining whether the second ratio is greater than a second standard ratio; if the first ratio is greater than the first standard ratio, and / or the second ratio is greater than the second standard ratio, determining that the informed consent form exceeds the reading level of the subject.

[0018] Optionally, the computer further performs the following steps: judging whether the subject understands the contents of the informed consent form based on the static score and the dynamic score.

[0019] Optionally, the display size is not less than 21 inches, the distance between the subject and the center point of the screen is greater than or equal to 50 cm and less than or equal to 100 cm, the computer is placed on one side of the display and cannot block the eye tracking device and the display within the subject's visible area, and the computer and the display are placed outside the working field of the eye tracking device.

[0020] The text readability evaluation system based on eye tracking technology provided in the embodiment of the present application can determine the text readability score of the informed consent form by capturing the subject's focus area through eye tracking equipment and analyzing the text of the informed consent form, thereby solving the problem in the prior art that the subject's actual understanding during the reading process cannot be reflected in real time and dynamically, and the readability of the informed consent form is determined more accurately based on the subject's dynamic response.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A schematic diagram of a text readability evaluation system based on eye tracking technology provided in an embodiment of the present application;

[0024] Figure 2 The process of the steps performed by the computer provided in the embodiment of the present application Figure 1 ;

[0025] Figure 3 The process of the steps performed by the computer provided in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0026] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0027] First, the application scenarios to which this application is applicable are introduced. This application can be applied to the text readability evaluation of the informed consent form.

[0028] According to research, the informed consent form is a document that proves that the subject voluntarily participates in medical research, clinical trials or other scientific and technological activities involving people. Its main purpose is to provide detailed information to participants, including the purpose, methods, potential risks and benefits of the research, to ensure that they voluntarily agree to participate on the premise of fully understanding all relevant information. The informed consent form is an important document to protect the rights and interests of the subjects, and it is also an important legal document to clarify the rights and responsibilities of all parties in the research process. The informed consent form needs to convey information to the subjects accurately and clearly, and its content should also be clearly stated and easy to read. However, since the text of the informed consent form in the medical field and other fields usually contains a large number of professional terms and complex sentence structures, it may be difficult for the general subjects to read and understand, which in turn affects the subjects' independent decision-making ability; interpreting all the professional content involved in the informed consent form will produce information overload, and the excessive length or dilution of the focus will indirectly lead to reading difficulties for the subjects. Therefore, evaluating the readability of the informed consent form and appropriately interpreting the professional content of the informed consent form will help enhance the readability of the informed consent form, thereby better protecting the informed rights and interests of the subjects.

[0029] At present, the readability evaluation methods for informed consent forms mainly include the Flesch-Kincaid scoring system, the SMOG score (Simple Measure of Gobbledygook SMOG), the Gunning Fog Index, etc., all of which are judged by breaking down the vocabulary of the informed consent form and comparing it with the total number of sentences or the number of professional (complex) words. On the one hand, these methods use English text as the evaluation object, and their scope of application is relatively limited; on the other hand, as mentioned in the above background, if the professional content is over-explained in order to improve the readability score, it will dilute the key points and also cause reading difficulties for the subjects.

[0030] Moreover, these traditional readability evaluation methods are mainly based on static text analysis. Although they can provide certain reference value for improving readability, they cannot reflect the subjects' actual understanding during the reading process in real time and dynamically.

[0031] Based on this, an embodiment of the present application provides a text readability evaluation system based on eye tracking technology to achieve the effect of more accurately determining the readability of the informed consent form based on the dynamic response of the subject.

[0032] See also Figure 1 , Figure 1 This is a schematic diagram of a text readability evaluation system based on eye tracking technology provided in an embodiment of the present application. Figure 1As shown in , the text readability evaluation system based on eye tracking technology provided in the embodiment of the present application includes: a computer 101, an eye tracking device 102, an artificial intelligence workstation 104 and a first display 103. The computer includes a second display 1011.

[0033] Specifically, 10. The system according to claim 1 is characterized in that the display size is not less than 21 inches, and the distance between the subject and the center point of the screen is greater than or equal to 50 cm and less than or equal to 100 cm.

[0034] The computer is placed on one side of the display and cannot be blocked by the eye tracking device and the display within the visible area of ​​the subject. The computer and the display are placed outside the working field of the eye tracking device.

[0035] It should be noted that the eye tracking device (eye tracker) is used to collect and monitor the gaze position of the subject when reading the informed consent form, that is, to collect the focus area during the reading process. The first display is used to display the informed consent form sample to the subject and the researcher. The second display is used to display the large language model's explanation of professional terms. The artificial intelligence workstation is used to run the large language model and perform word segmentation on the informed consent form.

[0036] Among them, eye tracking devices can be selected from wearable eye trackers, desktop eye trackers, etc., but they must ensure that the accuracy and spatial resolution can meet the needs of focusing on a certain word, and the sensitivity and delay can meet the reading speed of normal people. Among them, the desktop eye tracker should be placed directly below the center line of the display. The operating distance of the eye tracking device must cover the distance between the above-mentioned subject and the center point of the screen.

[0037] Here, the technology of this application involves three basic technologies: (1) eye tracking technology, that is, through real-time tracking and analysis of the user's gaze focus and eye movement path, it is used to detect the unfamiliar and obscure words and sentences in the informed consent form for the subject, providing a basis for the next step of enhancing reading and calculation readability; (2) Natural Language Processing (NLP) technology, which is used in this patent for tokenization of natural sentences and calculation of the number of words (tokens) in the informed consent form; (3) Artificial Intelligence (AI) technology, that is, generative artificial intelligence (GenAI) technology based on the Transformer architecture. The large language model (LLM) used in this patent is used to interpret professional vocabulary and sentences for the subjects.

[0038] See also Figure 2 , Figure 2 The process of the steps performed by the computer provided in the embodiment of the present application Figure 1 .like Figure 2 As shown in , the steps performed by the computer provided in the application embodiment include:

[0039] S101. Obtain the focus area of ​​the subject when reading the informed consent form captured by the eye tracking device.

[0040] Wherein, the informed consent form is displayed on the first display screen.

[0041] S102: Determine whether the attention time of the subject gazing at the attention area is greater than a preset first readable time.

[0042] As an example, the preset first readable time may be 2-4 seconds.

[0043] S103: If the subject's attention time for gazing at the focus area is greater than a preset first readable time, an annotation of the words to be explained in the text corresponding to the focus area is displayed on the second display screen.

[0044] S104. Obtain multiple text information of the informed consent form identified by the artificial intelligence workstation.

[0045] Among them, the artificial intelligence workstation identifies multiple text information of the informed consent form through the following steps: based on natural language processing technology, each word in the informed consent form is identified and each word is numbered; each sentence in the informed consent form is identified and each sentence is numbered.

[0046] In this way, the sentences and words in the text can be marked more clearly and simply through word numbers and sentence numbers, and the explanations corresponding to the words can be called.

[0047] Exemplarily, the text can be segmented by an artificial intelligence workstation, and each word will be assigned a unique number for this reading; according to Chinese habits, sentences ending with a period, exclamation mark, question mark, or carriage return will be segmented, and each sentence will be assigned a unique number for this reading. The gaze time is calculated independently by a computer, and the gaze time can be accumulated. The subject begins to read. After starting to read, the gaze time of a single word is accumulated. When the single gaze time of a word exceeds 2 seconds, the computer system inputs the word into the large language model. The text display is controlled by the subject, and the page display is scrolled up and down using the mouse or keyboard.

[0048] For example, a word that the subject fixates on for more than 2 seconds will be marked as a fixation word, and the sentence containing the word will be marked as a fixation sentence. If the cumulative fixation time of more than three words in a single sentence exceeds 2 seconds, the sentence can be considered complex and the sentence will also be marked as a fixation sentence. A fixation word and a fixation sentence can only be marked once.

[0049] Optionally, if the number of fixation words or fixation sentences exceeds a certain proportion, it can be considered that this informed consent form exceeds the reading level of the subject, or the subject may have a certain degree of reading disability and requires researcher intervention.

[0050] S105 : Calculate a text readability score of the informed consent form according to the multiple text information of the informed consent form and the display times of the annotation.

[0051] Specifically, the text readability score includes a static score and a dynamic score.

[0052] Among them, the computer can calculate the static score of the informed consent form through the following steps: based on natural language processing technology, determine the total number of words, the number of complex words, the total number of terms and the number of explained terms corresponding to each word number in the text of the informed consent form; based on natural language processing technology, determine the total number of words and the total number of sentences corresponding to each sentence number in the text of the informed consent form; calculate the static score of the informed consent form according to the total number of sentences, the total number of words, the number of complex words, the total number of words, the total number of terms and the number of explained terms.

[0053] Specifically, the static score of the informed consent form can be calculated by the following formula:

[0054]

[0055] Among them, α, β, and γ are adjustment coefficients.

[0056] Specifically, the computer further performs the following steps: determining whether the number of words to be explained that need to be annotated in a single sentence is greater than a preset number; if the number of words to be explained that need to be annotated in a single sentence is greater than a preset number, determining that the sentence is an annotated sentence to be explained.

[0057] The computer calculates the dynamic score of the informed consent form through the following steps: the dynamic score of the informed consent form is calculated according to the total number of sentences, the number of annotated sentences, the number of annotated words, the total number of words, and the total number of terms, wherein the number of attention words is the number of words to be explained in the text.

[0058] Specifically, the dynamic score of the informed consent form can be calculated by the following formula:

[0059]

[0060] Among them, α, β, and γ are adjustment coefficients.

[0061] Specifically, the computer further performs the following steps: calculating a first ratio based on the number of gazed sentences and the total number of sentences; calculating a second ratio based on the number of gazed words and the total number of words; determining whether the first ratio is greater than a first standard ratio, and determining whether the second ratio is greater than a second standard ratio; if the first ratio is greater than the first standard ratio, and / or the second ratio is greater than the second standard ratio, determining that the informed consent exceeds the reading level of the subject.

[0062] In this way, by setting the readability score of the informed consent form into two scoring rules, static and dynamic, the words and sentences in the focus area, that is, the number of annotated sentences and the number of gazed words, are collected through eye tracking technology, and the total number of sentences, total number of words, number of complex words, and total number of words in the informed consent form text are calculated using natural language processing technology. The total number of terms and the number of explained terms are calculated using artificial intelligence technology to comprehensively evaluate the readability of the informed consent form.

[0063] Optionally, the computer further performs the following steps: judging whether the subject understands the contents of the informed consent form based on the static score and the dynamic score.

[0064] In this way, if the number of fixation words or fixation sentences exceeds a certain proportion, it can be considered that this informed consent form exceeds the reading level of the subjects, or the subjects may have a certain degree of reading difficulties, and the researchers can intervene.

[0065] As an example, see Figure 3 , Figure 3 The process of the steps performed by the computer provided in the embodiment of the present application Figure 2 .like Figure 3 As shown in , the steps performed by the computer provided in the embodiment of the present application include:

[0066] S201, monitoring the gaze area.

[0067] In this step, the eye tracking device monitors the area where the subject is focusing.

[0068] S202: Vocabulary selection.

[0069] In this step, the computer selects words that have been fixated for a certain period of time.

[0070] S203: Model input.

[0071] In this step, the words selected by the computer that exceed a certain fixation time are input into the large language model of the artificial intelligence workstation.

[0072] S204: Output vocabulary explanation.

[0073] In this step, the large language model of the artificial intelligence workstation outputs the explanation of the words.

[0074] S205, vocabulary explanation display.

[0075] In this step, the interpretation of the words output by the large language model is displayed to the subject via the second display.

[0076] S206. Calculate a readability score.

[0077] In this step, after the subject finishes reading, the computer calculates the readability score of the informed consent form for the subject.

[0078] The text readability evaluation system based on eye tracking technology provided in the present application can determine the text readability score of the informed consent form by capturing the subject's focus area through eye tracking equipment and analyzing the text of the informed consent form, thereby solving the problem in the prior art that the subject's actual understanding during the reading process cannot be reflected in real time and dynamically, and the readability of the informed consent form can be determined more accurately based on the subject's dynamic response.

[0079] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0082] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0083] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A text readability evaluation system based on eye tracking technology, characterized in that: The system comprises: a computer, an eye tracking device, an artificial intelligence workstation and a first display, wherein the computer comprises a second display, The computer performs the following steps: Acquire a focus area of ​​the subject captured by an eye tracking device when the subject is reading an informed consent form, wherein the informed consent form is displayed on a first display screen; Determining whether the attention time of the subject looking at the attention area is greater than a preset first readable time; If the subject's attention time for gazing at the focus area is greater than a preset first readable time, displaying an annotation of the words to be explained in the text corresponding to the focus area on the second display screen; Acquire multiple text information of the informed consent form identified by the artificial intelligence workstation; A text readability score of the informed consent form is calculated based on the multiple text information of the informed consent form and the display times of the annotation.

2. The system according to claim 1, characterized in that The artificial intelligence workstation identifies multiple text information of the informed consent form through the following steps: Based on natural language processing technology, each word in the informed consent form is identified and each word is numbered; Each sentence in the informed consent form was identified and each sentence was numbered.

3. The system according to claim 1, characterized in that The text readability score includes a static score and a dynamic score. The computer calculates the static score of the informed consent form through the following steps: Based on natural language processing technology, the total number of words, the number of complex words, the total number of terms and the number of explained terms corresponding to each word number in the text of the informed consent form are determined; Based on natural language processing technology, the total number of words and the total number of sentences corresponding to each sentence number in the text of the informed consent form are determined; The static score of the informed consent form was calculated based on the total number of sentences, total number of words, number of complex words, total number of words, total number of terms and number of explained terms.

4. The system according to claim 3, characterized in that The static score of the informed consent form is calculated by the following formula: Among them, α, β, and γ are adjustment coefficients.

5. The system according to claim 1, characterized in that The computer also performs the following steps: Determine whether the number of words to be explained that need to be annotated in a single sentence is greater than a preset number; If the number of words to be explained that need to be annotated in a single sentence is greater than a preset number, the sentence is determined to be an annotated sentence to be explained.

6. The system according to claim 5, characterized in that The computer calculates the dynamic score of the informed consent form by the following steps: The dynamic score of the informed consent form is calculated according to the total number of sentences, the number of annotated sentences, the number of annotated words, the total number of words, and the total number of terms, wherein the number of fixated words is the number of words to be explained in the text.

7. The system according to claim 6, characterized in that The dynamic score of the informed consent form is calculated by the following formula: Among them, α, β, and γ are adjustment coefficients.

8. The system according to claim 6, characterized in that The computer also performs the following steps: The first ratio was calculated based on the number of fixation sentences and the total number of sentences; The second ratio was calculated based on the number of fixated words and the total number of words; Determining whether the first ratio is greater than the first standard ratio, and determining whether the second ratio is greater than the second standard ratio; If the first ratio is greater than the first standard ratio, and / or the second ratio is greater than the second standard ratio, it is determined that the informed consent form exceeds the reading level of the subject.

9. The system according to claim 1, characterized in that The computer also performs the following steps: Based on the static and dynamic scores, it is determined whether the subjects understand the contents of the informed consent form.

10. The system according to claim 1, characterized in that The display size is not less than 21 inches, and the distance between the subject and the center point of the screen is greater than or equal to 50 cm and less than or equal to 100 cm, The computer is placed on one side of the display and cannot be blocked by the eye tracking device and the display within the visible area of ​​the subject. The computer and the display are placed outside the working field of the eye tracking device.

Images