Vocabulary quantity test system and test method based on eye tracker

Abstract

The invention relates to the technical field of vocabulary quantity testing, and discloses a vocabulary quantity testing system and method based on an eye tracker, and the system comprises a collection module which is used for collecting eye movement data of a user within a specified time, and building an eye movement data set based on the eye movement data; the processing module is used for constructing an eye movement characteristic model according to the eye movement data set and acquiring an eye movement characteristic index; comparing the eye movement characteristic index with an eye movement characteristic index threshold value, and judging the English level of the user according to a comparison result; and the analysis module is used for collecting the content complexity of each word filling game, comparing the content complexity of each word filling game with a content complexity threshold value, and judging whether the English level of the user is adjusted or not according to a comparison result. By combining the eye movement data and the content complexity of the word filling game, the English level of the user can be evaluated and adjusted more comprehensively and more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of vocabulary testing, and in particular to a vocabulary testing system and a testing method based on an eye tracker. Background Art

[0002] Eye trackers are devices used to measure and record eye movements and are widely used in psychology, neuroscience, human-computer interaction and other fields. In recent years, with the continuous development of eye tracker technology, its application in the field of education has gradually increased. Especially in language learning and vocabulary testing, eye trackers can provide more objective and accurate evaluation data.

[0003] However, traditional vocabulary test methods mainly rely on paper-and-pencil tests or computer software, which often cannot fully reflect the subject's performance in actual language use. In addition, these test methods usually require subjects to give explicit answers, which are easily affected by subjective factors and lead to inaccurate test results.

[0004] In order to solve the above problems, the present invention proposes a vocabulary testing system and testing method based on an eye tracker. Summary of the invention

[0005] In view of this, the present invention proposes a vocabulary testing system and testing method based on an eye tracker, aiming to solve the problem that traditional vocabulary testing methods are easily affected by subjective factors, resulting in inaccurate test results.

[0006] In one aspect, the present invention provides a vocabulary testing system based on an eye tracker, comprising:

[0007] A collection module, used to collect the user's eye movement data within a specified time, and establish an eye movement data set based on the eye movement data;

[0008] A processing module, configured to construct an eye movement feature model according to the eye movement data set and obtain an eye movement feature index; compare the eye movement feature index with an eye movement feature index threshold, and determine the English proficiency level of the user according to the comparison result;

[0009] The analysis module collects the content complexity of each crossword puzzle, and compares the content complexity of each crossword puzzle with the content complexity threshold, and determines whether to adjust the English proficiency level of the user according to the comparison result; when it is determined that the English proficiency level of the user is to be adjusted, the difficulty level of the crossword puzzle is obtained according to the content complexity, the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, and the adjusted English proficiency level is obtained.

[0010] Furthermore, collecting the eye movement data of the user within a specified time and establishing an eye movement data set based on the eye movement data includes:

[0011] The eye movement data includes the user's gaze time on each space of the crossword puzzle within a specified time, the number of gazes on each space, the movement speed between spaces, the movement distance between spaces, the number of times the user returns to the previously gazed space, and the gaze path.

[0012] Furthermore, when an eye movement feature model is constructed based on the eye movement data set and an eye movement feature index is obtained, it includes:

[0013] The eye movement characteristic index is obtained by the following formula:

[0014] Y=α*Ta+βTt+γVa+δRt

[0015] Wherein, Y represents the eye movement feature index; Ta represents the average value of the user's gaze time on each space in the crossword puzzle within the specified time; Tt represents the total number of times the user gazes on each space in the crossword puzzle within the specified time; Va represents the average value of the user's moving speed between spaces in the crossword puzzle within the specified time; Rt represents the total number of times the user returns to the previously gazed space in the crossword puzzle within the specified time; α, β, γ and δ are weight coefficients, and the sum of α, β, γ and δ is 1.

[0016] Furthermore, comparing the eye movement feature index with the eye movement feature index threshold, and judging the English proficiency level of the user according to the comparison result, includes:

[0017] The eye movement feature index is compared with a first eye movement feature threshold, a second eye movement feature threshold and a third eye movement feature threshold that are preset, and the first eye movement feature threshold is smaller than the second eye movement feature threshold, and the second eye movement feature threshold is smaller than the third eye movement feature threshold, and the English proficiency level of the user is determined according to the comparison results;

[0018] When the eye movement feature index is less than or equal to the first eye movement feature threshold, determining that the English proficiency level of the user is at the first level;

[0019] When the eye movement feature index is greater than the first eye movement feature threshold and less than or equal to the second eye movement feature index threshold, determining that the English proficiency level of the user is the second level;

[0020] When the eye movement feature index is greater than the second eye movement feature threshold and less than or equal to the third eye movement feature index threshold, determining that the English proficiency level of the user is at the third level;

[0021] When the eye movement feature index is greater than the third eye movement feature threshold, determining that the English proficiency level of the user is at the fourth level;

[0022] The first level is smaller than the second level, the second level is smaller than the third level, and the third level is smaller than the fourth level.

[0023] Furthermore, when the content complexity of each crossword puzzle is compared with a content complexity threshold, the content complexity is obtained in the following manner:

[0024] calculating an average of the lengths of the words in the crossword puzzle;

[0025]

[0026] Wherein, n represents the total number of words in the crossword puzzle, Wi represents the i-th word in the crossword puzzle, and len(Wi) represents the length of the i-th word in the crossword puzzle;

[0027] Calculating an average difficulty level of the words in the crossword puzzle;

[0028]

[0029] Wherein, d(Wi) represents the difficulty coefficient of the i-th word in the crossword puzzle;

[0030] Counting the number of intersecting words in the crossword puzzle;

[0031]

[0032] Where k is the number of interleaved word pairs in the crossword puzzle;

[0033] Calculating the ratio of the number of spaces to the number of words in the crossword puzzle;

[0034]

[0035] Wherein, Ts represents the total number of spaces in the crossword puzzle;

[0036] Calculate content complexity;

[0037] F = εL + ζD + ηC + θS;

[0038] Among them, F represents the content complexity; L represents the average value of the word length in the crossword puzzle; D represents the average value of the word difficulty coefficient in the crossword puzzle; C represents the number of intersecting words in the crossword puzzle; S represents the ratio of the number of spaces to the number of words in the crossword puzzle; ε, ζ, η and θ are weight coefficients, and the sum of ε, ζ, η, θ is 1.

[0039] Further, judging whether to adjust the English proficiency level of the user according to the comparison result includes:

[0040] When the content complexity is less than or equal to the complexity threshold, determining not to adjust the English proficiency level of the user;

[0041] When the content complexity is greater than the complexity threshold, it is determined to adjust the English proficiency level of the user.

[0042] Further, obtaining the difficulty level of the crossword puzzle according to the content complexity includes:

[0043] Comparing the content complexity with a preset difficulty level threshold, wherein the difficulty level threshold includes three levels: a primary difficulty level threshold, an intermediate difficulty level threshold, and a high difficulty level threshold, and determining the difficulty level of the crossword puzzle according to the comparison result;

[0044] When the content complexity is less than or equal to the primary difficulty level threshold, determining the difficulty level of the crossword puzzle to be primary;

[0045] When the content complexity is greater than the primary difficulty level threshold and less than or equal to the intermediate difficulty level threshold, determining that the difficulty level of the crossword puzzle is intermediate;

[0046] When the content complexity is greater than the intermediate difficulty level threshold and less than or equal to the advanced difficulty level threshold, determining that the difficulty level of the crossword puzzle is advanced;

[0047] When the content complexity is greater than the advanced difficulty level threshold, the difficulty level of the crossword puzzle is determined to be super advanced.

[0048] Further, when adjusting the English proficiency level of the user according to the difficulty level of the crossword puzzle, it includes:

[0049] When the difficulty level of the crossword puzzle is determined to be elementary, and the user completes the answer within the specified time, the current English proficiency level of the user is maintained unchanged;

[0050] When the difficulty level of the crossword puzzle is determined to be intermediate, and the user completes the answer within the specified time, the English proficiency level of the user is adjusted upward by one level or remains unchanged;

[0051] When the difficulty level of the crossword puzzle is determined to be advanced, and the user completes the answer within the specified time, the user's English proficiency level is adjusted upward by two levels or remains unchanged;

[0052] When the difficulty level of the crossword puzzle is determined to be super advanced, and the user completes the answer within the specified time, the user's English proficiency level is adjusted upward by three levels or remains unchanged;

[0053] Among them, the user's English proficiency level is raised to the fourth level at most.

[0054] Furthermore, when the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, it also includes:

[0055] When the difficulty level of the crossword puzzle is determined to be elementary, and the user fails to complete the answer within the specified time, the English proficiency level of the user is adjusted down by three levels or remains unchanged;

[0056] When the difficulty level of the crossword puzzle is determined to be intermediate, and the user fails to complete the answer within the specified time, the user's English proficiency level is adjusted down by two levels or remains unchanged;

[0057] When the difficulty level of the crossword puzzle is determined to be high, and the user completes the answer within the specified time, the English proficiency level of the user is adjusted down by one level or remains unchanged;

[0058] When the difficulty level of the crossword puzzle is determined to be super advanced, and the user completes the answer within the specified time, the current English proficiency level of the user is maintained unchanged;

[0059] The user's English proficiency level is lowered to the first level at least.

[0060] Compared with the prior art, the present invention has the following beneficial effects: by combining eye tracker data with analysis of the complexity of crossword puzzle content, the present invention can more comprehensively evaluate the user's English proficiency. Eye tracker data can provide the user's physiological response when reading and processing language information, thereby revealing the depth and breadth of their language processing ability. By comparing the eye movement feature index with a preset threshold, the user's English proficiency can be evaluated more objectively, rather than just relying on the completion of the crossword puzzle.

[0061] The eye-tracker-based vocabulary test system and test method provided by the present invention can more comprehensively and accurately evaluate and adjust the user's English proficiency level by combining eye-tracking data and the content complexity of crossword puzzles. This test method not only improves the objectivity and accuracy of the test, but also can provide users with personalized learning suggestions, thereby helping users to improve their English proficiency more effectively.

[0062] In another aspect, the present invention also proposes a vocabulary testing method based on an eye tracker, comprising the following steps:

[0063] S100: collecting eye movement data of a user within a specified time, and establishing an eye movement data set based on the eye movement data;

[0064] S200: constructing an eye movement feature model according to the eye movement data set to obtain an eye movement feature index; comparing the eye movement feature index with an eye movement feature index threshold, and determining the English proficiency level of the user according to the comparison result;

[0065] S300: collecting the content complexity of each crossword puzzle, and comparing the content complexity of each crossword puzzle with a content complexity threshold, and determining whether to adjust the English proficiency level of the user according to the comparison result;

[0066] S400: When it is determined that the English proficiency level of the user is to be adjusted, the difficulty level of the crossword puzzle is obtained according to the content complexity, the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, and the adjusted English proficiency level is obtained.

[0067] It is understandable that the above-mentioned vocabulary test system and test method based on eye tracker have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0069] Figure 1 A structural block diagram of a vocabulary testing system based on an eye tracker provided in an embodiment of the present invention;

[0070] Figure 2 The present invention provides a flowchart of a vocabulary testing method based on an eye tracker. DETAILED DESCRIPTION

[0071] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0072] See also Figure 1As shown, in some embodiments of the present application, this embodiment provides a vocabulary testing system based on an eye tracker, comprising:

[0073] A collection module, used to collect the user's eye movement data within a specified time, and establish an eye movement data set based on the eye movement data;

[0074] In some embodiments of the present application, the acquisition module can more accurately reflect the user's reading habits and vocabulary mastery by collecting the user's eye movement data within a specified time. Since the eye tracker can capture the user's gaze point, gaze time, scanning path and other information during the reading process, these data can reveal the user's familiarity with the vocabulary and the depth of understanding when reading. For example, for familiar words, users tend to have a shorter gaze time and a smoother scanning path; while for unfamiliar words, the gaze time will be prolonged and the scanning path may jump repeatedly. By analyzing these eye movement data, the user's English level can be evaluated more objectively.

[0075] A processing module, configured to construct an eye movement feature model according to the eye movement data set and obtain an eye movement feature index; compare the eye movement feature index with an eye movement feature index threshold, and determine the English proficiency level of the user according to the comparison result;

[0076] In some embodiments of the present application, the processing module can convert these complex eye movement data into quantifiable indicators by constructing an eye movement feature model. The eye movement feature index can include multiple dimensions such as the number of fixations, fixation time, and scanning speed. These indexes comprehensively reflect the user's cognitive load and vocabulary processing ability during the reading process. By comparing with the eye movement feature index threshold, the user's English proficiency level can be judged more accurately, thereby avoiding the subjective bias that may occur in traditional testing methods.

[0077] The analysis module collects the content complexity of each crossword puzzle, and compares the content complexity of each crossword puzzle with the content complexity threshold, and determines whether to adjust the English proficiency level of the user according to the comparison result; when it is determined that the English proficiency level of the user is to be adjusted, the difficulty level of the crossword puzzle is obtained according to the content complexity, the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, and the adjusted English proficiency level is obtained.

[0078] In some embodiments of the present application, the analysis module further combines the content complexity of the crossword puzzle to dynamically adjust the user's English proficiency level. As a language game, the difficulty level of the crossword puzzle is closely related to factors such as the complexity of vocabulary and the complexity of sentence structure. By analyzing the content complexity of the crossword puzzle, the user's ability in actual language application can be more comprehensively evaluated. For example, a crossword puzzle of elementary difficulty may involve basic vocabulary and simple sentence patterns, while a crossword puzzle of super advanced difficulty may contain professional terms and complex sentence patterns. Adjusting the user's English proficiency level according to these difficulty levels can more effectively promote the user's learning progress.

[0079] In summary, the vocabulary test system and test method based on the eye tracker provided by the present invention can more comprehensively and accurately evaluate and adjust the user's English proficiency level by combining eye movement data and the content complexity of the crossword puzzle. This test method not only improves the objectivity and accuracy of the test, but also can provide users with personalized learning suggestions, thereby helping users to improve their English proficiency more effectively.

[0080] Specifically, collecting the user's eye movement data within a specified time and establishing an eye movement data set based on the eye movement data includes:

[0081] The eye movement data includes the user's gaze time on each space of the crossword puzzle within a specified time, the number of gazes on each space, the movement speed between spaces, the movement distance between spaces, the number of times the user returns to the previously gazed space, and the gaze path.

[0082] It can be seen that when constructing the eye movement feature model, the processing module will comprehensively consider these eye movement data and convert them into eye movement feature indexes. For example, spaces with shorter fixation time and fewer fixations may correspond to lower eye movement feature indexes, while spaces with longer fixation time and more fixations may correspond to higher eye movement feature indexes. Through these indexes, the processing module can more accurately evaluate the user's performance in the crossword puzzle and judge the user's English proficiency level accordingly.

[0083] Specifically, when building an eye movement feature model according to the eye movement data set and obtaining an eye movement feature index, it includes:

[0084] The eye movement characteristic index is obtained by the following formula:

[0085] Y=α*Ta+βTt+γVa+δRt

[0086] Wherein, Y represents the eye movement feature index; Ta represents the average value of the user's gaze time on each space in the crossword puzzle within the specified time; Tt represents the total number of times the user gazes on each space in the crossword puzzle within the specified time; Va represents the average value of the user's moving speed between spaces in the crossword puzzle within the specified time; Rt represents the total number of times the user returns to the previously gazed space in the crossword puzzle within the specified time; α, β, γ and δ are weight coefficients, and the sum of α, β, γ and δ is 1.

[0087] It can be seen that the setting of weight coefficients α, β, γ, and δ is based on the statistical analysis of a large number of user eye movement data. Different weight coefficients reflect the importance of different eye movement features in assessing English proficiency. For example, higher values ​​of α and β may mean that fixation time and number of fixations are more critical in the assessment process because they are directly related to the user's familiarity with vocabulary and depth of understanding. Lower values ​​of γ and δ may indicate that although movement speed and number of returns also provide useful information, their contribution to the overall assessment is relatively small. In practical applications, the determination of weight coefficients can be achieved through machine learning algorithms. Through the training data set, the algorithm can automatically adjust the weight coefficients to achieve the best evaluation effect. In addition, the weight coefficients can also be adjusted according to different test scenarios to adapt to different types of crossword puzzles and user groups.

[0088] Specifically, comparing the eye movement feature index with the eye movement feature index threshold, and judging the English proficiency level of the user according to the comparison result, includes:

[0089] The eye movement feature index is compared with a first eye movement feature threshold, a second eye movement feature threshold and a third eye movement feature threshold that are preset, and the first eye movement feature threshold is smaller than the second eye movement feature threshold, and the second eye movement feature threshold is smaller than the third eye movement feature threshold, and the English proficiency level of the user is determined according to the comparison results;

[0090] When the eye movement feature index is less than or equal to the first eye movement feature threshold, determining that the English proficiency level of the user is at the first level;

[0091] When the eye movement feature index is greater than the first eye movement feature threshold and less than or equal to the second eye movement feature index threshold, determining that the English proficiency level of the user is the second level;

[0092] When the eye movement feature index is greater than the second eye movement feature threshold and less than or equal to the third eye movement feature index threshold, determining that the English proficiency level of the user is at the third level;

[0093] When the eye movement feature index is greater than the third eye movement feature threshold, determining that the English proficiency level of the user is at the fourth level;

[0094] The first level is smaller than the second level, the second level is smaller than the third level, and the third level is smaller than the fourth level.

[0095] It can be seen that by setting different eye movement feature index thresholds, users' performance in crossword puzzles can be divided into different English proficiency levels. This grading method helps to understand the user's ability level more carefully, thereby providing more targeted learning suggestions.

[0096] Specifically, when the content complexity of each crossword puzzle is compared with the content complexity threshold, the content complexity is obtained in the following manner:

[0097] calculating an average of the lengths of the words in the crossword puzzle;

[0098]

[0099] Wherein, n represents the total number of words in the crossword puzzle, Wi represents the i-th word in the crossword puzzle, and len(Wi) represents the length of the i-th word in the crossword puzzle;

[0100] Calculating an average difficulty level of the words in the crossword puzzle;

[0101]

[0102] Wherein, d(Wi) represents the difficulty coefficient of the i-th word in the crossword puzzle;

[0103] Counting the number of intersecting words in the crossword puzzle;

[0104]

[0105] Where k is the number of interleaved word pairs in the crossword puzzle;

[0106] Calculating the ratio of the number of spaces to the number of words in the crossword puzzle;

[0107]

[0108] Wherein, Ts represents the total number of spaces in the crossword puzzle;

[0109] Calculate content complexity;

[0110] F = εL + ζD + ηC + θS;

[0111] Among them, F represents the content complexity; L represents the average value of the word length in the crossword puzzle; D represents the average value of the word difficulty coefficient in the crossword puzzle; C represents the number of intersecting words in the crossword puzzle; S represents the ratio of the number of spaces to the number of words in the crossword puzzle; ε, ζ, η and θ are weight coefficients, and the sum of ε, ζ, η, θ is 1.

[0112] It can be seen that the setting of weight coefficients ε, ζ, η and θ is also based on the statistical analysis of a large amount of crossword puzzle data. Different weight coefficients reflect the importance of word length, difficulty coefficient, number of crossed words, and the ratio of the number of spaces to the number of words in evaluating the complexity of crossword puzzle content. For example, higher values ​​of ε and ζ may mean that word length and difficulty coefficient are more critical in the evaluation process because they are directly related to the difficulty of the game and the challenge for users to solve the problem. Lower values ​​of η and θ may indicate that although the number of crossed words and the ratio of the number of spaces to the number of words also provide useful information, their contribution to the overall evaluation is relatively small.

[0113] Specifically, judging whether to adjust the English proficiency level of the user according to the comparison result includes:

[0114] When the content complexity is less than or equal to the complexity threshold, determining not to adjust the English proficiency level of the user;

[0115] When the content complexity is greater than the complexity threshold, it is determined to adjust the English proficiency level of the user.

[0116] It can be seen that by considering the content complexity of the crossword puzzle, the user's English proficiency can be assessed more accurately. If the game content is too complex, the user's performance may be limited and fail to truly reflect their English ability. Therefore, when the content complexity exceeds a certain threshold, the user's English proficiency level needs to be adjusted to ensure the fairness and accuracy of the assessment results.

[0117] Specifically, obtaining the difficulty level of the crossword puzzle according to the content complexity includes:

[0118] Comparing the content complexity with a preset difficulty level threshold, wherein the difficulty level threshold includes three levels: a primary difficulty level threshold, an intermediate difficulty level threshold, and a high difficulty level threshold, and determining the difficulty level of the crossword puzzle according to the comparison result;

[0119] When the content complexity is less than or equal to the primary difficulty level threshold, determining the difficulty level of the crossword puzzle to be primary;

[0120] When the content complexity is greater than the primary difficulty level threshold and less than or equal to the intermediate difficulty level threshold, determining that the difficulty level of the crossword puzzle is intermediate;

[0121] When the content complexity is greater than the intermediate difficulty level threshold and less than or equal to the advanced difficulty level threshold, determining that the difficulty level of the crossword puzzle is advanced;

[0122] When the content complexity is greater than the advanced difficulty level threshold, the difficulty level of the crossword puzzle is determined to be super advanced.

[0123] It can be seen that by setting different levels of difficulty thresholds, crossword puzzles can be divided into different difficulty levels, thereby providing users with a more challenging gaming experience. This grading method helps users choose the appropriate game difficulty according to their own abilities, so that they can improve their English proficiency while enjoying the game. Specifically, when a user performs well in a crossword puzzle and the content complexity is within an acceptable range, the user's English proficiency level can be considered to be increased. On the contrary, if a user performs poorly in a relatively simple game, the user's English proficiency level may need to be lowered to ensure the accuracy of the evaluation results.

[0124] Specifically, when adjusting the English proficiency level of the user according to the difficulty level of the crossword puzzle, it includes:

[0125] When the difficulty level of the crossword puzzle is determined to be elementary, and the user completes the answer within the specified time, the current English proficiency level of the user is maintained unchanged;

[0126] When the difficulty level of the crossword puzzle is determined to be intermediate, and the user completes the answer within the specified time, the English proficiency level of the user is adjusted upward by one level or remains unchanged;

[0127] When the difficulty level of the crossword puzzle is determined to be advanced, and the user completes the answer within the specified time, the user's English proficiency level is adjusted upward by two levels or remains unchanged;

[0128] When the difficulty level of the crossword puzzle is determined to be super advanced, and the user completes the answer within the specified time, the user's English proficiency level is adjusted upward by three levels or remains unchanged;

[0129] Among them, the user's English proficiency level is raised to the fourth level at most.

[0130] Specifically, when adjusting the English proficiency level of the user according to the difficulty level of the crossword puzzle, it also includes:

[0131] When the difficulty level of the crossword puzzle is determined to be elementary, and the user fails to complete the answer within the specified time, the English proficiency level of the user is adjusted down by three levels or remains unchanged;

[0132] When the difficulty level of the crossword puzzle is determined to be intermediate, and the user fails to complete the answer within the specified time, the user's English proficiency level is adjusted down by two levels or remains unchanged;

[0133] When the difficulty level of the crossword puzzle is determined to be high, and the user completes the answer within the specified time, the English proficiency level of the user is adjusted down by one level or remains unchanged;

[0134] When the difficulty level of the crossword puzzle is determined to be super advanced, and the user completes the answer within the specified time, the current English proficiency level of the user is maintained unchanged;

[0135] The user's English proficiency level is lowered to the first level at least.

[0136] It can be seen that this meticulous adjustment mechanism ensures that the user's performance in the crossword puzzle is reasonably evaluated. When a user fails to complete the answer on time in a game of elementary difficulty, it may indicate that his English foundation needs to be strengthened, so his English level needs to be adjusted down significantly. In higher-level games, even if the answer is not completed on time, the downward adjustment is relatively small, because the difficulty of high-level games is inherently high, and failure to complete the answer does not necessarily mean low English level.

[0137] See also Figure 2 As shown, in some embodiments of the present application, this embodiment provides a vocabulary testing method based on an eye tracker, comprising the following steps:

[0138] S100: collecting eye movement data of a user within a specified time, and establishing an eye movement data set based on the eye movement data;

[0139] S200: constructing an eye movement feature model according to the eye movement data set to obtain an eye movement feature index; comparing the eye movement feature index with an eye movement feature index threshold, and determining the English proficiency level of the user according to the comparison result;

[0140] S300: collecting the content complexity of each crossword puzzle, and comparing the content complexity of each crossword puzzle with a content complexity threshold, and determining whether to adjust the English proficiency level of the user according to the comparison result;

[0141] S400: When it is determined that the English proficiency level of the user is to be adjusted, the difficulty level of the crossword puzzle is obtained according to the content complexity, the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, and the adjusted English proficiency level is obtained.

[0142] It can be seen that by combining the eye tracker data and the analysis of the complexity of the crossword puzzle content, the user's English level can be more comprehensively assessed. Eye tracker data can provide users with physiological responses when reading and processing language information, thereby revealing the depth and breadth of their language processing ability. By comparing the eye movement feature index with the preset threshold, the user's English level can be assessed more objectively, rather than just relying on the completion of the crossword puzzle.

[0143] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0144] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A vocabulary testing system based on an eye tracker, the characteristics of which are as follows: A collection module, used to collect the user's eye movement data within a specified time, and establish an eye movement data set based on the eye movement data; A processing module, used for constructing an eye movement feature model according to the eye movement data set and obtaining an eye movement feature index; Comparing the eye movement feature index with an eye movement feature index threshold, and determining the English proficiency level of the user according to the comparison result; The analysis module collects the content complexity of each crossword puzzle, and compares the content complexity of each crossword puzzle with the content complexity threshold, and determines whether to adjust the English proficiency level of the user according to the comparison result; when it is determined that the English proficiency level of the user is to be adjusted, the difficulty level of the crossword puzzle is obtained according to the content complexity, the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, and the adjusted English proficiency level is obtained.

2. The vocabulary testing system based on eye tracker according to claim 1, characterized in that: Collecting the user's eye movement data within a specified time and establishing an eye movement data set based on the eye movement data includes: The eye movement data includes the user's gaze time on each space of the crossword puzzle within a specified time, the number of gazes on each space, the movement speed between spaces, the movement distance between spaces, the number of times the user returns to the previously gazed space, and the gaze path.

3. The vocabulary testing system based on eye tracker according to claim 2, characterized in that: Building an eye movement feature model according to the eye movement data set and obtaining an eye movement feature index includes: The eye movement characteristic index is obtained by the following formula: Y=α*Ta+βTt+γVa+δRt Wherein, Y represents the eye movement feature index; Ta represents the average value of the user's gaze time on each space in the crossword puzzle within the specified time; Tt represents the total number of times the user gazes on each space in the crossword puzzle within the specified time; Va represents the average value of the user's moving speed between spaces in the crossword puzzle within the specified time; Rt represents the total number of times the user returns to the previously gazed space in the crossword puzzle within the specified time; α, β, γ and δ are weight coefficients, and the sum of α, β, γ and δ is 1.

4. The vocabulary testing system based on eye tracker according to claim 3, characterized in that: The eye movement feature index is compared with the eye movement feature index threshold, and the English proficiency level of the user is determined according to the comparison result, including: The eye movement feature index is compared with a first eye movement feature threshold, a second eye movement feature threshold and a third eye movement feature threshold that are preset, and the first eye movement feature threshold is smaller than the second eye movement feature threshold, and the second eye movement feature threshold is smaller than the third eye movement feature threshold, and the English proficiency level of the user is determined according to the comparison results; When the eye movement feature index is less than or equal to the first eye movement feature threshold, determining that the English proficiency level of the user is at the first level; When the eye movement feature index is greater than the first eye movement feature threshold and less than or equal to the second eye movement feature index threshold, determining that the English proficiency level of the user is the second level; When the eye movement feature index is greater than the second eye movement feature threshold and less than or equal to the third eye movement feature index threshold, determining that the English proficiency level of the user is at the third level; When the eye movement feature index is greater than the third eye movement feature threshold, determining that the English proficiency level of the user is at the fourth level; The first level is smaller than the second level, the second level is smaller than the third level, and the third level is smaller than the fourth level.

5. The vocabulary testing system based on eye tracker according to claim 4, characterized in that: When the content complexity of each crossword puzzle is compared with the content complexity threshold, the content complexity is obtained in the following manner: calculating an average of the lengths of the words in the crossword puzzle; Wherein, n represents the total number of words in the crossword puzzle, Wi represents the i-th word in the crossword puzzle, and len(Wi) represents the length of the i-th word in the crossword puzzle; Calculating an average difficulty level of the words in the crossword puzzle; Wherein, d(Wi) represents the difficulty coefficient of the i-th word in the crossword puzzle; Counting the number of intersecting words in the crossword puzzle; Where k is the number of interleaved word pairs in the crossword puzzle; Calculating the ratio of the number of spaces to the number of words in the crossword puzzle; Wherein, Ts represents the total number of spaces in the crossword puzzle; Calculate content complexity; F = εL + ζD + ηC + θS; Among them, F represents the content complexity; L represents the average value of the word length in the crossword puzzle; D represents the average value of the word difficulty coefficient in the crossword puzzle; C represents the number of intersecting words in the crossword puzzle; S represents the ratio of the number of spaces to the number of words in the crossword puzzle; ε, ζ, η and θ are weight coefficients, and the sum of ε, ζ, η, θ is 1.

6. The vocabulary testing system based on eye tracker according to claim 5, characterized in that: When determining whether to adjust the English proficiency level of the user according to the comparison result, it includes: When the content complexity is less than or equal to the complexity threshold, determining not to adjust the English proficiency level of the user; When the content complexity is greater than the complexity threshold, it is determined to adjust the English proficiency level of the user.

7. The vocabulary testing system based on eye tracker according to claim 6, characterized in that: When obtaining the difficulty level of the crossword puzzle according to the content complexity, it includes: Comparing the content complexity with a preset difficulty level threshold, wherein the difficulty level threshold includes three levels: a primary difficulty level threshold, an intermediate difficulty level threshold, and a high difficulty level threshold, and determining the difficulty level of the crossword puzzle according to the comparison result; When the content complexity is less than or equal to the primary difficulty level threshold, determining the difficulty level of the crossword puzzle to be primary; When the content complexity is greater than the primary difficulty level threshold and less than or equal to the intermediate difficulty level threshold, determining that the difficulty level of the crossword puzzle is intermediate; When the content complexity is greater than the intermediate difficulty level threshold and less than or equal to the advanced difficulty level threshold, determining that the difficulty level of the crossword puzzle is advanced; When the content complexity is greater than the advanced difficulty level threshold, the difficulty level of the crossword puzzle is determined to be super advanced.

8. The vocabulary testing system based on eye tracker according to claim 7, characterized in that: When adjusting the English proficiency level of the user according to the difficulty level of the crossword puzzle, it includes: When the difficulty level of the crossword puzzle is determined to be elementary, and the user completes the answer within the specified time, the current English proficiency level of the user is maintained unchanged; When the difficulty level of the crossword puzzle is determined to be intermediate, and the user completes the answer within the specified time, the English proficiency level of the user is adjusted upward by one level or remains unchanged; When the difficulty level of the crossword puzzle is determined to be advanced, and the user completes the answer within the specified time, the user's English proficiency level is adjusted upward by two levels or remains unchanged; When the difficulty level of the crossword puzzle is determined to be super advanced, and the user completes the answer within the specified time, the user's English proficiency level is adjusted upward by three levels or remains unchanged; Among them, the user's English proficiency level is raised to the fourth level at most.

9. The vocabulary testing system based on eye tracker according to claim 8, characterized in that: When adjusting the English proficiency level of the user according to the difficulty level of the crossword puzzle, it also includes: When the difficulty level of the crossword puzzle is determined to be elementary, and the user fails to complete the answer within the specified time, the English proficiency level of the user is adjusted down by three levels or remains unchanged; When the difficulty level of the crossword puzzle is determined to be intermediate, and the user fails to complete the answer within the specified time, the user's English proficiency level is adjusted down by two levels or remains unchanged; When the difficulty level of the crossword puzzle is determined to be high, and the user completes the answer within the specified time, the English proficiency level of the user is adjusted down by one level or remains unchanged; When the difficulty level of the crossword puzzle is determined to be super advanced, and the user completes the answer within the specified time, the current English proficiency level of the user is maintained unchanged; The user's English proficiency level is lowered to the first level at least.

10. A vocabulary test method based on an eye tracker, applied in the vocabulary test system based on an eye tracker as claimed in any one of claims 1 to 9, characterized in that: include: Collecting eye movement data of the user within a specified time, and establishing an eye movement data set based on the eye movement data; constructing an eye movement feature model according to the eye movement data set to obtain an eye movement feature index; Comparing the eye movement feature index with an eye movement feature index threshold, and determining the English proficiency level of the user according to the comparison result; collecting the content complexity of each of the crossword puzzles, and comparing the content complexity of each of the crossword puzzles with a content complexity threshold, and determining whether to adjust the English proficiency level of the user according to the comparison result; When it is determined that the English proficiency level of the user is to be adjusted, the difficulty level of the crossword puzzle is obtained according to the content complexity, the English proficiency level of the user is adjusted according to the difficulty level of the crossword puzzle, and the adjusted English proficiency level is obtained.

Images