VFT task automatic generation method and system, medium and equipment

Abstract

The invention discloses a VFT task automatic generation method and system, a medium and equipment, and the method comprises the steps: obtaining the education information of a subject; presetting a plurality of word libraries with different difficulty levels, setting a mapping rule of the educational background and the difficulty levels, and selecting a target word library from the plurality of preset word libraries with different difficulty levels according to the educational background information based on the mapping rule; removing words used by the subject in a preset recent time window from the target word library to form an available word set, and randomly extracting multiple groups of non-repeated words from the available word set to generate a complete VFT task. According to the method, the lexicon with matching difficulty is dynamically selected according to the educational background information of the subject, so that the problem of non-uniform cognitive load caused by a fixed lexicon in a traditional VFT task is effectively solved. And a recent word rejection mechanism is introduced, so that the learning effect and the fatigue effect are avoided, and the reliability and repeatability of an experimental result are improved.

Description

Technical Field

[0001] This invention relates to the field of near-infrared spectroscopy brain imaging technology, and in particular to a method, system, medium, and device for automatically generating VFT tasks. Background Technology

[0002] In fNIRS brain imaging studies, the word fluency task (VFT) is a commonly used activation paradigm to probe participants' language abilities and the activity of brain regions related to cognitive control (such as the frontal lobe). Traditional VFT task designs typically employ a fixed vocabulary or a pre-set stimulus sequence.

[0003] Existing technical solutions and their problems: Fixed vocabulary and sequence: Existing VFT tasks often use fixed vocabulary and stimulus presentation order. This can lead to significant differences in cognitive load and engagement among different subjects when faced with the same task. For example, for subjects with higher education levels, high-frequency words may be too simple to effectively activate their brain's language-related areas; while for subjects with lower education levels, low-frequency words may be too difficult, leading to task failure or insufficient engagement.

[0004] Lack of personalization and dynamic adjustment: Existing protocols fail to dynamically adjust task difficulty based on individual differences among participants (such as education level and background). This limits the sensitivity and effectiveness of the task and may result in a low signal-to-noise ratio.

[0005] Word repetition issue: When performing the VFT task repeatedly, if the vocabulary and sequence remain unchanged, participants are prone to memory effects, affecting the authenticity and reliability of the task. Even if words are randomly selected, if recently used words are not effectively managed, participants may repeatedly encounter similar word groups in a short period, reducing novelty and challenge.

[0006] Limited engagement and brain activation: Due to the lack of personalization and dynamic adjustment, the level of engagement and brain activation of subjects may not reach the optimal state, affecting the quality of fNIRS signals and the accuracy of research conclusions. Summary of the Invention

[0007] To overcome the shortcomings of existing technologies, such as fixed vocabulary and sequences, lack of personalization and dynamic adjustment, word reuse problems, and limited engagement and brain activation.

[0008] In a first aspect, the present invention provides a method for automatically generating VFT tasks, comprising: Obtain the educational background information of the subjects; Multiple word libraries with different difficulty levels are preset, and mapping rules between education level and difficulty level are set. Based on the mapping rules and the education level information, the target word library is selected from multiple preset word libraries with different difficulty levels. Words used by the subject within a preset recent time window are removed from the target word library to form a set of available words. From the set of available words, multiple sets of non-repeating words are randomly selected to generate a complete VFT task.

[0009] Optionally, difficulty levels can be categorized based on word frequency, cognitive complexity, and cultural background.

[0010] Optionally, the available word set may include the first group of words, the second group of words, and the third group of words in the order of the test.

[0011] Optionally, randomly selecting multiple sets of non-repeating words includes the following steps: Randomly select the first group of words from the available word set; After the first group of words is extracted, the second group of words is randomly extracted from the remaining words in the available word set; After the second set of words is drawn, the third set of words is randomly drawn from the remaining words in the available word set.

[0012] Optionally, words used in multiple tasks within a predetermined time window can be recorded in a recently used word list, and the recently used word list can be removed from the target word library to form a set of available words.

[0013] Optionally, if the number of words in the available word set after removing recently used words is insufficient to generate a complete VFT task, the duration of the recent time window can be adjusted or a new word library can be selected.

[0014] Optionally, the difficulty level of the vocabulary used in subsequent tasks can be dynamically adjusted based on the subjects' performance data when completing the task.

[0015] Secondly, a method system for automatically generating VFT tasks includes: The subject management module is used to obtain the subject's educational background information; The vocabulary selection module is used to preset multiple vocabulary libraries of different difficulty levels, set mapping rules between education level and difficulty level, and select the target vocabulary library from multiple preset vocabulary libraries of different difficulty levels based on the mapping rules and the education information. The task generation module is used to remove words that the subject has used within a preset recent time window from the target word library to form a set of available words. From the set of available words, multiple sets of non-repeating words are randomly selected to generate a complete VFT task.

[0016] Thirdly, a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in any of the first aspects.

[0017] Fourthly, an electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the steps of the method described in the first aspect.

[0018] The beneficial effects of this invention are as follows: This method effectively solves the problem of uneven cognitive load caused by a fixed vocabulary in traditional VFT tasks by dynamically selecting a vocabulary of matching difficulty based on the subject's educational background. Simultaneously, by removing recently used words from the subject, word repetition is avoided, significantly improving the subject's focus and participation during the experiment. Personalized task difficulty can more effectively activate specific brain regions related to language processing, thereby improving the signal-to-noise ratio of the fNIRS signal and facilitating more accurate research on brain activity. The introduction of a recently used word removal mechanism ensures highly varied stimuli are provided even in multiple experiments, avoiding learning and fatigue effects and improving the reliability and reproducibility of experimental results. Attached Figure Description

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] Figure 1 These are flowcharts from some of the embodiments; Figure 2 These are system block diagrams from some embodiments. Detailed Implementation

[0021] The following will clearly and completely describe the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention. Furthermore, all connections / linkages involved in the patent do not simply refer to direct contact between components, but rather to the ability to form a better connection structure by adding or reducing connecting accessories according to specific implementation conditions. The various technical features in this invention can be combined interactively without contradicting each other.

[0022] This invention provides a method for automatically generating VFT tasks, comprising: Obtain the educational background information of the subjects; Multiple word libraries with different difficulty levels are preset, and mapping rules between education level and difficulty level are set. Based on the mapping rules and the education level information, the target word library is selected from multiple preset word libraries with different difficulty levels. Words used by the subject within a preset recent time window are removed from the target word library to form a set of available words. From the set of available words, multiple sets of non-repeating words are randomly selected to generate a complete VFT task.

[0023] The Verbal Fluency Task (VFT) is a cognitive testing paradigm typically used to assess an individual's language ability and executive function. It requires participants to generate as many words as possible within a specified time, conforming to specific rules. The lexicon refers to the set of words used in the VFT, containing a selection of words. Mapping rules are rules that establish correspondences between different data or information, such as associating a participant's educational background with the difficulty level of the lexicon.

[0024] Specifically, the difficulty levels include high-frequency, mid-frequency, and low-frequency word libraries. High-frequency, mid-frequency, and low-frequency refer to the frequency of word occurrence, respectively. Mapping rules map different education levels to corresponding preset word libraries. For example, highly educated subjects tend to be mapped to low-frequency or mid-frequency word libraries, while less educated subjects tend to be mapped to high-frequency or mid-frequency word libraries. The mapping relationship can be fine-tuned according to specific research objectives. Subjects' education data can be obtained through user interface input, reading user profiles, or through other data interfaces and stored in the subject information database. Once the education information is obtained, the system queries the pre-established education-difficulty level mapping rules to determine the appropriate word library difficulty level for the subject and selects one or more from all preset word libraries as the target word library for this task. For example, the higher the education level, the greater the probability of selecting a low-frequency word library; the lower the education level, the greater the probability of selecting a high-frequency word library. The system can maintain a list recording all words encountered by the subject when completing VFT tasks within a preset time period. When generating a new task, words in the target vocabulary are compared with the list. Any words that appear in the list are temporarily excluded to ensure the freshness of the words in the new task and to avoid the subject developing a memory effect.

[0025] In some cases, besides education level, other factors that may affect cognitive load, such as the participant's age, occupation, and native language, can be considered when selecting the vocabulary. Mapping rules between different factors and vocabulary at different difficulty levels can be established. Elimination can be based on semantic similarity, rather than simply removing identical words. The duration of the elimination window can also be adjusted according to research needs. Selecting a vocabulary based on the participant's education level, in addition to changing the way words are presented, can also involve altering parameters such as the order and interval of word presentation in the task to increase task variability.

[0026] In some embodiments, the academic level is divided into multiple gradients, each gradient corresponding to one or a set of vocabularies, and probabilistic selection is allowed between adjacent gradient vocabularies to provide more granular difficulty control.

[0027] This method effectively addresses the problem of uneven cognitive load caused by a fixed vocabulary in traditional VFT tasks by dynamically selecting a vocabulary lexicon with matching difficulty based on the subjects' educational background. Simultaneously, by removing recently used words, word repetition is avoided, significantly improving subjects' focus and engagement during the experiment. Personalized task difficulty can more effectively activate specific brain regions related to language processing, thereby improving the signal-to-noise ratio of fNIRS signals and facilitating more accurate studies of brain activity. The introduction of a recently used word removal mechanism ensures highly varied stimuli are provided even across multiple experiments, avoiding learning and fatigue effects and enhancing the reliability and reproducibility of experimental results.

[0028] In some embodiments, difficulty levels are categorized based on word frequency, cognitive complexity, and cultural background.

[0029] Specifically, difficulty levels can be assessed based on word frequency. Word frequency refers to the number of times or the probability of a word appearing in a specific language corpus, reflecting its commonness and recognizability. Generally, words with higher frequency have lower cognitive loads and are considered less difficult; conversely, words with lower frequency have higher cognitive loads and are considered more difficult. For example, large-scale language corpora (such as the Chinese Wikipedia corpus or the Modern Chinese Corpus) can be used to statistically analyze word frequencies, classifying the top X% of words as low difficulty, the middle Y% as medium difficulty, and the rest as high difficulty. Alternatively, familiarity surveys of words across different age groups or education levels can be used to classify words with high familiarity as low difficulty and words with low familiarity as high difficulty.

[0030] Furthermore, difficulty levels can be categorized based on the cognitive complexity of words. Cognitive complexity refers to the complexity of the psychological resources and cognitive processes required for a subject to understand and process a word; it encompasses dimensions such as the abstractness, polysemy, and semantic depth of a word. For example, abstract words (such as "freedom" and "philosophy") typically have higher cognitive complexity than concrete words (such as "apple" and "table"). Polysemous words or words with complex semantic structures may also have higher cognitive complexity. Expert assessment methods can be used, where linguistics or psychology experts score the abstractness, polysemy, and semantic depth of words, and the overall score determines their cognitive complexity. Alternatively, indicators such as imagery, concreteness, and familiarity of words in psycholinguistic databases can be used, combined with computational linguistics methods (such as word vector models to analyze semantic distance and relevance) to quantify the cognitive complexity of words and categorize them into difficulty levels accordingly.

[0031] Furthermore, difficulty levels can be categorized based on the cultural context of the words. Cultural context refers to the familiarity, acceptance, and relevance of words within a specific cultural group, ensuring cultural fairness and adaptability of the task. Some words may be very common and easily understood in a particular cultural context, but may be unfamiliar or have different meanings in other cultural contexts. For example, words related to traditional Chinese festivals, historical figures, or specific regional cultures are less difficult for subjects with the corresponding cultural background, but more difficult for those without. Pre-testing can be conducted with subjects from different cultural backgrounds, and their understanding and reaction speed can be used to assess the cultural relevance of the words. Alternatively, a multicultural corpus can be constructed to analyze the distribution and frequency of use of words across different cultural corpora, thereby identifying culturally specific words and adjusting the difficulty level according to the target subjects' cultural background.

[0032] Through the aforementioned technical solution, when multiple word libraries of varying difficulty levels are pre-set, a refined classification can be achieved based on multi-dimensional and objective indicators such as word frequency, cognitive complexity, and cultural background. This makes the difficulty levels of the word libraries more scientific, accurate, and universally applicable, effectively avoiding inaccurate difficulty classification caused by subjective judgment or a single standard. Therefore, when the educational background information of the subjects is obtained, and a target word library is selected from the pre-set word libraries based on more precise mapping rules and this educational information, the selected target word library can more accurately match the subjects' actual cognitive abilities and language proficiency. This not only improves the personalization of the VFT task and ensures that the task difficulty is moderate—neither too easy leading to insufficient subject engagement nor too difficult leading to task failure—but also more effectively activates language-related areas of the subjects' brains, improving the signal-to-noise ratio and reliability of research conclusions in fNIRS brain imaging studies. Simultaneously, this refined difficulty classification provides a solid foundation for subsequent dynamic adjustment of the word library difficulty level based on subject performance, further optimizing the adaptability and effectiveness of the task.

[0033] In some embodiments, the available word set may include a first group of words, a second group of words, and a third group of words in sequence according to the test order.

[0034] Specifically, the available word set refers to the set of words formed after removing words used by the subject within a preset recent time window from the target word library. It is the candidate word pool used to generate the VFT task. This set can be implemented in various ways. For example, it can be a dynamically maintained list or array that stores all words that meet the current conditions; or it can be a virtual set generated in real time through a database query that filters available words from a larger word database based on preset filtering conditions (such as difficulty level and usage history).

[0035] By structuring the available word set into three groups—the first, second, and third—in sequence according to the test order, the problem of disjointed or inefficient task sequences is effectively solved. This structured design gives the VFT task a clear phased and logical presentation, avoiding the sequence disorder that might result from completely random sampling. Subjects can perceive the orderly progress of the task while performing it, thereby reducing unnecessary cognitive load and improving the reliability and consistency of the task. This phased word presentation helps optimize the cognitive engagement of subjects, ensuring they receive appropriate stimulation at different stages, thus improving the quality and effectiveness of VFT task data acquisition in fNIRS brain imaging studies.

[0036] In some embodiments, randomly selecting multiple sets of non-repeating words includes the following steps: Randomly select the first group of words from the available word set; After the first group of words is extracted, the second group of words is randomly extracted from the remaining words in the available word set; After the second set of words is drawn, the third set of words is randomly drawn from the remaining words in the available word set.

[0037] Specifically, the step of randomly selecting the first group of words from the available word set aims to lay a random foundation for word grouping in the VFT task. Various random selection algorithms can be employed; for example, generating pseudo-random numbers to select word indices from the available word set, or randomly shuffling the available word set and selecting a predetermined number of words as the first group. This ensures the independence and unpredictability of the first group of words, avoiding biases introduced by human intervention or fixed patterns.

[0038] Subsequently, in the step of randomly selecting a second set of words from the remaining words in the available word set after the first set of words has been extracted and removed from the available word set, this application further randomly selects a second set of words from the remaining words. This can be achieved by maintaining a dynamically updated list of available words, deleting the selected words from the list after each set of words is extracted. The key to this step is ensuring that there are no duplicates between the second set of words and the first set of words, while maintaining the randomness of the extraction process and preventing the word order from becoming fixed.

[0039] Finally, in the step of randomly selecting a third group of words from the remaining words in the available word set after the second group of words has been extracted, similarly, the system randomly selects a third group of words from the remaining words in the available word set again after the second group of words has been extracted. This further strengthens the mutual exclusion between the groups of words, ensuring that the third group of words does not overlap with the first two groups of words. By extracting and excluding used words in this way, the uniqueness and randomness of all word groupings in the VFT task are guaranteed.

[0040] Through the aforementioned technical solution, this application ensures that multiple sets of words do not overlap when generating the VFT task by defining specific random sampling steps, effectively avoiding the memory effect caused by word reuse. This method of randomly sampling from the remaining words sequentially establishes an initial random basis for the entire sampling process and continuously maintains the random sampling mechanism, thereby improving the randomness and fairness of the task and preventing bias caused by fixed order. Ultimately, this enhances the novelty and challenge of the VFT task, enabling test takers to maintain a higher level of engagement and cognitive activation when completing the task, thus improving the authenticity and reliability of the test and effectively solving the problem of word reuse in the background technology.

[0041] In some cases, in addition to random sampling, control can be added when generating tasks to ensure that each group of words covers different semantic categories (such as animals, furniture, actions, etc.) in order to more comprehensively activate the brain's language network.

[0042] In some embodiments, words used in multiple tasks within a predetermined time window are recorded in a recently used word list, and the recently used word list is removed from the target word library to form a set of available words.

[0043] Specifically, the phrase "recording words used in multiple tasks within a predetermined time window to a recently used word list" means that the system sets a predetermined time period and records the number of tasks completed by the subject within this period, such as the most recent day, week, or month, as the basis for determining whether a word is "recently used." During this time period, all words used by the subject when completing multiple VFT tasks, along with their usage timestamps, are systematically recorded and stored in a dedicated "recently used word list." This list can be a dynamically updated data structure. For example, it can be maintained in a database as a word usage log table for each subject, recording the words and completion time of each task, and querying and summarizing them to form a list when needed; alternatively, it can maintain a subject-specific word list in local storage (such as cache or files), adding the used words and their timestamps to this list after each task is completed, and automatically removing old words that exceed the predetermined time window when a new task is generated. In this way, the system can establish a dynamic and personalized word usage history, providing an accurate data foundation for subsequent word removal operations.

[0044] Building upon this, the "removal of recently used words from the target vocabulary list to form a usable word set" refers to the process where, after selecting the target vocabulary from multiple preset vocabulary lists of different difficulty levels based on the subject's educational background, the system uses the generated recently used word list to filter the target vocabulary. Specifically, the system checks each word in the target vocabulary to determine if it appears in the recently used word list. If a word is in the recently used word list, it is removed from the target vocabulary; otherwise, if it is not, it is retained and added to the final "usable word set." This removal process can be implemented using set difference operations, treating the target vocabulary as one set and the recently used word list as another, and then calculating their difference; alternatively, it can be achieved by iterating through the words in the target vocabulary and comparing them one by one with the recently used word list. This removal mechanism ensures that the final usable word set used to generate the VFT task does not contain words that the subject has already used within the predetermined time window.

[0045] Through the aforementioned technical solution, this application introduces a systematic recording and elimination mechanism, effectively addressing the problem of word reuse across multiple tasks. Specifically, by recording words used in multiple tasks within a predetermined time window into a recently used word list, the system can dynamically and accurately track the subject's word usage history, overcoming the shortcomings of traditional solutions that lack effective management mechanisms. Based on this, the recently used word list is removed from the target word library, ensuring that the words used in newly generated VFT tasks are ones the subject has not recently encountered, thus significantly enhancing the task's novelty and challenge. This personalized word management approach avoids the subject's performance being affected by memory effects, thereby improving the reliability and authenticity of the test results. Combined with the basic solution of selecting the target word library based on educational background information, this application can provide subjects with more personalized, effective, and continuously challenging VFT tasks, thereby obtaining higher-quality cognitive assessment data.

[0046] In some embodiments, if the number of words in the available word set after removing recently used words is insufficient to generate a complete VFT task, the duration of the recent time window is adjusted or a new word library is selected.

[0047] Specifically, after removing words used by the subject within a preset recent time window from the target word library, the system needs to determine whether the resulting set of available words is sufficient to generate a complete VFT task. This determination can be achieved by setting a minimum word count threshold required to generate a complete VFT task. For example, a complete VFT task might require three sets of words, each with at least ten words, totaling at least thirty words. If the number of words in the available word set is below this threshold, it is considered insufficient. Alternatively, the system can dynamically calculate the total number of words required based on the specific configuration of the current VFT task, such as the number of subtasks and the number of words required for each subtask, and compare this total with the actual number of words in the available word set to determine whether the task generation requirements are met.

[0048] When the system determines that the available vocabulary set is insufficient to generate a complete VFT task, it will take dynamic adjustment measures. One possible adjustment method is to adjust the duration of the recent time window. For example, if a subject completes three tasks within the time window, they can select only the vocabulary from one task, thereby reducing the number of words marked as recently used and removed, and thus increasing the vocabulary set available. Alternatively, the system can employ a more refined strategy based on the degree of vocabulary insufficiency, such as proportionally shortening the time window until the available vocabulary meets the requirements for generating the task.

[0049] Another option for adjustment is to reselect a vocabulary. When the current target vocabulary cannot provide enough words, the system can switch to another vocabulary. For example, based on the subject's educational background and mapping rules, a vocabulary with a difficulty level adjacent to the current target vocabulary can be selected.

[0050] Through the above technical solution, this application effectively addresses the problem that the available word set is insufficient to generate a complete VFT task after recently used words are removed. By setting a conditional judgment mechanism, the system can promptly detect word shortages. Subsequently, by flexibly adjusting the duration of the recent time window, the range of the recently used word list can be dynamically controlled, thereby effectively increasing the available word set while ensuring task freshness and avoiding task generation failure due to excessive removal. Simultaneously, providing the option to reselect the thesaurus fundamentally broadens the word source, ensuring sufficient words for task generation under any circumstances. This dynamic response mechanism avoids task interruptions due to insufficient words, greatly improving the continuity and reliability of VFT task generation, enhancing the adaptability and robustness of the method, and thus ensuring smooth testing and data validity.

[0051] In some embodiments, the difficulty level of the vocabulary used in subsequent tasks is dynamically adjusted based on the subject's performance data when completing the task.

[0052] Specifically, the "performance data based on subjects completing the task" refers to the system collecting and analyzing various indicators of subjects during the completion of the VFT task. This performance data can objectively reflect the subject's current cognitive state and task adaptability. For example, performance data may include the subject's reaction time to complete the task, the accuracy rate of the task, fluency indicators, or the number of effective words generated within a specific time period. In addition, performance data may also include the types of errors made by the subject during the task, such as semantic errors or phonetic errors, which can provide a more detailed assessment of cognitive ability.

[0053] The "dynamic adjustment of the vocabulary difficulty level used in subsequent tasks" refers to the system's ability to change the difficulty of the vocabulary used in subsequent VFT tasks in real time or periodically based on the aforementioned performance data. For example, the system can preset a series of difficulty thresholds. When a subject's performance data (such as accuracy or reaction time) reaches or exceeds a certain threshold, the system automatically increases the vocabulary difficulty level of subsequent tasks by one level; conversely, if the performance data is below a certain threshold, it decreases by one level. Another implementation method is that the system can employ adaptive learning algorithms, such as those based on reinforcement learning or Bayesian inference models, to predict the subject's optimal cognitive load level by analyzing their historical and current performance data, and then select the most suitable vocabulary difficulty level accordingly.

[0054] Through the above technical solution, this application solves the problem of static task difficulty and achieves real-time optimization of task difficulty. Specifically, this solution assesses the cognitive ability level of subjects in real time based on their performance data when completing tasks, such as reaction time or accuracy. Based on this, the difficulty level of the vocabulary used in subsequent tasks is dynamically adjusted to ensure that the task difficulty matches the subject's current ability. This performance data-based adjustment method avoids the limitations of relying solely on initial educational information, making tasks more adaptable and challenging, thereby increasing subject engagement and brain activation, and ultimately improving the quality of fNIRS signals and the accuracy of research conclusions.

[0055] In some cases, during the experiment, once the system detects that the subject shows obvious signs of being "too easy" or "too difficult" (e.g., fluency scores are much higher or lower than average), the system can proactively adjust the vocabulary difficulty for the next round of tasks.

[0056] This invention provides a method system for automatically generating VFT tasks, comprising: The subject management module is used to obtain the subject's educational background information; The vocabulary selection module is used to preset multiple vocabulary libraries of different difficulty levels, set mapping rules between education level and difficulty level, and select the target vocabulary library from multiple preset vocabulary libraries of different difficulty levels based on the mapping rules and the education information. The task generation module is used to remove words that the subject has used within a preset recent time window from the target word library to form a set of available words. From the set of available words, multiple sets of non-repeating words are randomly selected to generate a complete VFT task.

[0057] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for automatically generating VFT tasks.

[0058] This invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The steps of implementing the VFT task automatic generation method when the processor executes a program stored in memory.

[0059] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A VFT task automatic generation method, characterized in that, include: Obtain the educational background information of the subjects; Multiple word libraries with different difficulty levels are preset, and mapping rules between education level and difficulty level are set. Based on the mapping rules and the education level information, the target word library is selected from multiple preset word libraries with different difficulty levels. Words used by the subject within a preset recent time window are removed from the target word library to form a set of available words. From the set of available words, multiple sets of non-repeating words are randomly selected to generate a complete VFT task.

2. The VFT task automatic generation method according to claim 1, characterized in that, Difficulty levels are categorized based on word frequency, cognitive complexity, and cultural background.

3. The VFT task automatic generation method according to claim 1, characterized in that, The available word set includes the first group of words, the second group of words, and the third group of words in the order of the test.

4. The VFT task automatic generation method according to claim 3, characterized in that, Randomly selecting multiple sets of non-repeating words involves the following steps: Randomly select the first group of words from the available word set; After the first group of words is extracted, the second group of words is randomly extracted from the remaining words in the available word set; After the second set of words is drawn, the third set of words is randomly drawn from the remaining words in the available word set.

5. The VFT task automatic generation method according to claim 1, characterized in that, The words used in multiple tasks within the predetermined time window are recorded in the recently used word list. The recently used word list is then removed from the target word library to form a set of usable words.

6. The VFT task automatic generation method according to claim 5, characterized in that, If the number of words in the available word set after removing recently used words is insufficient to generate a complete VFT task, then adjust the duration of the recent time window or reselect the word library.

7. The VFT task automatic generation method according to claim 1, characterized in that, Based on the performance data of the subjects when completing the task, the difficulty level of the vocabulary used in subsequent tasks is dynamically adjusted.

8. A method system for automatically generating VFT tasks, characterized in that, include: The subject management module is used to obtain the subject's educational background information; The vocabulary selection module is used to preset multiple vocabulary libraries of different difficulty levels, set mapping rules between education level and difficulty level, and select the target vocabulary library from multiple preset vocabulary libraries of different difficulty levels based on the mapping rules and the education information. The task generation module is used to remove words that the subject has used within a preset recent time window from the target word library to form a set of available words. From the set of available words, multiple sets of non-repeating words are randomly selected to generate a complete VFT task.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1-7.

Images