Target language vocabulary substitution load control and pacing management system

Abstract

The application discloses a target language vocabulary replacement load control and learning rhythm management system, comprising: a familiar word state acquisition module, which is used for acquiring a set of mastered target language vocabularies of a user; a learning content analysis module, which is used for identifying replaceable semantic units or replaceable vocabulary positions in to-be-output learning content; a replacement capacity determination module, which is used for determining a target vocabulary replacement capacity in current learning content; a familiar word priority mapping module, which is used for matching the replaceable semantic units or replaceable vocabulary positions with the set of target language vocabularies, and preferentially determining familiar word replacement positions within the target vocabulary replacement capacity range; a new word injection window allocation module, which is used for determining a new word injection window in current learning content based on remaining replacement positions; a learning rhythm adjustment module, which is used for dynamically adjusting subsequent learning content; and a learning content output module, which is used for outputting learning content according to the familiar word replacement positions and the new word injection window.

Description

Technical Field

[0001] This invention relates to the fields of language learning technology, intelligent education systems, natural language processing, and human-computer interaction control. In particular, it relates to a target language vocabulary replacement control and learning rhythm management system that dynamically allocates target language vocabulary replacement positions in learning content based on the user's familiarity with vocabulary, and jointly manages the learning rhythm through familiar vocabulary replacement load, new word injection window, and user behavior feedback. Background Technology

[0002] In the process of language learning, the learner's mastery of the target language vocabulary directly affects their comprehension burden of the learning content and their willingness to continue reading.

[0003] Existing language learning systems typically control learning difficulty in the following ways: 1) Pre-divide learning materials into fixed levels such as beginner, intermediate, and advanced; 2) Select content suitable for users based on word frequency or vocabulary levels; 3) Set a fixed proportion of new words or target language content in the learning materials; 4) Switch course levels based on user test results or learning progress.

[0004] However, the above method still has the following problems:

[0005] 1) Unable to dynamically adjust the current learning content using the user's existing vocabulary assets.

[0006] Existing systems typically treat "user-acquired vocabulary" as outcome data for evaluation or grading, rather than as a real-time control variable driving the distribution of target language substitution for current learning content. Vocabulary already acquired by the user cannot be reliably converted into low-burden target language input for subsequent reading.

[0007] 2) The target language replacement position lacks an orderly allocation mechanism.

[0008] In scenarios involving native language-assisted reading, mixed language reading, or gradual language replacement, the system often lacks a structured control mechanism to determine "how many target language words should be included in the current page, current paragraph, or current learning round, how many of them should be used to reproduce familiar words, and how many should be used to introduce new words," which can easily lead to an imbalance in the density of the target language.

[0009] 3) The introduction of new words lacks window control that is linked to the coverage status of familiar words.

[0010] Existing systems typically control the proportion of new words or the difficulty of content separately, but they do not establish a dynamic allocation logic that "within the total replacement capacity, familiar words first occupy replacement slots, and then the amount of new words injected is determined based on the remaining replacement slots," resulting in a disconnect between the introduction of new words and the user's existing capabilities.

[0011] 4) There is a lack of interpretable internal control over the regulation of learning pace.

[0012] Existing adaptive learning technologies often adjust the difficulty based on reading speed, completion rate, or test scores, but they do not take "familiar word replacement load," "new word injection window size," and "target language replacement capacity" as rhythm parameters that can be jointly controlled, making it difficult to form a continuous, stable, and predictable learning advancement mechanism.

[0013] 5) There is a lack of balance between reading experience and learning progress.

[0014] If too much target language is injected, the user's comprehension cost becomes too high, and the reading experience deteriorates; if too little target language is injected, already mastered vocabulary cannot be fully reproduced, and new word input is insufficient, slowing down learning progress. Therefore, a system is needed that can finely manage the vocabulary replacement load and the pace of new word injection based on the user's familiarity with vocabulary.

[0015] 6) The problem of familiar words still occupying replacement capacity for a long time after they have stabilized.

[0016] In progressive language replacement scenarios, some target language words have achieved high stability after repeated reproduction, user confirmation, or behavioral verification. If the system still includes these stable familiar words in the limited replacement capacity along with ordinary familiar words or newly added words, the replacement capacity will be occupied by low-burden words for a long time, compressing the space for injecting new words and reducing the efficiency of learning progress. Existing systems typically lack a mechanism to convert the stability of familiar words into a condition for releasing capacity.

[0017] 7) The problem of lack of dynamic refresh and re-spotting mechanism for replacement positions in the current visible area.

[0018] In mobile reading or scrolling reading scenarios, the text, line spacing, font size, screen status, user dwell time, or familiar word status within the currently visible area may change in real time. If the target language replacement position is fixed once generated, problems such as uneven target language density within the same visible area, low-value replacement positions being occupied, and familiar words repeatedly suppressing newly added words may occur.

[0019] Therefore, a control mechanism is needed to dynamically refresh or re-select replacement bits within the current visible area without exceeding the replacement capacity limit. Summary of the Invention

[0020] This invention aims to provide a vocabulary replacement load control and learning rhythm management system based on the status of familiar words. By acquiring the user's set of familiar words, the system determines the target vocabulary replacement capacity in the current learning content. Within this capacity, it prioritizes allocating replacement slots for familiar words and controls the injection of new words based on the remaining replacement slots, thereby achieving coordinated control between familiar word repetition, new word introduction, and learning rhythm adjustment. In this invention, the target vocabulary replacement capacity serves as a unified control quantity for the target language presentation load in the learning content. The number of familiar word replacement slots, the new word injection window, and subsequent learning rhythm adjustments are all constrained by this target vocabulary replacement capacity.

[0021] This invention does not merely adjust the overall difficulty of learning materials with coarse granularity, but further establishes the following control mechanisms at the vocabulary replacement level: 1) Determine the target language replacement capacity based on the current learning content or the current visible area; 2) Prioritize the allocation of familiar word replacement positions based on the user's familiar word set; 3) Determine the number of new words that can be introduced or the new word injection window within the remaining replacement capacity; 4) Dynamically adjust the subsequent replacement capacity, familiar word reproduction ratio, and new word injection amount based on user behavior feedback; 5) Ensure that the proportion of the target language in the learning content gradually expands with the user's real familiar word assets, rather than being statically determined by a fixed ratio or fixed level; 6) When the target language vocabulary reaches the stable familiar word condition, reduce or cancel its occupation of the new word replacement capacity, so that the released capacity can be used for new word injection, reproduction of other familiar words, or reading stability adjustment; 7) Dynamically refresh or re-select the target language replacement positions within the current visible area based on user operation, changes in familiar word status, or changes in display area, optimizing vocabulary distribution while keeping the total replacement load under control. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0023] Figure 1 This is a schematic diagram of the overall system structure of the present invention;

[0024] Figure 2 This is a flowchart illustrating the process of determining replacement capacity and prioritizing familiar words for placement.

[0025] Figure 3 A schematic diagram illustrating the process of allocating a window for injecting new words within the remaining replacement capacity;

[0026] Figure 4 A diagram illustrating the dynamic adjustment of the learning pace within a closed loop.

[0027] Figure 5 This is a schematic diagram of load replacement control within the currently visible area;

[0028] Figure 6 This is a schematic diagram of the mechanism for releasing replacement capacity after familiar words have stabilized. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] To achieve the above objectives, this invention provides a target language vocabulary substitution load control and learning rhythm management system based on the state of familiar words, such as... Figures 1 to 6 As shown, the system includes: a familiar word status acquisition module; a learning content analysis module; a replacement capacity determination module; a familiar word priority mapping module; a new word injection window allocation module; a learning rhythm adjustment module; a learning content output module; a status feedback update module; a familiar word stable capacity release module; and a visible area dynamic refresh and re-sampling module.

[0032] The “target language vocabulary replacement load” refers to the occupancy status of vocabulary replacement positions actually configured in the target language presentation format in the current learning content, current page, current paragraph, current visible area, or current learning cycle; the target language vocabulary replacement load is determined at least by the number of familiar word replacement positions, the number of newly injected word positions, and their occupancy relationship in the preset replacement capacity.

[0033] The “new word injection window” is not an open new word quota set independently of the replacement capacity, but a remaining allocation window constrained by the target word replacement capacity and the already allocated familiar word replacement slots.

[0034] The phrase "releasing replacement capacity after familiar words stabilize" means that when a target language word meets the preset stabilization conditions, the system can partially or completely release it from the new word capacity, the new word injection window, or the strict replacement capacity, so that when the word continues to appear in the target language form with low burden, it no longer occupies the limited new word quota, or is only counted in the replacement load with a lower weight.

[0035] The "dynamic refresh or reselection of replacement positions within the current visible area" refers to the system reselecting, replacing, retaining, or canceling some target language replacement positions based on the current visible area when the user stays, scrolls, refreshes, switches font size, switches content area, confirms familiar words, or the system detects changes in replacement load, and ensuring that the refreshed replacement results still meet the constraints of replacement capacity, priority of familiar words, release of stable familiar words, and injection window for new words.

[0036] The following will describe each module in detail.

[0037] 1) Familiar word status acquisition module

[0038] This is used to obtain a set of target language vocabulary that the user has mastered. The familiarity status of the words includes at least one of the following: words that the user has actively confirmed to have mastered; words that have been determined to be stably recognized through historical learning records; words that have been determined to be familiar through reading behavior, clicking behavior, recognition behavior, or repetition behavior; and a set of vocabulary that has been mastered corresponding to the user's learning level or stage.

[0039] 2) Learning Content Analysis Module

[0040] This is used to perform lexical unit analysis, semantic unit identification, or replaceable unit localization on the learning content to be output, determining candidate positions where words in the target language can be replaced. The learning content includes at least one of the following: native language text; mixed text with native language as the primary language and target language as the secondary language; bilingual comparative text; learning text generated by a generative model; and reading materials selected from a content library.

[0041] 3) Replace the capacity determination module

[0042] This tool is used to determine the target vocabulary replacement capacity in the current learning content based on at least one of the following: user learning stage, preset replacement limit, current learning task, text length, terminal display area, current visible area size, historical learning burden, or interaction state. The replacement capacity limits the total number of target language vocabulary replacements allowed to be presented in the current learning content, current page, current visible area, or current learning round. The replacement capacity can be expressed as: the number of target language vocabulary allowed to appear on a single screen; the number of target language vocabulary allowed to appear in a single paragraph; the number of target language vocabulary allowed to appear in a single article; the total number of target language vocabulary words allowed to be added or reproduced in a single learning round; and a dynamic replacement allowance related to text length, screen space, or user ability.

[0043] 4) Familiar word priority mapping module

[0044] This method is used to match replaceable candidate positions in the learning content with the user's set of familiar words, and within the replacement capacity, prioritizes the selection of candidate positions corresponding to the user's set of familiar words for target language mapping. The priority mapping of familiar words includes at least one of the following: within the target vocabulary replacement capacity, prioritizing the display of mastered target words; prioritizing the reproduction of words from the set of familiar words in the same learning content; when the number of replaceable positions exceeds the replacement capacity, prioritizing the retention of replacement positions corresponding to familiar words; determining replacement positions of familiar words after sorting according to the need for reproduction of familiar words, word frequency, recent usage interval, or learning objectives.

[0045] 5) Added a word injection window allocation module

[0046] This module is used to determine the remaining replacement slots after deducting the allocated familiar word replacement slots from the replacement capacity, and to allocate new word injection windows for new words based on the remaining replacement slots. The new word injection window is used to limit the number, proportion, or distribution range of target language vocabulary that can be added to the current learning content. The new word injection window allocation module can determine the amount of new words injected based on at least one of the following parameters; and when there are remaining replacement slots, the system can choose to use all, partially, or temporarily not use the remaining replacement slots according to the learning pace control needs, to avoid mechanically forcibly injecting new words when there is spare replacement capacity: number of remaining replacement slots; user's current familiar word coverage rate; recent familiar word growth rate; reading completion rate; reading dwell time; target language vocabulary click frequency; historical recognition accuracy rate; user-set learning intensity parameters.

[0047] 6) Learning Pace Adjustment Module

[0048] This module dynamically adjusts at least one of the following parameters in subsequent learning content based on factors such as the replacement capacity of familiar words, the frequency of familiar word recurrence, the amount of new words injected, the proportion of native language assistance, or the density of target language presentation. When the system detects smooth user reading, stable familiar word confirmation, high reading completion rate, or low demand for target word click prompts, the learning rhythm adjustment module can increase the replacement capacity, increase the new word injection window, or increase the target language presentation density. When the system detects a decrease in user reading speed, an abnormal increase in dwell time, an increase in prompt click frequency, a decrease in reading completion rate, or a decrease in recognition accuracy, the learning rhythm adjustment module can decrease the replacement capacity, shrink the new word injection window, or increase the proportion of native language assistance.

[0049] 7) Learning Content Output Module

[0050] This is used to output learning content based on the allocation results of the familiar word substitution positions and the new word injection positions. The output format includes at least one of the following: inserting target language vocabulary into the corresponding semantic position of the native language text; displaying the target language vocabulary with native language prompts; displaying the target language vocabulary in a native language wrapping format; using different prompt intensities, different auxiliary structures, or different visual presentation methods for familiar and new words; and controlling the distribution density of target language vocabulary in the current screen, current paragraph, or current visible area.

[0051] 8) Status Feedback Update Module

[0052] This module is used to update the user's familiarity status based on the user's interaction with the output learning content, and to feed back the updated familiarity status to at least one of the following modules: familiarity status acquisition module, familiarity priority mapping module, new word injection window allocation module, or learning rhythm adjustment module, for use in subsequent learning content replacement control.

[0053] 9) Familiar Word Stable Capacity Release Module

[0054] This module determines whether a target language word has reached the stable familiar word condition based on the user's recognition behavior, confirmation behavior, historical recurrence frequency, continuous reading performance, or reliance on prompts. Once a target language word reaches the stable familiar word condition, the familiar word stable capacity release module adjusts the capacity occupancy status of that word. The capacity occupancy status adjustment includes at least one of the following: removing stable familiar words from the new word injection window; ensuring stable familiar words no longer occupy new word quotas; including stable familiar words in the target language word replacement load with a lower weight than ordinary familiar words or new words; allocating the released replacement capacity to new words, low-frequency familiar words, or system-specified learning targets while maintaining the continued recurrence of stable familiar words; and temporarily not using the released replacement capacity when the user's burden is high to maintain reading stability. Through this module, the system can avoid high-stability familiar words occupying limited replacement capacity for a long time, enabling familiar word assets to not only generate recurrence value but also be transformed into new learning space.

[0055] 10) Visible area dynamic refresh and re-scan module

[0056] This module dynamically refreshes or re-selects target language word replacement positions within the current visible area based on text candidate positions, replacement capacity, user familiarity with words, stable familiarity word release status, new word injection window, screen display parameters, or user interaction behavior. The dynamic refresh or re-selection includes at least one of the following: when a user stays in the current visible area for more than a preset time, re-evaluating the distribution of replacement positions in the current area; when a user confirms a word as familiar or the system determines it has reached the stable familiarity word condition, releasing the corresponding capacity and re-selecting new words or other recurring words; when the target language word density in the current visible area is too high or too low, canceling, retaining, or adding some replacement positions; when a user refreshes, scrolls up, scrolls down, re-enters the page, adjusts the font size, or switches the display area, re-selecting replacement positions in the current area; during the re-selection process, the constraints of on-screen replacement capacity, inline distribution limits, familiarity word priority rules, and new word injection window are not violated. Through this module, the system does not simply replace words randomly, but rather redistributes target language replacement positions within the current visible area under constraints of capacity, familiarity word status, and reading burden.

[0057] The core operating mechanism is described below.

[0058] The core operating mechanism of this invention can be summarized as follows: familiar word status acquisition → replacement capacity determination → familiar words priority occupation → stable familiar word capacity release → new words injection based on remaining capacity → dynamic refresh / re-extraction of replacement positions in the current visible area → output of learning content → user behavior feedback → next round of rhythm update.

[0059] Unlike existing technologies that adjust content solely based on text difficulty or the proportion of unfamiliar words, this invention transforms "familiar word assets" into a priority allocation basis for target language substitution positions in learning content, and controls the introduction of new words through remaining substitution capacity, thereby forming a learning rhythm management mechanism based on the compounding effect of familiar words.

[0060] Among them, the stable familiar word capacity release mechanism enables the system to distinguish between "familiar words that still require learning load" and "stable familiar words that can already exist as low-burden reading elements"; the current visible area dynamic refresh and re-sampling mechanism enables the system to locally redistribute the target language replacement positions in the current screen without changing the overall structure of the article, thereby achieving more granular control of the learning rhythm.

[0061] This invention also provides a method for vocabulary substitution load control and learning rhythm management based on the status of familiar words, including the following steps:

[0062] S101: Obtain the status of familiar words. Obtain the user's current set of familiar words and the stability, recent usage records, or learning level information of familiar words associated with the set of familiar words.

[0063] S102: Analyze the learning content. Identify replaceable semantic units or mappable word locations in the learning content to be output.

[0064] S103: Determine replacement capacity. Based on the current learning task, user status, text length, visible area, or replacement limit, determine the replacement capacity of the target vocabulary in the current learning content.

[0065] S104: Perform familiar word priority mapping. Match replaceable semantic units with the user's familiar word set, and prioritize the determination of familiar word replacement positions within the replacement capacity.

[0066] S105: Determine the new word injection window. After deducting the replacement positions for familiar words, calculate the remaining replacement positions, and determine the amount of new words to be injected into the current learning content based on the remaining replacement positions.

[0067] S106: Output learning content. Generate or adjust learning content based on familiar word substitution positions and new word injection positions, and present it to the user in a native language-assisted, bilingual mixed, or native language-wrapped manner.

[0068] S107: Collect user feedback. Record user reading speed, dwell time, prompt click behavior, familiar word confirmation behavior, reading completion rate, or recognition accuracy rate.

[0069] S108: Update the learning pace. Based on the user feedback, adjust the replacement capacity, new word injection window, familiar word recurrence rate, target language presentation density, or native language assisted ratio in the next round of learning content.

[0070] S109: Update the status of familiar words. Update the set of familiar words based on user confirmation or system judgment, and use the updated set of familiar words for subsequent vocabulary replacement control.

[0071] S110: Determine stable familiar words and release capacity. When a target language word meets the preset condition for stable familiar words, mark it as a stable familiar word and adjust its occupation of the new word injection window or target word replacement capacity, so that the corresponding capacity is partially or completely released.

[0072] S111: Dynamically refresh or re-extract replacement positions within the current visible area. Based on the candidate replacement positions within the current visible area, the release results of stable familiar words, the remaining replacement capacity, user interaction behavior, or changes in display status, retain, cancel, add, or re-extract target language replacement positions within the current visible area.

[0073] Example 1: Prioritizing familiar words and injecting new words under single-screen replacement capacity

[0074] Assume the current screen content allows for 8 target language substitutions. The system detects 12 replaceable semantic units on the current screen and compares them with the user's set of familiar words.

[0075] Among them, 5 candidate positions correspond to familiar words that the user already knows. The system prioritizes these 5 candidate positions as replacement positions for familiar words.

[0076] After deducting the 5 familiar word replacement positions from the total replacement capacity of 8, 3 replacement positions remain. Based on this, the system determines that 3 new words can be added to this screen, and selects the corresponding new words according to word frequency level, learning objectives, or content suitability.

[0077] Ultimately, the current screen output includes: the reproduction of 5 mastered target language words; the introduction of 3 newly added target language words; and the remaining content that has not been assigned replacement positions maintains the native language or auxiliary display state.

[0078] This implementation allows users to review familiar words and expand their vocabulary by adding new words while maintaining a stable understanding of the text.

[0079] Example 2: The natural expansion of the substitution rhythm after the addition of familiar words

[0080] During the prior learning process, users cumulatively identify multiple new words as familiar words, thus expanding the set of familiar words.

[0081] In the next round of learning, the system will still maintain a single-screen replacement capacity of 8, but due to the increase in the number of possible familiar word candidate positions, the number of familiar word replacement positions will increase from the original 5 to 6.

[0082] The remaining word injection slots are reduced from 3 to 2; or, under the condition that the user's reading status is good, the system will simultaneously increase the total replacement capacity from 8 to 9, so that the recurrence of familiar words increases while still retaining 3 new word injection slots.

[0083] Therefore, this invention can dynamically adjust the proportion of the target language and the learning progress speed based on the growth of the user's familiar vocabulary assets without compromising reading stability.

[0084] Example 3: Dynamically reduce the new word injection window based on reading burden

[0085] The system detected the following user behaviors across multiple consecutive pages: significantly decreased reading speed; increased frequency of clicking on unfamiliar word suggestions; and decreased page completion rate.

[0086] Based on this, the learning pace adjustment module judges that the current learning burden is too high, and adjusts the total replacement capacity in the next screen from 8 to 7. At the same time, it reduces the number of new word injection windows from 3 to 2 to reduce the pressure of new learning.

[0087] Once the user's subsequent reading completion rate recovers and the frequency of prompt clicks decreases, the system can gradually expand the replacement capacity or add new words to the injection window again.

[0088] Example 4: Replacement load control within the current visible area

[0089] When a user uses a mobile device to swipe through text, the system uses the currently visible area as the unit for replacing capacity allocation.

[0090] For example, the current visible area allows a maximum of 6 target language words to be displayed. The system prioritizes allocating replacement slots for familiar words within the current visible area and uses the remaining slots for new words. After the user swipes to the next screen, the system reallocates replacement capacity based on the text content in the new visible area, the available replacement candidate positions, and the user's familiarity with the words.

[0091] This mechanism avoids situations where the vocabulary density on a particular screen is too high or too low after replacing the entire long text, thereby improving the stability of mobile reading and the consistency of the learning pace.

[0092] Example 5: Releasing replacement capacity after familiar words stabilize

[0093] Assume the target language replacement capacity on the current screen is 8. The system detects that 4 of the replacement slots correspond to words that the user already knows, and 2 of these words have been quickly identified by the user multiple times without requiring any prompts, and have been determined by the system to be stable, familiar words.

[0094] In traditional allocation methods, the two stable familiar words still occupy two replacement slots, compressing the new word injection window. However, in this embodiment, the system sets the two stable familiar words to have low weight capacity occupancy or excludes them from the new word injection window.

[0095] Therefore, while ensuring that the stable familiar words continue to appear in the target language form, the system can use the released 1 to 2 replacement capacity for injecting new words, reproducing low-frequency familiar words, or leaving them blank to reduce the reading burden.

[0096] This implementation allows users to stop using vocabulary they have already mastered to hinder their learning progress, thereby freeing up new learning capacity from familiar vocabulary assets.

[0097] Example 6: Dynamically refreshing and re-selecting replacement bits within the currently visible area

[0098] When a user reads a screen of learning content on a mobile device, the system initially allocates 8 target language replacement slots within the currently visible area. During the user's reading process, the system detects that one of the unfamiliar words is double-clicked to confirm and meets the stability condition of familiar words in the history.

[0099] The system releases the capacity corresponding to the word and re-evaluates candidate replacement positions within the current visible area. If there are still suitable candidate positions for injecting new words within the current area, the system can re-select a new replacement position, provided that there are no more than 8 target language replacement positions. If the system detects that the user's dwell time is too long or the prompt click frequency is too high, the system may also choose not to add new words and instead maintain a low load.

[0100] When a user scrolls back to this screen, changes the font size, or re-enters the current page, the system can refresh the screen's replacement area again based on the latest set of familiar words, the release status of stable familiar words, and the layout of the visible area.

[0101] This embodiment ensures that the replacement result in the current visible area is not fixed at once, but can be re-selected in a controlled manner as the user's learning state and display state change.

[0102] Compared with the prior art, the present invention has at least the following beneficial effects:

[0103] (1) Transform familiar word assets into real-time replacement control variables

[0104] The vocabulary that users have already mastered is no longer just used for statistics or rating, but directly participates in the allocation of target language vocabulary in the current learning content.

[0105] (2) The synergistic mechanism between the recurrence of mature words and the introduction of new words

[0106] By prioritizing familiar words and injecting new words into the remaining space, both review and expansion can be achieved within the limited replacement capacity.

[0107] (3) Stabilize and control the vocabulary load in the learning content

[0108] By replacing capacity control, the density of target language vocabulary is avoided from being too high or too low.

[0109] (4) Achieve continuous rather than abrupt adjustment of learning rhythm

[0110] The system can fine-tune the replacement capacity and the new word injection window based on reading behavior and the growth status of familiar words, making the learning process smoother.

[0111] (5) Adaptable to native language-immersive, bilingual mixed-text, and progressive reading scenarios.

[0112] This invention can be directly applied to various language learning content presentation formats, and is especially suitable for target language gradual immersion learning systems.

[0113] (6) Enhance users' willingness to use the product in the long term

[0114] By maintaining a balance between comprehensible input and an appropriate amount of new knowledge input, frustration can be reduced and the probability of continued learning can be increased.

[0115] (7) Adapt to the control requirements of mobile terminals and visible areas

[0116] By configuring replacement capacity on a per-screen or per-view basis, the mobile reading experience and learning density stability can be improved.

[0117] (8) Release the learning capacity occupied by stable familiar words

[0118] By setting capacity release rules for stable, familiar words, the system can prevent highly mastered vocabulary from occupying the new word injection window for a long time, thus directly converting the growth of familiar words into usable learning space.

[0119] (9) Supports local reallocation within the current visible area.

[0120] By dynamically refreshing and re-selecting replacement bits, the system can correct the distribution of target language words in real time on the current screen or in the current visible area, making the replacement load more in line with the user's real-time reading state.

[0121] This application also provides a method for vocabulary substitution load control and learning rhythm management based on the state of familiar words, which includes the following steps:

[0122] S1: Obtain the set of target language vocabulary that the user has mastered.

[0123] When a user enters the learning system, the system first establishes a vocabulary mastery status profile corresponding to the current user and obtains the set of target language vocabulary that the user has already mastered. This target language vocabulary set represents the range of target language vocabulary that the user currently possesses stable recognition or basic comprehension abilities for, and serves as an important basis for subsequent target language vocabulary replacement control.

[0124] In this embodiment, the target language vocabulary set can originate from multiple different data sources. Some vocabulary may come from words that the user has actively confirmed they have mastered; some may come from words that have been correctly identified multiple times in historical learning records; and some may come from words that can be understood without consulting definitions during reading. After the system uniformly summarizes the vocabulary from the above sources, it forms the target language vocabulary set corresponding to the current user.

[0125] Furthermore, to improve the accuracy of determining the status of familiar words, the system can also establish corresponding status record information for each word in the target language vocabulary set. This status record information may include cumulative occurrence count, cumulative correct recognition count, most recent occurrence time, number of prompt clicks, consecutive correct recognition period, and historical recurrence data. By recording this information, the system can not only determine whether a word is a familiar word, but also further assess the stability of word mastery.

[0126] In practical applications, a user's vocabulary familiarity level is not static. As the learning process continues, some newly added words may gradually become familiar, while some words that have not been encountered for a long time may experience a decline in mastery. Therefore, the system re-acquires the target language vocabulary set for the current user at the start of each learning task, ensuring that subsequent replacement control is always executed based on the latest learning status.

[0127] S2: Identify the locations of replaceable semantic units or replaceable words in the learning content to be output.

[0128] After obtaining the set of target language vocabulary already mastered by the user, the system performs content analysis on the learning content to be output in order to identify candidate positions suitable for performing target language replacement.

[0129] In practice, the system first performs text parsing on the learning content to be output, identifying lexical units, phrase structures, syntactic relationships, and semantic expressions within the text. For content fragments that correspond to the target language, the system marks them as candidate replacement objects.

[0130] In some implementations, the system can perform candidate position recognition based on a preset bilingual mapping dictionary. For example, when a word in the native language text has a clear correspondence with a word in the target language, the system automatically establishes a mapping relationship between the native language expression and the target language expression, and adds the corresponding position to the candidate replacement set. Fixed phrases, habitual expressions, or content corresponding to preset learning objectives can also be used as candidate replacement objects in subsequent processing.

[0131] To prevent replacement results from affecting the overall reading flow, the system can also filter candidate replacement positions based on readability. For example, for titles, key logical connections, or positions containing multiple complex expressions consecutively, the system can lower their replacement priority or disqualify them from replacement altogether, thereby ensuring the overall comprehensibility of the learning content.

[0132] After the above processing, the system forms a set of replaceable semantic units and a set of replaceable word positions corresponding to the current learning content, and sends the set to the subsequent target word replacement capacity determination step.

[0133] S3: Determine the target vocabulary replacement capacity in the current learning content based on at least one of the following: user learning stage, preset replacement limit, current learning task, text length, terminal display area, current visible area size, or interaction state.

[0134] After completing the identification of replaceable semantic units, the system begins to determine the total number of target language vocabulary substitutions allowed for the current learning content. It should be noted that the target vocabulary substitution capacity in this application is not a fixed proportion of the target language, nor is it a pre-set constant number of substitutions, but rather a capacity control parameter dynamically generated based on the current learning state.

[0135] In this embodiment, the system first acquires the basic control information corresponding to the current learning scenario. This basic control information may include the user's learning stage, learning task type, preset replacement limit, learning target level, text length, and terminal display area parameters. For example, for users in the beginner stage, the system can configure a lower basic replacement capacity; for users who already possess a certain reading ability, the target language presentation ratio can be increased.

[0136] Unlike existing technologies that uniformly set the target language ratio for the entire article, this embodiment preferably uses the currently visible area as the unit of capacity control. The system obtains the actual text range displayed on the screen in real time and establishes a reading load model corresponding to the current area based on the number of characters, lines, paragraphs, and candidate replacement positions in the current visible area.

[0137] Furthermore, this embodiment introduces a visual area load balancing replacement capacity control mechanism. The system does not directly determine the target word replacement capacity based on the number of candidate replacement positions, but first assesses the reading capacity corresponding to the current visual area. Specifically, the system obtains changes in the user's reading speed, page dwell time, prompt click frequency, and reading completion rate within the user's most recent preset time window, and generates a corresponding reading burden level based on the target language density in the current visual area.

[0138] When the system detects a continuous decrease in reading speed, a continuous increase in page dwell time, and a corresponding increase in prompt click frequency, it determines that the current reading burden is high. At this point, even if there are many replaceable positions on the current page, the system proactively reduces the target vocabulary replacement capacity to avoid excessive concentration of target language input, which could increase reading pressure. Conversely, when the user maintains a high reading completion rate and the reliance on prompts continues to decrease, the system appropriately increases the target vocabulary replacement capacity, allowing more target language vocabulary to be incorporated into the current learning content.

[0139] Furthermore, to avoid the concentration of target language vocabulary in localized areas, this embodiment also implements substitution position balancing constraint control on the current visible area. The system divides the current visible area into multiple continuous reading regions and limits the number of target language words allowed to appear in a single region. When the system detects that candidate substitution positions are too concentrated in a certain region, it prioritizes substitution positions with a more even distribution, making the distribution of target language vocabulary on the current screen smoother.

[0140] For example, when 8 target language substitutions are allowed, the traditional approach may concentrate the 8 substitutions in the first two paragraphs, while this embodiment prioritizes distributing the 8 substitutions to multiple reading areas in the current visible area, thereby reducing the sudden increase in local reading burden and improving the overall reading continuity and learning stability.

[0141] S4: Match the position of the replaceable semantic unit or replaceable word with the target language vocabulary set, and preferentially determine the replacement position of familiar words within the target vocabulary replacement capacity range.

[0142] After obtaining the target vocabulary replacement capacity, the system begins to perform a priority mapping process for familiar words. Unlike existing technologies that randomly replace words at a fixed ratio or directly replace words based on word frequency, this application first utilizes the user's existing familiar word assets to participate in the allocation of replacement positions, so that the limited replacement capacity prioritizes serving the target language vocabulary that the user already has a certain level of mastery over.

[0143] Specifically, the system performs item-by-item matching between the set of replaceable semantic units obtained in step S2 and the set of target language vocabulary obtained in step S1. For candidate positions that have a target language correspondence and belong to the user's already mastered vocabulary set, the system marks them as familiar word candidate positions. For candidate positions that do not match the familiar word set but meet the learning objective requirements, they are temporarily retained as candidate positions for subsequent new words.

[0144] In some implementations, the system not only determines whether a word is a familiar word, but also further analyzes the recurrence value of familiar words. For example, familiar words that have not appeared for a long time but are still within the current learning objective range usually have a higher recurrence value than familiar words that have appeared frequently recently. Therefore, the system can combine information such as the recent occurrence interval of familiar words, historical recurrence frequency, word frequency level, relevance to learning objectives, and user's historical usage status to prioritize the candidate positions of familiar words.

[0145] When the number of candidate positions for familiar words is less than the target word replacement capacity, the system directly determines all candidate positions for familiar words as replacement positions. When the number of candidate positions for familiar words exceeds the target word replacement capacity, the system filters according to the priority evaluation results and retains the corresponding replacement positions in descending order of priority until the target word replacement capacity is reached.

[0146] Furthermore, this embodiment preferably introduces a familiar word recurrence balancing control mechanism. When selecting familiar word replacement positions, the system considers not only the priority of individual words but also the coverage of the entire familiar word set. When the system detects that some familiar words have not had a chance to recur for a long time, even if their word frequency level is low, their priority can be appropriately increased to avoid the familiar word recurrence resources being concentrated on a small number of high-frequency words for a long time.

[0147] For example, if there are 12 candidate positions for replacement in the current learning content, and the system determines a target vocabulary replacement capacity of 8, with 7 of these candidate positions corresponding to the user's familiar vocabulary set, the system will prioritize retaining these 7 familiar vocabulary candidate positions as replacement positions, reserving only 1 replacement capacity for subsequent new word injection. If there are 10 familiar vocabulary candidate positions, the system will further select 8 of them as replacement positions based on the priority ranking result, while the remaining positions will maintain their original display format.

[0148] Through the above processing, the system can ensure that the target vocabulary replacement capacity is prioritized for the reproduction of familiar words, so that the vocabulary assets that users have already formed can continue to participate in the reading process, thereby increasing the frequency of exposure to the target language while maintaining the stability of reading comprehension.

[0149] S5: After deducting the determined familiar word replacement positions from the target vocabulary replacement capacity, determine the new word injection window in the current learning content based on the remaining replacement positions, so that the new word injection window is jointly constrained by the target vocabulary replacement capacity and the occupancy of the familiar word replacement positions.

[0150] After allocating replacement slots for familiar words, the system calculates the currently occupied replacement capacity and the number of remaining available replacement slots. These remaining available replacement slots are used to construct the new word injection window corresponding to the current learning content.

[0151] It should be noted that the new word injection window in this application is not a separate quota for new words set independently of the replacement capacity, but rather a remaining allocation space formed under the constraint of the target word replacement capacity. In other words, the introduction of new words does not occur preferentially, but is dynamically determined based on the remaining capacity after the allocation of familiar word replacement slots is completed.

[0152] After obtaining the remaining number of replacement words, the system first analyzes the current user's learning burden. This learning burden can be determined based on a combination of factors, including reading completion rate, page dwell time, changes in reading speed, frequency of clicks on prompts, and historical recognition accuracy. When the system determines that the user's current reading state is relatively stable, it can appropriately expand the new word injection window; when the system determines that the user is experiencing significant reading pressure, it will proactively shrink the new word injection window.

[0153] Unlike existing technologies that allocate learning content according to a fixed proportion of new words, this embodiment allows the new word injection window to change dynamically. For example, when there are 4 remaining replacement slots, the system does not necessarily use them all for new word injection. When a user's recent reading load is high, the system only uses 2 of the replacement slots as the new word injection window, and the remaining replacement capacity is temporarily reserved to avoid excessive introduction of new words that would degrade the reading experience.

[0154] Furthermore, this embodiment preferably introduces a stable familiar word capacity release mechanism. When the system detects that some familiar words have reached the preset stable familiar word conditions, the weight of such familiar words in the replacement load calculation can be reduced. The stable familiar word conditions may include multiple consecutive correct recognitions, no prompts or assistance required for multiple consecutive learning cycles, maintaining a high recognition accuracy rate for a long period of time, or no comprehension obstacles occurring during continuous reading.

[0155] For target language words that meet the criteria for stable familiar words, the system can include them in the target word replacement capacity with a lower weight than ordinary familiar words, or remove them from the new word injection window quota. The freed-up capacity can then be reallocated to the new word injection window.

[0156] For example, with a target vocabulary replacement capacity of 8, the system identifies 6 positions corresponding to familiar words, theoretically leaving only 2 positions for new word injection. However, when 2 of the 6 familiar words are determined to be stable familiar words, the system can reduce their capacity occupancy weight, increasing the actual capacity available for new word injection to 3 or 4. In this way, the vocabulary that the user has already mastered no longer occupies limited learning resources for a long time, but is gradually transformed into new learning space.

[0157] After the above processing, the system finally forms a new word injection window corresponding to the current learning content, and determines the number of new words allowed to be introduced, their distribution range, and their corresponding candidate positions, providing a basis for the generation of subsequent learning content.

[0158] S6: Output the learning content based on the familiar word replacement position and the newly added word injection window.

[0159] After the familiar word replacement positions and new word injection windows are determined, the system begins to generate the final output learning content.

[0160] In practice, the system first maps the target language vocabulary that the user has already mastered to the corresponding semantic positions in the learning content, based on the positions corresponding to familiar word substitutions. Since these words already have a certain degree of familiarity, the system prefers to use a weaker auxiliary form of presentation to increase the exposure frequency of the target language.

[0161] For target language words added to the new word injection window, the system uses an enhanced auxiliary approach for output. For example, it can display the target language word and its corresponding native language definition simultaneously, or it can display the target language word with a hint label, or it can present the target language word by wrapping it in the native language definition, thereby reducing the comprehension burden brought by the new words.

[0162] Furthermore, the system implements differentiated display control based on the different states of familiar words and newly added words. For stable familiar words, they can be displayed directly in the target language form; for ordinary familiar words, simplified prompts can be retained; and for newly added words, complete auxiliary information is retained. Through different levels of auxiliary strategies, the learning content forms a target language presentation structure that gradually transitions from familiar words to newly added words.

[0163] In some implementations, the system will also re-verify the distribution of target language vocabulary within the currently visible area. When multiple newly added words are detected to appear in adjacent areas, the system can readjust the positions of some replacement words to make the spatial distribution of target language vocabulary on the current page more balanced, so as to avoid a sudden increase in reading burden in local areas.

[0164] Finally, the system generates learning content that includes familiar word replacement positions and new word injection positions, and sends the learning content to the user terminal for display output, so that the user can simultaneously complete the reproduction of familiar words and the learning of new words during the reading process.

[0165] S7: Collect user reading behavior, interaction behavior, or vocabulary growth status of the learning content.

[0166] After the learning content is output, the system continuously monitors the user's behavioral feedback information during the reading process, and evaluates the degree of matching between the current learning content and the user's learning ability based on the feedback information.

[0167] In practice, the system can collect user reading behavior data within the current learning content. This reading behavior data includes, but is not limited to, page dwell time, reading completion rate, reading speed, page scrolling frequency, number of revisits, and reading interruptions. Reading speed can be represented by the number of characters, words, or pages read per unit of time; the reading completion rate reflects whether the user can successfully complete the current learning task.

[0168] Meanwhile, the system also records user interactions. These interactions can include the number of times vocabulary definitions are clicked, the number of times auxiliary prompts are invoked, the number of times target language vocabulary is long-pressed to view, the number of times playback is repeated, and the number of target language vocabulary confirmation actions. When users frequently invoke the prompt function, it usually means that the target language load in the current learning content has approached or exceeded the user's current cognitive capacity; while when users use auxiliary functions less and can complete reading quickly, it indicates that there is still room for improvement in the current learning pace.

[0169] In addition to reading and interaction behaviors, the system continuously tracks the growth status of familiar words. Specifically, the system records the appearance of new words in subsequent learning cycles and their corresponding recognition results, and analyzes the trends in user recognition accuracy, reliance on prompts, and consecutive correct recognition counts for new words. As the learning process progresses, some new words gradually become familiar words, and some common familiar words further transform into stable familiar words.

[0170] To improve the reliability of feedback data, this embodiment preferably uses a continuous observation window for status evaluation, rather than directly adjusting the learning pace based on a single behavior. For example, the system can generate a comprehensive evaluation result based on behavioral data from multiple recent learning pages, multiple learning tasks, or within a preset time period, thereby reducing the impact of random factors on system decision-making.

[0171] After obtaining the above behavioral data, the system constructs a set of learning state features corresponding to the current user and sends the set of learning state features to the subsequent learning rhythm adjustment step for processing.

[0172] S8: Based on the reading behavior, interaction behavior, or familiar word growth status, dynamically adjust at least one of the following in the subsequent learning content: replacement capacity, familiar word recurrence rate, new word injection rate, native language assistance ratio, or target language presentation density.

[0173] After obtaining the user's learning status feature set, the system begins to dynamically adjust the learning pace. Unlike existing technologies that advance learning content according to a fixed course schedule, the learning pace in this application is not preset, but is continuously and dynamically adjusted based on the user's actual learning status.

[0174] In practice, the system first analyzes the user's current reading burden. When the system detects a continuous decrease in reading speed, a continuous increase in page dwell time, a decrease in reading completion rate, and an increase in the frequency of prompts, it determines that the current learning burden is rising. At this point, the system automatically reduces the amount of target vocabulary replacements in subsequent learning content and simultaneously reduces the amount of new words injected to avoid the continuous accumulation of learning pressure.

[0175] For example, in the previous learning cycle, the system allows configuration of 8 target language substitution slots, including 5 familiar word substitution slots and 3 new word injection slots. When the system continuously detects reading difficulties on multiple pages, the target vocabulary substitution capacity in the next learning cycle can be adjusted to 7 slots, and the number of new word injections can be reduced from 3 to 2, thereby reducing the user's immediate cognitive burden.

[0176] Conversely, when the system detects that the user maintains a consistently high reading completion rate, a low frequency of prompt clicks, and a relatively fast reading speed, it determines that the current learning pace is relatively conservative. At this point, the system can appropriately increase the target vocabulary substitution capacity and the target language presentation density, giving the user more opportunities to input the target language.

[0177] Furthermore, this embodiment does not simply increase or decrease the number of target languages, but prioritizes adjusting the pace based on the growth status of familiar words. The system continuously tracks the process of new words transforming into familiar words and uses the growth of familiar word assets as an important basis for adjusting the learning pace. When new words continue to transform into familiar words, it indicates that the user has the ability to handle a higher density of target languages, so the system gradually increases the proportion of target languages.

[0178] To achieve a smoother learning process, this embodiment further introduces a capacity release mechanism driven by the growth of familiar words. Specifically, when a target language word meets the preset stable familiar word conditions, the system does not simply remove it from the learning content, but changes the way it occupies capacity in the replacement calculation.

[0179] For example, common words are counted as a complete substitution position when calculating replacement capacity, while stable words are counted with a lower capacity weight, or they no longer occupy new word injection window resources. As the number of stable words continues to increase, the system can gradually release more learning capacity to introduce new target language vocabulary.

[0180] Unlike traditional learning systems that continuously increase the total amount of learning tasks, this embodiment expands the learning space by releasing learning resources occupied by stable, familiar words. In other words, the increased learning capacity comes from the growth of the user's existing vocabulary assets, rather than simply increasing the intensity of learning. Therefore, the learning process can maintain a relatively stable level of cognitive burden.

[0181] Furthermore, in some implementations, the system can also synchronously adjust the proportion of native language assistance. When the system determines that the user has developed a high level of understanding of the current target language content, it gradually reduces the frequency of native language explanations and increases the proportion of direct target language display; when the system determines that the user has significant difficulty in understanding, it increases the proportion of auxiliary information again to ensure that the learning content remains comprehensible input.

[0182] Furthermore, this embodiment also allows for local dynamic adjustments within the current visible area. When the status of familiar words changes, stable familiar words form, or the display area changes during the user's reading process, the system can reassess the distribution of replacement capacity in the current visible area and reallocate some replacement positions. This reallocation may include operations such as retaining replacement positions, canceling replacement positions, adding replacement positions, or re-extracting replacement positions.

[0183] For example, if a user confirms during reading that they have mastered a new word and that the word meets the criteria for a stable, familiar word, the system can release the learning capacity occupied by that word and re-evaluate candidate replacement positions in the currently visible area. If there are still candidate positions for new words that meet the criteria in the current area, the released capacity is used to introduce new target language vocabulary; if the system detects that the user's current reading burden is too high, it chooses to retain the capacity without further increasing the learning load.

[0184] Through the above methods, this application establishes a closed-loop control mechanism encompassing reading behavior collection, learning status assessment, familiar word growth tracking, capacity release, and learning pace adjustment. As the learning process progresses, the system can continuously adjust the target language input intensity based on the user's actual learning status, ensuring a dynamic balance between familiar word repetition, new word expansion, and reading comprehension, thereby achieving a gradual, continuous, and individualized target language learning process.

[0185] It should be noted that this invention does not focus on "overall text difficulty assessment" or "text simplification after a high proportion of unfamiliar words". Instead, it focuses on the dynamic allocation of target language vocabulary substitution positions. Through prioritizing familiar words, injecting new words under the constraint of remaining capacity, and subsequent rhythm feedback, it establishes a substitution load control mechanism for progressive language learning.

[0186] Furthermore, the stable capacity release of familiar words in this invention is not a simple deletion of the display of familiar words, but rather a change in the occupancy relationship of stable familiar words on the limited learning load at the learning control level. Stable familiar words can still appear as part of the target language reading environment, but they do not necessarily occupy the same amount of learning capacity as newly added words or familiar words to be consolidated.

[0187] Furthermore, the dynamic refresh or re-scanning of the current visible area in this invention is not an arbitrary random refresh, but a local redistribution of replacement bits under the joint constraints of replacement capacity, stable state of familiar words, user burden state, and display area boundary.

[0188] Those skilled in the art should understand that, without departing from the spirit and scope of this invention, various substitutions or modifications can be made to the module composition, the method for determining the status of familiar words, the method for calculating replacement capacity, the rules for allocating new word injection windows, the parameters for adjusting learning rhythm, the output format of learning content, and the method for controlling the visible area, and all such substitutions or modifications should fall within the scope of protection of this invention.

[0189] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A target language vocabulary substitution load control and learning rhythm management system based on the state of familiar words, characterized in that, include: The familiarity status acquisition module is used to obtain the set of target language vocabulary that the user has mastered; The learning content analysis module is used to identify the locations of replaceable semantic units or replaceable words in the learning content to be output; The replacement capacity determination module is used to determine the target vocabulary replacement capacity in the current learning content based on at least one of the following: user learning stage, preset replacement limit, current learning task, text length, terminal display area, current visible area size, or interaction state. The target vocabulary replacement capacity is used to limit the total number of replacement positions of target language vocabulary in the current learning content. The familiar word priority mapping module is used to match the position of the replaceable semantic unit or replaceable word with the target language vocabulary set, and to preferentially determine the familiar word replacement position within the target vocabulary replacement capacity range; The new word injection window allocation module is used to determine the new word injection window in the current learning content based on the remaining replacement positions after deducting the determined familiar word replacement positions from the target word replacement capacity, so that the new word injection window is jointly constrained by the target word replacement capacity and the occupancy of the familiar word replacement positions. The learning pace adjustment module is used to dynamically adjust at least one of the following in subsequent learning content based on the familiar word replacement load, new word injection window, user reading behavior, or familiar word growth status: replacement capacity, familiar word recurrence rate, new word injection rate, native language assistance ratio, or target language presentation density. The learning content output module is used to output learning content based on the familiar word replacement position and the newly added word injection window.

2. The system according to claim 1, characterized in that, The target vocabulary replacement capacity is used to limit the total number of target language vocabulary replacement positions that can be presented in the current learning content, current page, current segment, current visible area, or current learning round; wherein, when the target vocabulary replacement capacity is determined on a unit of the current visible area, the system re-executes the allocation of familiar word replacement positions and new word injection windows after the user enters a new visible area.

3. The system according to claim 1, characterized in that, When the number of replaceable candidate positions exceeds the target word replacement capacity, the familiar word priority mapping module prioritizes retaining replaceable candidate positions that match the user's familiar word set. When the number of candidate positions that match the user's familiar word set exceeds the target word replacement capacity, the system determines the retained familiar word replacement positions based on at least one of the following: familiar word recurrence priority, recent occurrence interval, word frequency level, learning target, or user's historical usage status.

4. The system according to claim 1, characterized in that, The new word injection window is used to limit the number, proportion, or distribution range of new target language vocabulary that can be introduced into the current learning content; and when the number of remaining replacement positions is greater than zero, the new word injection window allocation module selects to use all, partially, or temporarily not use the remaining replacement positions based on the user's learning burden status, reading behavior feedback, or preset learning rhythm parameters.

5. The system according to claim 1, characterized in that, When the learning pace adjustment module detects a decrease in user reading speed, an increase in dwell time, an increase in prompt click frequency, a decrease in reading completion rate, or a decrease in recognition accuracy, it reduces the replacement capacity in subsequent learning content or shrinks the new word injection window; conversely, when it detects a high user reading completion rate, a decrease in prompt click frequency, stable confirmation of familiar words, or an improvement in recognition accuracy, it increases the replacement capacity in subsequent learning content or expands the new word injection window.

6. The system according to claim 1, characterized in that, The learning content output module adopts at least one of the following output methods: inserting target language words into the corresponding semantic positions of the native language text, displaying target language words in a native language wrapping manner, displaying target language words with native language prompts, using differentiated auxiliary display for familiar and unfamiliar words, or controlling the distribution density of target language words within the current visible area.

7. The system according to claim 1, characterized in that, The system also includes a status feedback update module, which updates the user's familiarity with words based on the user's interaction with the output learning content, and uses the updated user familiarity with words for subsequent vocabulary replacement control.

8. The system according to claim 1, characterized in that, The system also includes a stable capacity release module for familiar words, which is used to adjust the way the target language vocabulary occupies the new word injection window or the target word replacement capacity after the target language vocabulary meets the preset stable familiar word conditions; wherein, the adjustment includes removing the target language vocabulary from the new word injection window, reducing its replacement load weight, so that it no longer occupies the new word quota, or allocating its corresponding released capacity to at least one of new words, low-frequency familiar words, specified learning targets, or reading stability control.

9. The system according to claim 1, characterized in that, The system includes a dynamic refresh and re-sampling module for the visible area, which is used to perform dynamic refresh or re-sampling of target language word substitution positions within the current visible area.

10. A method for target language vocabulary substitution load control and learning rhythm management based on the state of familiar words, characterized in that, include: Obtain the set of vocabulary in the target language that the user already knows; Identify the locations of replaceable semantic units or replaceable words in the learning content to be output; The target vocabulary replacement capacity in the current learning content is determined based on at least one of the following: user learning stage, preset replacement limit, current learning task, text length, terminal display area, current visible area size, or interaction state. The replaceable semantic unit or replaceable word position is matched with the target language vocabulary set, and familiar word replacement positions are preferentially determined within the target vocabulary replacement capacity range; After deducting the determined familiar word replacement positions from the target vocabulary replacement capacity, a new word injection window in the current learning content is determined based on the remaining replacement positions, so that the new word injection window is jointly constrained by the target vocabulary replacement capacity and the occupancy of the familiar word replacement positions; The learning content is output through the window based on the familiar word replacement positions and newly added word injections. Collect user reading behavior, interaction behavior, or vocabulary learning status of the learning content; Based on the reading behavior, interaction behavior, or the growth status of familiar words, dynamically adjust at least one of the following in subsequent learning content: replacement capacity, familiar word recurrence rate, new word injection rate, native language assistance ratio, or target language presentation density.

11. The method according to claim 10, characterized in that, When the number of remaining replacement positions is greater than zero, the remaining replacement positions are selected to be used in full, partially used, or temporarily not used, based on the user's learning burden status, reading behavior feedback, or preset learning rhythm parameters, in order to determine the new word injection window.

12. The method according to claim 10, characterized in that, When a user's reading speed decreases, dwell time increases, prompt click frequency increases, reading completion rate decreases, or recognition accuracy decreases, reduce the replacement capacity in subsequent learning content or shrink the new word injection window; when a user's reading completion rate is high, prompt click frequency decreases, familiar word confirmation is stable, or recognition accuracy improves, increase the replacement capacity in subsequent learning content or expand the new word injection window.

13. The method according to claim 10, characterized in that, Within the currently visible area, the system dynamically refreshes or re-extracts target language vocabulary replacement positions based on at least one of the following: changes in the user's familiar word status, stable familiar word capacity release results, user dwell behavior, refresh operation, swipe operation, re-entering the page, font size change, display area change, or replacement load change. The dynamic refresh or re-extraction includes retaining, canceling, adding, replacing, or reordering the target language vocabulary replacement positions within the currently visible area, and ensuring that the refresh or re-extraction results are still constrained by the target vocabulary replacement capacity, familiar word priority rules, new word injection window, and reading load status.

Images